Merge branch 'for-linux-next-fixes' of https://gitlab.freedesktop.org/drm/misc/kernel.git
diff --git a/.clang-format b/.clang-format
index fe1aa1a..86c20ee 100644
--- a/.clang-format
+++ b/.clang-format
@@ -92,6 +92,7 @@
- '__rq_for_each_bio'
- '__shost_for_each_device'
- '__sym_for_each'
+ - '_for_each_counter'
- 'apei_estatus_for_each_section'
- 'ata_for_each_dev'
- 'ata_for_each_link'
@@ -141,11 +142,14 @@
- 'damon_for_each_target_safe'
- 'damos_for_each_filter'
- 'damos_for_each_filter_safe'
+ - 'damos_for_each_ops_filter'
+ - 'damos_for_each_ops_filter_safe'
- 'damos_for_each_quota_goal'
- 'damos_for_each_quota_goal_safe'
- 'data__for_each_file'
- 'data__for_each_file_new'
- 'data__for_each_file_start'
+ - 'def_for_each_cpu'
- 'device_for_each_child_node'
- 'device_for_each_child_node_scoped'
- 'dma_fence_array_for_each'
@@ -176,6 +180,7 @@
- 'drm_for_each_privobj'
- 'drm_gem_for_each_gpuvm_bo'
- 'drm_gem_for_each_gpuvm_bo_safe'
+ - 'drm_gpusvm_for_each_range'
- 'drm_gpuva_for_each_op'
- 'drm_gpuva_for_each_op_from_reverse'
- 'drm_gpuva_for_each_op_reverse'
@@ -216,8 +221,10 @@
- 'for_each_active_dev_scope'
- 'for_each_active_drhd_unit'
- 'for_each_active_iommu'
+ - 'for_each_active_irq'
- 'for_each_active_route'
- 'for_each_aggr_pgid'
+ - 'for_each_alloc_capable_rdt_resource'
- 'for_each_and_bit'
- 'for_each_andnot_bit'
- 'for_each_available_child_of_node'
@@ -228,6 +235,7 @@
- 'for_each_btf_ext_rec'
- 'for_each_btf_ext_sec'
- 'for_each_bvec'
+ - 'for_each_capable_rdt_resource'
- 'for_each_card_auxs'
- 'for_each_card_auxs_safe'
- 'for_each_card_components'
@@ -241,6 +249,7 @@
- 'for_each_cgroup_storage_type'
- 'for_each_child_of_node'
- 'for_each_child_of_node_scoped'
+ - 'for_each_child_of_node_with_prefix'
- 'for_each_clear_bit'
- 'for_each_clear_bit_from'
- 'for_each_clear_bitrange'
@@ -296,6 +305,7 @@
- 'for_each_group_member_head'
- 'for_each_hstate'
- 'for_each_hwgpio'
+ - 'for_each_hwgpio_in_range'
- 'for_each_if'
- 'for_each_inject_fn'
- 'for_each_insn'
@@ -304,6 +314,7 @@
- 'for_each_intid'
- 'for_each_iommu'
- 'for_each_ip_tunnel_rcu'
+ - 'for_each_irq_desc'
- 'for_each_irq_nr'
- 'for_each_lang'
- 'for_each_link_ch_maps'
@@ -324,6 +335,8 @@
- 'for_each_missing_reg'
- 'for_each_mle_subelement'
- 'for_each_mod_mem_type'
+ - 'for_each_mon_capable_rdt_resource'
+ - 'for_each_mp_bvec'
- 'for_each_net'
- 'for_each_net_continue_reverse'
- 'for_each_net_rcu'
@@ -351,6 +364,7 @@
- 'for_each_node_by_name'
- 'for_each_node_by_type'
- 'for_each_node_mask'
+ - 'for_each_node_numadist'
- 'for_each_node_state'
- 'for_each_node_with_cpus'
- 'for_each_node_with_property'
@@ -359,6 +373,8 @@
- 'for_each_of_allnodes'
- 'for_each_of_allnodes_from'
- 'for_each_of_cpu_node'
+ - 'for_each_of_graph_port'
+ - 'for_each_of_graph_port_endpoint'
- 'for_each_of_pci_range'
- 'for_each_old_connector_in_state'
- 'for_each_old_crtc_in_state'
@@ -372,9 +388,11 @@
- 'for_each_oldnew_plane_in_state_reverse'
- 'for_each_oldnew_private_obj_in_state'
- 'for_each_online_cpu'
+ - 'for_each_online_cpu_wrap'
- 'for_each_online_node'
- 'for_each_online_pgdat'
- 'for_each_or_bit'
+ - 'for_each_page_ext'
- 'for_each_path'
- 'for_each_pci_bridge'
- 'for_each_pci_dev'
@@ -382,8 +400,10 @@
- 'for_each_physmem_range'
- 'for_each_populated_zone'
- 'for_each_possible_cpu'
+ - 'for_each_possible_cpu_wrap'
- 'for_each_present_blessed_reg'
- 'for_each_present_cpu'
+ - 'for_each_present_section_nr'
- 'for_each_prime_number'
- 'for_each_prime_number_from'
- 'for_each_probe_cache_entry'
@@ -396,6 +416,7 @@
- 'for_each_prop_dlc_cpus'
- 'for_each_prop_dlc_platforms'
- 'for_each_property_of_node'
+ - 'for_each_rdt_resource'
- 'for_each_reg'
- 'for_each_reg_filtered'
- 'for_each_reloc'
@@ -434,10 +455,10 @@
- 'for_each_subelement_id'
- 'for_each_sublist'
- 'for_each_subsystem'
+ - 'for_each_suite'
- 'for_each_supported_activate_fn'
- 'for_each_supported_inject_fn'
- 'for_each_sym'
- - 'for_each_test'
- 'for_each_thread'
- 'for_each_token'
- 'for_each_unicast_dest_pgid'
@@ -499,8 +520,10 @@
- 'idr_for_each_entry_continue'
- 'idr_for_each_entry_continue_ul'
- 'idr_for_each_entry_ul'
+ - 'iio_for_each_active_channel'
- 'in_dev_for_each_ifa_rcu'
- 'in_dev_for_each_ifa_rtnl'
+ - 'in_dev_for_each_ifa_rtnl_net'
- 'inet_bind_bucket_for_each'
- 'interval_tree_for_each_span'
- 'intlist__for_each_entry'
@@ -542,7 +565,6 @@
- 'list_for_each_prev'
- 'list_for_each_prev_safe'
- 'list_for_each_rcu'
- - 'list_for_each_reverse'
- 'list_for_each_safe'
- 'llist_for_each'
- 'llist_for_each_entry'
@@ -552,6 +574,7 @@
- 'map__for_each_symbol'
- 'map__for_each_symbol_by_name'
- 'mas_for_each'
+ - 'mas_for_each_rev'
- 'mci_for_each_dimm'
- 'media_device_for_each_entity'
- 'media_device_for_each_intf'
@@ -561,10 +584,15 @@
- 'media_pipeline_for_each_entity'
- 'media_pipeline_for_each_pad'
- 'mlx5_lag_for_each_peer_mdev'
+ - 'mptcp_for_each_subflow'
- 'msi_domain_for_each_desc'
- 'msi_for_each_desc'
- 'mt_for_each'
+ - 'nanddev_io_for_each_block'
- 'nanddev_io_for_each_page'
+ - 'neigh_for_each_in_bucket'
+ - 'neigh_for_each_in_bucket_rcu'
+ - 'neigh_for_each_in_bucket_safe'
- 'netdev_for_each_lower_dev'
- 'netdev_for_each_lower_private'
- 'netdev_for_each_lower_private_rcu'
@@ -604,11 +632,11 @@
- 'perf_evlist__for_each_entry_safe'
- 'perf_evlist__for_each_evsel'
- 'perf_evlist__for_each_mmap'
+ - 'perf_evsel_for_each_per_thread_period_safe'
- 'perf_hpp_list__for_each_format'
- 'perf_hpp_list__for_each_format_safe'
- 'perf_hpp_list__for_each_sort_list'
- 'perf_hpp_list__for_each_sort_list_safe'
- - 'perf_tool_event__for_each_event'
- 'plist_for_each'
- 'plist_for_each_continue'
- 'plist_for_each_entry'
@@ -627,7 +655,6 @@
- 'rdma_for_each_block'
- 'rdma_for_each_port'
- 'rdma_umem_for_each_dma_block'
- - 'resort_rb__for_each_entry'
- 'resource_list_for_each_entry'
- 'resource_list_for_each_entry_safe'
- 'rhl_for_each_entry_rcu'
@@ -658,6 +685,7 @@
- 'shost_for_each_device'
- 'sk_for_each'
- 'sk_for_each_bound'
+ - 'sk_for_each_bound_safe'
- 'sk_for_each_entry_offset_rcu'
- 'sk_for_each_from'
- 'sk_for_each_rcu'
@@ -680,7 +708,11 @@
- 'tb_property_for_each'
- 'tcf_act_for_each_action'
- 'tcf_exts_for_each_action'
+ - 'test_suite__for_each_test_case'
+ - 'tool_pmu__for_each_event'
+ - 'ttm_bo_lru_for_each_reserved_guarded'
- 'ttm_resource_manager_for_each_res'
+ - 'udp_lrpa_for_each_entry_rcu'
- 'udp_portaddr_for_each_entry'
- 'udp_portaddr_for_each_entry_rcu'
- 'usb_hub_for_each_child'
@@ -691,6 +723,7 @@
- 'v4l2_m2m_for_each_src_buf_safe'
- 'virtio_device_for_each_vq'
- 'while_for_each_ftrace_op'
+ - 'workloads__for_each'
- 'xa_for_each'
- 'xa_for_each_marked'
- 'xa_for_each_range'
diff --git a/.mailmap b/.mailmap
index 4f7cd8e..1c70e51c 100644
--- a/.mailmap
+++ b/.mailmap
@@ -322,6 +322,7 @@
Jayachandran C <c.jayachandran@gmail.com> <jchandra@digeo.com>
Jayachandran C <c.jayachandran@gmail.com> <jnair@caviumnetworks.com>
<jean-philippe@linaro.org> <jean-philippe.brucker@arm.com>
+Jean-Michel Hautbois <jeanmichel.hautbois@yoseli.org> <jeanmichel.hautbois@ideasonboard.com>
Jean Tourrilhes <jt@hpl.hp.com>
Jeevan Shriram <quic_jshriram@quicinc.com> <jshriram@codeaurora.org>
Jeff Garzik <jgarzik@pretzel.yyz.us>
@@ -438,12 +439,16 @@
Li Yang <leoyang.li@nxp.com> <leoli@freescale.com>
Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org>
Lior David <quic_liord@quicinc.com> <liord@codeaurora.org>
+Loic Poulain <loic.poulain@oss.qualcomm.com> <loic.poulain@linaro.org>
+Loic Poulain <loic.poulain@oss.qualcomm.com> <loic.poulain@intel.com>
Lorenzo Pieralisi <lpieralisi@kernel.org> <lorenzo.pieralisi@arm.com>
Lorenzo Stoakes <lorenzo.stoakes@oracle.com> <lstoakes@gmail.com>
Luca Ceresoli <luca.ceresoli@bootlin.com> <luca@lucaceresoli.net>
Luca Weiss <luca@lucaweiss.eu> <luca@z3ntu.xyz>
Lukasz Luba <lukasz.luba@arm.com> <l.luba@partner.samsung.com>
Luo Jie <quic_luoj@quicinc.com> <luoj@codeaurora.org>
+Lance Yang <lance.yang@linux.dev> <ioworker0@gmail.com>
+Lance Yang <lance.yang@linux.dev> <mingzhe.yang@ly.com>
Maciej W. Rozycki <macro@mips.com> <macro@imgtec.com>
Maciej W. Rozycki <macro@orcam.me.uk> <macro@linux-mips.org>
Maharaja Kennadyrajan <quic_mkenna@quicinc.com> <mkenna@codeaurora.org>
@@ -480,6 +485,7 @@
Matthieu Baerts <matttbe@kernel.org> <matthieu.baerts@tessares.net>
Matthieu CASTET <castet.matthieu@free.fr>
Matti Vaittinen <mazziesaccount@gmail.com> <matti.vaittinen@fi.rohmeurope.com>
+Mattijs Korpershoek <mkorpershoek@kernel.org> <mkorpershoek@baylibre.com>
Matt Ranostay <matt@ranostay.sg> <matt.ranostay@konsulko.com>
Matt Ranostay <matt@ranostay.sg> <matt@ranostay.consulting>
Matt Ranostay <matt@ranostay.sg> Matthew Ranostay <mranostay@embeddedalley.com>
@@ -685,6 +691,8 @@
Simon Wunderlich <sw@simonwunderlich.de> <simon@open-mesh.com>
Simon Wunderlich <sw@simonwunderlich.de> <siwu@hrz.tu-chemnitz.de>
Sricharan Ramabadhran <quic_srichara@quicinc.com> <sricharan@codeaurora.org>
+Srinivas Kandagatla <srini@kernel.org> <srinivas.kandagatla@st.com>
+Srinivas Kandagatla <srini@kernel.org> <srinivas.kandagatla@linaro.org>
Srinivas Ramana <quic_sramana@quicinc.com> <sramana@codeaurora.org>
Sriram R <quic_srirrama@quicinc.com> <srirrama@codeaurora.org>
Sriram Yagnaraman <sriram.yagnaraman@ericsson.com> <sriram.yagnaraman@est.tech>
@@ -744,6 +752,7 @@
Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws>
Tzung-Bi Shih <tzungbi@kernel.org> <tzungbi@google.com>
Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
+Uwe Kleine-König <u.kleine-koenig@baylibre.com> <ukleinek@baylibre.com>
Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Uwe Kleine-König <ukleinek@strlen.de>
Uwe Kleine-König <ukl@pengutronix.de>
diff --git a/CREDITS b/CREDITS
index 1b77fba..f74d230 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2071,6 +2071,10 @@
S: Santa Clara, CA 95051
S: USA
+N: Joonsoo Kim
+E: iamjoonsoo.kim@lge.com
+D: Slab allocators
+
N: Kukjin Kim
E: kgene@kernel.org
D: Samsung S3C, S5P and Exynos ARM architectures
diff --git a/Documentation/ABI/stable/sysfs-block b/Documentation/ABI/stable/sysfs-block
index 3879963..11545c9 100644
--- a/Documentation/ABI/stable/sysfs-block
+++ b/Documentation/ABI/stable/sysfs-block
@@ -77,7 +77,7 @@
What: /sys/block/<disk>/diskseq
Date: February 2021
-Contact: Matteo Croce <mcroce@microsoft.com>
+Contact: Matteo Croce <teknoraver@meta.com>
Description:
The /sys/block/<disk>/diskseq files reports the disk
sequence number, which is a monotonically increasing
diff --git a/Documentation/ABI/testing/sysfs-driver-ufs b/Documentation/ABI/testing/sysfs-driver-ufs
index ae01912..e36d2de 100644
--- a/Documentation/ABI/testing/sysfs-driver-ufs
+++ b/Documentation/ABI/testing/sysfs-driver-ufs
@@ -1604,3 +1604,35 @@
prevent the UFS from frequently performing clock gating/ungating.
The attribute is read/write.
+
+What: /sys/bus/platform/drivers/ufshcd/*/device_lvl_exception_count
+What: /sys/bus/platform/devices/*.ufs/device_lvl_exception_count
+Date: March 2025
+Contact: Bao D. Nguyen <quic_nguyenb@quicinc.com>
+Description:
+ This attribute is applicable to ufs devices compliant to the
+ JEDEC specifications version 4.1 or later. The
+ device_lvl_exception_count is a counter indicating the number of
+ times the device level exceptions have occurred since the last
+ time this variable is reset. Writing a 0 value to this
+ attribute will reset the device_lvl_exception_count. If the
+ device_lvl_exception_count reads a positive value, the user
+ application should read the device_lvl_exception_id attribute to
+ know more information about the exception.
+
+ The attribute is read/write.
+
+What: /sys/bus/platform/drivers/ufshcd/*/device_lvl_exception_id
+What: /sys/bus/platform/devices/*.ufs/device_lvl_exception_id
+Date: March 2025
+Contact: Bao D. Nguyen <quic_nguyenb@quicinc.com>
+Description:
+ Reading the device_lvl_exception_id returns the
+ qDeviceLevelExceptionID attribute of the ufs device JEDEC
+ specification version 4.1. The definition of the
+ qDeviceLevelExceptionID is the ufs device vendor specific
+ implementation. Refer to the device manufacturer datasheet for
+ more information on the meaning of the qDeviceLevelExceptionID
+ attribute value.
+
+ The attribute is read only.
diff --git a/Documentation/ABI/testing/sysfs-kernel-reboot b/Documentation/ABI/testing/sysfs-kernel-reboot
index e117aba..52571fd 100644
--- a/Documentation/ABI/testing/sysfs-kernel-reboot
+++ b/Documentation/ABI/testing/sysfs-kernel-reboot
@@ -1,7 +1,7 @@
What: /sys/kernel/reboot
Date: November 2020
KernelVersion: 5.11
-Contact: Matteo Croce <mcroce@microsoft.com>
+Contact: Matteo Croce <teknoraver@meta.com>
Description: Interface to set the kernel reboot behavior, similarly to
what can be done via the reboot= cmdline option.
(see Documentation/admin-guide/kernel-parameters.txt)
@@ -9,25 +9,25 @@
What: /sys/kernel/reboot/mode
Date: November 2020
KernelVersion: 5.11
-Contact: Matteo Croce <mcroce@microsoft.com>
+Contact: Matteo Croce <teknoraver@meta.com>
Description: Reboot mode. Valid values are: cold warm hard soft gpio
What: /sys/kernel/reboot/type
Date: November 2020
KernelVersion: 5.11
-Contact: Matteo Croce <mcroce@microsoft.com>
+Contact: Matteo Croce <teknoraver@meta.com>
Description: Reboot type. Valid values are: bios acpi kbd triple efi pci
What: /sys/kernel/reboot/cpu
Date: November 2020
KernelVersion: 5.11
-Contact: Matteo Croce <mcroce@microsoft.com>
+Contact: Matteo Croce <teknoraver@meta.com>
Description: CPU number to use to reboot.
What: /sys/kernel/reboot/force
Date: November 2020
KernelVersion: 5.11
-Contact: Matteo Croce <mcroce@microsoft.com>
+Contact: Matteo Croce <teknoraver@meta.com>
Description: Don't wait for any other CPUs on reboot and
avoid anything that could hang.
diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst
index ff0b440..451874b 100644
--- a/Documentation/admin-guide/hw-vuln/index.rst
+++ b/Documentation/admin-guide/hw-vuln/index.rst
@@ -22,3 +22,4 @@
srso
gather_data_sampling
reg-file-data-sampling
+ rsb
diff --git a/Documentation/admin-guide/hw-vuln/rsb.rst b/Documentation/admin-guide/hw-vuln/rsb.rst
new file mode 100644
index 0000000..21dbf9c
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/rsb.rst
@@ -0,0 +1,268 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=======================
+RSB-related mitigations
+=======================
+
+.. warning::
+ Please keep this document up-to-date, otherwise you will be
+ volunteered to update it and convert it to a very long comment in
+ bugs.c!
+
+Since 2018 there have been many Spectre CVEs related to the Return Stack
+Buffer (RSB) (sometimes referred to as the Return Address Stack (RAS) or
+Return Address Predictor (RAP) on AMD).
+
+Information about these CVEs and how to mitigate them is scattered
+amongst a myriad of microarchitecture-specific documents.
+
+This document attempts to consolidate all the relevant information in
+once place and clarify the reasoning behind the current RSB-related
+mitigations. It's meant to be as concise as possible, focused only on
+the current kernel mitigations: what are the RSB-related attack vectors
+and how are they currently being mitigated?
+
+It's *not* meant to describe how the RSB mechanism operates or how the
+exploits work. More details about those can be found in the references
+below.
+
+Rather, this is basically a glorified comment, but too long to actually
+be one. So when the next CVE comes along, a kernel developer can
+quickly refer to this as a refresher to see what we're actually doing
+and why.
+
+At a high level, there are two classes of RSB attacks: RSB poisoning
+(Intel and AMD) and RSB underflow (Intel only). They must each be
+considered individually for each attack vector (and microarchitecture
+where applicable).
+
+----
+
+RSB poisoning (Intel and AMD)
+=============================
+
+SpectreRSB
+~~~~~~~~~~
+
+RSB poisoning is a technique used by SpectreRSB [#spectre-rsb]_ where
+an attacker poisons an RSB entry to cause a victim's return instruction
+to speculate to an attacker-controlled address. This can happen when
+there are unbalanced CALLs/RETs after a context switch or VMEXIT.
+
+* All attack vectors can potentially be mitigated by flushing out any
+ poisoned RSB entries using an RSB filling sequence
+ [#intel-rsb-filling]_ [#amd-rsb-filling]_ when transitioning between
+ untrusted and trusted domains. But this has a performance impact and
+ should be avoided whenever possible.
+
+ .. DANGER::
+ **FIXME**: Currently we're flushing 32 entries. However, some CPU
+ models have more than 32 entries. The loop count needs to be
+ increased for those. More detailed information is needed about RSB
+ sizes.
+
+* On context switch, the user->user mitigation requires ensuring the
+ RSB gets filled or cleared whenever IBPB gets written [#cond-ibpb]_
+ during a context switch:
+
+ * AMD:
+ On Zen 4+, IBPB (or SBPB [#amd-sbpb]_ if used) clears the RSB.
+ This is indicated by IBPB_RET in CPUID [#amd-ibpb-rsb]_.
+
+ On Zen < 4, the RSB filling sequence [#amd-rsb-filling]_ must be
+ always be done in addition to IBPB [#amd-ibpb-no-rsb]_. This is
+ indicated by X86_BUG_IBPB_NO_RET.
+
+ * Intel:
+ IBPB always clears the RSB:
+
+ "Software that executed before the IBPB command cannot control
+ the predicted targets of indirect branches executed after the
+ command on the same logical processor. The term indirect branch
+ in this context includes near return instructions, so these
+ predicted targets may come from the RSB." [#intel-ibpb-rsb]_
+
+* On context switch, user->kernel attacks are prevented by SMEP. User
+ space can only insert user space addresses into the RSB. Even
+ non-canonical addresses can't be inserted due to the page gap at the
+ end of the user canonical address space reserved by TASK_SIZE_MAX.
+ A SMEP #PF at instruction fetch prevents the kernel from speculatively
+ executing user space.
+
+ * AMD:
+ "Finally, branches that are predicted as 'ret' instructions get
+ their predicted targets from the Return Address Predictor (RAP).
+ AMD recommends software use a RAP stuffing sequence (mitigation
+ V2-3 in [2]) and/or Supervisor Mode Execution Protection (SMEP)
+ to ensure that the addresses in the RAP are safe for
+ speculation. Collectively, we refer to these mitigations as "RAP
+ Protection"." [#amd-smep-rsb]_
+
+ * Intel:
+ "On processors with enhanced IBRS, an RSB overwrite sequence may
+ not suffice to prevent the predicted target of a near return
+ from using an RSB entry created in a less privileged predictor
+ mode. Software can prevent this by enabling SMEP (for
+ transitions from user mode to supervisor mode) and by having
+ IA32_SPEC_CTRL.IBRS set during VM exits." [#intel-smep-rsb]_
+
+* On VMEXIT, guest->host attacks are mitigated by eIBRS (and PBRSB
+ mitigation if needed):
+
+ * AMD:
+ "When Automatic IBRS is enabled, the internal return address
+ stack used for return address predictions is cleared on VMEXIT."
+ [#amd-eibrs-vmexit]_
+
+ * Intel:
+ "On processors with enhanced IBRS, an RSB overwrite sequence may
+ not suffice to prevent the predicted target of a near return
+ from using an RSB entry created in a less privileged predictor
+ mode. Software can prevent this by enabling SMEP (for
+ transitions from user mode to supervisor mode) and by having
+ IA32_SPEC_CTRL.IBRS set during VM exits. Processors with
+ enhanced IBRS still support the usage model where IBRS is set
+ only in the OS/VMM for OSes that enable SMEP. To do this, such
+ processors will ensure that guest behavior cannot control the
+ RSB after a VM exit once IBRS is set, even if IBRS was not set
+ at the time of the VM exit." [#intel-eibrs-vmexit]_
+
+ Note that some Intel CPUs are susceptible to Post-barrier Return
+ Stack Buffer Predictions (PBRSB) [#intel-pbrsb]_, where the last
+ CALL from the guest can be used to predict the first unbalanced RET.
+ In this case the PBRSB mitigation is needed in addition to eIBRS.
+
+AMD RETBleed / SRSO / Branch Type Confusion
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+On AMD, poisoned RSB entries can also be created by the AMD RETBleed
+variant [#retbleed-paper]_ [#amd-btc]_ or by Speculative Return Stack
+Overflow [#amd-srso]_ (Inception [#inception-paper]_). The kernel
+protects itself by replacing every RET in the kernel with a branch to a
+single safe RET.
+
+----
+
+RSB underflow (Intel only)
+==========================
+
+RSB Alternate (RSBA) ("Intel Retbleed")
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Some Intel Skylake-generation CPUs are susceptible to the Intel variant
+of RETBleed [#retbleed-paper]_ (Return Stack Buffer Underflow
+[#intel-rsbu]_). If a RET is executed when the RSB buffer is empty due
+to mismatched CALLs/RETs or returning from a deep call stack, the branch
+predictor can fall back to using the Branch Target Buffer (BTB). If a
+user forces a BTB collision then the RET can speculatively branch to a
+user-controlled address.
+
+* Note that RSB filling doesn't fully mitigate this issue. If there
+ are enough unbalanced RETs, the RSB may still underflow and fall back
+ to using a poisoned BTB entry.
+
+* On context switch, user->user underflow attacks are mitigated by the
+ conditional IBPB [#cond-ibpb]_ on context switch which effectively
+ clears the BTB:
+
+ * "The indirect branch predictor barrier (IBPB) is an indirect branch
+ control mechanism that establishes a barrier, preventing software
+ that executed before the barrier from controlling the predicted
+ targets of indirect branches executed after the barrier on the same
+ logical processor." [#intel-ibpb-btb]_
+
+* On context switch and VMEXIT, user->kernel and guest->host RSB
+ underflows are mitigated by IBRS or eIBRS:
+
+ * "Enabling IBRS (including enhanced IBRS) will mitigate the "RSBU"
+ attack demonstrated by the researchers. As previously documented,
+ Intel recommends the use of enhanced IBRS, where supported. This
+ includes any processor that enumerates RRSBA but not RRSBA_DIS_S."
+ [#intel-rsbu]_
+
+ However, note that eIBRS and IBRS do not mitigate intra-mode attacks.
+ Like RRSBA below, this is mitigated by clearing the BHB on kernel
+ entry.
+
+ As an alternative to classic IBRS, call depth tracking (combined with
+ retpolines) can be used to track kernel returns and fill the RSB when
+ it gets close to being empty.
+
+Restricted RSB Alternate (RRSBA)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Some newer Intel CPUs have Restricted RSB Alternate (RRSBA) behavior,
+which, similar to RSBA described above, also falls back to using the BTB
+on RSB underflow. The only difference is that the predicted targets are
+restricted to the current domain when eIBRS is enabled:
+
+* "Restricted RSB Alternate (RRSBA) behavior allows alternate branch
+ predictors to be used by near RET instructions when the RSB is
+ empty. When eIBRS is enabled, the predicted targets of these
+ alternate predictors are restricted to those belonging to the
+ indirect branch predictor entries of the current prediction domain.
+ [#intel-eibrs-rrsba]_
+
+When a CPU with RRSBA is vulnerable to Branch History Injection
+[#bhi-paper]_ [#intel-bhi]_, an RSB underflow could be used for an
+intra-mode BTI attack. This is mitigated by clearing the BHB on
+kernel entry.
+
+However if the kernel uses retpolines instead of eIBRS, it needs to
+disable RRSBA:
+
+* "Where software is using retpoline as a mitigation for BHI or
+ intra-mode BTI, and the processor both enumerates RRSBA and
+ enumerates RRSBA_DIS controls, it should disable this behavior."
+ [#intel-retpoline-rrsba]_
+
+----
+
+References
+==========
+
+.. [#spectre-rsb] `Spectre Returns! Speculation Attacks using the Return Stack Buffer <https://arxiv.org/pdf/1807.07940.pdf>`_
+
+.. [#intel-rsb-filling] "Empty RSB Mitigation on Skylake-generation" in `Retpoline: A Branch Target Injection Mitigation <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/technical-documentation/retpoline-branch-target-injection-mitigation.html#inpage-nav-5-1>`_
+
+.. [#amd-rsb-filling] "Mitigation V2-3" in `Software Techniques for Managing Speculation <https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/programmer-references/software-techniques-for-managing-speculation.pdf>`_
+
+.. [#cond-ibpb] Whether IBPB is written depends on whether the prev and/or next task is protected from Spectre attacks. It typically requires opting in per task or system-wide. For more details see the documentation for the ``spectre_v2_user`` cmdline option in Documentation/admin-guide/kernel-parameters.txt.
+
+.. [#amd-sbpb] IBPB without flushing of branch type predictions. Only exists for AMD.
+
+.. [#amd-ibpb-rsb] "Function 8000_0008h -- Processor Capacity Parameters and Extended Feature Identification" in `AMD64 Architecture Programmer's Manual Volume 3: General-Purpose and System Instructions <https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/programmer-references/24594.pdf>`_. SBPB behaves the same way according to `this email <https://lore.kernel.org/5175b163a3736ca5fd01cedf406735636c99a>`_.
+
+.. [#amd-ibpb-no-rsb] `Spectre Attacks: Exploiting Speculative Execution <https://comsec.ethz.ch/wp-content/files/ibpb_sp25.pdf>`_
+
+.. [#intel-ibpb-rsb] "Introduction" in `Post-barrier Return Stack Buffer Predictions / CVE-2022-26373 / INTEL-SA-00706 <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/advisory-guidance/post-barrier-return-stack-buffer-predictions.html>`_
+
+.. [#amd-smep-rsb] "Existing Mitigations" in `Technical Guidance for Mitigating Branch Type Confusion <https://www.amd.com/content/dam/amd/en/documents/resources/technical-guidance-for-mitigating-branch-type-confusion.pdf>`_
+
+.. [#intel-smep-rsb] "Enhanced IBRS" in `Indirect Branch Restricted Speculation <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/technical-documentation/indirect-branch-restricted-speculation.html>`_
+
+.. [#amd-eibrs-vmexit] "Extended Feature Enable Register (EFER)" in `AMD64 Architecture Programmer's Manual Volume 2: System Programming <https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/programmer-references/24593.pdf>`_
+
+.. [#intel-eibrs-vmexit] "Enhanced IBRS" in `Indirect Branch Restricted Speculation <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/technical-documentation/indirect-branch-restricted-speculation.html>`_
+
+.. [#intel-pbrsb] `Post-barrier Return Stack Buffer Predictions / CVE-2022-26373 / INTEL-SA-00706 <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/advisory-guidance/post-barrier-return-stack-buffer-predictions.html>`_
+
+.. [#retbleed-paper] `RETBleed: Arbitrary Speculative Code Execution with Return Instruction <https://comsec.ethz.ch/wp-content/files/retbleed_sec22.pdf>`_
+
+.. [#amd-btc] `Technical Guidance for Mitigating Branch Type Confusion <https://www.amd.com/content/dam/amd/en/documents/resources/technical-guidance-for-mitigating-branch-type-confusion.pdf>`_
+
+.. [#amd-srso] `Technical Update Regarding Speculative Return Stack Overflow <https://www.amd.com/content/dam/amd/en/documents/corporate/cr/speculative-return-stack-overflow-whitepaper.pdf>`_
+
+.. [#inception-paper] `Inception: Exposing New Attack Surfaces with Training in Transient Execution <https://comsec.ethz.ch/wp-content/files/inception_sec23.pdf>`_
+
+.. [#intel-rsbu] `Return Stack Buffer Underflow / Return Stack Buffer Underflow / CVE-2022-29901, CVE-2022-28693 / INTEL-SA-00702 <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/advisory-guidance/return-stack-buffer-underflow.html>`_
+
+.. [#intel-ibpb-btb] `Indirect Branch Predictor Barrier' <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/technical-documentation/indirect-branch-predictor-barrier.html>`_
+
+.. [#intel-eibrs-rrsba] "Guidance for RSBU" in `Return Stack Buffer Underflow / Return Stack Buffer Underflow / CVE-2022-29901, CVE-2022-28693 / INTEL-SA-00702 <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/advisory-guidance/return-stack-buffer-underflow.html>`_
+
+.. [#bhi-paper] `Branch History Injection: On the Effectiveness of Hardware Mitigations Against Cross-Privilege Spectre-v2 Attacks <http://download.vusec.net/papers/bhi-spectre-bhb_sec22.pdf>`_
+
+.. [#intel-bhi] `Branch History Injection and Intra-mode Branch Target Injection / CVE-2022-0001, CVE-2022-0002 / INTEL-SA-00598 <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/technical-documentation/branch-history-injection.html>`_
+
+.. [#intel-retpoline-rrsba] "Retpoline" in `Branch History Injection and Intra-mode Branch Target Injection / CVE-2022-0001, CVE-2022-0002 / INTEL-SA-00598 <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/technical-documentation/branch-history-injection.html>`_
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 76e538c..eeba55d 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1407,18 +1407,15 @@
earlyprintk=serial[,0x...[,baudrate]]
earlyprintk=ttySn[,baudrate]
earlyprintk=dbgp[debugController#]
+ earlyprintk=mmio32,membase[,{nocfg|baudrate}]
earlyprintk=pciserial[,force],bus:device.function[,{nocfg|baudrate}]
earlyprintk=xdbc[xhciController#]
earlyprintk=bios
- earlyprintk=mmio,membase[,{nocfg|baudrate}]
earlyprintk is useful when the kernel crashes before
the normal console is initialized. It is not enabled by
default because it has some cosmetic problems.
- Only 32-bit memory addresses are supported for "mmio"
- and "pciserial" devices.
-
Use "nocfg" to skip UART configuration, assume
BIOS/firmware has configured UART correctly.
@@ -3623,7 +3620,7 @@
Note that even when enabled, there are a few cases where
the feature is not effective.
- memtest= [KNL,X86,ARM,M68K,PPC,RISCV,EARLY] Enable memtest
+ memtest= [KNL,X86,ARM,LOONGARCH,MIPS,M68K,PPC,RISCV,XTENSA,EARLY] Enable memtest
Format: <integer>
default : 0 <disable>
Specifies the number of memtest passes to be
diff --git a/Documentation/admin-guide/xfs.rst b/Documentation/admin-guide/xfs.rst
index b67772c..5becb44 100644
--- a/Documentation/admin-guide/xfs.rst
+++ b/Documentation/admin-guide/xfs.rst
@@ -124,6 +124,14 @@
controls the size of each buffer and so is also relevant to
this case.
+ lifetime (default) or nolifetime
+ Enable data placement based on write life time hints provided
+ by the user. This turns on co-allocation of data of similar
+ life times when statistically favorable to reduce garbage
+ collection cost.
+
+ These options are only available for zoned rt file systems.
+
logbsize=value
Set the size of each in-memory log buffer. The size may be
specified in bytes, or in kilobytes with a "k" suffix.
@@ -143,6 +151,14 @@
optional, and the log section can be separate from the data
section or contained within it.
+ max_open_zones=value
+ Specify the max number of zones to keep open for writing on a
+ zoned rt device. Many open zones aids file data separation
+ but may impact performance on HDDs.
+
+ If ``max_open_zones`` is not specified, the value is determined
+ by the capabilities and the size of the zoned rt device.
+
noalign
Data allocations will not be aligned at stripe unit
boundaries. This is only relevant to filesystems created
@@ -542,3 +558,24 @@
nice Relative priority of scheduling the threads. These are the
same nice levels that can be applied to userspace processes.
============ ===========
+
+Zoned Filesystems
+=================
+
+For zoned file systems, the following attributes are exposed in:
+
+ /sys/fs/xfs/<dev>/zoned/
+
+ max_open_zones (Min: 1 Default: Varies Max: UINTMAX)
+ This read-only attribute exposes the maximum number of open zones
+ available for data placement. The value is determined at mount time and
+ is limited by the capabilities of the backing zoned device, file system
+ size and the max_open_zones mount option.
+
+ zonegc_low_space (Min: 0 Default: 0 Max: 100)
+ Define a percentage for how much of the unused space that GC should keep
+ available for writing. A high value will reclaim more of the space
+ occupied by unused blocks, creating a larger buffer against write
+ bursts at the cost of increased write amplification. Regardless
+ of this value, garbage collection will always aim to free a minimum
+ amount of blocks to keep max_open_zones open for data placement purposes.
diff --git a/Documentation/arch/openrisc/openrisc_port.rst b/Documentation/arch/openrisc/openrisc_port.rst
index 1565b95..a8f307a 100644
--- a/Documentation/arch/openrisc/openrisc_port.rst
+++ b/Documentation/arch/openrisc/openrisc_port.rst
@@ -7,10 +7,10 @@
For information about OpenRISC processors and ongoing development:
- ======= =============================
+ ======= ==============================
website https://openrisc.io
- email openrisc@lists.librecores.org
- ======= =============================
+ email linux-openrisc@vger.kernel.org
+ ======= ==============================
---------------------------------------------------------------------
@@ -27,11 +27,11 @@
Instructions for building the different toolchains can be found on openrisc.io
or Stafford's toolchain build and release scripts.
- ========== =================================================
- binaries https://github.com/openrisc/or1k-gcc/releases
+ ========== ==========================================================
+ binaries https://github.com/stffrdhrn/or1k-toolchain-build/releases
toolchains https://openrisc.io/software
building https://github.com/stffrdhrn/or1k-toolchain-build
- ========== =================================================
+ ========== ==========================================================
2) Building
diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index 53607d9..f60bf599 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -51,7 +51,7 @@
* :c:macro:`RISCV_HWPROBE_KEY_MARCHID`: Contains the value of ``marchid``, as
defined by the RISC-V privileged architecture specification.
-* :c:macro:`RISCV_HWPROBE_KEY_MIMPLID`: Contains the value of ``mimplid``, as
+* :c:macro:`RISCV_HWPROBE_KEY_MIMPID`: Contains the value of ``mimpid``, as
defined by the RISC-V privileged architecture specification.
* :c:macro:`RISCV_HWPROBE_KEY_BASE_BEHAVIOR`: A bitmask containing the base
diff --git a/Documentation/arch/x86/cpuinfo.rst b/Documentation/arch/x86/cpuinfo.rst
index 6ef426a..f80e2a5 100644
--- a/Documentation/arch/x86/cpuinfo.rst
+++ b/Documentation/arch/x86/cpuinfo.rst
@@ -79,8 +79,9 @@
How are feature flags created?
==============================
-a: Feature flags can be derived from the contents of CPUID leaves.
-------------------------------------------------------------------
+Feature flags can be derived from the contents of CPUID leaves
+--------------------------------------------------------------
+
These feature definitions are organized mirroring the layout of CPUID
leaves and grouped in words with offsets as mapped in enum cpuid_leafs
in cpufeatures.h (see arch/x86/include/asm/cpufeatures.h for details).
@@ -89,8 +90,9 @@
displayed accordingly in /proc/cpuinfo. For example, the flag "avx2"
comes from X86_FEATURE_AVX2 in cpufeatures.h.
-b: Flags can be from scattered CPUID-based features.
-----------------------------------------------------
+Flags can be from scattered CPUID-based features
+------------------------------------------------
+
Hardware features enumerated in sparsely populated CPUID leaves get
software-defined values. Still, CPUID needs to be queried to determine
if a given feature is present. This is done in init_scattered_cpuid_features().
@@ -104,8 +106,9 @@
array. Since there is a struct cpuinfo_x86 for each possible CPU, the wasted
memory is not trivial.
-c: Flags can be created synthetically under certain conditions for hardware features.
--------------------------------------------------------------------------------------
+Flags can be created synthetically under certain conditions for hardware features
+---------------------------------------------------------------------------------
+
Examples of conditions include whether certain features are present in
MSR_IA32_CORE_CAPS or specific CPU models are identified. If the needed
conditions are met, the features are enabled by the set_cpu_cap or
@@ -114,8 +117,8 @@
"split_lock_detect" will be displayed. The flag "ring3mwait" will be
displayed only when running on INTEL_XEON_PHI_[KNL|KNM] processors.
-d: Flags can represent purely software features.
-------------------------------------------------
+Flags can represent purely software features
+--------------------------------------------
These flags do not represent hardware features. Instead, they represent a
software feature implemented in the kernel. For example, Kernel Page Table
Isolation is purely software feature and its feature flag X86_FEATURE_PTI is
@@ -130,14 +133,18 @@
resulting x86_cap/bug_flags[] are used to populate /proc/cpuinfo. The naming
of flags in the x86_cap/bug_flags[] are as follows:
-a: The name of the flag is from the string in X86_FEATURE_<name> by default.
-----------------------------------------------------------------------------
-By default, the flag <name> in /proc/cpuinfo is extracted from the respective
-X86_FEATURE_<name> in cpufeatures.h. For example, the flag "avx2" is from
-X86_FEATURE_AVX2.
+Flags do not appear by default in /proc/cpuinfo
+-----------------------------------------------
-b: The naming can be overridden.
---------------------------------
+Feature flags are omitted by default from /proc/cpuinfo as it does not make
+sense for the feature to be exposed to userspace in most cases. For example,
+X86_FEATURE_ALWAYS is defined in cpufeatures.h but that flag is an internal
+kernel feature used in the alternative runtime patching functionality. So the
+flag does not appear in /proc/cpuinfo.
+
+Specify a flag name if absolutely needed
+----------------------------------------
+
If the comment on the line for the #define X86_FEATURE_* starts with a
double-quote character (""), the string inside the double-quote characters
will be the name of the flags. For example, the flag "sse4_1" comes from
@@ -148,36 +155,31 @@
constant. If, for some reason, the naming of X86_FEATURE_<name> changes, one
shall override the new naming with the name already used in /proc/cpuinfo.
-c: The naming override can be "", which means it will not appear in /proc/cpuinfo.
-----------------------------------------------------------------------------------
-The feature shall be omitted from /proc/cpuinfo if it does not make sense for
-the feature to be exposed to userspace. For example, X86_FEATURE_ALWAYS is
-defined in cpufeatures.h but that flag is an internal kernel feature used
-in the alternative runtime patching functionality. So, its name is overridden
-with "". Its flag will not appear in /proc/cpuinfo.
-
Flags are missing when one or more of these happen
==================================================
-a: The hardware does not enumerate support for it.
---------------------------------------------------
+The hardware does not enumerate support for it
+----------------------------------------------
+
For example, when a new kernel is running on old hardware or the feature is
not enabled by boot firmware. Even if the hardware is new, there might be a
problem enabling the feature at run time, the flag will not be displayed.
-b: The kernel does not know about the flag.
--------------------------------------------
+The kernel does not know about the flag
+---------------------------------------
+
For example, when an old kernel is running on new hardware.
-c: The kernel disabled support for it at compile-time.
-------------------------------------------------------
+The kernel disabled support for it at compile-time
+--------------------------------------------------
+
For example, if 5-level-paging is not enabled when building (i.e.,
CONFIG_X86_5LEVEL is not selected) the flag "la57" will not show up [#f1]_.
Even though the feature will still be detected via CPUID, the kernel disables
it by clearing via setup_clear_cpu_cap(X86_FEATURE_LA57).
-d: The feature is disabled at boot-time.
-----------------------------------------
+The feature is disabled at boot-time
+------------------------------------
A feature can be disabled either using a command-line parameter or because
it failed to be enabled. The command-line parameter clearcpuid= can be used
to disable features using the feature number as defined in
@@ -190,8 +192,9 @@
to, nofsgsbase, nosgx, noxsave, etc. 5-level paging can also be disabled using
"no5lvl".
-e: The feature was known to be non-functional.
-----------------------------------------------
+The feature was known to be non-functional
+------------------------------------------
+
The feature was known to be non-functional because a dependency was
missing at runtime. For example, AVX flags will not show up if XSAVE feature
is disabled since they depend on XSAVE feature. Another example would be broken
diff --git a/Documentation/bpf/bpf_devel_QA.rst b/Documentation/bpf/bpf_devel_QA.rst
index de27e16..0acb4c9 100644
--- a/Documentation/bpf/bpf_devel_QA.rst
+++ b/Documentation/bpf/bpf_devel_QA.rst
@@ -382,6 +382,14 @@
into the Linux kernel, please implement support into LLVM's BPF back
end. See LLVM_ section below for further information.
+Q: What "BPF_INTERNAL" symbol namespace is for?
+-----------------------------------------------
+A: Symbols exported as BPF_INTERNAL can only be used by BPF infrastructure
+like preload kernel modules with light skeleton. Most symbols outside
+of BPF_INTERNAL are not expected to be used by code outside of BPF either.
+Symbols may lack the designation because they predate the namespaces,
+or due to an oversight.
+
Stable submission
=================
diff --git a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml
index 6ad7842..c923418 100644
--- a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml
+++ b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml
@@ -7,7 +7,6 @@
title: Ceva AHCI SATA Controller
maintainers:
- - Mubin Sayyed <mubin.sayyed@amd.com>
- Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
description: |
diff --git a/Documentation/devicetree/bindings/display/bridge/nwl-dsi.yaml b/Documentation/devicetree/bindings/display/bridge/nwl-dsi.yaml
index 350fb8f..5952e64 100644
--- a/Documentation/devicetree/bindings/display/bridge/nwl-dsi.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/nwl-dsi.yaml
@@ -111,11 +111,27 @@
unevaluatedProperties: false
port@1:
- $ref: /schemas/graph.yaml#/properties/port
+ $ref: /schemas/graph.yaml#/$defs/port-base
+ unevaluatedProperties: false
description:
DSI output port node to the panel or the next bridge
in the chain
+ properties:
+ endpoint:
+ $ref: /schemas/media/video-interfaces.yaml#
+ unevaluatedProperties: false
+
+ properties:
+ data-lanes:
+ description: array of physical DSI data lane indexes.
+ minItems: 1
+ items:
+ - const: 1
+ - const: 2
+ - const: 3
+ - const: 4
+
required:
- port@0
- port@1
diff --git a/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml b/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml
index bb93baa..e13e9d6d 100644
--- a/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml
+++ b/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml
@@ -12,7 +12,6 @@
PS_MODE). Every pin can be configured as input/output.
maintainers:
- - Mubin Sayyed <mubin.sayyed@amd.com>
- Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
properties:
diff --git a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml
index 517a4ac..e365413 100644
--- a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml
+++ b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml
@@ -7,7 +7,7 @@
title: Mediatek's Keypad Controller
maintainers:
- - Mattijs Korpershoek <mkorpershoek@baylibre.com>
+ - Mattijs Korpershoek <mkorpershoek@kernel.org>
allOf:
- $ref: /schemas/input/matrix-keymap.yaml#
diff --git a/Documentation/devicetree/bindings/interrupt-controller/fsl,irqsteer.yaml b/Documentation/devicetree/bindings/interrupt-controller/fsl,irqsteer.yaml
index 6076ddf..c49688b 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/fsl,irqsteer.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/fsl,irqsteer.yaml
@@ -19,6 +19,7 @@
- fsl,imx8mp-irqsteer
- fsl,imx8qm-irqsteer
- fsl,imx8qxp-irqsteer
+ - fsl,imx94-irqsteer
- const: fsl,imx-irqsteer
reg:
diff --git a/Documentation/devicetree/bindings/nvmem/layouts/fixed-cell.yaml b/Documentation/devicetree/bindings/nvmem/layouts/fixed-cell.yaml
index 8b382624..38e3ad5 100644
--- a/Documentation/devicetree/bindings/nvmem/layouts/fixed-cell.yaml
+++ b/Documentation/devicetree/bindings/nvmem/layouts/fixed-cell.yaml
@@ -27,7 +27,7 @@
$ref: /schemas/types.yaml#/definitions/uint32-array
items:
- minimum: 0
- maximum: 7
+ maximum: 31
description:
Offset in bit within the address range specified by reg.
- minimum: 1
diff --git a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml
index 39c2092..3f6dc6a 100644
--- a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml
+++ b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml
@@ -19,6 +19,7 @@
- enum:
- qcom,apq8064-qfprom
- qcom,apq8084-qfprom
+ - qcom,ipq5018-qfprom
- qcom,ipq5332-qfprom
- qcom,ipq5424-qfprom
- qcom,ipq6018-qfprom
@@ -28,6 +29,8 @@
- qcom,msm8226-qfprom
- qcom,msm8916-qfprom
- qcom,msm8917-qfprom
+ - qcom,msm8937-qfprom
+ - qcom,msm8960-qfprom
- qcom,msm8974-qfprom
- qcom,msm8976-qfprom
- qcom,msm8996-qfprom
@@ -51,6 +54,7 @@
- qcom,sm8450-qfprom
- qcom,sm8550-qfprom
- qcom,sm8650-qfprom
+ - qcom,x1e80100-qfprom
- const: qcom,qfprom
reg:
diff --git a/Documentation/devicetree/bindings/nvmem/rockchip,otp.yaml b/Documentation/devicetree/bindings/nvmem/rockchip,otp.yaml
index a44d44b..dc89020 100644
--- a/Documentation/devicetree/bindings/nvmem/rockchip,otp.yaml
+++ b/Documentation/devicetree/bindings/nvmem/rockchip,otp.yaml
@@ -14,6 +14,7 @@
enum:
- rockchip,px30-otp
- rockchip,rk3308-otp
+ - rockchip,rk3576-otp
- rockchip,rk3588-otp
reg:
@@ -62,6 +63,8 @@
properties:
clocks:
maxItems: 3
+ clock-names:
+ maxItems: 3
resets:
maxItems: 1
reset-names:
@@ -73,11 +76,33 @@
compatible:
contains:
enum:
+ - rockchip,rk3576-otp
+ then:
+ properties:
+ clocks:
+ maxItems: 3
+ clock-names:
+ maxItems: 3
+ resets:
+ minItems: 2
+ maxItems: 2
+ reset-names:
+ items:
+ - const: otp
+ - const: apb
+
+ - if:
+ properties:
+ compatible:
+ contains:
+ enum:
- rockchip,rk3588-otp
then:
properties:
clocks:
minItems: 4
+ clock-names:
+ minItems: 4
resets:
minItems: 3
reset-names:
diff --git a/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.yaml b/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.yaml
index a4dfa09..f85ee5d 100644
--- a/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.yaml
+++ b/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.yaml
@@ -9,15 +9,6 @@
maintainers:
- Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
-select:
- properties:
- compatible:
- contains:
- const: renesas,tpu
- required:
- - compatible
- - '#pwm-cells'
-
properties:
compatible:
items:
diff --git a/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml b/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml
index 1f1b42d..1db85fc 100644
--- a/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml
+++ b/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml
@@ -7,7 +7,6 @@
title: Zynq UltraScale+ MPSoC and Versal reset
maintainers:
- - Mubin Sayyed <mubin.sayyed@amd.com>
- Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
description: |
diff --git a/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml b/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml
index 31295be..234089b 100644
--- a/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml
+++ b/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml
@@ -7,7 +7,7 @@
title: Freescale Layerscape Reset Registers Module
maintainers:
- - Frank Li
+ - Frank Li <Frank.Li@nxp.com>
description:
Reset Module includes chip reset, service processor control and Reset Control
diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
index bccd00a..53d00ca 100644
--- a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
+++ b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
@@ -56,19 +56,18 @@
enum:
- snps,dw-apb-ssi
- snps,dwc-ssi-1.01a
- - description: Microsemi Ocelot/Jaguar2 SoC SPI Controller
- items:
- - enum:
- - mscc,ocelot-spi
- - mscc,jaguar2-spi
- - const: snps,dw-apb-ssi
- description: Microchip Sparx5 SoC SPI Controller
const: microchip,sparx5-spi
- description: Amazon Alpine SPI Controller
const: amazon,alpine-dw-apb-ssi
- - description: Renesas RZ/N1 SPI Controller
+ - description: Vendor controllers which use snps,dw-apb-ssi as fallback
items:
- - const: renesas,rzn1-spi
+ - enum:
+ - mscc,ocelot-spi
+ - mscc,jaguar2-spi
+ - renesas,rzn1-spi
+ - sophgo,sg2042-spi
+ - thead,th1520-spi
- const: snps,dw-apb-ssi
- description: Intel Keem Bay SPI Controller
const: intel,keembay-ssi
@@ -88,10 +87,6 @@
- renesas,r9a06g032-spi # RZ/N1D
- renesas,r9a06g033-spi # RZ/N1S
- const: renesas,rzn1-spi # RZ/N1
- - description: T-HEAD TH1520 SoC SPI Controller
- items:
- - const: thead,th1520-spi
- - const: snps,dw-apb-ssi
reg:
minItems: 1
diff --git a/Documentation/devicetree/bindings/timer/nxp,sysctr-timer.yaml b/Documentation/devicetree/bindings/timer/nxp,sysctr-timer.yaml
index 891cca0..6b80b06 100644
--- a/Documentation/devicetree/bindings/timer/nxp,sysctr-timer.yaml
+++ b/Documentation/devicetree/bindings/timer/nxp,sysctr-timer.yaml
@@ -18,9 +18,14 @@
properties:
compatible:
- enum:
- - nxp,imx95-sysctr-timer
- - nxp,sysctr-timer
+ oneOf:
+ - enum:
+ - nxp,imx95-sysctr-timer
+ - nxp,sysctr-timer
+ - items:
+ - enum:
+ - nxp,imx94-sysctr-timer
+ - const: nxp,imx95-sysctr-timer
reg:
maxItems: 1
diff --git a/Documentation/devicetree/bindings/timer/renesas,tpu.yaml b/Documentation/devicetree/bindings/timer/renesas,tpu.yaml
deleted file mode 100644
index 7a473b3..0000000
--- a/Documentation/devicetree/bindings/timer/renesas,tpu.yaml
+++ /dev/null
@@ -1,56 +0,0 @@
-# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
-%YAML 1.2
----
-$id: http://devicetree.org/schemas/timer/renesas,tpu.yaml#
-$schema: http://devicetree.org/meta-schemas/core.yaml#
-
-title: Renesas H8/300 Timer Pulse Unit
-
-maintainers:
- - Yoshinori Sato <ysato@users.sourceforge.jp>
-
-description:
- The TPU is a 16bit timer/counter with configurable clock inputs and
- programmable compare match.
- This implementation supports only cascade mode.
-
-select:
- properties:
- compatible:
- contains:
- const: renesas,tpu
- '#pwm-cells': false
- required:
- - compatible
-
-properties:
- compatible:
- const: renesas,tpu
-
- reg:
- items:
- - description: First channel
- - description: Second channel
-
- clocks:
- maxItems: 1
-
- clock-names:
- const: fck
-
-required:
- - compatible
- - reg
- - clocks
- - clock-names
-
-additionalProperties: false
-
-examples:
- - |
- tpu: tpu@ffffe0 {
- compatible = "renesas,tpu";
- reg = <0xffffe0 16>, <0xfffff0 12>;
- clocks = <&pclk>;
- clock-names = "fck";
- };
diff --git a/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml b/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml
index b5843f4..379daca 100644
--- a/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml
+++ b/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml
@@ -7,7 +7,6 @@
title: Xilinx SuperSpeed DWC3 USB SoC controller
maintainers:
- - Mubin Sayyed <mubin.sayyed@amd.com>
- Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
properties:
diff --git a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
index e2a72dea..c68c04d 100644
--- a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
+++ b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
@@ -17,7 +17,6 @@
maintainers:
- Michal Simek <michal.simek@amd.com>
- - Mubin Sayyed <mubin.sayyed@amd.com>
- Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
properties:
diff --git a/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml b/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml
index a7f75fe..f295aa9 100644
--- a/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml
+++ b/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml
@@ -7,7 +7,6 @@
title: Xilinx udc controller
maintainers:
- - Mubin Sayyed <mubin.sayyed@amd.com>
- Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
properties:
diff --git a/Documentation/filesystems/ext4/super.rst b/Documentation/filesystems/ext4/super.rst
index a1eb4a1..1b24066 100644
--- a/Documentation/filesystems/ext4/super.rst
+++ b/Documentation/filesystems/ext4/super.rst
@@ -328,9 +328,13 @@
- s_checksum_type
- Metadata checksum algorithm type. The only valid value is 1 (crc32c).
* - 0x176
- - __le16
- - s_reserved_pad
- -
+ - \_\_u8
+ - s\_encryption\_level
+ - Versioning level for encryption.
+ * - 0x177
+ - \_\_u8
+ - s\_reserved\_pad
+ - Padding to next 32bits.
* - 0x178
- __le64
- s_kbytes_written
@@ -466,9 +470,13 @@
- s_last_error_time_hi
- Upper 8 bits of the s_last_error_time field.
* - 0x27A
- - __u8
- - s_pad[2]
- - Zero padding.
+ - \_\_u8
+ - s\_first\_error\_errcode
+ -
+ * - 0x27B
+ - \_\_u8
+ - s\_last\_error\_errcode
+ -
* - 0x27C
- __le16
- s_encoding
diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 655d8d1..c650cd3 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -89,8 +89,10 @@
doc: Group of short_detected states
-
name: phy-upstream-type
- enum-name:
+ enum-name: phy-upstream
+ header: linux/ethtool.h
type: enum
+ name-prefix: phy-upstream
entries: [ mac, phy ]
-
name: tcp-data-split
diff --git a/Documentation/netlink/specs/ovs_vport.yaml b/Documentation/netlink/specs/ovs_vport.yaml
index 86ba9ac..b538bb9 100644
--- a/Documentation/netlink/specs/ovs_vport.yaml
+++ b/Documentation/netlink/specs/ovs_vport.yaml
@@ -123,12 +123,12 @@
operations:
name-prefix: ovs-vport-cmd-
+ fixed-header: ovs-header
list:
-
name: new
doc: Create a new OVS vport
attribute-set: vport
- fixed-header: ovs-header
do:
request:
attributes:
@@ -141,7 +141,6 @@
name: del
doc: Delete existing OVS vport from a data path
attribute-set: vport
- fixed-header: ovs-header
do:
request:
attributes:
@@ -152,7 +151,6 @@
name: get
doc: Get / dump OVS vport configuration and state
attribute-set: vport
- fixed-header: ovs-header
do: &vport-get-op
request:
attributes:
diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml
index 3123845..6b9d5ee 100644
--- a/Documentation/netlink/specs/rt_link.yaml
+++ b/Documentation/netlink/specs/rt_link.yaml
@@ -1113,11 +1113,10 @@
-
name: prop-list
type: nest
- nested-attributes: link-attrs
+ nested-attributes: prop-list-link-attrs
-
name: alt-ifname
type: string
- multi-attr: true
-
name: perm-address
type: binary
@@ -1164,6 +1163,13 @@
name: netns-immutable
type: u8
-
+ name: prop-list-link-attrs
+ subset-of: link-attrs
+ attributes:
+ -
+ name: alt-ifname
+ multi-attr: true
+ -
name: af-spec-attrs
attributes:
-
@@ -1585,7 +1591,7 @@
name: nf-call-iptables
type: u8
-
- name: nf-call-ip6-tables
+ name: nf-call-ip6tables
type: u8
-
name: nf-call-arptables
@@ -2077,7 +2083,7 @@
name: id
type: u16
-
- name: flag
+ name: flags
type: binary
struct: ifla-vlan-flags
-
@@ -2165,7 +2171,7 @@
type: binary
struct: ifla-cacheinfo
-
- name: icmp6-stats
+ name: icmp6stats
type: binary
struct: ifla-icmp6-stats
-
@@ -2179,9 +2185,10 @@
type: u32
-
name: mctp-attrs
+ name-prefix: ifla-mctp-
attributes:
-
- name: mctp-net
+ name: net
type: u32
-
name: phys-binding
@@ -2453,7 +2460,6 @@
- min-mtu
- max-mtu
- prop-list
- - alt-ifname
- perm-address
- proto-down-reason
- parent-dev-name
diff --git a/Documentation/netlink/specs/rt_neigh.yaml b/Documentation/netlink/specs/rt_neigh.yaml
index e670b6d..a843caa 100644
--- a/Documentation/netlink/specs/rt_neigh.yaml
+++ b/Documentation/netlink/specs/rt_neigh.yaml
@@ -13,25 +13,25 @@
type: struct
members:
-
- name: family
+ name: ndm-family
type: u8
-
- name: pad
+ name: ndm-pad
type: pad
len: 3
-
- name: ifindex
+ name: ndm-ifindex
type: s32
-
- name: state
+ name: ndm-state
type: u16
enum: nud-state
-
- name: flags
+ name: ndm-flags
type: u8
enum: ntf-flags
-
- name: type
+ name: ndm-type
type: u8
enum: rtm-type
-
@@ -189,7 +189,7 @@
type: binary
display-hint: ipv4
-
- name: lladr
+ name: lladdr
type: binary
display-hint: mac
-
diff --git a/Documentation/networking/netdevices.rst b/Documentation/networking/netdevices.rst
index 6c2d894..eab601a 100644
--- a/Documentation/networking/netdevices.rst
+++ b/Documentation/networking/netdevices.rst
@@ -338,10 +338,11 @@
Devices drivers are encouraged to rely on the instance lock where possible.
For the (mostly software) drivers that need to interact with the core stack,
-there are two sets of interfaces: ``dev_xxx`` and ``netif_xxx`` (e.g.,
-``dev_set_mtu`` and ``netif_set_mtu``). The ``dev_xxx`` functions handle
-acquiring the instance lock themselves, while the ``netif_xxx`` functions
-assume that the driver has already acquired the instance lock.
+there are two sets of interfaces: ``dev_xxx``/``netdev_xxx`` and ``netif_xxx``
+(e.g., ``dev_set_mtu`` and ``netif_set_mtu``). The ``dev_xxx``/``netdev_xxx``
+functions handle acquiring the instance lock themselves, while the
+``netif_xxx`` functions assume that the driver has already acquired
+the instance lock.
Notifiers and netdev instance lock
==================================
@@ -354,6 +355,7 @@
running under the lock:
* ``NETDEV_REGISTER``
* ``NETDEV_UP``
+* ``NETDEV_CHANGE``
The following notifiers are running without the lock:
* ``NETDEV_UNREGISTER``
diff --git a/Documentation/power/runtime_pm.rst b/Documentation/power/runtime_pm.rst
index 12f4293..63344be 100644
--- a/Documentation/power/runtime_pm.rst
+++ b/Documentation/power/runtime_pm.rst
@@ -154,7 +154,7 @@
device in that case. If there is no idle callback, or if the callback returns
0, then the PM core will attempt to carry out a runtime suspend of the device,
also respecting devices configured for autosuspend. In essence this means a
-call to __pm_runtime_autosuspend() (do note that drivers needs to update the
+call to pm_runtime_autosuspend() (do note that drivers needs to update the
device last busy mark, pm_runtime_mark_last_busy(), to control the delay under
this circumstance). To prevent this (for example, if the callback routine has
started a delayed suspend), the routine must return a non-zero value. Negative
diff --git a/Documentation/translations/zh_CN/arch/openrisc/openrisc_port.rst b/Documentation/translations/zh_CN/arch/openrisc/openrisc_port.rst
index cadc580..d728e4d 100644
--- a/Documentation/translations/zh_CN/arch/openrisc/openrisc_port.rst
+++ b/Documentation/translations/zh_CN/arch/openrisc/openrisc_port.rst
@@ -17,10 +17,10 @@
关于OpenRISC处理器和正在进行中的开发的信息:
- ======= =============================
+ ======= ==============================
网站 https://openrisc.io
- 邮箱 openrisc@lists.librecores.org
- ======= =============================
+ 邮箱 linux-openrisc@vger.kernel.org
+ ======= ==============================
---------------------------------------------------------------------
@@ -36,11 +36,11 @@
工具链的构建指南可以在openrisc.io或Stafford的工具链构建和发布脚本
中找到。
- ====== =================================================
- 二进制 https://github.com/openrisc/or1k-gcc/releases
+ ====== ==========================================================
+ 二进制 https://github.com/stffrdhrn/or1k-toolchain-build/releases
工具链 https://openrisc.io/software
构建 https://github.com/stffrdhrn/or1k-toolchain-build
- ====== =================================================
+ ====== ==========================================================
2) 构建
diff --git a/Documentation/translations/zh_TW/arch/openrisc/openrisc_port.rst b/Documentation/translations/zh_TW/arch/openrisc/openrisc_port.rst
index 422fe9f..a1e4517 100644
--- a/Documentation/translations/zh_TW/arch/openrisc/openrisc_port.rst
+++ b/Documentation/translations/zh_TW/arch/openrisc/openrisc_port.rst
@@ -17,10 +17,10 @@
關於OpenRISC處理器和正在進行中的開發的信息:
- ======= =============================
+ ======= ==============================
網站 https://openrisc.io
- 郵箱 openrisc@lists.librecores.org
- ======= =============================
+ 郵箱 linux-openrisc@vger.kernel.org
+ ======= ==============================
---------------------------------------------------------------------
@@ -36,11 +36,11 @@
工具鏈的構建指南可以在openrisc.io或Stafford的工具鏈構建和發佈腳本
中找到。
- ====== =================================================
- 二進制 https://github.com/openrisc/or1k-gcc/releases
+ ====== ==========================================================
+ 二進制 https://github.com/stffrdhrn/or1k-toolchain-build/releases
工具鏈 https://openrisc.io/software
構建 https://github.com/stffrdhrn/or1k-toolchain-build
- ====== =================================================
+ ====== ==========================================================
2) 構建
diff --git a/Documentation/userspace-api/mseal.rst b/Documentation/userspace-api/mseal.rst
index 1dabfc2..7195a7f 100644
--- a/Documentation/userspace-api/mseal.rst
+++ b/Documentation/userspace-api/mseal.rst
@@ -27,7 +27,7 @@
=======
mseal syscall signature
-----------------------
- ``int mseal(void \* addr, size_t len, unsigned long flags)``
+ ``int mseal(void *addr, size_t len, unsigned long flags)``
**addr**/**len**: virtual memory address range.
The address range set by **addr**/**len** must meet:
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 1f8625b..47c7c3f 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -7447,6 +7447,75 @@
This capability connects the vcpu to an in-kernel XIVE device.
+6.76 KVM_CAP_HYPERV_SYNIC
+-------------------------
+
+:Architectures: x86
+:Target: vcpu
+
+This capability, if KVM_CHECK_EXTENSION indicates that it is
+available, means that the kernel has an implementation of the
+Hyper-V Synthetic interrupt controller(SynIC). Hyper-V SynIC is
+used to support Windows Hyper-V based guest paravirt drivers(VMBus).
+
+In order to use SynIC, it has to be activated by setting this
+capability via KVM_ENABLE_CAP ioctl on the vcpu fd. Note that this
+will disable the use of APIC hardware virtualization even if supported
+by the CPU, as it's incompatible with SynIC auto-EOI behavior.
+
+6.77 KVM_CAP_HYPERV_SYNIC2
+--------------------------
+
+:Architectures: x86
+:Target: vcpu
+
+This capability enables a newer version of Hyper-V Synthetic interrupt
+controller (SynIC). The only difference with KVM_CAP_HYPERV_SYNIC is that KVM
+doesn't clear SynIC message and event flags pages when they are enabled by
+writing to the respective MSRs.
+
+6.78 KVM_CAP_HYPERV_DIRECT_TLBFLUSH
+-----------------------------------
+
+:Architectures: x86
+:Target: vcpu
+
+This capability indicates that KVM running on top of Hyper-V hypervisor
+enables Direct TLB flush for its guests meaning that TLB flush
+hypercalls are handled by Level 0 hypervisor (Hyper-V) bypassing KVM.
+Due to the different ABI for hypercall parameters between Hyper-V and
+KVM, enabling this capability effectively disables all hypercall
+handling by KVM (as some KVM hypercall may be mistakenly treated as TLB
+flush hypercalls by Hyper-V) so userspace should disable KVM identification
+in CPUID and only exposes Hyper-V identification. In this case, guest
+thinks it's running on Hyper-V and only use Hyper-V hypercalls.
+
+6.79 KVM_CAP_HYPERV_ENFORCE_CPUID
+---------------------------------
+
+:Architectures: x86
+:Target: vcpu
+
+When enabled, KVM will disable emulated Hyper-V features provided to the
+guest according to the bits Hyper-V CPUID feature leaves. Otherwise, all
+currently implemented Hyper-V features are provided unconditionally when
+Hyper-V identification is set in the HYPERV_CPUID_INTERFACE (0x40000001)
+leaf.
+
+6.80 KVM_CAP_ENFORCE_PV_FEATURE_CPUID
+-------------------------------------
+
+:Architectures: x86
+:Target: vcpu
+
+When enabled, KVM will disable paravirtual features provided to the
+guest according to the bits in the KVM_CPUID_FEATURES CPUID leaf
+(0x40000001). Otherwise, a guest may use the paravirtual features
+regardless of what has actually been exposed through the CPUID leaf.
+
+.. _KVM_CAP_DIRTY_LOG_RING:
+
+
.. _cap_enable_vm:
7. Capabilities that can be enabled on VMs
@@ -7927,10 +7996,10 @@
7.24 KVM_CAP_VM_COPY_ENC_CONTEXT_FROM
-------------------------------------
-Architectures: x86 SEV enabled
-Type: vm
-Parameters: args[0] is the fd of the source vm
-Returns: 0 on success; ENOTTY on error
+:Architectures: x86 SEV enabled
+:Type: vm
+:Parameters: args[0] is the fd of the source vm
+:Returns: 0 on success; ENOTTY on error
This capability enables userspace to copy encryption context from the vm
indicated by the fd to the vm this is called on.
@@ -7963,24 +8032,6 @@
See Documentation/arch/x86/sgx.rst for more details.
-7.26 KVM_CAP_PPC_RPT_INVALIDATE
--------------------------------
-
-:Capability: KVM_CAP_PPC_RPT_INVALIDATE
-:Architectures: ppc
-:Type: vm
-
-This capability indicates that the kernel is capable of handling
-H_RPT_INVALIDATE hcall.
-
-In order to enable the use of H_RPT_INVALIDATE in the guest,
-user space might have to advertise it for the guest. For example,
-IBM pSeries (sPAPR) guest starts using it if "hcall-rpt-invalidate" is
-present in the "ibm,hypertas-functions" device-tree property.
-
-This capability is enabled for hypervisors on platforms like POWER9
-that support radix MMU.
-
7.27 KVM_CAP_EXIT_ON_EMULATION_FAILURE
--------------------------------------
@@ -8038,24 +8089,9 @@
This is intended to support intra-host migration of VMs between userspace VMMs,
upgrading the VMM process without interrupting the guest.
-7.30 KVM_CAP_PPC_AIL_MODE_3
--------------------------------
-
-:Capability: KVM_CAP_PPC_AIL_MODE_3
-:Architectures: ppc
-:Type: vm
-
-This capability indicates that the kernel supports the mode 3 setting for the
-"Address Translation Mode on Interrupt" aka "Alternate Interrupt Location"
-resource that is controlled with the H_SET_MODE hypercall.
-
-This capability allows a guest kernel to use a better-performance mode for
-handling interrupts and system calls.
-
7.31 KVM_CAP_DISABLE_QUIRKS2
----------------------------
-:Capability: KVM_CAP_DISABLE_QUIRKS2
:Parameters: args[0] - set of KVM quirks to disable
:Architectures: x86
:Type: vm
@@ -8210,27 +8246,6 @@
cause CPU stuck (due to event windows don't open up) and make the CPU
unavailable to host or other VMs.
-7.34 KVM_CAP_MEMORY_FAULT_INFO
-------------------------------
-
-:Architectures: x86
-:Returns: Informational only, -EINVAL on direct KVM_ENABLE_CAP.
-
-The presence of this capability indicates that KVM_RUN will fill
-kvm_run.memory_fault if KVM cannot resolve a guest page fault VM-Exit, e.g. if
-there is a valid memslot but no backing VMA for the corresponding host virtual
-address.
-
-The information in kvm_run.memory_fault is valid if and only if KVM_RUN returns
-an error with errno=EFAULT or errno=EHWPOISON *and* kvm_run.exit_reason is set
-to KVM_EXIT_MEMORY_FAULT.
-
-Note: Userspaces which attempt to resolve memory faults so that they can retry
-KVM_RUN are encouraged to guard against repeatedly receiving the same
-error/annotated fault.
-
-See KVM_EXIT_MEMORY_FAULT for more information.
-
7.35 KVM_CAP_X86_APIC_BUS_CYCLES_NS
-----------------------------------
@@ -8248,421 +8263,11 @@
Note: Userspace is responsible for correctly configuring CPUID 0x15, a.k.a. the
core crystal clock frequency, if a non-zero CPUID 0x15 is exposed to the guest.
-7.36 KVM_CAP_X86_GUEST_MODE
-------------------------------
-
-:Architectures: x86
-:Returns: Informational only, -EINVAL on direct KVM_ENABLE_CAP.
-
-The presence of this capability indicates that KVM_RUN will update the
-KVM_RUN_X86_GUEST_MODE bit in kvm_run.flags to indicate whether the
-vCPU was executing nested guest code when it exited.
-
-KVM exits with the register state of either the L1 or L2 guest
-depending on which executed at the time of an exit. Userspace must
-take care to differentiate between these cases.
-
-7.37 KVM_CAP_ARM_WRITABLE_IMP_ID_REGS
--------------------------------------
-
-:Architectures: arm64
-:Target: VM
-:Parameters: None
-:Returns: 0 on success, -EINVAL if vCPUs have been created before enabling this
- capability.
-
-This capability changes the behavior of the registers that identify a PE
-implementation of the Arm architecture: MIDR_EL1, REVIDR_EL1, and AIDR_EL1.
-By default, these registers are visible to userspace but treated as invariant.
-
-When this capability is enabled, KVM allows userspace to change the
-aforementioned registers before the first KVM_RUN. These registers are VM
-scoped, meaning that the same set of values are presented on all vCPUs in a
-given VM.
-
-8. Other capabilities.
-======================
-
-This section lists capabilities that give information about other
-features of the KVM implementation.
-
-8.1 KVM_CAP_PPC_HWRNG
----------------------
-
-:Architectures: ppc
-
-This capability, if KVM_CHECK_EXTENSION indicates that it is
-available, means that the kernel has an implementation of the
-H_RANDOM hypercall backed by a hardware random-number generator.
-If present, the kernel H_RANDOM handler can be enabled for guest use
-with the KVM_CAP_PPC_ENABLE_HCALL capability.
-
-8.2 KVM_CAP_HYPERV_SYNIC
-------------------------
-
-:Architectures: x86
-
-This capability, if KVM_CHECK_EXTENSION indicates that it is
-available, means that the kernel has an implementation of the
-Hyper-V Synthetic interrupt controller(SynIC). Hyper-V SynIC is
-used to support Windows Hyper-V based guest paravirt drivers(VMBus).
-
-In order to use SynIC, it has to be activated by setting this
-capability via KVM_ENABLE_CAP ioctl on the vcpu fd. Note that this
-will disable the use of APIC hardware virtualization even if supported
-by the CPU, as it's incompatible with SynIC auto-EOI behavior.
-
-8.3 KVM_CAP_PPC_MMU_RADIX
--------------------------
-
-:Architectures: ppc
-
-This capability, if KVM_CHECK_EXTENSION indicates that it is
-available, means that the kernel can support guests using the
-radix MMU defined in Power ISA V3.00 (as implemented in the POWER9
-processor).
-
-8.4 KVM_CAP_PPC_MMU_HASH_V3
----------------------------
-
-:Architectures: ppc
-
-This capability, if KVM_CHECK_EXTENSION indicates that it is
-available, means that the kernel can support guests using the
-hashed page table MMU defined in Power ISA V3.00 (as implemented in
-the POWER9 processor), including in-memory segment tables.
-
-8.5 KVM_CAP_MIPS_VZ
--------------------
-
-:Architectures: mips
-
-This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that
-it is available, means that full hardware assisted virtualization capabilities
-of the hardware are available for use through KVM. An appropriate
-KVM_VM_MIPS_* type must be passed to KVM_CREATE_VM to create a VM which
-utilises it.
-
-If KVM_CHECK_EXTENSION on a kvm VM handle indicates that this capability is
-available, it means that the VM is using full hardware assisted virtualization
-capabilities of the hardware. This is useful to check after creating a VM with
-KVM_VM_MIPS_DEFAULT.
-
-The value returned by KVM_CHECK_EXTENSION should be compared against known
-values (see below). All other values are reserved. This is to allow for the
-possibility of other hardware assisted virtualization implementations which
-may be incompatible with the MIPS VZ ASE.
-
-== ==========================================================================
- 0 The trap & emulate implementation is in use to run guest code in user
- mode. Guest virtual memory segments are rearranged to fit the guest in the
- user mode address space.
-
- 1 The MIPS VZ ASE is in use, providing full hardware assisted
- virtualization, including standard guest virtual memory segments.
-== ==========================================================================
-
-8.6 KVM_CAP_MIPS_TE
--------------------
-
-:Architectures: mips
-
-This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that
-it is available, means that the trap & emulate implementation is available to
-run guest code in user mode, even if KVM_CAP_MIPS_VZ indicates that hardware
-assisted virtualisation is also available. KVM_VM_MIPS_TE (0) must be passed
-to KVM_CREATE_VM to create a VM which utilises it.
-
-If KVM_CHECK_EXTENSION on a kvm VM handle indicates that this capability is
-available, it means that the VM is using trap & emulate.
-
-8.7 KVM_CAP_MIPS_64BIT
-----------------------
-
-:Architectures: mips
-
-This capability indicates the supported architecture type of the guest, i.e. the
-supported register and address width.
-
-The values returned when this capability is checked by KVM_CHECK_EXTENSION on a
-kvm VM handle correspond roughly to the CP0_Config.AT register field, and should
-be checked specifically against known values (see below). All other values are
-reserved.
-
-== ========================================================================
- 0 MIPS32 or microMIPS32.
- Both registers and addresses are 32-bits wide.
- It will only be possible to run 32-bit guest code.
-
- 1 MIPS64 or microMIPS64 with access only to 32-bit compatibility segments.
- Registers are 64-bits wide, but addresses are 32-bits wide.
- 64-bit guest code may run but cannot access MIPS64 memory segments.
- It will also be possible to run 32-bit guest code.
-
- 2 MIPS64 or microMIPS64 with access to all address segments.
- Both registers and addresses are 64-bits wide.
- It will be possible to run 64-bit or 32-bit guest code.
-== ========================================================================
-
-8.9 KVM_CAP_ARM_USER_IRQ
-------------------------
-
-:Architectures: arm64
-
-This capability, if KVM_CHECK_EXTENSION indicates that it is available, means
-that if userspace creates a VM without an in-kernel interrupt controller, it
-will be notified of changes to the output level of in-kernel emulated devices,
-which can generate virtual interrupts, presented to the VM.
-For such VMs, on every return to userspace, the kernel
-updates the vcpu's run->s.regs.device_irq_level field to represent the actual
-output level of the device.
-
-Whenever kvm detects a change in the device output level, kvm guarantees at
-least one return to userspace before running the VM. This exit could either
-be a KVM_EXIT_INTR or any other exit event, like KVM_EXIT_MMIO. This way,
-userspace can always sample the device output level and re-compute the state of
-the userspace interrupt controller. Userspace should always check the state
-of run->s.regs.device_irq_level on every kvm exit.
-The value in run->s.regs.device_irq_level can represent both level and edge
-triggered interrupt signals, depending on the device. Edge triggered interrupt
-signals will exit to userspace with the bit in run->s.regs.device_irq_level
-set exactly once per edge signal.
-
-The field run->s.regs.device_irq_level is available independent of
-run->kvm_valid_regs or run->kvm_dirty_regs bits.
-
-If KVM_CAP_ARM_USER_IRQ is supported, the KVM_CHECK_EXTENSION ioctl returns a
-number larger than 0 indicating the version of this capability is implemented
-and thereby which bits in run->s.regs.device_irq_level can signal values.
-
-Currently the following bits are defined for the device_irq_level bitmap::
-
- KVM_CAP_ARM_USER_IRQ >= 1:
-
- KVM_ARM_DEV_EL1_VTIMER - EL1 virtual timer
- KVM_ARM_DEV_EL1_PTIMER - EL1 physical timer
- KVM_ARM_DEV_PMU - ARM PMU overflow interrupt signal
-
-Future versions of kvm may implement additional events. These will get
-indicated by returning a higher number from KVM_CHECK_EXTENSION and will be
-listed above.
-
-8.10 KVM_CAP_PPC_SMT_POSSIBLE
------------------------------
-
-:Architectures: ppc
-
-Querying this capability returns a bitmap indicating the possible
-virtual SMT modes that can be set using KVM_CAP_PPC_SMT. If bit N
-(counting from the right) is set, then a virtual SMT mode of 2^N is
-available.
-
-8.11 KVM_CAP_HYPERV_SYNIC2
---------------------------
-
-:Architectures: x86
-
-This capability enables a newer version of Hyper-V Synthetic interrupt
-controller (SynIC). The only difference with KVM_CAP_HYPERV_SYNIC is that KVM
-doesn't clear SynIC message and event flags pages when they are enabled by
-writing to the respective MSRs.
-
-8.12 KVM_CAP_HYPERV_VP_INDEX
-----------------------------
-
-:Architectures: x86
-
-This capability indicates that userspace can load HV_X64_MSR_VP_INDEX msr. Its
-value is used to denote the target vcpu for a SynIC interrupt. For
-compatibility, KVM initializes this msr to KVM's internal vcpu index. When this
-capability is absent, userspace can still query this msr's value.
-
-8.13 KVM_CAP_S390_AIS_MIGRATION
--------------------------------
-
-:Architectures: s390
-:Parameters: none
-
-This capability indicates if the flic device will be able to get/set the
-AIS states for migration via the KVM_DEV_FLIC_AISM_ALL attribute and allows
-to discover this without having to create a flic device.
-
-8.14 KVM_CAP_S390_PSW
----------------------
-
-:Architectures: s390
-
-This capability indicates that the PSW is exposed via the kvm_run structure.
-
-8.15 KVM_CAP_S390_GMAP
-----------------------
-
-:Architectures: s390
-
-This capability indicates that the user space memory used as guest mapping can
-be anywhere in the user memory address space, as long as the memory slots are
-aligned and sized to a segment (1MB) boundary.
-
-8.16 KVM_CAP_S390_COW
----------------------
-
-:Architectures: s390
-
-This capability indicates that the user space memory used as guest mapping can
-use copy-on-write semantics as well as dirty pages tracking via read-only page
-tables.
-
-8.17 KVM_CAP_S390_BPB
----------------------
-
-:Architectures: s390
-
-This capability indicates that kvm will implement the interfaces to handle
-reset, migration and nested KVM for branch prediction blocking. The stfle
-facility 82 should not be provided to the guest without this capability.
-
-8.18 KVM_CAP_HYPERV_TLBFLUSH
-----------------------------
-
-:Architectures: x86
-
-This capability indicates that KVM supports paravirtualized Hyper-V TLB Flush
-hypercalls:
-HvFlushVirtualAddressSpace, HvFlushVirtualAddressSpaceEx,
-HvFlushVirtualAddressList, HvFlushVirtualAddressListEx.
-
-8.19 KVM_CAP_ARM_INJECT_SERROR_ESR
-----------------------------------
-
-:Architectures: arm64
-
-This capability indicates that userspace can specify (via the
-KVM_SET_VCPU_EVENTS ioctl) the syndrome value reported to the guest when it
-takes a virtual SError interrupt exception.
-If KVM advertises this capability, userspace can only specify the ISS field for
-the ESR syndrome. Other parts of the ESR, such as the EC are generated by the
-CPU when the exception is taken. If this virtual SError is taken to EL1 using
-AArch64, this value will be reported in the ISS field of ESR_ELx.
-
-See KVM_CAP_VCPU_EVENTS for more details.
-
-8.20 KVM_CAP_HYPERV_SEND_IPI
-----------------------------
-
-:Architectures: x86
-
-This capability indicates that KVM supports paravirtualized Hyper-V IPI send
-hypercalls:
-HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx.
-
-8.21 KVM_CAP_HYPERV_DIRECT_TLBFLUSH
------------------------------------
-
-:Architectures: x86
-
-This capability indicates that KVM running on top of Hyper-V hypervisor
-enables Direct TLB flush for its guests meaning that TLB flush
-hypercalls are handled by Level 0 hypervisor (Hyper-V) bypassing KVM.
-Due to the different ABI for hypercall parameters between Hyper-V and
-KVM, enabling this capability effectively disables all hypercall
-handling by KVM (as some KVM hypercall may be mistakenly treated as TLB
-flush hypercalls by Hyper-V) so userspace should disable KVM identification
-in CPUID and only exposes Hyper-V identification. In this case, guest
-thinks it's running on Hyper-V and only use Hyper-V hypercalls.
-
-8.22 KVM_CAP_S390_VCPU_RESETS
------------------------------
-
-:Architectures: s390
-
-This capability indicates that the KVM_S390_NORMAL_RESET and
-KVM_S390_CLEAR_RESET ioctls are available.
-
-8.23 KVM_CAP_S390_PROTECTED
----------------------------
-
-:Architectures: s390
-
-This capability indicates that the Ultravisor has been initialized and
-KVM can therefore start protected VMs.
-This capability governs the KVM_S390_PV_COMMAND ioctl and the
-KVM_MP_STATE_LOAD MP_STATE. KVM_SET_MP_STATE can fail for protected
-guests when the state change is invalid.
-
-8.24 KVM_CAP_STEAL_TIME
------------------------
-
-:Architectures: arm64, x86
-
-This capability indicates that KVM supports steal time accounting.
-When steal time accounting is supported it may be enabled with
-architecture-specific interfaces. This capability and the architecture-
-specific interfaces must be consistent, i.e. if one says the feature
-is supported, than the other should as well and vice versa. For arm64
-see Documentation/virt/kvm/devices/vcpu.rst "KVM_ARM_VCPU_PVTIME_CTRL".
-For x86 see Documentation/virt/kvm/x86/msr.rst "MSR_KVM_STEAL_TIME".
-
-8.25 KVM_CAP_S390_DIAG318
--------------------------
-
-:Architectures: s390
-
-This capability enables a guest to set information about its control program
-(i.e. guest kernel type and version). The information is helpful during
-system/firmware service events, providing additional data about the guest
-environments running on the machine.
-
-The information is associated with the DIAGNOSE 0x318 instruction, which sets
-an 8-byte value consisting of a one-byte Control Program Name Code (CPNC) and
-a 7-byte Control Program Version Code (CPVC). The CPNC determines what
-environment the control program is running in (e.g. Linux, z/VM...), and the
-CPVC is used for information specific to OS (e.g. Linux version, Linux
-distribution...)
-
-If this capability is available, then the CPNC and CPVC can be synchronized
-between KVM and userspace via the sync regs mechanism (KVM_SYNC_DIAG318).
-
-8.26 KVM_CAP_X86_USER_SPACE_MSR
--------------------------------
-
-:Architectures: x86
-
-This capability indicates that KVM supports deflection of MSR reads and
-writes to user space. It can be enabled on a VM level. If enabled, MSR
-accesses that would usually trigger a #GP by KVM into the guest will
-instead get bounced to user space through the KVM_EXIT_X86_RDMSR and
-KVM_EXIT_X86_WRMSR exit notifications.
-
-8.27 KVM_CAP_X86_MSR_FILTER
----------------------------
-
-:Architectures: x86
-
-This capability indicates that KVM supports that accesses to user defined MSRs
-may be rejected. With this capability exposed, KVM exports new VM ioctl
-KVM_X86_SET_MSR_FILTER which user space can call to specify bitmaps of MSR
-ranges that KVM should deny access to.
-
-In combination with KVM_CAP_X86_USER_SPACE_MSR, this allows user space to
-trap and emulate MSRs that are outside of the scope of KVM as well as
-limit the attack surface on KVM's MSR emulation code.
-
-8.28 KVM_CAP_ENFORCE_PV_FEATURE_CPUID
--------------------------------------
-
-Architectures: x86
-
-When enabled, KVM will disable paravirtual features provided to the
-guest according to the bits in the KVM_CPUID_FEATURES CPUID leaf
-(0x40000001). Otherwise, a guest may use the paravirtual features
-regardless of what has actually been exposed through the CPUID leaf.
-
-.. _KVM_CAP_DIRTY_LOG_RING:
-
-8.29 KVM_CAP_DIRTY_LOG_RING/KVM_CAP_DIRTY_LOG_RING_ACQ_REL
+7.36 KVM_CAP_DIRTY_LOG_RING/KVM_CAP_DIRTY_LOG_RING_ACQ_REL
----------------------------------------------------------
:Architectures: x86, arm64
+:Type: vm
:Parameters: args[0] - size of the dirty log ring
KVM is capable of tracking dirty memory using ring buffers that are
@@ -8783,6 +8388,426 @@
vgic3 pending table through KVM_DEV_ARM_VGIC_{GRP_CTRL, SAVE_PENDING_TABLES}
command on KVM device "kvm-arm-vgic-v3".
+7.37 KVM_CAP_PMU_CAPABILITY
+---------------------------
+
+:Architectures: x86
+:Type: vm
+:Parameters: arg[0] is bitmask of PMU virtualization capabilities.
+:Returns: 0 on success, -EINVAL when arg[0] contains invalid bits
+
+This capability alters PMU virtualization in KVM.
+
+Calling KVM_CHECK_EXTENSION for this capability returns a bitmask of
+PMU virtualization capabilities that can be adjusted on a VM.
+
+The argument to KVM_ENABLE_CAP is also a bitmask and selects specific
+PMU virtualization capabilities to be applied to the VM. This can
+only be invoked on a VM prior to the creation of VCPUs.
+
+At this time, KVM_PMU_CAP_DISABLE is the only capability. Setting
+this capability will disable PMU virtualization for that VM. Usermode
+should adjust CPUID leaf 0xA to reflect that the PMU is disabled.
+
+7.38 KVM_CAP_VM_DISABLE_NX_HUGE_PAGES
+-------------------------------------
+
+:Architectures: x86
+:Type: vm
+:Parameters: arg[0] must be 0.
+:Returns: 0 on success, -EPERM if the userspace process does not
+ have CAP_SYS_BOOT, -EINVAL if args[0] is not 0 or any vCPUs have been
+ created.
+
+This capability disables the NX huge pages mitigation for iTLB MULTIHIT.
+
+The capability has no effect if the nx_huge_pages module parameter is not set.
+
+This capability may only be set before any vCPUs are created.
+
+7.39 KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE
+---------------------------------------
+
+:Architectures: arm64
+:Type: vm
+:Parameters: arg[0] is the new split chunk size.
+:Returns: 0 on success, -EINVAL if any memslot was already created.
+
+This capability sets the chunk size used in Eager Page Splitting.
+
+Eager Page Splitting improves the performance of dirty-logging (used
+in live migrations) when guest memory is backed by huge-pages. It
+avoids splitting huge-pages (into PAGE_SIZE pages) on fault, by doing
+it eagerly when enabling dirty logging (with the
+KVM_MEM_LOG_DIRTY_PAGES flag for a memory region), or when using
+KVM_CLEAR_DIRTY_LOG.
+
+The chunk size specifies how many pages to break at a time, using a
+single allocation for each chunk. Bigger the chunk size, more pages
+need to be allocated ahead of time.
+
+The chunk size needs to be a valid block size. The list of acceptable
+block sizes is exposed in KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES as a
+64-bit bitmap (each bit describing a block size). The default value is
+0, to disable the eager page splitting.
+
+7.40 KVM_CAP_EXIT_HYPERCALL
+---------------------------
+
+:Architectures: x86
+:Type: vm
+
+This capability, if enabled, will cause KVM to exit to userspace
+with KVM_EXIT_HYPERCALL exit reason to process some hypercalls.
+
+Calling KVM_CHECK_EXTENSION for this capability will return a bitmask
+of hypercalls that can be configured to exit to userspace.
+Right now, the only such hypercall is KVM_HC_MAP_GPA_RANGE.
+
+The argument to KVM_ENABLE_CAP is also a bitmask, and must be a subset
+of the result of KVM_CHECK_EXTENSION. KVM will forward to userspace
+the hypercalls whose corresponding bit is in the argument, and return
+ENOSYS for the others.
+
+7.41 KVM_CAP_ARM_SYSTEM_SUSPEND
+-------------------------------
+
+:Architectures: arm64
+:Type: vm
+
+When enabled, KVM will exit to userspace with KVM_EXIT_SYSTEM_EVENT of
+type KVM_SYSTEM_EVENT_SUSPEND to process the guest suspend request.
+
+7.37 KVM_CAP_ARM_WRITABLE_IMP_ID_REGS
+-------------------------------------
+
+:Architectures: arm64
+:Target: VM
+:Parameters: None
+:Returns: 0 on success, -EINVAL if vCPUs have been created before enabling this
+ capability.
+
+This capability changes the behavior of the registers that identify a PE
+implementation of the Arm architecture: MIDR_EL1, REVIDR_EL1, and AIDR_EL1.
+By default, these registers are visible to userspace but treated as invariant.
+
+When this capability is enabled, KVM allows userspace to change the
+aforementioned registers before the first KVM_RUN. These registers are VM
+scoped, meaning that the same set of values are presented on all vCPUs in a
+given VM.
+
+8. Other capabilities.
+======================
+
+This section lists capabilities that give information about other
+features of the KVM implementation.
+
+8.1 KVM_CAP_PPC_HWRNG
+---------------------
+
+:Architectures: ppc
+
+This capability, if KVM_CHECK_EXTENSION indicates that it is
+available, means that the kernel has an implementation of the
+H_RANDOM hypercall backed by a hardware random-number generator.
+If present, the kernel H_RANDOM handler can be enabled for guest use
+with the KVM_CAP_PPC_ENABLE_HCALL capability.
+
+8.3 KVM_CAP_PPC_MMU_RADIX
+-------------------------
+
+:Architectures: ppc
+
+This capability, if KVM_CHECK_EXTENSION indicates that it is
+available, means that the kernel can support guests using the
+radix MMU defined in Power ISA V3.00 (as implemented in the POWER9
+processor).
+
+8.4 KVM_CAP_PPC_MMU_HASH_V3
+---------------------------
+
+:Architectures: ppc
+
+This capability, if KVM_CHECK_EXTENSION indicates that it is
+available, means that the kernel can support guests using the
+hashed page table MMU defined in Power ISA V3.00 (as implemented in
+the POWER9 processor), including in-memory segment tables.
+
+8.5 KVM_CAP_MIPS_VZ
+-------------------
+
+:Architectures: mips
+
+This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that
+it is available, means that full hardware assisted virtualization capabilities
+of the hardware are available for use through KVM. An appropriate
+KVM_VM_MIPS_* type must be passed to KVM_CREATE_VM to create a VM which
+utilises it.
+
+If KVM_CHECK_EXTENSION on a kvm VM handle indicates that this capability is
+available, it means that the VM is using full hardware assisted virtualization
+capabilities of the hardware. This is useful to check after creating a VM with
+KVM_VM_MIPS_DEFAULT.
+
+The value returned by KVM_CHECK_EXTENSION should be compared against known
+values (see below). All other values are reserved. This is to allow for the
+possibility of other hardware assisted virtualization implementations which
+may be incompatible with the MIPS VZ ASE.
+
+== ==========================================================================
+ 0 The trap & emulate implementation is in use to run guest code in user
+ mode. Guest virtual memory segments are rearranged to fit the guest in the
+ user mode address space.
+
+ 1 The MIPS VZ ASE is in use, providing full hardware assisted
+ virtualization, including standard guest virtual memory segments.
+== ==========================================================================
+
+8.7 KVM_CAP_MIPS_64BIT
+----------------------
+
+:Architectures: mips
+
+This capability indicates the supported architecture type of the guest, i.e. the
+supported register and address width.
+
+The values returned when this capability is checked by KVM_CHECK_EXTENSION on a
+kvm VM handle correspond roughly to the CP0_Config.AT register field, and should
+be checked specifically against known values (see below). All other values are
+reserved.
+
+== ========================================================================
+ 0 MIPS32 or microMIPS32.
+ Both registers and addresses are 32-bits wide.
+ It will only be possible to run 32-bit guest code.
+
+ 1 MIPS64 or microMIPS64 with access only to 32-bit compatibility segments.
+ Registers are 64-bits wide, but addresses are 32-bits wide.
+ 64-bit guest code may run but cannot access MIPS64 memory segments.
+ It will also be possible to run 32-bit guest code.
+
+ 2 MIPS64 or microMIPS64 with access to all address segments.
+ Both registers and addresses are 64-bits wide.
+ It will be possible to run 64-bit or 32-bit guest code.
+== ========================================================================
+
+8.9 KVM_CAP_ARM_USER_IRQ
+------------------------
+
+:Architectures: arm64
+
+This capability, if KVM_CHECK_EXTENSION indicates that it is available, means
+that if userspace creates a VM without an in-kernel interrupt controller, it
+will be notified of changes to the output level of in-kernel emulated devices,
+which can generate virtual interrupts, presented to the VM.
+For such VMs, on every return to userspace, the kernel
+updates the vcpu's run->s.regs.device_irq_level field to represent the actual
+output level of the device.
+
+Whenever kvm detects a change in the device output level, kvm guarantees at
+least one return to userspace before running the VM. This exit could either
+be a KVM_EXIT_INTR or any other exit event, like KVM_EXIT_MMIO. This way,
+userspace can always sample the device output level and re-compute the state of
+the userspace interrupt controller. Userspace should always check the state
+of run->s.regs.device_irq_level on every kvm exit.
+The value in run->s.regs.device_irq_level can represent both level and edge
+triggered interrupt signals, depending on the device. Edge triggered interrupt
+signals will exit to userspace with the bit in run->s.regs.device_irq_level
+set exactly once per edge signal.
+
+The field run->s.regs.device_irq_level is available independent of
+run->kvm_valid_regs or run->kvm_dirty_regs bits.
+
+If KVM_CAP_ARM_USER_IRQ is supported, the KVM_CHECK_EXTENSION ioctl returns a
+number larger than 0 indicating the version of this capability is implemented
+and thereby which bits in run->s.regs.device_irq_level can signal values.
+
+Currently the following bits are defined for the device_irq_level bitmap::
+
+ KVM_CAP_ARM_USER_IRQ >= 1:
+
+ KVM_ARM_DEV_EL1_VTIMER - EL1 virtual timer
+ KVM_ARM_DEV_EL1_PTIMER - EL1 physical timer
+ KVM_ARM_DEV_PMU - ARM PMU overflow interrupt signal
+
+Future versions of kvm may implement additional events. These will get
+indicated by returning a higher number from KVM_CHECK_EXTENSION and will be
+listed above.
+
+8.10 KVM_CAP_PPC_SMT_POSSIBLE
+-----------------------------
+
+:Architectures: ppc
+
+Querying this capability returns a bitmap indicating the possible
+virtual SMT modes that can be set using KVM_CAP_PPC_SMT. If bit N
+(counting from the right) is set, then a virtual SMT mode of 2^N is
+available.
+
+8.12 KVM_CAP_HYPERV_VP_INDEX
+----------------------------
+
+:Architectures: x86
+
+This capability indicates that userspace can load HV_X64_MSR_VP_INDEX msr. Its
+value is used to denote the target vcpu for a SynIC interrupt. For
+compatibility, KVM initializes this msr to KVM's internal vcpu index. When this
+capability is absent, userspace can still query this msr's value.
+
+8.13 KVM_CAP_S390_AIS_MIGRATION
+-------------------------------
+
+:Architectures: s390
+
+This capability indicates if the flic device will be able to get/set the
+AIS states for migration via the KVM_DEV_FLIC_AISM_ALL attribute and allows
+to discover this without having to create a flic device.
+
+8.14 KVM_CAP_S390_PSW
+---------------------
+
+:Architectures: s390
+
+This capability indicates that the PSW is exposed via the kvm_run structure.
+
+8.15 KVM_CAP_S390_GMAP
+----------------------
+
+:Architectures: s390
+
+This capability indicates that the user space memory used as guest mapping can
+be anywhere in the user memory address space, as long as the memory slots are
+aligned and sized to a segment (1MB) boundary.
+
+8.16 KVM_CAP_S390_COW
+---------------------
+
+:Architectures: s390
+
+This capability indicates that the user space memory used as guest mapping can
+use copy-on-write semantics as well as dirty pages tracking via read-only page
+tables.
+
+8.17 KVM_CAP_S390_BPB
+---------------------
+
+:Architectures: s390
+
+This capability indicates that kvm will implement the interfaces to handle
+reset, migration and nested KVM for branch prediction blocking. The stfle
+facility 82 should not be provided to the guest without this capability.
+
+8.18 KVM_CAP_HYPERV_TLBFLUSH
+----------------------------
+
+:Architectures: x86
+
+This capability indicates that KVM supports paravirtualized Hyper-V TLB Flush
+hypercalls:
+HvFlushVirtualAddressSpace, HvFlushVirtualAddressSpaceEx,
+HvFlushVirtualAddressList, HvFlushVirtualAddressListEx.
+
+8.19 KVM_CAP_ARM_INJECT_SERROR_ESR
+----------------------------------
+
+:Architectures: arm64
+
+This capability indicates that userspace can specify (via the
+KVM_SET_VCPU_EVENTS ioctl) the syndrome value reported to the guest when it
+takes a virtual SError interrupt exception.
+If KVM advertises this capability, userspace can only specify the ISS field for
+the ESR syndrome. Other parts of the ESR, such as the EC are generated by the
+CPU when the exception is taken. If this virtual SError is taken to EL1 using
+AArch64, this value will be reported in the ISS field of ESR_ELx.
+
+See KVM_CAP_VCPU_EVENTS for more details.
+
+8.20 KVM_CAP_HYPERV_SEND_IPI
+----------------------------
+
+:Architectures: x86
+
+This capability indicates that KVM supports paravirtualized Hyper-V IPI send
+hypercalls:
+HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx.
+
+8.22 KVM_CAP_S390_VCPU_RESETS
+-----------------------------
+
+:Architectures: s390
+
+This capability indicates that the KVM_S390_NORMAL_RESET and
+KVM_S390_CLEAR_RESET ioctls are available.
+
+8.23 KVM_CAP_S390_PROTECTED
+---------------------------
+
+:Architectures: s390
+
+This capability indicates that the Ultravisor has been initialized and
+KVM can therefore start protected VMs.
+This capability governs the KVM_S390_PV_COMMAND ioctl and the
+KVM_MP_STATE_LOAD MP_STATE. KVM_SET_MP_STATE can fail for protected
+guests when the state change is invalid.
+
+8.24 KVM_CAP_STEAL_TIME
+-----------------------
+
+:Architectures: arm64, x86
+
+This capability indicates that KVM supports steal time accounting.
+When steal time accounting is supported it may be enabled with
+architecture-specific interfaces. This capability and the architecture-
+specific interfaces must be consistent, i.e. if one says the feature
+is supported, than the other should as well and vice versa. For arm64
+see Documentation/virt/kvm/devices/vcpu.rst "KVM_ARM_VCPU_PVTIME_CTRL".
+For x86 see Documentation/virt/kvm/x86/msr.rst "MSR_KVM_STEAL_TIME".
+
+8.25 KVM_CAP_S390_DIAG318
+-------------------------
+
+:Architectures: s390
+
+This capability enables a guest to set information about its control program
+(i.e. guest kernel type and version). The information is helpful during
+system/firmware service events, providing additional data about the guest
+environments running on the machine.
+
+The information is associated with the DIAGNOSE 0x318 instruction, which sets
+an 8-byte value consisting of a one-byte Control Program Name Code (CPNC) and
+a 7-byte Control Program Version Code (CPVC). The CPNC determines what
+environment the control program is running in (e.g. Linux, z/VM...), and the
+CPVC is used for information specific to OS (e.g. Linux version, Linux
+distribution...)
+
+If this capability is available, then the CPNC and CPVC can be synchronized
+between KVM and userspace via the sync regs mechanism (KVM_SYNC_DIAG318).
+
+8.26 KVM_CAP_X86_USER_SPACE_MSR
+-------------------------------
+
+:Architectures: x86
+
+This capability indicates that KVM supports deflection of MSR reads and
+writes to user space. It can be enabled on a VM level. If enabled, MSR
+accesses that would usually trigger a #GP by KVM into the guest will
+instead get bounced to user space through the KVM_EXIT_X86_RDMSR and
+KVM_EXIT_X86_WRMSR exit notifications.
+
+8.27 KVM_CAP_X86_MSR_FILTER
+---------------------------
+
+:Architectures: x86
+
+This capability indicates that KVM supports that accesses to user defined MSRs
+may be rejected. With this capability exposed, KVM exports new VM ioctl
+KVM_X86_SET_MSR_FILTER which user space can call to specify bitmaps of MSR
+ranges that KVM should deny access to.
+
+In combination with KVM_CAP_X86_USER_SPACE_MSR, this allows user space to
+trap and emulate MSRs that are outside of the scope of KVM as well as
+limit the attack surface on KVM's MSR emulation code.
+
8.30 KVM_CAP_XEN_HVM
--------------------
@@ -8847,10 +8872,9 @@
done when the KVM_CAP_XEN_HVM ioctl sets the
KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE flag.
-8.31 KVM_CAP_PPC_MULTITCE
--------------------------
+8.31 KVM_CAP_SPAPR_MULTITCE
+---------------------------
-:Capability: KVM_CAP_PPC_MULTITCE
:Architectures: ppc
:Type: vm
@@ -8882,72 +8906,9 @@
supported in the host. A VMM can check whether the service is
available to the guest on migration.
-8.33 KVM_CAP_HYPERV_ENFORCE_CPUID
----------------------------------
-
-Architectures: x86
-
-When enabled, KVM will disable emulated Hyper-V features provided to the
-guest according to the bits Hyper-V CPUID feature leaves. Otherwise, all
-currently implemented Hyper-V features are provided unconditionally when
-Hyper-V identification is set in the HYPERV_CPUID_INTERFACE (0x40000001)
-leaf.
-
-8.34 KVM_CAP_EXIT_HYPERCALL
----------------------------
-
-:Capability: KVM_CAP_EXIT_HYPERCALL
-:Architectures: x86
-:Type: vm
-
-This capability, if enabled, will cause KVM to exit to userspace
-with KVM_EXIT_HYPERCALL exit reason to process some hypercalls.
-
-Calling KVM_CHECK_EXTENSION for this capability will return a bitmask
-of hypercalls that can be configured to exit to userspace.
-Right now, the only such hypercall is KVM_HC_MAP_GPA_RANGE.
-
-The argument to KVM_ENABLE_CAP is also a bitmask, and must be a subset
-of the result of KVM_CHECK_EXTENSION. KVM will forward to userspace
-the hypercalls whose corresponding bit is in the argument, and return
-ENOSYS for the others.
-
-8.35 KVM_CAP_PMU_CAPABILITY
----------------------------
-
-:Capability: KVM_CAP_PMU_CAPABILITY
-:Architectures: x86
-:Type: vm
-:Parameters: arg[0] is bitmask of PMU virtualization capabilities.
-:Returns: 0 on success, -EINVAL when arg[0] contains invalid bits
-
-This capability alters PMU virtualization in KVM.
-
-Calling KVM_CHECK_EXTENSION for this capability returns a bitmask of
-PMU virtualization capabilities that can be adjusted on a VM.
-
-The argument to KVM_ENABLE_CAP is also a bitmask and selects specific
-PMU virtualization capabilities to be applied to the VM. This can
-only be invoked on a VM prior to the creation of VCPUs.
-
-At this time, KVM_PMU_CAP_DISABLE is the only capability. Setting
-this capability will disable PMU virtualization for that VM. Usermode
-should adjust CPUID leaf 0xA to reflect that the PMU is disabled.
-
-8.36 KVM_CAP_ARM_SYSTEM_SUSPEND
--------------------------------
-
-:Capability: KVM_CAP_ARM_SYSTEM_SUSPEND
-:Architectures: arm64
-:Type: vm
-
-When enabled, KVM will exit to userspace with KVM_EXIT_SYSTEM_EVENT of
-type KVM_SYSTEM_EVENT_SUSPEND to process the guest suspend request.
-
8.37 KVM_CAP_S390_PROTECTED_DUMP
--------------------------------
-:Capability: KVM_CAP_S390_PROTECTED_DUMP
:Architectures: s390
:Type: vm
@@ -8957,27 +8918,9 @@
dump related UV data. Also the vcpu ioctl `KVM_S390_PV_CPU_COMMAND` is
available and supports the `KVM_PV_DUMP_CPU` subcommand.
-8.38 KVM_CAP_VM_DISABLE_NX_HUGE_PAGES
--------------------------------------
-
-:Capability: KVM_CAP_VM_DISABLE_NX_HUGE_PAGES
-:Architectures: x86
-:Type: vm
-:Parameters: arg[0] must be 0.
-:Returns: 0 on success, -EPERM if the userspace process does not
- have CAP_SYS_BOOT, -EINVAL if args[0] is not 0 or any vCPUs have been
- created.
-
-This capability disables the NX huge pages mitigation for iTLB MULTIHIT.
-
-The capability has no effect if the nx_huge_pages module parameter is not set.
-
-This capability may only be set before any vCPUs are created.
-
8.39 KVM_CAP_S390_CPU_TOPOLOGY
------------------------------
-:Capability: KVM_CAP_S390_CPU_TOPOLOGY
:Architectures: s390
:Type: vm
@@ -8999,37 +8942,9 @@
When getting the Modified Change Topology Report value, the attr->addr
must point to a byte where the value will be stored or retrieved from.
-8.40 KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE
----------------------------------------
-
-:Capability: KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE
-:Architectures: arm64
-:Type: vm
-:Parameters: arg[0] is the new split chunk size.
-:Returns: 0 on success, -EINVAL if any memslot was already created.
-
-This capability sets the chunk size used in Eager Page Splitting.
-
-Eager Page Splitting improves the performance of dirty-logging (used
-in live migrations) when guest memory is backed by huge-pages. It
-avoids splitting huge-pages (into PAGE_SIZE pages) on fault, by doing
-it eagerly when enabling dirty logging (with the
-KVM_MEM_LOG_DIRTY_PAGES flag for a memory region), or when using
-KVM_CLEAR_DIRTY_LOG.
-
-The chunk size specifies how many pages to break at a time, using a
-single allocation for each chunk. Bigger the chunk size, more pages
-need to be allocated ahead of time.
-
-The chunk size needs to be a valid block size. The list of acceptable
-block sizes is exposed in KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES as a
-64-bit bitmap (each bit describing a block size). The default value is
-0, to disable the eager page splitting.
-
8.41 KVM_CAP_VM_TYPES
---------------------
-:Capability: KVM_CAP_MEMORY_ATTRIBUTES
:Architectures: x86
:Type: system ioctl
@@ -9046,6 +8961,67 @@
production. The behavior and effective ABI for software-protected VMs is
unstable.
+8.42 KVM_CAP_PPC_RPT_INVALIDATE
+-------------------------------
+
+:Architectures: ppc
+
+This capability indicates that the kernel is capable of handling
+H_RPT_INVALIDATE hcall.
+
+In order to enable the use of H_RPT_INVALIDATE in the guest,
+user space might have to advertise it for the guest. For example,
+IBM pSeries (sPAPR) guest starts using it if "hcall-rpt-invalidate" is
+present in the "ibm,hypertas-functions" device-tree property.
+
+This capability is enabled for hypervisors on platforms like POWER9
+that support radix MMU.
+
+8.43 KVM_CAP_PPC_AIL_MODE_3
+---------------------------
+
+:Architectures: ppc
+
+This capability indicates that the kernel supports the mode 3 setting for the
+"Address Translation Mode on Interrupt" aka "Alternate Interrupt Location"
+resource that is controlled with the H_SET_MODE hypercall.
+
+This capability allows a guest kernel to use a better-performance mode for
+handling interrupts and system calls.
+
+8.44 KVM_CAP_MEMORY_FAULT_INFO
+------------------------------
+
+:Architectures: x86
+
+The presence of this capability indicates that KVM_RUN will fill
+kvm_run.memory_fault if KVM cannot resolve a guest page fault VM-Exit, e.g. if
+there is a valid memslot but no backing VMA for the corresponding host virtual
+address.
+
+The information in kvm_run.memory_fault is valid if and only if KVM_RUN returns
+an error with errno=EFAULT or errno=EHWPOISON *and* kvm_run.exit_reason is set
+to KVM_EXIT_MEMORY_FAULT.
+
+Note: Userspaces which attempt to resolve memory faults so that they can retry
+KVM_RUN are encouraged to guard against repeatedly receiving the same
+error/annotated fault.
+
+See KVM_EXIT_MEMORY_FAULT for more information.
+
+8.45 KVM_CAP_X86_GUEST_MODE
+---------------------------
+
+:Architectures: x86
+
+The presence of this capability indicates that KVM_RUN will update the
+KVM_RUN_X86_GUEST_MODE bit in kvm_run.flags to indicate whether the
+vCPU was executing nested guest code when it exited.
+
+KVM exits with the register state of either the L1 or L2 guest
+depending on which executed at the time of an exit. Userspace must
+take care to differentiate between these cases.
+
9. Known KVM API problems
=========================
@@ -9076,9 +9052,10 @@
The same is true for the ``KVM_FEATURE_PV_UNHALT`` paravirtualized feature.
-CPU[EAX=1]:ECX[24] (TSC_DEADLINE) is not reported by ``KVM_GET_SUPPORTED_CPUID``.
-It can be enabled if ``KVM_CAP_TSC_DEADLINE_TIMER`` is present and the kernel
-has enabled in-kernel emulation of the local APIC.
+On older versions of Linux, CPU[EAX=1]:ECX[24] (TSC_DEADLINE) is not reported by
+``KVM_GET_SUPPORTED_CPUID``, but it can be enabled if ``KVM_CAP_TSC_DEADLINE_TIMER``
+is present and the kernel has enabled in-kernel emulation of the local APIC.
+On newer versions, ``KVM_GET_SUPPORTED_CPUID`` does report the bit as available.
CPU topology
~~~~~~~~~~~~
diff --git a/Documentation/wmi/devices/msi-wmi-platform.rst b/Documentation/wmi/devices/msi-wmi-platform.rst
index 31a1369..73197b3 100644
--- a/Documentation/wmi/devices/msi-wmi-platform.rst
+++ b/Documentation/wmi/devices/msi-wmi-platform.rst
@@ -138,6 +138,10 @@
The output buffer contains a single byte which signals success or failure (``0x00`` on failure)
and 31 bytes of output data, the meaning if which depends on the subfeature being accessed.
+.. note::
+ The ACPI control method responsible for handling the WMI method calls is not thread-safe.
+ This is a firmware bug that needs to be handled inside the driver itself.
+
WMI method Get_EC()
-------------------
diff --git a/MAINTAINERS b/MAINTAINERS
index 96b8270..d4b39f2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2519,6 +2519,7 @@
F: arch/arm/boot/dts/nxp/imx/
F: arch/arm/boot/dts/nxp/mxs/
F: arch/arm64/boot/dts/freescale/
+X: Documentation/devicetree/bindings/media/i2c/
X: arch/arm64/boot/dts/freescale/fsl-*
X: arch/arm64/boot/dts/freescale/qoriq-*
X: drivers/media/i2c/
@@ -3191,6 +3192,12 @@
S: Maintained
F: drivers/clk/socfpga/
+ARM/SOCFPGA DWMAC GLUE LAYER
+M: Maxime Chevallier <maxime.chevallier@bootlin.com>
+S: Maintained
+F: Documentation/devicetree/bindings/net/socfpga-dwmac.txt
+F: drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+
ARM/SOCFPGA EDAC BINDINGS
M: Matthew Gerlach <matthew.gerlach@altera.com>
S: Maintained
@@ -3867,8 +3874,9 @@
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
R: Dave Ertman <david.m.ertman@intel.com>
R: Ira Weiny <ira.weiny@intel.com>
+R: Leon Romanovsky <leon@kernel.org>
S: Supported
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/driver-core/driver-core.git
F: Documentation/driver-api/auxiliary_bus.rst
F: drivers/base/auxiliary.c
F: include/linux/auxiliary_bus.h
@@ -6335,6 +6343,7 @@
CW1200 WLAN driver
S: Orphan
+L: linux-wireless@vger.kernel.org
F: drivers/net/wireless/st/
F: include/linux/platform_data/net-cw1200.h
@@ -7020,6 +7029,7 @@
S: Supported
W: https://rust-for-linux.com
T: git https://github.com/Rust-for-Linux/linux.git alloc-next
+F: rust/helpers/dma.c
F: rust/kernel/dma.rs
F: samples/rust/rust_dma.rs
@@ -7225,7 +7235,7 @@
M: "Rafael J. Wysocki" <rafael@kernel.org>
M: Danilo Krummrich <dakr@kernel.org>
S: Supported
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/driver-core/driver-core.git
F: Documentation/core-api/kobject.rst
F: drivers/base/
F: fs/debugfs/
@@ -8717,6 +8727,7 @@
R: Yue Hu <zbestahu@gmail.com>
R: Jeffle Xu <jefflexu@linux.alibaba.com>
R: Sandeep Dhavale <dhavale@google.com>
+R: Hongbo Li <lihongbo22@huawei.com>
L: linux-erofs@lists.ozlabs.org
S: Maintained
W: https://erofs.docs.kernel.org
@@ -10151,6 +10162,8 @@
F: include/linux/gpio/
F: include/linux/of_gpio.h
K: (devm_)?gpio_(request|free|direction|get|set)
+K: GPIOD_FLAGS_BIT_NONEXCLUSIVE
+K: devm_gpiod_unhinge
GPIO UAPI
M: Bartosz Golaszewski <brgl@bgdev.pl>
@@ -10453,14 +10466,20 @@
F: drivers/infiniband/hw/hfi1
HFS FILESYSTEM
+M: Viacheslav Dubeyko <slava@dubeyko.com>
+M: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
+M: Yangtao Li <frank.li@vivo.com>
L: linux-fsdevel@vger.kernel.org
-S: Orphan
+S: Maintained
F: Documentation/filesystems/hfs.rst
F: fs/hfs/
HFSPLUS FILESYSTEM
+M: Viacheslav Dubeyko <slava@dubeyko.com>
+M: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
+M: Yangtao Li <frank.li@vivo.com>
L: linux-fsdevel@vger.kernel.org
-S: Orphan
+S: Maintained
F: Documentation/filesystems/hfsplus.rst
F: fs/hfsplus/
@@ -10954,6 +10973,7 @@
HUGETLB SUBSYSTEM
M: Muchun Song <muchun.song@linux.dev>
+R: Oscar Salvador <osalvador@suse.de>
L: linux-mm@kvack.org
S: Maintained
F: Documentation/ABI/testing/sysfs-kernel-mm-hugepages
@@ -12810,6 +12830,7 @@
F: scripts/Makefile.kcsan
KDUMP
+M: Andrew Morton <akpm@linux-foundation.org>
M: Baoquan He <bhe@redhat.com>
R: Vivek Goyal <vgoyal@redhat.com>
R: Dave Young <dyoung@redhat.com>
@@ -13106,11 +13127,13 @@
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
M: Tejun Heo <tj@kernel.org>
S: Supported
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/driver-core/driver-core.git
F: fs/kernfs/
F: include/linux/kernfs.h
KEXEC
+M: Andrew Morton <akpm@linux-foundation.org>
+M: Baoquan He <bhe@redhat.com>
L: kexec@lists.infradead.org
W: http://kernel.org/pub/linux/utils/kernel/kexec/
F: include/linux/kexec.h
@@ -14283,6 +14306,7 @@
F: drivers/net/ethernet/marvell/sk*
MARVELL LIBERTAS WIRELESS DRIVER
+L: linux-wireless@vger.kernel.org
L: libertas-dev@lists.infradead.org
S: Orphan
F: drivers/net/wireless/marvell/libertas/
@@ -15049,7 +15073,7 @@
F: drivers/media/platform/mediatek/jpeg/
MEDIATEK KEYPAD DRIVER
-M: Mattijs Korpershoek <mkorpershoek@baylibre.com>
+M: Mattijs Korpershoek <mkorpershoek@kernel.org>
S: Supported
F: Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml
F: drivers/input/keyboard/mt6779-keypad.c
@@ -15472,24 +15496,45 @@
F: include/linux/gfp.h
F: include/linux/gfp_types.h
F: include/linux/memfd.h
-F: include/linux/memory.h
F: include/linux/memory_hotplug.h
F: include/linux/memory-tiers.h
F: include/linux/mempolicy.h
F: include/linux/mempool.h
F: include/linux/memremap.h
-F: include/linux/mm.h
-F: include/linux/mm_*.h
F: include/linux/mmzone.h
F: include/linux/mmu_notifier.h
F: include/linux/pagewalk.h
-F: include/linux/rmap.h
F: include/trace/events/ksm.h
F: mm/
F: tools/mm/
F: tools/testing/selftests/mm/
N: include/linux/page[-_]*
+MEMORY MANAGEMENT - CORE
+M: Andrew Morton <akpm@linux-foundation.org>
+M: David Hildenbrand <david@redhat.com>
+R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R: Liam R. Howlett <Liam.Howlett@oracle.com>
+R: Vlastimil Babka <vbabka@suse.cz>
+R: Mike Rapoport <rppt@kernel.org>
+R: Suren Baghdasaryan <surenb@google.com>
+R: Michal Hocko <mhocko@suse.com>
+L: linux-mm@kvack.org
+S: Maintained
+W: http://www.linux-mm.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F: include/linux/memory.h
+F: include/linux/mm.h
+F: include/linux/mm_*.h
+F: include/linux/mmdebug.h
+F: include/linux/pagewalk.h
+F: mm/Kconfig
+F: mm/debug.c
+F: mm/init-mm.c
+F: mm/memory.c
+F: mm/pagewalk.c
+F: mm/util.c
+
MEMORY MANAGEMENT - EXECMEM
M: Andrew Morton <akpm@linux-foundation.org>
M: Mike Rapoport <rppt@kernel.org>
@@ -15508,6 +15553,34 @@
F: mm/numa_emulation.c
F: mm/numa_memblks.c
+MEMORY MANAGEMENT - PAGE ALLOCATOR
+M: Andrew Morton <akpm@linux-foundation.org>
+R: Vlastimil Babka <vbabka@suse.cz>
+R: Suren Baghdasaryan <surenb@google.com>
+R: Michal Hocko <mhocko@suse.com>
+R: Brendan Jackman <jackmanb@google.com>
+R: Johannes Weiner <hannes@cmpxchg.org>
+R: Zi Yan <ziy@nvidia.com>
+L: linux-mm@kvack.org
+S: Maintained
+F: mm/compaction.c
+F: mm/page_alloc.c
+F: include/linux/gfp.h
+F: include/linux/compaction.h
+
+MEMORY MANAGEMENT - RMAP (REVERSE MAPPING)
+M: Andrew Morton <akpm@linux-foundation.org>
+M: David Hildenbrand <david@redhat.com>
+M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R: Rik van Riel <riel@surriel.com>
+R: Liam R. Howlett <Liam.Howlett@oracle.com>
+R: Vlastimil Babka <vbabka@suse.cz>
+R: Harry Yoo <harry.yoo@oracle.com>
+L: linux-mm@kvack.org
+S: Maintained
+F: include/linux/rmap.h
+F: mm/rmap.c
+
MEMORY MANAGEMENT - SECRETMEM
M: Andrew Morton <akpm@linux-foundation.org>
M: Mike Rapoport <rppt@kernel.org>
@@ -15516,6 +15589,30 @@
F: include/linux/secretmem.h
F: mm/secretmem.c
+MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE)
+M: Andrew Morton <akpm@linux-foundation.org>
+M: David Hildenbrand <david@redhat.com>
+R: Zi Yan <ziy@nvidia.com>
+R: Baolin Wang <baolin.wang@linux.alibaba.com>
+R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R: Liam R. Howlett <Liam.Howlett@oracle.com>
+R: Nico Pache <npache@redhat.com>
+R: Ryan Roberts <ryan.roberts@arm.com>
+R: Dev Jain <dev.jain@arm.com>
+L: linux-mm@kvack.org
+S: Maintained
+W: http://www.linux-mm.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F: Documentation/admin-guide/mm/transhuge.rst
+F: include/linux/huge_mm.h
+F: include/linux/khugepaged.h
+F: include/trace/events/huge_memory.h
+F: mm/huge_memory.c
+F: mm/khugepaged.c
+F: tools/testing/selftests/mm/khugepaged.c
+F: tools/testing/selftests/mm/split_huge_page_test.c
+F: tools/testing/selftests/mm/transhuge-stress.c
+
MEMORY MANAGEMENT - USERFAULTFD
M: Andrew Morton <akpm@linux-foundation.org>
R: Peter Xu <peterx@redhat.com>
@@ -15535,10 +15632,12 @@
M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
R: Vlastimil Babka <vbabka@suse.cz>
R: Jann Horn <jannh@google.com>
+R: Pedro Falcato <pfalcato@suse.de>
L: linux-mm@kvack.org
S: Maintained
W: http://www.linux-mm.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F: include/trace/events/mmap.h
F: mm/mlock.c
F: mm/mmap.c
F: mm/mprotect.c
@@ -15549,6 +15648,36 @@
F: mm/vma_internal.h
F: tools/testing/vma/
+MEMORY MAPPING - LOCKING
+M: Andrew Morton <akpm@linux-foundation.org>
+M: Suren Baghdasaryan <surenb@google.com>
+M: Liam R. Howlett <Liam.Howlett@oracle.com>
+M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R: Vlastimil Babka <vbabka@suse.cz>
+R: Shakeel Butt <shakeel.butt@linux.dev>
+L: linux-mm@kvack.org
+S: Maintained
+W: http://www.linux-mm.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F: Documentation/mm/process_addrs.rst
+F: include/linux/mmap_lock.h
+F: include/trace/events/mmap_lock.h
+F: mm/mmap_lock.c
+
+MEMORY MAPPING - MADVISE (MEMORY ADVICE)
+M: Andrew Morton <akpm@linux-foundation.org>
+M: Liam R. Howlett <Liam.Howlett@oracle.com>
+M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+M: David Hildenbrand <david@redhat.com>
+R: Vlastimil Babka <vbabka@suse.cz>
+R: Jann Horn <jannh@google.com>
+L: linux-mm@kvack.org
+S: Maintained
+W: http://www.linux-mm.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F: include/uapi/asm-generic/mman-common.h
+F: mm/madvise.c
+
MEMORY TECHNOLOGY DEVICES (MTD)
M: Miquel Raynal <miquel.raynal@bootlin.com>
M: Richard Weinberger <richard@nod.at>
@@ -16756,6 +16885,7 @@
F: drivers/connector/
F: drivers/net/
F: drivers/ptp/
+F: drivers/s390/net/
F: include/dt-bindings/net/
F: include/linux/cn_proc.h
F: include/linux/etherdevice.h
@@ -16765,6 +16895,7 @@
F: include/linux/hippidevice.h
F: include/linux/if_*
F: include/linux/inetdevice.h
+F: include/linux/ism.h
F: include/linux/netdev*
F: include/linux/platform_data/wiznet.h
F: include/uapi/linux/cn_proc.h
@@ -17368,7 +17499,7 @@
F: drivers/nvme/target/
NVMEM FRAMEWORK
-M: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+M: Srinivas Kandagatla <srini@kernel.org>
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/srini/nvmem.git
F: Documentation/ABI/stable/sysfs-bus-nvmem
@@ -18633,7 +18764,7 @@
PCI NATIVE HOST BRIDGE AND ENDPOINT DRIVERS
M: Lorenzo Pieralisi <lpieralisi@kernel.org>
M: Krzysztof Wilczyński <kw@linux.com>
-R: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
R: Rob Herring <robh@kernel.org>
L: linux-pci@vger.kernel.org
S: Supported
@@ -18686,6 +18817,16 @@
F: include/linux/of_pci.h
F: include/linux/pci*
F: include/uapi/linux/pci*
+
+PCI SUBSYSTEM [RUST]
+M: Danilo Krummrich <dakr@kernel.org>
+R: Bjorn Helgaas <bhelgaas@google.com>
+R: Krzysztof Wilczyński <kwilczynski@kernel.org>
+L: linux-pci@vger.kernel.org
+S: Maintained
+C: irc://irc.oftc.net/linux-pci
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci.git
+F: rust/helpers/pci.c
F: rust/kernel/pci.rs
F: samples/rust/rust_driver_pci.rs
@@ -19573,7 +19714,7 @@
F: drivers/crypto/intel/qat/
QCOM AUDIO (ASoC) DRIVERS
-M: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+M: Srinivas Kandagatla <srini@kernel.org>
L: linux-sound@vger.kernel.org
L: linux-arm-msm@vger.kernel.org
S: Supported
@@ -19746,6 +19887,7 @@
QUALCOMM ATH12K WIRELESS DRIVER
M: Jeff Johnson <jjohnson@kernel.org>
+L: linux-wireless@vger.kernel.org
L: ath12k@lists.infradead.org
S: Supported
W: https://wireless.wiki.kernel.org/en/users/Drivers/ath12k
@@ -19755,6 +19897,7 @@
QUALCOMM ATHEROS ATH10K WIRELESS DRIVER
M: Jeff Johnson <jjohnson@kernel.org>
+L: linux-wireless@vger.kernel.org
L: ath10k@lists.infradead.org
S: Supported
W: https://wireless.wiki.kernel.org/en/users/Drivers/ath10k
@@ -19764,6 +19907,7 @@
QUALCOMM ATHEROS ATH11K WIRELESS DRIVER
M: Jeff Johnson <jjohnson@kernel.org>
+L: linux-wireless@vger.kernel.org
L: ath11k@lists.infradead.org
S: Supported
W: https://wireless.wiki.kernel.org/en/users/Drivers/ath11k
@@ -19873,7 +20017,7 @@
F: drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
QUALCOMM FASTRPC DRIVER
-M: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+M: Srinivas Kandagatla <srini@kernel.org>
M: Amol Maheshwari <amahesh@qti.qualcomm.com>
L: linux-arm-msm@vger.kernel.org
L: dri-devel@lists.freedesktop.org
@@ -21253,6 +21397,7 @@
L: netdev@vger.kernel.org
S: Supported
F: drivers/s390/net/
+F: include/linux/ism.h
S390 PCI SUBSYSTEM
M: Niklas Schnelle <schnelle@linux.ibm.com>
@@ -21921,7 +22066,7 @@
F: drivers/media/rc/serial_ir.c
SERIAL LOW-POWER INTER-CHIP MEDIA BUS (SLIMbus)
-M: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+M: Srinivas Kandagatla <srini@kernel.org>
L: linux-sound@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/slimbus/
@@ -22137,6 +22282,7 @@
SILICON LABS WIRELESS DRIVERS (for WFxxx series)
M: Jérôme Pouiller <jerome.pouiller@silabs.com>
+L: linux-wireless@vger.kernel.org
S: Supported
F: Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml
F: drivers/net/wireless/silabs/
@@ -22237,9 +22383,7 @@
SLAB ALLOCATOR
M: Christoph Lameter <cl@linux.com>
-M: Pekka Enberg <penberg@kernel.org>
M: David Rientjes <rientjes@google.com>
-M: Joonsoo Kim <iamjoonsoo.kim@lge.com>
M: Andrew Morton <akpm@linux-foundation.org>
M: Vlastimil Babka <vbabka@suse.cz>
R: Roman Gushchin <roman.gushchin@linux.dev>
@@ -22654,9 +22798,15 @@
F: Documentation/devicetree/bindings/sound/
F: Documentation/sound/soc/
F: include/dt-bindings/sound/
+F: include/sound/cs-amp-lib.h
+F: include/sound/cs35l*
+F: include/sound/cs4271.h
+F: include/sound/cs42l*
+F: include/sound/madera-pdata.h
F: include/sound/soc*
F: include/sound/sof.h
F: include/sound/sof/
+F: include/sound/wm*.h
F: include/trace/events/sof*.h
F: include/uapi/sound/asoc.h
F: sound/soc/
@@ -25126,9 +25276,13 @@
F: drivers/usb/typec/mux/pi3usb30532.c
USB TYPEC PORT CONTROLLER DRIVERS
+M: Badhri Jagan Sridharan <badhri@google.com>
L: linux-usb@vger.kernel.org
-S: Orphan
-F: drivers/usb/typec/tcpm/
+S: Maintained
+F: drivers/usb/typec/tcpm/tcpci.c
+F: drivers/usb/typec/tcpm/tcpm.c
+F: include/linux/usb/tcpci.h
+F: include/linux/usb/tcpm.h
USB TYPEC TUSB1046 MUX DRIVER
M: Romain Gantois <romain.gantois@bootlin.com>
diff --git a/Makefile b/Makefile
index 38689a0..94be5df 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 15
SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc4
NAME = Baby Opossum Posse
# *DOCUMENTATION*
@@ -477,7 +477,6 @@
-Wclippy::ignored_unit_patterns \
-Wclippy::mut_mut \
-Wclippy::needless_bitwise_bool \
- -Wclippy::needless_continue \
-Aclippy::needless_lifetimes \
-Wclippy::no_mangle_with_rust_abi \
-Wclippy::undocumented_unsafe_blocks \
@@ -1053,10 +1052,6 @@
# perform bounds checking.
KBUILD_CFLAGS += $(call cc-option, -fstrict-flex-arrays=3)
-#Currently, disable -Wstringop-overflow for GCC 11, globally.
-KBUILD_CFLAGS-$(CONFIG_CC_NO_STRINGOP_OVERFLOW) += $(call cc-option, -Wno-stringop-overflow)
-KBUILD_CFLAGS-$(CONFIG_CC_STRINGOP_OVERFLOW) += $(call cc-option, -Wstringop-overflow)
-
# disable invalid "can't wrap" optimizations for signed / pointers
KBUILD_CFLAGS += -fno-strict-overflow
@@ -1068,6 +1063,9 @@
KBUILD_CFLAGS += -fconserve-stack
endif
+# Ensure compilers do not transform certain loops into calls to wcslen()
+KBUILD_CFLAGS += -fno-builtin-wcslen
+
# change __FILE__ to the relative path to the source directory
ifdef building_out_of_srctree
KBUILD_CPPFLAGS += $(call cc-option,-ffile-prefix-map=$(srcroot)/=)
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi
index f2386dc..dda4fa91 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi
@@ -40,6 +40,9 @@ ethphy1: ethernet-phy@1 {
reg = <1>;
interrupt-parent = <&gpio4>;
interrupts = <16 IRQ_TYPE_LEVEL_LOW>;
+ micrel,led-mode = <1>;
+ clocks = <&clks IMX6UL_CLK_ENET_REF>;
+ clock-names = "rmii-ref";
status = "okay";
};
};
diff --git a/arch/arm/configs/at91_dt_defconfig b/arch/arm/configs/at91_dt_defconfig
index f2596a1..ff13e1e 100644
--- a/arch/arm/configs/at91_dt_defconfig
+++ b/arch/arm/configs/at91_dt_defconfig
@@ -232,7 +232,6 @@
CONFIG_CRYPTO_DEV_ATMEL_AES=y
CONFIG_CRYPTO_DEV_ATMEL_TDES=y
CONFIG_CRYPTO_DEV_ATMEL_SHA=y
-CONFIG_CRC_CCITT=y
CONFIG_FONTS=y
CONFIG_FONT_8x8=y
CONFIG_FONT_ACORN_8x8=y
diff --git a/arch/arm/configs/collie_defconfig b/arch/arm/configs/collie_defconfig
index 42cb1c8..578c6a4 100644
--- a/arch/arm/configs/collie_defconfig
+++ b/arch/arm/configs/collie_defconfig
@@ -78,7 +78,6 @@
CONFIG_NLS_DEFAULT="cp437"
CONFIG_NLS_CODEPAGE_437=y
CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_CCITT=y
CONFIG_FONTS=y
CONFIG_FONT_MINI_4x6=y
# CONFIG_DEBUG_BUGVERBOSE is not set
diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig
index 3474e47..70b8c78 100644
--- a/arch/arm/configs/davinci_all_defconfig
+++ b/arch/arm/configs/davinci_all_defconfig
@@ -249,7 +249,6 @@
CONFIG_NLS_ISO8859_1=y
CONFIG_NLS_UTF8=m
# CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=m
CONFIG_DMA_CMA=y
CONFIG_DEBUG_FS=y
CONFIG_DEBUG_RT_MUTEXES=y
diff --git a/arch/arm/configs/dove_defconfig b/arch/arm/configs/dove_defconfig
index b382a2e..d76eb12 100644
--- a/arch/arm/configs/dove_defconfig
+++ b/arch/arm/configs/dove_defconfig
@@ -128,7 +128,6 @@
CONFIG_CRYPTO_LZO=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
CONFIG_CRYPTO_DEV_MARVELL_CESA=y
-CONFIG_CRC_CCITT=y
CONFIG_PRINTK_TIME=y
# CONFIG_DEBUG_BUGVERBOSE is not set
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index 7ad48fd..e81a5d6 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -370,7 +370,6 @@
CONFIG_CRYPTO_CHACHA20_NEON=m
CONFIG_CRYPTO_DEV_EXYNOS_RNG=y
CONFIG_CRYPTO_DEV_S5P=y
-CONFIG_CRC_CCITT=y
CONFIG_DMA_CMA=y
CONFIG_CMA_SIZE_MBYTES=96
CONFIG_FONTS=y
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index 297c6a7b..062c1eb 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -481,8 +481,6 @@
CONFIG_CRYPTO_DEV_FSL_CAAM=y
CONFIG_CRYPTO_DEV_SAHARA=y
CONFIG_CRYPTO_DEV_MXS_DCP=y
-CONFIG_CRC_CCITT=m
-CONFIG_CRC_T10DIF=y
CONFIG_CMA_SIZE_MBYTES=64
CONFIG_FONTS=y
CONFIG_FONT_8x8=y
diff --git a/arch/arm/configs/lpc18xx_defconfig b/arch/arm/configs/lpc18xx_defconfig
index 2aa2ac8..2d48918 100644
--- a/arch/arm/configs/lpc18xx_defconfig
+++ b/arch/arm/configs/lpc18xx_defconfig
@@ -147,7 +147,6 @@
# CONFIG_INOTIFY_USER is not set
CONFIG_JFFS2_FS=y
# CONFIG_NETWORK_FILESYSTEMS is not set
-CONFIG_CRC_ITU_T=y
CONFIG_PRINTK_TIME=y
# CONFIG_ENABLE_MUST_CHECK is not set
# CONFIG_DEBUG_BUGVERBOSE is not set
diff --git a/arch/arm/configs/lpc32xx_defconfig b/arch/arm/configs/lpc32xx_defconfig
index 98e2672..9afccd7 100644
--- a/arch/arm/configs/lpc32xx_defconfig
+++ b/arch/arm/configs/lpc32xx_defconfig
@@ -179,7 +179,6 @@
CONFIG_NLS_UTF8=y
CONFIG_CRYPTO_ANSI_CPRNG=y
# CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_CCITT=y
CONFIG_PRINTK_TIME=y
CONFIG_DYNAMIC_DEBUG=y
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
diff --git a/arch/arm/configs/milbeaut_m10v_defconfig b/arch/arm/configs/milbeaut_m10v_defconfig
index acd1620..275ddf7 100644
--- a/arch/arm/configs/milbeaut_m10v_defconfig
+++ b/arch/arm/configs/milbeaut_m10v_defconfig
@@ -108,8 +108,6 @@
CONFIG_CRYPTO_AES_ARM_CE=m
CONFIG_CRYPTO_CHACHA20_NEON=m
# CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_CCITT=m
-CONFIG_CRC_ITU_T=m
CONFIG_DMA_CMA=y
CONFIG_CMA_SIZE_MBYTES=64
CONFIG_PRINTK_TIME=y
diff --git a/arch/arm/configs/mmp2_defconfig b/arch/arm/configs/mmp2_defconfig
index f6f9e13..842a989 100644
--- a/arch/arm/configs/mmp2_defconfig
+++ b/arch/arm/configs/mmp2_defconfig
@@ -67,7 +67,6 @@
CONFIG_NFS_V3_ACL=y
CONFIG_NFS_V4=y
CONFIG_ROOT_NFS=y
-CONFIG_CRC_CCITT=y
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_KERNEL=y
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
diff --git a/arch/arm/configs/multi_v4t_defconfig b/arch/arm/configs/multi_v4t_defconfig
index 27d6506..1a86dc3 100644
--- a/arch/arm/configs/multi_v4t_defconfig
+++ b/arch/arm/configs/multi_v4t_defconfig
@@ -91,6 +91,5 @@
CONFIG_VFAT_FS=y
CONFIG_CRAMFS=y
CONFIG_MINIX_FS=y
-CONFIG_CRC_CCITT=y
# CONFIG_FTRACE is not set
CONFIG_DEBUG_USER=y
diff --git a/arch/arm/configs/multi_v5_defconfig b/arch/arm/configs/multi_v5_defconfig
index db81862..cf6180b 100644
--- a/arch/arm/configs/multi_v5_defconfig
+++ b/arch/arm/configs/multi_v5_defconfig
@@ -289,7 +289,6 @@
CONFIG_CRYPTO_CBC=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_DEV_MARVELL_CESA=y
-CONFIG_CRC_CCITT=y
CONFIG_DEBUG_KERNEL=y
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/arm/configs/mvebu_v5_defconfig b/arch/arm/configs/mvebu_v5_defconfig
index a518d4a..23dbb80 100644
--- a/arch/arm/configs/mvebu_v5_defconfig
+++ b/arch/arm/configs/mvebu_v5_defconfig
@@ -187,7 +187,6 @@
CONFIG_CRYPTO_CBC=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_DEV_MARVELL_CESA=y
-CONFIG_CRC_CCITT=y
CONFIG_DEBUG_KERNEL=y
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig
index d8a6e43..c76d661 100644
--- a/arch/arm/configs/mxs_defconfig
+++ b/arch/arm/configs/mxs_defconfig
@@ -160,7 +160,6 @@
CONFIG_NLS_ISO8859_1=y
CONFIG_NLS_ISO8859_15=y
CONFIG_CRYPTO_DEV_MXS_DCP=y
-CONFIG_CRC_ITU_T=m
CONFIG_FONTS=y
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_KERNEL=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 113d6df..75b326b 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -706,9 +706,6 @@
CONFIG_CRYPTO_DEV_OMAP_SHAM=m
CONFIG_CRYPTO_DEV_OMAP_AES=m
CONFIG_CRYPTO_DEV_OMAP_DES=m
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_T10DIF=y
-CONFIG_CRC_ITU_T=y
CONFIG_DMA_CMA=y
CONFIG_FONTS=y
CONFIG_FONT_8x8=y
diff --git a/arch/arm/configs/orion5x_defconfig b/arch/arm/configs/orion5x_defconfig
index 0629b08..62b9c61 100644
--- a/arch/arm/configs/orion5x_defconfig
+++ b/arch/arm/configs/orion5x_defconfig
@@ -136,7 +136,6 @@
CONFIG_CRYPTO_ECB=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_DEV_MARVELL_CESA=y
-CONFIG_CRC_T10DIF=y
# CONFIG_DEBUG_BUGVERBOSE is not set
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/arm/configs/pxa168_defconfig b/arch/arm/configs/pxa168_defconfig
index ce10fe2..4748c7d 100644
--- a/arch/arm/configs/pxa168_defconfig
+++ b/arch/arm/configs/pxa168_defconfig
@@ -41,7 +41,6 @@
CONFIG_NFS_V3_ACL=y
CONFIG_NFS_V4=y
CONFIG_ROOT_NFS=y
-CONFIG_CRC_CCITT=y
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_KERNEL=y
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
diff --git a/arch/arm/configs/pxa910_defconfig b/arch/arm/configs/pxa910_defconfig
index 1f28aea..49b59c6 100644
--- a/arch/arm/configs/pxa910_defconfig
+++ b/arch/arm/configs/pxa910_defconfig
@@ -50,7 +50,6 @@
CONFIG_NFS_V3_ACL=y
CONFIG_NFS_V4=y
CONFIG_ROOT_NFS=y
-CONFIG_CRC_CCITT=y
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_KERNEL=y
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
index de0ac8f..24fca86 100644
--- a/arch/arm/configs/pxa_defconfig
+++ b/arch/arm/configs/pxa_defconfig
@@ -663,8 +663,6 @@
CONFIG_CRYPTO_SHA256_ARM=m
CONFIG_CRYPTO_SHA512_ARM=m
CONFIG_CRYPTO_AES_ARM=m
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_T10DIF=m
CONFIG_FONTS=y
CONFIG_FONT_8x8=y
CONFIG_FONT_8x16=y
diff --git a/arch/arm/configs/s5pv210_defconfig b/arch/arm/configs/s5pv210_defconfig
index 5dbe85c..02121ee 100644
--- a/arch/arm/configs/s5pv210_defconfig
+++ b/arch/arm/configs/s5pv210_defconfig
@@ -113,7 +113,6 @@
CONFIG_NLS_ASCII=y
CONFIG_NLS_ISO8859_1=y
CONFIG_NLS_UTF8=y
-CONFIG_CRC_CCITT=y
CONFIG_DEBUG_KERNEL=y
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/arm/configs/sama7_defconfig b/arch/arm/configs/sama7_defconfig
index ea7ddf6..e14720a 100644
--- a/arch/arm/configs/sama7_defconfig
+++ b/arch/arm/configs/sama7_defconfig
@@ -227,8 +227,6 @@
CONFIG_CRYPTO_DEV_ATMEL_AES=y
CONFIG_CRYPTO_DEV_ATMEL_TDES=y
CONFIG_CRYPTO_DEV_ATMEL_SHA=y
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_ITU_T=y
CONFIG_DMA_CMA=y
CONFIG_CMA_SIZE_MBYTES=32
CONFIG_CMA_ALIGNMENT=9
diff --git a/arch/arm/configs/spitz_defconfig b/arch/arm/configs/spitz_defconfig
index ac5b7a5..ffec59e 100644
--- a/arch/arm/configs/spitz_defconfig
+++ b/arch/arm/configs/spitz_defconfig
@@ -234,7 +234,6 @@
CONFIG_CRYPTO_MICHAEL_MIC=m
CONFIG_CRYPTO_SHA512=m
CONFIG_CRYPTO_WP512=m
-CONFIG_CRC_CCITT=y
CONFIG_FONTS=y
CONFIG_FONT_8x8=y
CONFIG_FONT_8x16=y
diff --git a/arch/arm/configs/stm32_defconfig b/arch/arm/configs/stm32_defconfig
index 423bb41..dcd9c316 100644
--- a/arch/arm/configs/stm32_defconfig
+++ b/arch/arm/configs/stm32_defconfig
@@ -74,7 +74,6 @@
# CONFIG_DNOTIFY is not set
# CONFIG_INOTIFY_USER is not set
CONFIG_NLS=y
-CONFIG_CRC_ITU_T=y
CONFIG_PRINTK_TIME=y
# CONFIG_DEBUG_BUGVERBOSE is not set
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
diff --git a/arch/arm/configs/wpcm450_defconfig b/arch/arm/configs/wpcm450_defconfig
index 5e4397f..cd4b3e7 100644
--- a/arch/arm/configs/wpcm450_defconfig
+++ b/arch/arm/configs/wpcm450_defconfig
@@ -191,8 +191,6 @@
CONFIG_X509_CERTIFICATE_PARSER=y
CONFIG_PKCS7_MESSAGE_PARSER=y
CONFIG_SYSTEM_TRUSTED_KEYRING=y
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_ITU_T=m
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_KERNEL=y
CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/arm64/boot/dts/arm/morello.dtsi b/arch/arm64/boot/dts/arm/morello.dtsi
index 0bab0b3..5bc1c72 100644
--- a/arch/arm64/boot/dts/arm/morello.dtsi
+++ b/arch/arm64/boot/dts/arm/morello.dtsi
@@ -44,7 +44,7 @@ cpu0: cpu@0 {
next-level-cache = <&l2_0>;
clocks = <&scmi_dvfs 0>;
- l2_0: l2-cache-0 {
+ l2_0: l2-cache {
compatible = "cache";
cache-level = <2>;
/* 8 ways set associative */
@@ -53,13 +53,6 @@ l2_0: l2-cache-0 {
cache-sets = <2048>;
cache-unified;
next-level-cache = <&l3_0>;
-
- l3_0: l3-cache {
- compatible = "cache";
- cache-level = <3>;
- cache-size = <0x100000>;
- cache-unified;
- };
};
};
@@ -78,7 +71,7 @@ cpu1: cpu@100 {
next-level-cache = <&l2_1>;
clocks = <&scmi_dvfs 0>;
- l2_1: l2-cache-1 {
+ l2_1: l2-cache {
compatible = "cache";
cache-level = <2>;
/* 8 ways set associative */
@@ -105,7 +98,7 @@ cpu2: cpu@10000 {
next-level-cache = <&l2_2>;
clocks = <&scmi_dvfs 1>;
- l2_2: l2-cache-2 {
+ l2_2: l2-cache {
compatible = "cache";
cache-level = <2>;
/* 8 ways set associative */
@@ -132,7 +125,7 @@ cpu3: cpu@10100 {
next-level-cache = <&l2_3>;
clocks = <&scmi_dvfs 1>;
- l2_3: l2-cache-3 {
+ l2_3: l2-cache {
compatible = "cache";
cache-level = <2>;
/* 8 ways set associative */
@@ -143,6 +136,13 @@ l2_3: l2-cache-3 {
next-level-cache = <&l3_0>;
};
};
+
+ l3_0: l3-cache {
+ compatible = "cache";
+ cache-level = <3>;
+ cache-size = <0x100000>;
+ cache-unified;
+ };
};
firmware {
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi
index 7251ad3..b46566f 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi
@@ -144,6 +144,19 @@ reg_usdhc2_vmmc: regulator-usdhc2 {
startup-delay-us = <20000>;
};
+ reg_usdhc2_vqmmc: regulator-usdhc2-vqmmc {
+ compatible = "regulator-gpio";
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_usdhc2_vsel>;
+ gpios = <&gpio1 4 GPIO_ACTIVE_HIGH>;
+ regulator-max-microvolt = <3300000>;
+ regulator-min-microvolt = <1800000>;
+ states = <1800000 0x1>,
+ <3300000 0x0>;
+ regulator-name = "PMIC_USDHC_VSELECT";
+ vin-supply = <®_nvcc_sd>;
+ };
+
reserved-memory {
#address-cells = <2>;
#size-cells = <2>;
@@ -269,7 +282,7 @@ &gpio1 {
"SODIMM_19",
"",
"",
- "",
+ "PMIC_USDHC_VSELECT",
"",
"",
"",
@@ -785,6 +798,7 @@ &usdhc2 {
pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_cd>;
pinctrl-3 = <&pinctrl_usdhc2_sleep>, <&pinctrl_usdhc2_cd_sleep>;
vmmc-supply = <®_usdhc2_vmmc>;
+ vqmmc-supply = <®_usdhc2_vqmmc>;
};
&wdog1 {
@@ -1206,13 +1220,17 @@ pinctrl_usdhc2_pwr_en: usdhc2pwrengrp {
<MX8MM_IOMUXC_NAND_CLE_GPIO3_IO5 0x6>; /* SODIMM 76 */
};
+ pinctrl_usdhc2_vsel: usdhc2vselgrp {
+ fsl,pins =
+ <MX8MM_IOMUXC_GPIO1_IO04_GPIO1_IO4 0x10>; /* PMIC_USDHC_VSELECT */
+ };
+
/*
* Note: Due to ERR050080 we use discrete external on-module resistors pulling-up to the
* on-module +V3.3_1.8_SD (LDO5) rail and explicitly disable the internal pull-ups here.
*/
pinctrl_usdhc2: usdhc2grp {
fsl,pins =
- <MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x10>,
<MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x90>, /* SODIMM 78 */
<MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x90>, /* SODIMM 74 */
<MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x90>, /* SODIMM 80 */
@@ -1223,7 +1241,6 @@ pinctrl_usdhc2: usdhc2grp {
pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp {
fsl,pins =
- <MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x10>,
<MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x94>,
<MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x94>,
<MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x94>,
@@ -1234,7 +1251,6 @@ pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp {
pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp {
fsl,pins =
- <MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x10>,
<MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x96>,
<MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x96>,
<MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x96>,
@@ -1246,7 +1262,6 @@ pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp {
/* Avoid backfeeding with removed card power */
pinctrl_usdhc2_sleep: usdhc2slpgrp {
fsl,pins =
- <MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x0>,
<MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x0>,
<MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x0>,
<MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x0>,
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi
index a1b75c9..dc0ccd7 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi
@@ -24,6 +24,20 @@ &clk {
fsl,operating-mode = "nominal";
};
+&gpu2d {
+ assigned-clocks = <&clk IMX8MP_CLK_GPU2D_CORE>;
+ assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>;
+ assigned-clock-rates = <800000000>;
+};
+
+&gpu3d {
+ assigned-clocks = <&clk IMX8MP_CLK_GPU3D_CORE>,
+ <&clk IMX8MP_CLK_GPU3D_SHADER_CORE>;
+ assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
+ <&clk IMX8MP_SYS_PLL1_800M>;
+ assigned-clock-rates = <800000000>, <800000000>;
+};
+
&pgc_hdmimix {
assigned-clocks = <&clk IMX8MP_CLK_HDMI_AXI>,
<&clk IMX8MP_CLK_HDMI_APB>;
@@ -46,6 +60,18 @@ &pgc_gpumix {
assigned-clock-rates = <600000000>, <300000000>;
};
+&pgc_mlmix {
+ assigned-clocks = <&clk IMX8MP_CLK_ML_CORE>,
+ <&clk IMX8MP_CLK_ML_AXI>,
+ <&clk IMX8MP_CLK_ML_AHB>;
+ assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
+ <&clk IMX8MP_SYS_PLL1_800M>,
+ <&clk IMX8MP_SYS_PLL1_800M>;
+ assigned-clock-rates = <800000000>,
+ <800000000>,
+ <300000000>;
+};
+
&media_blk_ctrl {
assigned-clocks = <&clk IMX8MP_CLK_MEDIA_AXI>,
<&clk IMX8MP_CLK_MEDIA_APB>,
diff --git a/arch/arm64/boot/dts/freescale/imx95.dtsi b/arch/arm64/boot/dts/freescale/imx95.dtsi
index 9bb26b4..59f057b 100644
--- a/arch/arm64/boot/dts/freescale/imx95.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx95.dtsi
@@ -1626,7 +1626,7 @@ pcie0: pcie@4c300000 {
reg = <0 0x4c300000 0 0x10000>,
<0 0x60100000 0 0xfe00000>,
<0 0x4c360000 0 0x10000>,
- <0 0x4c340000 0 0x2000>;
+ <0 0x4c340000 0 0x4000>;
reg-names = "dbi", "config", "atu", "app";
ranges = <0x81000000 0x0 0x00000000 0x0 0x6ff00000 0 0x00100000>,
<0x82000000 0x0 0x10000000 0x9 0x10000000 0 0x10000000>;
@@ -1673,7 +1673,7 @@ pcie0_ep: pcie-ep@4c300000 {
reg = <0 0x4c300000 0 0x10000>,
<0 0x4c360000 0 0x1000>,
<0 0x4c320000 0 0x1000>,
- <0 0x4c340000 0 0x2000>,
+ <0 0x4c340000 0 0x4000>,
<0 0x4c370000 0 0x10000>,
<0x9 0 1 0>;
reg-names = "dbi","atu", "dbi2", "app", "dma", "addr_space";
@@ -1700,7 +1700,7 @@ pcie1: pcie@4c380000 {
reg = <0 0x4c380000 0 0x10000>,
<8 0x80100000 0 0xfe00000>,
<0 0x4c3e0000 0 0x10000>,
- <0 0x4c3c0000 0 0x2000>;
+ <0 0x4c3c0000 0 0x4000>;
reg-names = "dbi", "config", "atu", "app";
ranges = <0x81000000 0 0x00000000 0x8 0x8ff00000 0 0x00100000>,
<0x82000000 0 0x10000000 0xa 0x10000000 0 0x10000000>;
@@ -1749,7 +1749,7 @@ pcie1_ep: pcie-ep@4c380000 {
reg = <0 0x4c380000 0 0x10000>,
<0 0x4c3e0000 0 0x1000>,
<0 0x4c3a0000 0 0x1000>,
- <0 0x4c3c0000 0 0x2000>,
+ <0 0x4c3c0000 0 0x4000>,
<0 0x4c3f0000 0 0x10000>,
<0xa 0 1 0>;
reg-names = "dbi", "atu", "dbi2", "app", "dma", "addr_space";
diff --git a/arch/arm64/boot/dts/st/stm32mp211.dtsi b/arch/arm64/boot/dts/st/stm32mp211.dtsi
index 6dd1377..bf888d6 100644
--- a/arch/arm64/boot/dts/st/stm32mp211.dtsi
+++ b/arch/arm64/boot/dts/st/stm32mp211.dtsi
@@ -116,11 +116,11 @@ syscfg: syscon@44230000 {
};
intc: interrupt-controller@4ac10000 {
- compatible = "arm,cortex-a7-gic";
+ compatible = "arm,gic-400";
reg = <0x4ac10000 0x0 0x1000>,
- <0x4ac20000 0x0 0x2000>,
- <0x4ac40000 0x0 0x2000>,
- <0x4ac60000 0x0 0x2000>;
+ <0x4ac20000 0x0 0x20000>,
+ <0x4ac40000 0x0 0x20000>,
+ <0x4ac60000 0x0 0x20000>;
#interrupt-cells = <3>;
interrupt-controller;
};
diff --git a/arch/arm64/boot/dts/st/stm32mp231.dtsi b/arch/arm64/boot/dts/st/stm32mp231.dtsi
index 8820d21..75697ac 100644
--- a/arch/arm64/boot/dts/st/stm32mp231.dtsi
+++ b/arch/arm64/boot/dts/st/stm32mp231.dtsi
@@ -1201,13 +1201,12 @@ exti2: interrupt-controller@46230000 {
};
intc: interrupt-controller@4ac10000 {
- compatible = "arm,cortex-a7-gic";
+ compatible = "arm,gic-400";
reg = <0x4ac10000 0x1000>,
- <0x4ac20000 0x2000>,
- <0x4ac40000 0x2000>,
- <0x4ac60000 0x2000>;
+ <0x4ac20000 0x20000>,
+ <0x4ac40000 0x20000>,
+ <0x4ac60000 0x20000>;
#interrupt-cells = <3>;
- #address-cells = <1>;
interrupt-controller;
};
};
diff --git a/arch/arm64/boot/dts/st/stm32mp251.dtsi b/arch/arm64/boot/dts/st/stm32mp251.dtsi
index f3c6cdf..87110f9 100644
--- a/arch/arm64/boot/dts/st/stm32mp251.dtsi
+++ b/arch/arm64/boot/dts/st/stm32mp251.dtsi
@@ -115,14 +115,13 @@ scmi_vdda18adc: regulator@7 {
};
intc: interrupt-controller@4ac00000 {
- compatible = "arm,cortex-a7-gic";
+ compatible = "arm,gic-400";
#interrupt-cells = <3>;
- #address-cells = <1>;
interrupt-controller;
reg = <0x0 0x4ac10000 0x0 0x1000>,
- <0x0 0x4ac20000 0x0 0x2000>,
- <0x0 0x4ac40000 0x0 0x2000>,
- <0x0 0x4ac60000 0x0 0x2000>;
+ <0x0 0x4ac20000 0x0 0x20000>,
+ <0x0 0x4ac40000 0x0 0x20000>,
+ <0x0 0x4ac60000 0x0 0x20000>;
};
psci {
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index d1b1a33..e4f7775 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -121,6 +121,15 @@
#define ESR_ELx_FSC_SEA_TTW(n) (0x14 + (n))
#define ESR_ELx_FSC_SECC (0x18)
#define ESR_ELx_FSC_SECC_TTW(n) (0x1c + (n))
+#define ESR_ELx_FSC_ADDRSZ (0x00)
+
+/*
+ * Annoyingly, the negative levels for Address size faults aren't laid out
+ * contiguously (or in the desired order)
+ */
+#define ESR_ELx_FSC_ADDRSZ_nL(n) ((n) == -1 ? 0x25 : 0x2C)
+#define ESR_ELx_FSC_ADDRSZ_L(n) ((n) < 0 ? ESR_ELx_FSC_ADDRSZ_nL(n) : \
+ (ESR_ELx_FSC_ADDRSZ + (n)))
/* Status codes for individual page table levels */
#define ESR_ELx_FSC_ACCESS_L(n) (ESR_ELx_FSC_ACCESS + (n))
@@ -161,8 +170,6 @@
#define ESR_ELx_Xs_MASK (GENMASK_ULL(4, 0))
/* ISS field definitions for exceptions taken in to Hyp */
-#define ESR_ELx_FSC_ADDRSZ (0x00)
-#define ESR_ELx_FSC_ADDRSZ_L(n) (ESR_ELx_FSC_ADDRSZ + (n))
#define ESR_ELx_CV (UL(1) << 24)
#define ESR_ELx_COND_SHIFT (20)
#define ESR_ELx_COND_MASK (UL(0xF) << ESR_ELx_COND_SHIFT)
@@ -464,6 +471,39 @@ static inline bool esr_fsc_is_access_flag_fault(unsigned long esr)
(esr == ESR_ELx_FSC_ACCESS_L(0));
}
+static inline bool esr_fsc_is_addr_sz_fault(unsigned long esr)
+{
+ esr &= ESR_ELx_FSC;
+
+ return (esr == ESR_ELx_FSC_ADDRSZ_L(3)) ||
+ (esr == ESR_ELx_FSC_ADDRSZ_L(2)) ||
+ (esr == ESR_ELx_FSC_ADDRSZ_L(1)) ||
+ (esr == ESR_ELx_FSC_ADDRSZ_L(0)) ||
+ (esr == ESR_ELx_FSC_ADDRSZ_L(-1));
+}
+
+static inline bool esr_fsc_is_sea_ttw(unsigned long esr)
+{
+ esr = esr & ESR_ELx_FSC;
+
+ return (esr == ESR_ELx_FSC_SEA_TTW(3)) ||
+ (esr == ESR_ELx_FSC_SEA_TTW(2)) ||
+ (esr == ESR_ELx_FSC_SEA_TTW(1)) ||
+ (esr == ESR_ELx_FSC_SEA_TTW(0)) ||
+ (esr == ESR_ELx_FSC_SEA_TTW(-1));
+}
+
+static inline bool esr_fsc_is_secc_ttw(unsigned long esr)
+{
+ esr = esr & ESR_ELx_FSC;
+
+ return (esr == ESR_ELx_FSC_SECC_TTW(3)) ||
+ (esr == ESR_ELx_FSC_SECC_TTW(2)) ||
+ (esr == ESR_ELx_FSC_SECC_TTW(1)) ||
+ (esr == ESR_ELx_FSC_SECC_TTW(0)) ||
+ (esr == ESR_ELx_FSC_SECC_TTW(-1));
+}
+
/* Indicate whether ESR.EC==0x1A is for an ERETAx instruction */
static inline bool esr_iss_is_eretax(unsigned long esr)
{
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index d7cf665..bd020fc2 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -305,7 +305,12 @@ static __always_inline unsigned long kvm_vcpu_get_hfar(const struct kvm_vcpu *vc
static __always_inline phys_addr_t kvm_vcpu_get_fault_ipa(const struct kvm_vcpu *vcpu)
{
- return ((phys_addr_t)vcpu->arch.fault.hpfar_el2 & HPFAR_MASK) << 8;
+ u64 hpfar = vcpu->arch.fault.hpfar_el2;
+
+ if (unlikely(!(hpfar & HPFAR_EL2_NS)))
+ return INVALID_GPA;
+
+ return FIELD_GET(HPFAR_EL2_FIPA, hpfar) << 12;
}
static inline u64 kvm_vcpu_get_disr(const struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e98cfe7..08ba91e6 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1588,4 +1588,9 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val);
#define kvm_has_s1poe(k) \
(kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP))
+static inline bool kvm_arch_has_irq_bypass(void)
+{
+ return true;
+}
+
#endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_ras.h b/arch/arm64/include/asm/kvm_ras.h
index 87e10d9..9398ade 100644
--- a/arch/arm64/include/asm/kvm_ras.h
+++ b/arch/arm64/include/asm/kvm_ras.h
@@ -14,7 +14,7 @@
* Was this synchronous external abort a RAS notification?
* Returns '0' for errors handled by some RAS subsystem, or -ENOENT.
*/
-static inline int kvm_handle_guest_sea(phys_addr_t addr, u64 esr)
+static inline int kvm_handle_guest_sea(void)
{
/* apei_claim_sea(NULL) expects to mask interrupts itself */
lockdep_assert_irqs_enabled();
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 30a29e8..6e8aa8e 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -94,17 +94,6 @@ static inline bool kaslr_requires_kpti(void)
return false;
}
- /*
- * Systems affected by Cavium erratum 24756 are incompatible
- * with KPTI.
- */
- if (IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) {
- extern const struct midr_range cavium_erratum_27456_cpus[];
-
- if (is_midr_in_range_list(cavium_erratum_27456_cpus))
- return false;
- }
-
return true;
}
diff --git a/arch/arm64/include/asm/rqspinlock.h b/arch/arm64/include/asm/rqspinlock.h
index 5b80785..9ea0a74 100644
--- a/arch/arm64/include/asm/rqspinlock.h
+++ b/arch/arm64/include/asm/rqspinlock.h
@@ -86,7 +86,7 @@
#endif
-#define res_smp_cond_load_acquire_timewait(v, c) smp_cond_load_acquire_timewait(v, c, 0, 1)
+#define res_smp_cond_load_acquire(v, c) smp_cond_load_acquire_timewait(v, c, 0, 1)
#include <asm-generic/rqspinlock.h>
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index b55f5f7..6b0ad50 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -335,7 +335,7 @@ static const struct midr_range cavium_erratum_23154_cpus[] = {
#endif
#ifdef CONFIG_CAVIUM_ERRATUM_27456
-const struct midr_range cavium_erratum_27456_cpus[] = {
+static const struct midr_range cavium_erratum_27456_cpus[] = {
/* Cavium ThunderX, T88 pass 1.x - 2.1 */
MIDR_RANGE(MIDR_THUNDERX, 0, 0, 1, 1),
/* Cavium ThunderX, T81 pass 1.0 */
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 5e3c4b5..2004b4f 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -47,10 +47,6 @@ PROVIDE(__pi_id_aa64smfr0_override = id_aa64smfr0_override);
PROVIDE(__pi_id_aa64zfr0_override = id_aa64zfr0_override);
PROVIDE(__pi_arm64_sw_feature_override = arm64_sw_feature_override);
PROVIDE(__pi_arm64_use_ng_mappings = arm64_use_ng_mappings);
-#ifdef CONFIG_CAVIUM_ERRATUM_27456
-PROVIDE(__pi_cavium_erratum_27456_cpus = cavium_erratum_27456_cpus);
-PROVIDE(__pi_is_midr_in_range_list = is_midr_in_range_list);
-#endif
PROVIDE(__pi__ctype = _ctype);
PROVIDE(__pi_memstart_offset_seed = memstart_offset_seed);
diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c
index e57b043..c6650cf 100644
--- a/arch/arm64/kernel/pi/map_kernel.c
+++ b/arch/arm64/kernel/pi/map_kernel.c
@@ -207,6 +207,29 @@ static void __init map_fdt(u64 fdt)
dsb(ishst);
}
+/*
+ * PI version of the Cavium Eratum 27456 detection, which makes it
+ * impossible to use non-global mappings.
+ */
+static bool __init ng_mappings_allowed(void)
+{
+ static const struct midr_range cavium_erratum_27456_cpus[] __initconst = {
+ /* Cavium ThunderX, T88 pass 1.x - 2.1 */
+ MIDR_RANGE(MIDR_THUNDERX, 0, 0, 1, 1),
+ /* Cavium ThunderX, T81 pass 1.0 */
+ MIDR_REV(MIDR_THUNDERX_81XX, 0, 0),
+ {},
+ };
+
+ for (const struct midr_range *r = cavium_erratum_27456_cpus; r->model; r++) {
+ if (midr_is_cpu_model_range(read_cpuid_id(), r->model,
+ r->rv_min, r->rv_max))
+ return false;
+ }
+
+ return true;
+}
+
asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
{
static char const chosen_str[] __initconst = "/chosen";
@@ -246,7 +269,7 @@ asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
u64 kaslr_seed = kaslr_early_init(fdt, chosen);
if (kaslr_seed && kaslr_requires_kpti())
- arm64_use_ng_mappings = true;
+ arm64_use_ng_mappings = ng_mappings_allowed();
kaslr_offset |= kaslr_seed & ~(MIN_KIMG_ALIGN - 1);
}
diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c
index b198dde..b607f6d 100644
--- a/arch/arm64/kernel/proton-pack.c
+++ b/arch/arm64/kernel/proton-pack.c
@@ -879,10 +879,12 @@ static u8 spectre_bhb_loop_affected(void)
static const struct midr_range spectre_bhb_k132_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_X3),
MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2),
+ {},
};
static const struct midr_range spectre_bhb_k38_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_A715),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A720),
+ {},
};
static const struct midr_range spectre_bhb_k32_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_A78),
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 68fec8c..19ca57d 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2743,11 +2743,6 @@ bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
return irqchip_in_kernel(kvm);
}
-bool kvm_arch_has_irq_bypass(void)
-{
- return true;
-}
-
int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
struct irq_bypass_producer *prod)
{
diff --git a/arch/arm64/kvm/hyp/include/hyp/fault.h b/arch/arm64/kvm/hyp/include/hyp/fault.h
index 17df945..fc573fc 100644
--- a/arch/arm64/kvm/hyp/include/hyp/fault.h
+++ b/arch/arm64/kvm/hyp/include/hyp/fault.h
@@ -12,6 +12,16 @@
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
+static inline bool __fault_safe_to_translate(u64 esr)
+{
+ u64 fsc = esr & ESR_ELx_FSC;
+
+ if (esr_fsc_is_sea_ttw(esr) || esr_fsc_is_secc_ttw(esr))
+ return false;
+
+ return !(fsc == ESR_ELx_FSC_EXTABT && (esr & ESR_ELx_FnV));
+}
+
static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
{
int ret;
@@ -44,34 +54,50 @@ static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
return true;
}
+/*
+ * Checks for the conditions when HPFAR_EL2 is written, per ARM ARM R_FKLWR.
+ */
+static inline bool __hpfar_valid(u64 esr)
+{
+ /*
+ * CPUs affected by ARM erratum #834220 may incorrectly report a
+ * stage-2 translation fault when a stage-1 permission fault occurs.
+ *
+ * Re-walk the page tables to determine if a stage-1 fault actually
+ * occurred.
+ */
+ if (cpus_have_final_cap(ARM64_WORKAROUND_834220) &&
+ esr_fsc_is_translation_fault(esr))
+ return false;
+
+ if (esr_fsc_is_translation_fault(esr) || esr_fsc_is_access_flag_fault(esr))
+ return true;
+
+ if ((esr & ESR_ELx_S1PTW) && esr_fsc_is_permission_fault(esr))
+ return true;
+
+ return esr_fsc_is_addr_sz_fault(esr);
+}
+
static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
{
- u64 hpfar, far;
+ u64 hpfar;
- far = read_sysreg_el2(SYS_FAR);
+ fault->far_el2 = read_sysreg_el2(SYS_FAR);
+ fault->hpfar_el2 = 0;
+
+ if (__hpfar_valid(esr))
+ hpfar = read_sysreg(hpfar_el2);
+ else if (unlikely(!__fault_safe_to_translate(esr)))
+ return true;
+ else if (!__translate_far_to_hpfar(fault->far_el2, &hpfar))
+ return false;
/*
- * The HPFAR can be invalid if the stage 2 fault did not
- * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
- * bit is clear) and one of the two following cases are true:
- * 1. The fault was due to a permission fault
- * 2. The processor carries errata 834220
- *
- * Therefore, for all non S1PTW faults where we either have a
- * permission fault or the errata workaround is enabled, we
- * resolve the IPA using the AT instruction.
+ * Hijack HPFAR_EL2.NS (RES0 in Non-secure) to indicate a valid
+ * HPFAR value.
*/
- if (!(esr & ESR_ELx_S1PTW) &&
- (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
- esr_fsc_is_permission_fault(esr))) {
- if (!__translate_far_to_hpfar(far, &hpfar))
- return false;
- } else {
- hpfar = read_sysreg(hpfar_el2);
- }
-
- fault->far_el2 = far;
- fault->hpfar_el2 = hpfar;
+ fault->hpfar_el2 = hpfar | HPFAR_EL2_NS;
return true;
}
diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c
index e433dfa..3369dd0 100644
--- a/arch/arm64/kvm/hyp/nvhe/ffa.c
+++ b/arch/arm64/kvm/hyp/nvhe/ffa.c
@@ -730,10 +730,10 @@ static void do_ffa_version(struct arm_smccc_res *res,
hyp_ffa_version = ffa_req_version;
}
- if (hyp_ffa_post_init())
+ if (hyp_ffa_post_init()) {
res->a0 = FFA_RET_NOT_SUPPORTED;
- else {
- has_version_negotiated = true;
+ } else {
+ smp_store_release(&has_version_negotiated, true);
res->a0 = hyp_ffa_version;
}
unlock:
@@ -809,7 +809,8 @@ bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id)
if (!is_ffa_call(func_id))
return false;
- if (!has_version_negotiated && func_id != FFA_VERSION) {
+ if (func_id != FFA_VERSION &&
+ !smp_load_acquire(&has_version_negotiated)) {
ffa_to_smccc_error(&res, FFA_RET_INVALID_PARAMETERS);
goto out_handled;
}
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index f34f11c..2a5284f 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -578,7 +578,14 @@ void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
return;
}
- addr = (fault.hpfar_el2 & HPFAR_MASK) << 8;
+
+ /*
+ * Yikes, we couldn't resolve the fault IPA. This should reinject an
+ * abort into the host when we figure out how to do that.
+ */
+ BUG_ON(!(fault.hpfar_el2 & HPFAR_EL2_NS));
+ addr = FIELD_GET(HPFAR_EL2_FIPA, fault.hpfar_el2) << 12;
+
ret = host_stage2_idmap(addr);
BUG_ON(ret && ret != -EAGAIN);
}
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 2feb6c6..754f2fe 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1794,9 +1794,28 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
gfn_t gfn;
int ret, idx;
+ /* Synchronous External Abort? */
+ if (kvm_vcpu_abt_issea(vcpu)) {
+ /*
+ * For RAS the host kernel may handle this abort.
+ * There is no need to pass the error into the guest.
+ */
+ if (kvm_handle_guest_sea())
+ kvm_inject_vabt(vcpu);
+
+ return 1;
+ }
+
esr = kvm_vcpu_get_esr(vcpu);
+ /*
+ * The fault IPA should be reliable at this point as we're not dealing
+ * with an SEA.
+ */
ipa = fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
+ if (KVM_BUG_ON(ipa == INVALID_GPA, vcpu->kvm))
+ return -EFAULT;
+
is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
if (esr_fsc_is_translation_fault(esr)) {
@@ -1818,18 +1837,6 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
}
}
- /* Synchronous External Abort? */
- if (kvm_vcpu_abt_issea(vcpu)) {
- /*
- * For RAS the host kernel may handle this abort.
- * There is no need to pass the error into the guest.
- */
- if (kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu)))
- kvm_inject_vabt(vcpu);
-
- return 1;
- }
-
trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu),
kvm_vcpu_get_hfar(vcpu), fault_ipa);
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index f947684..bdf044c 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -3536,3 +3536,10 @@
Field 4 P
Field 3:0 Align
EndSysreg
+
+Sysreg HPFAR_EL2 3 4 6 0 4
+Field 63 NS
+Res0 62:48
+Field 47:4 FIPA
+Res0 3:0
+EndSysreg
diff --git a/arch/hexagon/configs/comet_defconfig b/arch/hexagon/configs/comet_defconfig
index 469c025..c6108f0 100644
--- a/arch/hexagon/configs/comet_defconfig
+++ b/arch/hexagon/configs/comet_defconfig
@@ -72,9 +72,6 @@
CONFIG_CRYPTO_MD5=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
# CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_CCITT=y
-CONFIG_CRC16=y
-CONFIG_CRC_T10DIF=y
CONFIG_FRAME_WARN=0
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_FS=y
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 067c0b9..1a2cf01 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -73,6 +73,7 @@
select ARCH_SUPPORTS_RT
select ARCH_USE_BUILTIN_BSWAP
select ARCH_USE_CMPXCHG_LOCKREF
+ select ARCH_USE_MEMTEST
select ARCH_USE_QUEUED_RWLOCKS
select ARCH_USE_QUEUED_SPINLOCKS
select ARCH_WANT_DEFAULT_BPF_JIT
diff --git a/arch/loongarch/include/asm/fpu.h b/arch/loongarch/include/asm/fpu.h
index 3177674..45514f3 100644
--- a/arch/loongarch/include/asm/fpu.h
+++ b/arch/loongarch/include/asm/fpu.h
@@ -22,22 +22,29 @@
struct sigcontext;
#define kernel_fpu_available() cpu_has_fpu
-extern void kernel_fpu_begin(void);
-extern void kernel_fpu_end(void);
-extern void _init_fpu(unsigned int);
-extern void _save_fp(struct loongarch_fpu *);
-extern void _restore_fp(struct loongarch_fpu *);
+void kernel_fpu_begin(void);
+void kernel_fpu_end(void);
-extern void _save_lsx(struct loongarch_fpu *fpu);
-extern void _restore_lsx(struct loongarch_fpu *fpu);
-extern void _init_lsx_upper(void);
-extern void _restore_lsx_upper(struct loongarch_fpu *fpu);
+asmlinkage void _init_fpu(unsigned int);
+asmlinkage void _save_fp(struct loongarch_fpu *);
+asmlinkage void _restore_fp(struct loongarch_fpu *);
+asmlinkage int _save_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
+asmlinkage int _restore_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
-extern void _save_lasx(struct loongarch_fpu *fpu);
-extern void _restore_lasx(struct loongarch_fpu *fpu);
-extern void _init_lasx_upper(void);
-extern void _restore_lasx_upper(struct loongarch_fpu *fpu);
+asmlinkage void _save_lsx(struct loongarch_fpu *fpu);
+asmlinkage void _restore_lsx(struct loongarch_fpu *fpu);
+asmlinkage void _init_lsx_upper(void);
+asmlinkage void _restore_lsx_upper(struct loongarch_fpu *fpu);
+asmlinkage int _save_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
+asmlinkage int _restore_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
+
+asmlinkage void _save_lasx(struct loongarch_fpu *fpu);
+asmlinkage void _restore_lasx(struct loongarch_fpu *fpu);
+asmlinkage void _init_lasx_upper(void);
+asmlinkage void _restore_lasx_upper(struct loongarch_fpu *fpu);
+asmlinkage int _save_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
+asmlinkage int _restore_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
static inline void enable_lsx(void);
static inline void disable_lsx(void);
diff --git a/arch/loongarch/include/asm/lbt.h b/arch/loongarch/include/asm/lbt.h
index e671978..3856657 100644
--- a/arch/loongarch/include/asm/lbt.h
+++ b/arch/loongarch/include/asm/lbt.h
@@ -12,9 +12,13 @@
#include <asm/loongarch.h>
#include <asm/processor.h>
-extern void _init_lbt(void);
-extern void _save_lbt(struct loongarch_lbt *);
-extern void _restore_lbt(struct loongarch_lbt *);
+asmlinkage void _init_lbt(void);
+asmlinkage void _save_lbt(struct loongarch_lbt *);
+asmlinkage void _restore_lbt(struct loongarch_lbt *);
+asmlinkage int _save_lbt_context(void __user *regs, void __user *eflags);
+asmlinkage int _restore_lbt_context(void __user *regs, void __user *eflags);
+asmlinkage int _save_ftop_context(void __user *ftop);
+asmlinkage int _restore_ftop_context(void __user *ftop);
static inline int is_lbt_enabled(void)
{
diff --git a/arch/loongarch/include/asm/ptrace.h b/arch/loongarch/include/asm/ptrace.h
index f3ddaed..a5b63c8 100644
--- a/arch/loongarch/include/asm/ptrace.h
+++ b/arch/loongarch/include/asm/ptrace.h
@@ -33,9 +33,9 @@ struct pt_regs {
unsigned long __last[];
} __aligned(8);
-static inline int regs_irqs_disabled(struct pt_regs *regs)
+static __always_inline bool regs_irqs_disabled(struct pt_regs *regs)
{
- return arch_irqs_disabled_flags(regs->csr_prmd);
+ return !(regs->csr_prmd & CSR_PRMD_PIE);
}
static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index 4853e8b..f9dcaa6 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -21,10 +21,10 @@
obj-$(CONFIG_ARCH_STRICT_ALIGN) += unaligned.o
-CFLAGS_module.o += $(call cc-option,-Wno-override-init,)
-CFLAGS_syscall.o += $(call cc-option,-Wno-override-init,)
-CFLAGS_traps.o += $(call cc-option,-Wno-override-init,)
-CFLAGS_perf_event.o += $(call cc-option,-Wno-override-init,)
+CFLAGS_module.o += $(call cc-disable-warning, override-init)
+CFLAGS_syscall.o += $(call cc-disable-warning, override-init)
+CFLAGS_traps.o += $(call cc-disable-warning, override-init)
+CFLAGS_perf_event.o += $(call cc-disable-warning, override-init)
ifdef CONFIG_FUNCTION_TRACER
ifndef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S
index 6ab6401..28caf41 100644
--- a/arch/loongarch/kernel/fpu.S
+++ b/arch/loongarch/kernel/fpu.S
@@ -458,6 +458,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_save_fp_context)
+EXPORT_SYMBOL_GPL(_save_fp_context)
/*
* a0: fpregs
@@ -471,6 +472,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_restore_fp_context)
+EXPORT_SYMBOL_GPL(_restore_fp_context)
/*
* a0: fpregs
@@ -484,6 +486,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_save_lsx_context)
+EXPORT_SYMBOL_GPL(_save_lsx_context)
/*
* a0: fpregs
@@ -497,6 +500,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_restore_lsx_context)
+EXPORT_SYMBOL_GPL(_restore_lsx_context)
/*
* a0: fpregs
@@ -510,6 +514,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_save_lasx_context)
+EXPORT_SYMBOL_GPL(_save_lasx_context)
/*
* a0: fpregs
@@ -523,6 +528,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_restore_lasx_context)
+EXPORT_SYMBOL_GPL(_restore_lasx_context)
.L_fpu_fault:
li.w a0, -EFAULT # failure
diff --git a/arch/loongarch/kernel/lbt.S b/arch/loongarch/kernel/lbt.S
index 001f061d..7167891 100644
--- a/arch/loongarch/kernel/lbt.S
+++ b/arch/loongarch/kernel/lbt.S
@@ -90,6 +90,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_save_lbt_context)
+EXPORT_SYMBOL_GPL(_save_lbt_context)
/*
* a0: scr
@@ -110,6 +111,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_restore_lbt_context)
+EXPORT_SYMBOL_GPL(_restore_lbt_context)
/*
* a0: ftop
@@ -120,6 +122,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_save_ftop_context)
+EXPORT_SYMBOL_GPL(_save_ftop_context)
/*
* a0: ftop
@@ -150,6 +153,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_restore_ftop_context)
+EXPORT_SYMBOL_GPL(_restore_ftop_context)
.L_lbt_fault:
li.w a0, -EFAULT # failure
diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c
index 7a555b6..4740cb5 100644
--- a/arch/loongarch/kernel/signal.c
+++ b/arch/loongarch/kernel/signal.c
@@ -51,27 +51,6 @@
#define lock_lbt_owner() ({ preempt_disable(); pagefault_disable(); })
#define unlock_lbt_owner() ({ pagefault_enable(); preempt_enable(); })
-/* Assembly functions to move context to/from the FPU */
-extern asmlinkage int
-_save_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
-extern asmlinkage int
-_restore_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
-extern asmlinkage int
-_save_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-extern asmlinkage int
-_restore_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-extern asmlinkage int
-_save_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-extern asmlinkage int
-_restore_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-
-#ifdef CONFIG_CPU_HAS_LBT
-extern asmlinkage int _save_lbt_context(void __user *regs, void __user *eflags);
-extern asmlinkage int _restore_lbt_context(void __user *regs, void __user *eflags);
-extern asmlinkage int _save_ftop_context(void __user *ftop);
-extern asmlinkage int _restore_ftop_context(void __user *ftop);
-#endif
-
struct rt_sigframe {
struct siginfo rs_info;
struct ucontext rs_uctx;
diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c
index 2ec3106..47fc2de 100644
--- a/arch/loongarch/kernel/traps.c
+++ b/arch/loongarch/kernel/traps.c
@@ -553,9 +553,10 @@ asmlinkage void noinstr do_ale(struct pt_regs *regs)
die_if_kernel("Kernel ale access", regs);
force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr);
#else
+ bool pie = regs_irqs_disabled(regs);
unsigned int *pc;
- if (regs->csr_prmd & CSR_PRMD_PIE)
+ if (!pie)
local_irq_enable();
perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, regs->csr_badvaddr);
@@ -582,7 +583,7 @@ asmlinkage void noinstr do_ale(struct pt_regs *regs)
die_if_kernel("Kernel ale access", regs);
force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr);
out:
- if (regs->csr_prmd & CSR_PRMD_PIE)
+ if (!pie)
local_irq_disable();
#endif
irqentry_exit(regs, state);
@@ -621,12 +622,13 @@ static void bug_handler(struct pt_regs *regs)
asmlinkage void noinstr do_bce(struct pt_regs *regs)
{
bool user = user_mode(regs);
+ bool pie = regs_irqs_disabled(regs);
unsigned long era = exception_era(regs);
u64 badv = 0, lower = 0, upper = ULONG_MAX;
union loongarch_instruction insn;
irqentry_state_t state = irqentry_enter(regs);
- if (regs->csr_prmd & CSR_PRMD_PIE)
+ if (!pie)
local_irq_enable();
current->thread.trap_nr = read_csr_excode();
@@ -692,7 +694,7 @@ asmlinkage void noinstr do_bce(struct pt_regs *regs)
force_sig_bnderr((void __user *)badv, (void __user *)lower, (void __user *)upper);
out:
- if (regs->csr_prmd & CSR_PRMD_PIE)
+ if (!pie)
local_irq_disable();
irqentry_exit(regs, state);
@@ -710,11 +712,12 @@ asmlinkage void noinstr do_bce(struct pt_regs *regs)
asmlinkage void noinstr do_bp(struct pt_regs *regs)
{
bool user = user_mode(regs);
+ bool pie = regs_irqs_disabled(regs);
unsigned int opcode, bcode;
unsigned long era = exception_era(regs);
irqentry_state_t state = irqentry_enter(regs);
- if (regs->csr_prmd & CSR_PRMD_PIE)
+ if (!pie)
local_irq_enable();
if (__get_inst(&opcode, (u32 *)era, user))
@@ -780,7 +783,7 @@ asmlinkage void noinstr do_bp(struct pt_regs *regs)
}
out:
- if (regs->csr_prmd & CSR_PRMD_PIE)
+ if (!pie)
local_irq_disable();
irqentry_exit(regs, state);
@@ -1015,6 +1018,7 @@ static void init_restore_lbt(void)
asmlinkage void noinstr do_lbt(struct pt_regs *regs)
{
+ bool pie = regs_irqs_disabled(regs);
irqentry_state_t state = irqentry_enter(regs);
/*
@@ -1024,7 +1028,7 @@ asmlinkage void noinstr do_lbt(struct pt_regs *regs)
* (including the user using 'MOVGR2GCSR' to turn on TM, which
* will not trigger the BTE), we need to check PRMD first.
*/
- if (regs->csr_prmd & CSR_PRMD_PIE)
+ if (!pie)
local_irq_enable();
if (!cpu_has_lbt) {
@@ -1038,7 +1042,7 @@ asmlinkage void noinstr do_lbt(struct pt_regs *regs)
preempt_enable();
out:
- if (regs->csr_prmd & CSR_PRMD_PIE)
+ if (!pie)
local_irq_disable();
irqentry_exit(regs, state);
diff --git a/arch/loongarch/kvm/Makefile b/arch/loongarch/kvm/Makefile
index f4c8e35..cb41d92 100644
--- a/arch/loongarch/kvm/Makefile
+++ b/arch/loongarch/kvm/Makefile
@@ -21,4 +21,4 @@
kvm-y += intc/pch_pic.o
kvm-y += irqfd.o
-CFLAGS_exit.o += $(call cc-option,-Wno-override-init,)
+CFLAGS_exit.o += $(call cc-disable-warning, override-init)
diff --git a/arch/loongarch/kvm/intc/ipi.c b/arch/loongarch/kvm/intc/ipi.c
index 93f4acd..fe734dc 100644
--- a/arch/loongarch/kvm/intc/ipi.c
+++ b/arch/loongarch/kvm/intc/ipi.c
@@ -111,7 +111,7 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val);
srcu_read_unlock(&vcpu->kvm->srcu, idx);
if (unlikely(ret)) {
- kvm_err("%s: : read date from addr %llx failed\n", __func__, addr);
+ kvm_err("%s: : read data from addr %llx failed\n", __func__, addr);
return ret;
}
/* Construct the mask by scanning the bit 27-30 */
@@ -127,7 +127,7 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val);
srcu_read_unlock(&vcpu->kvm->srcu, idx);
if (unlikely(ret))
- kvm_err("%s: : write date to addr %llx failed\n", __func__, addr);
+ kvm_err("%s: : write data to addr %llx failed\n", __func__, addr);
return ret;
}
diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c
index d165cd3..80ea63d 100644
--- a/arch/loongarch/kvm/main.c
+++ b/arch/loongarch/kvm/main.c
@@ -296,10 +296,10 @@ int kvm_arch_enable_virtualization_cpu(void)
/*
* Enable virtualization features granting guest direct control of
* certain features:
- * GCI=2: Trap on init or unimplement cache instruction.
+ * GCI=2: Trap on init or unimplemented cache instruction.
* TORU=0: Trap on Root Unimplement.
* CACTRL=1: Root control cache.
- * TOP=0: Trap on Previlege.
+ * TOP=0: Trap on Privilege.
* TOE=0: Trap on Exception.
* TIT=0: Trap on Timer.
*/
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 8e427b3..5af32ec 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -294,6 +294,7 @@ static int kvm_pre_enter_guest(struct kvm_vcpu *vcpu)
vcpu->arch.aux_inuse &= ~KVM_LARCH_SWCSR_LATEST;
if (kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending()) {
+ kvm_lose_pmu(vcpu);
/* make sure the vcpu mode has been written */
smp_store_mb(vcpu->mode, OUTSIDE_GUEST_MODE);
local_irq_enable();
@@ -902,6 +903,13 @@ static int kvm_set_one_reg(struct kvm_vcpu *vcpu,
vcpu->arch.st.guest_addr = 0;
memset(&vcpu->arch.irq_pending, 0, sizeof(vcpu->arch.irq_pending));
memset(&vcpu->arch.irq_clear, 0, sizeof(vcpu->arch.irq_clear));
+
+ /*
+ * When vCPU reset, clear the ESTAT and GINTC registers
+ * Other CSR registers are cleared with function _kvm_setcsr().
+ */
+ kvm_write_sw_gcsr(vcpu->arch.csr, LOONGARCH_CSR_GINTC, 0);
+ kvm_write_sw_gcsr(vcpu->arch.csr, LOONGARCH_CSR_ESTAT, 0);
break;
default:
ret = -EINVAL;
diff --git a/arch/loongarch/mm/hugetlbpage.c b/arch/loongarch/mm/hugetlbpage.c
index e406890..cea84d7f 100644
--- a/arch/loongarch/mm/hugetlbpage.c
+++ b/arch/loongarch/mm/hugetlbpage.c
@@ -47,7 +47,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
pmd = pmd_offset(pud, addr);
}
}
- return (pte_t *) pmd;
+ return pmd_none(pmdp_get(pmd)) ? NULL : (pte_t *) pmd;
}
uint64_t pmd_to_entrylo(unsigned long pmd_val)
diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c
index fdb7f73..06f11d9 100644
--- a/arch/loongarch/mm/init.c
+++ b/arch/loongarch/mm/init.c
@@ -65,9 +65,6 @@ void __init paging_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
-#ifdef CONFIG_ZONE_DMA
- max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
-#endif
#ifdef CONFIG_ZONE_DMA32
max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
#endif
diff --git a/arch/m68k/configs/amcore_defconfig b/arch/m68k/configs/amcore_defconfig
index 67a0d15..110279a 100644
--- a/arch/m68k/configs/amcore_defconfig
+++ b/arch/m68k/configs/amcore_defconfig
@@ -89,4 +89,3 @@
# CONFIG_CRYPTO_ECHAINIV is not set
CONFIG_CRYPTO_ANSI_CPRNG=y
# CONFIG_CRYPTO_HW is not set
-CONFIG_CRC16=y
diff --git a/arch/mips/configs/ath79_defconfig b/arch/mips/configs/ath79_defconfig
index 8caa03a..cba0b85 100644
--- a/arch/mips/configs/ath79_defconfig
+++ b/arch/mips/configs/ath79_defconfig
@@ -82,7 +82,6 @@
# CONFIG_IOMMU_SUPPORT is not set
# CONFIG_DNOTIFY is not set
# CONFIG_PROC_PAGE_MONITOR is not set
-CONFIG_CRC_ITU_T=m
CONFIG_STRIP_ASM_SYMS=y
CONFIG_DEBUG_FS=y
# CONFIG_SCHED_DEBUG is not set
diff --git a/arch/mips/configs/bigsur_defconfig b/arch/mips/configs/bigsur_defconfig
index fe28263..8f7c368 100644
--- a/arch/mips/configs/bigsur_defconfig
+++ b/arch/mips/configs/bigsur_defconfig
@@ -238,7 +238,6 @@
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_LZO=m
-CONFIG_CRC_T10DIF=m
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_MEMORY_INIT=y
CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/mips/configs/fuloong2e_defconfig b/arch/mips/configs/fuloong2e_defconfig
index 5ab149c..114fcd6 100644
--- a/arch/mips/configs/fuloong2e_defconfig
+++ b/arch/mips/configs/fuloong2e_defconfig
@@ -218,4 +218,3 @@
CONFIG_CRYPTO_DEFLATE=m
CONFIG_CRYPTO_LZO=m
# CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_CCITT=y
diff --git a/arch/mips/configs/ip22_defconfig b/arch/mips/configs/ip22_defconfig
index 31ca93d..f1a8ccf 100644
--- a/arch/mips/configs/ip22_defconfig
+++ b/arch/mips/configs/ip22_defconfig
@@ -326,5 +326,4 @@
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_LZO=m
# CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=m
CONFIG_DEBUG_MEMORY_INIT=y
diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig
index b8907b3..5d07994 100644
--- a/arch/mips/configs/ip27_defconfig
+++ b/arch/mips/configs/ip27_defconfig
@@ -317,4 +317,3 @@
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_LZO=m
-CONFIG_CRC_T10DIF=m
diff --git a/arch/mips/configs/ip30_defconfig b/arch/mips/configs/ip30_defconfig
index 270181a..a4524e7 100644
--- a/arch/mips/configs/ip30_defconfig
+++ b/arch/mips/configs/ip30_defconfig
@@ -179,4 +179,3 @@
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_LZO=m
-CONFIG_CRC_T10DIF=m
diff --git a/arch/mips/configs/ip32_defconfig b/arch/mips/configs/ip32_defconfig
index 121e7e4..d8ac114 100644
--- a/arch/mips/configs/ip32_defconfig
+++ b/arch/mips/configs/ip32_defconfig
@@ -177,7 +177,6 @@
CONFIG_CRYPTO_TEA=y
CONFIG_CRYPTO_TWOFISH=y
CONFIG_CRYPTO_DEFLATE=y
-CONFIG_CRC_T10DIF=y
CONFIG_FONTS=y
CONFIG_FONT_8x8=y
CONFIG_FONT_8x16=y
diff --git a/arch/mips/configs/omega2p_defconfig b/arch/mips/configs/omega2p_defconfig
index 128f9ab..e2bcdfd 100644
--- a/arch/mips/configs/omega2p_defconfig
+++ b/arch/mips/configs/omega2p_defconfig
@@ -111,7 +111,6 @@
CONFIG_NLS_UTF8=y
CONFIG_CRYPTO_DEFLATE=y
CONFIG_CRYPTO_LZO=y
-CONFIG_CRC16=y
CONFIG_XZ_DEC=y
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
diff --git a/arch/mips/configs/rb532_defconfig b/arch/mips/configs/rb532_defconfig
index 0261969..42b161d 100644
--- a/arch/mips/configs/rb532_defconfig
+++ b/arch/mips/configs/rb532_defconfig
@@ -155,5 +155,4 @@
CONFIG_SQUASHFS=y
CONFIG_CRYPTO_TEST=m
# CONFIG_CRYPTO_HW is not set
-CONFIG_CRC16=m
CONFIG_STRIP_ASM_SYMS=y
diff --git a/arch/mips/configs/rt305x_defconfig b/arch/mips/configs/rt305x_defconfig
index 8404e0a..8f9701e 100644
--- a/arch/mips/configs/rt305x_defconfig
+++ b/arch/mips/configs/rt305x_defconfig
@@ -128,7 +128,6 @@
# CONFIG_SQUASHFS_ZLIB is not set
CONFIG_SQUASHFS_XZ=y
CONFIG_CRYPTO_ARC4=m
-CONFIG_CRC_ITU_T=m
# CONFIG_XZ_DEC_X86 is not set
# CONFIG_XZ_DEC_POWERPC is not set
# CONFIG_XZ_DEC_IA64 is not set
diff --git a/arch/mips/configs/sb1250_swarm_defconfig b/arch/mips/configs/sb1250_swarm_defconfig
index ce855b6..ae2afff 100644
--- a/arch/mips/configs/sb1250_swarm_defconfig
+++ b/arch/mips/configs/sb1250_swarm_defconfig
@@ -99,4 +99,3 @@
CONFIG_CRYPTO_DEFLATE=m
CONFIG_CRYPTO_LZO=m
# CONFIG_CRYPTO_HW is not set
-CONFIG_CRC16=m
diff --git a/arch/mips/configs/vocore2_defconfig b/arch/mips/configs/vocore2_defconfig
index 917967f..2a9a9b1 100644
--- a/arch/mips/configs/vocore2_defconfig
+++ b/arch/mips/configs/vocore2_defconfig
@@ -111,7 +111,6 @@
CONFIG_NLS_UTF8=y
CONFIG_CRYPTO_DEFLATE=y
CONFIG_CRYPTO_LZO=y
-CONFIG_CRC16=y
CONFIG_XZ_DEC=y
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
diff --git a/arch/mips/configs/xway_defconfig b/arch/mips/configs/xway_defconfig
index 7b91edf..aae8497 100644
--- a/arch/mips/configs/xway_defconfig
+++ b/arch/mips/configs/xway_defconfig
@@ -140,7 +140,6 @@
# CONFIG_SQUASHFS_ZLIB is not set
CONFIG_SQUASHFS_XZ=y
CONFIG_CRYPTO_ARC4=m
-CONFIG_CRC_ITU_T=m
CONFIG_PRINTK_TIME=y
CONFIG_STRIP_ASM_SYMS=y
CONFIG_DEBUG_FS=y
diff --git a/arch/mips/include/asm/idle.h b/arch/mips/include/asm/idle.h
index 0992cad..c7d7580 100644
--- a/arch/mips/include/asm/idle.h
+++ b/arch/mips/include/asm/idle.h
@@ -6,11 +6,10 @@
#include <linux/linkage.h>
extern void (*cpu_wait)(void);
-extern void r4k_wait(void);
-extern asmlinkage void __r4k_wait(void);
+extern asmlinkage void r4k_wait(void);
extern void r4k_wait_irqoff(void);
-static inline int using_rollback_handler(void)
+static inline int using_skipover_handler(void)
{
return cpu_wait == r4k_wait;
}
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index 85fa996..ef72c46 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -65,7 +65,8 @@ static inline void instruction_pointer_set(struct pt_regs *regs,
/* Query offset/name of register from its name/offset */
extern int regs_query_register_offset(const char *name);
-#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last))
+#define MAX_REG_OFFSET \
+ (offsetof(struct pt_regs, __last) - sizeof(unsigned long))
/**
* regs_get_register() - get register value from its offset
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index a572ce3..08c0a01 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -104,48 +104,59 @@
__FINIT
- .align 5 /* 32 byte rollback region */
-LEAF(__r4k_wait)
- .set push
- .set noreorder
- /* start of rollback region */
- LONG_L t0, TI_FLAGS($28)
- nop
- andi t0, _TIF_NEED_RESCHED
- bnez t0, 1f
- nop
- nop
- nop
-#ifdef CONFIG_CPU_MICROMIPS
- nop
- nop
- nop
- nop
-#endif
+ .section .cpuidle.text,"ax"
+ /* Align to 32 bytes for the maximum idle interrupt region size. */
+ .align 5
+LEAF(r4k_wait)
+ /* Keep the ISA bit clear for calculations on local labels here. */
+0: .fill 0
+ /* Start of idle interrupt region. */
+ local_irq_enable
+ /*
+ * If an interrupt lands here, before going idle on the next
+ * instruction, we must *NOT* go idle since the interrupt could
+ * have set TIF_NEED_RESCHED or caused a timer to need resched.
+ * Fall through -- see skipover_handler below -- and have the
+ * idle loop take care of things.
+ */
+1: .fill 0
+ /* The R2 EI/EHB sequence takes 8 bytes, otherwise pad up. */
+ .if 1b - 0b > 32
+ .error "overlong idle interrupt region"
+ .elseif 1b - 0b > 8
+ .align 4
+ .endif
+2: .fill 0
+ .equ r4k_wait_idle_size, 2b - 0b
+ /* End of idle interrupt region; size has to be a power of 2. */
.set MIPS_ISA_ARCH_LEVEL_RAW
+r4k_wait_insn:
wait
- /* end of rollback region (the region size must be power of two) */
-1:
+r4k_wait_exit:
+ .set mips0
+ local_irq_disable
jr ra
- nop
- .set pop
- END(__r4k_wait)
+ END(r4k_wait)
+ .previous
- .macro BUILD_ROLLBACK_PROLOGUE handler
- FEXPORT(rollback_\handler)
+ .macro BUILD_SKIPOVER_PROLOGUE handler
+ FEXPORT(skipover_\handler)
.set push
.set noat
MFC0 k0, CP0_EPC
- PTR_LA k1, __r4k_wait
- ori k0, 0x1f /* 32 byte rollback region */
- xori k0, 0x1f
+ /* Subtract/add 2 to let the ISA bit propagate through the mask. */
+ PTR_LA k1, r4k_wait_insn - 2
+ ori k0, r4k_wait_idle_size - 2
+ .set noreorder
bne k0, k1, \handler
+ PTR_ADDIU k0, r4k_wait_exit - r4k_wait_insn + 2
+ .set reorder
MTC0 k0, CP0_EPC
.set pop
.endm
.align 5
-BUILD_ROLLBACK_PROLOGUE handle_int
+BUILD_SKIPOVER_PROLOGUE handle_int
NESTED(handle_int, PT_SIZE, sp)
.cfi_signal_frame
#ifdef CONFIG_TRACE_IRQFLAGS
@@ -265,7 +276,7 @@
* This prototype is copied to ebase + n*IntCtl.VS and patched
* to invoke the handler
*/
-BUILD_ROLLBACK_PROLOGUE except_vec_vi
+BUILD_SKIPOVER_PROLOGUE except_vec_vi
NESTED(except_vec_vi, 0, sp)
SAVE_SOME docfi=1
SAVE_AT docfi=1
diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
index 5abc8b7..80e8a04a 100644
--- a/arch/mips/kernel/idle.c
+++ b/arch/mips/kernel/idle.c
@@ -35,13 +35,6 @@ static void __cpuidle r3081_wait(void)
write_c0_conf(cfg | R30XX_CONF_HALT);
}
-void __cpuidle r4k_wait(void)
-{
- raw_local_irq_enable();
- __r4k_wait();
- raw_local_irq_disable();
-}
-
/*
* This variant is preferable as it allows testing need_resched and going to
* sleep depending on the outcome atomically. Unfortunately the "It is
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index e85bd08..cc26d56 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -332,6 +332,8 @@ static void __init cps_prepare_cpus(unsigned int max_cpus)
mips_cps_cluster_bootcfg = kcalloc(nclusters,
sizeof(*mips_cps_cluster_bootcfg),
GFP_KERNEL);
+ if (!mips_cps_cluster_bootcfg)
+ goto err_out;
if (nclusters > 1)
mips_cm_update_property();
@@ -348,6 +350,8 @@ static void __init cps_prepare_cpus(unsigned int max_cpus)
mips_cps_cluster_bootcfg[cl].core_power =
kcalloc(BITS_TO_LONGS(ncores), sizeof(unsigned long),
GFP_KERNEL);
+ if (!mips_cps_cluster_bootcfg[cl].core_power)
+ goto err_out;
/* Allocate VPE boot configuration structs */
for (c = 0; c < ncores; c++) {
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 39e248d0..8ec1e18 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -77,7 +77,7 @@
#include "access-helper.h"
extern void check_wait(void);
-extern asmlinkage void rollback_handle_int(void);
+extern asmlinkage void skipover_handle_int(void);
extern asmlinkage void handle_int(void);
extern asmlinkage void handle_adel(void);
extern asmlinkage void handle_ades(void);
@@ -2066,7 +2066,7 @@ void *set_vi_handler(int n, vi_handler_t addr)
{
extern const u8 except_vec_vi[];
extern const u8 except_vec_vi_ori[], except_vec_vi_end[];
- extern const u8 rollback_except_vec_vi[];
+ extern const u8 skipover_except_vec_vi[];
unsigned long handler;
unsigned long old_handler = vi_handlers[n];
int srssets = current_cpu_data.srsets;
@@ -2095,7 +2095,7 @@ void *set_vi_handler(int n, vi_handler_t addr)
change_c0_srsmap(0xf << n*4, 0 << n*4);
}
- vec_start = using_rollback_handler() ? rollback_except_vec_vi :
+ vec_start = using_skipover_handler() ? skipover_except_vec_vi :
except_vec_vi;
#if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_BIG_ENDIAN)
ori_offset = except_vec_vi_ori - vec_start + 2;
@@ -2426,8 +2426,8 @@ void __init trap_init(void)
if (board_be_init)
board_be_init();
- set_except_vector(EXCCODE_INT, using_rollback_handler() ?
- rollback_handle_int : handle_int);
+ set_except_vector(EXCCODE_INT, using_skipover_handler() ?
+ skipover_handle_int : handle_int);
set_except_vector(EXCCODE_MOD, handle_tlbm);
set_except_vector(EXCCODE_TLBL, handle_tlbl);
set_except_vector(EXCCODE_TLBS, handle_tlbs);
diff --git a/arch/openrisc/include/asm/cacheflush.h b/arch/openrisc/include/asm/cacheflush.h
index 984c331..0e60af4 100644
--- a/arch/openrisc/include/asm/cacheflush.h
+++ b/arch/openrisc/include/asm/cacheflush.h
@@ -23,6 +23,9 @@
*/
extern void local_dcache_page_flush(struct page *page);
extern void local_icache_page_inv(struct page *page);
+extern void local_dcache_range_flush(unsigned long start, unsigned long end);
+extern void local_dcache_range_inv(unsigned long start, unsigned long end);
+extern void local_icache_range_inv(unsigned long start, unsigned long end);
/*
* Data cache flushing always happen on the local cpu. Instruction cache
@@ -39,6 +42,20 @@ extern void smp_icache_page_inv(struct page *page);
#endif /* CONFIG_SMP */
/*
+ * Even if the actual block size is larger than L1_CACHE_BYTES, paddr
+ * can be incremented by L1_CACHE_BYTES. When paddr is written to the
+ * invalidate register, the entire cache line encompassing this address
+ * is invalidated. Each subsequent reference to the same cache line will
+ * not affect the invalidation process.
+ */
+#define local_dcache_block_flush(addr) \
+ local_dcache_range_flush(addr, addr + L1_CACHE_BYTES)
+#define local_dcache_block_inv(addr) \
+ local_dcache_range_inv(addr, addr + L1_CACHE_BYTES)
+#define local_icache_block_inv(addr) \
+ local_icache_range_inv(addr, addr + L1_CACHE_BYTES)
+
+/*
* Synchronizes caches. Whenever a cpu writes executable code to memory, this
* should be called to make sure the processor sees the newly written code.
*/
diff --git a/arch/openrisc/include/asm/cpuinfo.h b/arch/openrisc/include/asm/cpuinfo.h
index 5e47441..3cfc4cf 100644
--- a/arch/openrisc/include/asm/cpuinfo.h
+++ b/arch/openrisc/include/asm/cpuinfo.h
@@ -15,16 +15,21 @@
#ifndef __ASM_OPENRISC_CPUINFO_H
#define __ASM_OPENRISC_CPUINFO_H
+#include <asm/spr.h>
+#include <asm/spr_defs.h>
+
+struct cache_desc {
+ u32 size;
+ u32 sets;
+ u32 block_size;
+ u32 ways;
+};
+
struct cpuinfo_or1k {
u32 clock_frequency;
- u32 icache_size;
- u32 icache_block_size;
- u32 icache_ways;
-
- u32 dcache_size;
- u32 dcache_block_size;
- u32 dcache_ways;
+ struct cache_desc icache;
+ struct cache_desc dcache;
u16 coreid;
};
@@ -32,4 +37,9 @@ struct cpuinfo_or1k {
extern struct cpuinfo_or1k cpuinfo_or1k[NR_CPUS];
extern void setup_cpuinfo(void);
+/*
+ * Check if the cache component exists.
+ */
+extern bool cpu_cache_is_present(const unsigned int cache_type);
+
#endif /* __ASM_OPENRISC_CPUINFO_H */
diff --git a/arch/openrisc/kernel/Makefile b/arch/openrisc/kernel/Makefile
index 7912916..e4c7d9b 100644
--- a/arch/openrisc/kernel/Makefile
+++ b/arch/openrisc/kernel/Makefile
@@ -7,7 +7,7 @@
obj-y := head.o setup.o or32_ksyms.o process.o dma.o \
traps.o time.o irq.o entry.o ptrace.o signal.o \
- sys_call_table.o unwinder.o
+ sys_call_table.o unwinder.o cacheinfo.o
obj-$(CONFIG_SMP) += smp.o sync-timer.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
diff --git a/arch/openrisc/kernel/cacheinfo.c b/arch/openrisc/kernel/cacheinfo.c
new file mode 100644
index 0000000..6123054
--- /dev/null
+++ b/arch/openrisc/kernel/cacheinfo.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * OpenRISC cacheinfo support
+ *
+ * Based on work done for MIPS and LoongArch. All original copyrights
+ * apply as per the original source declaration.
+ *
+ * OpenRISC implementation:
+ * Copyright (C) 2025 Sahil Siddiq <sahilcdq@proton.me>
+ */
+
+#include <linux/cacheinfo.h>
+#include <asm/cpuinfo.h>
+#include <asm/spr.h>
+#include <asm/spr_defs.h>
+
+static inline void ci_leaf_init(struct cacheinfo *this_leaf, enum cache_type type,
+ unsigned int level, struct cache_desc *cache, int cpu)
+{
+ this_leaf->type = type;
+ this_leaf->level = level;
+ this_leaf->coherency_line_size = cache->block_size;
+ this_leaf->number_of_sets = cache->sets;
+ this_leaf->ways_of_associativity = cache->ways;
+ this_leaf->size = cache->size;
+ cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map);
+}
+
+int init_cache_level(unsigned int cpu)
+{
+ struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
+ struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+ int leaves = 0, levels = 0;
+ unsigned long upr = mfspr(SPR_UPR);
+ unsigned long iccfgr, dccfgr;
+
+ if (!(upr & SPR_UPR_UP)) {
+ printk(KERN_INFO
+ "-- no UPR register... unable to detect configuration\n");
+ return -ENOENT;
+ }
+
+ if (cpu_cache_is_present(SPR_UPR_DCP)) {
+ dccfgr = mfspr(SPR_DCCFGR);
+ cpuinfo->dcache.ways = 1 << (dccfgr & SPR_DCCFGR_NCW);
+ cpuinfo->dcache.sets = 1 << ((dccfgr & SPR_DCCFGR_NCS) >> 3);
+ cpuinfo->dcache.block_size = 16 << ((dccfgr & SPR_DCCFGR_CBS) >> 7);
+ cpuinfo->dcache.size =
+ cpuinfo->dcache.sets * cpuinfo->dcache.ways * cpuinfo->dcache.block_size;
+ leaves += 1;
+ printk(KERN_INFO
+ "-- dcache: %d bytes total, %d bytes/line, %d set(s), %d way(s)\n",
+ cpuinfo->dcache.size, cpuinfo->dcache.block_size,
+ cpuinfo->dcache.sets, cpuinfo->dcache.ways);
+ } else
+ printk(KERN_INFO "-- dcache disabled\n");
+
+ if (cpu_cache_is_present(SPR_UPR_ICP)) {
+ iccfgr = mfspr(SPR_ICCFGR);
+ cpuinfo->icache.ways = 1 << (iccfgr & SPR_ICCFGR_NCW);
+ cpuinfo->icache.sets = 1 << ((iccfgr & SPR_ICCFGR_NCS) >> 3);
+ cpuinfo->icache.block_size = 16 << ((iccfgr & SPR_ICCFGR_CBS) >> 7);
+ cpuinfo->icache.size =
+ cpuinfo->icache.sets * cpuinfo->icache.ways * cpuinfo->icache.block_size;
+ leaves += 1;
+ printk(KERN_INFO
+ "-- icache: %d bytes total, %d bytes/line, %d set(s), %d way(s)\n",
+ cpuinfo->icache.size, cpuinfo->icache.block_size,
+ cpuinfo->icache.sets, cpuinfo->icache.ways);
+ } else
+ printk(KERN_INFO "-- icache disabled\n");
+
+ if (!leaves)
+ return -ENOENT;
+
+ levels = 1;
+
+ this_cpu_ci->num_leaves = leaves;
+ this_cpu_ci->num_levels = levels;
+
+ return 0;
+}
+
+int populate_cache_leaves(unsigned int cpu)
+{
+ struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
+ struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+ struct cacheinfo *this_leaf = this_cpu_ci->info_list;
+ int level = 1;
+
+ if (cpu_cache_is_present(SPR_UPR_DCP)) {
+ ci_leaf_init(this_leaf, CACHE_TYPE_DATA, level, &cpuinfo->dcache, cpu);
+ this_leaf->attributes = ((mfspr(SPR_DCCFGR) & SPR_DCCFGR_CWS) >> 8) ?
+ CACHE_WRITE_BACK : CACHE_WRITE_THROUGH;
+ this_leaf++;
+ }
+
+ if (cpu_cache_is_present(SPR_UPR_ICP))
+ ci_leaf_init(this_leaf, CACHE_TYPE_INST, level, &cpuinfo->icache, cpu);
+
+ this_cpu_ci->cpu_map_populated = true;
+
+ return 0;
+}
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index b3edbb3..3a7b5ba 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -17,6 +17,7 @@
#include <linux/pagewalk.h>
#include <asm/cpuinfo.h>
+#include <asm/cacheflush.h>
#include <asm/spr_defs.h>
#include <asm/tlbflush.h>
@@ -24,9 +25,6 @@ static int
page_set_nocache(pte_t *pte, unsigned long addr,
unsigned long next, struct mm_walk *walk)
{
- unsigned long cl;
- struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
-
pte_val(*pte) |= _PAGE_CI;
/*
@@ -36,8 +34,7 @@ page_set_nocache(pte_t *pte, unsigned long addr,
flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
/* Flush page out of dcache */
- for (cl = __pa(addr); cl < __pa(next); cl += cpuinfo->dcache_block_size)
- mtspr(SPR_DCBFR, cl);
+ local_dcache_range_flush(__pa(addr), __pa(next));
return 0;
}
@@ -98,21 +95,14 @@ void arch_dma_clear_uncached(void *cpu_addr, size_t size)
void arch_sync_dma_for_device(phys_addr_t addr, size_t size,
enum dma_data_direction dir)
{
- unsigned long cl;
- struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
-
switch (dir) {
case DMA_TO_DEVICE:
/* Flush the dcache for the requested range */
- for (cl = addr; cl < addr + size;
- cl += cpuinfo->dcache_block_size)
- mtspr(SPR_DCBFR, cl);
+ local_dcache_range_flush(addr, addr + size);
break;
case DMA_FROM_DEVICE:
/* Invalidate the dcache for the requested range */
- for (cl = addr; cl < addr + size;
- cl += cpuinfo->dcache_block_size)
- mtspr(SPR_DCBIR, cl);
+ local_dcache_range_inv(addr, addr + size);
break;
default:
/*
diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c
index be56eaa..a9fb9cc 100644
--- a/arch/openrisc/kernel/setup.c
+++ b/arch/openrisc/kernel/setup.c
@@ -113,21 +113,6 @@ static void print_cpuinfo(void)
return;
}
- if (upr & SPR_UPR_DCP)
- printk(KERN_INFO
- "-- dcache: %4d bytes total, %2d bytes/line, %d way(s)\n",
- cpuinfo->dcache_size, cpuinfo->dcache_block_size,
- cpuinfo->dcache_ways);
- else
- printk(KERN_INFO "-- dcache disabled\n");
- if (upr & SPR_UPR_ICP)
- printk(KERN_INFO
- "-- icache: %4d bytes total, %2d bytes/line, %d way(s)\n",
- cpuinfo->icache_size, cpuinfo->icache_block_size,
- cpuinfo->icache_ways);
- else
- printk(KERN_INFO "-- icache disabled\n");
-
if (upr & SPR_UPR_DMP)
printk(KERN_INFO "-- dmmu: %4d entries, %lu way(s)\n",
1 << ((mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTS) >> 2),
@@ -155,8 +140,6 @@ static void print_cpuinfo(void)
void __init setup_cpuinfo(void)
{
struct device_node *cpu;
- unsigned long iccfgr, dccfgr;
- unsigned long cache_set_size;
int cpu_id = smp_processor_id();
struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[cpu_id];
@@ -164,20 +147,6 @@ void __init setup_cpuinfo(void)
if (!cpu)
panic("Couldn't find CPU%d in device tree...\n", cpu_id);
- iccfgr = mfspr(SPR_ICCFGR);
- cpuinfo->icache_ways = 1 << (iccfgr & SPR_ICCFGR_NCW);
- cache_set_size = 1 << ((iccfgr & SPR_ICCFGR_NCS) >> 3);
- cpuinfo->icache_block_size = 16 << ((iccfgr & SPR_ICCFGR_CBS) >> 7);
- cpuinfo->icache_size =
- cache_set_size * cpuinfo->icache_ways * cpuinfo->icache_block_size;
-
- dccfgr = mfspr(SPR_DCCFGR);
- cpuinfo->dcache_ways = 1 << (dccfgr & SPR_DCCFGR_NCW);
- cache_set_size = 1 << ((dccfgr & SPR_DCCFGR_NCS) >> 3);
- cpuinfo->dcache_block_size = 16 << ((dccfgr & SPR_DCCFGR_CBS) >> 7);
- cpuinfo->dcache_size =
- cache_set_size * cpuinfo->dcache_ways * cpuinfo->dcache_block_size;
-
if (of_property_read_u32(cpu, "clock-frequency",
&cpuinfo->clock_frequency)) {
printk(KERN_WARNING
@@ -294,14 +263,14 @@ static int show_cpuinfo(struct seq_file *m, void *v)
unsigned int vr, cpucfgr;
unsigned int avr;
unsigned int version;
+#ifdef CONFIG_SMP
struct cpuinfo_or1k *cpuinfo = v;
+ seq_printf(m, "processor\t\t: %d\n", cpuinfo->coreid);
+#endif
vr = mfspr(SPR_VR);
cpucfgr = mfspr(SPR_CPUCFGR);
-#ifdef CONFIG_SMP
- seq_printf(m, "processor\t\t: %d\n", cpuinfo->coreid);
-#endif
if (vr & SPR_VR_UVRP) {
vr = mfspr(SPR_VR2);
version = vr & SPR_VR2_VER;
@@ -320,14 +289,6 @@ static int show_cpuinfo(struct seq_file *m, void *v)
seq_printf(m, "revision\t\t: %d\n", vr & SPR_VR_REV);
}
seq_printf(m, "frequency\t\t: %ld\n", loops_per_jiffy * HZ);
- seq_printf(m, "dcache size\t\t: %d bytes\n", cpuinfo->dcache_size);
- seq_printf(m, "dcache block size\t: %d bytes\n",
- cpuinfo->dcache_block_size);
- seq_printf(m, "dcache ways\t\t: %d\n", cpuinfo->dcache_ways);
- seq_printf(m, "icache size\t\t: %d bytes\n", cpuinfo->icache_size);
- seq_printf(m, "icache block size\t: %d bytes\n",
- cpuinfo->icache_block_size);
- seq_printf(m, "icache ways\t\t: %d\n", cpuinfo->icache_ways);
seq_printf(m, "immu\t\t\t: %d entries, %lu ways\n",
1 << ((mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTS) >> 2),
1 + (mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTW));
diff --git a/arch/openrisc/mm/cache.c b/arch/openrisc/mm/cache.c
index eb43b73..0f265b8 100644
--- a/arch/openrisc/mm/cache.c
+++ b/arch/openrisc/mm/cache.c
@@ -14,31 +14,70 @@
#include <asm/spr_defs.h>
#include <asm/cache.h>
#include <asm/cacheflush.h>
+#include <asm/cpuinfo.h>
#include <asm/tlbflush.h>
-static __always_inline void cache_loop(struct page *page, const unsigned int reg)
+/*
+ * Check if the cache component exists.
+ */
+bool cpu_cache_is_present(const unsigned int cache_type)
+{
+ unsigned long upr = mfspr(SPR_UPR);
+ unsigned long mask = SPR_UPR_UP | cache_type;
+
+ return !((upr & mask) ^ mask);
+}
+
+static __always_inline void cache_loop(unsigned long paddr, unsigned long end,
+ const unsigned short reg, const unsigned int cache_type)
+{
+ if (!cpu_cache_is_present(cache_type))
+ return;
+
+ while (paddr < end) {
+ mtspr(reg, paddr);
+ paddr += L1_CACHE_BYTES;
+ }
+}
+
+static __always_inline void cache_loop_page(struct page *page, const unsigned short reg,
+ const unsigned int cache_type)
{
unsigned long paddr = page_to_pfn(page) << PAGE_SHIFT;
- unsigned long line = paddr & ~(L1_CACHE_BYTES - 1);
+ unsigned long end = paddr + PAGE_SIZE;
- while (line < paddr + PAGE_SIZE) {
- mtspr(reg, line);
- line += L1_CACHE_BYTES;
- }
+ paddr &= ~(L1_CACHE_BYTES - 1);
+
+ cache_loop(paddr, end, reg, cache_type);
}
void local_dcache_page_flush(struct page *page)
{
- cache_loop(page, SPR_DCBFR);
+ cache_loop_page(page, SPR_DCBFR, SPR_UPR_DCP);
}
EXPORT_SYMBOL(local_dcache_page_flush);
void local_icache_page_inv(struct page *page)
{
- cache_loop(page, SPR_ICBIR);
+ cache_loop_page(page, SPR_ICBIR, SPR_UPR_ICP);
}
EXPORT_SYMBOL(local_icache_page_inv);
+void local_dcache_range_flush(unsigned long start, unsigned long end)
+{
+ cache_loop(start, end, SPR_DCBFR, SPR_UPR_DCP);
+}
+
+void local_dcache_range_inv(unsigned long start, unsigned long end)
+{
+ cache_loop(start, end, SPR_DCBIR, SPR_UPR_DCP);
+}
+
+void local_icache_range_inv(unsigned long start, unsigned long end)
+{
+ cache_loop(start, end, SPR_ICBIR, SPR_UPR_ICP);
+}
+
void update_cache(struct vm_area_struct *vma, unsigned long address,
pte_t *pte)
{
@@ -58,4 +97,3 @@ void update_cache(struct vm_area_struct *vma, unsigned long address,
sync_icache_dcache(folio_page(folio, nr));
}
}
-
diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c
index be1c2eb..e4904ca 100644
--- a/arch/openrisc/mm/init.c
+++ b/arch/openrisc/mm/init.c
@@ -35,6 +35,7 @@
#include <asm/fixmap.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
+#include <asm/cacheflush.h>
int mem_init_done;
@@ -176,8 +177,8 @@ void __init paging_init(void)
barrier();
/* Invalidate instruction caches after code modification */
- mtspr(SPR_ICBIR, 0x900);
- mtspr(SPR_ICBIR, 0xa00);
+ local_icache_block_inv(0x900);
+ local_icache_block_inv(0xa00);
/* New TLB miss handlers and kernel page tables are in now place.
* Make sure that page flags get updated for all pages in TLB by
diff --git a/arch/parisc/configs/generic-32bit_defconfig b/arch/parisc/configs/generic-32bit_defconfig
index f5fffc2..5b65c98 100644
--- a/arch/parisc/configs/generic-32bit_defconfig
+++ b/arch/parisc/configs/generic-32bit_defconfig
@@ -264,8 +264,6 @@
CONFIG_CRYPTO_SHA1=y
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_DEFLATE=y
-CONFIG_CRC_CCITT=m
-CONFIG_CRC_T10DIF=y
CONFIG_FONTS=y
CONFIG_PRINTK_TIME=y
CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig
index 2487765..ecc9ffc 100644
--- a/arch/parisc/configs/generic-64bit_defconfig
+++ b/arch/parisc/configs/generic-64bit_defconfig
@@ -292,7 +292,6 @@
CONFIG_CRYPTO_MICHAEL_MIC=m
CONFIG_CRYPTO_DEFLATE=m
# CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_CCITT=m
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_KERNEL=y
CONFIG_STRIP_ASM_SYMS=y
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index 1db60fe..3d8dc82 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -234,10 +234,8 @@
# suppress some warnings in recent ld versions
nowarn="-z noexecstack"
-if ! ld_is_lld; then
- if [ "$LD_VERSION" -ge "$(echo 2.39 | ld_version)" ]; then
- nowarn="$nowarn --no-warn-rwx-segments"
- fi
+if "${CROSS}ld" -v --no-warn-rwx-segments >/dev/null 2>&1; then
+ nowarn="$nowarn --no-warn-rwx-segments"
fi
platformo=$object/"$platform".o
diff --git a/arch/powerpc/configs/44x/sam440ep_defconfig b/arch/powerpc/configs/44x/sam440ep_defconfig
index 2479ab6..98221bd 100644
--- a/arch/powerpc/configs/44x/sam440ep_defconfig
+++ b/arch/powerpc/configs/44x/sam440ep_defconfig
@@ -91,5 +91,4 @@
# CONFIG_NETWORK_FILESYSTEMS is not set
CONFIG_NLS_CODEPAGE_437=y
CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_T10DIF=y
CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/powerpc/configs/44x/warp_defconfig b/arch/powerpc/configs/44x/warp_defconfig
index 20891c4..5757625 100644
--- a/arch/powerpc/configs/44x/warp_defconfig
+++ b/arch/powerpc/configs/44x/warp_defconfig
@@ -85,8 +85,6 @@
CONFIG_NLS_ISO8859_1=y
CONFIG_NLS_ISO8859_15=y
CONFIG_NLS_UTF8=y
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_T10DIF=y
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
CONFIG_DEBUG_FS=y
diff --git a/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig b/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig
index 1715ff5..b99caba 100644
--- a/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig
+++ b/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig
@@ -73,6 +73,5 @@
CONFIG_NLS_CODEPAGE_932=y
CONFIG_NLS_ISO8859_8=y
CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_T10DIF=y
CONFIG_CRYPTO_ECB=m
CONFIG_CRYPTO_PCBC=m
diff --git a/arch/powerpc/configs/83xx/mpc834x_itx_defconfig b/arch/powerpc/configs/83xx/mpc834x_itx_defconfig
index e65c0057..1116305 100644
--- a/arch/powerpc/configs/83xx/mpc834x_itx_defconfig
+++ b/arch/powerpc/configs/83xx/mpc834x_itx_defconfig
@@ -80,5 +80,4 @@
CONFIG_NFS_FS=y
CONFIG_NFS_V4=y
CONFIG_ROOT_NFS=y
-CONFIG_CRC_T10DIF=y
CONFIG_CRYPTO_PCBC=m
diff --git a/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig b/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig
index 17714bf..312d39e 100644
--- a/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig
+++ b/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig
@@ -72,5 +72,4 @@
CONFIG_NFS_FS=y
CONFIG_NFS_V4=y
CONFIG_ROOT_NFS=y
-CONFIG_CRC_T10DIF=y
CONFIG_CRYPTO_PCBC=m
diff --git a/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig b/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig
index 58fae51..ac27f99 100644
--- a/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig
+++ b/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig
@@ -75,6 +75,5 @@
CONFIG_NFS_FS=y
CONFIG_NFS_V4=y
CONFIG_ROOT_NFS=y
-CONFIG_CRC_T10DIF=y
CONFIG_CRYPTO_ECB=m
CONFIG_CRYPTO_PCBC=m
diff --git a/arch/powerpc/configs/85xx/ge_imp3a_defconfig b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
index 6f58ee1..7beb36a 100644
--- a/arch/powerpc/configs/85xx/ge_imp3a_defconfig
+++ b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
@@ -221,8 +221,6 @@
CONFIG_NLS_KOI8_R=m
CONFIG_NLS_KOI8_U=m
CONFIG_NLS_UTF8=y
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_T10DIF=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_CRYPTO_CBC=y
CONFIG_CRYPTO_MD5=y
diff --git a/arch/powerpc/configs/85xx/stx_gp3_defconfig b/arch/powerpc/configs/85xx/stx_gp3_defconfig
index e708049..0a42072 100644
--- a/arch/powerpc/configs/85xx/stx_gp3_defconfig
+++ b/arch/powerpc/configs/85xx/stx_gp3_defconfig
@@ -60,8 +60,6 @@
CONFIG_NFS_FS=y
CONFIG_ROOT_NFS=y
CONFIG_NLS=y
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_T10DIF=m
CONFIG_DETECT_HUNG_TASK=y
# CONFIG_DEBUG_BUGVERBOSE is not set
CONFIG_BDI_SWITCH=y
diff --git a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
index 3a6381a..488d03a 100644
--- a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
+++ b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
@@ -132,7 +132,6 @@
CONFIG_NFSD=y
CONFIG_NLS_CODEPAGE_437=y
CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_T10DIF=y
CONFIG_DETECT_HUNG_TASK=y
# CONFIG_DEBUG_BUGVERBOSE is not set
CONFIG_CRYPTO_HMAC=y
diff --git a/arch/powerpc/configs/86xx-hw.config b/arch/powerpc/configs/86xx-hw.config
index 0cb24b3..e7bd265 100644
--- a/arch/powerpc/configs/86xx-hw.config
+++ b/arch/powerpc/configs/86xx-hw.config
@@ -5,7 +5,6 @@
# CONFIG_CARDBUS is not set
CONFIG_CHR_DEV_SG=y
CONFIG_CHR_DEV_ST=y
-CONFIG_CRC_T10DIF=y
CONFIG_CRYPTO_HMAC=y
CONFIG_DS1682=y
CONFIG_EEPROM_LEGACY=y
diff --git a/arch/powerpc/configs/amigaone_defconfig b/arch/powerpc/configs/amigaone_defconfig
index 200bb1e..69ef3dc 100644
--- a/arch/powerpc/configs/amigaone_defconfig
+++ b/arch/powerpc/configs/amigaone_defconfig
@@ -106,7 +106,6 @@
CONFIG_AFFS_FS=m
CONFIG_NLS_ASCII=y
CONFIG_NLS_ISO8859_1=m
-CONFIG_CRC_T10DIF=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_KERNEL=y
CONFIG_DEBUG_MUTEXES=y
diff --git a/arch/powerpc/configs/chrp32_defconfig b/arch/powerpc/configs/chrp32_defconfig
index fb314f7..b799c95 100644
--- a/arch/powerpc/configs/chrp32_defconfig
+++ b/arch/powerpc/configs/chrp32_defconfig
@@ -110,7 +110,6 @@
CONFIG_TMPFS=y
CONFIG_NLS_ASCII=y
CONFIG_NLS_ISO8859_1=m
-CONFIG_CRC_T10DIF=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_KERNEL=y
CONFIG_DEBUG_MUTEXES=y
diff --git a/arch/powerpc/configs/fsl-emb-nonhw.config b/arch/powerpc/configs/fsl-emb-nonhw.config
index d6d2a45..2f81bc2 100644
--- a/arch/powerpc/configs/fsl-emb-nonhw.config
+++ b/arch/powerpc/configs/fsl-emb-nonhw.config
@@ -15,7 +15,6 @@
CONFIG_CGROUP_SCHED=y
CONFIG_CGROUPS=y
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_CRC_T10DIF=y
CONFIG_CPUSETS=y
CONFIG_CRAMFS=y
CONFIG_CRYPTO_MD4=y
diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig
index 9215bed..7e58f3e 100644
--- a/arch/powerpc/configs/g5_defconfig
+++ b/arch/powerpc/configs/g5_defconfig
@@ -231,7 +231,6 @@
CONFIG_NLS_ISO8859_1=y
CONFIG_NLS_ISO8859_15=y
CONFIG_NLS_UTF8=y
-CONFIG_CRC_T10DIF=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_KERNEL=y
CONFIG_DEBUG_MUTEXES=y
diff --git a/arch/powerpc/configs/gamecube_defconfig b/arch/powerpc/configs/gamecube_defconfig
index d77eeb5..cdd9965 100644
--- a/arch/powerpc/configs/gamecube_defconfig
+++ b/arch/powerpc/configs/gamecube_defconfig
@@ -82,7 +82,6 @@
CONFIG_CIFS=y
CONFIG_NLS_CODEPAGE_437=y
CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_CCITT=y
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_SPINLOCK=y
CONFIG_DEBUG_MUTEXES=y
diff --git a/arch/powerpc/configs/linkstation_defconfig b/arch/powerpc/configs/linkstation_defconfig
index fa707de..b564f9e 100644
--- a/arch/powerpc/configs/linkstation_defconfig
+++ b/arch/powerpc/configs/linkstation_defconfig
@@ -125,8 +125,6 @@
CONFIG_NLS_CODEPAGE_932=m
CONFIG_NLS_ISO8859_1=m
CONFIG_NLS_UTF8=m
-CONFIG_CRC_CCITT=m
-CONFIG_CRC_T10DIF=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_KERNEL=y
CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/powerpc/configs/mpc83xx_defconfig b/arch/powerpc/configs/mpc83xx_defconfig
index 83c4710..a815d9e 100644
--- a/arch/powerpc/configs/mpc83xx_defconfig
+++ b/arch/powerpc/configs/mpc83xx_defconfig
@@ -97,7 +97,6 @@
CONFIG_NFS_FS=y
CONFIG_NFS_V4=y
CONFIG_ROOT_NFS=y
-CONFIG_CRC_T10DIF=y
CONFIG_CRYPTO_ECB=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_SHA512=y
diff --git a/arch/powerpc/configs/mpc866_ads_defconfig b/arch/powerpc/configs/mpc866_ads_defconfig
index a0d27c5..dfbdd5e 100644
--- a/arch/powerpc/configs/mpc866_ads_defconfig
+++ b/arch/powerpc/configs/mpc866_ads_defconfig
@@ -38,4 +38,3 @@
CONFIG_CRAMFS=y
CONFIG_NFS_FS=y
CONFIG_ROOT_NFS=y
-CONFIG_CRC_CCITT=y
diff --git a/arch/powerpc/configs/mvme5100_defconfig b/arch/powerpc/configs/mvme5100_defconfig
index d1c7fd5..fa2b3b9 100644
--- a/arch/powerpc/configs/mvme5100_defconfig
+++ b/arch/powerpc/configs/mvme5100_defconfig
@@ -107,8 +107,6 @@
CONFIG_NLS_CODEPAGE_932=m
CONFIG_NLS_ISO8859_1=m
CONFIG_NLS_UTF8=m
-CONFIG_CRC_CCITT=m
-CONFIG_CRC_T10DIF=y
CONFIG_XZ_DEC=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_KERNEL=y
diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig
index 6199394..8bbf51b3 100644
--- a/arch/powerpc/configs/pasemi_defconfig
+++ b/arch/powerpc/configs/pasemi_defconfig
@@ -159,7 +159,6 @@
CONFIG_NFSD_V4=y
CONFIG_NLS_CODEPAGE_437=y
CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_CCITT=y
CONFIG_PRINTK_TIME=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_KERNEL=y
diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig
index e8b3f67..1bc3466 100644
--- a/arch/powerpc/configs/pmac32_defconfig
+++ b/arch/powerpc/configs/pmac32_defconfig
@@ -276,7 +276,6 @@
CONFIG_NFSD_V4=y
CONFIG_NLS_CODEPAGE_437=m
CONFIG_NLS_ISO8859_1=m
-CONFIG_CRC_T10DIF=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_KERNEL=y
CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/powerpc/configs/ppc44x_defconfig b/arch/powerpc/configs/ppc44x_defconfig
index 8b595f6..41c930f 100644
--- a/arch/powerpc/configs/ppc44x_defconfig
+++ b/arch/powerpc/configs/ppc44x_defconfig
@@ -90,7 +90,6 @@
CONFIG_ROOT_NFS=y
CONFIG_NLS_CODEPAGE_437=m
CONFIG_NLS_ISO8859_1=m
-CONFIG_CRC_T10DIF=m
CONFIG_MAGIC_SYSRQ=y
CONFIG_DETECT_HUNG_TASK=y
CONFIG_CRYPTO_ECB=y
diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig
index 4c05f4e..d2e659a 100644
--- a/arch/powerpc/configs/ppc64e_defconfig
+++ b/arch/powerpc/configs/ppc64e_defconfig
@@ -207,7 +207,6 @@
CONFIG_NLS_ASCII=y
CONFIG_NLS_ISO8859_1=y
CONFIG_NLS_UTF8=y
-CONFIG_CRC_T10DIF=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_KERNEL=y
CONFIG_DEBUG_STACK_USAGE=y
diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig
index 2b175dd..0b48d2b 100644
--- a/arch/powerpc/configs/ps3_defconfig
+++ b/arch/powerpc/configs/ps3_defconfig
@@ -148,8 +148,6 @@
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_MICHAEL_MIC=m
CONFIG_CRYPTO_LZO=m
-CONFIG_CRC_CCITT=m
-CONFIG_CRC_T10DIF=y
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig
index 3086c4a..2b71a6d 100644
--- a/arch/powerpc/configs/skiroot_defconfig
+++ b/arch/powerpc/configs/skiroot_defconfig
@@ -278,8 +278,6 @@
# CONFIG_INTEGRITY is not set
CONFIG_LSM="yama,loadpin,safesetid,integrity"
# CONFIG_CRYPTO_HW is not set
-CONFIG_CRC16=y
-CONFIG_CRC_ITU_T=y
# CONFIG_XZ_DEC_X86 is not set
# CONFIG_XZ_DEC_IA64 is not set
# CONFIG_XZ_DEC_ARM is not set
diff --git a/arch/powerpc/configs/storcenter_defconfig b/arch/powerpc/configs/storcenter_defconfig
index 7a978d3..e415222b 100644
--- a/arch/powerpc/configs/storcenter_defconfig
+++ b/arch/powerpc/configs/storcenter_defconfig
@@ -75,4 +75,3 @@
CONFIG_NLS_CODEPAGE_437=y
CONFIG_NLS_ISO8859_1=y
CONFIG_NLS_UTF8=y
-CONFIG_CRC_T10DIF=y
diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig
index 5017a69..7c714a1 100644
--- a/arch/powerpc/configs/wii_defconfig
+++ b/arch/powerpc/configs/wii_defconfig
@@ -114,7 +114,6 @@
CONFIG_CIFS=m
CONFIG_NLS_CODEPAGE_437=y
CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_CCITT=y
CONFIG_PRINTK_TIME=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_SPINLOCK=y
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 34a5aec..126bf3b 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -258,10 +258,6 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
break;
}
}
- if (i == hdr->e_shnum) {
- pr_err("%s: doesn't contain __patchable_function_entries.\n", me->name);
- return -ENOEXEC;
- }
#endif
pr_debug("Looks like a total of %lu stubs, max\n", relocs);
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 311e211..9f764bc 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -976,7 +976,7 @@ int __meminit radix__vmemmap_create_mapping(unsigned long start,
return 0;
}
-
+#ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP
bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
{
if (radix_enabled())
@@ -984,6 +984,7 @@ bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
return false;
}
+#endif
int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node,
unsigned long addr, unsigned long next)
@@ -1120,6 +1121,19 @@ int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, in
pmd_t *pmd;
pte_t *pte;
+ /*
+ * Make sure we align the start vmemmap addr so that we calculate
+ * the correct start_pfn in altmap boundary check to decided whether
+ * we should use altmap or RAM based backing memory allocation. Also
+ * the address need to be aligned for set_pte operation.
+
+ * If the start addr is already PMD_SIZE aligned we will try to use
+ * a pmd mapping. We don't want to be too aggressive here beacause
+ * that will cause more allocations in RAM. So only if the namespace
+ * vmemmap start addr is PMD_SIZE aligned we will use PMD mapping.
+ */
+
+ start = ALIGN_DOWN(start, PAGE_SIZE);
for (addr = start; addr < end; addr = next) {
next = pmd_addr_end(addr, end);
@@ -1145,8 +1159,8 @@ int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, in
* in altmap block allocation failures, in which case
* we fallback to RAM for vmemmap allocation.
*/
- if (altmap && (!IS_ALIGNED(addr, PMD_SIZE) ||
- altmap_cross_boundary(altmap, addr, PMD_SIZE))) {
+ if (!IS_ALIGNED(addr, PMD_SIZE) || (altmap &&
+ altmap_cross_boundary(altmap, addr, PMD_SIZE))) {
/*
* make sure we don't create altmap mappings
* covering things outside the device.
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index 3fbe029..95d7ba7 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -17,7 +17,7 @@
select MMU_NOTIFIER
select FORCE_SMP
select ARCH_SUPPORTS_PER_VMA_LOCK
- select PPC_RADIX_BROADCAST_TLBIE
+ select PPC_RADIX_BROADCAST_TLBIE if PPC_RADIX_MMU
default y
config OPAL_PRD
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index a934c2a..fa3c2ff 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -23,7 +23,7 @@
select FORCE_SMP
select SWIOTLB
select ARCH_SUPPORTS_PER_VMA_LOCK
- select PPC_RADIX_BROADCAST_TLBIE
+ select PPC_RADIX_BROADCAST_TLBIE if PPC_RADIX_MMU
default y
config PARAVIRT
diff --git a/arch/riscv/boot/dts/sophgo/cv18xx.dtsi b/arch/riscv/boot/dts/sophgo/cv18xx.dtsi
index c18822e..58cd5463 100644
--- a/arch/riscv/boot/dts/sophgo/cv18xx.dtsi
+++ b/arch/riscv/boot/dts/sophgo/cv18xx.dtsi
@@ -341,7 +341,7 @@ dmac: dma-controller@4330000 {
1024 1024 1024 1024>;
snps,priority = <0 1 2 3 4 5 6 7>;
snps,dma-masters = <2>;
- snps,data-width = <4>;
+ snps,data-width = <2>;
status = "disabled";
};
diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h
index 721ec27..231d777 100644
--- a/arch/riscv/include/asm/alternative-macros.h
+++ b/arch/riscv/include/asm/alternative-macros.h
@@ -115,24 +115,19 @@
\old_c
.endm
-#define _ALTERNATIVE_CFG(old_c, ...) \
- ALTERNATIVE_CFG old_c
-
-#define _ALTERNATIVE_CFG_2(old_c, ...) \
- ALTERNATIVE_CFG old_c
+#define __ALTERNATIVE_CFG(old_c, ...) ALTERNATIVE_CFG old_c
+#define __ALTERNATIVE_CFG_2(old_c, ...) ALTERNATIVE_CFG old_c
#else /* !__ASSEMBLY__ */
-#define __ALTERNATIVE_CFG(old_c) \
- old_c "\n"
-
-#define _ALTERNATIVE_CFG(old_c, ...) \
- __ALTERNATIVE_CFG(old_c)
-
-#define _ALTERNATIVE_CFG_2(old_c, ...) \
- __ALTERNATIVE_CFG(old_c)
+#define __ALTERNATIVE_CFG(old_c, ...) old_c "\n"
+#define __ALTERNATIVE_CFG_2(old_c, ...) old_c "\n"
#endif /* __ASSEMBLY__ */
+
+#define _ALTERNATIVE_CFG(old_c, ...) __ALTERNATIVE_CFG(old_c)
+#define _ALTERNATIVE_CFG_2(old_c, ...) __ALTERNATIVE_CFG_2(old_c)
+
#endif /* CONFIG_RISCV_ALTERNATIVE */
/*
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index 8de73f9..b59ffeb 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -34,11 +34,6 @@ static inline void flush_dcache_page(struct page *page)
flush_dcache_folio(page_folio(page));
}
-/*
- * RISC-V doesn't have an instruction to flush parts of the instruction cache,
- * so instead we just flush the whole thing.
- */
-#define flush_icache_range(start, end) flush_icache_all()
#define flush_icache_user_page(vma, pg, addr, len) \
do { \
if (vma->vm_flags & VM_EXEC) \
@@ -78,6 +73,16 @@ void flush_icache_mm(struct mm_struct *mm, bool local);
#endif /* CONFIG_SMP */
+/*
+ * RISC-V doesn't have an instruction to flush parts of the instruction cache,
+ * so instead we just flush the whole thing.
+ */
+#define flush_icache_range flush_icache_range
+static inline void flush_icache_range(unsigned long start, unsigned long end)
+{
+ flush_icache_all();
+}
+
extern unsigned int riscv_cbom_block_size;
extern unsigned int riscv_cboz_block_size;
void riscv_init_cbo_blocksizes(void);
diff --git a/arch/riscv/include/asm/kgdb.h b/arch/riscv/include/asm/kgdb.h
index 46677da..cc11c45 100644
--- a/arch/riscv/include/asm/kgdb.h
+++ b/arch/riscv/include/asm/kgdb.h
@@ -19,16 +19,9 @@
#ifndef __ASSEMBLY__
+void arch_kgdb_breakpoint(void);
extern unsigned long kgdb_compiled_break;
-static inline void arch_kgdb_breakpoint(void)
-{
- asm(".global kgdb_compiled_break\n"
- ".option norvc\n"
- "kgdb_compiled_break: ebreak\n"
- ".option rvc\n");
-}
-
#endif /* !__ASSEMBLY__ */
#define DBG_REG_ZERO "zero"
diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h
index 121fff4..eceabf5 100644
--- a/arch/riscv/include/asm/syscall.h
+++ b/arch/riscv/include/asm/syscall.h
@@ -62,8 +62,11 @@ static inline void syscall_get_arguments(struct task_struct *task,
unsigned long *args)
{
args[0] = regs->orig_a0;
- args++;
- memcpy(args, ®s->a1, 5 * sizeof(args[0]));
+ args[1] = regs->a1;
+ args[2] = regs->a2;
+ args[3] = regs->a3;
+ args[4] = regs->a4;
+ args[5] = regs->a5;
}
static inline int syscall_get_arch(struct task_struct *task)
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 8d186bf..f7480c9 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -9,8 +9,8 @@
CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE)
endif
-CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,)
-CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,)
+CFLAGS_syscall_table.o += $(call cc-disable-warning, override-init)
+CFLAGS_compat_syscall_table.o += $(call cc-disable-warning, override-init)
ifdef CONFIG_KEXEC_CORE
AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax)
diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c
index 2e0266a..9f3db35 100644
--- a/arch/riscv/kernel/kgdb.c
+++ b/arch/riscv/kernel/kgdb.c
@@ -254,6 +254,12 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
regs->epc = pc;
}
+noinline void arch_kgdb_breakpoint(void)
+{
+ asm(".global kgdb_compiled_break\n"
+ "kgdb_compiled_break: ebreak\n");
+}
+
void kgdb_arch_handle_qxfer_pkt(char *remcom_in_buffer,
char *remcom_out_buffer)
{
diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c
index e264e59..91d0b35 100644
--- a/arch/riscv/kernel/module-sections.c
+++ b/arch/riscv/kernel/module-sections.c
@@ -73,16 +73,17 @@ static bool duplicate_rela(const Elf_Rela *rela, int idx)
static void count_max_entries(Elf_Rela *relas, int num,
unsigned int *plts, unsigned int *gots)
{
- unsigned int type, i;
-
- for (i = 0; i < num; i++) {
- type = ELF_RISCV_R_TYPE(relas[i].r_info);
- if (type == R_RISCV_CALL_PLT) {
+ for (int i = 0; i < num; i++) {
+ switch (ELF_R_TYPE(relas[i].r_info)) {
+ case R_RISCV_CALL_PLT:
+ case R_RISCV_PLT32:
if (!duplicate_rela(relas, i))
(*plts)++;
- } else if (type == R_RISCV_GOT_HI20) {
+ break;
+ case R_RISCV_GOT_HI20:
if (!duplicate_rela(relas, i))
(*gots)++;
+ break;
}
}
}
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 47d0ebe..7f6147c 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -648,7 +648,7 @@ process_accumulated_relocations(struct module *me,
kfree(bucket_iter);
}
- kfree(*relocation_hashtable);
+ kvfree(*relocation_hashtable);
}
static int add_relocation_to_accumulate(struct module *me, int type,
@@ -752,9 +752,10 @@ initialize_relocation_hashtable(unsigned int num_relocations,
hashtable_size <<= should_double_size;
- *relocation_hashtable = kmalloc_array(hashtable_size,
- sizeof(**relocation_hashtable),
- GFP_KERNEL);
+ /* Number of relocations may be large, so kvmalloc it */
+ *relocation_hashtable = kvmalloc_array(hashtable_size,
+ sizeof(**relocation_hashtable),
+ GFP_KERNEL);
if (!*relocation_hashtable)
return 0;
@@ -859,7 +860,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
}
j++;
- if (j > sechdrs[relsec].sh_size / sizeof(*rel))
+ if (j == num_relocations)
j = 0;
} while (j_idx != j);
diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c
index 4b3dc8b..cc15f7ca 100644
--- a/arch/riscv/kernel/probes/uprobes.c
+++ b/arch/riscv/kernel/probes/uprobes.c
@@ -167,6 +167,7 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
/* Initialize the slot */
void *kaddr = kmap_atomic(page);
void *dst = kaddr + (vaddr & ~PAGE_MASK);
+ unsigned long start = (unsigned long)dst;
memcpy(dst, src, len);
@@ -176,13 +177,6 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
*(uprobe_opcode_t *)dst = __BUG_INSN_32;
}
+ flush_icache_range(start, start + len);
kunmap_atomic(kaddr);
-
- /*
- * We probably need flush_icache_user_page() but it needs vma.
- * This should work on most of architectures by default. If
- * architecture needs to do something different it can define
- * its own version of the function.
- */
- flush_dcache_page(page);
}
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index c174544..f7c9a1c 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -66,6 +66,9 @@ static struct resource bss_res = { .name = "Kernel bss", };
static struct resource elfcorehdr_res = { .name = "ELF Core hdr", };
#endif
+static int num_standard_resources;
+static struct resource *standard_resources;
+
static int __init add_resource(struct resource *parent,
struct resource *res)
{
@@ -139,7 +142,7 @@ static void __init init_resources(void)
struct resource *res = NULL;
struct resource *mem_res = NULL;
size_t mem_res_sz = 0;
- int num_resources = 0, res_idx = 0;
+ int num_resources = 0, res_idx = 0, non_resv_res = 0;
int ret = 0;
/* + 1 as memblock_alloc() might increase memblock.reserved.cnt */
@@ -193,6 +196,7 @@ static void __init init_resources(void)
/* Add /memory regions to the resource tree */
for_each_mem_region(region) {
res = &mem_res[res_idx--];
+ non_resv_res++;
if (unlikely(memblock_is_nomap(region))) {
res->name = "Reserved";
@@ -210,6 +214,9 @@ static void __init init_resources(void)
goto error;
}
+ num_standard_resources = non_resv_res;
+ standard_resources = &mem_res[res_idx + 1];
+
/* Clean-up any unused pre-allocated resources */
if (res_idx >= 0)
memblock_free(mem_res, (res_idx + 1) * sizeof(*mem_res));
@@ -221,6 +228,33 @@ static void __init init_resources(void)
memblock_free(mem_res, mem_res_sz);
}
+static int __init reserve_memblock_reserved_regions(void)
+{
+ u64 i, j;
+
+ for (i = 0; i < num_standard_resources; i++) {
+ struct resource *mem = &standard_resources[i];
+ phys_addr_t r_start, r_end, mem_size = resource_size(mem);
+
+ if (!memblock_is_region_reserved(mem->start, mem_size))
+ continue;
+
+ for_each_reserved_mem_range(j, &r_start, &r_end) {
+ resource_size_t start, end;
+
+ start = max(PFN_PHYS(PFN_DOWN(r_start)), mem->start);
+ end = min(PFN_PHYS(PFN_UP(r_end)) - 1, mem->end);
+
+ if (start > mem->end || end < mem->start)
+ continue;
+
+ reserve_region_with_split(mem, start, end, "Reserved");
+ }
+ }
+
+ return 0;
+}
+arch_initcall(reserve_memblock_reserved_regions);
static void __init parse_dtb(void)
{
diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c
index 585d2dc..b8ba138 100644
--- a/arch/riscv/kernel/unaligned_access_speed.c
+++ b/arch/riscv/kernel/unaligned_access_speed.c
@@ -439,29 +439,36 @@ static int __init check_unaligned_access_all_cpus(void)
{
int cpu;
- if (unaligned_scalar_speed_param == RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN &&
- !check_unaligned_access_emulated_all_cpus()) {
- check_unaligned_access_speed_all_cpus();
- } else {
- pr_info("scalar unaligned access speed set to '%s' by command line\n",
- speed_str[unaligned_scalar_speed_param]);
+ if (unaligned_scalar_speed_param != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) {
+ pr_info("scalar unaligned access speed set to '%s' (%lu) by command line\n",
+ speed_str[unaligned_scalar_speed_param], unaligned_scalar_speed_param);
for_each_online_cpu(cpu)
per_cpu(misaligned_access_speed, cpu) = unaligned_scalar_speed_param;
+ } else if (!check_unaligned_access_emulated_all_cpus()) {
+ check_unaligned_access_speed_all_cpus();
+ }
+
+ if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) {
+ if (!has_vector() &&
+ unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED) {
+ pr_warn("vector support is not available, ignoring unaligned_vector_speed=%s\n",
+ speed_str[unaligned_vector_speed_param]);
+ } else {
+ pr_info("vector unaligned access speed set to '%s' (%lu) by command line\n",
+ speed_str[unaligned_vector_speed_param], unaligned_vector_speed_param);
+ }
}
if (!has_vector())
unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED;
- if (unaligned_vector_speed_param == RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN &&
- !check_vector_unaligned_access_emulated_all_cpus() &&
- IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) {
- kthread_run(vec_check_unaligned_access_speed_all_cpus,
- NULL, "vec_check_unaligned_access_speed_all_cpus");
- } else {
- pr_info("vector unaligned access speed set to '%s' by command line\n",
- speed_str[unaligned_vector_speed_param]);
+ if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) {
for_each_online_cpu(cpu)
per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param;
+ } else if (!check_vector_unaligned_access_emulated_all_cpus() &&
+ IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) {
+ kthread_run(vec_check_unaligned_access_speed_all_cpus,
+ NULL, "vec_check_unaligned_access_speed_all_cpus");
}
/*
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index db8161e..99fb986 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -332,6 +332,10 @@
def_bool n
select HAVE_MARCH_Z15_FEATURES
+config HAVE_MARCH_Z17_FEATURES
+ def_bool n
+ select HAVE_MARCH_Z16_FEATURES
+
choice
prompt "Processor type"
default MARCH_Z196
@@ -397,6 +401,14 @@
Select this to enable optimizations for IBM z16 (3931 and
3932 series).
+config MARCH_Z17
+ bool "IBM z17"
+ select HAVE_MARCH_Z17_FEATURES
+ depends on $(cc-option,-march=z17)
+ help
+ Select this to enable optimizations for IBM z17 (9175 and
+ 9176 series).
+
endchoice
config MARCH_Z10_TUNE
@@ -420,6 +432,9 @@
config MARCH_Z16_TUNE
def_bool TUNE_Z16 || MARCH_Z16 && TUNE_DEFAULT
+config MARCH_Z17_TUNE
+ def_bool TUNE_Z17 || MARCH_Z17 && TUNE_DEFAULT
+
choice
prompt "Tune code generation"
default TUNE_DEFAULT
@@ -464,6 +479,10 @@
bool "IBM z16"
depends on $(cc-option,-mtune=z16)
+config TUNE_Z17
+ bool "IBM z17"
+ depends on $(cc-option,-mtune=z17)
+
endchoice
config 64BIT
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index b06dc53..7679bc1 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -48,6 +48,7 @@
mflags-$(CONFIG_MARCH_Z14) := -march=z14
mflags-$(CONFIG_MARCH_Z15) := -march=z15
mflags-$(CONFIG_MARCH_Z16) := -march=z16
+mflags-$(CONFIG_MARCH_Z17) := -march=z17
export CC_FLAGS_MARCH := $(mflags-y)
@@ -61,6 +62,7 @@
cflags-$(CONFIG_MARCH_Z14_TUNE) += -mtune=z14
cflags-$(CONFIG_MARCH_Z15_TUNE) += -mtune=z15
cflags-$(CONFIG_MARCH_Z16_TUNE) += -mtune=z16
+cflags-$(CONFIG_MARCH_Z17_TUNE) += -mtune=z17
cflags-y += -Wa,-I$(srctree)/arch/$(ARCH)/include
diff --git a/arch/s390/include/asm/march.h b/arch/s390/include/asm/march.h
index fd9eef3..11a71bd 100644
--- a/arch/s390/include/asm/march.h
+++ b/arch/s390/include/asm/march.h
@@ -33,6 +33,10 @@
#define MARCH_HAS_Z16_FEATURES 1
#endif
+#ifdef CONFIG_HAVE_MARCH_Z17_FEATURES
+#define MARCH_HAS_Z17_FEATURES 1
+#endif
+
#endif /* __DECOMPRESSOR */
#endif /* __ASM_S390_MARCH_H */
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 33205dd..e657fad 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -442,7 +442,7 @@ static void cpum_cf_make_setsize(enum cpumf_ctr_set ctrset)
ctrset_size = 48;
else if (cpumf_ctr_info.csvn >= 3 && cpumf_ctr_info.csvn <= 5)
ctrset_size = 128;
- else if (cpumf_ctr_info.csvn == 6 || cpumf_ctr_info.csvn == 7)
+ else if (cpumf_ctr_info.csvn >= 6 && cpumf_ctr_info.csvn <= 8)
ctrset_size = 160;
break;
case CPUMF_CTR_SET_MT_DIAG:
@@ -858,18 +858,13 @@ static int cpumf_pmu_event_type(struct perf_event *event)
static int cpumf_pmu_event_init(struct perf_event *event)
{
unsigned int type = event->attr.type;
- int err;
+ int err = -ENOENT;
if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW)
err = __hw_perf_event_init(event, type);
else if (event->pmu->type == type)
/* Registered as unknown PMU */
err = __hw_perf_event_init(event, cpumf_pmu_event_type(event));
- else
- return -ENOENT;
-
- if (unlikely(err) && event->destroy)
- event->destroy(event);
return err;
}
@@ -1819,8 +1814,6 @@ static int cfdiag_event_init(struct perf_event *event)
event->destroy = hw_perf_event_destroy;
err = cfdiag_event_init2(event);
- if (unlikely(err))
- event->destroy(event);
out:
return err;
}
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
index e4a6bfc..690a293 100644
--- a/arch/s390/kernel/perf_cpum_cf_events.c
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -237,7 +237,6 @@ CPUMF_EVENT_ATTR(cf_z14, TX_C_TABORT_NO_SPECIAL, 0x00f4);
CPUMF_EVENT_ATTR(cf_z14, TX_C_TABORT_SPECIAL, 0x00f5);
CPUMF_EVENT_ATTR(cf_z14, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
CPUMF_EVENT_ATTR(cf_z14, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
-
CPUMF_EVENT_ATTR(cf_z15, L1D_RO_EXCL_WRITES, 0x0080);
CPUMF_EVENT_ATTR(cf_z15, DTLB2_WRITES, 0x0081);
CPUMF_EVENT_ATTR(cf_z15, DTLB2_MISSES, 0x0082);
@@ -365,6 +364,83 @@ CPUMF_EVENT_ATTR(cf_z16, NNPA_WAIT_LOCK, 0x010d);
CPUMF_EVENT_ATTR(cf_z16, NNPA_HOLD_LOCK, 0x010e);
CPUMF_EVENT_ATTR(cf_z16, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
CPUMF_EVENT_ATTR(cf_z16, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
+CPUMF_EVENT_ATTR(cf_z17, L1D_RO_EXCL_WRITES, 0x0080);
+CPUMF_EVENT_ATTR(cf_z17, DTLB2_WRITES, 0x0081);
+CPUMF_EVENT_ATTR(cf_z17, DTLB2_MISSES, 0x0082);
+CPUMF_EVENT_ATTR(cf_z17, CRSTE_1MB_WRITES, 0x0083);
+CPUMF_EVENT_ATTR(cf_z17, DTLB2_GPAGE_WRITES, 0x0084);
+CPUMF_EVENT_ATTR(cf_z17, ITLB2_WRITES, 0x0086);
+CPUMF_EVENT_ATTR(cf_z17, ITLB2_MISSES, 0x0087);
+CPUMF_EVENT_ATTR(cf_z17, TLB2_PTE_WRITES, 0x0089);
+CPUMF_EVENT_ATTR(cf_z17, TLB2_CRSTE_WRITES, 0x008a);
+CPUMF_EVENT_ATTR(cf_z17, TLB2_ENGINES_BUSY, 0x008b);
+CPUMF_EVENT_ATTR(cf_z17, TX_C_TEND, 0x008c);
+CPUMF_EVENT_ATTR(cf_z17, TX_NC_TEND, 0x008d);
+CPUMF_EVENT_ATTR(cf_z17, L1C_TLB2_MISSES, 0x008f);
+CPUMF_EVENT_ATTR(cf_z17, DCW_REQ, 0x0091);
+CPUMF_EVENT_ATTR(cf_z17, DCW_REQ_IV, 0x0092);
+CPUMF_EVENT_ATTR(cf_z17, DCW_REQ_CHIP_HIT, 0x0093);
+CPUMF_EVENT_ATTR(cf_z17, DCW_REQ_DRAWER_HIT, 0x0094);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP, 0x0095);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP_IV, 0x0096);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP_CHIP_HIT, 0x0097);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP_DRAWER_HIT, 0x0098);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_MODULE, 0x0099);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_DRAWER, 0x009a);
+CPUMF_EVENT_ATTR(cf_z17, DCW_OFF_DRAWER, 0x009b);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP_MEMORY, 0x009c);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_MODULE_MEMORY, 0x009d);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_DRAWER_MEMORY, 0x009e);
+CPUMF_EVENT_ATTR(cf_z17, DCW_OFF_DRAWER_MEMORY, 0x009f);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_MODULE_IV, 0x00a0);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_MODULE_CHIP_HIT, 0x00a1);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_MODULE_DRAWER_HIT, 0x00a2);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_DRAWER_IV, 0x00a3);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_DRAWER_CHIP_HIT, 0x00a4);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_DRAWER_DRAWER_HIT, 0x00a5);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_OFF_DRAWER_IV, 0x00a6);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_OFF_DRAWER_CHIP_HIT, 0x00a7);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_OFF_DRAWER_DRAWER_HIT, 0x00a8);
+CPUMF_EVENT_ATTR(cf_z17, ICW_REQ, 0x00a9);
+CPUMF_EVENT_ATTR(cf_z17, ICW_REQ_IV, 0x00aa);
+CPUMF_EVENT_ATTR(cf_z17, ICW_REQ_CHIP_HIT, 0x00ab);
+CPUMF_EVENT_ATTR(cf_z17, ICW_REQ_DRAWER_HIT, 0x00ac);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_CHIP, 0x00ad);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_CHIP_IV, 0x00ae);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_CHIP_CHIP_HIT, 0x00af);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_CHIP_DRAWER_HIT, 0x00b0);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_MODULE, 0x00b1);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_DRAWER, 0x00b2);
+CPUMF_EVENT_ATTR(cf_z17, ICW_OFF_DRAWER, 0x00b3);
+CPUMF_EVENT_ATTR(cf_z17, CYCLES_SAMETHRD, 0x00ca);
+CPUMF_EVENT_ATTR(cf_z17, CYCLES_DIFFTHRD, 0x00cb);
+CPUMF_EVENT_ATTR(cf_z17, INST_SAMETHRD, 0x00cc);
+CPUMF_EVENT_ATTR(cf_z17, INST_DIFFTHRD, 0x00cd);
+CPUMF_EVENT_ATTR(cf_z17, WRONG_BRANCH_PREDICTION, 0x00ce);
+CPUMF_EVENT_ATTR(cf_z17, VX_BCD_EXECUTION_SLOTS, 0x00e1);
+CPUMF_EVENT_ATTR(cf_z17, DECIMAL_INSTRUCTIONS, 0x00e2);
+CPUMF_EVENT_ATTR(cf_z17, LAST_HOST_TRANSLATIONS, 0x00e8);
+CPUMF_EVENT_ATTR(cf_z17, TX_NC_TABORT, 0x00f4);
+CPUMF_EVENT_ATTR(cf_z17, TX_C_TABORT_NO_SPECIAL, 0x00f5);
+CPUMF_EVENT_ATTR(cf_z17, TX_C_TABORT_SPECIAL, 0x00f6);
+CPUMF_EVENT_ATTR(cf_z17, DFLT_ACCESS, 0x00f8);
+CPUMF_EVENT_ATTR(cf_z17, DFLT_CYCLES, 0x00fd);
+CPUMF_EVENT_ATTR(cf_z17, SORTL, 0x0100);
+CPUMF_EVENT_ATTR(cf_z17, DFLT_CC, 0x0109);
+CPUMF_EVENT_ATTR(cf_z17, DFLT_CCFINISH, 0x010a);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_INVOCATIONS, 0x010b);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_COMPLETIONS, 0x010c);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_WAIT_LOCK, 0x010d);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_HOLD_LOCK, 0x010e);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_INST_ONCHIP, 0x0110);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_INST_OFFCHIP, 0x0111);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_INST_DIFF, 0x0112);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_4K_PREFETCH, 0x0114);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_COMPL_LOCK, 0x0115);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_RETRY_LOCK, 0x0116);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_RETRY_LOCK_WITH_PLO, 0x0117);
+CPUMF_EVENT_ATTR(cf_z17, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
+CPUMF_EVENT_ATTR(cf_z17, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
static struct attribute *cpumcf_fvn1_pmu_event_attr[] __initdata = {
CPUMF_EVENT_PTR(cf_fvn1, CPU_CYCLES),
@@ -414,7 +490,7 @@ static struct attribute *cpumcf_svn_12345_pmu_event_attr[] __initdata = {
NULL,
};
-static struct attribute *cpumcf_svn_67_pmu_event_attr[] __initdata = {
+static struct attribute *cpumcf_svn_678_pmu_event_attr[] __initdata = {
CPUMF_EVENT_PTR(cf_svn_12345, PRNG_FUNCTIONS),
CPUMF_EVENT_PTR(cf_svn_12345, PRNG_CYCLES),
CPUMF_EVENT_PTR(cf_svn_12345, PRNG_BLOCKED_FUNCTIONS),
@@ -779,6 +855,87 @@ static struct attribute *cpumcf_z16_pmu_event_attr[] __initdata = {
NULL,
};
+static struct attribute *cpumcf_z17_pmu_event_attr[] __initdata = {
+ CPUMF_EVENT_PTR(cf_z17, L1D_RO_EXCL_WRITES),
+ CPUMF_EVENT_PTR(cf_z17, DTLB2_WRITES),
+ CPUMF_EVENT_PTR(cf_z17, DTLB2_MISSES),
+ CPUMF_EVENT_PTR(cf_z17, CRSTE_1MB_WRITES),
+ CPUMF_EVENT_PTR(cf_z17, DTLB2_GPAGE_WRITES),
+ CPUMF_EVENT_PTR(cf_z17, ITLB2_WRITES),
+ CPUMF_EVENT_PTR(cf_z17, ITLB2_MISSES),
+ CPUMF_EVENT_PTR(cf_z17, TLB2_PTE_WRITES),
+ CPUMF_EVENT_PTR(cf_z17, TLB2_CRSTE_WRITES),
+ CPUMF_EVENT_PTR(cf_z17, TLB2_ENGINES_BUSY),
+ CPUMF_EVENT_PTR(cf_z17, TX_C_TEND),
+ CPUMF_EVENT_PTR(cf_z17, TX_NC_TEND),
+ CPUMF_EVENT_PTR(cf_z17, L1C_TLB2_MISSES),
+ CPUMF_EVENT_PTR(cf_z17, DCW_REQ),
+ CPUMF_EVENT_PTR(cf_z17, DCW_REQ_IV),
+ CPUMF_EVENT_PTR(cf_z17, DCW_REQ_CHIP_HIT),
+ CPUMF_EVENT_PTR(cf_z17, DCW_REQ_DRAWER_HIT),
+ CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP),
+ CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP_IV),
+ CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP_CHIP_HIT),
+ CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP_DRAWER_HIT),
+ CPUMF_EVENT_PTR(cf_z17, DCW_ON_MODULE),
+ CPUMF_EVENT_PTR(cf_z17, DCW_ON_DRAWER),
+ CPUMF_EVENT_PTR(cf_z17, DCW_OFF_DRAWER),
+ CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP_MEMORY),
+ CPUMF_EVENT_PTR(cf_z17, DCW_ON_MODULE_MEMORY),
+ CPUMF_EVENT_PTR(cf_z17, DCW_ON_DRAWER_MEMORY),
+ CPUMF_EVENT_PTR(cf_z17, DCW_OFF_DRAWER_MEMORY),
+ CPUMF_EVENT_PTR(cf_z17, IDCW_ON_MODULE_IV),
+ CPUMF_EVENT_PTR(cf_z17, IDCW_ON_MODULE_CHIP_HIT),
+ CPUMF_EVENT_PTR(cf_z17, IDCW_ON_MODULE_DRAWER_HIT),
+ CPUMF_EVENT_PTR(cf_z17, IDCW_ON_DRAWER_IV),
+ CPUMF_EVENT_PTR(cf_z17, IDCW_ON_DRAWER_CHIP_HIT),
+ CPUMF_EVENT_PTR(cf_z17, IDCW_ON_DRAWER_DRAWER_HIT),
+ CPUMF_EVENT_PTR(cf_z17, IDCW_OFF_DRAWER_IV),
+ CPUMF_EVENT_PTR(cf_z17, IDCW_OFF_DRAWER_CHIP_HIT),
+ CPUMF_EVENT_PTR(cf_z17, IDCW_OFF_DRAWER_DRAWER_HIT),
+ CPUMF_EVENT_PTR(cf_z17, ICW_REQ),
+ CPUMF_EVENT_PTR(cf_z17, ICW_REQ_IV),
+ CPUMF_EVENT_PTR(cf_z17, ICW_REQ_CHIP_HIT),
+ CPUMF_EVENT_PTR(cf_z17, ICW_REQ_DRAWER_HIT),
+ CPUMF_EVENT_PTR(cf_z17, ICW_ON_CHIP),
+ CPUMF_EVENT_PTR(cf_z17, ICW_ON_CHIP_IV),
+ CPUMF_EVENT_PTR(cf_z17, ICW_ON_CHIP_CHIP_HIT),
+ CPUMF_EVENT_PTR(cf_z17, ICW_ON_CHIP_DRAWER_HIT),
+ CPUMF_EVENT_PTR(cf_z17, ICW_ON_MODULE),
+ CPUMF_EVENT_PTR(cf_z17, ICW_ON_DRAWER),
+ CPUMF_EVENT_PTR(cf_z17, ICW_OFF_DRAWER),
+ CPUMF_EVENT_PTR(cf_z17, CYCLES_SAMETHRD),
+ CPUMF_EVENT_PTR(cf_z17, CYCLES_DIFFTHRD),
+ CPUMF_EVENT_PTR(cf_z17, INST_SAMETHRD),
+ CPUMF_EVENT_PTR(cf_z17, INST_DIFFTHRD),
+ CPUMF_EVENT_PTR(cf_z17, WRONG_BRANCH_PREDICTION),
+ CPUMF_EVENT_PTR(cf_z17, VX_BCD_EXECUTION_SLOTS),
+ CPUMF_EVENT_PTR(cf_z17, DECIMAL_INSTRUCTIONS),
+ CPUMF_EVENT_PTR(cf_z17, LAST_HOST_TRANSLATIONS),
+ CPUMF_EVENT_PTR(cf_z17, TX_NC_TABORT),
+ CPUMF_EVENT_PTR(cf_z17, TX_C_TABORT_NO_SPECIAL),
+ CPUMF_EVENT_PTR(cf_z17, TX_C_TABORT_SPECIAL),
+ CPUMF_EVENT_PTR(cf_z17, DFLT_ACCESS),
+ CPUMF_EVENT_PTR(cf_z17, DFLT_CYCLES),
+ CPUMF_EVENT_PTR(cf_z17, SORTL),
+ CPUMF_EVENT_PTR(cf_z17, DFLT_CC),
+ CPUMF_EVENT_PTR(cf_z17, DFLT_CCFINISH),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_INVOCATIONS),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_COMPLETIONS),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_WAIT_LOCK),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_HOLD_LOCK),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_INST_ONCHIP),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_INST_OFFCHIP),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_INST_DIFF),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_4K_PREFETCH),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_COMPL_LOCK),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_RETRY_LOCK),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_RETRY_LOCK_WITH_PLO),
+ CPUMF_EVENT_PTR(cf_z17, MT_DIAG_CYCLES_ONE_THR_ACTIVE),
+ CPUMF_EVENT_PTR(cf_z17, MT_DIAG_CYCLES_TWO_THR_ACTIVE),
+ NULL,
+};
+
/* END: CPUM_CF COUNTER DEFINITIONS ===================================== */
static struct attribute_group cpumcf_pmu_events_group = {
@@ -859,7 +1016,7 @@ __init const struct attribute_group **cpumf_cf_event_group(void)
if (ci.csvn >= 1 && ci.csvn <= 5)
csvn = cpumcf_svn_12345_pmu_event_attr;
else if (ci.csvn >= 6)
- csvn = cpumcf_svn_67_pmu_event_attr;
+ csvn = cpumcf_svn_678_pmu_event_attr;
/* Determine model-specific counter set(s) */
get_cpu_id(&cpu_id);
@@ -892,6 +1049,10 @@ __init const struct attribute_group **cpumf_cf_event_group(void)
case 0x3932:
model = cpumcf_z16_pmu_event_attr;
break;
+ case 0x9175:
+ case 0x9176:
+ model = cpumcf_z17_pmu_event_attr;
+ break;
default:
model = none;
break;
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 5f60248..ad22799 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -885,9 +885,6 @@ static int cpumsf_pmu_event_init(struct perf_event *event)
event->attr.exclude_idle = 0;
err = __hw_perf_event_init(event);
- if (unlikely(err))
- if (event->destroy)
- event->destroy(event);
return err;
}
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 54e2814..80b1f7a 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -294,6 +294,10 @@ static int __init setup_elf_platform(void)
case 0x3932:
strcpy(elf_platform, "z16");
break;
+ case 0x9175:
+ case 0x9176:
+ strcpy(elf_platform, "z17");
+ break;
}
return 0;
}
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 610dd44..a06a000 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -95,7 +95,7 @@ static int handle_validity(struct kvm_vcpu *vcpu)
vcpu->stat.exit_validity++;
trace_kvm_s390_intercept_validity(vcpu, viwhy);
- KVM_EVENT(3, "validity intercept 0x%x for pid %u (kvm 0x%pK)", viwhy,
+ KVM_EVENT(3, "validity intercept 0x%x for pid %u (kvm 0x%p)", viwhy,
current->pid, vcpu->kvm);
/* do not warn on invalid runtime instrumentation mode */
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 2811a6c..60c360c 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -3161,7 +3161,7 @@ void kvm_s390_gisa_clear(struct kvm *kvm)
if (!gi->origin)
return;
gisa_clear_ipm(gi->origin);
- VM_EVENT(kvm, 3, "gisa 0x%pK cleared", gi->origin);
+ VM_EVENT(kvm, 3, "gisa 0x%p cleared", gi->origin);
}
void kvm_s390_gisa_init(struct kvm *kvm)
@@ -3177,7 +3177,7 @@ void kvm_s390_gisa_init(struct kvm *kvm)
hrtimer_setup(&gi->timer, gisa_vcpu_kicker, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
memset(gi->origin, 0, sizeof(struct kvm_s390_gisa));
gi->origin->next_alert = (u32)virt_to_phys(gi->origin);
- VM_EVENT(kvm, 3, "gisa 0x%pK initialized", gi->origin);
+ VM_EVENT(kvm, 3, "gisa 0x%p initialized", gi->origin);
}
void kvm_s390_gisa_enable(struct kvm *kvm)
@@ -3218,7 +3218,7 @@ void kvm_s390_gisa_destroy(struct kvm *kvm)
process_gib_alert_list();
hrtimer_cancel(&gi->timer);
gi->origin = NULL;
- VM_EVENT(kvm, 3, "gisa 0x%pK destroyed", gisa);
+ VM_EVENT(kvm, 3, "gisa 0x%p destroyed", gisa);
}
void kvm_s390_gisa_disable(struct kvm *kvm)
@@ -3467,7 +3467,7 @@ int __init kvm_s390_gib_init(u8 nisc)
}
}
- KVM_EVENT(3, "gib 0x%pK (nisc=%d) initialized", gib, gib->nisc);
+ KVM_EVENT(3, "gib 0x%p (nisc=%d) initialized", gib, gib->nisc);
goto out;
out_unreg_gal:
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index fff8637..3f31751 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1022,7 +1022,7 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
}
mutex_unlock(&kvm->lock);
VM_EVENT(kvm, 3, "SET: max guest address: %lu", new_limit);
- VM_EVENT(kvm, 3, "New guest asce: 0x%pK",
+ VM_EVENT(kvm, 3, "New guest asce: 0x%p",
(void *) kvm->arch.gmap->asce);
break;
}
@@ -3466,7 +3466,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm_s390_gisa_init(kvm);
INIT_LIST_HEAD(&kvm->arch.pv.need_cleanup);
kvm->arch.pv.set_aside = NULL;
- KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
+ KVM_EVENT(3, "vm 0x%p created by pid %u", kvm, current->pid);
return 0;
out_err:
@@ -3529,7 +3529,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
kvm_s390_destroy_adapters(kvm);
kvm_s390_clear_float_irqs(kvm);
kvm_s390_vsie_destroy(kvm);
- KVM_EVENT(3, "vm 0x%pK destroyed", kvm);
+ KVM_EVENT(3, "vm 0x%p destroyed", kvm);
}
/* Section: vcpu related */
@@ -3650,7 +3650,7 @@ static int sca_switch_to_extended(struct kvm *kvm)
free_page((unsigned long)old_sca);
- VM_EVENT(kvm, 2, "Switched to ESCA (0x%pK -> 0x%pK)",
+ VM_EVENT(kvm, 2, "Switched to ESCA (0x%p -> 0x%p)",
old_sca, kvm->arch.sca);
return 0;
}
@@ -4027,7 +4027,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
goto out_free_sie_block;
}
- VM_EVENT(vcpu->kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK",
+ VM_EVENT(vcpu->kvm, 3, "create cpu %d at 0x%p, sie block at 0x%p",
vcpu->vcpu_id, vcpu, vcpu->arch.sie_block);
trace_kvm_s390_create_vcpu(vcpu->vcpu_id, vcpu, vcpu->arch.sie_block);
diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h
index 9ac92db..9e28f16 100644
--- a/arch/s390/kvm/trace-s390.h
+++ b/arch/s390/kvm/trace-s390.h
@@ -56,7 +56,7 @@ TRACE_EVENT(kvm_s390_create_vcpu,
__entry->sie_block = sie_block;
),
- TP_printk("create cpu %d at 0x%pK, sie block at 0x%pK",
+ TP_printk("create cpu %d at 0x%p, sie block at 0x%p",
__entry->id, __entry->vcpu, __entry->sie_block)
);
@@ -255,7 +255,7 @@ TRACE_EVENT(kvm_s390_enable_css,
__entry->kvm = kvm;
),
- TP_printk("enabling channel I/O support (kvm @ %pK)\n",
+ TP_printk("enabling channel I/O support (kvm @ %p)\n",
__entry->kvm)
);
diff --git a/arch/s390/tools/gen_facilities.c b/arch/s390/tools/gen_facilities.c
index 855f818..d5c68ad 100644
--- a/arch/s390/tools/gen_facilities.c
+++ b/arch/s390/tools/gen_facilities.c
@@ -54,6 +54,9 @@ static struct facility_def facility_defs[] = {
#ifdef CONFIG_HAVE_MARCH_Z15_FEATURES
61, /* miscellaneous-instruction-extension 3 */
#endif
+#ifdef CONFIG_HAVE_MARCH_Z17_FEATURES
+ 84, /* miscellaneous-instruction-extension 4 */
+#endif
-1 /* END */
}
},
diff --git a/arch/sh/configs/ap325rxa_defconfig b/arch/sh/configs/ap325rxa_defconfig
index 4464a2a..b6f36c9 100644
--- a/arch/sh/configs/ap325rxa_defconfig
+++ b/arch/sh/configs/ap325rxa_defconfig
@@ -99,4 +99,3 @@
CONFIG_CRYPTO=y
CONFIG_CRYPTO_CBC=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/ecovec24_defconfig b/arch/sh/configs/ecovec24_defconfig
index ee1b366..e76694a 100644
--- a/arch/sh/configs/ecovec24_defconfig
+++ b/arch/sh/configs/ecovec24_defconfig
@@ -128,4 +128,3 @@
CONFIG_CRYPTO=y
CONFIG_CRYPTO_CBC=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/edosk7705_defconfig b/arch/sh/configs/edosk7705_defconfig
index 296ed76..ee3f6db 100644
--- a/arch/sh/configs/edosk7705_defconfig
+++ b/arch/sh/configs/edosk7705_defconfig
@@ -33,4 +33,3 @@
# CONFIG_PROC_FS is not set
# CONFIG_SYSFS is not set
# CONFIG_ENABLE_MUST_CHECK is not set
-# CONFIG_CRC32 is not set
diff --git a/arch/sh/configs/espt_defconfig b/arch/sh/configs/espt_defconfig
index 67716a4..da176f1 100644
--- a/arch/sh/configs/espt_defconfig
+++ b/arch/sh/configs/espt_defconfig
@@ -110,4 +110,3 @@
# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_DEBUG_FS=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/hp6xx_defconfig b/arch/sh/configs/hp6xx_defconfig
index 77e3185..3582af1 100644
--- a/arch/sh/configs/hp6xx_defconfig
+++ b/arch/sh/configs/hp6xx_defconfig
@@ -56,5 +56,3 @@
CONFIG_CRYPTO_MD5=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
# CONFIG_CRYPTO_HW is not set
-CONFIG_CRC16=y
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/kfr2r09-romimage_defconfig b/arch/sh/configs/kfr2r09-romimage_defconfig
index 42bf341..88fbb65 100644
--- a/arch/sh/configs/kfr2r09-romimage_defconfig
+++ b/arch/sh/configs/kfr2r09-romimage_defconfig
@@ -49,4 +49,3 @@
# CONFIG_NETWORK_FILESYSTEMS is not set
# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_DEBUG_FS=y
-# CONFIG_CRC32 is not set
diff --git a/arch/sh/configs/landisk_defconfig b/arch/sh/configs/landisk_defconfig
index d871623..924bb32 100644
--- a/arch/sh/configs/landisk_defconfig
+++ b/arch/sh/configs/landisk_defconfig
@@ -111,4 +111,3 @@
CONFIG_NLS_CODEPAGE_932=y
CONFIG_SH_STANDARD_BIOS=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/lboxre2_defconfig b/arch/sh/configs/lboxre2_defconfig
index 6a23476..0307bb2 100644
--- a/arch/sh/configs/lboxre2_defconfig
+++ b/arch/sh/configs/lboxre2_defconfig
@@ -58,4 +58,3 @@
CONFIG_NLS_CODEPAGE_437=y
CONFIG_SH_STANDARD_BIOS=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/magicpanelr2_defconfig b/arch/sh/configs/magicpanelr2_defconfig
index 8d44374..93b9aa3 100644
--- a/arch/sh/configs/magicpanelr2_defconfig
+++ b/arch/sh/configs/magicpanelr2_defconfig
@@ -86,5 +86,3 @@
CONFIG_DEBUG_KOBJECT=y
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
CONFIG_FRAME_POINTER=y
-CONFIG_CRC_CCITT=m
-CONFIG_CRC16=m
diff --git a/arch/sh/configs/migor_defconfig b/arch/sh/configs/migor_defconfig
index 2d1e65c..fc2010c 100644
--- a/arch/sh/configs/migor_defconfig
+++ b/arch/sh/configs/migor_defconfig
@@ -90,4 +90,3 @@
CONFIG_CRYPTO_MANAGER=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
# CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/r7780mp_defconfig b/arch/sh/configs/r7780mp_defconfig
index 6bd6c0a..f28b8c4 100644
--- a/arch/sh/configs/r7780mp_defconfig
+++ b/arch/sh/configs/r7780mp_defconfig
@@ -105,4 +105,3 @@
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_HMAC=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/r7785rp_defconfig b/arch/sh/configs/r7785rp_defconfig
index cde6685..3a4239f2 100644
--- a/arch/sh/configs/r7785rp_defconfig
+++ b/arch/sh/configs/r7785rp_defconfig
@@ -103,4 +103,3 @@
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_HMAC=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/rts7751r2d1_defconfig b/arch/sh/configs/rts7751r2d1_defconfig
index c863a11..69568cc 100644
--- a/arch/sh/configs/rts7751r2d1_defconfig
+++ b/arch/sh/configs/rts7751r2d1_defconfig
@@ -87,4 +87,3 @@
CONFIG_NLS_CODEPAGE_932=y
CONFIG_DEBUG_FS=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/rts7751r2dplus_defconfig b/arch/sh/configs/rts7751r2dplus_defconfig
index 7e4f710..ecb4bdb 100644
--- a/arch/sh/configs/rts7751r2dplus_defconfig
+++ b/arch/sh/configs/rts7751r2dplus_defconfig
@@ -92,4 +92,3 @@
CONFIG_NLS_CODEPAGE_932=y
CONFIG_DEBUG_FS=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/sdk7780_defconfig b/arch/sh/configs/sdk7780_defconfig
index cd24cf0..9870d16 100644
--- a/arch/sh/configs/sdk7780_defconfig
+++ b/arch/sh/configs/sdk7780_defconfig
@@ -136,4 +136,3 @@
CONFIG_CRYPTO_MD5=y
CONFIG_CRYPTO_DES=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/se7206_defconfig b/arch/sh/configs/se7206_defconfig
index 472fdf3..64f9308 100644
--- a/arch/sh/configs/se7206_defconfig
+++ b/arch/sh/configs/se7206_defconfig
@@ -101,6 +101,3 @@
CONFIG_CRYPTO_LZO=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
# CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_CCITT=y
-CONFIG_CRC16=y
-CONFIG_CRC_ITU_T=y
diff --git a/arch/sh/configs/se7712_defconfig b/arch/sh/configs/se7712_defconfig
index 49a4961..8770a72 100644
--- a/arch/sh/configs/se7712_defconfig
+++ b/arch/sh/configs/se7712_defconfig
@@ -96,4 +96,3 @@
CONFIG_CRYPTO_ECB=m
CONFIG_CRYPTO_PCBC=m
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_CCITT=y
diff --git a/arch/sh/configs/se7721_defconfig b/arch/sh/configs/se7721_defconfig
index de29379..b15c640 100644
--- a/arch/sh/configs/se7721_defconfig
+++ b/arch/sh/configs/se7721_defconfig
@@ -122,4 +122,3 @@
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
CONFIG_FRAME_POINTER=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_CCITT=y
diff --git a/arch/sh/configs/se7724_defconfig b/arch/sh/configs/se7724_defconfig
index 9652127..9501e69 100644
--- a/arch/sh/configs/se7724_defconfig
+++ b/arch/sh/configs/se7724_defconfig
@@ -128,4 +128,3 @@
CONFIG_CRYPTO=y
CONFIG_CRYPTO_CBC=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/sh03_defconfig b/arch/sh/configs/sh03_defconfig
index 48f38ec..4d75c92 100644
--- a/arch/sh/configs/sh03_defconfig
+++ b/arch/sh/configs/sh03_defconfig
@@ -120,6 +120,5 @@
CONFIG_CRYPTO_SHA1=y
CONFIG_CRYPTO_DEFLATE=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_CCITT=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_GENERIC=y
diff --git a/arch/sh/configs/sh2007_defconfig b/arch/sh/configs/sh2007_defconfig
index 1b1174a..cc6292b 100644
--- a/arch/sh/configs/sh2007_defconfig
+++ b/arch/sh/configs/sh2007_defconfig
@@ -193,5 +193,3 @@
CONFIG_CRYPTO_LZO=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
# CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_CCITT=y
-CONFIG_CRC16=y
diff --git a/arch/sh/configs/sh7724_generic_defconfig b/arch/sh/configs/sh7724_generic_defconfig
index 5440bd0..e6298f2 100644
--- a/arch/sh/configs/sh7724_generic_defconfig
+++ b/arch/sh/configs/sh7724_generic_defconfig
@@ -39,4 +39,3 @@
# CONFIG_SYSFS is not set
# CONFIG_MISC_FILESYSTEMS is not set
# CONFIG_ENABLE_MUST_CHECK is not set
-# CONFIG_CRC32 is not set
diff --git a/arch/sh/configs/sh7763rdp_defconfig b/arch/sh/configs/sh7763rdp_defconfig
index 57923c3..b77b331 100644
--- a/arch/sh/configs/sh7763rdp_defconfig
+++ b/arch/sh/configs/sh7763rdp_defconfig
@@ -112,4 +112,3 @@
# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_DEBUG_FS=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/sh7770_generic_defconfig b/arch/sh/configs/sh7770_generic_defconfig
index 4338af8..2e2b4698 100644
--- a/arch/sh/configs/sh7770_generic_defconfig
+++ b/arch/sh/configs/sh7770_generic_defconfig
@@ -41,4 +41,3 @@
# CONFIG_SYSFS is not set
# CONFIG_MISC_FILESYSTEMS is not set
# CONFIG_ENABLE_MUST_CHECK is not set
-# CONFIG_CRC32 is not set
diff --git a/arch/sh/configs/titan_defconfig b/arch/sh/configs/titan_defconfig
index 8e85f20..f022ada 100644
--- a/arch/sh/configs/titan_defconfig
+++ b/arch/sh/configs/titan_defconfig
@@ -264,4 +264,3 @@
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC16=m
diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig
index 01b2bdf..f1ba0fe 100644
--- a/arch/sparc/configs/sparc64_defconfig
+++ b/arch/sparc/configs/sparc64_defconfig
@@ -229,7 +229,6 @@
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC16=m
CONFIG_VCC=m
CONFIG_PATA_CMD64X=y
CONFIG_IP_PNP=y
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 81f55da..640fcac 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -59,7 +59,7 @@
$(obj)/bzImage: asflags-y := $(SVGA_MODE)
quiet_cmd_image = BUILD $@
- cmd_image = cp $< $@; truncate -s %4K $@; cat $(obj)/vmlinux.bin >>$@
+ cmd_image = (dd if=$< bs=4k conv=sync status=none; cat $(filter-out $<,$(real-prereqs))) >$@
$(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin FORCE
$(call if_changed,image)
diff --git a/arch/x86/boot/compressed/mem.c b/arch/x86/boot/compressed/mem.c
index dbba332..f676156 100644
--- a/arch/x86/boot/compressed/mem.c
+++ b/arch/x86/boot/compressed/mem.c
@@ -34,11 +34,14 @@ static bool early_is_tdx_guest(void)
void arch_accept_memory(phys_addr_t start, phys_addr_t end)
{
+ static bool sevsnp;
+
/* Platform-specific memory-acceptance call goes here */
if (early_is_tdx_guest()) {
if (!tdx_accept_memory(start, end))
panic("TDX: Failed to accept memory\n");
- } else if (sev_snp_enabled()) {
+ } else if (sevsnp || (sev_get_status() & MSR_AMD64_SEV_SNP_ENABLED)) {
+ sevsnp = true;
snp_accept_memory(start, end);
} else {
error("Cannot accept memory: unknown platform\n");
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index bb55934..89ba168 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -164,10 +164,7 @@ bool sev_snp_enabled(void)
static void __page_state_change(unsigned long paddr, enum psc_op op)
{
- u64 val;
-
- if (!sev_snp_enabled())
- return;
+ u64 val, msr;
/*
* If private -> shared then invalidate the page before requesting the
@@ -176,6 +173,9 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
if (op == SNP_PAGE_STATE_SHARED)
pvalidate_4k_page(paddr, paddr, false);
+ /* Save the current GHCB MSR value */
+ msr = sev_es_rd_ghcb_msr();
+
/* Issue VMGEXIT to change the page state in RMP table. */
sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op));
VMGEXIT();
@@ -185,6 +185,9 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
if ((GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP) || GHCB_MSR_PSC_RESP_VAL(val))
sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
+ /* Restore the GHCB MSR value */
+ sev_es_wr_ghcb_msr(msr);
+
/*
* Now that page state is changed in the RMP table, validate it so that it is
* consistent with the RMP entry.
@@ -195,11 +198,17 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
void snp_set_page_private(unsigned long paddr)
{
+ if (!sev_snp_enabled())
+ return;
+
__page_state_change(paddr, SNP_PAGE_STATE_PRIVATE);
}
void snp_set_page_shared(unsigned long paddr)
{
+ if (!sev_snp_enabled())
+ return;
+
__page_state_change(paddr, SNP_PAGE_STATE_SHARED);
}
@@ -223,56 +232,10 @@ static bool early_setup_ghcb(void)
return true;
}
-static phys_addr_t __snp_accept_memory(struct snp_psc_desc *desc,
- phys_addr_t pa, phys_addr_t pa_end)
-{
- struct psc_hdr *hdr;
- struct psc_entry *e;
- unsigned int i;
-
- hdr = &desc->hdr;
- memset(hdr, 0, sizeof(*hdr));
-
- e = desc->entries;
-
- i = 0;
- while (pa < pa_end && i < VMGEXIT_PSC_MAX_ENTRY) {
- hdr->end_entry = i;
-
- e->gfn = pa >> PAGE_SHIFT;
- e->operation = SNP_PAGE_STATE_PRIVATE;
- if (IS_ALIGNED(pa, PMD_SIZE) && (pa_end - pa) >= PMD_SIZE) {
- e->pagesize = RMP_PG_SIZE_2M;
- pa += PMD_SIZE;
- } else {
- e->pagesize = RMP_PG_SIZE_4K;
- pa += PAGE_SIZE;
- }
-
- e++;
- i++;
- }
-
- if (vmgexit_psc(boot_ghcb, desc))
- sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
-
- pvalidate_pages(desc);
-
- return pa;
-}
-
void snp_accept_memory(phys_addr_t start, phys_addr_t end)
{
- struct snp_psc_desc desc = {};
- unsigned int i;
- phys_addr_t pa;
-
- if (!boot_ghcb && !early_setup_ghcb())
- sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
-
- pa = start;
- while (pa < end)
- pa = __snp_accept_memory(&desc, pa, end);
+ for (phys_addr_t pa = start; pa < end; pa += PAGE_SIZE)
+ __page_state_change(pa, SNP_PAGE_STATE_PRIVATE);
}
void sev_es_shutdown_ghcb(void)
diff --git a/arch/x86/boot/compressed/sev.h b/arch/x86/boot/compressed/sev.h
index fc725a9..4e463f3 100644
--- a/arch/x86/boot/compressed/sev.h
+++ b/arch/x86/boot/compressed/sev.h
@@ -12,11 +12,13 @@
bool sev_snp_enabled(void);
void snp_accept_memory(phys_addr_t start, phys_addr_t end);
+u64 sev_get_status(void);
#else
static inline bool sev_snp_enabled(void) { return false; }
static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { }
+static inline u64 sev_get_status(void) { return 0; }
#endif
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index d3caa31..175958b 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -17,19 +17,20 @@
.pushsection .noinstr.text, "ax"
-SYM_FUNC_START(entry_ibpb)
+/* Clobbers AX, CX, DX */
+SYM_FUNC_START(write_ibpb)
ANNOTATE_NOENDBR
movl $MSR_IA32_PRED_CMD, %ecx
- movl $PRED_CMD_IBPB, %eax
+ movl _ASM_RIP(x86_pred_cmd), %eax
xorl %edx, %edx
wrmsr
/* Make sure IBPB clears return stack preductions too. */
FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_BUG_IBPB_NO_RET
RET
-SYM_FUNC_END(entry_ibpb)
+SYM_FUNC_END(write_ibpb)
/* For KVM */
-EXPORT_SYMBOL_GPL(entry_ibpb);
+EXPORT_SYMBOL_GPL(write_ibpb);
.popsection
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 6866cc5..3a4f031 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -629,7 +629,7 @@ int x86_pmu_hw_config(struct perf_event *event)
if (event->attr.type == event->pmu->type)
event->hw.config |= x86_pmu_get_event_config(event);
- if (!event->attr.freq && x86_pmu.limit_period) {
+ if (is_sampling_event(event) && !event->attr.freq && x86_pmu.limit_period) {
s64 left = event->attr.sample_period;
x86_pmu.limit_period(event, &left);
if (left > event->attr.sample_period)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 09d2d66..00dfe48 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3049,7 +3049,6 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int bit;
int handled = 0;
- u64 intel_ctrl = hybrid(cpuc->pmu, intel_ctrl);
inc_irq_stat(apic_perf_irqs);
@@ -3093,7 +3092,6 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
handled++;
x86_pmu_handle_guest_pebs(regs, &data);
static_call(x86_pmu_drain_pebs)(regs, &data);
- status &= intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
/*
* PMI throttle may be triggered, which stops the PEBS event.
@@ -3104,6 +3102,15 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
*/
if (pebs_enabled != cpuc->pebs_enabled)
wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
+
+ /*
+ * Above PEBS handler (PEBS counters snapshotting) has updated fixed
+ * counter 3 and perf metrics counts if they are in counter group,
+ * unnecessary to update again.
+ */
+ if (cpuc->events[INTEL_PMC_IDX_FIXED_SLOTS] &&
+ is_pebs_counter_event_group(cpuc->events[INTEL_PMC_IDX_FIXED_SLOTS]))
+ status &= ~GLOBAL_STATUS_PERF_METRICS_OVF_BIT;
}
/*
@@ -3123,6 +3130,8 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
static_call(intel_pmu_update_topdown_event)(NULL, NULL);
}
+ status &= hybrid(cpuc->pmu, intel_ctrl);
+
/*
* Checkpointed counters can lead to 'spurious' PMIs because the
* rollback caused by the PMI will have cleared the overflow status
@@ -7305,8 +7314,17 @@ __init int intel_pmu_init(void)
name = "meteorlake_hybrid";
break;
+ case INTEL_PANTHERLAKE_L:
+ pr_cont("Pantherlake Hybrid events, ");
+ name = "pantherlake_hybrid";
+ goto lnl_common;
+
case INTEL_LUNARLAKE_M:
case INTEL_ARROWLAKE:
+ pr_cont("Lunarlake Hybrid events, ");
+ name = "lunarlake_hybrid";
+
+ lnl_common:
intel_pmu_init_hybrid(hybrid_big_small);
x86_pmu.pebs_latency_data = lnl_latency_data;
@@ -7328,8 +7346,6 @@ __init int intel_pmu_init(void)
intel_pmu_init_skt(&pmu->pmu);
intel_pmu_pebs_data_source_lnl();
- pr_cont("Lunarlake Hybrid events, ");
- name = "lunarlake_hybrid";
break;
case INTEL_ARROWLAKE_H:
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 1f7e1a6..18c3ab5 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1399,8 +1399,10 @@ static u64 pebs_update_adaptive_cfg(struct perf_event *event)
* + precise_ip < 2 for the non event IP
* + For RTM TSX weight we need GPRs for the abort code.
*/
- gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
- (attr->sample_regs_intr & PEBS_GP_REGS);
+ gprs = ((sample_type & PERF_SAMPLE_REGS_INTR) &&
+ (attr->sample_regs_intr & PEBS_GP_REGS)) ||
+ ((sample_type & PERF_SAMPLE_REGS_USER) &&
+ (attr->sample_regs_user & PEBS_GP_REGS));
tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT_TYPE) &&
((attr->config & INTEL_ARCH_EVENT_MASK) ==
@@ -2123,7 +2125,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
regs->flags &= ~PERF_EFLAGS_EXACT;
}
- if (sample_type & PERF_SAMPLE_REGS_INTR)
+ if (sample_type & (PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER))
adaptive_pebs_save_regs(regs, gprs);
}
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 60973c2..76d96df 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -4891,28 +4891,28 @@ static struct uncore_event_desc snr_uncore_iio_freerunning_events[] = {
INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"),
/* Free-Running IIO BANDWIDTH IN Counters */
INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.0517578125e-5"),
INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.0517578125e-5"),
INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.0517578125e-5"),
INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.0517578125e-5"),
INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.0517578125e-5"),
INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.0517578125e-5"),
INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.0517578125e-5"),
INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.0517578125e-5"),
INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"),
{ /* end: all zeroes */ },
};
@@ -5485,37 +5485,6 @@ static struct freerunning_counters icx_iio_freerunning[] = {
[ICX_IIO_MSR_BW_IN] = { 0xaa0, 0x1, 0x10, 8, 48, icx_iio_bw_freerunning_box_offsets },
};
-static struct uncore_event_desc icx_uncore_iio_freerunning_events[] = {
- /* Free-Running IIO CLOCKS Counter */
- INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"),
- /* Free-Running IIO BANDWIDTH IN Counters */
- INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"),
- { /* end: all zeroes */ },
-};
-
static struct intel_uncore_type icx_uncore_iio_free_running = {
.name = "iio_free_running",
.num_counters = 9,
@@ -5523,7 +5492,7 @@ static struct intel_uncore_type icx_uncore_iio_free_running = {
.num_freerunning_types = ICX_IIO_FREERUNNING_TYPE_MAX,
.freerunning = icx_iio_freerunning,
.ops = &skx_uncore_iio_freerunning_ops,
- .event_descs = icx_uncore_iio_freerunning_events,
+ .event_descs = snr_uncore_iio_freerunning_events,
.format_group = &skx_uncore_iio_freerunning_format_group,
};
@@ -6320,69 +6289,13 @@ static struct freerunning_counters spr_iio_freerunning[] = {
[SPR_IIO_MSR_BW_OUT] = { 0x3808, 0x1, 0x10, 8, 48 },
};
-static struct uncore_event_desc spr_uncore_iio_freerunning_events[] = {
- /* Free-Running IIO CLOCKS Counter */
- INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"),
- /* Free-Running IIO BANDWIDTH IN Counters */
- INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"),
- /* Free-Running IIO BANDWIDTH OUT Counters */
- INTEL_UNCORE_EVENT_DESC(bw_out_port0, "event=0xff,umask=0x30"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port0.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port0.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port1, "event=0xff,umask=0x31"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port1.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port1.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port2, "event=0xff,umask=0x32"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port2.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port2.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port3, "event=0xff,umask=0x33"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port3.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port3.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port4, "event=0xff,umask=0x34"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port4.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port4.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port5, "event=0xff,umask=0x35"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port5.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port5.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port6, "event=0xff,umask=0x36"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port6.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port6.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port7, "event=0xff,umask=0x37"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port7.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port7.unit, "MiB"),
- { /* end: all zeroes */ },
-};
-
static struct intel_uncore_type spr_uncore_iio_free_running = {
.name = "iio_free_running",
.num_counters = 17,
.num_freerunning_types = SPR_IIO_FREERUNNING_TYPE_MAX,
.freerunning = spr_iio_freerunning,
.ops = &skx_uncore_iio_freerunning_ops,
- .event_descs = spr_uncore_iio_freerunning_events,
+ .event_descs = snr_uncore_iio_freerunning_events,
.format_group = &skx_uncore_iio_freerunning_format_group,
};
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 3a97a7e..be10c18 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -126,6 +126,8 @@
#define INTEL_GRANITERAPIDS_X IFM(6, 0xAD) /* Redwood Cove */
#define INTEL_GRANITERAPIDS_D IFM(6, 0xAE)
+#define INTEL_BARTLETTLAKE IFM(6, 0xD7) /* Raptor Cove */
+
/* "Hybrid" Processors (P-Core/E-Core) */
#define INTEL_LAKEFIELD IFM(6, 0x8A) /* Sunny Cove / Tremont */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index a884ab5..7bc174a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -35,6 +35,7 @@
#include <asm/mtrr.h>
#include <asm/msr-index.h>
#include <asm/asm.h>
+#include <asm/irq_remapping.h>
#include <asm/kvm_page_track.h>
#include <asm/kvm_vcpu_regs.h>
#include <asm/reboot.h>
@@ -1472,8 +1473,13 @@ struct kvm_arch {
struct once nx_once;
#ifdef CONFIG_X86_64
- /* The number of TDP MMU pages across all roots. */
+#ifdef CONFIG_KVM_PROVE_MMU
+ /*
+ * The number of TDP MMU pages across all roots. Used only to sanity
+ * check that KVM isn't leaking TDP MMU pages.
+ */
atomic64_t tdp_mmu_pages;
+#endif
/*
* List of struct kvm_mmu_pages being used as roots.
@@ -2418,4 +2424,9 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
*/
#define KVM_EXIT_HYPERCALL_MBZ GENMASK_ULL(31, 1)
+static inline bool kvm_arch_has_irq_bypass(void)
+{
+ return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP);
+}
+
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 8a5cc8e..5c43f14 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -269,7 +269,7 @@
* typically has NO_MELTDOWN).
*
* While retbleed_untrain_ret() doesn't clobber anything but requires stack,
- * entry_ibpb() will clobber AX, CX, DX.
+ * write_ibpb() will clobber AX, CX, DX.
*
* As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point
* where we have a stack but before any RET instruction.
@@ -279,7 +279,7 @@
VALIDATE_UNRET_END
CALL_UNTRAIN_RET
ALTERNATIVE_2 "", \
- "call entry_ibpb", \ibpb_feature, \
+ "call write_ibpb", \ibpb_feature, \
__stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH
#endif
.endm
@@ -368,7 +368,7 @@ extern void srso_return_thunk(void);
extern void srso_alias_return_thunk(void);
extern void entry_untrain_ret(void);
-extern void entry_ibpb(void);
+extern void write_ibpb(void);
#ifdef CONFIG_X86_64
extern void clear_bhb_loop(void);
@@ -514,11 +514,11 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
: "memory");
}
-extern u64 x86_pred_cmd;
-
static inline void indirect_branch_prediction_barrier(void)
{
- alternative_msr_write(MSR_IA32_PRED_CMD, x86_pred_cmd, X86_FEATURE_IBPB);
+ asm_inline volatile(ALTERNATIVE("", "call write_ibpb", X86_FEATURE_IBPB)
+ : ASM_CALL_CONSTRAINT
+ :: "rax", "rcx", "rdx", "memory");
}
/* The Intel SPEC CTRL MSR base value cache */
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index a331475..c88691b 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -6,6 +6,8 @@
#include <linux/mm.h> /* for struct page */
#include <linux/pagemap.h>
+#include <asm/cpufeature.h>
+
#define __HAVE_ARCH_PTE_ALLOC_ONE
#define __HAVE_ARCH_PGD_FREE
#include <asm-generic/pgalloc.h>
@@ -29,16 +31,17 @@ static inline void paravirt_release_pud(unsigned long pfn) {}
static inline void paravirt_release_p4d(unsigned long pfn) {}
#endif
-#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
/*
- * Instead of one PGD, we acquire two PGDs. Being order-1, it is
- * both 8k in size and 8k-aligned. That lets us just flip bit 12
- * in a pointer to swap between the two 4k halves.
+ * In case of Page Table Isolation active, we acquire two PGDs instead of one.
+ * Being order-1, it is both 8k in size and 8k-aligned. That lets us just
+ * flip bit 12 in a pointer to swap between the two 4k halves.
*/
-#define PGD_ALLOCATION_ORDER 1
-#else
-#define PGD_ALLOCATION_ORDER 0
-#endif
+static inline unsigned int pgd_allocation_order(void)
+{
+ if (cpu_feature_enabled(X86_FEATURE_PTI))
+ return 1;
+ return 0;
+}
/*
* Allocate and free page tables.
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index 55a5e65..4f84d42 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -16,23 +16,23 @@
#ifdef __ASSEMBLER__
#define ASM_CLAC \
- ALTERNATIVE __stringify(ANNOTATE_IGNORE_ALTERNATIVE), "clac", X86_FEATURE_SMAP
+ ALTERNATIVE "", "clac", X86_FEATURE_SMAP
#define ASM_STAC \
- ALTERNATIVE __stringify(ANNOTATE_IGNORE_ALTERNATIVE), "stac", X86_FEATURE_SMAP
+ ALTERNATIVE "", "stac", X86_FEATURE_SMAP
#else /* __ASSEMBLER__ */
static __always_inline void clac(void)
{
/* Note: a barrier is implicit in alternative() */
- alternative(ANNOTATE_IGNORE_ALTERNATIVE "", "clac", X86_FEATURE_SMAP);
+ alternative("", "clac", X86_FEATURE_SMAP);
}
static __always_inline void stac(void)
{
/* Note: a barrier is implicit in alternative() */
- alternative(ANNOTATE_IGNORE_ALTERNATIVE "", "stac", X86_FEATURE_SMAP);
+ alternative("", "stac", X86_FEATURE_SMAP);
}
static __always_inline unsigned long smap_save(void)
@@ -59,9 +59,9 @@ static __always_inline void smap_restore(unsigned long flags)
/* These macros can be used in asm() statements */
#define ASM_CLAC \
- ALTERNATIVE(ANNOTATE_IGNORE_ALTERNATIVE "", "clac", X86_FEATURE_SMAP)
+ ALTERNATIVE("", "clac", X86_FEATURE_SMAP)
#define ASM_STAC \
- ALTERNATIVE(ANNOTATE_IGNORE_ALTERNATIVE "", "stac", X86_FEATURE_SMAP)
+ ALTERNATIVE("", "stac", X86_FEATURE_SMAP)
#define ASM_CLAC_UNSAFE \
ALTERNATIVE("", ANNOTATE_IGNORE_ALTERNATIVE "clac", X86_FEATURE_SMAP)
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index dae6a73..9fa321a 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -23,6 +23,8 @@
#include <linux/serial_core.h>
#include <linux/pgtable.h>
+#include <xen/xen.h>
+
#include <asm/e820/api.h>
#include <asm/irqdomain.h>
#include <asm/pci_x86.h>
@@ -1729,6 +1731,15 @@ int __init acpi_mps_check(void)
{
#if defined(CONFIG_X86_LOCAL_APIC) && !defined(CONFIG_X86_MPPARSE)
/* mptable code is not built-in*/
+
+ /*
+ * Xen disables ACPI in PV DomU guests but it still emulates APIC and
+ * supports SMP. Returning early here ensures that APIC is not disabled
+ * unnecessarily and the guest is not limited to a single vCPU.
+ */
+ if (xen_pv_domain() && !xen_initial_domain())
+ return 0;
+
if (acpi_disabled || acpi_noirq) {
pr_warn("MPS support code is not built-in, using acpi=off or acpi=noirq or pci=noacpi may have problem\n");
return 1;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 79569f7..2b36379 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -805,6 +805,7 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
static const struct x86_cpu_id erratum_1386_microcode[] = {
X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, 0x17, 0x01), 0x2, 0x2, 0x0800126e),
X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, 0x17, 0x31), 0x0, 0x0, 0x08301052),
+ {}
};
static void fix_erratum_1386(struct cpuinfo_x86 *c)
@@ -868,6 +869,16 @@ static void init_amd_zen1(struct cpuinfo_x86 *c)
pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n");
setup_force_cpu_bug(X86_BUG_DIV0);
+
+ /*
+ * Turn off the Instructions Retired free counter on machines that are
+ * susceptible to erratum #1054 "Instructions Retired Performance
+ * Counter May Be Inaccurate".
+ */
+ if (c->x86_model < 0x30) {
+ msr_clear_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
+ clear_cpu_cap(c, X86_FEATURE_IRPERF);
+ }
}
static bool cpu_has_zenbleed_microcode(void)
@@ -1051,13 +1062,8 @@ static void init_amd(struct cpuinfo_x86 *c)
if (!cpu_feature_enabled(X86_FEATURE_XENPV))
set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
- /*
- * Turn on the Instructions Retired free counter on machines not
- * susceptible to erratum #1054 "Instructions Retired Performance
- * Counter May Be Inaccurate".
- */
- if (cpu_has(c, X86_FEATURE_IRPERF) &&
- (boot_cpu_has(X86_FEATURE_ZEN1) && c->x86_model > 0x2f))
+ /* Enable the Instructions Retired free counter */
+ if (cpu_has(c, X86_FEATURE_IRPERF))
msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
check_null_seg_clears_base(c);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 4386aa6..362602b 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -59,7 +59,6 @@ DEFINE_PER_CPU(u64, x86_spec_ctrl_current);
EXPORT_PER_CPU_SYMBOL_GPL(x86_spec_ctrl_current);
u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB;
-EXPORT_SYMBOL_GPL(x86_pred_cmd);
static u64 __ro_after_init x86_arch_cap_msr;
@@ -1142,7 +1141,7 @@ static void __init retbleed_select_mitigation(void)
setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
/*
- * There is no need for RSB filling: entry_ibpb() ensures
+ * There is no need for RSB filling: write_ibpb() ensures
* all predictions, including the RSB, are invalidated,
* regardless of IBPB implementation.
*/
@@ -1592,51 +1591,54 @@ static void __init spec_ctrl_disable_kernel_rrsba(void)
rrsba_disabled = true;
}
-static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_mitigation mode)
+static void __init spectre_v2_select_rsb_mitigation(enum spectre_v2_mitigation mode)
{
/*
- * Similar to context switches, there are two types of RSB attacks
- * after VM exit:
+ * WARNING! There are many subtleties to consider when changing *any*
+ * code related to RSB-related mitigations. Before doing so, carefully
+ * read the following document, and update if necessary:
*
- * 1) RSB underflow
+ * Documentation/admin-guide/hw-vuln/rsb.rst
*
- * 2) Poisoned RSB entry
+ * In an overly simplified nutshell:
*
- * When retpoline is enabled, both are mitigated by filling/clearing
- * the RSB.
+ * - User->user RSB attacks are conditionally mitigated during
+ * context switches by cond_mitigation -> write_ibpb().
*
- * When IBRS is enabled, while #1 would be mitigated by the IBRS branch
- * prediction isolation protections, RSB still needs to be cleared
- * because of #2. Note that SMEP provides no protection here, unlike
- * user-space-poisoned RSB entries.
+ * - User->kernel and guest->host attacks are mitigated by eIBRS or
+ * RSB filling.
*
- * eIBRS should protect against RSB poisoning, but if the EIBRS_PBRSB
- * bug is present then a LITE version of RSB protection is required,
- * just a single call needs to retire before a RET is executed.
+ * Though, depending on config, note that other alternative
+ * mitigations may end up getting used instead, e.g., IBPB on
+ * entry/vmexit, call depth tracking, or return thunks.
*/
+
switch (mode) {
case SPECTRE_V2_NONE:
- return;
+ break;
- case SPECTRE_V2_EIBRS_LFENCE:
case SPECTRE_V2_EIBRS:
- if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) {
- setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT_LITE);
- pr_info("Spectre v2 / PBRSB-eIBRS: Retire a single CALL on VMEXIT\n");
- }
- return;
-
+ case SPECTRE_V2_EIBRS_LFENCE:
case SPECTRE_V2_EIBRS_RETPOLINE:
+ if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) {
+ pr_info("Spectre v2 / PBRSB-eIBRS: Retire a single CALL on VMEXIT\n");
+ setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT_LITE);
+ }
+ break;
+
case SPECTRE_V2_RETPOLINE:
case SPECTRE_V2_LFENCE:
case SPECTRE_V2_IBRS:
+ pr_info("Spectre v2 / SpectreRSB: Filling RSB on context switch and VMEXIT\n");
+ setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT);
- pr_info("Spectre v2 / SpectreRSB : Filling RSB on VMEXIT\n");
- return;
- }
+ break;
- pr_warn_once("Unknown Spectre v2 mode, disabling RSB mitigation at VM exit");
- dump_stack();
+ default:
+ pr_warn_once("Unknown Spectre v2 mode, disabling RSB mitigation\n");
+ dump_stack();
+ break;
+ }
}
/*
@@ -1830,48 +1832,7 @@ static void __init spectre_v2_select_mitigation(void)
spectre_v2_enabled = mode;
pr_info("%s\n", spectre_v2_strings[mode]);
- /*
- * If Spectre v2 protection has been enabled, fill the RSB during a
- * context switch. In general there are two types of RSB attacks
- * across context switches, for which the CALLs/RETs may be unbalanced.
- *
- * 1) RSB underflow
- *
- * Some Intel parts have "bottomless RSB". When the RSB is empty,
- * speculated return targets may come from the branch predictor,
- * which could have a user-poisoned BTB or BHB entry.
- *
- * AMD has it even worse: *all* returns are speculated from the BTB,
- * regardless of the state of the RSB.
- *
- * When IBRS or eIBRS is enabled, the "user -> kernel" attack
- * scenario is mitigated by the IBRS branch prediction isolation
- * properties, so the RSB buffer filling wouldn't be necessary to
- * protect against this type of attack.
- *
- * The "user -> user" attack scenario is mitigated by RSB filling.
- *
- * 2) Poisoned RSB entry
- *
- * If the 'next' in-kernel return stack is shorter than 'prev',
- * 'next' could be tricked into speculating with a user-poisoned RSB
- * entry.
- *
- * The "user -> kernel" attack scenario is mitigated by SMEP and
- * eIBRS.
- *
- * The "user -> user" scenario, also known as SpectreBHB, requires
- * RSB clearing.
- *
- * So to mitigate all cases, unconditionally fill RSB on context
- * switches.
- *
- * FIXME: Is this pointless for retbleed-affected AMD?
- */
- setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
- pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");
-
- spectre_v2_determine_rsb_fill_type_at_vmexit(mode);
+ spectre_v2_select_rsb_mitigation(mode);
/*
* Retpoline protects the kernel, but doesn't protect firmware. IBRS
@@ -2676,7 +2637,7 @@ static void __init srso_select_mitigation(void)
setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
/*
- * There is no need for RSB filling: entry_ibpb() ensures
+ * There is no need for RSB filling: write_ibpb() ensures
* all predictions, including the RSB, are invalidated,
* regardless of IBPB implementation.
*/
@@ -2701,7 +2662,7 @@ static void __init srso_select_mitigation(void)
srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT;
/*
- * There is no need for RSB filling: entry_ibpb() ensures
+ * There is no need for RSB filling: write_ibpb() ensures
* all predictions, including the RSB, are invalidated,
* regardless of IBPB implementation.
*/
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index b61028c..4a10d35 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -199,6 +199,12 @@ static bool need_sha_check(u32 cur_rev)
case 0xa70c0: return cur_rev <= 0xa70C009; break;
case 0xaa001: return cur_rev <= 0xaa00116; break;
case 0xaa002: return cur_rev <= 0xaa00218; break;
+ case 0xb0021: return cur_rev <= 0xb002146; break;
+ case 0xb1010: return cur_rev <= 0xb101046; break;
+ case 0xb2040: return cur_rev <= 0xb204031; break;
+ case 0xb4040: return cur_rev <= 0xb404031; break;
+ case 0xb6000: return cur_rev <= 0xb600031; break;
+ case 0xb7000: return cur_rev <= 0xb700031; break;
default: break;
}
@@ -214,8 +220,7 @@ static bool verify_sha256_digest(u32 patch_id, u32 cur_rev, const u8 *data, unsi
struct sha256_state s;
int i;
- if (x86_family(bsp_cpuid_1_eax) < 0x17 ||
- x86_family(bsp_cpuid_1_eax) > 0x19)
+ if (x86_family(bsp_cpuid_1_eax) < 0x17)
return true;
if (!need_sha_check(cur_rev))
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 93ec829..cc4a541 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -3553,6 +3553,22 @@ static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp)
free_rmid(rgrp->closid, rgrp->mon.rmid);
}
+/*
+ * We allow creating mon groups only with in a directory called "mon_groups"
+ * which is present in every ctrl_mon group. Check if this is a valid
+ * "mon_groups" directory.
+ *
+ * 1. The directory should be named "mon_groups".
+ * 2. The mon group itself should "not" be named "mon_groups".
+ * This makes sure "mon_groups" directory always has a ctrl_mon group
+ * as parent.
+ */
+static bool is_mon_groups(struct kernfs_node *kn, const char *name)
+{
+ return (!strcmp(rdt_kn_name(kn), "mon_groups") &&
+ strcmp(name, "mon_groups"));
+}
+
static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
const char *name, umode_t mode,
enum rdt_group_type rtype, struct rdtgroup **r)
@@ -3568,6 +3584,15 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
goto out_unlock;
}
+ /*
+ * Check that the parent directory for a monitor group is a "mon_groups"
+ * directory.
+ */
+ if (rtype == RDTMON_GROUP && !is_mon_groups(parent_kn, name)) {
+ ret = -EPERM;
+ goto out_unlock;
+ }
+
if (rtype == RDTMON_GROUP &&
(prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) {
@@ -3751,22 +3776,6 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
return ret;
}
-/*
- * We allow creating mon groups only with in a directory called "mon_groups"
- * which is present in every ctrl_mon group. Check if this is a valid
- * "mon_groups" directory.
- *
- * 1. The directory should be named "mon_groups".
- * 2. The mon group itself should "not" be named "mon_groups".
- * This makes sure "mon_groups" directory always has a ctrl_mon group
- * as parent.
- */
-static bool is_mon_groups(struct kernfs_node *kn, const char *name)
-{
- return (!strcmp(rdt_kn_name(kn), "mon_groups") &&
- strcmp(name, "mon_groups"));
-}
-
static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
umode_t mode)
{
@@ -3782,11 +3791,8 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
if (resctrl_arch_alloc_capable() && parent_kn == rdtgroup_default.kn)
return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode);
- /*
- * If RDT monitoring is supported and the parent directory is a valid
- * "mon_groups" directory, add a monitoring subdirectory.
- */
- if (resctrl_arch_mon_capable() && is_mon_groups(parent_kn, name))
+ /* Else, attempt to add a monitoring subdirectory. */
+ if (resctrl_arch_mon_capable())
return rdtgroup_mkdir_mon(parent_kn, name, mode);
return -EPERM;
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 57120f0..9920122 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -753,22 +753,21 @@ void __init e820__memory_setup_extended(u64 phys_addr, u32 data_len)
void __init e820__register_nosave_regions(unsigned long limit_pfn)
{
int i;
- unsigned long pfn = 0;
+ u64 last_addr = 0;
for (i = 0; i < e820_table->nr_entries; i++) {
struct e820_entry *entry = &e820_table->entries[i];
- if (pfn < PFN_UP(entry->addr))
- register_nosave_region(pfn, PFN_UP(entry->addr));
-
- pfn = PFN_DOWN(entry->addr + entry->size);
-
if (entry->type != E820_TYPE_RAM)
- register_nosave_region(PFN_UP(entry->addr), pfn);
+ continue;
- if (pfn >= limit_pfn)
- break;
+ if (last_addr < entry->addr)
+ register_nosave_region(PFN_DOWN(last_addr), PFN_UP(entry->addr));
+
+ last_addr = entry->addr + entry->size;
}
+
+ register_nosave_region(PFN_DOWN(last_addr), limit_pfn);
}
#ifdef CONFIG_ACPI
@@ -1300,6 +1299,14 @@ void __init e820__memblock_setup(void)
memblock_add(entry->addr, entry->size);
}
+ /*
+ * 32-bit systems are limited to 4BG of memory even with HIGHMEM and
+ * to even less without it.
+ * Discard memory after max_pfn - the actual limit detected at runtime.
+ */
+ if (IS_ENABLED(CONFIG_X86_32))
+ memblock_remove(PFN_PHYS(max_pfn), -1);
+
/* Throw away partial pages: */
memblock_trim_memory(PAGE_SIZE);
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 611f27e..3aad78b 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -389,10 +389,10 @@ static int __init setup_early_printk(char *buf)
keep = (strstr(buf, "keep") != NULL);
while (*buf != '\0') {
- if (!strncmp(buf, "mmio", 4)) {
- early_mmio_serial_init(buf + 4);
+ if (!strncmp(buf, "mmio32", 6)) {
+ buf += 6;
+ early_mmio_serial_init(buf);
early_console_register(&early_serial_console, keep);
- buf += 4;
}
if (!strncmp(buf, "serial", 6)) {
buf += 6;
@@ -407,9 +407,9 @@ static int __init setup_early_printk(char *buf)
}
#ifdef CONFIG_PCI
if (!strncmp(buf, "pciserial", 9)) {
- early_pci_serial_init(buf + 9);
+ buf += 9; /* Keep from match the above "pciserial" */
+ early_pci_serial_init(buf);
early_console_register(&early_serial_console, keep);
- buf += 9; /* Keep from match the above "serial" */
}
#endif
if (!strncmp(buf, "vga", 3) &&
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index 80e262b..cb9852a 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -46,7 +46,8 @@ bool __init pit_timer_init(void)
* VMMs otherwise steal CPU time just to pointlessly waggle
* the (masked) IRQ.
*/
- clockevent_i8253_disable();
+ scoped_guard(irq)
+ clockevent_i8253_disable();
return false;
}
clockevent_i8253_init(true);
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 8026516..1f32530 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -42,7 +42,7 @@ static void load_segments(void)
static void machine_kexec_free_page_tables(struct kimage *image)
{
- free_pages((unsigned long)image->arch.pgd, PGD_ALLOCATION_ORDER);
+ free_pages((unsigned long)image->arch.pgd, pgd_allocation_order());
image->arch.pgd = NULL;
#ifdef CONFIG_X86_PAE
free_page((unsigned long)image->arch.pmd0);
@@ -59,7 +59,7 @@ static void machine_kexec_free_page_tables(struct kimage *image)
static int machine_kexec_alloc_page_tables(struct kimage *image)
{
image->arch.pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
- PGD_ALLOCATION_ORDER);
+ pgd_allocation_order());
#ifdef CONFIG_X86_PAE
image->arch.pmd0 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
image->arch.pmd1 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index ccdc45e..aa4d022 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -466,10 +466,18 @@
}
/*
- * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
+ * COMPILE_TEST kernels can be large - CONFIG_KASAN, for example, can cause
+ * this. Let's assume that nobody will be running a COMPILE_TEST kernel and
+ * let's assert that fuller build coverage is more valuable than being able to
+ * run a COMPILE_TEST kernel.
+ */
+#ifndef CONFIG_COMPILE_TEST
+/*
+ * The ASSERT() sync to . is intentional, for binutils 2.14 compatibility:
*/
. = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
"kernel image bigger than KERNEL_IMAGE_SIZE");
+#endif
/* needed for Clang - see arch/x86/entry/entry.S */
PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 5e4d493..571c906 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -1427,8 +1427,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
}
break;
case 0xa: { /* Architectural Performance Monitoring */
- union cpuid10_eax eax;
- union cpuid10_edx edx;
+ union cpuid10_eax eax = { };
+ union cpuid10_edx edx = { };
if (!enable_pmu || !static_cpu_has(X86_FEATURE_ARCH_PERFMON)) {
entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
@@ -1444,8 +1444,6 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
if (kvm_pmu_cap.version)
edx.split.anythread_deprecated = 1;
- edx.split.reserved1 = 0;
- edx.split.reserved2 = 0;
entry->eax = eax.full;
entry->ebx = kvm_pmu_cap.events_mask;
@@ -1763,7 +1761,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
break;
/* AMD Extended Performance Monitoring and Debug */
case 0x80000022: {
- union cpuid_0x80000022_ebx ebx;
+ union cpuid_0x80000022_ebx ebx = { };
entry->ecx = entry->edx = 0;
if (!enable_pmu || !kvm_cpu_cap_has(X86_FEATURE_PERFMON_V2)) {
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 7cc0564..21a3b81 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -40,7 +40,9 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
kvm_tdp_mmu_invalidate_roots(kvm, KVM_VALID_ROOTS);
kvm_tdp_mmu_zap_invalidated_roots(kvm, false);
- WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages));
+#ifdef CONFIG_KVM_PROVE_MMU
+ KVM_MMU_WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages));
+#endif
WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
/*
@@ -325,13 +327,17 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
static void tdp_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
kvm_account_pgtable_pages((void *)sp->spt, +1);
+#ifdef CONFIG_KVM_PROVE_MMU
atomic64_inc(&kvm->arch.tdp_mmu_pages);
+#endif
}
static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
kvm_account_pgtable_pages((void *)sp->spt, -1);
+#ifdef CONFIG_KVM_PROVE_MMU
atomic64_dec(&kvm->arch.tdp_mmu_pages);
+#endif
}
/**
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 65fd245..7338879 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -796,12 +796,15 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
struct amd_svm_iommu_ir *ir;
u64 entry;
+ if (WARN_ON_ONCE(!pi->ir_data))
+ return -EINVAL;
+
/**
* In some cases, the existing irte is updated and re-set,
* so we need to check here if it's already been * added
* to the ir_list.
*/
- if (pi->ir_data && (pi->prev_ga_tag != 0)) {
+ if (pi->prev_ga_tag) {
struct kvm *kvm = svm->vcpu.kvm;
u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag);
struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
@@ -820,7 +823,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
* Allocating new amd_iommu_pi_data, which will get
* add to the per-vcpu ir_list.
*/
- ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL_ACCOUNT);
+ ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_ATOMIC | __GFP_ACCOUNT);
if (!ir) {
ret = -ENOMEM;
goto out;
@@ -896,10 +899,10 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
{
struct kvm_kernel_irq_routing_entry *e;
struct kvm_irq_routing_table *irq_rt;
+ bool enable_remapped_mode = true;
int idx, ret = 0;
- if (!kvm_arch_has_assigned_device(kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP))
+ if (!kvm_arch_has_assigned_device(kvm) || !kvm_arch_has_irq_bypass())
return 0;
pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n",
@@ -933,6 +936,8 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
kvm_vcpu_apicv_active(&svm->vcpu)) {
struct amd_iommu_pi_data pi;
+ enable_remapped_mode = false;
+
/* Try to enable guest_mode in IRTE */
pi.base = __sme_set(page_to_phys(svm->avic_backing_page) &
AVIC_HPA_MASK);
@@ -951,33 +956,6 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
*/
if (!ret && pi.is_guest_mode)
svm_ir_list_add(svm, &pi);
- } else {
- /* Use legacy mode in IRTE */
- struct amd_iommu_pi_data pi;
-
- /**
- * Here, pi is used to:
- * - Tell IOMMU to use legacy mode for this interrupt.
- * - Retrieve ga_tag of prior interrupt remapping data.
- */
- pi.prev_ga_tag = 0;
- pi.is_guest_mode = false;
- ret = irq_set_vcpu_affinity(host_irq, &pi);
-
- /**
- * Check if the posted interrupt was previously
- * setup with the guest_mode by checking if the ga_tag
- * was cached. If so, we need to clean up the per-vcpu
- * ir_list.
- */
- if (!ret && pi.prev_ga_tag) {
- int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
- struct kvm_vcpu *vcpu;
-
- vcpu = kvm_get_vcpu_by_id(kvm, id);
- if (vcpu)
- svm_ir_list_del(to_svm(vcpu), &pi);
- }
}
if (!ret && svm) {
@@ -993,6 +971,34 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
}
ret = 0;
+ if (enable_remapped_mode) {
+ /* Use legacy mode in IRTE */
+ struct amd_iommu_pi_data pi;
+
+ /**
+ * Here, pi is used to:
+ * - Tell IOMMU to use legacy mode for this interrupt.
+ * - Retrieve ga_tag of prior interrupt remapping data.
+ */
+ pi.prev_ga_tag = 0;
+ pi.is_guest_mode = false;
+ ret = irq_set_vcpu_affinity(host_irq, &pi);
+
+ /**
+ * Check if the posted interrupt was previously
+ * setup with the guest_mode by checking if the ga_tag
+ * was cached. If so, we need to clean up the per-vcpu
+ * ir_list.
+ */
+ if (!ret && pi.prev_ga_tag) {
+ int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
+ struct kvm_vcpu *vcpu;
+
+ vcpu = kvm_get_vcpu_by_id(kvm, id);
+ if (vcpu)
+ svm_ir_list_del(to_svm(vcpu), &pi);
+ }
+ }
out:
srcu_read_unlock(&kvm->irq_srcu, idx);
return ret;
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index ccda95e53..ba736cb 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -11,6 +11,13 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM kvm
+#ifdef CREATE_TRACE_POINTS
+#define tracing_kvm_rip_read(vcpu) ({ \
+ typeof(vcpu) __vcpu = vcpu; \
+ __vcpu->arch.guest_state_protected ? 0 : kvm_rip_read(__vcpu); \
+ })
+#endif
+
/*
* Tracepoint for guest mode entry.
*/
@@ -28,7 +35,7 @@ TRACE_EVENT(kvm_entry,
TP_fast_assign(
__entry->vcpu_id = vcpu->vcpu_id;
- __entry->rip = kvm_rip_read(vcpu);
+ __entry->rip = tracing_kvm_rip_read(vcpu);
__entry->immediate_exit = force_immediate_exit;
kvm_x86_call(get_entry_info)(vcpu, &__entry->intr_info,
@@ -319,7 +326,7 @@ TRACE_EVENT(name, \
), \
\
TP_fast_assign( \
- __entry->guest_rip = kvm_rip_read(vcpu); \
+ __entry->guest_rip = tracing_kvm_rip_read(vcpu); \
__entry->isa = isa; \
__entry->vcpu_id = vcpu->vcpu_id; \
__entry->requests = READ_ONCE(vcpu->requests); \
@@ -423,7 +430,7 @@ TRACE_EVENT(kvm_page_fault,
TP_fast_assign(
__entry->vcpu_id = vcpu->vcpu_id;
- __entry->guest_rip = kvm_rip_read(vcpu);
+ __entry->guest_rip = tracing_kvm_rip_read(vcpu);
__entry->fault_address = fault_address;
__entry->error_code = error_code;
),
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index ec08fa3..d70e5b9 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -31,6 +31,8 @@ static DEFINE_PER_CPU(struct list_head, wakeup_vcpus_on_cpu);
*/
static DEFINE_PER_CPU(raw_spinlock_t, wakeup_vcpus_on_cpu_lock);
+#define PI_LOCK_SCHED_OUT SINGLE_DEPTH_NESTING
+
static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
{
return &(to_vmx(vcpu)->pi_desc);
@@ -89,9 +91,20 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
* current pCPU if the task was migrated.
*/
if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR) {
- raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
+ raw_spinlock_t *spinlock = &per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu);
+
+ /*
+ * In addition to taking the wakeup lock for the regular/IRQ
+ * context, tell lockdep it is being taken for the "sched out"
+ * context as well. vCPU loads happens in task context, and
+ * this is taking the lock of the *previous* CPU, i.e. can race
+ * with both the scheduler and the wakeup handler.
+ */
+ raw_spin_lock(spinlock);
+ spin_acquire(&spinlock->dep_map, PI_LOCK_SCHED_OUT, 0, _RET_IP_);
list_del(&vmx->pi_wakeup_list);
- raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
+ spin_release(&spinlock->dep_map, _RET_IP_);
+ raw_spin_unlock(spinlock);
}
dest = cpu_physical_id(cpu);
@@ -148,11 +161,23 @@ static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu)
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct pi_desc old, new;
- unsigned long flags;
- local_irq_save(flags);
+ lockdep_assert_irqs_disabled();
- raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
+ /*
+ * Acquire the wakeup lock using the "sched out" context to workaround
+ * a lockdep false positive. When this is called, schedule() holds
+ * various per-CPU scheduler locks. When the wakeup handler runs, it
+ * holds this CPU's wakeup lock while calling try_to_wake_up(), which
+ * can eventually take the aforementioned scheduler locks, which causes
+ * lockdep to assume there is deadlock.
+ *
+ * Deadlock can't actually occur because IRQs are disabled for the
+ * entirety of the sched_out critical section, i.e. the wakeup handler
+ * can't run while the scheduler locks are held.
+ */
+ raw_spin_lock_nested(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu),
+ PI_LOCK_SCHED_OUT);
list_add_tail(&vmx->pi_wakeup_list,
&per_cpu(wakeup_vcpus_on_cpu, vcpu->cpu));
raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
@@ -176,8 +201,6 @@ static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu)
*/
if (pi_test_on(&new))
__apic_send_IPI_self(POSTED_INTR_WAKEUP_VECTOR);
-
- local_irq_restore(flags);
}
static bool vmx_needs_pi_wakeup(struct kvm_vcpu *vcpu)
@@ -274,6 +297,7 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
{
struct kvm_kernel_irq_routing_entry *e;
struct kvm_irq_routing_table *irq_rt;
+ bool enable_remapped_mode = true;
struct kvm_lapic_irq irq;
struct kvm_vcpu *vcpu;
struct vcpu_data vcpu_info;
@@ -312,21 +336,8 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
kvm_set_msi_irq(kvm, e, &irq);
if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
- !kvm_irq_is_postable(&irq)) {
- /*
- * Make sure the IRTE is in remapped mode if
- * we don't handle it in posted mode.
- */
- ret = irq_set_vcpu_affinity(host_irq, NULL);
- if (ret < 0) {
- printk(KERN_INFO
- "failed to back to remapped mode, irq: %u\n",
- host_irq);
- goto out;
- }
-
+ !kvm_irq_is_postable(&irq))
continue;
- }
vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
vcpu_info.vector = irq.vector;
@@ -334,11 +345,12 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
vcpu_info.vector, vcpu_info.pi_desc_addr, set);
- if (set)
- ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
- else
- ret = irq_set_vcpu_affinity(host_irq, NULL);
+ if (!set)
+ continue;
+ enable_remapped_mode = false;
+
+ ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
if (ret < 0) {
printk(KERN_INFO "%s: failed to update PI IRTE\n",
__func__);
@@ -346,6 +358,9 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
}
}
+ if (enable_remapped_mode)
+ ret = irq_set_vcpu_affinity(host_irq, NULL);
+
ret = 0;
out:
srcu_read_unlock(&kvm->irq_srcu, idx);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c841817a..df5b99e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11098,7 +11098,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
/*
* Profile KVM exit RIPs:
*/
- if (unlikely(prof_on == KVM_PROFILING)) {
+ if (unlikely(prof_on == KVM_PROFILING &&
+ !vcpu->arch.guest_state_protected)) {
unsigned long rip = kvm_rip_read(vcpu);
profile_hit(KVM_PROFILING, (void *)rip);
}
@@ -11786,6 +11787,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
if (kvm_mpx_supported())
kvm_load_guest_fpu(vcpu);
+ kvm_vcpu_srcu_read_lock(vcpu);
+
r = kvm_apic_accept_events(vcpu);
if (r < 0)
goto out;
@@ -11799,6 +11802,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
mp_state->mp_state = vcpu->arch.mp_state;
out:
+ kvm_vcpu_srcu_read_unlock(vcpu);
+
if (kvm_mpx_supported())
kvm_put_guest_fpu(vcpu);
vcpu_put(vcpu);
@@ -13552,25 +13557,27 @@ bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
}
EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma);
-bool kvm_arch_has_irq_bypass(void)
-{
- return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP);
-}
-
int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
struct irq_bypass_producer *prod)
{
struct kvm_kernel_irqfd *irqfd =
container_of(cons, struct kvm_kernel_irqfd, consumer);
+ struct kvm *kvm = irqfd->kvm;
int ret;
- irqfd->producer = prod;
kvm_arch_start_assignment(irqfd->kvm);
+
+ spin_lock_irq(&kvm->irqfds.lock);
+ irqfd->producer = prod;
+
ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
prod->irq, irqfd->gsi, 1);
if (ret)
kvm_arch_end_assignment(irqfd->kvm);
+ spin_unlock_irq(&kvm->irqfds.lock);
+
+
return ret;
}
@@ -13580,9 +13587,9 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
int ret;
struct kvm_kernel_irqfd *irqfd =
container_of(cons, struct kvm_kernel_irqfd, consumer);
+ struct kvm *kvm = irqfd->kvm;
WARN_ON(irqfd->producer != prod);
- irqfd->producer = NULL;
/*
* When producer of consumer is unregistered, we change back to
@@ -13590,12 +13597,18 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
* when the irq is masked/disabled or the consumer side (KVM
* int this case doesn't want to receive the interrupts.
*/
+ spin_lock_irq(&kvm->irqfds.lock);
+ irqfd->producer = NULL;
+
ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
prod->irq, irqfd->gsi, 0);
if (ret)
printk(KERN_INFO "irq bypass consumer (token %p) unregistration"
" fails: %d\n", irqfd->consumer.token, ret);
+ spin_unlock_irq(&kvm->irqfds.lock);
+
+
kvm_arch_end_assignment(irqfd->kvm);
}
@@ -13608,7 +13621,8 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
struct kvm_kernel_irq_routing_entry *new)
{
- if (new->type != KVM_IRQ_ROUTING_MSI)
+ if (old->type != KVM_IRQ_ROUTING_MSI ||
+ new->type != KVM_IRQ_ROUTING_MSI)
return true;
return !!memcmp(&old->msi, &new->msi, sizeof(new->msi));
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index caedb3e..f5dd84e 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -996,8 +996,8 @@
83: Grp1 Ev,Ib (1A),(es)
# CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL,
# CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ
-84: CTESTSCC (ev)
-85: CTESTSCC (es) | CTESTSCC (66),(es)
+84: CTESTSCC Eb,Gb (ev)
+85: CTESTSCC Ev,Gv (es) | CTESTSCC Ev,Gv (66),(es)
88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es)
8f: POP2 Bq,Rq (000),(11B),(ev)
a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es)
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index a05fcdd..f7ae44d3 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -360,7 +360,7 @@ static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
* We allocate one page for pgd.
*/
if (!SHARED_KERNEL_PMD)
- return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
+ return __pgd_alloc(mm, pgd_allocation_order());
/*
* Now PAE kernel is not running as a Xen domain. We can allocate
@@ -380,7 +380,7 @@ static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
{
- return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
+ return __pgd_alloc(mm, pgd_allocation_order());
}
static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index e459d97..eb83348f 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -667,9 +667,9 @@ static void cond_mitigation(struct task_struct *next)
prev_mm = this_cpu_read(cpu_tlbstate.last_user_mm_spec);
/*
- * Avoid user/user BTB poisoning by flushing the branch predictor
- * when switching between processes. This stops one process from
- * doing Spectre-v2 attacks on another.
+ * Avoid user->user BTB/RSB poisoning by flushing them when switching
+ * between processes. This stops one process from doing Spectre-v2
+ * attacks on another.
*
* Both, the conditional and the always IBPB mode use the mm
* pointer to avoid the IBPB when switching between tasks of the
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index ac57259..a4b4ebd 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -73,7 +73,7 @@ int __init efi_alloc_page_tables(void)
gfp_t gfp_mask;
gfp_mask = GFP_KERNEL | __GFP_ZERO;
- efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER);
+ efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, pgd_allocation_order());
if (!efi_pgd)
goto fail;
@@ -96,7 +96,7 @@ int __init efi_alloc_page_tables(void)
if (pgtable_l5_enabled())
free_page((unsigned long)pgd_page_vaddr(*pgd));
free_pgd:
- free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
+ free_pages((unsigned long)efi_pgd, pgd_allocation_order());
fail:
return -ENOMEM;
}
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 8c534c3..66f066b 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -26,7 +26,7 @@
/* code below belongs to the image kernel */
.align PAGE_SIZE
SYM_FUNC_START(restore_registers)
- ANNOTATE_NOENDBR
+ ENDBR
/* go back to the original page tables */
movq %r9, %cr3
@@ -120,7 +120,7 @@
/* code below has been relocated to a safe page */
SYM_FUNC_START(core_restore_code)
- ANNOTATE_NOENDBR
+ ENDBR
/* switch to temporary page tables */
movq %rax, %cr3
/* flush TLB */
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 43dcd8c..53282dc 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -70,6 +70,9 @@ EXPORT_SYMBOL(xen_start_flags);
*/
struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info;
+/* Number of pages released from the initial allocation. */
+unsigned long xen_released_pages;
+
static __ref void xen_get_vendor(void)
{
init_cpu_devs();
@@ -100,10 +103,6 @@ noinstr void *__xen_hypercall_setfunc(void)
void (*func)(void);
/*
- * Xen is supported only on CPUs with CPUID, so testing for
- * X86_FEATURE_CPUID is a test for early_cpu_init() having been
- * run.
- *
* Note that __xen_hypercall_setfunc() is noinstr only due to a nasty
* dependency chain: it is being called via the xen_hypercall static
* call when running as a PVH or HVM guest. Hypercalls need to be
@@ -115,8 +114,7 @@ noinstr void *__xen_hypercall_setfunc(void)
*/
instrumentation_begin();
- if (!boot_cpu_has(X86_FEATURE_CPUID))
- xen_get_vendor();
+ xen_get_vendor();
if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
boot_cpu_data.x86_vendor == X86_VENDOR_HYGON))
@@ -466,6 +464,13 @@ int __init arch_xen_unpopulated_init(struct resource **res)
xen_free_unpopulated_pages(1, &pg);
}
+ /*
+ * Account for the region being in the physmap but unpopulated.
+ * The value in xen_released_pages is used by the balloon
+ * driver to know how much of the physmap is unpopulated and
+ * set an accurate initial memory target.
+ */
+ xen_released_pages += xen_extra_mem[i].n_pfns;
/* Zero so region is not also added to the balloon driver. */
xen_extra_mem[i].n_pfns = 0;
}
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index 0e3d930..9d25d93 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -1,5 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/acpi.h>
+#include <linux/cpufreq.h>
+#include <linux/cpuidle.h>
#include <linux/export.h>
#include <linux/mm.h>
@@ -123,8 +125,23 @@ static void __init pvh_arch_setup(void)
{
pvh_reserve_extra_memory();
- if (xen_initial_domain())
+ if (xen_initial_domain()) {
xen_add_preferred_consoles();
+
+ /*
+ * Disable usage of CPU idle and frequency drivers: when
+ * running as hardware domain the exposed native ACPI tables
+ * causes idle and/or frequency drivers to attach and
+ * malfunction. It's Xen the entity that controls the idle and
+ * frequency states.
+ *
+ * For unprivileged domains the exposed ACPI tables are
+ * fabricated and don't contain such data.
+ */
+ disable_cpuidle();
+ disable_cpufreq();
+ WARN_ON(xen_set_default_idle());
+ }
}
void __init xen_pvh_init(struct boot_params *boot_params)
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 10c660f..7237d56 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -54,14 +54,20 @@ struct mc_debug_data {
static DEFINE_PER_CPU(struct mc_buffer, mc_buffer);
static struct mc_debug_data mc_debug_data_early __initdata;
-static DEFINE_PER_CPU(struct mc_debug_data *, mc_debug_data) =
- &mc_debug_data_early;
static struct mc_debug_data __percpu *mc_debug_data_ptr;
DEFINE_PER_CPU(unsigned long, xen_mc_irq_flags);
static struct static_key mc_debug __ro_after_init;
static bool mc_debug_enabled __initdata;
+static struct mc_debug_data * __ref get_mc_debug(void)
+{
+ if (!mc_debug_data_ptr)
+ return &mc_debug_data_early;
+
+ return this_cpu_ptr(mc_debug_data_ptr);
+}
+
static int __init xen_parse_mc_debug(char *arg)
{
mc_debug_enabled = true;
@@ -71,20 +77,16 @@ static int __init xen_parse_mc_debug(char *arg)
}
early_param("xen_mc_debug", xen_parse_mc_debug);
-void mc_percpu_init(unsigned int cpu)
-{
- per_cpu(mc_debug_data, cpu) = per_cpu_ptr(mc_debug_data_ptr, cpu);
-}
-
static int __init mc_debug_enable(void)
{
unsigned long flags;
+ struct mc_debug_data __percpu *mcdb;
if (!mc_debug_enabled)
return 0;
- mc_debug_data_ptr = alloc_percpu(struct mc_debug_data);
- if (!mc_debug_data_ptr) {
+ mcdb = alloc_percpu(struct mc_debug_data);
+ if (!mcdb) {
pr_err("xen_mc_debug inactive\n");
static_key_slow_dec(&mc_debug);
return -ENOMEM;
@@ -93,7 +95,7 @@ static int __init mc_debug_enable(void)
/* Be careful when switching to percpu debug data. */
local_irq_save(flags);
xen_mc_flush();
- mc_percpu_init(0);
+ mc_debug_data_ptr = mcdb;
local_irq_restore(flags);
pr_info("xen_mc_debug active\n");
@@ -155,7 +157,7 @@ void xen_mc_flush(void)
trace_xen_mc_flush(b->mcidx, b->argidx, b->cbidx);
if (static_key_false(&mc_debug)) {
- mcdb = __this_cpu_read(mc_debug_data);
+ mcdb = get_mc_debug();
memcpy(mcdb->entries, b->entries,
b->mcidx * sizeof(struct multicall_entry));
}
@@ -235,7 +237,7 @@ struct multicall_space __xen_mc_entry(size_t args)
ret.mc = &b->entries[b->mcidx];
if (static_key_false(&mc_debug)) {
- struct mc_debug_data *mcdb = __this_cpu_read(mc_debug_data);
+ struct mc_debug_data *mcdb = get_mc_debug();
mcdb->caller[b->mcidx] = __builtin_return_address(0);
mcdb->argsz[b->mcidx] = args;
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index c3db71d..3823e52 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -37,9 +37,6 @@
#define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024)
-/* Number of pages released from the initial allocation. */
-unsigned long xen_released_pages;
-
/* Memory map would allow PCI passthrough. */
bool xen_pv_pci_possible;
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 688ff5931..9bb8ff8 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -305,7 +305,6 @@ static int xen_pv_kick_ap(unsigned int cpu, struct task_struct *idle)
return rc;
xen_pmu_init(cpu);
- mc_percpu_init(cpu);
/*
* Why is this a BUG? If the hypercall fails then everything can be
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 109af12..461bb15 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -226,9 +226,7 @@
push %rax
mov $__HYPERVISOR_iret, %eax
syscall /* Do the IRET. */
-#ifdef CONFIG_MITIGATION_SLS
- int3
-#endif
+ ud2 /* The SYSCALL should never return. */
.endm
SYM_CODE_START(xen_iret)
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 63c13a2..25e318e 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -261,9 +261,6 @@ void xen_mc_callback(void (*fn)(void *), void *data);
*/
struct multicall_space xen_mc_extend_args(unsigned long op, size_t arg_size);
-/* Do percpu data initialization for multicalls. */
-void mc_percpu_init(unsigned int cpu);
-
extern bool is_xen_pmu;
irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id);
diff --git a/block/bdev.c b/block/bdev.c
index 4844d1e..889ec6e 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -152,27 +152,65 @@ static void set_init_blocksize(struct block_device *bdev)
get_order(bsize));
}
+/**
+ * bdev_validate_blocksize - check that this block size is acceptable
+ * @bdev: blockdevice to check
+ * @block_size: block size to check
+ *
+ * For block device users that do not use buffer heads or the block device
+ * page cache, make sure that this block size can be used with the device.
+ *
+ * Return: On success zero is returned, negative error code on failure.
+ */
+int bdev_validate_blocksize(struct block_device *bdev, int block_size)
+{
+ if (blk_validate_block_size(block_size))
+ return -EINVAL;
+
+ /* Size cannot be smaller than the size supported by the device */
+ if (block_size < bdev_logical_block_size(bdev))
+ return -EINVAL;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(bdev_validate_blocksize);
+
int set_blocksize(struct file *file, int size)
{
struct inode *inode = file->f_mapping->host;
struct block_device *bdev = I_BDEV(inode);
+ int ret;
- if (blk_validate_block_size(size))
- return -EINVAL;
-
- /* Size cannot be smaller than the size supported by the device */
- if (size < bdev_logical_block_size(bdev))
- return -EINVAL;
+ ret = bdev_validate_blocksize(bdev, size);
+ if (ret)
+ return ret;
if (!file->private_data)
return -EINVAL;
/* Don't change the size if it is same as current */
if (inode->i_blkbits != blksize_bits(size)) {
+ /*
+ * Flush and truncate the pagecache before we reconfigure the
+ * mapping geometry because folio sizes are variable now. If a
+ * reader has already allocated a folio whose size is smaller
+ * than the new min_order but invokes readahead after the new
+ * min_order becomes visible, readahead will think there are
+ * "zero" blocks per folio and crash. Take the inode and
+ * invalidation locks to avoid racing with
+ * read/write/fallocate.
+ */
+ inode_lock(inode);
+ filemap_invalidate_lock(inode->i_mapping);
+
sync_blockdev(bdev);
+ kill_bdev(bdev);
+
inode->i_blkbits = blksize_bits(size);
mapping_set_folio_min_order(inode->i_mapping, get_order(size));
kill_bdev(bdev);
+ filemap_invalidate_unlock(inode->i_mapping);
+ inode_unlock(inode);
}
return 0;
}
@@ -777,13 +815,13 @@ static void blkdev_put_part(struct block_device *part)
blkdev_put_whole(whole);
}
-struct block_device *blkdev_get_no_open(dev_t dev)
+struct block_device *blkdev_get_no_open(dev_t dev, bool autoload)
{
struct block_device *bdev;
struct inode *inode;
inode = ilookup(blockdev_superblock, dev);
- if (!inode && IS_ENABLED(CONFIG_BLOCK_LEGACY_AUTOLOAD)) {
+ if (!inode && autoload && IS_ENABLED(CONFIG_BLOCK_LEGACY_AUTOLOAD)) {
blk_request_module(dev);
inode = ilookup(blockdev_superblock, dev);
if (inode)
@@ -1005,7 +1043,7 @@ struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
if (ret)
return ERR_PTR(ret);
- bdev = blkdev_get_no_open(dev);
+ bdev = blkdev_get_no_open(dev, true);
if (!bdev)
return ERR_PTR(-ENXIO);
@@ -1272,21 +1310,17 @@ void sync_bdevs(bool wait)
/*
* Handle STATX_{DIOALIGN, WRITE_ATOMIC} for block devices.
*/
-void bdev_statx(struct path *path, struct kstat *stat,
- u32 request_mask)
+void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask)
{
- struct inode *backing_inode;
struct block_device *bdev;
- backing_inode = d_backing_inode(path->dentry);
-
/*
- * Note that backing_inode is the inode of a block device node file,
- * not the block device's internal inode. Therefore it is *not* valid
- * to use I_BDEV() here; the block device has to be looked up by i_rdev
+ * Note that d_backing_inode() returns the block device node inode, not
+ * the block device's internal inode. Therefore it is *not* valid to
+ * use I_BDEV() here; the block device has to be looked up by i_rdev
* instead.
*/
- bdev = blkdev_get_no_open(backing_inode->i_rdev);
+ bdev = blkdev_get_no_open(d_backing_inode(path->dentry)->i_rdev, false);
if (!bdev)
return;
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 608594a..43ef6bd 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -66,16 +66,12 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
}
EXPORT_SYMBOL(bio_integrity_alloc);
-static void bio_integrity_unpin_bvec(struct bio_vec *bv, int nr_vecs,
- bool dirty)
+static void bio_integrity_unpin_bvec(struct bio_vec *bv, int nr_vecs)
{
int i;
- for (i = 0; i < nr_vecs; i++) {
- if (dirty && !PageCompound(bv[i].bv_page))
- set_page_dirty_lock(bv[i].bv_page);
+ for (i = 0; i < nr_vecs; i++)
unpin_user_page(bv[i].bv_page);
- }
}
static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip)
@@ -91,7 +87,7 @@ static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip)
ret = copy_to_iter(bvec_virt(bounce_bvec), bytes, &orig_iter);
WARN_ON_ONCE(ret != bytes);
- bio_integrity_unpin_bvec(orig_bvecs, orig_nr_vecs, true);
+ bio_integrity_unpin_bvec(orig_bvecs, orig_nr_vecs);
}
/**
@@ -111,8 +107,7 @@ void bio_integrity_unmap_user(struct bio *bio)
return;
}
- bio_integrity_unpin_bvec(bip->bip_vec, bip->bip_max_vcnt,
- bio_data_dir(bio) == READ);
+ bio_integrity_unpin_bvec(bip->bip_vec, bip->bip_max_vcnt);
}
/**
@@ -198,7 +193,7 @@ static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec,
}
if (write)
- bio_integrity_unpin_bvec(bvec, nr_vecs, false);
+ bio_integrity_unpin_bvec(bvec, nr_vecs);
else
memcpy(&bip->bip_vec[1], bvec, nr_vecs * sizeof(*bvec));
@@ -319,7 +314,7 @@ int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter)
return 0;
release_pages:
- bio_integrity_unpin_bvec(bvec, nr_bvecs, false);
+ bio_integrity_unpin_bvec(bvec, nr_bvecs);
free_bvec:
if (bvec != stack_vec)
kfree(bvec);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 5905f27..ce93706 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -797,7 +797,7 @@ int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx)
return -EINVAL;
input = skip_spaces(input);
- bdev = blkdev_get_no_open(MKDEV(major, minor));
+ bdev = blkdev_get_no_open(MKDEV(major, minor), false);
if (!bdev)
return -ENODEV;
if (bdev_is_partition(bdev)) {
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 6b2dbe6..4817e7c 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -61,8 +61,14 @@ void blk_apply_bdi_limits(struct backing_dev_info *bdi,
/*
* For read-ahead of large files to be effective, we need to read ahead
* at least twice the optimal I/O size.
+ *
+ * There is no hardware limitation for the read-ahead size and the user
+ * might have increased the read-ahead size through sysfs, so don't ever
+ * decrease it.
*/
- bdi->ra_pages = max(lim->io_opt * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
+ bdi->ra_pages = max3(bdi->ra_pages,
+ lim->io_opt * 2 / PAGE_SIZE,
+ VM_READAHEAD_PAGES);
bdi->io_pages = lim->max_sectors >> PAGE_SECTORS_SHIFT;
}
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index a288275..1f9b45b 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -909,6 +909,8 @@ int blk_register_queue(struct gendisk *disk)
out_debugfs_remove:
blk_debugfs_remove(disk);
mutex_unlock(&q->sysfs_lock);
+ if (queue_is_mq(q))
+ blk_mq_sysfs_unregister(disk);
out_put_queue_kobj:
kobject_put(&disk->queue_kobj);
return ret;
diff --git a/block/blk-throttle.h b/block/blk-throttle.h
index 7964cc0..f9f8666 100644
--- a/block/blk-throttle.h
+++ b/block/blk-throttle.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef BLK_THROTTLE_H
#define BLK_THROTTLE_H
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 0c77244..8f15d1a 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -343,6 +343,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
op = REQ_OP_ZONE_RESET;
/* Invalidate the page cache, including dirty pages. */
+ inode_lock(bdev->bd_mapping->host);
filemap_invalidate_lock(bdev->bd_mapping);
ret = blkdev_truncate_zone_range(bdev, mode, &zrange);
if (ret)
@@ -364,8 +365,10 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors);
fail:
- if (cmd == BLKRESETZONE)
+ if (cmd == BLKRESETZONE) {
filemap_invalidate_unlock(bdev->bd_mapping);
+ inode_unlock(bdev->bd_mapping->host);
+ }
return ret;
}
diff --git a/block/blk.h b/block/blk.h
index 006e3be..3280757 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -94,6 +94,9 @@ static inline void blk_wait_io(struct completion *done)
wait_for_completion_io(done);
}
+struct block_device *blkdev_get_no_open(dev_t dev, bool autoload);
+void blkdev_put_no_open(struct block_device *bdev);
+
#define BIO_INLINE_VECS 4
struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,
gfp_t gfp_mask);
diff --git a/block/fops.c b/block/fops.c
index be9f1db..82b672d 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -642,7 +642,7 @@ static int blkdev_open(struct inode *inode, struct file *filp)
if (ret)
return ret;
- bdev = blkdev_get_no_open(inode->i_rdev);
+ bdev = blkdev_get_no_open(inode->i_rdev, true);
if (!bdev)
return -ENXIO;
@@ -746,7 +746,14 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
ret = direct_write_fallback(iocb, from, ret,
blkdev_buffered_write(iocb, from));
} else {
+ /*
+ * Take i_rwsem and invalidate_lock to avoid racing with
+ * set_blocksize changing i_blkbits/folio order and punching
+ * out the pagecache.
+ */
+ inode_lock_shared(bd_inode);
ret = blkdev_buffered_write(iocb, from);
+ inode_unlock_shared(bd_inode);
}
if (ret > 0)
@@ -757,6 +764,7 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
+ struct inode *bd_inode = bdev_file_inode(iocb->ki_filp);
struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
loff_t size = bdev_nr_bytes(bdev);
loff_t pos = iocb->ki_pos;
@@ -793,7 +801,13 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
goto reexpand;
}
+ /*
+ * Take i_rwsem and invalidate_lock to avoid racing with set_blocksize
+ * changing i_blkbits/folio order and punching out the pagecache.
+ */
+ inode_lock_shared(bd_inode);
ret = filemap_read(iocb, to, ret);
+ inode_unlock_shared(bd_inode);
reexpand:
if (unlikely(shorted))
@@ -836,6 +850,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
if ((start | len) & (bdev_logical_block_size(bdev) - 1))
return -EINVAL;
+ inode_lock(inode);
filemap_invalidate_lock(inode->i_mapping);
/*
@@ -868,6 +883,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
fail:
filemap_invalidate_unlock(inode->i_mapping);
+ inode_unlock(inode);
return error;
}
diff --git a/block/ioctl.c b/block/ioctl.c
index faa40f3..e472cc10 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -142,6 +142,7 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
if (err)
return err;
+ inode_lock(bdev->bd_mapping->host);
filemap_invalidate_lock(bdev->bd_mapping);
err = truncate_bdev_range(bdev, mode, start, start + len - 1);
if (err)
@@ -174,6 +175,7 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
blk_finish_plug(&plug);
fail:
filemap_invalidate_unlock(bdev->bd_mapping);
+ inode_unlock(bdev->bd_mapping->host);
return err;
}
@@ -199,12 +201,14 @@ static int blk_ioctl_secure_erase(struct block_device *bdev, blk_mode_t mode,
end > bdev_nr_bytes(bdev))
return -EINVAL;
+ inode_lock(bdev->bd_mapping->host);
filemap_invalidate_lock(bdev->bd_mapping);
err = truncate_bdev_range(bdev, mode, start, end - 1);
if (!err)
err = blkdev_issue_secure_erase(bdev, start >> 9, len >> 9,
GFP_KERNEL);
filemap_invalidate_unlock(bdev->bd_mapping);
+ inode_unlock(bdev->bd_mapping->host);
return err;
}
@@ -236,6 +240,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode,
return -EINVAL;
/* Invalidate the page cache, including dirty pages */
+ inode_lock(bdev->bd_mapping->host);
filemap_invalidate_lock(bdev->bd_mapping);
err = truncate_bdev_range(bdev, mode, start, end);
if (err)
@@ -246,6 +251,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode,
fail:
filemap_invalidate_unlock(bdev->bd_mapping);
+ inode_unlock(bdev->bd_mapping->host);
return err;
}
diff --git a/crypto/ahash.c b/crypto/ahash.c
index 9f57b925..2d9eec2 100644
--- a/crypto/ahash.c
+++ b/crypto/ahash.c
@@ -315,16 +315,7 @@ EXPORT_SYMBOL_GPL(crypto_ahash_setkey);
static bool ahash_request_hasvirt(struct ahash_request *req)
{
- struct ahash_request *r2;
-
- if (ahash_request_isvirt(req))
- return true;
-
- list_for_each_entry(r2, &req->base.list, base.list)
- if (ahash_request_isvirt(r2))
- return true;
-
- return false;
+ return ahash_request_isvirt(req);
}
static int ahash_reqchain_virt(struct ahash_save_req_state *state,
@@ -472,7 +463,6 @@ static int ahash_do_req_chain(struct ahash_request *req,
bool update = op == crypto_ahash_alg(tfm)->update;
struct ahash_save_req_state *state;
struct ahash_save_req_state state0;
- struct ahash_request *r2;
u8 *page = NULL;
int err;
@@ -509,7 +499,6 @@ static int ahash_do_req_chain(struct ahash_request *req,
state->offset = 0;
state->nbytes = 0;
INIT_LIST_HEAD(&state->head);
- list_splice_init(&req->base.list, &state->head);
if (page)
sg_init_one(&state->sg, page, PAGE_SIZE);
@@ -540,9 +529,6 @@ static int ahash_do_req_chain(struct ahash_request *req,
out_set_chain:
req->base.err = err;
- list_for_each_entry(r2, &req->base.list, base.list)
- r2->base.err = err;
-
return err;
}
@@ -551,19 +537,10 @@ int crypto_ahash_init(struct ahash_request *req)
struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
if (likely(tfm->using_shash)) {
- struct ahash_request *r2;
int err;
err = crypto_shash_init(prepare_shash_desc(req, tfm));
req->base.err = err;
-
- list_for_each_entry(r2, &req->base.list, base.list) {
- struct shash_desc *desc;
-
- desc = prepare_shash_desc(r2, tfm);
- r2->base.err = crypto_shash_init(desc);
- }
-
return err;
}
@@ -620,19 +597,10 @@ int crypto_ahash_update(struct ahash_request *req)
struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
if (likely(tfm->using_shash)) {
- struct ahash_request *r2;
int err;
err = shash_ahash_update(req, ahash_request_ctx(req));
req->base.err = err;
-
- list_for_each_entry(r2, &req->base.list, base.list) {
- struct shash_desc *desc;
-
- desc = ahash_request_ctx(r2);
- r2->base.err = shash_ahash_update(r2, desc);
- }
-
return err;
}
@@ -645,19 +613,10 @@ int crypto_ahash_final(struct ahash_request *req)
struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
if (likely(tfm->using_shash)) {
- struct ahash_request *r2;
int err;
err = crypto_shash_final(ahash_request_ctx(req), req->result);
req->base.err = err;
-
- list_for_each_entry(r2, &req->base.list, base.list) {
- struct shash_desc *desc;
-
- desc = ahash_request_ctx(r2);
- r2->base.err = crypto_shash_final(desc, r2->result);
- }
-
return err;
}
@@ -670,19 +629,10 @@ int crypto_ahash_finup(struct ahash_request *req)
struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
if (likely(tfm->using_shash)) {
- struct ahash_request *r2;
int err;
err = shash_ahash_finup(req, ahash_request_ctx(req));
req->base.err = err;
-
- list_for_each_entry(r2, &req->base.list, base.list) {
- struct shash_desc *desc;
-
- desc = ahash_request_ctx(r2);
- r2->base.err = shash_ahash_finup(r2, desc);
- }
-
return err;
}
@@ -757,19 +707,10 @@ int crypto_ahash_digest(struct ahash_request *req)
struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
if (likely(tfm->using_shash)) {
- struct ahash_request *r2;
int err;
err = shash_ahash_digest(req, prepare_shash_desc(req, tfm));
req->base.err = err;
-
- list_for_each_entry(r2, &req->base.list, base.list) {
- struct shash_desc *desc;
-
- desc = prepare_shash_desc(r2, tfm);
- r2->base.err = shash_ahash_digest(r2, desc);
- }
-
return err;
}
@@ -1133,20 +1074,5 @@ int ahash_register_instance(struct crypto_template *tmpl,
}
EXPORT_SYMBOL_GPL(ahash_register_instance);
-void ahash_request_free(struct ahash_request *req)
-{
- struct ahash_request *tmp;
- struct ahash_request *r2;
-
- if (unlikely(!req))
- return;
-
- list_for_each_entry_safe(r2, tmp, &req->base.list, base.list)
- kfree_sensitive(r2);
-
- kfree_sensitive(req);
-}
-EXPORT_SYMBOL_GPL(ahash_request_free);
-
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Asynchronous cryptographic hash type");
diff --git a/crypto/scompress.c b/crypto/scompress.c
index d435d4b..ffeedcf 100644
--- a/crypto/scompress.c
+++ b/crypto/scompress.c
@@ -111,10 +111,14 @@ static void scomp_free_streams(struct scomp_alg *alg)
struct crypto_acomp_stream __percpu *stream = alg->stream;
int i;
+ alg->stream = NULL;
+ if (!stream)
+ return;
+
for_each_possible_cpu(i) {
struct crypto_acomp_stream *ps = per_cpu_ptr(stream, i);
- if (!ps->ctx)
+ if (IS_ERR_OR_NULL(ps->ctx))
break;
alg->free_ctx(ps->ctx);
@@ -132,6 +136,8 @@ static int scomp_alloc_streams(struct scomp_alg *alg)
if (!stream)
return -ENOMEM;
+ alg->stream = stream;
+
for_each_possible_cpu(i) {
struct crypto_acomp_stream *ps = per_cpu_ptr(stream, i);
@@ -143,8 +149,6 @@ static int scomp_alloc_streams(struct scomp_alg *alg)
spin_lock_init(&ps->lock);
}
-
- alg->stream = stream;
return 0;
}
@@ -159,11 +163,10 @@ static int crypto_scomp_init_tfm(struct crypto_tfm *tfm)
if (ret)
goto unlock;
}
- if (!scomp_scratch_users) {
+ if (!scomp_scratch_users++) {
ret = crypto_scomp_alloc_scratches();
if (ret)
- goto unlock;
- scomp_scratch_users++;
+ scomp_scratch_users--;
}
unlock:
mutex_unlock(&scomp_lock);
@@ -211,8 +214,8 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir)
spage = nth_page(spage, soff / PAGE_SIZE);
soff = offset_in_page(soff);
- n = slen / PAGE_SIZE;
- n += (offset_in_page(slen) + soff - 1) / PAGE_SIZE;
+ n = (slen - 1) / PAGE_SIZE;
+ n += (offset_in_page(slen - 1) + soff) / PAGE_SIZE;
if (PageHighMem(nth_page(spage, n)) &&
size_add(soff, slen) > PAGE_SIZE)
break;
@@ -239,9 +242,9 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir)
dpage = nth_page(dpage, doff / PAGE_SIZE);
doff = offset_in_page(doff);
- n = dlen / PAGE_SIZE;
- n += (offset_in_page(dlen) + doff - 1) / PAGE_SIZE;
- if (PageHighMem(dpage + n) &&
+ n = (dlen - 1) / PAGE_SIZE;
+ n += (offset_in_page(dlen - 1) + doff) / PAGE_SIZE;
+ if (PageHighMem(nth_page(dpage, n)) &&
size_add(doff, dlen) > PAGE_SIZE)
break;
dst = kmap_local_page(dpage) + doff;
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index abd609d..82977ea 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -58,9 +58,6 @@ module_param(fuzz_iterations, uint, 0644);
MODULE_PARM_DESC(fuzz_iterations, "number of fuzz test iterations");
#endif
-/* Multibuffer is unlimited. Set arbitrary limit for testing. */
-#define MAX_MB_MSGS 16
-
#ifdef CONFIG_CRYPTO_MANAGER_DISABLE_TESTS
/* a perfect nop */
@@ -3329,48 +3326,27 @@ static int test_acomp(struct crypto_acomp *tfm,
int ctcount, int dtcount)
{
const char *algo = crypto_tfm_alg_driver_name(crypto_acomp_tfm(tfm));
- struct scatterlist *src = NULL, *dst = NULL;
- struct acomp_req *reqs[MAX_MB_MSGS] = {};
- char *decomp_out[MAX_MB_MSGS] = {};
- char *output[MAX_MB_MSGS] = {};
- struct crypto_wait wait;
- struct acomp_req *req;
- int ret = -ENOMEM;
unsigned int i;
+ char *output, *decomp_out;
+ int ret;
+ struct scatterlist src, dst;
+ struct acomp_req *req;
+ struct crypto_wait wait;
- src = kmalloc_array(MAX_MB_MSGS, sizeof(*src), GFP_KERNEL);
- if (!src)
- goto out;
- dst = kmalloc_array(MAX_MB_MSGS, sizeof(*dst), GFP_KERNEL);
- if (!dst)
- goto out;
+ output = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
+ if (!output)
+ return -ENOMEM;
- for (i = 0; i < MAX_MB_MSGS; i++) {
- reqs[i] = acomp_request_alloc(tfm);
- if (!reqs[i])
- goto out;
-
- acomp_request_set_callback(reqs[i],
- CRYPTO_TFM_REQ_MAY_SLEEP |
- CRYPTO_TFM_REQ_MAY_BACKLOG,
- crypto_req_done, &wait);
- if (i)
- acomp_request_chain(reqs[i], reqs[0]);
-
- output[i] = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
- if (!output[i])
- goto out;
-
- decomp_out[i] = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
- if (!decomp_out[i])
- goto out;
+ decomp_out = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
+ if (!decomp_out) {
+ kfree(output);
+ return -ENOMEM;
}
for (i = 0; i < ctcount; i++) {
unsigned int dlen = COMP_BUF_SIZE;
int ilen = ctemplate[i].inlen;
void *input_vec;
- int j;
input_vec = kmemdup(ctemplate[i].input, ilen, GFP_KERNEL);
if (!input_vec) {
@@ -3378,61 +3354,70 @@ static int test_acomp(struct crypto_acomp *tfm,
goto out;
}
+ memset(output, 0, dlen);
crypto_init_wait(&wait);
- sg_init_one(src, input_vec, ilen);
+ sg_init_one(&src, input_vec, ilen);
+ sg_init_one(&dst, output, dlen);
- for (j = 0; j < MAX_MB_MSGS; j++) {
- sg_init_one(dst + j, output[j], dlen);
- acomp_request_set_params(reqs[j], src, dst + j, ilen, dlen);
+ req = acomp_request_alloc(tfm);
+ if (!req) {
+ pr_err("alg: acomp: request alloc failed for %s\n",
+ algo);
+ kfree(input_vec);
+ ret = -ENOMEM;
+ goto out;
}
- req = reqs[0];
+ acomp_request_set_params(req, &src, &dst, ilen, dlen);
+ acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+ crypto_req_done, &wait);
+
ret = crypto_wait_req(crypto_acomp_compress(req), &wait);
if (ret) {
pr_err("alg: acomp: compression failed on test %d for %s: ret=%d\n",
i + 1, algo, -ret);
kfree(input_vec);
+ acomp_request_free(req);
goto out;
}
ilen = req->dlen;
dlen = COMP_BUF_SIZE;
+ sg_init_one(&src, output, ilen);
+ sg_init_one(&dst, decomp_out, dlen);
crypto_init_wait(&wait);
- for (j = 0; j < MAX_MB_MSGS; j++) {
- sg_init_one(src + j, output[j], ilen);
- sg_init_one(dst + j, decomp_out[j], dlen);
- acomp_request_set_params(reqs[j], src + j, dst + j, ilen, dlen);
+ acomp_request_set_params(req, &src, &dst, ilen, dlen);
+
+ ret = crypto_wait_req(crypto_acomp_decompress(req), &wait);
+ if (ret) {
+ pr_err("alg: acomp: compression failed on test %d for %s: ret=%d\n",
+ i + 1, algo, -ret);
+ kfree(input_vec);
+ acomp_request_free(req);
+ goto out;
}
- crypto_wait_req(crypto_acomp_decompress(req), &wait);
- for (j = 0; j < MAX_MB_MSGS; j++) {
- ret = reqs[j]->base.err;
- if (ret) {
- pr_err("alg: acomp: compression failed on test %d (%d) for %s: ret=%d\n",
- i + 1, j, algo, -ret);
- kfree(input_vec);
- goto out;
- }
+ if (req->dlen != ctemplate[i].inlen) {
+ pr_err("alg: acomp: Compression test %d failed for %s: output len = %d\n",
+ i + 1, algo, req->dlen);
+ ret = -EINVAL;
+ kfree(input_vec);
+ acomp_request_free(req);
+ goto out;
+ }
- if (reqs[j]->dlen != ctemplate[i].inlen) {
- pr_err("alg: acomp: Compression test %d (%d) failed for %s: output len = %d\n",
- i + 1, j, algo, reqs[j]->dlen);
- ret = -EINVAL;
- kfree(input_vec);
- goto out;
- }
-
- if (memcmp(input_vec, decomp_out[j], reqs[j]->dlen)) {
- pr_err("alg: acomp: Compression test %d (%d) failed for %s\n",
- i + 1, j, algo);
- hexdump(output[j], reqs[j]->dlen);
- ret = -EINVAL;
- kfree(input_vec);
- goto out;
- }
+ if (memcmp(input_vec, decomp_out, req->dlen)) {
+ pr_err("alg: acomp: Compression test %d failed for %s\n",
+ i + 1, algo);
+ hexdump(output, req->dlen);
+ ret = -EINVAL;
+ kfree(input_vec);
+ acomp_request_free(req);
+ goto out;
}
kfree(input_vec);
+ acomp_request_free(req);
}
for (i = 0; i < dtcount; i++) {
@@ -3446,9 +3431,10 @@ static int test_acomp(struct crypto_acomp *tfm,
goto out;
}
+ memset(output, 0, dlen);
crypto_init_wait(&wait);
- sg_init_one(src, input_vec, ilen);
- sg_init_one(dst, output[0], dlen);
+ sg_init_one(&src, input_vec, ilen);
+ sg_init_one(&dst, output, dlen);
req = acomp_request_alloc(tfm);
if (!req) {
@@ -3459,7 +3445,7 @@ static int test_acomp(struct crypto_acomp *tfm,
goto out;
}
- acomp_request_set_params(req, src, dst, ilen, dlen);
+ acomp_request_set_params(req, &src, &dst, ilen, dlen);
acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
crypto_req_done, &wait);
@@ -3481,10 +3467,10 @@ static int test_acomp(struct crypto_acomp *tfm,
goto out;
}
- if (memcmp(output[0], dtemplate[i].output, req->dlen)) {
+ if (memcmp(output, dtemplate[i].output, req->dlen)) {
pr_err("alg: acomp: Decompression test %d failed for %s\n",
i + 1, algo);
- hexdump(output[0], req->dlen);
+ hexdump(output, req->dlen);
ret = -EINVAL;
kfree(input_vec);
acomp_request_free(req);
@@ -3498,13 +3484,8 @@ static int test_acomp(struct crypto_acomp *tfm,
ret = 0;
out:
- acomp_request_free(reqs[0]);
- for (i = 0; i < MAX_MB_MSGS; i++) {
- kfree(output[i]);
- kfree(decomp_out[i]);
- }
- kfree(dst);
- kfree(src);
+ kfree(decomp_out);
+ kfree(output);
return ret;
}
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index 6f4fe47..6481c48 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -293,7 +293,7 @@ acpi_status (*acpi_internal_method) (struct acpi_walk_state * walk_state);
* expected_return_btypes - Allowed type(s) for the return value
*/
struct acpi_name_info {
- char name[ACPI_NAMESEG_SIZE];
+ char name[ACPI_NAMESEG_SIZE] __nonstring;
u16 argument_list;
u8 expected_btypes;
};
@@ -370,7 +370,7 @@ typedef acpi_status (*acpi_object_converter) (struct acpi_namespace_node *
converted_object);
struct acpi_simple_repair_info {
- char name[ACPI_NAMESEG_SIZE];
+ char name[ACPI_NAMESEG_SIZE] __nonstring;
u32 unexpected_btypes;
u32 package_index;
acpi_object_converter object_converter;
diff --git a/drivers/acpi/acpica/nsrepair2.c b/drivers/acpi/acpica/nsrepair2.c
index 1bb7b71..330b5e4 100644
--- a/drivers/acpi/acpica/nsrepair2.c
+++ b/drivers/acpi/acpica/nsrepair2.c
@@ -25,7 +25,7 @@ acpi_status (*acpi_repair_function) (struct acpi_evaluate_info * info,
return_object_ptr);
typedef struct acpi_repair_info {
- char name[ACPI_NAMESEG_SIZE];
+ char name[ACPI_NAMESEG_SIZE] __nonstring;
acpi_repair_function repair_function;
} acpi_repair_info;
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 90b0984..0a70260 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -458,7 +458,7 @@ static void acpi_button_notify(acpi_handle handle, u32 event, void *data)
acpi_pm_wakeup_event(&device->dev);
button = acpi_driver_data(device);
- if (button->suspended)
+ if (button->suspended || event == ACPI_BUTTON_NOTIFY_WAKE)
return;
input = button->input;
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 8db09d8..3c5f348 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -2301,6 +2301,34 @@ static const struct dmi_system_id acpi_ec_no_wakeup[] = {
DMI_MATCH(DMI_PRODUCT_FAMILY, "103C_5336AN HP ZHAN 66 Pro"),
},
},
+ /*
+ * Lenovo Legion Go S; touchscreen blocks HW sleep when woken up from EC
+ * https://gitlab.freedesktop.org/drm/amd/-/issues/3929
+ */
+ {
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "83L3"),
+ }
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "83N6"),
+ }
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "83Q2"),
+ }
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "83Q3"),
+ }
+ },
{ },
};
diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c
index a35dd0e..f73ce6e 100644
--- a/drivers/acpi/pptt.c
+++ b/drivers/acpi/pptt.c
@@ -229,7 +229,7 @@ static int acpi_pptt_leaf_node(struct acpi_table_header *table_hdr,
node_entry = ACPI_PTR_DIFF(node, table_hdr);
entry = ACPI_ADD_PTR(struct acpi_subtable_header, table_hdr,
sizeof(struct acpi_table_pptt));
- proc_sz = sizeof(struct acpi_pptt_processor *);
+ proc_sz = sizeof(struct acpi_pptt_processor);
while ((unsigned long)entry + proc_sz < table_end) {
cpu_node = (struct acpi_pptt_processor *)entry;
@@ -270,7 +270,7 @@ static struct acpi_pptt_processor *acpi_find_processor_node(struct acpi_table_he
table_end = (unsigned long)table_hdr + table_hdr->length;
entry = ACPI_ADD_PTR(struct acpi_subtable_header, table_hdr,
sizeof(struct acpi_table_pptt));
- proc_sz = sizeof(struct acpi_pptt_processor *);
+ proc_sz = sizeof(struct acpi_pptt_processor);
/* find the processor structure associated with this cpuid */
while ((unsigned long)entry + proc_sz < table_end) {
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 7605200..5fc2c8e 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -6373,7 +6373,7 @@ static void print_binder_transaction_ilocked(struct seq_file *m,
seq_printf(m, " node %d", buffer->target_node->debug_id);
seq_printf(m, " size %zd:%zd offset %lx\n",
buffer->data_size, buffer->offsets_size,
- proc->alloc.vm_start - buffer->user_data);
+ buffer->user_data - proc->alloc.vm_start);
}
static void print_binder_work_ilocked(struct seq_file *m,
diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c
index ba300cc..2e4463d 100644
--- a/drivers/ata/libata-sata.c
+++ b/drivers/ata/libata-sata.c
@@ -1510,6 +1510,8 @@ int ata_eh_get_ncq_success_sense(struct ata_link *link)
unsigned int err_mask, tag;
u8 *sense, sk = 0, asc = 0, ascq = 0;
u64 sense_valid, val;
+ u16 extended_sense;
+ bool aux_icc_valid;
int ret = 0;
err_mask = ata_read_log_page(dev, ATA_LOG_SENSE_NCQ, 0, buf, 2);
@@ -1529,6 +1531,8 @@ int ata_eh_get_ncq_success_sense(struct ata_link *link)
sense_valid = (u64)buf[8] | ((u64)buf[9] << 8) |
((u64)buf[10] << 16) | ((u64)buf[11] << 24);
+ extended_sense = get_unaligned_le16(&buf[14]);
+ aux_icc_valid = extended_sense & BIT(15);
ata_qc_for_each_raw(ap, qc, tag) {
if (!(qc->flags & ATA_QCFLAG_EH) ||
@@ -1556,6 +1560,17 @@ int ata_eh_get_ncq_success_sense(struct ata_link *link)
continue;
}
+ qc->result_tf.nsect = sense[6];
+ qc->result_tf.hob_nsect = sense[7];
+ qc->result_tf.lbal = sense[8];
+ qc->result_tf.lbam = sense[9];
+ qc->result_tf.lbah = sense[10];
+ qc->result_tf.hob_lbal = sense[11];
+ qc->result_tf.hob_lbam = sense[12];
+ qc->result_tf.hob_lbah = sense[13];
+ if (aux_icc_valid)
+ qc->result_tf.auxiliary = get_unaligned_le32(&sense[16]);
+
/* Set sense without also setting scsicmd->result */
scsi_build_sense_buffer(dev->flags & ATA_DFLAG_D_SENSE,
qc->scsicmd->sense_buffer, sk,
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 2796c0d..c0eb8c6 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -2453,8 +2453,8 @@ static unsigned int ata_msense_control_ata_feature(struct ata_device *dev,
*/
put_unaligned_be16(ATA_FEATURE_SUB_MPAGE_LEN - 4, &buf[2]);
- if (dev->flags & ATA_DFLAG_CDL)
- buf[4] = 0x02; /* Support T2A and T2B pages */
+ if (dev->flags & ATA_DFLAG_CDL_ENABLED)
+ buf[4] = 0x02; /* T2A and T2B pages enabled */
else
buf[4] = 0;
@@ -3886,12 +3886,11 @@ static int ata_mselect_control_spg0(struct ata_queued_cmd *qc,
}
/*
- * Translate MODE SELECT control mode page, sub-pages f2h (ATA feature mode
+ * Translate MODE SELECT control mode page, sub-page f2h (ATA feature mode
* page) into a SET FEATURES command.
*/
-static unsigned int ata_mselect_control_ata_feature(struct ata_queued_cmd *qc,
- const u8 *buf, int len,
- u16 *fp)
+static int ata_mselect_control_ata_feature(struct ata_queued_cmd *qc,
+ const u8 *buf, int len, u16 *fp)
{
struct ata_device *dev = qc->dev;
struct ata_taskfile *tf = &qc->tf;
@@ -3909,17 +3908,27 @@ static unsigned int ata_mselect_control_ata_feature(struct ata_queued_cmd *qc,
/* Check cdl_ctrl */
switch (buf[0] & 0x03) {
case 0:
- /* Disable CDL */
+ /* Disable CDL if it is enabled */
+ if (!(dev->flags & ATA_DFLAG_CDL_ENABLED))
+ return 0;
+ ata_dev_dbg(dev, "Disabling CDL\n");
cdl_action = 0;
dev->flags &= ~ATA_DFLAG_CDL_ENABLED;
break;
case 0x02:
- /* Enable CDL T2A/T2B: NCQ priority must be disabled */
+ /*
+ * Enable CDL if not already enabled. Since this is mutually
+ * exclusive with NCQ priority, allow this only if NCQ priority
+ * is disabled.
+ */
+ if (dev->flags & ATA_DFLAG_CDL_ENABLED)
+ return 0;
if (dev->flags & ATA_DFLAG_NCQ_PRIO_ENABLED) {
ata_dev_err(dev,
"NCQ priority must be disabled to enable CDL\n");
return -EINVAL;
}
+ ata_dev_dbg(dev, "Enabling CDL\n");
cdl_action = 1;
dev->flags |= ATA_DFLAG_CDL_ENABLED;
break;
diff --git a/drivers/ata/pata_pxa.c b/drivers/ata/pata_pxa.c
index 434f380..03dbaf4 100644
--- a/drivers/ata/pata_pxa.c
+++ b/drivers/ata/pata_pxa.c
@@ -223,10 +223,16 @@ static int pxa_ata_probe(struct platform_device *pdev)
ap->ioaddr.cmd_addr = devm_ioremap(&pdev->dev, cmd_res->start,
resource_size(cmd_res));
+ if (!ap->ioaddr.cmd_addr)
+ return -ENOMEM;
ap->ioaddr.ctl_addr = devm_ioremap(&pdev->dev, ctl_res->start,
resource_size(ctl_res));
+ if (!ap->ioaddr.ctl_addr)
+ return -ENOMEM;
ap->ioaddr.bmdma_addr = devm_ioremap(&pdev->dev, dma_res->start,
resource_size(dma_res));
+ if (!ap->ioaddr.bmdma_addr)
+ return -ENOMEM;
/*
* Adjust register offsets
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index a482741..c3042ec 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -1117,9 +1117,14 @@ static int pdc20621_prog_dimm0(struct ata_host *host)
mmio += PDC_CHIP0_OFS;
for (i = 0; i < ARRAY_SIZE(pdc_i2c_read_data); i++)
- pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS,
- pdc_i2c_read_data[i].reg,
- &spd0[pdc_i2c_read_data[i].ofs]);
+ if (!pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS,
+ pdc_i2c_read_data[i].reg,
+ &spd0[pdc_i2c_read_data[i].ofs])) {
+ dev_err(host->dev,
+ "Failed in i2c read at index %d: device=%#x, reg=%#x\n",
+ i, PDC_DIMM0_SPD_DEV_ADDRESS, pdc_i2c_read_data[i].reg);
+ return -EIO;
+ }
data |= (spd0[4] - 8) | ((spd0[21] != 0) << 3) | ((spd0[3]-11) << 4);
data |= ((spd0[17] / 4) << 6) | ((spd0[5] / 2) << 7) |
@@ -1284,6 +1289,8 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host)
/* Programming DIMM0 Module Control Register (index_CID0:80h) */
size = pdc20621_prog_dimm0(host);
+ if (size < 0)
+ return size;
dev_dbg(host->dev, "Local DIMM Size = %dMB\n", size);
/* Programming DIMM Module Global Control Register (index_CID0:88h) */
diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c
index afa4df4..95717d5 100644
--- a/drivers/base/auxiliary.c
+++ b/drivers/base/auxiliary.c
@@ -156,6 +156,16 @@
* },
* .ops = my_custom_ops,
* };
+ *
+ * Please note that such custom ops approach is valid, but it is hard to implement
+ * it right without global locks per-device to protect from auxiliary_drv removal
+ * during call to that ops. In addition, this implementation lacks proper module
+ * dependency, which causes to load/unload races between auxiliary parent and devices
+ * modules.
+ *
+ * The most easiest way to provide these ops reliably without needing to
+ * have a lock is to EXPORT_SYMBOL*() them and rely on already existing
+ * modules infrastructure for validity and correct dependencies chains.
*/
static const struct auxiliary_device_id *auxiliary_match_id(const struct auxiliary_device_id *id,
diff --git a/drivers/base/base.h b/drivers/base/base.h
index 0042e47..123031a 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -73,6 +73,7 @@ static inline void subsys_put(struct subsys_private *sp)
kset_put(&sp->subsys);
}
+struct subsys_private *bus_to_subsys(const struct bus_type *bus);
struct subsys_private *class_to_subsys(const struct class *class);
struct driver_private {
@@ -180,6 +181,22 @@ int driver_add_groups(const struct device_driver *drv, const struct attribute_gr
void driver_remove_groups(const struct device_driver *drv, const struct attribute_group **groups);
void device_driver_detach(struct device *dev);
+static inline void device_set_driver(struct device *dev, const struct device_driver *drv)
+{
+ /*
+ * Majority (all?) read accesses to dev->driver happens either
+ * while holding device lock or in bus/driver code that is only
+ * invoked when the device is bound to a driver and there is no
+ * concern of the pointer being changed while it is being read.
+ * However when reading device's uevent file we read driver pointer
+ * without taking device lock (so we do not block there for
+ * arbitrary amount of time). We use WRITE_ONCE() here to prevent
+ * tearing so that READ_ONCE() can safely be used in uevent code.
+ */
+ // FIXME - this cast should not be needed "soon"
+ WRITE_ONCE(dev->driver, (struct device_driver *)drv);
+}
+
int devres_release_all(struct device *dev);
void device_block_probing(void);
void device_unblock_probing(void);
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 5ea3b03..5e75e1b 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -57,7 +57,7 @@ static int __must_check bus_rescan_devices_helper(struct device *dev,
* NULL. A call to subsys_put() must be done when finished with the pointer in
* order for it to be properly freed.
*/
-static struct subsys_private *bus_to_subsys(const struct bus_type *bus)
+struct subsys_private *bus_to_subsys(const struct bus_type *bus)
{
struct subsys_private *sp = NULL;
struct kobject *kobj;
diff --git a/drivers/base/core.c b/drivers/base/core.c
index d2f9d3a..cbc0099 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -2624,6 +2624,35 @@ static const char *dev_uevent_name(const struct kobject *kobj)
return NULL;
}
+/*
+ * Try filling "DRIVER=<name>" uevent variable for a device. Because this
+ * function may race with binding and unbinding the device from a driver,
+ * we need to be careful. Binding is generally safe, at worst we miss the
+ * fact that the device is already bound to a driver (but the driver
+ * information that is delivered through uevents is best-effort, it may
+ * become obsolete as soon as it is generated anyways). Unbinding is more
+ * risky as driver pointer is transitioning to NULL, so READ_ONCE() should
+ * be used to make sure we are dealing with the same pointer, and to
+ * ensure that driver structure is not going to disappear from under us
+ * we take bus' drivers klist lock. The assumption that only registered
+ * driver can be bound to a device, and to unregister a driver bus code
+ * will take the same lock.
+ */
+static void dev_driver_uevent(const struct device *dev, struct kobj_uevent_env *env)
+{
+ struct subsys_private *sp = bus_to_subsys(dev->bus);
+
+ if (sp) {
+ scoped_guard(spinlock, &sp->klist_drivers.k_lock) {
+ struct device_driver *drv = READ_ONCE(dev->driver);
+ if (drv)
+ add_uevent_var(env, "DRIVER=%s", drv->name);
+ }
+
+ subsys_put(sp);
+ }
+}
+
static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
{
const struct device *dev = kobj_to_dev(kobj);
@@ -2655,8 +2684,8 @@ static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
if (dev->type && dev->type->name)
add_uevent_var(env, "DEVTYPE=%s", dev->type->name);
- if (dev->driver)
- add_uevent_var(env, "DRIVER=%s", dev->driver->name);
+ /* Add "DRIVER=%s" variable if the device is bound to a driver */
+ dev_driver_uevent(dev, env);
/* Add common DT information about the device */
of_device_uevent(dev, env);
@@ -2726,11 +2755,8 @@ static ssize_t uevent_show(struct device *dev, struct device_attribute *attr,
if (!env)
return -ENOMEM;
- /* Synchronize with really_probe() */
- device_lock(dev);
/* let the kset specific function add its keys */
retval = kset->uevent_ops->uevent(&dev->kobj, env);
- device_unlock(dev);
if (retval)
goto out;
@@ -3700,7 +3726,7 @@ int device_add(struct device *dev)
device_pm_remove(dev);
dpm_sysfs_remove(dev);
DPMError:
- dev->driver = NULL;
+ device_set_driver(dev, NULL);
bus_remove_device(dev);
BusError:
device_remove_attrs(dev);
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index f0e4b4ab..b526e0e 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -550,7 +550,7 @@ static void device_unbind_cleanup(struct device *dev)
arch_teardown_dma_ops(dev);
kfree(dev->dma_range_map);
dev->dma_range_map = NULL;
- dev->driver = NULL;
+ device_set_driver(dev, NULL);
dev_set_drvdata(dev, NULL);
if (dev->pm_domain && dev->pm_domain->dismiss)
dev->pm_domain->dismiss(dev);
@@ -629,8 +629,7 @@ static int really_probe(struct device *dev, const struct device_driver *drv)
}
re_probe:
- // FIXME - this cast should not be needed "soon"
- dev->driver = (struct device_driver *)drv;
+ device_set_driver(dev, drv);
/* If using pinctrl, bind pins now before probing */
ret = pinctrl_bind_pins(dev);
@@ -1014,7 +1013,7 @@ static int __device_attach(struct device *dev, bool allow_async)
if (ret == 0)
ret = 1;
else {
- dev->driver = NULL;
+ device_set_driver(dev, NULL);
ret = 0;
}
} else {
diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index 6dd1a88..31bfb31 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -296,7 +296,7 @@ static int delete_path(const char *nodepath)
return err;
}
-static int dev_mynode(struct device *dev, struct inode *inode, struct kstat *stat)
+static int dev_mynode(struct device *dev, struct inode *inode)
{
/* did we create it */
if (inode->i_private != &thread)
@@ -304,13 +304,13 @@ static int dev_mynode(struct device *dev, struct inode *inode, struct kstat *sta
/* does the dev_t match */
if (is_blockdev(dev)) {
- if (!S_ISBLK(stat->mode))
+ if (!S_ISBLK(inode->i_mode))
return 0;
} else {
- if (!S_ISCHR(stat->mode))
+ if (!S_ISCHR(inode->i_mode))
return 0;
}
- if (stat->rdev != dev->devt)
+ if (inode->i_rdev != dev->devt)
return 0;
/* ours */
@@ -321,20 +321,16 @@ static int handle_remove(const char *nodename, struct device *dev)
{
struct path parent;
struct dentry *dentry;
- struct kstat stat;
- struct path p;
+ struct inode *inode;
int deleted = 0;
- int err;
+ int err = 0;
dentry = kern_path_locked(nodename, &parent);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
- p.mnt = parent.mnt;
- p.dentry = dentry;
- err = vfs_getattr(&p, &stat, STATX_TYPE | STATX_MODE,
- AT_STATX_SYNC_AS_STAT);
- if (!err && dev_mynode(dev, d_inode(dentry), &stat)) {
+ inode = d_inode(dentry);
+ if (dev_mynode(dev, inode)) {
struct iattr newattrs;
/*
* before unlinking this node, reset permissions
@@ -342,7 +338,7 @@ static int handle_remove(const char *nodename, struct device *dev)
*/
newattrs.ia_uid = GLOBAL_ROOT_UID;
newattrs.ia_gid = GLOBAL_ROOT_GID;
- newattrs.ia_mode = stat.mode & ~0777;
+ newattrs.ia_mode = inode->i_mode & ~0777;
newattrs.ia_valid =
ATTR_UID|ATTR_GID|ATTR_MODE;
inode_lock(d_inode(dentry));
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 8f3a41d..19469e7 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -816,21 +816,6 @@ static int add_memory_block(unsigned long block_id, unsigned long state,
return 0;
}
-static int __init add_boot_memory_block(unsigned long base_section_nr)
-{
- unsigned long nr;
-
- for_each_present_section_nr(base_section_nr, nr) {
- if (nr >= (base_section_nr + sections_per_block))
- break;
-
- return add_memory_block(memory_block_id(base_section_nr),
- MEM_ONLINE, NULL, NULL);
- }
-
- return 0;
-}
-
static int add_hotplug_memory_block(unsigned long block_id,
struct vmem_altmap *altmap,
struct memory_group *group)
@@ -957,7 +942,7 @@ static const struct attribute_group *memory_root_attr_groups[] = {
void __init memory_dev_init(void)
{
int ret;
- unsigned long block_sz, nr;
+ unsigned long block_sz, block_id, nr;
/* Validate the configured memory block size */
block_sz = memory_block_size_bytes();
@@ -970,15 +955,23 @@ void __init memory_dev_init(void)
panic("%s() failed to register subsystem: %d\n", __func__, ret);
/*
- * Create entries for memory sections that were found
- * during boot and have been initialized
+ * Create entries for memory sections that were found during boot
+ * and have been initialized. Use @block_id to track the last
+ * handled block and initialize it to an invalid value (ULONG_MAX)
+ * to bypass the block ID matching check for the first present
+ * block so that it can be covered.
*/
- for (nr = 0; nr <= __highest_present_section_nr;
- nr += sections_per_block) {
- ret = add_boot_memory_block(nr);
- if (ret)
- panic("%s() failed to add memory block: %d\n", __func__,
- ret);
+ block_id = ULONG_MAX;
+ for_each_present_section_nr(0, nr) {
+ if (block_id != ULONG_MAX && memory_block_id(nr) == block_id)
+ continue;
+
+ block_id = memory_block_id(nr);
+ ret = add_memory_block(block_id, MEM_ONLINE, NULL, NULL);
+ if (ret) {
+ panic("%s() failed to add memory block: %d\n",
+ __func__, ret);
+ }
}
}
diff --git a/drivers/base/module.c b/drivers/base/module.c
index 5bc71be..218aaa0 100644
--- a/drivers/base/module.c
+++ b/drivers/base/module.c
@@ -42,16 +42,13 @@ int module_add_driver(struct module *mod, const struct device_driver *drv)
if (mod)
mk = &mod->mkobj;
else if (drv->mod_name) {
- struct kobject *mkobj;
-
- /* Lookup built-in module entry in /sys/modules */
- mkobj = kset_find_obj(module_kset, drv->mod_name);
- if (mkobj) {
- mk = container_of(mkobj, struct module_kobject, kobj);
+ /* Lookup or create built-in module entry in /sys/modules */
+ mk = lookup_or_create_module_kobject(drv->mod_name);
+ if (mk) {
/* remember our module structure */
drv->p->mkobj = mk;
- /* kset_find_obj took a reference */
- kobject_put(mkobj);
+ /* lookup_or_create_module_kobject took a reference */
+ kobject_put(&mk->kobj);
}
}
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 1813cfd0..cfccf3f 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -1440,7 +1440,7 @@ static void platform_shutdown(struct device *_dev)
static int platform_dma_configure(struct device *dev)
{
- struct platform_driver *drv = to_platform_driver(dev->driver);
+ struct device_driver *drv = READ_ONCE(dev->driver);
struct fwnode_handle *fwnode = dev_fwnode(dev);
enum dev_dma_attr attr;
int ret = 0;
@@ -1451,8 +1451,8 @@ static int platform_dma_configure(struct device *dev)
attr = acpi_get_dma_attr(to_acpi_device_node(fwnode));
ret = acpi_dma_configure(dev, attr);
}
- /* @drv may not be valid when we're called from the IOMMU layer */
- if (ret || !dev->driver || drv->driver_managed_dma)
+ /* @dev->driver may not be valid when we're called from the IOMMU layer */
+ if (ret || !drv || to_platform_driver(drv)->driver_managed_dma)
return ret;
ret = iommu_device_use_default_domain(dev);
diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c
index b1726a3..5c78fa6 100644
--- a/drivers/base/swnode.c
+++ b/drivers/base/swnode.c
@@ -1080,6 +1080,7 @@ void software_node_notify(struct device *dev)
if (!swnode)
return;
+ kobject_get(&swnode->kobj);
ret = sysfs_create_link(&dev->kobj, &swnode->kobj, "software_node");
if (ret)
return;
@@ -1089,8 +1090,6 @@ void software_node_notify(struct device *dev)
sysfs_remove_link(&dev->kobj, "software_node");
return;
}
-
- kobject_get(&swnode->kobj);
}
void software_node_notify_remove(struct device *dev)
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index a97f2c4..e48b24b 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -367,7 +367,7 @@
tristate "Rados block device (RBD)"
depends on INET && BLOCK
select CEPH_LIB
- select LIBCRC32C
+ select CRC32
select CRYPTO_AES
select CRYPTO
help
@@ -388,12 +388,6 @@
definition isn't finalized yet, and might change according to future
requirement, so mark is as experimental now.
- Say Y if you want to get better performance because task_work_add()
- can be used in IO path for replacing io_uring cmd, which will become
- shared between IO tasks and ubq daemon, meantime task_work_add() can
- can handle batch more effectively, but task_work_add() isn't exported
- for module, so ublk has to be built to kernel.
-
config BLKDEV_UBLK_LEGACY_OPCODES
bool "Support legacy command opcode"
depends on BLK_DEV_UBLK
diff --git a/drivers/block/drbd/Kconfig b/drivers/block/drbd/Kconfig
index 6fb4e38..495a72d 100644
--- a/drivers/block/drbd/Kconfig
+++ b/drivers/block/drbd/Kconfig
@@ -10,7 +10,7 @@
tristate "DRBD Distributed Replicated Block Device support"
depends on PROC_FS && INET
select LRU_CACHE
- select LIBCRC32C
+ select CRC32
help
NOTE: In order to authenticate connections you have to select
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 674527d..46cba26 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -211,72 +211,6 @@ static void loop_set_size(struct loop_device *lo, loff_t size)
kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
}
-static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos)
-{
- struct iov_iter i;
- ssize_t bw;
-
- iov_iter_bvec(&i, ITER_SOURCE, bvec, 1, bvec->bv_len);
-
- bw = vfs_iter_write(file, &i, ppos, 0);
-
- if (likely(bw == bvec->bv_len))
- return 0;
-
- printk_ratelimited(KERN_ERR
- "loop: Write error at byte offset %llu, length %i.\n",
- (unsigned long long)*ppos, bvec->bv_len);
- if (bw >= 0)
- bw = -EIO;
- return bw;
-}
-
-static int lo_write_simple(struct loop_device *lo, struct request *rq,
- loff_t pos)
-{
- struct bio_vec bvec;
- struct req_iterator iter;
- int ret = 0;
-
- rq_for_each_segment(bvec, rq, iter) {
- ret = lo_write_bvec(lo->lo_backing_file, &bvec, &pos);
- if (ret < 0)
- break;
- cond_resched();
- }
-
- return ret;
-}
-
-static int lo_read_simple(struct loop_device *lo, struct request *rq,
- loff_t pos)
-{
- struct bio_vec bvec;
- struct req_iterator iter;
- struct iov_iter i;
- ssize_t len;
-
- rq_for_each_segment(bvec, rq, iter) {
- iov_iter_bvec(&i, ITER_DEST, &bvec, 1, bvec.bv_len);
- len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0);
- if (len < 0)
- return len;
-
- flush_dcache_page(bvec.bv_page);
-
- if (len != bvec.bv_len) {
- struct bio *bio;
-
- __rq_for_each_bio(bio, rq)
- zero_fill_bio(bio);
- break;
- }
- cond_resched();
- }
-
- return 0;
-}
-
static void loop_clear_limits(struct loop_device *lo, int mode)
{
struct queue_limits lim = queue_limits_start_update(lo->lo_queue);
@@ -342,7 +276,7 @@ static void lo_complete_rq(struct request *rq)
struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
blk_status_t ret = BLK_STS_OK;
- if (!cmd->use_aio || cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) ||
+ if (cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) ||
req_op(rq) != REQ_OP_READ) {
if (cmd->ret < 0)
ret = errno_to_blk_status(cmd->ret);
@@ -358,14 +292,13 @@ static void lo_complete_rq(struct request *rq)
cmd->ret = 0;
blk_mq_requeue_request(rq, true);
} else {
- if (cmd->use_aio) {
- struct bio *bio = rq->bio;
+ struct bio *bio = rq->bio;
- while (bio) {
- zero_fill_bio(bio);
- bio = bio->bi_next;
- }
+ while (bio) {
+ zero_fill_bio(bio);
+ bio = bio->bi_next;
}
+
ret = BLK_STS_IOERR;
end_io:
blk_mq_end_request(rq, ret);
@@ -445,9 +378,14 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
cmd->iocb.ki_pos = pos;
cmd->iocb.ki_filp = file;
- cmd->iocb.ki_complete = lo_rw_aio_complete;
- cmd->iocb.ki_flags = IOCB_DIRECT;
- cmd->iocb.ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0);
+ cmd->iocb.ki_ioprio = req_get_ioprio(rq);
+ if (cmd->use_aio) {
+ cmd->iocb.ki_complete = lo_rw_aio_complete;
+ cmd->iocb.ki_flags = IOCB_DIRECT;
+ } else {
+ cmd->iocb.ki_complete = NULL;
+ cmd->iocb.ki_flags = 0;
+ }
if (rw == ITER_SOURCE)
ret = file->f_op->write_iter(&cmd->iocb, &iter);
@@ -458,7 +396,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
if (ret != -EIOCBQUEUED)
lo_rw_aio_complete(&cmd->iocb, ret);
- return 0;
+ return -EIOCBQUEUED;
}
static int do_req_filebacked(struct loop_device *lo, struct request *rq)
@@ -466,15 +404,6 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
loff_t pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset;
- /*
- * lo_write_simple and lo_read_simple should have been covered
- * by io submit style function like lo_rw_aio(), one blocker
- * is that lo_read_simple() need to call flush_dcache_page after
- * the page is written from kernel, and it isn't easy to handle
- * this in io submit style function which submits all segments
- * of the req at one time. And direct read IO doesn't need to
- * run flush_dcache_page().
- */
switch (req_op(rq)) {
case REQ_OP_FLUSH:
return lo_req_flush(lo, rq);
@@ -490,15 +419,9 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
case REQ_OP_DISCARD:
return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE);
case REQ_OP_WRITE:
- if (cmd->use_aio)
- return lo_rw_aio(lo, cmd, pos, ITER_SOURCE);
- else
- return lo_write_simple(lo, rq, pos);
+ return lo_rw_aio(lo, cmd, pos, ITER_SOURCE);
case REQ_OP_READ:
- if (cmd->use_aio)
- return lo_rw_aio(lo, cmd, pos, ITER_DEST);
- else
- return lo_read_simple(lo, rq, pos);
+ return lo_rw_aio(lo, cmd, pos, ITER_DEST);
default:
WARN_ON_ONCE(1);
return -EIO;
@@ -662,19 +585,20 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
* dependency.
*/
fput(old_file);
+ dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0);
if (partscan)
loop_reread_partitions(lo);
error = 0;
done:
- /* enable and uncork uevent now that we are done */
- dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0);
+ kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
return error;
out_err:
loop_global_unlock(lo, is_loop);
out_putf:
fput(file);
+ dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0);
goto done;
}
@@ -1129,8 +1053,8 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
if (partscan)
clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state);
- /* enable and uncork uevent now that we are done */
dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0);
+ kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
loop_global_unlock(lo, is_loop);
if (partscan)
@@ -1921,7 +1845,6 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
struct loop_device *lo = rq->q->queuedata;
int ret = 0;
struct mem_cgroup *old_memcg = NULL;
- const bool use_aio = cmd->use_aio;
if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) {
ret = -EIO;
@@ -1951,7 +1874,7 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
}
failed:
/* complete non-aio request */
- if (!use_aio || ret) {
+ if (ret != -EIOCBQUEUED) {
if (ret == -EOPNOTSUPP)
cmd->ret = ret;
else
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 3bb9cee..aa163ae 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -2031,7 +2031,7 @@ static int null_add_dev(struct nullb_device *dev)
nullb->disk->minors = 1;
nullb->disk->fops = &null_ops;
nullb->disk->private_data = nullb;
- strscpy_pad(nullb->disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
+ strscpy(nullb->disk->disk_name, nullb->disk_name);
if (nullb->dev->zoned) {
rv = null_register_zoned_dev(nullb);
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 2fd05c1..40f971a 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -123,15 +123,6 @@ struct ublk_uring_cmd_pdu {
#define UBLK_IO_FLAG_OWNED_BY_SRV 0x02
/*
- * IO command is aborted, so this flag is set in case of
- * !UBLK_IO_FLAG_ACTIVE.
- *
- * After this flag is observed, any pending or new incoming request
- * associated with this io command will be failed immediately
- */
-#define UBLK_IO_FLAG_ABORTED 0x04
-
-/*
* UBLK_IO_FLAG_NEED_GET_DATA is set because IO command requires
* get data buffer address from ublksrv.
*
@@ -199,8 +190,6 @@ struct ublk_device {
struct completion completion;
unsigned int nr_queues_ready;
unsigned int nr_privileged_daemon;
-
- struct work_struct nosrv_work;
};
/* header of ublk_params */
@@ -209,8 +198,8 @@ struct ublk_params_header {
__u32 types;
};
-static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq);
-
+static void ublk_stop_dev_unlocked(struct ublk_device *ub);
+static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq);
static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub,
struct ublk_queue *ubq, int tag, size_t offset);
static inline unsigned int ublk_req_build_flags(struct request *req);
@@ -1074,7 +1063,7 @@ static inline struct ublk_uring_cmd_pdu *ublk_get_uring_cmd_pdu(
static inline bool ubq_daemon_is_dying(struct ublk_queue *ubq)
{
- return ubq->ubq_daemon->flags & PF_EXITING;
+ return !ubq->ubq_daemon || ubq->ubq_daemon->flags & PF_EXITING;
}
/* todo: handle partial completion */
@@ -1085,12 +1074,6 @@ static inline void __ublk_complete_rq(struct request *req)
unsigned int unmapped_bytes;
blk_status_t res = BLK_STS_OK;
- /* called from ublk_abort_queue() code path */
- if (io->flags & UBLK_IO_FLAG_ABORTED) {
- res = BLK_STS_IOERR;
- goto exit;
- }
-
/* failed read IO if nothing is read */
if (!io->res && req_op(req) == REQ_OP_READ)
io->res = -EIO;
@@ -1140,25 +1123,6 @@ static void ublk_complete_rq(struct kref *ref)
__ublk_complete_rq(req);
}
-/*
- * Since ublk_rq_task_work_cb always fails requests immediately during
- * exiting, __ublk_fail_req() is only called from abort context during
- * exiting. So lock is unnecessary.
- *
- * Also aborting may not be started yet, keep in mind that one failed
- * request may be issued by block layer again.
- */
-static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io,
- struct request *req)
-{
- WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE);
-
- if (ublk_nosrv_should_reissue_outstanding(ubq->dev))
- blk_mq_requeue_request(req, false);
- else
- ublk_put_req_ref(ubq, req);
-}
-
static void ubq_complete_io_cmd(struct ublk_io *io, int res,
unsigned issue_flags)
{
@@ -1314,8 +1278,6 @@ static void ublk_queue_cmd_list(struct ublk_queue *ubq, struct rq_list *l)
static enum blk_eh_timer_return ublk_timeout(struct request *rq)
{
struct ublk_queue *ubq = rq->mq_hctx->driver_data;
- unsigned int nr_inflight = 0;
- int i;
if (ubq->flags & UBLK_F_UNPRIVILEGED_DEV) {
if (!ubq->timeout) {
@@ -1326,30 +1288,11 @@ static enum blk_eh_timer_return ublk_timeout(struct request *rq)
return BLK_EH_DONE;
}
- if (!ubq_daemon_is_dying(ubq))
- return BLK_EH_RESET_TIMER;
-
- for (i = 0; i < ubq->q_depth; i++) {
- struct ublk_io *io = &ubq->ios[i];
-
- if (!(io->flags & UBLK_IO_FLAG_ACTIVE))
- nr_inflight++;
- }
-
- /* cancelable uring_cmd can't help us if all commands are in-flight */
- if (nr_inflight == ubq->q_depth) {
- struct ublk_device *ub = ubq->dev;
-
- if (ublk_abort_requests(ub, ubq)) {
- schedule_work(&ub->nosrv_work);
- }
- return BLK_EH_DONE;
- }
-
return BLK_EH_RESET_TIMER;
}
-static blk_status_t ublk_prep_req(struct ublk_queue *ubq, struct request *rq)
+static blk_status_t ublk_prep_req(struct ublk_queue *ubq, struct request *rq,
+ bool check_cancel)
{
blk_status_t res;
@@ -1368,7 +1311,7 @@ static blk_status_t ublk_prep_req(struct ublk_queue *ubq, struct request *rq)
if (ublk_nosrv_should_queue_io(ubq) && unlikely(ubq->force_abort))
return BLK_STS_IOERR;
- if (unlikely(ubq->canceling))
+ if (check_cancel && unlikely(ubq->canceling))
return BLK_STS_IOERR;
/* fill iod to slot in io cmd buffer */
@@ -1387,7 +1330,7 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx,
struct request *rq = bd->rq;
blk_status_t res;
- res = ublk_prep_req(ubq, rq);
+ res = ublk_prep_req(ubq, rq, false);
if (res != BLK_STS_OK)
return res;
@@ -1419,7 +1362,7 @@ static void ublk_queue_rqs(struct rq_list *rqlist)
ublk_queue_cmd_list(ubq, &submit_list);
ubq = this_q;
- if (ublk_prep_req(ubq, req) == BLK_STS_OK)
+ if (ublk_prep_req(ubq, req, true) == BLK_STS_OK)
rq_list_add_tail(&submit_list, req);
else
rq_list_add_tail(&requeue_list, req);
@@ -1447,6 +1390,37 @@ static const struct blk_mq_ops ublk_mq_ops = {
.timeout = ublk_timeout,
};
+static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq)
+{
+ int i;
+
+ /* All old ioucmds have to be completed */
+ ubq->nr_io_ready = 0;
+
+ /*
+ * old daemon is PF_EXITING, put it now
+ *
+ * It could be NULL in case of closing one quisced device.
+ */
+ if (ubq->ubq_daemon)
+ put_task_struct(ubq->ubq_daemon);
+ /* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */
+ ubq->ubq_daemon = NULL;
+ ubq->timeout = false;
+
+ for (i = 0; i < ubq->q_depth; i++) {
+ struct ublk_io *io = &ubq->ios[i];
+
+ /*
+ * UBLK_IO_FLAG_CANCELED is kept for avoiding to touch
+ * io->cmd
+ */
+ io->flags &= UBLK_IO_FLAG_CANCELED;
+ io->cmd = NULL;
+ io->addr = 0;
+ }
+}
+
static int ublk_ch_open(struct inode *inode, struct file *filp)
{
struct ublk_device *ub = container_of(inode->i_cdev,
@@ -1458,10 +1432,119 @@ static int ublk_ch_open(struct inode *inode, struct file *filp)
return 0;
}
+static void ublk_reset_ch_dev(struct ublk_device *ub)
+{
+ int i;
+
+ for (i = 0; i < ub->dev_info.nr_hw_queues; i++)
+ ublk_queue_reinit(ub, ublk_get_queue(ub, i));
+
+ /* set to NULL, otherwise new ubq_daemon cannot mmap the io_cmd_buf */
+ ub->mm = NULL;
+ ub->nr_queues_ready = 0;
+ ub->nr_privileged_daemon = 0;
+}
+
+static struct gendisk *ublk_get_disk(struct ublk_device *ub)
+{
+ struct gendisk *disk;
+
+ spin_lock(&ub->lock);
+ disk = ub->ub_disk;
+ if (disk)
+ get_device(disk_to_dev(disk));
+ spin_unlock(&ub->lock);
+
+ return disk;
+}
+
+static void ublk_put_disk(struct gendisk *disk)
+{
+ if (disk)
+ put_device(disk_to_dev(disk));
+}
+
static int ublk_ch_release(struct inode *inode, struct file *filp)
{
struct ublk_device *ub = filp->private_data;
+ struct gendisk *disk;
+ int i;
+ /*
+ * disk isn't attached yet, either device isn't live, or it has
+ * been removed already, so we needn't to do anything
+ */
+ disk = ublk_get_disk(ub);
+ if (!disk)
+ goto out;
+
+ /*
+ * All uring_cmd are done now, so abort any request outstanding to
+ * the ublk server
+ *
+ * This can be done in lockless way because ublk server has been
+ * gone
+ *
+ * More importantly, we have to provide forward progress guarantee
+ * without holding ub->mutex, otherwise control task grabbing
+ * ub->mutex triggers deadlock
+ *
+ * All requests may be inflight, so ->canceling may not be set, set
+ * it now.
+ */
+ for (i = 0; i < ub->dev_info.nr_hw_queues; i++) {
+ struct ublk_queue *ubq = ublk_get_queue(ub, i);
+
+ ubq->canceling = true;
+ ublk_abort_queue(ub, ubq);
+ }
+ blk_mq_kick_requeue_list(disk->queue);
+
+ /*
+ * All infligh requests have been completed or requeued and any new
+ * request will be failed or requeued via `->canceling` now, so it is
+ * fine to grab ub->mutex now.
+ */
+ mutex_lock(&ub->mutex);
+
+ /* double check after grabbing lock */
+ if (!ub->ub_disk)
+ goto unlock;
+
+ /*
+ * Transition the device to the nosrv state. What exactly this
+ * means depends on the recovery flags
+ */
+ blk_mq_quiesce_queue(disk->queue);
+ if (ublk_nosrv_should_stop_dev(ub)) {
+ /*
+ * Allow any pending/future I/O to pass through quickly
+ * with an error. This is needed because del_gendisk
+ * waits for all pending I/O to complete
+ */
+ for (i = 0; i < ub->dev_info.nr_hw_queues; i++)
+ ublk_get_queue(ub, i)->force_abort = true;
+ blk_mq_unquiesce_queue(disk->queue);
+
+ ublk_stop_dev_unlocked(ub);
+ } else {
+ if (ublk_nosrv_dev_should_queue_io(ub)) {
+ /* ->canceling is set and all requests are aborted */
+ ub->dev_info.state = UBLK_S_DEV_QUIESCED;
+ } else {
+ ub->dev_info.state = UBLK_S_DEV_FAIL_IO;
+ for (i = 0; i < ub->dev_info.nr_hw_queues; i++)
+ ublk_get_queue(ub, i)->fail_io = true;
+ }
+ blk_mq_unquiesce_queue(disk->queue);
+ }
+unlock:
+ mutex_unlock(&ub->mutex);
+ ublk_put_disk(disk);
+
+ /* all uring_cmd has been done now, reset device & ubq */
+ ublk_reset_ch_dev(ub);
+out:
clear_bit(UB_STATE_OPEN, &ub->state);
return 0;
}
@@ -1528,10 +1611,26 @@ static void ublk_commit_completion(struct ublk_device *ub,
ublk_put_req_ref(ubq, req);
}
+static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io,
+ struct request *req)
+{
+ WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE);
+
+ if (ublk_nosrv_should_reissue_outstanding(ubq->dev))
+ blk_mq_requeue_request(req, false);
+ else {
+ io->res = -EIO;
+ __ublk_complete_rq(req);
+ }
+}
+
/*
- * Called from ubq_daemon context via cancel fn, meantime quiesce ublk
- * blk-mq queue, so we are called exclusively with blk-mq and ubq_daemon
- * context, so everything is serialized.
+ * Called from ublk char device release handler, when any uring_cmd is
+ * done, meantime request queue is "quiesced" since all inflight requests
+ * can't be completed because ublk server is dead.
+ *
+ * So no one can hold our request IO reference any more, simply ignore the
+ * reference, and complete the request immediately
*/
static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq)
{
@@ -1548,46 +1647,29 @@ static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq)
* will do it
*/
rq = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], i);
- if (rq && blk_mq_request_started(rq)) {
- io->flags |= UBLK_IO_FLAG_ABORTED;
+ if (rq && blk_mq_request_started(rq))
__ublk_fail_req(ubq, io, rq);
- }
}
}
}
/* Must be called when queue is frozen */
-static bool ublk_mark_queue_canceling(struct ublk_queue *ubq)
+static void ublk_mark_queue_canceling(struct ublk_queue *ubq)
{
- bool canceled;
-
spin_lock(&ubq->cancel_lock);
- canceled = ubq->canceling;
- if (!canceled)
+ if (!ubq->canceling)
ubq->canceling = true;
spin_unlock(&ubq->cancel_lock);
-
- return canceled;
}
-static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq)
+static void ublk_start_cancel(struct ublk_queue *ubq)
{
- bool was_canceled = ubq->canceling;
- struct gendisk *disk;
-
- if (was_canceled)
- return false;
-
- spin_lock(&ub->lock);
- disk = ub->ub_disk;
- if (disk)
- get_device(disk_to_dev(disk));
- spin_unlock(&ub->lock);
+ struct ublk_device *ub = ubq->dev;
+ struct gendisk *disk = ublk_get_disk(ub);
/* Our disk has been dead */
if (!disk)
- return false;
-
+ return;
/*
* Now we are serialized with ublk_queue_rq()
*
@@ -1596,25 +1678,36 @@ static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq)
* touch completed uring_cmd
*/
blk_mq_quiesce_queue(disk->queue);
- was_canceled = ublk_mark_queue_canceling(ubq);
- if (!was_canceled) {
- /* abort queue is for making forward progress */
- ublk_abort_queue(ub, ubq);
- }
+ ublk_mark_queue_canceling(ubq);
blk_mq_unquiesce_queue(disk->queue);
- put_device(disk_to_dev(disk));
-
- return !was_canceled;
+ ublk_put_disk(disk);
}
-static void ublk_cancel_cmd(struct ublk_queue *ubq, struct ublk_io *io,
+static void ublk_cancel_cmd(struct ublk_queue *ubq, unsigned tag,
unsigned int issue_flags)
{
+ struct ublk_io *io = &ubq->ios[tag];
+ struct ublk_device *ub = ubq->dev;
+ struct request *req;
bool done;
if (!(io->flags & UBLK_IO_FLAG_ACTIVE))
return;
+ /*
+ * Don't try to cancel this command if the request is started for
+ * avoiding race between io_uring_cmd_done() and
+ * io_uring_cmd_complete_in_task().
+ *
+ * Either the started request will be aborted via __ublk_abort_rq(),
+ * then this uring_cmd is canceled next time, or it will be done in
+ * task work function ublk_dispatch_req() because io_uring guarantees
+ * that ublk_dispatch_req() is always called
+ */
+ req = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], tag);
+ if (req && blk_mq_request_started(req))
+ return;
+
spin_lock(&ubq->cancel_lock);
done = !!(io->flags & UBLK_IO_FLAG_CANCELED);
if (!done)
@@ -1628,6 +1721,17 @@ static void ublk_cancel_cmd(struct ublk_queue *ubq, struct ublk_io *io,
/*
* The ublk char device won't be closed when calling cancel fn, so both
* ublk device and queue are guaranteed to be live
+ *
+ * Two-stage cancel:
+ *
+ * - make every active uring_cmd done in ->cancel_fn()
+ *
+ * - aborting inflight ublk IO requests in ublk char device release handler,
+ * which depends on 1st stage because device can only be closed iff all
+ * uring_cmd are done
+ *
+ * Do _not_ try to acquire ub->mutex before all inflight requests are
+ * aborted, otherwise deadlock may be caused.
*/
static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd,
unsigned int issue_flags)
@@ -1635,9 +1739,6 @@ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd,
struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
struct ublk_queue *ubq = pdu->ubq;
struct task_struct *task;
- struct ublk_device *ub;
- bool need_schedule;
- struct ublk_io *io;
if (WARN_ON_ONCE(!ubq))
return;
@@ -1649,16 +1750,11 @@ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd,
if (WARN_ON_ONCE(task && task != ubq->ubq_daemon))
return;
- ub = ubq->dev;
- need_schedule = ublk_abort_requests(ub, ubq);
+ if (!ubq->canceling)
+ ublk_start_cancel(ubq);
- io = &ubq->ios[pdu->tag];
- WARN_ON_ONCE(io->cmd != cmd);
- ublk_cancel_cmd(ubq, io, issue_flags);
-
- if (need_schedule) {
- schedule_work(&ub->nosrv_work);
- }
+ WARN_ON_ONCE(ubq->ios[pdu->tag].cmd != cmd);
+ ublk_cancel_cmd(ubq, pdu->tag, issue_flags);
}
static inline bool ublk_queue_ready(struct ublk_queue *ubq)
@@ -1671,7 +1767,7 @@ static void ublk_cancel_queue(struct ublk_queue *ubq)
int i;
for (i = 0; i < ubq->q_depth; i++)
- ublk_cancel_cmd(ubq, &ubq->ios[i], IO_URING_F_UNLOCKED);
+ ublk_cancel_cmd(ubq, i, IO_URING_F_UNLOCKED);
}
/* Cancel all pending commands, must be called after del_gendisk() returns */
@@ -1709,33 +1805,20 @@ static void ublk_wait_tagset_rqs_idle(struct ublk_device *ub)
}
}
-static void __ublk_quiesce_dev(struct ublk_device *ub)
+static void ublk_force_abort_dev(struct ublk_device *ub)
{
- pr_devel("%s: quiesce ub: dev_id %d state %s\n",
+ int i;
+
+ pr_devel("%s: force abort ub: dev_id %d state %s\n",
__func__, ub->dev_info.dev_id,
ub->dev_info.state == UBLK_S_DEV_LIVE ?
"LIVE" : "QUIESCED");
blk_mq_quiesce_queue(ub->ub_disk->queue);
- ublk_wait_tagset_rqs_idle(ub);
- ub->dev_info.state = UBLK_S_DEV_QUIESCED;
-}
+ if (ub->dev_info.state == UBLK_S_DEV_LIVE)
+ ublk_wait_tagset_rqs_idle(ub);
-static void ublk_unquiesce_dev(struct ublk_device *ub)
-{
- int i;
-
- pr_devel("%s: unquiesce ub: dev_id %d state %s\n",
- __func__, ub->dev_info.dev_id,
- ub->dev_info.state == UBLK_S_DEV_LIVE ?
- "LIVE" : "QUIESCED");
- /* quiesce_work has run. We let requeued rqs be aborted
- * before running fallback_wq. "force_abort" must be seen
- * after request queue is unqiuesced. Then del_gendisk()
- * can move on.
- */
for (i = 0; i < ub->dev_info.nr_hw_queues; i++)
ublk_get_queue(ub, i)->force_abort = true;
-
blk_mq_unquiesce_queue(ub->ub_disk->queue);
/* We may have requeued some rqs in ublk_quiesce_queue() */
blk_mq_kick_requeue_list(ub->ub_disk->queue);
@@ -1756,61 +1839,51 @@ static struct gendisk *ublk_detach_disk(struct ublk_device *ub)
return disk;
}
-static void ublk_stop_dev(struct ublk_device *ub)
+static void ublk_stop_dev_unlocked(struct ublk_device *ub)
+ __must_hold(&ub->mutex)
{
struct gendisk *disk;
- mutex_lock(&ub->mutex);
if (ub->dev_info.state == UBLK_S_DEV_DEAD)
- goto unlock;
- if (ublk_nosrv_dev_should_queue_io(ub)) {
- if (ub->dev_info.state == UBLK_S_DEV_LIVE)
- __ublk_quiesce_dev(ub);
- ublk_unquiesce_dev(ub);
- }
+ return;
+
+ if (ublk_nosrv_dev_should_queue_io(ub))
+ ublk_force_abort_dev(ub);
del_gendisk(ub->ub_disk);
disk = ublk_detach_disk(ub);
put_disk(disk);
- unlock:
+}
+
+static void ublk_stop_dev(struct ublk_device *ub)
+{
+ mutex_lock(&ub->mutex);
+ ublk_stop_dev_unlocked(ub);
mutex_unlock(&ub->mutex);
ublk_cancel_dev(ub);
}
-static void ublk_nosrv_work(struct work_struct *work)
+/* reset ublk io_uring queue & io flags */
+static void ublk_reset_io_flags(struct ublk_device *ub)
{
- struct ublk_device *ub =
- container_of(work, struct ublk_device, nosrv_work);
- int i;
+ int i, j;
- if (ublk_nosrv_should_stop_dev(ub)) {
- ublk_stop_dev(ub);
- return;
+ for (i = 0; i < ub->dev_info.nr_hw_queues; i++) {
+ struct ublk_queue *ubq = ublk_get_queue(ub, i);
+
+ /* UBLK_IO_FLAG_CANCELED can be cleared now */
+ spin_lock(&ubq->cancel_lock);
+ for (j = 0; j < ubq->q_depth; j++)
+ ubq->ios[j].flags &= ~UBLK_IO_FLAG_CANCELED;
+ spin_unlock(&ubq->cancel_lock);
+ ubq->canceling = false;
+ ubq->fail_io = false;
}
-
- mutex_lock(&ub->mutex);
- if (ub->dev_info.state != UBLK_S_DEV_LIVE)
- goto unlock;
-
- if (ublk_nosrv_dev_should_queue_io(ub)) {
- __ublk_quiesce_dev(ub);
- } else {
- blk_mq_quiesce_queue(ub->ub_disk->queue);
- ub->dev_info.state = UBLK_S_DEV_FAIL_IO;
- for (i = 0; i < ub->dev_info.nr_hw_queues; i++) {
- ublk_get_queue(ub, i)->fail_io = true;
- }
- blk_mq_unquiesce_queue(ub->ub_disk->queue);
- }
-
- unlock:
- mutex_unlock(&ub->mutex);
- ublk_cancel_dev(ub);
}
/* device can only be started after all IOs are ready */
static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq)
+ __must_hold(&ub->mutex)
{
- mutex_lock(&ub->mutex);
ubq->nr_io_ready++;
if (ublk_queue_ready(ubq)) {
ubq->ubq_daemon = current;
@@ -1820,18 +1893,12 @@ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq)
if (capable(CAP_SYS_ADMIN))
ub->nr_privileged_daemon++;
}
- if (ub->nr_queues_ready == ub->dev_info.nr_hw_queues)
+
+ if (ub->nr_queues_ready == ub->dev_info.nr_hw_queues) {
+ /* now we are ready for handling ublk io request */
+ ublk_reset_io_flags(ub);
complete_all(&ub->completion);
- mutex_unlock(&ub->mutex);
-}
-
-static void ublk_handle_need_get_data(struct ublk_device *ub, int q_id,
- int tag)
-{
- struct ublk_queue *ubq = ublk_get_queue(ub, q_id);
- struct request *req = blk_mq_tag_to_rq(ub->tag_set.tags[q_id], tag);
-
- ublk_queue_cmd(ubq, req);
+ }
}
static inline int ublk_check_cmd_op(u32 cmd_op)
@@ -1906,6 +1973,52 @@ static int ublk_unregister_io_buf(struct io_uring_cmd *cmd,
return io_buffer_unregister_bvec(cmd, index, issue_flags);
}
+static int ublk_fetch(struct io_uring_cmd *cmd, struct ublk_queue *ubq,
+ struct ublk_io *io, __u64 buf_addr)
+{
+ struct ublk_device *ub = ubq->dev;
+ int ret = 0;
+
+ /*
+ * When handling FETCH command for setting up ublk uring queue,
+ * ub->mutex is the innermost lock, and we won't block for handling
+ * FETCH, so it is fine even for IO_URING_F_NONBLOCK.
+ */
+ mutex_lock(&ub->mutex);
+ /* UBLK_IO_FETCH_REQ is only allowed before queue is setup */
+ if (ublk_queue_ready(ubq)) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ /* allow each command to be FETCHed at most once */
+ if (io->flags & UBLK_IO_FLAG_ACTIVE) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV);
+
+ if (ublk_need_map_io(ubq)) {
+ /*
+ * FETCH_RQ has to provide IO buffer if NEED GET
+ * DATA is not enabled
+ */
+ if (!buf_addr && !ublk_need_get_data(ubq))
+ goto out;
+ } else if (buf_addr) {
+ /* User copy requires addr to be unset */
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ublk_fill_io_cmd(io, cmd, buf_addr);
+ ublk_mark_io_ready(ub, ubq);
+out:
+ mutex_unlock(&ub->mutex);
+ return ret;
+}
+
static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
unsigned int issue_flags,
const struct ublksrv_io_cmd *ub_cmd)
@@ -1962,33 +2075,9 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
case UBLK_IO_UNREGISTER_IO_BUF:
return ublk_unregister_io_buf(cmd, ub_cmd->addr, issue_flags);
case UBLK_IO_FETCH_REQ:
- /* UBLK_IO_FETCH_REQ is only allowed before queue is setup */
- if (ublk_queue_ready(ubq)) {
- ret = -EBUSY;
+ ret = ublk_fetch(cmd, ubq, io, ub_cmd->addr);
+ if (ret)
goto out;
- }
- /*
- * The io is being handled by server, so COMMIT_RQ is expected
- * instead of FETCH_REQ
- */
- if (io->flags & UBLK_IO_FLAG_OWNED_BY_SRV)
- goto out;
-
- if (ublk_need_map_io(ubq)) {
- /*
- * FETCH_RQ has to provide IO buffer if NEED GET
- * DATA is not enabled
- */
- if (!ub_cmd->addr && !ublk_need_get_data(ubq))
- goto out;
- } else if (ub_cmd->addr) {
- /* User copy requires addr to be unset */
- ret = -EINVAL;
- goto out;
- }
-
- ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
- ublk_mark_io_ready(ub, ubq);
break;
case UBLK_IO_COMMIT_AND_FETCH_REQ:
req = blk_mq_tag_to_rq(ub->tag_set.tags[ub_cmd->q_id], tag);
@@ -2020,8 +2109,9 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV))
goto out;
ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
- ublk_handle_need_get_data(ub, ub_cmd->q_id, ub_cmd->tag);
- break;
+ req = blk_mq_tag_to_rq(ub->tag_set.tags[ub_cmd->q_id], tag);
+ ublk_dispatch_req(ubq, req, issue_flags);
+ return -EIOCBQUEUED;
default:
goto out;
}
@@ -2388,7 +2478,6 @@ static void ublk_remove(struct ublk_device *ub)
bool unprivileged;
ublk_stop_dev(ub);
- cancel_work_sync(&ub->nosrv_work);
cdev_device_del(&ub->cdev, &ub->cdev_dev);
unprivileged = ub->dev_info.flags & UBLK_F_UNPRIVILEGED_DEV;
ublk_put_device(ub);
@@ -2413,9 +2502,9 @@ static struct ublk_device *ublk_get_device_from_id(int idx)
return ub;
}
-static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
+static int ublk_ctrl_start_dev(struct ublk_device *ub,
+ const struct ublksrv_ctrl_cmd *header)
{
- const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
const struct ublk_param_basic *p = &ub->params.basic;
int ublksrv_pid = (int)header->data[0];
struct queue_limits lim = {
@@ -2534,9 +2623,8 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
}
static int ublk_ctrl_get_queue_affinity(struct ublk_device *ub,
- struct io_uring_cmd *cmd)
+ const struct ublksrv_ctrl_cmd *header)
{
- const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
void __user *argp = (void __user *)(unsigned long)header->addr;
cpumask_var_t cpumask;
unsigned long queue;
@@ -2585,9 +2673,8 @@ static inline void ublk_dump_dev_info(struct ublksrv_ctrl_dev_info *info)
info->nr_hw_queues, info->queue_depth);
}
-static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd)
+static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header)
{
- const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
void __user *argp = (void __user *)(unsigned long)header->addr;
struct ublksrv_ctrl_dev_info info;
struct ublk_device *ub;
@@ -2675,7 +2762,6 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd)
goto out_unlock;
mutex_init(&ub->mutex);
spin_lock_init(&ub->lock);
- INIT_WORK(&ub->nosrv_work, ublk_nosrv_work);
ret = ublk_alloc_dev_number(ub, header->dev_id);
if (ret < 0)
@@ -2807,14 +2893,12 @@ static inline void ublk_ctrl_cmd_dump(struct io_uring_cmd *cmd)
static int ublk_ctrl_stop_dev(struct ublk_device *ub)
{
ublk_stop_dev(ub);
- cancel_work_sync(&ub->nosrv_work);
return 0;
}
static int ublk_ctrl_get_dev_info(struct ublk_device *ub,
- struct io_uring_cmd *cmd)
+ const struct ublksrv_ctrl_cmd *header)
{
- const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
void __user *argp = (void __user *)(unsigned long)header->addr;
if (header->len < sizeof(struct ublksrv_ctrl_dev_info) || !header->addr)
@@ -2843,9 +2927,8 @@ static void ublk_ctrl_fill_params_devt(struct ublk_device *ub)
}
static int ublk_ctrl_get_params(struct ublk_device *ub,
- struct io_uring_cmd *cmd)
+ const struct ublksrv_ctrl_cmd *header)
{
- const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
void __user *argp = (void __user *)(unsigned long)header->addr;
struct ublk_params_header ph;
int ret;
@@ -2874,9 +2957,8 @@ static int ublk_ctrl_get_params(struct ublk_device *ub,
}
static int ublk_ctrl_set_params(struct ublk_device *ub,
- struct io_uring_cmd *cmd)
+ const struct ublksrv_ctrl_cmd *header)
{
- const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
void __user *argp = (void __user *)(unsigned long)header->addr;
struct ublk_params_header ph;
int ret = -EFAULT;
@@ -2914,43 +2996,14 @@ static int ublk_ctrl_set_params(struct ublk_device *ub,
return ret;
}
-static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq)
-{
- int i;
-
- WARN_ON_ONCE(!(ubq->ubq_daemon && ubq_daemon_is_dying(ubq)));
-
- /* All old ioucmds have to be completed */
- ubq->nr_io_ready = 0;
- /* old daemon is PF_EXITING, put it now */
- put_task_struct(ubq->ubq_daemon);
- /* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */
- ubq->ubq_daemon = NULL;
- ubq->timeout = false;
- ubq->canceling = false;
-
- for (i = 0; i < ubq->q_depth; i++) {
- struct ublk_io *io = &ubq->ios[i];
-
- /* forget everything now and be ready for new FETCH_REQ */
- io->flags = 0;
- io->cmd = NULL;
- io->addr = 0;
- }
-}
-
static int ublk_ctrl_start_recovery(struct ublk_device *ub,
- struct io_uring_cmd *cmd)
+ const struct ublksrv_ctrl_cmd *header)
{
- const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
int ret = -EINVAL;
- int i;
mutex_lock(&ub->mutex);
if (ublk_nosrv_should_stop_dev(ub))
goto out_unlock;
- if (!ub->nr_queues_ready)
- goto out_unlock;
/*
* START_RECOVERY is only allowd after:
*
@@ -2974,12 +3027,6 @@ static int ublk_ctrl_start_recovery(struct ublk_device *ub,
goto out_unlock;
}
pr_devel("%s: start recovery for dev id %d.\n", __func__, header->dev_id);
- for (i = 0; i < ub->dev_info.nr_hw_queues; i++)
- ublk_queue_reinit(ub, ublk_get_queue(ub, i));
- /* set to NULL, otherwise new ubq_daemon cannot mmap the io_cmd_buf */
- ub->mm = NULL;
- ub->nr_queues_ready = 0;
- ub->nr_privileged_daemon = 0;
init_completion(&ub->completion);
ret = 0;
out_unlock:
@@ -2988,12 +3035,10 @@ static int ublk_ctrl_start_recovery(struct ublk_device *ub,
}
static int ublk_ctrl_end_recovery(struct ublk_device *ub,
- struct io_uring_cmd *cmd)
+ const struct ublksrv_ctrl_cmd *header)
{
- const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
int ublksrv_pid = (int)header->data[0];
int ret = -EINVAL;
- int i;
pr_devel("%s: Waiting for new ubq_daemons(nr: %d) are ready, dev id %d...\n",
__func__, ub->dev_info.nr_hw_queues, header->dev_id);
@@ -3013,33 +3058,18 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub,
goto out_unlock;
}
ub->dev_info.ublksrv_pid = ublksrv_pid;
+ ub->dev_info.state = UBLK_S_DEV_LIVE;
pr_devel("%s: new ublksrv_pid %d, dev id %d\n",
__func__, ublksrv_pid, header->dev_id);
-
- if (ublk_nosrv_dev_should_queue_io(ub)) {
- ub->dev_info.state = UBLK_S_DEV_LIVE;
- blk_mq_unquiesce_queue(ub->ub_disk->queue);
- pr_devel("%s: queue unquiesced, dev id %d.\n",
- __func__, header->dev_id);
- blk_mq_kick_requeue_list(ub->ub_disk->queue);
- } else {
- blk_mq_quiesce_queue(ub->ub_disk->queue);
- ub->dev_info.state = UBLK_S_DEV_LIVE;
- for (i = 0; i < ub->dev_info.nr_hw_queues; i++) {
- ublk_get_queue(ub, i)->fail_io = false;
- }
- blk_mq_unquiesce_queue(ub->ub_disk->queue);
- }
-
+ blk_mq_kick_requeue_list(ub->ub_disk->queue);
ret = 0;
out_unlock:
mutex_unlock(&ub->mutex);
return ret;
}
-static int ublk_ctrl_get_features(struct io_uring_cmd *cmd)
+static int ublk_ctrl_get_features(const struct ublksrv_ctrl_cmd *header)
{
- const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
void __user *argp = (void __user *)(unsigned long)header->addr;
u64 features = UBLK_F_ALL;
@@ -3178,7 +3208,7 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
goto out;
if (cmd_op == UBLK_U_CMD_GET_FEATURES) {
- ret = ublk_ctrl_get_features(cmd);
+ ret = ublk_ctrl_get_features(header);
goto out;
}
@@ -3195,17 +3225,17 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
switch (_IOC_NR(cmd_op)) {
case UBLK_CMD_START_DEV:
- ret = ublk_ctrl_start_dev(ub, cmd);
+ ret = ublk_ctrl_start_dev(ub, header);
break;
case UBLK_CMD_STOP_DEV:
ret = ublk_ctrl_stop_dev(ub);
break;
case UBLK_CMD_GET_DEV_INFO:
case UBLK_CMD_GET_DEV_INFO2:
- ret = ublk_ctrl_get_dev_info(ub, cmd);
+ ret = ublk_ctrl_get_dev_info(ub, header);
break;
case UBLK_CMD_ADD_DEV:
- ret = ublk_ctrl_add_dev(cmd);
+ ret = ublk_ctrl_add_dev(header);
break;
case UBLK_CMD_DEL_DEV:
ret = ublk_ctrl_del_dev(&ub, true);
@@ -3214,19 +3244,19 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
ret = ublk_ctrl_del_dev(&ub, false);
break;
case UBLK_CMD_GET_QUEUE_AFFINITY:
- ret = ublk_ctrl_get_queue_affinity(ub, cmd);
+ ret = ublk_ctrl_get_queue_affinity(ub, header);
break;
case UBLK_CMD_GET_PARAMS:
- ret = ublk_ctrl_get_params(ub, cmd);
+ ret = ublk_ctrl_get_params(ub, header);
break;
case UBLK_CMD_SET_PARAMS:
- ret = ublk_ctrl_set_params(ub, cmd);
+ ret = ublk_ctrl_set_params(ub, header);
break;
case UBLK_CMD_START_USER_RECOVERY:
- ret = ublk_ctrl_start_recovery(ub, cmd);
+ ret = ublk_ctrl_start_recovery(ub, header);
break;
case UBLK_CMD_END_USER_RECOVERY:
- ret = ublk_ctrl_end_recovery(ub, cmd);
+ ret = ublk_ctrl_end_recovery(ub, header);
break;
default:
ret = -EOPNOTSUPP;
diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index c1e69fc..0a759ea 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -957,8 +957,10 @@ static int btintel_pcie_recv_event(struct hci_dev *hdev, struct sk_buff *skb)
/* This is a debug event that comes from IML and OP image when it
* starts execution. There is no need pass this event to stack.
*/
- if (skb->data[2] == 0x97)
+ if (skb->data[2] == 0x97) {
+ hci_recv_diag(hdev, skb);
return 0;
+ }
}
return hci_recv_frame(hdev, skb);
@@ -974,7 +976,6 @@ static int btintel_pcie_recv_frame(struct btintel_pcie_data *data,
u8 pkt_type;
u16 plen;
u32 pcie_pkt_type;
- struct sk_buff *new_skb;
void *pdata;
struct hci_dev *hdev = data->hdev;
@@ -1051,24 +1052,20 @@ static int btintel_pcie_recv_frame(struct btintel_pcie_data *data,
bt_dev_dbg(hdev, "pkt_type: 0x%2.2x len: %u", pkt_type, plen);
- new_skb = bt_skb_alloc(plen, GFP_ATOMIC);
- if (!new_skb) {
- bt_dev_err(hdev, "Failed to allocate memory for skb of len: %u",
- skb->len);
- ret = -ENOMEM;
- goto exit_error;
- }
-
- hci_skb_pkt_type(new_skb) = pkt_type;
- skb_put_data(new_skb, skb->data, plen);
+ hci_skb_pkt_type(skb) = pkt_type;
hdev->stat.byte_rx += plen;
+ skb_trim(skb, plen);
if (pcie_pkt_type == BTINTEL_PCIE_HCI_EVT_PKT)
- ret = btintel_pcie_recv_event(hdev, new_skb);
+ ret = btintel_pcie_recv_event(hdev, skb);
else
- ret = hci_recv_frame(hdev, new_skb);
+ ret = hci_recv_frame(hdev, skb);
+ skb = NULL; /* skb is freed in the callee */
exit_error:
+ if (skb)
+ kfree_skb(skb);
+
if (ret)
hdev->stat.err_rx++;
@@ -1202,8 +1199,6 @@ static void btintel_pcie_rx_work(struct work_struct *work)
struct btintel_pcie_data *data = container_of(work,
struct btintel_pcie_data, rx_work);
struct sk_buff *skb;
- int err;
- struct hci_dev *hdev = data->hdev;
if (test_bit(BTINTEL_PCIE_HWEXP_INPROGRESS, &data->flags)) {
/* Unlike usb products, controller will not send hardware
@@ -1224,11 +1219,7 @@ static void btintel_pcie_rx_work(struct work_struct *work)
/* Process the sk_buf in queue and send to the HCI layer */
while ((skb = skb_dequeue(&data->rx_skb_q))) {
- err = btintel_pcie_recv_frame(data, skb);
- if (err)
- bt_dev_err(hdev, "Failed to send received frame: %d",
- err);
- kfree_skb(skb);
+ btintel_pcie_recv_frame(data, skb);
}
}
@@ -1281,10 +1272,8 @@ static void btintel_pcie_msix_rx_handle(struct btintel_pcie_data *data)
bt_dev_dbg(hdev, "RXQ: cr_hia: %u cr_tia: %u", cr_hia, cr_tia);
/* Check CR_TIA and CR_HIA for change */
- if (cr_tia == cr_hia) {
- bt_dev_warn(hdev, "RXQ: no new CD found");
+ if (cr_tia == cr_hia)
return;
- }
rxq = &data->rxq;
@@ -1320,6 +1309,16 @@ static irqreturn_t btintel_pcie_msix_isr(int irq, void *data)
return IRQ_WAKE_THREAD;
}
+static inline bool btintel_pcie_is_rxq_empty(struct btintel_pcie_data *data)
+{
+ return data->ia.cr_hia[BTINTEL_PCIE_RXQ_NUM] == data->ia.cr_tia[BTINTEL_PCIE_RXQ_NUM];
+}
+
+static inline bool btintel_pcie_is_txackq_empty(struct btintel_pcie_data *data)
+{
+ return data->ia.cr_tia[BTINTEL_PCIE_TXQ_NUM] == data->ia.cr_hia[BTINTEL_PCIE_TXQ_NUM];
+}
+
static irqreturn_t btintel_pcie_irq_msix_handler(int irq, void *dev_id)
{
struct msix_entry *entry = dev_id;
@@ -1351,12 +1350,18 @@ static irqreturn_t btintel_pcie_irq_msix_handler(int irq, void *dev_id)
btintel_pcie_msix_gp0_handler(data);
/* For TX */
- if (intr_fh & BTINTEL_PCIE_MSIX_FH_INT_CAUSES_0)
+ if (intr_fh & BTINTEL_PCIE_MSIX_FH_INT_CAUSES_0) {
btintel_pcie_msix_tx_handle(data);
+ if (!btintel_pcie_is_rxq_empty(data))
+ btintel_pcie_msix_rx_handle(data);
+ }
/* For RX */
- if (intr_fh & BTINTEL_PCIE_MSIX_FH_INT_CAUSES_1)
+ if (intr_fh & BTINTEL_PCIE_MSIX_FH_INT_CAUSES_1) {
btintel_pcie_msix_rx_handle(data);
+ if (!btintel_pcie_is_txackq_empty(data))
+ btintel_pcie_msix_tx_handle(data);
+ }
/*
* Before sending the interrupt the HW disables it to prevent a nested
diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c
index edd5eea..1d26207 100644
--- a/drivers/bluetooth/btmtksdio.c
+++ b/drivers/bluetooth/btmtksdio.c
@@ -723,6 +723,10 @@ static int btmtksdio_close(struct hci_dev *hdev)
{
struct btmtksdio_dev *bdev = hci_get_drvdata(hdev);
+ /* Skip btmtksdio_close if BTMTKSDIO_FUNC_ENABLED isn't set */
+ if (!test_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state))
+ return 0;
+
sdio_claim_host(bdev->func);
/* Disable interrupt */
@@ -1443,11 +1447,15 @@ static void btmtksdio_remove(struct sdio_func *func)
if (!bdev)
return;
+ hdev = bdev->hdev;
+
+ /* Make sure to call btmtksdio_close before removing sdio card */
+ if (test_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state))
+ btmtksdio_close(hdev);
+
/* Be consistent the state in btmtksdio_probe */
pm_runtime_get_noresume(bdev->dev);
- hdev = bdev->hdev;
-
sdio_set_drvdata(func, NULL);
hci_unregister_dev(hdev);
hci_free_dev(hdev);
diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index 5091dea..604ab2b 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -1286,7 +1286,9 @@ static void nxp_coredump(struct hci_dev *hdev)
u8 pcmd = 2;
skb = nxp_drv_send_cmd(hdev, HCI_NXP_TRIGGER_DUMP, 1, &pcmd);
- if (!IS_ERR(skb))
+ if (IS_ERR(skb))
+ bt_dev_err(hdev, "Failed to trigger FW Dump. (%ld)", PTR_ERR(skb));
+ else
kfree_skb(skb);
}
@@ -1445,9 +1447,6 @@ static int nxp_shutdown(struct hci_dev *hdev)
/* HCI_NXP_IND_RESET command may not returns any response */
if (!IS_ERR(skb))
kfree_skb(skb);
- } else if (nxpdev->current_baudrate != nxpdev->fw_init_baudrate) {
- nxpdev->new_baudrate = nxpdev->fw_init_baudrate;
- nxp_set_baudrate_cmd(hdev, NULL);
}
return 0;
@@ -1799,13 +1798,15 @@ static void nxp_serdev_remove(struct serdev_device *serdev)
clear_bit(BTNXPUART_FW_DOWNLOADING, &nxpdev->tx_state);
wake_up_interruptible(&nxpdev->check_boot_sign_wait_q);
wake_up_interruptible(&nxpdev->fw_dnld_done_wait_q);
- }
-
- if (test_bit(HCI_RUNNING, &hdev->flags)) {
- /* Ensure shutdown callback is executed before unregistering, so
- * that baudrate is reset to initial value.
+ } else {
+ /* Restore FW baudrate to fw_init_baudrate if changed.
+ * This will ensure FW baudrate is in sync with
+ * driver baudrate in case this driver is re-inserted.
*/
- nxp_shutdown(hdev);
+ if (nxpdev->current_baudrate != nxpdev->fw_init_baudrate) {
+ nxpdev->new_baudrate = nxpdev->fw_init_baudrate;
+ nxp_set_baudrate_cmd(hdev, NULL);
+ }
}
ps_cleanup(nxpdev);
diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index 3d6778b..edefb9d 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -889,7 +889,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
if (le32_to_cpu(ver.soc_id) == QCA_WCN3950_SOC_ID_T)
variant = "t";
else if (le32_to_cpu(ver.soc_id) == QCA_WCN3950_SOC_ID_S)
- variant = "u";
+ variant = "s";
snprintf(config.fwname, sizeof(config.fwname),
"qca/cmnv%02x%s.bin", rom_ver, variant);
diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index d3eba0d..7838c89 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -1215,6 +1215,8 @@ struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev,
rtl_dev_err(hdev, "mandatory config file %s not found",
btrtl_dev->ic_info->cfg_name);
ret = btrtl_dev->cfg_len;
+ if (!ret)
+ ret = -EINVAL;
goto err_free;
}
}
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 5012b5f..a42dedb 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -3010,22 +3010,16 @@ static void btusb_coredump_qca(struct hci_dev *hdev)
bt_dev_err(hdev, "%s: triggle crash failed (%d)", __func__, err);
}
-/*
- * ==0: not a dump pkt.
- * < 0: fails to handle a dump pkt
- * > 0: otherwise.
- */
+/* Return: 0 on success, negative errno on failure. */
static int handle_dump_pkt_qca(struct hci_dev *hdev, struct sk_buff *skb)
{
- int ret = 1;
+ int ret = 0;
u8 pkt_type;
u8 *sk_ptr;
unsigned int sk_len;
u16 seqno;
u32 dump_size;
- struct hci_event_hdr *event_hdr;
- struct hci_acl_hdr *acl_hdr;
struct qca_dump_hdr *dump_hdr;
struct btusb_data *btdata = hci_get_drvdata(hdev);
struct usb_device *udev = btdata->udev;
@@ -3035,30 +3029,14 @@ static int handle_dump_pkt_qca(struct hci_dev *hdev, struct sk_buff *skb)
sk_len = skb->len;
if (pkt_type == HCI_ACLDATA_PKT) {
- acl_hdr = hci_acl_hdr(skb);
- if (le16_to_cpu(acl_hdr->handle) != QCA_MEMDUMP_ACL_HANDLE)
- return 0;
sk_ptr += HCI_ACL_HDR_SIZE;
sk_len -= HCI_ACL_HDR_SIZE;
- event_hdr = (struct hci_event_hdr *)sk_ptr;
- } else {
- event_hdr = hci_event_hdr(skb);
}
- if ((event_hdr->evt != HCI_VENDOR_PKT)
- || (event_hdr->plen != (sk_len - HCI_EVENT_HDR_SIZE)))
- return 0;
-
sk_ptr += HCI_EVENT_HDR_SIZE;
sk_len -= HCI_EVENT_HDR_SIZE;
dump_hdr = (struct qca_dump_hdr *)sk_ptr;
- if ((sk_len < offsetof(struct qca_dump_hdr, data))
- || (dump_hdr->vse_class != QCA_MEMDUMP_VSE_CLASS)
- || (dump_hdr->msg_type != QCA_MEMDUMP_MSG_TYPE))
- return 0;
-
- /*it is dump pkt now*/
seqno = le16_to_cpu(dump_hdr->seqno);
if (seqno == 0) {
set_bit(BTUSB_HW_SSR_ACTIVE, &btdata->flags);
@@ -3132,17 +3110,84 @@ static int handle_dump_pkt_qca(struct hci_dev *hdev, struct sk_buff *skb)
return ret;
}
+/* Return: true if the ACL packet is a dump packet, false otherwise. */
+static bool acl_pkt_is_dump_qca(struct hci_dev *hdev, struct sk_buff *skb)
+{
+ u8 *sk_ptr;
+ unsigned int sk_len;
+
+ struct hci_event_hdr *event_hdr;
+ struct hci_acl_hdr *acl_hdr;
+ struct qca_dump_hdr *dump_hdr;
+
+ sk_ptr = skb->data;
+ sk_len = skb->len;
+
+ acl_hdr = hci_acl_hdr(skb);
+ if (le16_to_cpu(acl_hdr->handle) != QCA_MEMDUMP_ACL_HANDLE)
+ return false;
+
+ sk_ptr += HCI_ACL_HDR_SIZE;
+ sk_len -= HCI_ACL_HDR_SIZE;
+ event_hdr = (struct hci_event_hdr *)sk_ptr;
+
+ if ((event_hdr->evt != HCI_VENDOR_PKT) ||
+ (event_hdr->plen != (sk_len - HCI_EVENT_HDR_SIZE)))
+ return false;
+
+ sk_ptr += HCI_EVENT_HDR_SIZE;
+ sk_len -= HCI_EVENT_HDR_SIZE;
+
+ dump_hdr = (struct qca_dump_hdr *)sk_ptr;
+ if ((sk_len < offsetof(struct qca_dump_hdr, data)) ||
+ (dump_hdr->vse_class != QCA_MEMDUMP_VSE_CLASS) ||
+ (dump_hdr->msg_type != QCA_MEMDUMP_MSG_TYPE))
+ return false;
+
+ return true;
+}
+
+/* Return: true if the event packet is a dump packet, false otherwise. */
+static bool evt_pkt_is_dump_qca(struct hci_dev *hdev, struct sk_buff *skb)
+{
+ u8 *sk_ptr;
+ unsigned int sk_len;
+
+ struct hci_event_hdr *event_hdr;
+ struct qca_dump_hdr *dump_hdr;
+
+ sk_ptr = skb->data;
+ sk_len = skb->len;
+
+ event_hdr = hci_event_hdr(skb);
+
+ if ((event_hdr->evt != HCI_VENDOR_PKT)
+ || (event_hdr->plen != (sk_len - HCI_EVENT_HDR_SIZE)))
+ return false;
+
+ sk_ptr += HCI_EVENT_HDR_SIZE;
+ sk_len -= HCI_EVENT_HDR_SIZE;
+
+ dump_hdr = (struct qca_dump_hdr *)sk_ptr;
+ if ((sk_len < offsetof(struct qca_dump_hdr, data)) ||
+ (dump_hdr->vse_class != QCA_MEMDUMP_VSE_CLASS) ||
+ (dump_hdr->msg_type != QCA_MEMDUMP_MSG_TYPE))
+ return false;
+
+ return true;
+}
+
static int btusb_recv_acl_qca(struct hci_dev *hdev, struct sk_buff *skb)
{
- if (handle_dump_pkt_qca(hdev, skb))
- return 0;
+ if (acl_pkt_is_dump_qca(hdev, skb))
+ return handle_dump_pkt_qca(hdev, skb);
return hci_recv_frame(hdev, skb);
}
static int btusb_recv_evt_qca(struct hci_dev *hdev, struct sk_buff *skb)
{
- if (handle_dump_pkt_qca(hdev, skb))
- return 0;
+ if (evt_pkt_is_dump_qca(hdev, skb))
+ return handle_dump_pkt_qca(hdev, skb);
return hci_recv_frame(hdev, skb);
}
diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index a51935d..59f4d7b 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -289,18 +289,18 @@ static void vhci_coredump(struct hci_dev *hdev)
static void vhci_coredump_hdr(struct hci_dev *hdev, struct sk_buff *skb)
{
- char buf[80];
+ const char *buf;
- snprintf(buf, sizeof(buf), "Controller Name: vhci_ctrl\n");
+ buf = "Controller Name: vhci_ctrl\n";
skb_put_data(skb, buf, strlen(buf));
- snprintf(buf, sizeof(buf), "Firmware Version: vhci_fw\n");
+ buf = "Firmware Version: vhci_fw\n";
skb_put_data(skb, buf, strlen(buf));
- snprintf(buf, sizeof(buf), "Driver: vhci_drv\n");
+ buf = "Driver: vhci_drv\n";
skb_put_data(skb, buf, strlen(buf));
- snprintf(buf, sizeof(buf), "Vendor: vhci\n");
+ buf = "Vendor: vhci\n";
skb_put_data(skb, buf, strlen(buf));
}
diff --git a/drivers/char/misc.c b/drivers/char/misc.c
index f7dd455..dda466f 100644
--- a/drivers/char/misc.c
+++ b/drivers/char/misc.c
@@ -315,7 +315,7 @@ static int __init misc_init(void)
goto fail_remove;
err = -EIO;
- if (register_chrdev(MISC_MAJOR, "misc", &misc_fops))
+ if (__register_chrdev(MISC_MAJOR, 0, MINORMASK + 1, "misc", &misc_fops))
goto fail_printk;
return 0;
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 5f04951..088182e 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1576,8 +1576,8 @@ static void handle_control_message(struct virtio_device *vdev,
break;
case VIRTIO_CONSOLE_RESIZE: {
struct {
- __u16 rows;
- __u16 cols;
+ __virtio16 cols;
+ __virtio16 rows;
} size;
if (!is_console_port(port))
@@ -1585,7 +1585,8 @@ static void handle_control_message(struct virtio_device *vdev,
memcpy(&size, buf->buf + buf->offset + sizeof(*cpkt),
sizeof(size));
- set_console_size(port, size.rows, size.cols);
+ set_console_size(port, virtio16_to_cpu(vdev, size.rows),
+ virtio16_to_cpu(vdev, size.cols));
port->cons.hvc->irq_requested = 1;
resize_console(port);
diff --git a/drivers/comedi/drivers/jr3_pci.c b/drivers/comedi/drivers/jr3_pci.c
index cdc842b..75dce1f 100644
--- a/drivers/comedi/drivers/jr3_pci.c
+++ b/drivers/comedi/drivers/jr3_pci.c
@@ -758,7 +758,7 @@ static void jr3_pci_detach(struct comedi_device *dev)
struct jr3_pci_dev_private *devpriv = dev->private;
if (devpriv)
- timer_delete_sync(&devpriv->timer);
+ timer_shutdown_sync(&devpriv->timer);
comedi_pci_detach(dev);
}
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 4f9cb94..0d46402 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -76,7 +76,7 @@
config ARM_BRCMSTB_AVS_CPUFREQ
tristate "Broadcom STB AVS CPUfreq driver"
depends on (ARCH_BRCMSTB && !ARM_SCMI_CPUFREQ) || COMPILE_TEST
- default y
+ default y if ARCH_BRCMSTB && !ARM_SCMI_CPUFREQ
help
Some Broadcom STB SoCs use a co-processor running proprietary firmware
("AVS") to handle voltage and frequency scaling. This driver provides
@@ -88,7 +88,7 @@
tristate "Calxeda Highbank-based"
depends on ARCH_HIGHBANK || COMPILE_TEST
depends on CPUFREQ_DT && REGULATOR && PL320_MBOX
- default m
+ default m if ARCH_HIGHBANK
help
This adds the CPUFreq driver for Calxeda Highbank SoC
based boards.
@@ -133,7 +133,7 @@
config ARM_MEDIATEK_CPUFREQ_HW
tristate "MediaTek CPUFreq HW driver"
depends on ARCH_MEDIATEK || COMPILE_TEST
- default m
+ default m if ARCH_MEDIATEK
help
Support for the CPUFreq HW driver.
Some MediaTek chipsets have a HW engine to offload the steps
@@ -181,7 +181,7 @@
config ARM_S3C64XX_CPUFREQ
bool "Samsung S3C64XX"
depends on CPU_S3C6410 || COMPILE_TEST
- default y
+ default CPU_S3C6410
help
This adds the CPUFreq driver for Samsung S3C6410 SoC.
@@ -190,7 +190,7 @@
config ARM_S5PV210_CPUFREQ
bool "Samsung S5PV210 and S5PC110"
depends on CPU_S5PV210 || COMPILE_TEST
- default y
+ default CPU_S5PV210
help
This adds the CPUFreq driver for Samsung S5PV210 and
S5PC110 SoCs.
@@ -214,7 +214,7 @@
config ARM_SPEAR_CPUFREQ
bool "SPEAr CPUFreq support"
depends on PLAT_SPEAR || COMPILE_TEST
- default y
+ default PLAT_SPEAR
help
This adds the CPUFreq driver support for SPEAr SOCs.
@@ -233,7 +233,7 @@
tristate "Tegra20/30 CPUFreq support"
depends on ARCH_TEGRA || COMPILE_TEST
depends on CPUFREQ_DT
- default y
+ default ARCH_TEGRA
help
This adds the CPUFreq driver support for Tegra20/30 SOCs.
@@ -241,7 +241,7 @@
bool "Tegra124 CPUFreq support"
depends on ARCH_TEGRA || COMPILE_TEST
depends on CPUFREQ_DT
- default y
+ default ARCH_TEGRA
help
This adds the CPUFreq driver support for Tegra124 SOCs.
@@ -256,14 +256,14 @@
tristate "Tegra194 CPUFreq support"
depends on ARCH_TEGRA_194_SOC || ARCH_TEGRA_234_SOC || (64BIT && COMPILE_TEST)
depends on TEGRA_BPMP
- default y
+ default ARCH_TEGRA_194_SOC || ARCH_TEGRA_234_SOC
help
This adds CPU frequency driver support for Tegra194 SOCs.
config ARM_TI_CPUFREQ
bool "Texas Instruments CPUFreq support"
depends on ARCH_OMAP2PLUS || ARCH_K3 || COMPILE_TEST
- default y
+ default ARCH_OMAP2PLUS || ARCH_K3
help
This driver enables valid OPPs on the running platform based on
values contained within the SoC in use. Enable this in order to
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 6789eed1..b961f3a 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -607,13 +607,16 @@ static void amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
union perf_cached perf = READ_ONCE(cpudata->perf);
perf.max_limit_perf = freq_to_perf(perf, cpudata->nominal_freq, policy->max);
- perf.min_limit_perf = freq_to_perf(perf, cpudata->nominal_freq, policy->min);
-
- if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
- perf.min_limit_perf = min(perf.nominal_perf, perf.max_limit_perf);
-
WRITE_ONCE(cpudata->max_limit_freq, policy->max);
- WRITE_ONCE(cpudata->min_limit_freq, policy->min);
+
+ if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) {
+ perf.min_limit_perf = min(perf.nominal_perf, perf.max_limit_perf);
+ WRITE_ONCE(cpudata->min_limit_freq, min(cpudata->nominal_freq, cpudata->max_limit_freq));
+ } else {
+ perf.min_limit_perf = freq_to_perf(perf, cpudata->nominal_freq, policy->min);
+ WRITE_ONCE(cpudata->min_limit_freq, policy->min);
+ }
+
WRITE_ONCE(cpudata->perf, perf);
}
@@ -791,16 +794,6 @@ static void amd_perf_ctl_reset(unsigned int cpu)
wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0);
}
-/*
- * Set amd-pstate preferred core enable can't be done directly from cpufreq callbacks
- * due to locking, so queue the work for later.
- */
-static void amd_pstste_sched_prefcore_workfn(struct work_struct *work)
-{
- sched_set_itmt_support();
-}
-static DECLARE_WORK(sched_prefcore_work, amd_pstste_sched_prefcore_workfn);
-
#define CPPC_MAX_PERF U8_MAX
static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata)
@@ -811,14 +804,8 @@ static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata)
cpudata->hw_prefcore = true;
- /*
- * The priorities can be set regardless of whether or not
- * sched_set_itmt_support(true) has been called and it is valid to
- * update them at any time after it has been called.
- */
+ /* Priorities must be initialized before ITMT support can be toggled on. */
sched_set_itmt_core_prio((int)READ_ONCE(cpudata->prefcore_ranking), cpudata->cpu);
-
- schedule_work(&sched_prefcore_work);
}
static void amd_pstate_update_limits(unsigned int cpu)
@@ -1193,6 +1180,9 @@ static ssize_t show_energy_performance_preference(
static void amd_pstate_driver_cleanup(void)
{
+ if (amd_pstate_prefcore)
+ sched_clear_itmt_support();
+
cppc_state = AMD_PSTATE_DISABLE;
current_pstate_driver = NULL;
}
@@ -1235,6 +1225,10 @@ static int amd_pstate_register_driver(int mode)
return ret;
}
+ /* Enable ITMT support once all CPUs have initialized their asym priorities. */
+ if (amd_pstate_prefcore)
+ sched_set_itmt_support();
+
return 0;
}
diff --git a/drivers/cpufreq/apple-soc-cpufreq.c b/drivers/cpufreq/apple-soc-cpufreq.c
index 4994c86..b1d29b7 100644
--- a/drivers/cpufreq/apple-soc-cpufreq.c
+++ b/drivers/cpufreq/apple-soc-cpufreq.c
@@ -134,11 +134,17 @@ static const struct of_device_id apple_soc_cpufreq_of_match[] __maybe_unused = {
static unsigned int apple_soc_cpufreq_get_rate(unsigned int cpu)
{
- struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
- struct apple_cpu_priv *priv = policy->driver_data;
+ struct cpufreq_policy *policy;
+ struct apple_cpu_priv *priv;
struct cpufreq_frequency_table *p;
unsigned int pstate;
+ policy = cpufreq_cpu_get_raw(cpu);
+ if (unlikely(!policy))
+ return 0;
+
+ priv = policy->driver_data;
+
if (priv->info->cur_pstate_mask) {
u32 reg = readl_relaxed(priv->reg_base + APPLE_DVFS_STATUS);
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index b3d74f9..cb93f00 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -747,7 +747,7 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
int ret;
if (!policy)
- return -ENODEV;
+ return 0;
cpu_data = policy->driver_data;
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 2aa0076..a010da0 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -175,6 +175,7 @@ static const struct of_device_id blocklist[] __initconst = {
{ .compatible = "qcom,sm8350", },
{ .compatible = "qcom,sm8450", },
{ .compatible = "qcom,sm8550", },
+ { .compatible = "qcom,sm8650", },
{ .compatible = "st,stih407", },
{ .compatible = "st,stih410", },
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 3841c9d..acf19b0 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -540,8 +540,6 @@ static unsigned int __resolve_freq(struct cpufreq_policy *policy,
{
unsigned int idx;
- target_freq = clamp_val(target_freq, policy->min, policy->max);
-
if (!policy->freq_table)
return target_freq;
@@ -565,7 +563,22 @@ static unsigned int __resolve_freq(struct cpufreq_policy *policy,
unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy,
unsigned int target_freq)
{
- return __resolve_freq(policy, target_freq, CPUFREQ_RELATION_LE);
+ unsigned int min = READ_ONCE(policy->min);
+ unsigned int max = READ_ONCE(policy->max);
+
+ /*
+ * If this function runs in parallel with cpufreq_set_policy(), it may
+ * read policy->min before the update and policy->max after the update
+ * or the other way around, so there is no ordering guarantee.
+ *
+ * Resolve this by always honoring the max (in case it comes from
+ * thermal throttling or similar).
+ */
+ if (unlikely(min > max))
+ min = max;
+
+ return __resolve_freq(policy, clamp_val(target_freq, min, max),
+ CPUFREQ_RELATION_LE);
}
EXPORT_SYMBOL_GPL(cpufreq_driver_resolve_freq);
@@ -2384,6 +2397,7 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
if (cpufreq_disabled())
return -ENODEV;
+ target_freq = clamp_val(target_freq, policy->min, policy->max);
target_freq = __resolve_freq(policy, target_freq, relation);
pr_debug("target for CPU %u: %u kHz, relation %u, requested %u kHz\n",
@@ -2708,11 +2722,15 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
* Resolve policy min/max to available frequencies. It ensures
* no frequency resolution will neither overshoot the requested maximum
* nor undershoot the requested minimum.
+ *
+ * Avoid storing intermediate values in policy->max or policy->min and
+ * compiler optimizations around them because they may be accessed
+ * concurrently by cpufreq_driver_resolve_freq() during the update.
*/
- policy->min = new_data.min;
- policy->max = new_data.max;
- policy->min = __resolve_freq(policy, policy->min, CPUFREQ_RELATION_L);
- policy->max = __resolve_freq(policy, policy->max, CPUFREQ_RELATION_H);
+ WRITE_ONCE(policy->max, __resolve_freq(policy, new_data.max, CPUFREQ_RELATION_H));
+ new_data.min = __resolve_freq(policy, new_data.min, CPUFREQ_RELATION_L);
+ WRITE_ONCE(policy->min, new_data.min > policy->max ? policy->max : new_data.min);
+
trace_cpu_frequency_limits(policy);
cpufreq_update_pressure(policy);
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 4aad79d..f41ed0b 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2209,7 +2209,7 @@ static int knl_get_turbo_pstate(int cpu)
static int hwp_get_cpu_scaling(int cpu)
{
if (hybrid_scaling_factor) {
- struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
u8 cpu_type = c->topo.intel_type;
/*
diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
index c310aee..944e899 100644
--- a/drivers/cpufreq/scmi-cpufreq.c
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -37,11 +37,17 @@ static struct cpufreq_driver scmi_cpufreq_driver;
static unsigned int scmi_cpufreq_get_rate(unsigned int cpu)
{
- struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
- struct scmi_data *priv = policy->driver_data;
+ struct cpufreq_policy *policy;
+ struct scmi_data *priv;
unsigned long rate;
int ret;
+ policy = cpufreq_cpu_get_raw(cpu);
+ if (unlikely(!policy))
+ return 0;
+
+ priv = policy->driver_data;
+
ret = perf_ops->freq_get(ph, priv->domain_id, &rate, false);
if (ret)
return 0;
diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c
index 17cda84..dcbb0ae 100644
--- a/drivers/cpufreq/scpi-cpufreq.c
+++ b/drivers/cpufreq/scpi-cpufreq.c
@@ -29,9 +29,16 @@ static struct scpi_ops *scpi_ops;
static unsigned int scpi_cpufreq_get_rate(unsigned int cpu)
{
- struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
- struct scpi_data *priv = policy->driver_data;
- unsigned long rate = clk_get_rate(priv->clk);
+ struct cpufreq_policy *policy;
+ struct scpi_data *priv;
+ unsigned long rate;
+
+ policy = cpufreq_cpu_get_raw(cpu);
+ if (unlikely(!policy))
+ return 0;
+
+ priv = policy->driver_data;
+ rate = clk_get_rate(priv->clk);
return rate / 1000;
}
diff --git a/drivers/cpufreq/sun50i-cpufreq-nvmem.c b/drivers/cpufreq/sun50i-cpufreq-nvmem.c
index 47d6840..744312a 100644
--- a/drivers/cpufreq/sun50i-cpufreq-nvmem.c
+++ b/drivers/cpufreq/sun50i-cpufreq-nvmem.c
@@ -194,7 +194,9 @@ static int sun50i_cpufreq_get_efuse(void)
struct nvmem_cell *speedbin_nvmem;
const struct of_device_id *match;
struct device *cpu_dev;
- u32 *speedbin;
+ void *speedbin_ptr;
+ u32 speedbin = 0;
+ size_t len;
int ret;
cpu_dev = get_cpu_device(0);
@@ -217,14 +219,18 @@ static int sun50i_cpufreq_get_efuse(void)
return dev_err_probe(cpu_dev, PTR_ERR(speedbin_nvmem),
"Could not get nvmem cell\n");
- speedbin = nvmem_cell_read(speedbin_nvmem, NULL);
+ speedbin_ptr = nvmem_cell_read(speedbin_nvmem, &len);
nvmem_cell_put(speedbin_nvmem);
- if (IS_ERR(speedbin))
- return PTR_ERR(speedbin);
+ if (IS_ERR(speedbin_ptr))
+ return PTR_ERR(speedbin_ptr);
- ret = opp_data->efuse_xlate(*speedbin);
+ if (len <= 4)
+ memcpy(&speedbin, speedbin_ptr, len);
+ speedbin = le32_to_cpu(speedbin);
- kfree(speedbin);
+ ret = opp_data->efuse_xlate(speedbin);
+
+ kfree(speedbin_ptr);
return ret;
};
diff --git a/drivers/crypto/atmel-sha204a.c b/drivers/crypto/atmel-sha204a.c
index 75bebec..0fcf4a3 100644
--- a/drivers/crypto/atmel-sha204a.c
+++ b/drivers/crypto/atmel-sha204a.c
@@ -163,6 +163,12 @@ static int atmel_sha204a_probe(struct i2c_client *client)
i2c_priv->hwrng.name = dev_name(&client->dev);
i2c_priv->hwrng.read = atmel_sha204a_rng_read;
+ /*
+ * According to review by Bill Cox [1], this HWRNG has very low entropy.
+ * [1] https://www.metzdowd.com/pipermail/cryptography/2014-December/023858.html
+ */
+ i2c_priv->hwrng.quality = 1;
+
ret = devm_hwrng_register(&client->dev, &i2c_priv->hwrng);
if (ret)
dev_warn(&client->dev, "failed to register RNG (%d)\n", ret);
diff --git a/drivers/crypto/caam/qi.c b/drivers/crypto/caam/qi.c
index 7701d00..b6e7c0b2 100644
--- a/drivers/crypto/caam/qi.c
+++ b/drivers/crypto/caam/qi.c
@@ -122,12 +122,12 @@ int caam_qi_enqueue(struct device *qidev, struct caam_drv_req *req)
qm_fd_addr_set64(&fd, addr);
do {
+ refcount_inc(&req->drv_ctx->refcnt);
ret = qman_enqueue(req->drv_ctx->req_fq, &fd);
- if (likely(!ret)) {
- refcount_inc(&req->drv_ctx->refcnt);
+ if (likely(!ret))
return 0;
- }
+ refcount_dec(&req->drv_ctx->refcnt);
if (ret != -EBUSY)
break;
num_retries++;
diff --git a/drivers/crypto/tegra/tegra-se-aes.c b/drivers/crypto/tegra/tegra-se-aes.c
index ca9d0cc..0e07d05 100644
--- a/drivers/crypto/tegra/tegra-se-aes.c
+++ b/drivers/crypto/tegra/tegra-se-aes.c
@@ -269,7 +269,7 @@ static int tegra_aes_do_one_req(struct crypto_engine *engine, void *areq)
unsigned int cmdlen, key1_id, key2_id;
int ret;
- rctx->iv = (u32 *)req->iv;
+ rctx->iv = (ctx->alg == SE_ALG_ECB) ? NULL : (u32 *)req->iv;
rctx->len = req->cryptlen;
key1_id = ctx->key1_id;
key2_id = ctx->key2_id;
@@ -498,9 +498,6 @@ static int tegra_aes_crypt(struct skcipher_request *req, bool encrypt)
if (!req->cryptlen)
return 0;
- if (ctx->alg == SE_ALG_ECB)
- req->iv = NULL;
-
rctx->encrypt = encrypt;
return crypto_transfer_skcipher_request_to_engine(ctx->se->engine, req);
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 1569929..17b692e 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -119,7 +119,7 @@ int cxl_port_get_switch_dport_bandwidth(struct cxl_port *port,
int cxl_ras_init(void);
void cxl_ras_exit(void);
-int cxl_gpf_port_setup(struct device *dport_dev, struct cxl_port *port);
+int cxl_gpf_port_setup(struct cxl_dport *dport);
int cxl_acpi_get_extended_linear_cache_size(struct resource *backing_res,
int nid, resource_size_t *size);
diff --git a/drivers/cxl/core/features.c b/drivers/cxl/core/features.c
index f4daefe..1498e23 100644
--- a/drivers/cxl/core/features.c
+++ b/drivers/cxl/core/features.c
@@ -528,13 +528,13 @@ static void *cxlctl_set_feature(struct cxl_features_state *cxlfs,
rc = cxl_set_feature(cxl_mbox, &feat_in->uuid,
feat_in->version, feat_in->feat_data,
data_size, flags, offset, &return_code);
+ *out_len = sizeof(*rpc_out);
if (rc) {
rpc_out->retval = return_code;
return no_free_ptr(rpc_out);
}
rpc_out->retval = CXL_MBOX_CMD_RC_SUCCESS;
- *out_len = sizeof(*rpc_out);
return no_free_ptr(rpc_out);
}
@@ -677,7 +677,7 @@ static void free_memdev_fwctl(void *_fwctl_dev)
fwctl_put(fwctl_dev);
}
-int devm_cxl_setup_fwctl(struct cxl_memdev *cxlmd)
+int devm_cxl_setup_fwctl(struct device *host, struct cxl_memdev *cxlmd)
{
struct cxl_dev_state *cxlds = cxlmd->cxlds;
struct cxl_features_state *cxlfs;
@@ -700,7 +700,7 @@ int devm_cxl_setup_fwctl(struct cxl_memdev *cxlmd)
if (rc)
return rc;
- return devm_add_action_or_reset(&cxlmd->dev, free_memdev_fwctl,
+ return devm_add_action_or_reset(host, free_memdev_fwctl,
no_free_ptr(fwctl_dev));
}
EXPORT_SYMBOL_NS_GPL(devm_cxl_setup_fwctl, "CXL");
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 96fecb7..3b80e9a7 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -1072,14 +1072,20 @@ int cxl_pci_get_bandwidth(struct pci_dev *pdev, struct access_coordinate *c)
#define GPF_TIMEOUT_BASE_MAX 2
#define GPF_TIMEOUT_SCALE_MAX 7 /* 10 seconds */
-u16 cxl_gpf_get_dvsec(struct device *dev, bool is_port)
+u16 cxl_gpf_get_dvsec(struct device *dev)
{
+ struct pci_dev *pdev;
+ bool is_port = true;
u16 dvsec;
if (!dev_is_pci(dev))
return 0;
- dvsec = pci_find_dvsec_capability(to_pci_dev(dev), PCI_VENDOR_ID_CXL,
+ pdev = to_pci_dev(dev);
+ if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ENDPOINT)
+ is_port = false;
+
+ dvsec = pci_find_dvsec_capability(pdev, PCI_VENDOR_ID_CXL,
is_port ? CXL_DVSEC_PORT_GPF : CXL_DVSEC_DEVICE_GPF);
if (!dvsec)
dev_warn(dev, "%s GPF DVSEC not present\n",
@@ -1128,26 +1134,24 @@ static int update_gpf_port_dvsec(struct pci_dev *pdev, int dvsec, int phase)
return rc;
}
-int cxl_gpf_port_setup(struct device *dport_dev, struct cxl_port *port)
+int cxl_gpf_port_setup(struct cxl_dport *dport)
{
- struct pci_dev *pdev;
-
- if (!port)
+ if (!dport)
return -EINVAL;
- if (!port->gpf_dvsec) {
+ if (!dport->gpf_dvsec) {
+ struct pci_dev *pdev;
int dvsec;
- dvsec = cxl_gpf_get_dvsec(dport_dev, true);
+ dvsec = cxl_gpf_get_dvsec(dport->dport_dev);
if (!dvsec)
return -EINVAL;
- port->gpf_dvsec = dvsec;
+ dport->gpf_dvsec = dvsec;
+ pdev = to_pci_dev(dport->dport_dev);
+ update_gpf_port_dvsec(pdev, dport->gpf_dvsec, 1);
+ update_gpf_port_dvsec(pdev, dport->gpf_dvsec, 2);
}
- pdev = to_pci_dev(dport_dev);
- update_gpf_port_dvsec(pdev, port->gpf_dvsec, 1);
- update_gpf_port_dvsec(pdev, port->gpf_dvsec, 2);
-
return 0;
}
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 0fd6646c..726bd4a 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -1678,7 +1678,7 @@ int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd)
if (rc && rc != -EBUSY)
return rc;
- cxl_gpf_port_setup(dport_dev, port);
+ cxl_gpf_port_setup(dport);
/* Any more ports to add between this one and the root? */
if (!dev_is_cxl_root_child(&port->dev))
diff --git a/drivers/cxl/core/regs.c b/drivers/cxl/core/regs.c
index 117c2e9..5ca7b0e 100644
--- a/drivers/cxl/core/regs.c
+++ b/drivers/cxl/core/regs.c
@@ -581,7 +581,6 @@ resource_size_t __rcrb_to_component(struct device *dev, struct cxl_rcrb_info *ri
resource_size_t rcrb = ri->base;
void __iomem *addr;
u32 bar0, bar1;
- u16 cmd;
u32 id;
if (which == CXL_RCRB_UPSTREAM)
@@ -603,7 +602,6 @@ resource_size_t __rcrb_to_component(struct device *dev, struct cxl_rcrb_info *ri
}
id = readl(addr + PCI_VENDOR_ID);
- cmd = readw(addr + PCI_COMMAND);
bar0 = readl(addr + PCI_BASE_ADDRESS_0);
bar1 = readl(addr + PCI_BASE_ADDRESS_1);
iounmap(addr);
@@ -618,8 +616,6 @@ resource_size_t __rcrb_to_component(struct device *dev, struct cxl_rcrb_info *ri
dev_err(dev, "Failed to access Downstream Port RCRB\n");
return CXL_RESOURCE_NONE;
}
- if (!(cmd & PCI_COMMAND_MEMORY))
- return CXL_RESOURCE_NONE;
/* The RCRB is a Memory Window, and the MEM_TYPE_1M bit is obsolete */
if (bar0 & (PCI_BASE_ADDRESS_MEM_TYPE_1M | PCI_BASE_ADDRESS_SPACE_IO))
return CXL_RESOURCE_NONE;
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index be8a7dc..a9ab46e 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -592,7 +592,6 @@ struct cxl_dax_region {
* @cdat: Cached CDAT data
* @cdat_available: Should a CDAT attribute be available in sysfs
* @pci_latency: Upstream latency in picoseconds
- * @gpf_dvsec: Cached GPF port DVSEC
*/
struct cxl_port {
struct device dev;
@@ -616,7 +615,6 @@ struct cxl_port {
} cdat;
bool cdat_available;
long pci_latency;
- int gpf_dvsec;
};
/**
@@ -664,6 +662,7 @@ struct cxl_rcrb_info {
* @regs: Dport parsed register blocks
* @coord: access coordinates (bandwidth and latency performance attributes)
* @link_latency: calculated PCIe downstream latency
+ * @gpf_dvsec: Cached GPF port DVSEC
*/
struct cxl_dport {
struct device *dport_dev;
@@ -675,6 +674,7 @@ struct cxl_dport {
struct cxl_regs regs;
struct access_coordinate coord[ACCESS_COORDINATE_MAX];
long link_latency;
+ int gpf_dvsec;
};
/**
@@ -910,6 +910,6 @@ bool cxl_endpoint_decoder_reset_detected(struct cxl_port *port);
#define __mock static
#endif
-u16 cxl_gpf_get_dvsec(struct device *dev, bool is_port);
+u16 cxl_gpf_get_dvsec(struct device *dev);
#endif /* __CXL_H__ */
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index 7b14a15..785aa2a 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -1018,7 +1018,7 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
if (rc)
return rc;
- rc = devm_cxl_setup_fwctl(cxlmd);
+ rc = devm_cxl_setup_fwctl(&pdev->dev, cxlmd);
if (rc)
dev_dbg(&pdev->dev, "No CXL FWCTL setup\n");
diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c
index d061fe3..e197883 100644
--- a/drivers/cxl/pmem.c
+++ b/drivers/cxl/pmem.c
@@ -108,7 +108,7 @@ static void cxl_nvdimm_arm_dirty_shutdown_tracking(struct cxl_nvdimm *cxl_nvd)
return;
}
- if (!cxl_gpf_get_dvsec(cxlds->dev, false))
+ if (!cxl_gpf_get_dvsec(cxlds->dev))
return;
if (cxl_get_dirty_count(mds, &count)) {
diff --git a/drivers/dma/amd/ptdma/ptdma-dmaengine.c b/drivers/dma/amd/ptdma/ptdma-dmaengine.c
index 715ac3a..8133966 100644
--- a/drivers/dma/amd/ptdma/ptdma-dmaengine.c
+++ b/drivers/dma/amd/ptdma/ptdma-dmaengine.c
@@ -342,6 +342,9 @@ static void pt_cmd_callback_work(void *data, int err)
struct pt_dma_chan *chan;
unsigned long flags;
+ if (!desc)
+ return;
+
dma_chan = desc->vd.tx.chan;
chan = to_pt_chan(dma_chan);
@@ -355,16 +358,14 @@ static void pt_cmd_callback_work(void *data, int err)
desc->status = DMA_ERROR;
spin_lock_irqsave(&chan->vc.lock, flags);
- if (desc) {
- if (desc->status != DMA_COMPLETE) {
- if (desc->status != DMA_ERROR)
- desc->status = DMA_COMPLETE;
+ if (desc->status != DMA_COMPLETE) {
+ if (desc->status != DMA_ERROR)
+ desc->status = DMA_COMPLETE;
- dma_cookie_complete(tx_desc);
- dma_descriptor_unmap(tx_desc);
- } else {
- tx_desc = NULL;
- }
+ dma_cookie_complete(tx_desc);
+ dma_descriptor_unmap(tx_desc);
+ } else {
+ tx_desc = NULL;
}
spin_unlock_irqrestore(&chan->vc.lock, flags);
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index d891dfc..91b2fbc 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -841,9 +841,9 @@ static int dmatest_func(void *data)
} else {
dma_async_issue_pending(chan);
- wait_event_timeout(thread->done_wait,
- done->done,
- msecs_to_jiffies(params->timeout));
+ wait_event_freezable_timeout(thread->done_wait,
+ done->done,
+ msecs_to_jiffies(params->timeout));
status = dma_async_is_tx_complete(chan, cookie, NULL,
NULL);
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index ff94ee8..a2fb2b8 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -222,7 +222,7 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp)
struct idxd_wq *wq;
struct device *dev, *fdev;
int rc = 0;
- struct iommu_sva *sva;
+ struct iommu_sva *sva = NULL;
unsigned int pasid;
struct idxd_cdev *idxd_cdev;
@@ -317,7 +317,7 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp)
if (device_user_pasid_enabled(idxd))
idxd_xa_pasid_remove(ctx);
failed_get_pasid:
- if (device_user_pasid_enabled(idxd))
+ if (device_user_pasid_enabled(idxd) && !IS_ERR_OR_NULL(sva))
iommu_sva_unbind_device(sva);
failed:
mutex_unlock(&wq->wq_lock);
@@ -407,6 +407,9 @@ static int idxd_cdev_mmap(struct file *filp, struct vm_area_struct *vma)
if (!idxd->user_submission_safe && !capable(CAP_SYS_RAWIO))
return -EPERM;
+ if (current->mm != ctx->mm)
+ return -EPERM;
+
rc = check_vma(wq, vma, __func__);
if (rc < 0)
return rc;
@@ -473,6 +476,9 @@ static ssize_t idxd_cdev_write(struct file *filp, const char __user *buf, size_t
ssize_t written = 0;
int i;
+ if (current->mm != ctx->mm)
+ return -EPERM;
+
for (i = 0; i < len/sizeof(struct dsa_hw_desc); i++) {
int rc = idxd_submit_user_descriptor(ctx, udesc + i);
@@ -493,6 +499,9 @@ static __poll_t idxd_cdev_poll(struct file *filp,
struct idxd_device *idxd = wq->idxd;
__poll_t out = 0;
+ if (current->mm != ctx->mm)
+ return -EPERM;
+
poll_wait(filp, &wq->err_queue, wait);
spin_lock(&idxd->dev_lock);
if (idxd->sw_err.valid)
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index b223a7a..b6255c0 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -1091,8 +1091,11 @@ static void udma_check_tx_completion(struct work_struct *work)
u32 residue_diff;
ktime_t time_diff;
unsigned long delay;
+ unsigned long flags;
while (1) {
+ spin_lock_irqsave(&uc->vc.lock, flags);
+
if (uc->desc) {
/* Get previous residue and time stamp */
residue_diff = uc->tx_drain.residue;
@@ -1127,6 +1130,8 @@ static void udma_check_tx_completion(struct work_struct *work)
break;
}
+ spin_unlock_irqrestore(&uc->vc.lock, flags);
+
usleep_range(ktime_to_us(delay),
ktime_to_us(delay) + 10);
continue;
@@ -1143,6 +1148,8 @@ static void udma_check_tx_completion(struct work_struct *work)
break;
}
+
+ spin_unlock_irqrestore(&uc->vc.lock, flags);
}
static irqreturn_t udma_ring_irq_handler(int irq, void *data)
@@ -4246,7 +4253,6 @@ static struct dma_chan *udma_of_xlate(struct of_phandle_args *dma_spec,
struct of_dma *ofdma)
{
struct udma_dev *ud = ofdma->of_dma_data;
- dma_cap_mask_t mask = ud->ddev.cap_mask;
struct udma_filter_param filter_param;
struct dma_chan *chan;
@@ -4278,7 +4284,7 @@ static struct dma_chan *udma_of_xlate(struct of_phandle_args *dma_spec,
}
}
- chan = __dma_request_channel(&mask, udma_dma_filter_fn, &filter_param,
+ chan = __dma_request_channel(&ud->ddev.cap_mask, udma_dma_filter_fn, &filter_param,
ofdma->of_node);
if (!chan) {
dev_err(ud->dev, "get channel fail in %s.\n", __func__);
diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index 1929528..fe55613 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -299,7 +299,8 @@ __ffa_partition_info_get(u32 uuid0, u32 uuid1, u32 uuid2, u32 uuid3,
import_uuid(&buf->uuid, (u8 *)&rx_buf->uuid);
}
- ffa_rx_release();
+ if (!(flags & PARTITION_INFO_GET_RETURN_COUNT_ONLY))
+ ffa_rx_release();
mutex_unlock(&drv_info->rx_lock);
diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c
index 7af0166..3a54740 100644
--- a/drivers/firmware/arm_scmi/bus.c
+++ b/drivers/firmware/arm_scmi/bus.c
@@ -255,6 +255,9 @@ static struct scmi_device *scmi_child_dev_find(struct device *parent,
if (!dev)
return NULL;
+ /* Drop the refcnt bumped implicitly by device_find_child */
+ put_device(dev);
+
return to_scmi_dev(dev);
}
diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c
index 1c75a4c..0390d5f 100644
--- a/drivers/firmware/arm_scmi/driver.c
+++ b/drivers/firmware/arm_scmi/driver.c
@@ -1248,7 +1248,8 @@ static void xfer_put(const struct scmi_protocol_handle *ph,
}
static bool scmi_xfer_done_no_timeout(struct scmi_chan_info *cinfo,
- struct scmi_xfer *xfer, ktime_t stop)
+ struct scmi_xfer *xfer, ktime_t stop,
+ bool *ooo)
{
struct scmi_info *info = handle_to_scmi_info(cinfo->handle);
@@ -1257,7 +1258,7 @@ static bool scmi_xfer_done_no_timeout(struct scmi_chan_info *cinfo,
* in case of out-of-order receptions of delayed responses
*/
return info->desc->ops->poll_done(cinfo, xfer) ||
- try_wait_for_completion(&xfer->done) ||
+ (*ooo = try_wait_for_completion(&xfer->done)) ||
ktime_after(ktime_get(), stop);
}
@@ -1274,15 +1275,17 @@ static int scmi_wait_for_reply(struct device *dev, const struct scmi_desc *desc,
* itself to support synchronous commands replies.
*/
if (!desc->sync_cmds_completed_on_ret) {
+ bool ooo = false;
+
/*
* Poll on xfer using transport provided .poll_done();
* assumes no completion interrupt was available.
*/
ktime_t stop = ktime_add_ms(ktime_get(), timeout_ms);
- spin_until_cond(scmi_xfer_done_no_timeout(cinfo,
- xfer, stop));
- if (ktime_after(ktime_get(), stop)) {
+ spin_until_cond(scmi_xfer_done_no_timeout(cinfo, xfer,
+ stop, &ooo));
+ if (!ooo && !info->desc->ops->poll_done(cinfo, xfer)) {
dev_err(dev,
"timed out in resp(caller: %pS) - polling\n",
(void *)_RET_IP_);
diff --git a/drivers/firmware/cirrus/Kconfig b/drivers/firmware/cirrus/Kconfig
index 0a88309..e3c2e38b 100644
--- a/drivers/firmware/cirrus/Kconfig
+++ b/drivers/firmware/cirrus/Kconfig
@@ -6,14 +6,11 @@
config FW_CS_DSP_KUNIT_TEST_UTILS
tristate
- depends on KUNIT && REGMAP
- select FW_CS_DSP
config FW_CS_DSP_KUNIT_TEST
tristate "KUnit tests for Cirrus Logic cs_dsp" if !KUNIT_ALL_TESTS
- depends on KUNIT && REGMAP
+ depends on KUNIT && REGMAP && FW_CS_DSP
default KUNIT_ALL_TESTS
- select FW_CS_DSP
select FW_CS_DSP_KUNIT_TEST_UTILS
help
This builds KUnit tests for cs_dsp.
diff --git a/drivers/firmware/cirrus/test/cs_dsp_mock_mem_maps.c b/drivers/firmware/cirrus/test/cs_dsp_mock_mem_maps.c
index 161272e..73412bc 100644
--- a/drivers/firmware/cirrus/test/cs_dsp_mock_mem_maps.c
+++ b/drivers/firmware/cirrus/test/cs_dsp_mock_mem_maps.c
@@ -462,36 +462,6 @@ unsigned int cs_dsp_mock_xm_header_get_alg_base_in_words(struct cs_dsp_test *pri
EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_xm_header_get_alg_base_in_words, "FW_CS_DSP_KUNIT_TEST_UTILS");
/**
- * cs_dsp_mock_xm_header_get_fw_version_from_regmap() - Firmware version.
- *
- * @priv: Pointer to struct cs_dsp_test.
- *
- * Return: Firmware version word value.
- */
-unsigned int cs_dsp_mock_xm_header_get_fw_version_from_regmap(struct cs_dsp_test *priv)
-{
- unsigned int xm = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_XM);
- union {
- struct wmfw_id_hdr adsp2;
- struct wmfw_v3_id_hdr halo;
- } hdr;
-
- switch (priv->dsp->type) {
- case WMFW_ADSP2:
- regmap_raw_read(priv->dsp->regmap, xm, &hdr.adsp2, sizeof(hdr.adsp2));
- return be32_to_cpu(hdr.adsp2.ver);
- case WMFW_HALO:
- regmap_raw_read(priv->dsp->regmap, xm, &hdr.halo, sizeof(hdr.halo));
- return be32_to_cpu(hdr.halo.ver);
- default:
- KUNIT_FAIL(priv->test, NULL);
- return 0;
- }
-}
-EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_xm_header_get_fw_version_from_regmap,
- "FW_CS_DSP_KUNIT_TEST_UTILS");
-
-/**
* cs_dsp_mock_xm_header_get_fw_version() - Firmware version.
*
* @header: Pointer to struct cs_dsp_mock_xm_header.
diff --git a/drivers/firmware/cirrus/test/cs_dsp_test_bin.c b/drivers/firmware/cirrus/test/cs_dsp_test_bin.c
index 1e161bb..163b7fa 100644
--- a/drivers/firmware/cirrus/test/cs_dsp_test_bin.c
+++ b/drivers/firmware/cirrus/test/cs_dsp_test_bin.c
@@ -2198,7 +2198,7 @@ static int cs_dsp_bin_test_common_init(struct kunit *test, struct cs_dsp *dsp)
priv->local->bin_builder =
cs_dsp_mock_bin_init(priv, 1,
- cs_dsp_mock_xm_header_get_fw_version_from_regmap(priv));
+ cs_dsp_mock_xm_header_get_fw_version(xm_hdr));
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, priv->local->bin_builder);
/* We must provide a dummy wmfw to load */
diff --git a/drivers/firmware/cirrus/test/cs_dsp_test_bin_error.c b/drivers/firmware/cirrus/test/cs_dsp_test_bin_error.c
index 8748874f..a7ec956 100644
--- a/drivers/firmware/cirrus/test/cs_dsp_test_bin_error.c
+++ b/drivers/firmware/cirrus/test/cs_dsp_test_bin_error.c
@@ -451,7 +451,7 @@ static int cs_dsp_bin_err_test_common_init(struct kunit *test, struct cs_dsp *ds
local->bin_builder =
cs_dsp_mock_bin_init(priv, 1,
- cs_dsp_mock_xm_header_get_fw_version_from_regmap(priv));
+ cs_dsp_mock_xm_header_get_fw_version(local->xm_header));
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, local->bin_builder);
/* Init cs_dsp */
diff --git a/drivers/firmware/samsung/exynos-acpm.c b/drivers/firmware/samsung/exynos-acpm.c
index a85b2db..15e991b 100644
--- a/drivers/firmware/samsung/exynos-acpm.c
+++ b/drivers/firmware/samsung/exynos-acpm.c
@@ -185,6 +185,29 @@ struct acpm_match_data {
#define handle_to_acpm_info(h) container_of(h, struct acpm_info, handle)
/**
+ * acpm_get_saved_rx() - get the response if it was already saved.
+ * @achan: ACPM channel info.
+ * @xfer: reference to the transfer to get response for.
+ * @tx_seqnum: xfer TX sequence number.
+ */
+static void acpm_get_saved_rx(struct acpm_chan *achan,
+ const struct acpm_xfer *xfer, u32 tx_seqnum)
+{
+ const struct acpm_rx_data *rx_data = &achan->rx_data[tx_seqnum - 1];
+ u32 rx_seqnum;
+
+ if (!rx_data->response)
+ return;
+
+ rx_seqnum = FIELD_GET(ACPM_PROTOCOL_SEQNUM, rx_data->cmd[0]);
+
+ if (rx_seqnum == tx_seqnum) {
+ memcpy(xfer->rxd, rx_data->cmd, xfer->rxlen);
+ clear_bit(rx_seqnum - 1, achan->bitmap_seqnum);
+ }
+}
+
+/**
* acpm_get_rx() - get response from RX queue.
* @achan: ACPM channel info.
* @xfer: reference to the transfer to get response for.
@@ -204,15 +227,16 @@ static int acpm_get_rx(struct acpm_chan *achan, const struct acpm_xfer *xfer)
rx_front = readl(achan->rx.front);
i = readl(achan->rx.rear);
- /* Bail out if RX is empty. */
- if (i == rx_front)
+ tx_seqnum = FIELD_GET(ACPM_PROTOCOL_SEQNUM, xfer->txd[0]);
+
+ if (i == rx_front) {
+ acpm_get_saved_rx(achan, xfer, tx_seqnum);
return 0;
+ }
base = achan->rx.base;
mlen = achan->mlen;
- tx_seqnum = FIELD_GET(ACPM_PROTOCOL_SEQNUM, xfer->txd[0]);
-
/* Drain RX queue. */
do {
/* Read RX seqnum. */
@@ -259,16 +283,8 @@ static int acpm_get_rx(struct acpm_chan *achan, const struct acpm_xfer *xfer)
* If the response was not in this iteration of the queue, check if the
* RX data was previously saved.
*/
- rx_data = &achan->rx_data[tx_seqnum - 1];
- if (!rx_set && rx_data->response) {
- rx_seqnum = FIELD_GET(ACPM_PROTOCOL_SEQNUM,
- rx_data->cmd[0]);
-
- if (rx_seqnum == tx_seqnum) {
- memcpy(xfer->rxd, rx_data->cmd, xfer->rxlen);
- clear_bit(rx_seqnum - 1, achan->bitmap_seqnum);
- }
- }
+ if (!rx_set)
+ acpm_get_saved_rx(achan, xfer, tx_seqnum);
return 0;
}
diff --git a/drivers/firmware/smccc/kvm_guest.c b/drivers/firmware/smccc/kvm_guest.c
index 5767aed..a123c05 100644
--- a/drivers/firmware/smccc/kvm_guest.c
+++ b/drivers/firmware/smccc/kvm_guest.c
@@ -95,7 +95,7 @@ void __init kvm_arm_target_impl_cpu_init(void)
for (i = 0; i < max_cpus; i++) {
arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_KVM_DISCOVER_IMPL_CPUS_FUNC_ID,
- i, &res);
+ i, 0, 0, &res);
if (res.a0 != SMCCC_RET_SUCCESS) {
pr_warn("Discovering target implementation CPUs failed\n");
goto mem_free;
@@ -103,7 +103,7 @@ void __init kvm_arm_target_impl_cpu_init(void)
target[i].midr = res.a1;
target[i].revidr = res.a2;
target[i].aidr = res.a3;
- };
+ }
if (!cpu_errata_set_target_impl(max_cpus, target)) {
pr_warn("Failed to set target implementation CPUs\n");
diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c
index 3c52cb7..e3f990d 100644
--- a/drivers/firmware/stratix10-svc.c
+++ b/drivers/firmware/stratix10-svc.c
@@ -1224,22 +1224,28 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev)
if (!svc->intel_svc_fcs) {
dev_err(dev, "failed to allocate %s device\n", INTEL_FCS);
ret = -ENOMEM;
- goto err_unregister_dev;
+ goto err_unregister_rsu_dev;
}
ret = platform_device_add(svc->intel_svc_fcs);
if (ret) {
platform_device_put(svc->intel_svc_fcs);
- goto err_unregister_dev;
+ goto err_unregister_rsu_dev;
}
+ ret = of_platform_default_populate(dev_of_node(dev), NULL, dev);
+ if (ret)
+ goto err_unregister_fcs_dev;
+
dev_set_drvdata(dev, svc);
pr_info("Intel Service Layer Driver Initialized\n");
return 0;
-err_unregister_dev:
+err_unregister_fcs_dev:
+ platform_device_unregister(svc->intel_svc_fcs);
+err_unregister_rsu_dev:
platform_device_unregister(svc->stratix10_svc_rsu);
err_free_kfifo:
kfifo_free(&controller->svc_fifo);
@@ -1253,6 +1259,8 @@ static void stratix10_svc_drv_remove(struct platform_device *pdev)
struct stratix10_svc *svc = dev_get_drvdata(&pdev->dev);
struct stratix10_svc_controller *ctrl = platform_get_drvdata(pdev);
+ of_platform_depopulate(ctrl->dev);
+
platform_device_unregister(svc->intel_svc_fcs);
platform_device_unregister(svc->stratix10_svc_rsu);
diff --git a/drivers/fpga/tests/fpga-bridge-test.c b/drivers/fpga/tests/fpga-bridge-test.c
index b9ab298..124ba40 100644
--- a/drivers/fpga/tests/fpga-bridge-test.c
+++ b/drivers/fpga/tests/fpga-bridge-test.c
@@ -170,4 +170,5 @@ static struct kunit_suite fpga_bridge_suite = {
kunit_test_suite(fpga_bridge_suite);
+MODULE_DESCRIPTION("KUnit test for the FPGA Bridge");
MODULE_LICENSE("GPL");
diff --git a/drivers/fpga/tests/fpga-mgr-test.c b/drivers/fpga/tests/fpga-mgr-test.c
index 9cb37ae..8748bab 100644
--- a/drivers/fpga/tests/fpga-mgr-test.c
+++ b/drivers/fpga/tests/fpga-mgr-test.c
@@ -330,4 +330,5 @@ static struct kunit_suite fpga_mgr_suite = {
kunit_test_suite(fpga_mgr_suite);
+MODULE_DESCRIPTION("KUnit test for the FPGA Manager");
MODULE_LICENSE("GPL");
diff --git a/drivers/fpga/tests/fpga-region-test.c b/drivers/fpga/tests/fpga-region-test.c
index 6a108ca..020ceac48 100644
--- a/drivers/fpga/tests/fpga-region-test.c
+++ b/drivers/fpga/tests/fpga-region-test.c
@@ -214,4 +214,5 @@ static struct kunit_suite fpga_region_suite = {
kunit_test_suite(fpga_region_suite);
+MODULE_DESCRIPTION("KUnit test for the FPGA Region");
MODULE_LICENSE("GPL");
diff --git a/drivers/fwctl/main.c b/drivers/fwctl/main.c
index cb1ac9c..bc63785 100644
--- a/drivers/fwctl/main.c
+++ b/drivers/fwctl/main.c
@@ -105,7 +105,7 @@ static int fwctl_cmd_rpc(struct fwctl_ucmd *ucmd)
if (!test_and_set_bit(0, &fwctl_tainted)) {
dev_warn(
&fwctl->dev,
- "%s(%d): has requested full access to the physical device device",
+ "%s(%d): has requested full access to the physical device",
current->comm, task_pid_nr(current));
add_taint(TAINT_FWCTL, LOCKDEP_STILL_OK);
}
diff --git a/drivers/fwctl/pds/main.c b/drivers/fwctl/pds/main.c
index 284c416..9b9d1f6 100644
--- a/drivers/fwctl/pds/main.c
+++ b/drivers/fwctl/pds/main.c
@@ -105,12 +105,14 @@ static int pdsfc_identify(struct pdsfc_dev *pdsfc)
static void pdsfc_free_endpoints(struct pdsfc_dev *pdsfc)
{
struct device *dev = &pdsfc->fwctl.dev;
+ u32 num_endpoints;
int i;
if (!pdsfc->endpoints)
return;
- for (i = 0; pdsfc->endpoint_info && i < pdsfc->endpoints->num_entries; i++)
+ num_endpoints = le32_to_cpu(pdsfc->endpoints->num_entries);
+ for (i = 0; pdsfc->endpoint_info && i < num_endpoints; i++)
mutex_destroy(&pdsfc->endpoint_info[i].lock);
vfree(pdsfc->endpoint_info);
pdsfc->endpoint_info = NULL;
@@ -199,7 +201,7 @@ static int pdsfc_init_endpoints(struct pdsfc_dev *pdsfc)
ep_entry = (struct pds_fwctl_query_data_endpoint *)pdsfc->endpoints->entries;
for (i = 0; i < num_endpoints; i++) {
mutex_init(&pdsfc->endpoint_info[i].lock);
- pdsfc->endpoint_info[i].endpoint = ep_entry[i].id;
+ pdsfc->endpoint_info[i].endpoint = le32_to_cpu(ep_entry[i].id);
}
return 0;
@@ -214,6 +216,7 @@ static struct pds_fwctl_query_data *pdsfc_get_operations(struct pdsfc_dev *pdsfc
struct pds_fwctl_query_data *data;
union pds_core_adminq_cmd cmd;
dma_addr_t data_pa;
+ u32 num_entries;
int err;
int i;
@@ -246,8 +249,9 @@ static struct pds_fwctl_query_data *pdsfc_get_operations(struct pdsfc_dev *pdsfc
*pa = data_pa;
entries = (struct pds_fwctl_query_data_operation *)data->entries;
- dev_dbg(dev, "num_entries %d\n", data->num_entries);
- for (i = 0; i < data->num_entries; i++) {
+ num_entries = le32_to_cpu(data->num_entries);
+ dev_dbg(dev, "num_entries %d\n", num_entries);
+ for (i = 0; i < num_entries; i++) {
/* Translate FW command attribute to fwctl scope */
switch (entries[i].scope) {
@@ -267,7 +271,7 @@ static struct pds_fwctl_query_data *pdsfc_get_operations(struct pdsfc_dev *pdsfc
break;
}
dev_dbg(dev, "endpoint %d operation: id %x scope %d\n",
- ep, entries[i].id, entries[i].scope);
+ ep, le32_to_cpu(entries[i].id), entries[i].scope);
}
return data;
@@ -280,24 +284,26 @@ static int pdsfc_validate_rpc(struct pdsfc_dev *pdsfc,
struct pds_fwctl_query_data_operation *op_entry;
struct pdsfc_rpc_endpoint_info *ep_info = NULL;
struct device *dev = &pdsfc->fwctl.dev;
+ u32 num_entries;
int i;
/* validate rpc in_len & out_len based
* on ident.max_req_sz & max_resp_sz
*/
- if (rpc->in.len > pdsfc->ident.max_req_sz) {
+ if (rpc->in.len > le32_to_cpu(pdsfc->ident.max_req_sz)) {
dev_dbg(dev, "Invalid request size %u, max %u\n",
- rpc->in.len, pdsfc->ident.max_req_sz);
+ rpc->in.len, le32_to_cpu(pdsfc->ident.max_req_sz));
return -EINVAL;
}
- if (rpc->out.len > pdsfc->ident.max_resp_sz) {
+ if (rpc->out.len > le32_to_cpu(pdsfc->ident.max_resp_sz)) {
dev_dbg(dev, "Invalid response size %u, max %u\n",
- rpc->out.len, pdsfc->ident.max_resp_sz);
+ rpc->out.len, le32_to_cpu(pdsfc->ident.max_resp_sz));
return -EINVAL;
}
- for (i = 0; i < pdsfc->endpoints->num_entries; i++) {
+ num_entries = le32_to_cpu(pdsfc->endpoints->num_entries);
+ for (i = 0; i < num_entries; i++) {
if (pdsfc->endpoint_info[i].endpoint == rpc->in.ep) {
ep_info = &pdsfc->endpoint_info[i];
break;
@@ -326,8 +332,9 @@ static int pdsfc_validate_rpc(struct pdsfc_dev *pdsfc,
/* reject unsupported and/or out of scope commands */
op_entry = (struct pds_fwctl_query_data_operation *)ep_info->operations->entries;
- for (i = 0; i < ep_info->operations->num_entries; i++) {
- if (PDS_FWCTL_RPC_OPCODE_CMP(rpc->in.op, op_entry[i].id)) {
+ num_entries = le32_to_cpu(ep_info->operations->num_entries);
+ for (i = 0; i < num_entries; i++) {
+ if (PDS_FWCTL_RPC_OPCODE_CMP(rpc->in.op, le32_to_cpu(op_entry[i].id))) {
if (scope < op_entry[i].scope)
return -EPERM;
return 0;
@@ -402,7 +409,7 @@ static void *pdsfc_fw_rpc(struct fwctl_uctx *uctx, enum fwctl_rpc_scope scope,
cmd = (union pds_core_adminq_cmd) {
.fwctl_rpc = {
.opcode = PDS_FWCTL_CMD_RPC,
- .flags = PDS_FWCTL_RPC_IND_REQ | PDS_FWCTL_RPC_IND_RESP,
+ .flags = cpu_to_le16(PDS_FWCTL_RPC_IND_REQ | PDS_FWCTL_RPC_IND_RESP),
.ep = cpu_to_le32(rpc->in.ep),
.op = cpu_to_le32(rpc->in.op),
.req_pa = cpu_to_le64(in_payload_dma_addr),
diff --git a/drivers/gpio/TODO b/drivers/gpio/TODO
index b5f0a7a..4b70cba 100644
--- a/drivers/gpio/TODO
+++ b/drivers/gpio/TODO
@@ -186,3 +186,37 @@
Encourage users to switch to using them and eventually remove the existing
global export/unexport attribues.
+
+-------------------------------------------------------------------------------
+
+Remove GPIOD_FLAGS_BIT_NONEXCLUSIVE
+
+GPIOs in the linux kernel are meant to be an exclusive resource. This means
+that the GPIO descriptors (the software representation of the hardware concept)
+are not reference counted and - in general - only one user at a time can
+request a GPIO line and control its settings. The consumer API is designed
+around full control of the line's state as evidenced by the fact that, for
+instance, gpiod_set_value() does indeed drive the line as requested, instead
+of bumping an enable counter of some sort.
+
+A problematic use-case for GPIOs is when two consumers want to use the same
+descriptor independently. An example of such a user is the regulator subsystem
+which may instantiate several struct regulator_dev instances containing
+a struct device but using the same enable GPIO line.
+
+A workaround was introduced in the form of the GPIOD_FLAGS_BIT_NONEXCLUSIVE
+flag but its implementation is problematic: it does not provide any
+synchronization of usage nor did it introduce any enable count meaning the
+non-exclusive users of the same descriptor will in fact "fight" for the
+control over it. This flag should be removed and replaced with a better
+solution, possibly based on the new power sequencing subsystem.
+
+-------------------------------------------------------------------------------
+
+Remove devm_gpiod_unhinge()
+
+devm_gpiod_unhinge() is provided as a way to transfer the ownership of managed
+enable GPIOs to the regulator core. Rather than doing that however, we should
+make it possible for the regulator subsystem to deal with GPIO resources the
+lifetime of which it doesn't control as logically, a GPIO obtained by a caller
+should also be freed by it.
diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c
index 0cd4c36..5415175 100644
--- a/drivers/gpio/gpio-mpc8xxx.c
+++ b/drivers/gpio/gpio-mpc8xxx.c
@@ -410,7 +410,9 @@ static int mpc8xxx_probe(struct platform_device *pdev)
goto err;
}
- device_init_wakeup(dev, true);
+ ret = devm_device_init_wakeup(dev);
+ if (ret)
+ return dev_err_probe(dev, ret, "Failed to init wakeup\n");
return 0;
err:
diff --git a/drivers/gpio/gpio-tegra186.c b/drivers/gpio/gpio-tegra186.c
index 6895b65..d27bfac 100644
--- a/drivers/gpio/gpio-tegra186.c
+++ b/drivers/gpio/gpio-tegra186.c
@@ -823,6 +823,7 @@ static int tegra186_gpio_probe(struct platform_device *pdev)
struct gpio_irq_chip *irq;
struct tegra_gpio *gpio;
struct device_node *np;
+ struct resource *res;
char **names;
int err;
@@ -842,19 +843,19 @@ static int tegra186_gpio_probe(struct platform_device *pdev)
gpio->num_banks++;
/* get register apertures */
- gpio->secure = devm_platform_ioremap_resource_byname(pdev, "security");
- if (IS_ERR(gpio->secure)) {
- gpio->secure = devm_platform_ioremap_resource(pdev, 0);
- if (IS_ERR(gpio->secure))
- return PTR_ERR(gpio->secure);
- }
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "security");
+ if (!res)
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ gpio->secure = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(gpio->secure))
+ return PTR_ERR(gpio->secure);
- gpio->base = devm_platform_ioremap_resource_byname(pdev, "gpio");
- if (IS_ERR(gpio->base)) {
- gpio->base = devm_platform_ioremap_resource(pdev, 1);
- if (IS_ERR(gpio->base))
- return PTR_ERR(gpio->base);
- }
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "gpio");
+ if (!res)
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+ gpio->base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(gpio->base))
+ return PTR_ERR(gpio->base);
err = platform_irq_count(pdev);
if (err < 0)
diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c
index be81fa2..3dae63f 100644
--- a/drivers/gpio/gpio-zynq.c
+++ b/drivers/gpio/gpio-zynq.c
@@ -1011,6 +1011,7 @@ static void zynq_gpio_remove(struct platform_device *pdev)
ret = pm_runtime_get_sync(&pdev->dev);
if (ret < 0)
dev_warn(&pdev->dev, "pm_runtime_get_sync() Failed\n");
+ device_init_wakeup(&pdev->dev, 0);
gpiochip_remove(&gpio->chip);
device_set_wakeup_capable(&pdev->dev, 0);
pm_runtime_disable(&pdev->dev);
diff --git a/drivers/gpio/gpiolib-devres.c b/drivers/gpio/gpiolib-devres.c
index 08205f3..120d1ec 100644
--- a/drivers/gpio/gpiolib-devres.c
+++ b/drivers/gpio/gpiolib-devres.c
@@ -317,11 +317,15 @@ EXPORT_SYMBOL_GPL(devm_gpiod_put);
* @dev: GPIO consumer
* @desc: GPIO descriptor to remove resource management from
*
+ * *DEPRECATED*
+ * This function should not be used. It's been provided as a workaround for
+ * resource ownership issues in the regulator framework and should be replaced
+ * with a better solution.
+ *
* Remove resource management from a GPIO descriptor. This is needed when
* you want to hand over lifecycle management of a descriptor to another
* mechanism.
*/
-
void devm_gpiod_unhinge(struct device *dev, struct gpio_desc *desc)
{
int ret;
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index eb667f8..65f6a71 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -193,6 +193,8 @@ static void of_gpio_try_fixup_polarity(const struct device_node *np,
*/
{ "himax,hx8357", "gpios-reset", false },
{ "himax,hx8369", "gpios-reset", false },
+#endif
+#if IS_ENABLED(CONFIG_MTD_NAND_JZ4780)
/*
* The rb-gpios semantics was undocumented and qi,lb60 (along with
* the ingenic driver) got it wrong. The active state encodes the
@@ -266,6 +268,9 @@ static void of_gpio_set_polarity_by_property(const struct device_node *np,
{ "fsl,imx8qm-fec", "phy-reset-gpios", "phy-reset-active-high" },
{ "fsl,s32v234-fec", "phy-reset-gpios", "phy-reset-active-high" },
#endif
+#if IS_ENABLED(CONFIG_MMC_ATMELMCI)
+ { "atmel,hsmci", "cd-gpios", "cd-inverted" },
+#endif
#if IS_ENABLED(CONFIG_PCI_IMX6)
{ "fsl,imx6q-pcie", "reset-gpio", "reset-gpio-active-high" },
{ "fsl,imx6sx-pcie", "reset-gpio", "reset-gpio-active-high" },
@@ -292,9 +297,6 @@ static void of_gpio_set_polarity_by_property(const struct device_node *np,
{ "regulator-gpio", "enable-gpio", "enable-active-high" },
{ "regulator-gpio", "enable-gpios", "enable-active-high" },
#endif
-#if IS_ENABLED(CONFIG_MMC_ATMELMCI)
- { "atmel,hsmci", "cd-gpios", "cd-inverted" },
-#endif
};
unsigned int i;
bool active_high;
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index b8197502..cd4fecb 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -2879,7 +2879,7 @@ static int gpiod_direction_output_raw_commit(struct gpio_desc *desc, int value)
* output-only, but if there is then not even a .set() operation it
* is pretty tricky to drive the output line.
*/
- if (!guard.gc->set && !guard.gc->direction_output) {
+ if (!guard.gc->set && !guard.gc->set_rv && !guard.gc->direction_output) {
gpiod_warn(desc,
"%s: missing set() and direction_output() operations\n",
__func__);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 6d83ccf..ef6e782 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -353,7 +353,6 @@ enum amdgpu_kiq_irq {
AMDGPU_CP_KIQ_IRQ_DRIVER0 = 0,
AMDGPU_CP_KIQ_IRQ_LAST
};
-#define SRIOV_USEC_TIMEOUT 1200000 /* wait 12 * 100ms for SRIOV */
#define MAX_KIQ_REG_WAIT 5000 /* in usecs, 5ms */
#define MAX_KIQ_REG_BAILOUT_INTERVAL 5 /* in msecs, 5ms */
#define MAX_KIQ_REG_TRY 1000
@@ -1124,6 +1123,7 @@ struct amdgpu_device {
bool in_s3;
bool in_s4;
bool in_s0ix;
+ suspend_state_t last_suspend_state;
enum pp_mp1_state mp1_state;
struct amdgpu_doorbell_index doorbell_index;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index a30111d..7f354cd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3510,6 +3510,7 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
amdgpu_device_mem_scratch_fini(adev);
amdgpu_ib_pool_fini(adev);
amdgpu_seq64_fini(adev);
+ amdgpu_doorbell_fini(adev);
}
if (adev->ip_blocks[i].version->funcs->sw_fini) {
r = adev->ip_blocks[i].version->funcs->sw_fini(&adev->ip_blocks[i]);
@@ -3643,6 +3644,13 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
adev, adev->ip_blocks[i].version->type))
continue;
+ /* Since we skip suspend for S0i3, we need to cancel the delayed
+ * idle work here as the suspend callback never gets called.
+ */
+ if (adev->in_s0ix &&
+ adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX &&
+ amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(10, 0, 0))
+ cancel_delayed_work_sync(&adev->gfx.idle_work);
/* skip suspend of gfx/mes and psp for S0ix
* gfx is in gfxoff state, so on resume it will exit gfxoff just
* like at runtime. PSP is also part of the always on hardware
@@ -4851,7 +4859,6 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev)
iounmap(adev->rmmio);
adev->rmmio = NULL;
- amdgpu_doorbell_fini(adev);
drm_dev_exit(idx);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index dc2713e..9e738fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -120,6 +120,8 @@ MODULE_FIRMWARE("amdgpu/vega20_ip_discovery.bin");
MODULE_FIRMWARE("amdgpu/raven_ip_discovery.bin");
MODULE_FIRMWARE("amdgpu/raven2_ip_discovery.bin");
MODULE_FIRMWARE("amdgpu/picasso_ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/arcturus_ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/aldebaran_ip_discovery.bin");
#define mmIP_DISCOVERY_VERSION 0x16A00
#define mmRCC_CONFIG_MEMSIZE 0xde3
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index 9f627ca..e6913fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -43,6 +43,29 @@
#include <linux/dma-fence-array.h>
#include <linux/pci-p2pdma.h>
+static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops;
+
+/**
+ * dma_buf_attach_adev - Helper to get adev of an attachment
+ *
+ * @attach: attachment
+ *
+ * Returns:
+ * A struct amdgpu_device * if the attaching device is an amdgpu device or
+ * partition, NULL otherwise.
+ */
+static struct amdgpu_device *dma_buf_attach_adev(struct dma_buf_attachment *attach)
+{
+ if (attach->importer_ops == &amdgpu_dma_buf_attach_ops) {
+ struct drm_gem_object *obj = attach->importer_priv;
+ struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+
+ return amdgpu_ttm_adev(bo->tbo.bdev);
+ }
+
+ return NULL;
+}
+
/**
* amdgpu_dma_buf_attach - &dma_buf_ops.attach implementation
*
@@ -54,11 +77,13 @@
static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
struct dma_buf_attachment *attach)
{
+ struct amdgpu_device *attach_adev = dma_buf_attach_adev(attach);
struct drm_gem_object *obj = dmabuf->priv;
struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
- if (pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0)
+ if (!amdgpu_dmabuf_is_xgmi_accessible(attach_adev, bo) &&
+ pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0)
attach->peer2peer = false;
amdgpu_vm_bo_update_shared(bo);
@@ -75,11 +100,35 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
*/
static int amdgpu_dma_buf_pin(struct dma_buf_attachment *attach)
{
- struct drm_gem_object *obj = attach->dmabuf->priv;
- struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+ struct dma_buf *dmabuf = attach->dmabuf;
+ struct amdgpu_bo *bo = gem_to_amdgpu_bo(dmabuf->priv);
+ u32 domains = bo->allowed_domains;
- /* pin buffer into GTT */
- return amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
+ dma_resv_assert_held(dmabuf->resv);
+
+ /* Try pinning into VRAM to allow P2P with RDMA NICs without ODP
+ * support if all attachments can do P2P. If any attachment can't do
+ * P2P just pin into GTT instead.
+ *
+ * To avoid with conflicting pinnings between GPUs and RDMA when move
+ * notifiers are disabled, only allow pinning in VRAM when move
+ * notiers are enabled.
+ */
+ if (!IS_ENABLED(CONFIG_DMABUF_MOVE_NOTIFY)) {
+ domains &= ~AMDGPU_GEM_DOMAIN_VRAM;
+ } else {
+ list_for_each_entry(attach, &dmabuf->attachments, node)
+ if (!attach->peer2peer)
+ domains &= ~AMDGPU_GEM_DOMAIN_VRAM;
+ }
+
+ if (domains & AMDGPU_GEM_DOMAIN_VRAM)
+ bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+
+ if (WARN_ON(!domains))
+ return -EINVAL;
+
+ return amdgpu_bo_pin(bo, domains);
}
/**
@@ -134,9 +183,6 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach,
r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
if (r)
return ERR_PTR(r);
-
- } else if (bo->tbo.resource->mem_type != TTM_PL_TT) {
- return ERR_PTR(-EBUSY);
}
switch (bo->tbo.resource->mem_type) {
@@ -184,7 +230,7 @@ static void amdgpu_dma_buf_unmap(struct dma_buf_attachment *attach,
struct sg_table *sgt,
enum dma_data_direction dir)
{
- if (sgt->sgl->page_link) {
+ if (sg_page(sgt->sgl)) {
dma_unmap_sgtable(attach->dev, sgt, dir, 0);
sg_free_table(sgt);
kfree(sgt);
@@ -459,6 +505,9 @@ bool amdgpu_dmabuf_is_xgmi_accessible(struct amdgpu_device *adev,
struct drm_gem_object *obj = &bo->tbo.base;
struct drm_gem_object *gobj;
+ if (!adev)
+ return false;
+
if (obj->import_attach) {
struct dma_buf *dma_buf = obj->import_attach->dmabuf;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 26bf896..24ee471 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2548,8 +2548,20 @@ static int amdgpu_pmops_suspend(struct device *dev)
adev->in_s0ix = true;
else if (amdgpu_acpi_is_s3_active(adev))
adev->in_s3 = true;
- if (!adev->in_s0ix && !adev->in_s3)
+ if (!adev->in_s0ix && !adev->in_s3) {
+ /* don't allow going deep first time followed by s2idle the next time */
+ if (adev->last_suspend_state != PM_SUSPEND_ON &&
+ adev->last_suspend_state != pm_suspend_target_state) {
+ drm_err_once(drm_dev, "Unsupported suspend state %d\n",
+ pm_suspend_target_state);
+ return -EINVAL;
+ }
return 0;
+ }
+
+ /* cache the state last used for suspend */
+ adev->last_suspend_state = pm_suspend_target_state;
+
return amdgpu_device_suspend(drm_dev, true);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 72af5e5..cf2df77 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -1438,9 +1438,11 @@ static int amdgpu_gfx_run_cleaner_shader_job(struct amdgpu_ring *ring)
struct amdgpu_device *adev = ring->adev;
struct drm_gpu_scheduler *sched = &ring->sched;
struct drm_sched_entity entity;
+ static atomic_t counter;
struct dma_fence *f;
struct amdgpu_job *job;
struct amdgpu_ib *ib;
+ void *owner;
int i, r;
/* Initialize the scheduler entity */
@@ -1451,9 +1453,15 @@ static int amdgpu_gfx_run_cleaner_shader_job(struct amdgpu_ring *ring)
goto err;
}
- r = amdgpu_job_alloc_with_ib(ring->adev, &entity, NULL,
- 64, 0,
- &job);
+ /*
+ * Use some unique dummy value as the owner to make sure we execute
+ * the cleaner shader on each submission. The value just need to change
+ * for each submission and is otherwise meaningless.
+ */
+ owner = (void *)(unsigned long)atomic_inc_return(&counter);
+
+ r = amdgpu_job_alloc_with_ib(ring->adev, &entity, owner,
+ 64, 0, &job);
if (r)
goto err;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 4646252..ecb74cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -699,12 +699,10 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid,
uint32_t flush_type, bool all_hub,
uint32_t inst)
{
- u32 usec_timeout = amdgpu_sriov_vf(adev) ? SRIOV_USEC_TIMEOUT :
- adev->usec_timeout;
struct amdgpu_ring *ring = &adev->gfx.kiq[inst].ring;
struct amdgpu_kiq *kiq = &adev->gfx.kiq[inst];
unsigned int ndw;
- int r;
+ int r, cnt = 0;
uint32_t seq;
/*
@@ -761,10 +759,21 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid,
amdgpu_ring_commit(ring);
spin_unlock(&adev->gfx.kiq[inst].ring_lock);
- if (amdgpu_fence_wait_polling(ring, seq, usec_timeout) < 1) {
+
+ r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
+
+ might_sleep();
+ while (r < 1 && cnt++ < MAX_KIQ_REG_TRY &&
+ !amdgpu_reset_pending(adev->reset_domain)) {
+ msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
+ r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
+ }
+
+ if (cnt > MAX_KIQ_REG_TRY) {
dev_err(adev->dev, "timeout waiting for kiq fence\n");
r = -ETIME;
- }
+ } else
+ r = 0;
}
error_unlock_reset:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 80cd6f5..0b99877 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -163,8 +163,8 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
* When GTT is just an alternative to VRAM make sure that we
* only use it as fallback and still try to fill up VRAM first.
*/
- if (domain & abo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM &&
- !(adev->flags & AMD_IS_APU))
+ if (abo->tbo.resource && !(adev->flags & AMD_IS_APU) &&
+ domain & abo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM)
places[c].flags |= TTM_PL_FLAG_FALLBACK;
c++;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 6da8994..2d7f82e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -24,6 +24,7 @@
#include <linux/dma-mapping.h>
#include <drm/ttm/ttm_range_manager.h>
+#include <drm/drm_drv.h>
#include "amdgpu.h"
#include "amdgpu_vm.h"
@@ -907,6 +908,9 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev)
struct ttm_resource_manager *man = &mgr->manager;
int err;
+ man->cg = drmm_cgroup_register_region(adev_to_drm(adev), "vram", adev->gmc.real_vram_size);
+ if (IS_ERR(man->cg))
+ return PTR_ERR(man->cg);
ttm_resource_manager_init(man, &adev->mman.bdev,
adev->gmc.real_vram_size);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index a63ce74..23e6a05 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -6114,7 +6114,7 @@ static int gfx_v10_0_cp_gfx_load_pfp_microcode(struct amdgpu_device *adev)
}
if (amdgpu_emu_mode == 1)
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
tmp = RREG32_SOC15(GC, 0, mmCP_PFP_IC_BASE_CNTL);
tmp = REG_SET_FIELD(tmp, CP_PFP_IC_BASE_CNTL, VMID, 0);
@@ -6192,7 +6192,7 @@ static int gfx_v10_0_cp_gfx_load_ce_microcode(struct amdgpu_device *adev)
}
if (amdgpu_emu_mode == 1)
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
tmp = RREG32_SOC15(GC, 0, mmCP_CE_IC_BASE_CNTL);
tmp = REG_SET_FIELD(tmp, CP_CE_IC_BASE_CNTL, VMID, 0);
@@ -6269,7 +6269,7 @@ static int gfx_v10_0_cp_gfx_load_me_microcode(struct amdgpu_device *adev)
}
if (amdgpu_emu_mode == 1)
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
tmp = RREG32_SOC15(GC, 0, mmCP_ME_IC_BASE_CNTL);
tmp = REG_SET_FIELD(tmp, CP_ME_IC_BASE_CNTL, VMID, 0);
@@ -6644,7 +6644,7 @@ static int gfx_v10_0_cp_compute_load_microcode(struct amdgpu_device *adev)
}
if (amdgpu_emu_mode == 1)
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
tmp = RREG32_SOC15(GC, 0, mmCP_CPC_IC_BASE_CNTL);
tmp = REG_SET_FIELD(tmp, CP_CPC_IC_BASE_CNTL, CACHE_POLICY, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index d57db42..2a5c2a1 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -2428,7 +2428,7 @@ static int gfx_v11_0_config_me_cache(struct amdgpu_device *adev, uint64_t addr)
}
if (amdgpu_emu_mode == 1)
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
tmp = RREG32_SOC15(GC, 0, regCP_ME_IC_BASE_CNTL);
tmp = REG_SET_FIELD(tmp, CP_ME_IC_BASE_CNTL, VMID, 0);
@@ -2472,7 +2472,7 @@ static int gfx_v11_0_config_pfp_cache(struct amdgpu_device *adev, uint64_t addr)
}
if (amdgpu_emu_mode == 1)
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
tmp = RREG32_SOC15(GC, 0, regCP_PFP_IC_BASE_CNTL);
tmp = REG_SET_FIELD(tmp, CP_PFP_IC_BASE_CNTL, VMID, 0);
@@ -2517,7 +2517,7 @@ static int gfx_v11_0_config_mec_cache(struct amdgpu_device *adev, uint64_t addr)
}
if (amdgpu_emu_mode == 1)
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
tmp = RREG32_SOC15(GC, 0, regCP_CPC_IC_BASE_CNTL);
tmp = REG_SET_FIELD(tmp, CP_CPC_IC_BASE_CNTL, CACHE_POLICY, 0);
@@ -3153,7 +3153,7 @@ static int gfx_v11_0_cp_gfx_load_pfp_microcode_rs64(struct amdgpu_device *adev)
amdgpu_bo_unreserve(adev->gfx.pfp.pfp_fw_data_obj);
if (amdgpu_emu_mode == 1)
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
WREG32_SOC15(GC, 0, regCP_PFP_IC_BASE_LO,
lower_32_bits(adev->gfx.pfp.pfp_fw_gpu_addr));
@@ -3371,7 +3371,7 @@ static int gfx_v11_0_cp_gfx_load_me_microcode_rs64(struct amdgpu_device *adev)
amdgpu_bo_unreserve(adev->gfx.me.me_fw_data_obj);
if (amdgpu_emu_mode == 1)
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
WREG32_SOC15(GC, 0, regCP_ME_IC_BASE_LO,
lower_32_bits(adev->gfx.me.me_fw_gpu_addr));
@@ -4541,7 +4541,7 @@ static int gfx_v11_0_gfxhub_enable(struct amdgpu_device *adev)
if (r)
return r;
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
false : true;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index e7b58e4..62a257a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -2324,7 +2324,7 @@ static int gfx_v12_0_cp_gfx_load_pfp_microcode_rs64(struct amdgpu_device *adev)
amdgpu_bo_unreserve(adev->gfx.pfp.pfp_fw_data_obj);
if (amdgpu_emu_mode == 1)
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
WREG32_SOC15(GC, 0, regCP_PFP_IC_BASE_LO,
lower_32_bits(adev->gfx.pfp.pfp_fw_gpu_addr));
@@ -2468,7 +2468,7 @@ static int gfx_v12_0_cp_gfx_load_me_microcode_rs64(struct amdgpu_device *adev)
amdgpu_bo_unreserve(adev->gfx.me.me_fw_data_obj);
if (amdgpu_emu_mode == 1)
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
WREG32_SOC15(GC, 0, regCP_ME_IC_BASE_LO,
lower_32_bits(adev->gfx.me.me_fw_gpu_addr));
@@ -3426,7 +3426,7 @@ static int gfx_v12_0_gfxhub_enable(struct amdgpu_device *adev)
if (r)
return r;
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
false : true;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 95d894a..809b3a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -268,7 +268,7 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
ack = hub->vm_inv_eng0_ack + hub->eng_distance * eng;
/* flush hdp cache */
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
/* This is necessary for SRIOV as well as for GFXOFF to function
* properly under bare metal
@@ -969,7 +969,7 @@ static int gmc_v10_0_gart_enable(struct amdgpu_device *adev)
adev->hdp.funcs->init_registers(adev);
/* Flush HDP after it is initialized */
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
false : true;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index ad099f1..e74e26b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
@@ -229,7 +229,7 @@ static void gmc_v11_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
ack = hub->vm_inv_eng0_ack + hub->eng_distance * eng;
/* flush hdp cache */
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
/* This is necessary for SRIOV as well as for GFXOFF to function
* properly under bare metal
@@ -899,7 +899,7 @@ static int gmc_v11_0_gart_enable(struct amdgpu_device *adev)
return r;
/* Flush HDP after it is initialized */
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
false : true;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
index 05c026d..c6f2907 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
@@ -297,7 +297,7 @@ static void gmc_v12_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
return;
/* flush hdp cache */
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
/* This is necessary for SRIOV as well as for GFXOFF to function
* properly under bare metal
@@ -881,7 +881,7 @@ static int gmc_v12_0_gart_enable(struct amdgpu_device *adev)
return r;
/* Flush HDP after it is initialized */
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
false : true;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 783e0c3..5effe83 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -2435,7 +2435,7 @@ static int gmc_v9_0_hw_init(struct amdgpu_ip_block *ip_block)
adev->hdp.funcs->init_registers(adev);
/* After HDP is initialized, flush HDP.*/
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS)
value = false;
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index e65916a..ef9538fb 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -894,6 +894,10 @@ static void mes_v11_0_get_fw_version(struct amdgpu_device *adev)
{
int pipe;
+ /* return early if we have already fetched these */
+ if (adev->mes.sched_version && adev->mes.kiq_version)
+ return;
+
/* get MES scheduler/KIQ versions */
mutex_lock(&adev->srbm_mutex);
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 183dd33..e6ab617 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -1392,17 +1392,20 @@ static int mes_v12_0_queue_init(struct amdgpu_device *adev,
mes_v12_0_queue_init_register(ring);
}
- /* get MES scheduler/KIQ versions */
- mutex_lock(&adev->srbm_mutex);
- soc21_grbm_select(adev, 3, pipe, 0, 0);
+ if (((pipe == AMDGPU_MES_SCHED_PIPE) && !adev->mes.sched_version) ||
+ ((pipe == AMDGPU_MES_KIQ_PIPE) && !adev->mes.kiq_version)) {
+ /* get MES scheduler/KIQ versions */
+ mutex_lock(&adev->srbm_mutex);
+ soc21_grbm_select(adev, 3, pipe, 0, 0);
- if (pipe == AMDGPU_MES_SCHED_PIPE)
- adev->mes.sched_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
- else if (pipe == AMDGPU_MES_KIQ_PIPE && adev->enable_mes_kiq)
- adev->mes.kiq_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
+ if (pipe == AMDGPU_MES_SCHED_PIPE)
+ adev->mes.sched_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
+ else if (pipe == AMDGPU_MES_KIQ_PIPE && adev->enable_mes_kiq)
+ adev->mes.kiq_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
- soc21_grbm_select(adev, 0, 0, 0, 0);
- mutex_unlock(&adev->srbm_mutex);
+ soc21_grbm_select(adev, 0, 0, 0, 0);
+ mutex_unlock(&adev->srbm_mutex);
+ }
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index bb5dfc4..2155435 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -533,7 +533,7 @@ static int psp_v11_0_memory_training(struct psp_context *psp, uint32_t ops)
}
memcpy_toio(adev->mman.aper_base_kaddr, buf, sz);
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
vfree(buf);
drm_dev_exit(idx);
} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
index cc62106..afdf8ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
@@ -610,7 +610,7 @@ static int psp_v13_0_memory_training(struct psp_context *psp, uint32_t ops)
}
memcpy_toio(adev->mman.aper_base_kaddr, buf, sz);
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
vfree(buf);
drm_dev_exit(idx);
} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c
index 7c49c3f..256288c 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c
@@ -498,7 +498,7 @@ static int psp_v14_0_memory_training(struct psp_context *psp, uint32_t ops)
}
memcpy_toio(adev->mman.aper_base_kaddr, buf, sz);
- adev->hdp.funcs->flush_hdp(adev, NULL);
+ amdgpu_device_flush_hdp(adev, NULL);
vfree(buf);
drm_dev_exit(idx);
} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 86d8bc1..9b3510e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -239,6 +239,13 @@ static const struct amdgpu_video_codec_info cz_video_codecs_decode_array[] =
.max_pixels_per_frame = 4096 * 4096,
.max_level = 186,
},
+ {
+ .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
+ .max_width = 4096,
+ .max_height = 4096,
+ .max_pixels_per_frame = 4096 * 4096,
+ .max_level = 0,
+ },
};
static const struct amdgpu_video_codecs cz_video_codecs_decode =
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index e477d75..9bbee48 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1983,9 +1983,6 @@ static void kfd_topology_set_capabilities(struct kfd_topology_device *dev)
if (kfd_dbg_has_ttmps_always_setup(dev->gpu))
dev->node_props.debug_prop |= HSA_DBG_DISPATCH_INFO_ALWAYS_VALID;
- if (dev->gpu->adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE)
- dev->node_props.capability2 |= HSA_CAP2_PER_SDMA_QUEUE_RESET_SUPPORTED;
-
if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(10, 0, 0)) {
if (KFD_GC_VERSION(dev->gpu) == IP_VERSION(9, 4, 3) ||
KFD_GC_VERSION(dev->gpu) == IP_VERSION(9, 4, 4))
@@ -2001,7 +1998,11 @@ static void kfd_topology_set_capabilities(struct kfd_topology_device *dev)
dev->node_props.capability |=
HSA_CAP_TRAP_DEBUG_PRECISE_MEMORY_OPERATIONS_SUPPORTED;
- dev->node_props.capability |= HSA_CAP_PER_QUEUE_RESET_SUPPORTED;
+ if (!amdgpu_sriov_vf(dev->gpu->adev))
+ dev->node_props.capability |= HSA_CAP_PER_QUEUE_RESET_SUPPORTED;
+
+ if (dev->gpu->adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE)
+ dev->node_props.capability2 |= HSA_CAP2_PER_SDMA_QUEUE_RESET_SUPPORTED;
} else {
dev->node_props.debug_prop |= HSA_DBG_WATCH_ADDR_MASK_LO_BIT_GFX10 |
HSA_DBG_WATCH_ADDR_MASK_HI_BIT;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index d0d8ad5..536f731 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1726,9 +1726,30 @@ static const struct dmi_system_id dmi_quirk_table[] = {
.callback = edp0_on_dp1_callback,
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 645 14 inch G11 Notebook PC"),
+ },
+ },
+ {
+ .callback = edp0_on_dp1_callback,
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 665 16 inch G11 Notebook PC"),
},
},
+ {
+ .callback = edp0_on_dp1_callback,
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook 445 14 inch G11 Notebook PC"),
+ },
+ },
+ {
+ .callback = edp0_on_dp1_callback,
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook 465 16 inch G11 Notebook PC"),
+ },
+ },
{}
/* TODO: refactor this from a fixed table to a dynamic option */
};
@@ -1899,26 +1920,6 @@ static enum dmub_ips_disable_type dm_get_default_ips_mode(
switch (amdgpu_ip_version(adev, DCE_HWIP, 0)) {
case IP_VERSION(3, 5, 0):
case IP_VERSION(3, 6, 0):
- /*
- * On DCN35 systems with Z8 enabled, it's possible for IPS2 + Z8 to
- * cause a hard hang. A fix exists for newer PMFW.
- *
- * As a workaround, for non-fixed PMFW, force IPS1+RCG as the deepest
- * IPS state in all cases, except for s0ix and all displays off (DPMS),
- * where IPS2 is allowed.
- *
- * When checking pmfw version, use the major and minor only.
- */
- if ((adev->pm.fw_version & 0x00FFFF00) < 0x005D6300)
- ret = DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF;
- else if (amdgpu_ip_version(adev, GC_HWIP, 0) > IP_VERSION(11, 5, 0))
- /*
- * Other ASICs with DCN35 that have residency issues with
- * IPS2 in idle.
- * We want them to use IPS2 only in display off cases.
- */
- ret = DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF;
- break;
case IP_VERSION(3, 5, 1):
ret = DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF;
break;
@@ -3334,16 +3335,16 @@ static void dm_gpureset_commit_state(struct dc_state *dc_state,
for (k = 0; k < dc_state->stream_count; k++) {
bundle->stream_update.stream = dc_state->streams[k];
- for (m = 0; m < dc_state->stream_status->plane_count; m++) {
+ for (m = 0; m < dc_state->stream_status[k].plane_count; m++) {
bundle->surface_updates[m].surface =
- dc_state->stream_status->plane_states[m];
+ dc_state->stream_status[k].plane_states[m];
bundle->surface_updates[m].surface->force_full_update =
true;
}
update_planes_and_stream_adapter(dm->dc,
UPDATE_TYPE_FULL,
- dc_state->stream_status->plane_count,
+ dc_state->stream_status[k].plane_count,
dc_state->streams[k],
&bundle->stream_update,
bundle->surface_updates);
@@ -6500,12 +6501,12 @@ decide_crtc_timing_for_drm_display_mode(struct drm_display_mode *drm_mode,
const struct drm_display_mode *native_mode,
bool scale_enabled)
{
- if (scale_enabled) {
- copy_crtc_timing_for_drm_display_mode(native_mode, drm_mode);
- } else if (native_mode->clock == drm_mode->clock &&
- native_mode->htotal == drm_mode->htotal &&
- native_mode->vtotal == drm_mode->vtotal) {
- copy_crtc_timing_for_drm_display_mode(native_mode, drm_mode);
+ if (scale_enabled || (
+ native_mode->clock == drm_mode->clock &&
+ native_mode->htotal == drm_mode->htotal &&
+ native_mode->vtotal == drm_mode->vtotal)) {
+ if (native_mode->crtc_clock)
+ copy_crtc_timing_for_drm_display_mode(native_mode, drm_mode);
} else {
/* no scaling nor amdgpu inserted, no need to patch */
}
@@ -11022,6 +11023,9 @@ static bool should_reset_plane(struct drm_atomic_state *state,
state->allow_modeset)
return true;
+ if (amdgpu_in_reset(adev) && state->allow_modeset)
+ return true;
+
/* Exit early if we know that we're adding or removing the plane. */
if (old_plane_state->crtc != new_plane_state->crtc)
return true;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
index 36a830a..e8bdd7f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
@@ -113,6 +113,7 @@ bool amdgpu_dm_crtc_vrr_active(const struct dm_crtc_state *dm_state)
*
* Panel Replay and PSR SU
* - Enable when:
+ * - VRR is disabled
* - vblank counter is disabled
* - entry is allowed: usermode demonstrates an adequate number of fast
* commits)
@@ -131,19 +132,20 @@ static void amdgpu_dm_crtc_set_panel_sr_feature(
bool is_sr_active = (link->replay_settings.replay_allow_active ||
link->psr_settings.psr_allow_active);
bool is_crc_window_active = false;
+ bool vrr_active = amdgpu_dm_crtc_vrr_active_irq(vblank_work->acrtc);
#ifdef CONFIG_DRM_AMD_SECURE_DISPLAY
is_crc_window_active =
amdgpu_dm_crc_window_is_activated(&vblank_work->acrtc->base);
#endif
- if (link->replay_settings.replay_feature_enabled &&
+ if (link->replay_settings.replay_feature_enabled && !vrr_active &&
allow_sr_entry && !is_sr_active && !is_crc_window_active) {
amdgpu_dm_replay_enable(vblank_work->stream, true);
} else if (vblank_enabled) {
if (link->psr_settings.psr_version < DC_PSR_VERSION_SU_1 && is_sr_active)
amdgpu_dm_psr_disable(vblank_work->stream, false);
- } else if (link->psr_settings.psr_feature_enabled &&
+ } else if (link->psr_settings.psr_feature_enabled && !vrr_active &&
allow_sr_entry && !is_sr_active && !is_crc_window_active) {
struct amdgpu_dm_connector *aconn =
@@ -244,6 +246,8 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work)
struct vblank_control_work *vblank_work =
container_of(work, struct vblank_control_work, work);
struct amdgpu_display_manager *dm = vblank_work->dm;
+ struct amdgpu_device *adev = drm_to_adev(dm->ddev);
+ int r;
mutex_lock(&dm->dc_lock);
@@ -271,8 +275,15 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work)
vblank_work->acrtc->dm_irq_params.allow_sr_entry);
}
- if (dm->active_vblank_irq_count == 0)
+ if (dm->active_vblank_irq_count == 0) {
+ r = amdgpu_dpm_pause_power_profile(adev, true);
+ if (r)
+ dev_warn(adev->dev, "failed to set default power profile mode\n");
dc_allow_idle_optimizations(dm->dc, true);
+ r = amdgpu_dpm_pause_power_profile(adev, false);
+ if (r)
+ dev_warn(adev->dev, "failed to restore the power profile mode\n");
+ }
mutex_unlock(&dm->dc_lock);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index 2cd3539..1395a74 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -918,7 +918,7 @@ dm_helpers_probe_acpi_edid(void *data, u8 *buf, unsigned int block, size_t len)
{
struct drm_connector *connector = data;
struct acpi_device *acpidev = ACPI_COMPANION(connector->dev->dev);
- unsigned char start = block * EDID_LENGTH;
+ unsigned short start = block * EDID_LENGTH;
struct edid *edid;
int r;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
index 92f0a09..d9159ca 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
@@ -195,9 +195,9 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
.dcn_downspread_percent = 0.5,
.gpuvm_min_page_size_bytes = 4096,
.hostvm_min_page_size_bytes = 4096,
- .do_urgent_latency_adjustment = 0,
+ .do_urgent_latency_adjustment = 1,
.urgent_latency_adjustment_fabric_clock_component_us = 0,
- .urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
+ .urgent_latency_adjustment_fabric_clock_reference_mhz = 3000,
};
void dcn35_build_wm_range_table_fpu(struct clk_mgr *clk_mgr)
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c
index be54f0e..5d16f36 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c
@@ -2,6 +2,7 @@
//
// Copyright 2024 Advanced Micro Devices, Inc.
+#include <linux/vmalloc.h>
#include "dml2_internal_types.h"
#include "dml_top.h"
@@ -13,11 +14,11 @@
static bool dml21_allocate_memory(struct dml2_context **dml_ctx)
{
- *dml_ctx = kzalloc(sizeof(struct dml2_context), GFP_KERNEL);
+ *dml_ctx = vzalloc(sizeof(struct dml2_context));
if (!(*dml_ctx))
return false;
- (*dml_ctx)->v21.dml_init.dml2_instance = kzalloc(sizeof(struct dml2_instance), GFP_KERNEL);
+ (*dml_ctx)->v21.dml_init.dml2_instance = vzalloc(sizeof(struct dml2_instance));
if (!((*dml_ctx)->v21.dml_init.dml2_instance))
return false;
@@ -27,7 +28,7 @@ static bool dml21_allocate_memory(struct dml2_context **dml_ctx)
(*dml_ctx)->v21.mode_support.display_config = &(*dml_ctx)->v21.display_config;
(*dml_ctx)->v21.mode_programming.display_config = (*dml_ctx)->v21.mode_support.display_config;
- (*dml_ctx)->v21.mode_programming.programming = kzalloc(sizeof(struct dml2_display_cfg_programming), GFP_KERNEL);
+ (*dml_ctx)->v21.mode_programming.programming = vzalloc(sizeof(struct dml2_display_cfg_programming));
if (!((*dml_ctx)->v21.mode_programming.programming))
return false;
@@ -86,6 +87,8 @@ static void dml21_init(const struct dc *in_dc, struct dml2_context **dml_ctx, co
/* Store configuration options */
(*dml_ctx)->config = *config;
+ DC_FP_START();
+
/*Initialize SOCBB and DCNIP params */
dml21_initialize_soc_bb_params(&(*dml_ctx)->v21.dml_init, config, in_dc);
dml21_initialize_ip_params(&(*dml_ctx)->v21.dml_init, config, in_dc);
@@ -96,6 +99,8 @@ static void dml21_init(const struct dc *in_dc, struct dml2_context **dml_ctx, co
/*Initialize DML21 instance */
dml2_initialize_instance(&(*dml_ctx)->v21.dml_init);
+
+ DC_FP_END();
}
bool dml21_create(const struct dc *in_dc, struct dml2_context **dml_ctx, const struct dml2_configuration_options *config)
@@ -111,8 +116,8 @@ bool dml21_create(const struct dc *in_dc, struct dml2_context **dml_ctx, const s
void dml21_destroy(struct dml2_context *dml2)
{
- kfree(dml2->v21.dml_init.dml2_instance);
- kfree(dml2->v21.mode_programming.programming);
+ vfree(dml2->v21.dml_init.dml2_instance);
+ vfree(dml2->v21.mode_programming.programming);
}
static void dml21_calculate_rq_and_dlg_params(const struct dc *dc, struct dc_state *context, struct resource_context *out_new_hw_state,
@@ -283,11 +288,16 @@ bool dml21_validate(const struct dc *in_dc, struct dc_state *context, struct dml
{
bool out = false;
+ DC_FP_START();
+
/* Use dml_validate_only for fast_validate path */
- if (fast_validate) {
+ if (fast_validate)
out = dml21_check_mode_support(in_dc, context, dml_ctx);
- } else
+ else
out = dml21_mode_check_and_programming(in_dc, context, dml_ctx);
+
+ DC_FP_END();
+
return out;
}
@@ -426,8 +436,12 @@ void dml21_copy(struct dml2_context *dst_dml_ctx,
dst_dml_ctx->v21.mode_programming.programming = dst_dml2_programming;
+ DC_FP_START();
+
/* need to initialize copied instance for internal references to be correct */
dml2_initialize_instance(&dst_dml_ctx->v21.dml_init);
+
+ DC_FP_END();
}
bool dml21_create_copy(struct dml2_context **dst_dml_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
index 939ee07..e895718 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
@@ -24,6 +24,8 @@
*
*/
+#include <linux/vmalloc.h>
+
#include "display_mode_core.h"
#include "dml2_internal_types.h"
#include "dml2_utils.h"
@@ -732,17 +734,22 @@ bool dml2_validate(const struct dc *in_dc, struct dc_state *context, struct dml2
return out;
}
+ DC_FP_START();
+
/* Use dml_validate_only for fast_validate path */
if (fast_validate)
out = dml2_validate_only(context);
else
out = dml2_validate_and_build_resource(in_dc, context);
+
+ DC_FP_END();
+
return out;
}
static inline struct dml2_context *dml2_allocate_memory(void)
{
- return (struct dml2_context *) kzalloc(sizeof(struct dml2_context), GFP_KERNEL);
+ return (struct dml2_context *) vzalloc(sizeof(struct dml2_context));
}
static void dml2_init(const struct dc *in_dc, const struct dml2_configuration_options *config, struct dml2_context **dml2)
@@ -779,11 +786,15 @@ static void dml2_init(const struct dc *in_dc, const struct dml2_configuration_op
break;
}
+ DC_FP_START();
+
initialize_dml2_ip_params(*dml2, in_dc, &(*dml2)->v20.dml_core_ctx.ip);
initialize_dml2_soc_bbox(*dml2, in_dc, &(*dml2)->v20.dml_core_ctx.soc);
initialize_dml2_soc_states(*dml2, in_dc, &(*dml2)->v20.dml_core_ctx.soc, &(*dml2)->v20.dml_core_ctx.states);
+
+ DC_FP_END();
}
bool dml2_create(const struct dc *in_dc, const struct dml2_configuration_options *config, struct dml2_context **dml2)
@@ -812,7 +823,7 @@ void dml2_destroy(struct dml2_context *dml2)
if (dml2->architecture == dml2_architecture_21)
dml21_destroy(dml2);
- kfree(dml2);
+ vfree(dml2);
}
void dml2_extract_dram_and_fclk_change_support(struct dml2_context *dml2,
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c
index 34d2e09..5a5d48f 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c
@@ -35,6 +35,17 @@
#define DC_LOGGER \
link->ctx->logger
+static void get_default_8b_10b_lttpr_aux_rd_interval(
+ union training_aux_rd_interval *training_rd_interval)
+{
+ /* LTTPR are required to program DPCD 0000Eh to 0x4 (16ms) upon AUX
+ * read reply to this register. Since old sinks with DPCD rev 1.1
+ * and earlier may not support this register, assume the mandatory
+ * value is programmed by the LTTPR to avoid AUX timeout issues.
+ */
+ training_rd_interval->raw = 0x4;
+}
+
static int32_t get_cr_training_aux_rd_interval(struct dc_link *link,
const struct dc_link_settings *link_settings,
enum lttpr_mode lttpr_mode)
@@ -43,17 +54,22 @@ static int32_t get_cr_training_aux_rd_interval(struct dc_link *link,
uint32_t wait_in_micro_secs = 100;
memset(&training_rd_interval, 0, sizeof(training_rd_interval));
- if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING &&
- link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12) {
- core_link_read_dpcd(
- link,
- DP_TRAINING_AUX_RD_INTERVAL,
- (uint8_t *)&training_rd_interval,
- sizeof(training_rd_interval));
- if (lttpr_mode != LTTPR_MODE_NON_TRANSPARENT)
- wait_in_micro_secs = 400;
- if (training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL)
- wait_in_micro_secs = training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL * 4000;
+ if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING) {
+ if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12)
+ core_link_read_dpcd(
+ link,
+ DP_TRAINING_AUX_RD_INTERVAL,
+ (uint8_t *)&training_rd_interval,
+ sizeof(training_rd_interval));
+ else if (dp_is_lttpr_present(link))
+ get_default_8b_10b_lttpr_aux_rd_interval(&training_rd_interval);
+
+ if (training_rd_interval.raw != 0) {
+ if (lttpr_mode != LTTPR_MODE_NON_TRANSPARENT)
+ wait_in_micro_secs = 400;
+ if (training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL)
+ wait_in_micro_secs = training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL * 4000;
+ }
}
return wait_in_micro_secs;
}
@@ -71,13 +87,15 @@ static uint32_t get_eq_training_aux_rd_interval(
DP_128B132B_TRAINING_AUX_RD_INTERVAL,
(uint8_t *)&training_rd_interval,
sizeof(training_rd_interval));
- } else if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING &&
- link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12) {
- core_link_read_dpcd(
- link,
- DP_TRAINING_AUX_RD_INTERVAL,
- (uint8_t *)&training_rd_interval,
- sizeof(training_rd_interval));
+ } else if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING) {
+ if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12)
+ core_link_read_dpcd(
+ link,
+ DP_TRAINING_AUX_RD_INTERVAL,
+ (uint8_t *)&training_rd_interval,
+ sizeof(training_rd_interval));
+ else if (dp_is_lttpr_present(link))
+ get_default_8b_10b_lttpr_aux_rd_interval(&training_rd_interval);
}
switch (training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL) {
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index 2a96061..21dc956 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -429,6 +429,7 @@ struct amd_pm_funcs {
int (*set_pp_table)(void *handle, const char *buf, size_t size);
void (*debugfs_print_current_performance_level)(void *handle, struct seq_file *m);
int (*switch_power_profile)(void *handle, enum PP_SMC_POWER_PROFILE type, bool en);
+ int (*pause_power_profile)(void *handle, bool pause);
/* export to amdgpu */
struct amd_vce_state *(*get_vce_clock_state)(void *handle, u32 idx);
int (*dispatch_tasks)(void *handle, enum amd_pp_task task_id,
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 81e9b44..3533d43 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -349,6 +349,25 @@ int amdgpu_dpm_switch_power_profile(struct amdgpu_device *adev,
return ret;
}
+int amdgpu_dpm_pause_power_profile(struct amdgpu_device *adev,
+ bool pause)
+{
+ const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+ int ret = 0;
+
+ if (amdgpu_sriov_vf(adev))
+ return 0;
+
+ if (pp_funcs && pp_funcs->pause_power_profile) {
+ mutex_lock(&adev->pm.mutex);
+ ret = pp_funcs->pause_power_profile(
+ adev->powerplay.pp_handle, pause);
+ mutex_unlock(&adev->pm.mutex);
+ }
+
+ return ret;
+}
+
int amdgpu_dpm_set_xgmi_pstate(struct amdgpu_device *adev,
uint32_t pstate)
{
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index f93d287..4c0f7ad 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -410,6 +410,8 @@ int amdgpu_dpm_set_xgmi_pstate(struct amdgpu_device *adev,
int amdgpu_dpm_switch_power_profile(struct amdgpu_device *adev,
enum PP_SMC_POWER_PROFILE type,
bool en);
+int amdgpu_dpm_pause_power_profile(struct amdgpu_device *adev,
+ bool pause);
int amdgpu_dpm_baco_reset(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 033c322..46cce1d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -2398,7 +2398,11 @@ static int smu_switch_power_profile(void *handle,
smu_power_profile_mode_get(smu, type);
else
smu_power_profile_mode_put(smu, type);
- ret = smu_bump_power_profile_mode(smu, NULL, 0);
+ /* don't switch the active workload when paused */
+ if (smu->pause_workload)
+ ret = 0;
+ else
+ ret = smu_bump_power_profile_mode(smu, NULL, 0);
if (ret) {
if (enable)
smu_power_profile_mode_put(smu, type);
@@ -2411,6 +2415,35 @@ static int smu_switch_power_profile(void *handle,
return 0;
}
+static int smu_pause_power_profile(void *handle,
+ bool pause)
+{
+ struct smu_context *smu = handle;
+ struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm);
+ u32 workload_mask = 1 << PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
+ int ret;
+
+ if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
+ return -EOPNOTSUPP;
+
+ if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL &&
+ smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) {
+ smu->pause_workload = pause;
+
+ /* force to bootup default profile */
+ if (smu->pause_workload && smu->ppt_funcs->set_power_profile_mode)
+ ret = smu->ppt_funcs->set_power_profile_mode(smu,
+ workload_mask,
+ NULL,
+ 0);
+ else
+ ret = smu_bump_power_profile_mode(smu, NULL, 0);
+ return ret;
+ }
+
+ return 0;
+}
+
static enum amd_dpm_forced_level smu_get_performance_level(void *handle)
{
struct smu_context *smu = handle;
@@ -3733,6 +3766,7 @@ static const struct amd_pm_funcs swsmu_pm_funcs = {
.get_pp_table = smu_sys_get_pp_table,
.set_pp_table = smu_sys_set_pp_table,
.switch_power_profile = smu_switch_power_profile,
+ .pause_power_profile = smu_pause_power_profile,
/* export to amdgpu */
.dispatch_tasks = smu_handle_dpm_task,
.load_firmware = smu_load_microcode,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index 3ba1696..dd6d0e7 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -558,6 +558,7 @@ struct smu_context {
/* asic agnostic workload mask */
uint32_t workload_mask;
+ bool pause_workload;
/* default/user workload preference */
uint32_t power_profile_mode;
uint32_t workload_refcount[PP_SMC_POWER_PROFILE_COUNT];
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index 78391d8..25fabf3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -1204,7 +1204,7 @@ int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu,
uint32_t crystal_clock_freq = 2500;
uint32_t tach_period;
- if (speed == 0)
+ if (!speed || speed > UINT_MAX/8)
return -EINVAL;
/*
* To prevent from possible overheat, some ASICs may have requirement
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index 5170f72..f91daef 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -43,13 +43,13 @@ struct decon_data {
unsigned int wincon_burstlen_shift;
};
-static struct decon_data exynos7_decon_data = {
+static const struct decon_data exynos7_decon_data = {
.vidw_buf_start_base = 0x80,
.shadowcon_win_protect_shift = 10,
.wincon_burstlen_shift = 11,
};
-static struct decon_data exynos7870_decon_data = {
+static const struct decon_data exynos7870_decon_data = {
.vidw_buf_start_base = 0x880,
.shadowcon_win_protect_shift = 8,
.wincon_burstlen_shift = 10,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index f313ae7..6cc7bf7 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -355,8 +355,7 @@ static void exynos_drm_platform_shutdown(struct platform_device *pdev)
{
struct drm_device *drm = platform_get_drvdata(pdev);
- if (drm)
- drm_atomic_helper_shutdown(drm);
+ drm_atomic_helper_shutdown(drm);
}
static struct platform_driver exynos_drm_platform_driver = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index b150cfd..09e33a2 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -908,7 +908,7 @@ static void fimc_dst_set_buf_seq(struct fimc_context *ctx, u32 buf_id,
u32 buf_num;
u32 cfg;
- DRM_DEV_DEBUG_KMS(ctx->dev, "buf_id[%d]enqueu[%d]\n", buf_id, enqueue);
+ DRM_DEV_DEBUG_KMS(ctx->dev, "buf_id[%d]enqueue[%d]\n", buf_id, enqueue);
spin_lock_irqsave(&ctx->lock, flags);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 1ad8758..c394cc7 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -731,7 +731,7 @@ static void fimd_win_set_pixfmt(struct fimd_context *ctx, unsigned int win,
/*
* Setting dma-burst to 16Word causes permanent tearing for very small
* buffers, e.g. cursor buffer. Burst Mode switching which based on
- * plane size is not recommended as plane size varies alot towards the
+ * plane size is not recommended as plane size varies a lot towards the
* end of the screen and rapid movement causes unstable DMA, but it is
* still better to change dma-burst than displaying garbage.
*/
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 08cf79a..e644e23 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -312,9 +312,6 @@ static int vidi_get_modes(struct drm_connector *connector)
else
drm_edid = drm_edid_alloc(fake_edid_info, sizeof(fake_edid_info));
- if (!drm_edid)
- return 0;
-
drm_edid_connector_update(connector, drm_edid);
count = drm_edid_connector_add_modes(connector);
diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c
index 048be287..98b898a 100644
--- a/drivers/gpu/drm/i915/display/intel_bw.c
+++ b/drivers/gpu/drm/i915/display/intel_bw.c
@@ -244,6 +244,7 @@ static int icl_get_qgv_points(struct drm_i915_private *dev_priv,
qi->deinterleave = 4;
break;
case INTEL_DRAM_GDDR:
+ case INTEL_DRAM_GDDR_ECC:
qi->channel_width = 32;
break;
default:
@@ -398,6 +399,12 @@ static const struct intel_sa_info xe2_hpd_sa_info = {
/* Other values not used by simplified algorithm */
};
+static const struct intel_sa_info xe2_hpd_ecc_sa_info = {
+ .derating = 45,
+ .deprogbwlimit = 53,
+ /* Other values not used by simplified algorithm */
+};
+
static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel_sa_info *sa)
{
struct intel_qgv_info qi = {};
@@ -740,10 +747,15 @@ static unsigned int icl_qgv_bw(struct drm_i915_private *i915,
void intel_bw_init_hw(struct drm_i915_private *dev_priv)
{
+ const struct dram_info *dram_info = &dev_priv->dram_info;
+
if (!HAS_DISPLAY(dev_priv))
return;
- if (DISPLAY_VERx100(dev_priv) >= 1401 && IS_DGFX(dev_priv))
+ if (DISPLAY_VERx100(dev_priv) >= 1401 && IS_DGFX(dev_priv) &&
+ dram_info->type == INTEL_DRAM_GDDR_ECC)
+ xe2_hpd_get_bw_info(dev_priv, &xe2_hpd_ecc_sa_info);
+ else if (DISPLAY_VERx100(dev_priv) >= 1401 && IS_DGFX(dev_priv))
xe2_hpd_get_bw_info(dev_priv, &xe2_hpd_sa_info);
else if (DISPLAY_VER(dev_priv) >= 14)
tgl_get_bw_info(dev_priv, &mtl_sa_info);
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 3afb85f..3b509c7 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -968,7 +968,9 @@ static bool vrr_params_changed(const struct intel_crtc_state *old_crtc_state,
old_crtc_state->vrr.vmin != new_crtc_state->vrr.vmin ||
old_crtc_state->vrr.vmax != new_crtc_state->vrr.vmax ||
old_crtc_state->vrr.guardband != new_crtc_state->vrr.guardband ||
- old_crtc_state->vrr.pipeline_full != new_crtc_state->vrr.pipeline_full;
+ old_crtc_state->vrr.pipeline_full != new_crtc_state->vrr.pipeline_full ||
+ old_crtc_state->vrr.vsync_start != new_crtc_state->vrr.vsync_start ||
+ old_crtc_state->vrr.vsync_end != new_crtc_state->vrr.vsync_end;
}
static bool cmrr_params_changed(const struct intel_crtc_state *old_crtc_state,
diff --git a/drivers/gpu/drm/i915/display/intel_display_device.h b/drivers/gpu/drm/i915/display/intel_display_device.h
index 7172869..7a3bb77 100644
--- a/drivers/gpu/drm/i915/display/intel_display_device.h
+++ b/drivers/gpu/drm/i915/display/intel_display_device.h
@@ -161,6 +161,7 @@ struct intel_display_platforms {
#define HAS_DPT(__display) (DISPLAY_VER(__display) >= 13)
#define HAS_DSB(__display) (DISPLAY_INFO(__display)->has_dsb)
#define HAS_DSC(__display) (DISPLAY_RUNTIME_INFO(__display)->has_dsc)
+#define HAS_DSC_3ENGINES(__display) (DISPLAY_VERx100(__display) == 1401 && HAS_DSC(__display))
#define HAS_DSC_MST(__display) (DISPLAY_VER(__display) >= 12 && HAS_DSC(__display))
#define HAS_FBC(__display) (DISPLAY_RUNTIME_INFO(__display)->fbc_mask != 0)
#define HAS_FBC_DIRTY_RECT(__display) (DISPLAY_VER(__display) >= 30)
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index a236b5f..392c365 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -172,10 +172,28 @@ int intel_dp_link_symbol_clock(int rate)
static int max_dprx_rate(struct intel_dp *intel_dp)
{
- if (intel_dp_tunnel_bw_alloc_is_enabled(intel_dp))
- return drm_dp_tunnel_max_dprx_rate(intel_dp->tunnel);
+ struct intel_display *display = to_intel_display(intel_dp);
+ struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+ int max_rate;
- return drm_dp_bw_code_to_link_rate(intel_dp->dpcd[DP_MAX_LINK_RATE]);
+ if (intel_dp_tunnel_bw_alloc_is_enabled(intel_dp))
+ max_rate = drm_dp_tunnel_max_dprx_rate(intel_dp->tunnel);
+ else
+ max_rate = drm_dp_bw_code_to_link_rate(intel_dp->dpcd[DP_MAX_LINK_RATE]);
+
+ /*
+ * Some broken eDP sinks illegally declare support for
+ * HBR3 without TPS4, and are unable to produce a stable
+ * output. Reject HBR3 when TPS4 is not available.
+ */
+ if (max_rate >= 810000 && !drm_dp_tps4_supported(intel_dp->dpcd)) {
+ drm_dbg_kms(display->drm,
+ "[ENCODER:%d:%s] Rejecting HBR3 due to missing TPS4 support\n",
+ encoder->base.base.id, encoder->base.name);
+ max_rate = 540000;
+ }
+
+ return max_rate;
}
static int max_dprx_lane_count(struct intel_dp *intel_dp)
@@ -1032,10 +1050,11 @@ u8 intel_dp_dsc_get_slice_count(const struct intel_connector *connector,
u8 test_slice_count = valid_dsc_slicecount[i] * num_joined_pipes;
/*
- * 3 DSC Slices per pipe need 3 DSC engines,
- * which is supported only with Ultrajoiner.
+ * 3 DSC Slices per pipe need 3 DSC engines, which is supported only
+ * with Ultrajoiner only for some platforms.
*/
- if (valid_dsc_slicecount[i] == 3 && num_joined_pipes != 4)
+ if (valid_dsc_slicecount[i] == 3 &&
+ (!HAS_DSC_3ENGINES(display) || num_joined_pipes != 4))
continue;
if (test_slice_count >
@@ -4170,6 +4189,9 @@ static void intel_edp_mso_init(struct intel_dp *intel_dp)
static void
intel_edp_set_sink_rates(struct intel_dp *intel_dp)
{
+ struct intel_display *display = to_intel_display(intel_dp);
+ struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+
intel_dp->num_sink_rates = 0;
if (intel_dp->edp_dpcd[0] >= DP_EDP_14) {
@@ -4180,10 +4202,7 @@ intel_edp_set_sink_rates(struct intel_dp *intel_dp)
sink_rates, sizeof(sink_rates));
for (i = 0; i < ARRAY_SIZE(sink_rates); i++) {
- int val = le16_to_cpu(sink_rates[i]);
-
- if (val == 0)
- break;
+ int rate;
/* Value read multiplied by 200kHz gives the per-lane
* link rate in kHz. The source rates are, however,
@@ -4191,7 +4210,24 @@ intel_edp_set_sink_rates(struct intel_dp *intel_dp)
* back to symbols is
* (val * 200kHz)*(8/10 ch. encoding)*(1/8 bit to Byte)
*/
- intel_dp->sink_rates[i] = (val * 200) / 10;
+ rate = le16_to_cpu(sink_rates[i]) * 200 / 10;
+
+ if (rate == 0)
+ break;
+
+ /*
+ * Some broken eDP sinks illegally declare support for
+ * HBR3 without TPS4, and are unable to produce a stable
+ * output. Reject HBR3 when TPS4 is not available.
+ */
+ if (rate >= 810000 && !drm_dp_tps4_supported(intel_dp->dpcd)) {
+ drm_dbg_kms(display->drm,
+ "[ENCODER:%d:%s] Rejecting HBR3 due to missing TPS4 support\n",
+ encoder->base.base.id, encoder->base.name);
+ break;
+ }
+
+ intel_dp->sink_rates[i] = rate;
}
intel_dp->num_sink_rates = i;
}
diff --git a/drivers/gpu/drm/i915/display/intel_vblank.c b/drivers/gpu/drm/i915/display/intel_vblank.c
index 4efd4f7..7b240ce 100644
--- a/drivers/gpu/drm/i915/display/intel_vblank.c
+++ b/drivers/gpu/drm/i915/display/intel_vblank.c
@@ -222,7 +222,9 @@ int intel_crtc_scanline_offset(const struct intel_crtc_state *crtc_state)
* However if queried just before the start of vblank we'll get an
* answer that's slightly in the future.
*/
- if (DISPLAY_VER(display) == 2)
+ if (DISPLAY_VER(display) >= 20 || display->platform.battlemage)
+ return 1;
+ else if (DISPLAY_VER(display) == 2)
return -1;
else if (HAS_DDI(display) && intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
return 2;
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c
index 9378d59..9ca4258 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6.c
+++ b/drivers/gpu/drm/i915/gt/intel_rc6.c
@@ -117,21 +117,10 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6)
GEN6_RC_CTL_RC6_ENABLE |
GEN6_RC_CTL_EI_MODE(1);
- /*
- * BSpec 52698 - Render powergating must be off.
- * FIXME BSpec is outdated, disabling powergating for MTL is just
- * temporary wa and should be removed after fixing real cause
- * of forcewake timeouts.
- */
- if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74)))
- pg_enable =
- GEN9_MEDIA_PG_ENABLE |
- GEN11_MEDIA_SAMPLER_PG_ENABLE;
- else
- pg_enable =
- GEN9_RENDER_PG_ENABLE |
- GEN9_MEDIA_PG_ENABLE |
- GEN11_MEDIA_SAMPLER_PG_ENABLE;
+ pg_enable =
+ GEN9_RENDER_PG_ENABLE |
+ GEN9_MEDIA_PG_ENABLE |
+ GEN11_MEDIA_SAMPLER_PG_ENABLE;
if (GRAPHICS_VER(gt->i915) >= 12 && !IS_DG1(gt->i915)) {
for (i = 0; i < I915_MAX_VCS; i++)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
index d791f9b..456d337 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
@@ -317,6 +317,11 @@ void intel_huc_init_early(struct intel_huc *huc)
}
}
+void intel_huc_fini_late(struct intel_huc *huc)
+{
+ delayed_huc_load_fini(huc);
+}
+
#define HUC_LOAD_MODE_STRING(x) (x ? "GSC" : "legacy")
static int check_huc_loading_mode(struct intel_huc *huc)
{
@@ -414,12 +419,6 @@ int intel_huc_init(struct intel_huc *huc)
void intel_huc_fini(struct intel_huc *huc)
{
- /*
- * the fence is initialized in init_early, so we need to clean it up
- * even if HuC loading is off.
- */
- delayed_huc_load_fini(huc);
-
if (huc->heci_pkt)
i915_vma_unpin_and_release(&huc->heci_pkt, 0);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.h b/drivers/gpu/drm/i915/gt/uc/intel_huc.h
index d5e441b..921ad4b 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.h
@@ -55,6 +55,7 @@ struct intel_huc {
int intel_huc_sanitize(struct intel_huc *huc);
void intel_huc_init_early(struct intel_huc *huc);
+void intel_huc_fini_late(struct intel_huc *huc);
int intel_huc_init(struct intel_huc *huc);
void intel_huc_fini(struct intel_huc *huc);
int intel_huc_auth(struct intel_huc *huc, enum intel_huc_authentication_type type);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index 90ba1b0..4a3493e 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -136,6 +136,7 @@ void intel_uc_init_late(struct intel_uc *uc)
void intel_uc_driver_late_release(struct intel_uc *uc)
{
+ intel_huc_fini_late(&uc->huc);
}
/**
diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c
index 509f9cca..dbad4d8 100644
--- a/drivers/gpu/drm/i915/gvt/opregion.c
+++ b/drivers/gpu/drm/i915/gvt/opregion.c
@@ -222,7 +222,6 @@ int intel_vgpu_init_opregion(struct intel_vgpu *vgpu)
u8 *buf;
struct opregion_header *header;
struct vbt v;
- const char opregion_signature[16] = OPREGION_SIGNATURE;
gvt_dbg_core("init vgpu%d opregion\n", vgpu->id);
vgpu_opregion(vgpu)->va = (void *)__get_free_pages(GFP_KERNEL |
@@ -236,8 +235,10 @@ int intel_vgpu_init_opregion(struct intel_vgpu *vgpu)
/* emulated opregion with VBT mailbox only */
buf = (u8 *)vgpu_opregion(vgpu)->va;
header = (struct opregion_header *)buf;
- memcpy(header->signature, opregion_signature,
- sizeof(opregion_signature));
+
+ static_assert(sizeof(header->signature) == sizeof(OPREGION_SIGNATURE) - 1);
+ memcpy(header->signature, OPREGION_SIGNATURE, sizeof(header->signature));
+
header->size = 0x8;
header->opregion_ver = 0x02000000;
header->mboxes = MBOX_VBT;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ffc3463..54538b6f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -305,6 +305,7 @@ struct drm_i915_private {
INTEL_DRAM_DDR5,
INTEL_DRAM_LPDDR5,
INTEL_DRAM_GDDR,
+ INTEL_DRAM_GDDR_ECC,
} type;
u8 num_qgv_points;
u8 num_psf_gv_points;
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h b/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h
index 9aae779..4969d3d 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h
@@ -23,6 +23,7 @@ int intel_pxp_gsccs_init(struct intel_pxp *pxp);
int intel_pxp_gsccs_create_session(struct intel_pxp *pxp, int arb_session_id);
void intel_pxp_gsccs_end_arb_fw_session(struct intel_pxp *pxp, u32 arb_session_id);
+bool intel_pxp_gsccs_is_ready_for_sessions(struct intel_pxp *pxp);
#else
static inline void intel_pxp_gsccs_fini(struct intel_pxp *pxp)
@@ -34,8 +35,11 @@ static inline int intel_pxp_gsccs_init(struct intel_pxp *pxp)
return 0;
}
-#endif
+static inline bool intel_pxp_gsccs_is_ready_for_sessions(struct intel_pxp *pxp)
+{
+ return false;
+}
-bool intel_pxp_gsccs_is_ready_for_sessions(struct intel_pxp *pxp);
+#endif
#endif /*__INTEL_PXP_GSCCS_H__ */
diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c
index fee76c1..8892818 100644
--- a/drivers/gpu/drm/i915/selftests/i915_selftest.c
+++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c
@@ -23,7 +23,9 @@
#include <linux/random.h>
+#include "gt/intel_gt.h"
#include "gt/intel_gt_pm.h"
+#include "gt/intel_gt_regs.h"
#include "gt/uc/intel_gsc_fw.h"
#include "i915_driver.h"
@@ -253,11 +255,27 @@ int i915_mock_selftests(void)
int i915_live_selftests(struct pci_dev *pdev)
{
struct drm_i915_private *i915 = pdev_to_i915(pdev);
+ struct intel_uncore *uncore = &i915->uncore;
int err;
+ u32 pg_enable;
+ intel_wakeref_t wakeref;
if (!i915_selftest.live)
return 0;
+ /*
+ * FIXME Disable render powergating, this is temporary wa and should be removed
+ * after fixing real cause of forcewake timeouts.
+ */
+ with_intel_runtime_pm(uncore->rpm, wakeref) {
+ if (IS_GFX_GT_IP_RANGE(to_gt(i915), IP_VER(12, 00), IP_VER(12, 74))) {
+ pg_enable = intel_uncore_read(uncore, GEN9_PG_ENABLE);
+ if (pg_enable & GEN9_RENDER_PG_ENABLE)
+ intel_uncore_write_fw(uncore, GEN9_PG_ENABLE,
+ pg_enable & ~GEN9_RENDER_PG_ENABLE);
+ }
+ }
+
__wait_gsc_proxy_completed(i915);
__wait_gsc_huc_load_completed(i915);
diff --git a/drivers/gpu/drm/i915/soc/intel_dram.c b/drivers/gpu/drm/i915/soc/intel_dram.c
index 9e310f4..f60eedb 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.c
+++ b/drivers/gpu/drm/i915/soc/intel_dram.c
@@ -687,6 +687,10 @@ static int xelpdp_get_dram_info(struct drm_i915_private *i915)
drm_WARN_ON(&i915->drm, !IS_DGFX(i915));
dram_info->type = INTEL_DRAM_GDDR;
break;
+ case 9:
+ drm_WARN_ON(&i915->drm, !IS_DGFX(i915));
+ dram_info->type = INTEL_DRAM_GDDR_ECC;
+ break;
default:
MISSING_CASE(val);
return -EINVAL;
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 06465bc..242d02d 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -242,10 +242,10 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
break;
fallthrough;
case MSM_SUBMIT_CMD_BUF:
- OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3);
+ OUT_PKT7(ring, CP_INDIRECT_BUFFER, 3);
OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
OUT_RING(ring, upper_32_bits(submit->cmd[i].iova));
- OUT_RING(ring, submit->cmd[i].size);
+ OUT_RING(ring, A5XX_CP_INDIRECT_BUFFER_2_IB_SIZE(submit->cmd[i].size));
ibs++;
break;
}
@@ -377,10 +377,10 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
break;
fallthrough;
case MSM_SUBMIT_CMD_BUF:
- OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3);
+ OUT_PKT7(ring, CP_INDIRECT_BUFFER, 3);
OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
OUT_RING(ring, upper_32_bits(submit->cmd[i].iova));
- OUT_RING(ring, submit->cmd[i].size);
+ OUT_RING(ring, A5XX_CP_INDIRECT_BUFFER_2_IB_SIZE(submit->cmd[i].size));
ibs++;
break;
}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h
index 1f32807..ad60089 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h
@@ -132,7 +132,6 @@ static const struct dpu_intf_cfg msm8937_intf[] = {
.prog_fetch_lines_worst_case = 14,
.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26),
.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27),
- .intr_tear_rd_ptr = -1,
}, {
.name = "intf_2", .id = INTF_2,
.base = 0x6b000, .len = 0x268,
@@ -141,7 +140,6 @@ static const struct dpu_intf_cfg msm8937_intf[] = {
.prog_fetch_lines_worst_case = 14,
.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28),
.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29),
- .intr_tear_rd_ptr = -1,
},
};
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h
index 4213195..a1cf89a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h
@@ -118,7 +118,6 @@ static const struct dpu_intf_cfg msm8917_intf[] = {
.prog_fetch_lines_worst_case = 14,
.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26),
.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27),
- .intr_tear_rd_ptr = -1,
},
};
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h
index 2b4723a..eea9b80 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h
@@ -131,7 +131,6 @@ static const struct dpu_intf_cfg msm8953_intf[] = {
.prog_fetch_lines_worst_case = 14,
.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
- .intr_tear_rd_ptr = -1,
}, {
.name = "intf_1", .id = INTF_1,
.base = 0x6a800, .len = 0x268,
@@ -140,7 +139,6 @@ static const struct dpu_intf_cfg msm8953_intf[] = {
.prog_fetch_lines_worst_case = 14,
.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26),
.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27),
- .intr_tear_rd_ptr = -1,
}, {
.name = "intf_2", .id = INTF_2,
.base = 0x6b000, .len = 0x268,
@@ -149,7 +147,6 @@ static const struct dpu_intf_cfg msm8953_intf[] = {
.prog_fetch_lines_worst_case = 14,
.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28),
.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29),
- .intr_tear_rd_ptr = -1,
},
};
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h
index 5cf19de..ae18a35 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h
@@ -241,7 +241,6 @@ static const struct dpu_intf_cfg msm8996_intf[] = {
.prog_fetch_lines_worst_case = 25,
.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
- .intr_tear_rd_ptr = -1,
}, {
.name = "intf_1", .id = INTF_1,
.base = 0x6a800, .len = 0x268,
@@ -250,7 +249,6 @@ static const struct dpu_intf_cfg msm8996_intf[] = {
.prog_fetch_lines_worst_case = 25,
.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26),
.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27),
- .intr_tear_rd_ptr = -1,
}, {
.name = "intf_2", .id = INTF_2,
.base = 0x6b000, .len = 0x268,
@@ -259,7 +257,6 @@ static const struct dpu_intf_cfg msm8996_intf[] = {
.prog_fetch_lines_worst_case = 25,
.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28),
.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29),
- .intr_tear_rd_ptr = -1,
}, {
.name = "intf_3", .id = INTF_3,
.base = 0x6b800, .len = 0x268,
@@ -267,7 +264,6 @@ static const struct dpu_intf_cfg msm8996_intf[] = {
.prog_fetch_lines_worst_case = 25,
.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30),
.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31),
- .intr_tear_rd_ptr = -1,
},
};
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h
index 4f2f68b..bb89da0 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h
@@ -202,7 +202,6 @@ static const struct dpu_intf_cfg sdm660_intf[] = {
.prog_fetch_lines_worst_case = 21,
.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
- .intr_tear_rd_ptr = -1,
}, {
.name = "intf_1", .id = INTF_1,
.base = 0x6a800, .len = 0x280,
@@ -211,7 +210,6 @@ static const struct dpu_intf_cfg sdm660_intf[] = {
.prog_fetch_lines_worst_case = 21,
.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26),
.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27),
- .intr_tear_rd_ptr = -1,
}, {
.name = "intf_2", .id = INTF_2,
.base = 0x6b000, .len = 0x280,
@@ -220,7 +218,6 @@ static const struct dpu_intf_cfg sdm660_intf[] = {
.prog_fetch_lines_worst_case = 21,
.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28),
.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29),
- .intr_tear_rd_ptr = -1,
},
};
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h
index c70bef0..7caf876 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h
@@ -147,7 +147,6 @@ static const struct dpu_intf_cfg sdm630_intf[] = {
.prog_fetch_lines_worst_case = 21,
.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
- .intr_tear_rd_ptr = -1,
}, {
.name = "intf_1", .id = INTF_1,
.base = 0x6a800, .len = 0x280,
@@ -156,7 +155,6 @@ static const struct dpu_intf_cfg sdm630_intf[] = {
.prog_fetch_lines_worst_case = 21,
.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26),
.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27),
- .intr_tear_rd_ptr = -1,
},
};
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 8610bbf..862e9e6 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -1666,7 +1666,7 @@ static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc,
*/
static void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys)
{
- struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(phys->parent);
+ struct dpu_encoder_virt *dpu_enc;
if (!phys) {
DPU_ERROR("invalid argument(s)\n");
@@ -1678,6 +1678,8 @@ static void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys)
return;
}
+ dpu_enc = to_dpu_encoder_virt(phys->parent);
+
if (phys->parent->encoder_type == DRM_MODE_ENCODER_VIRTUAL &&
dpu_enc->cwb_mask) {
DPU_DEBUG("encoder %d CWB enabled, skipping\n", DRMID(phys->parent));
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index af3e541..e03d609 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -729,12 +729,40 @@ static int dpu_plane_check_inline_rotation(struct dpu_plane *pdpu,
static int dpu_plane_atomic_check_pipe(struct dpu_plane *pdpu,
struct dpu_sw_pipe *pipe,
struct dpu_sw_pipe_cfg *pipe_cfg,
- const struct msm_format *fmt,
- const struct drm_display_mode *mode)
+ const struct drm_display_mode *mode,
+ struct drm_plane_state *new_plane_state)
{
uint32_t min_src_size;
struct dpu_kms *kms = _dpu_plane_get_kms(&pdpu->base);
int ret;
+ const struct msm_format *fmt;
+ uint32_t supported_rotations;
+ const struct dpu_sspp_cfg *pipe_hw_caps;
+ const struct dpu_sspp_sub_blks *sblk;
+
+ pipe_hw_caps = pipe->sspp->cap;
+ sblk = pipe->sspp->cap->sblk;
+
+ /*
+ * We already have verified scaling against platform limitations.
+ * Now check if the SSPP supports scaling at all.
+ */
+ if (!sblk->scaler_blk.len &&
+ ((drm_rect_width(&new_plane_state->src) >> 16 !=
+ drm_rect_width(&new_plane_state->dst)) ||
+ (drm_rect_height(&new_plane_state->src) >> 16 !=
+ drm_rect_height(&new_plane_state->dst))))
+ return -ERANGE;
+
+ fmt = msm_framebuffer_format(new_plane_state->fb);
+
+ supported_rotations = DRM_MODE_REFLECT_MASK | DRM_MODE_ROTATE_0;
+
+ if (pipe_hw_caps->features & BIT(DPU_SSPP_INLINE_ROTATION))
+ supported_rotations |= DRM_MODE_ROTATE_90;
+
+ pipe_cfg->rotation = drm_rotation_simplify(new_plane_state->rotation,
+ supported_rotations);
min_src_size = MSM_FORMAT_IS_YUV(fmt) ? 2 : 1;
@@ -923,47 +951,20 @@ static int dpu_plane_atomic_check_sspp(struct drm_plane *plane,
struct dpu_plane_state *pstate = to_dpu_plane_state(new_plane_state);
struct dpu_sw_pipe *pipe = &pstate->pipe;
struct dpu_sw_pipe *r_pipe = &pstate->r_pipe;
- const struct msm_format *fmt;
struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg;
struct dpu_sw_pipe_cfg *r_pipe_cfg = &pstate->r_pipe_cfg;
- uint32_t supported_rotations;
- const struct dpu_sspp_cfg *pipe_hw_caps;
- const struct dpu_sspp_sub_blks *sblk;
int ret = 0;
- pipe_hw_caps = pipe->sspp->cap;
- sblk = pipe->sspp->cap->sblk;
-
- /*
- * We already have verified scaling against platform limitations.
- * Now check if the SSPP supports scaling at all.
- */
- if (!sblk->scaler_blk.len &&
- ((drm_rect_width(&new_plane_state->src) >> 16 !=
- drm_rect_width(&new_plane_state->dst)) ||
- (drm_rect_height(&new_plane_state->src) >> 16 !=
- drm_rect_height(&new_plane_state->dst))))
- return -ERANGE;
-
- fmt = msm_framebuffer_format(new_plane_state->fb);
-
- supported_rotations = DRM_MODE_REFLECT_MASK | DRM_MODE_ROTATE_0;
-
- if (pipe_hw_caps->features & BIT(DPU_SSPP_INLINE_ROTATION))
- supported_rotations |= DRM_MODE_ROTATE_90;
-
- pipe_cfg->rotation = drm_rotation_simplify(new_plane_state->rotation,
- supported_rotations);
- r_pipe_cfg->rotation = pipe_cfg->rotation;
-
- ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg, fmt,
- &crtc_state->adjusted_mode);
+ ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg,
+ &crtc_state->adjusted_mode,
+ new_plane_state);
if (ret)
return ret;
if (drm_rect_width(&r_pipe_cfg->src_rect) != 0) {
- ret = dpu_plane_atomic_check_pipe(pdpu, r_pipe, r_pipe_cfg, fmt,
- &crtc_state->adjusted_mode);
+ ret = dpu_plane_atomic_check_pipe(pdpu, r_pipe, r_pipe_cfg,
+ &crtc_state->adjusted_mode,
+ new_plane_state);
if (ret)
return ret;
}
@@ -1059,6 +1060,9 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane,
struct drm_crtc_state *crtc_state;
int ret;
+ if (IS_ERR(plane_state))
+ return PTR_ERR(plane_state);
+
if (plane_state->crtc)
crtc_state = drm_atomic_get_new_crtc_state(state,
plane_state->crtc);
diff --git a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml
index 55a3518..5a6ae9f 100644
--- a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml
+++ b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml
@@ -2259,5 +2259,12 @@
</reg32>
</domain>
+<domain name="CP_INDIRECT_BUFFER" width="32" varset="chip" prefix="chip" variants="A5XX-">
+ <reg64 offset="0" name="IB_BASE" type="address"/>
+ <reg32 offset="2" name="2">
+ <bitfield name="IB_SIZE" low="0" high="19"/>
+ </reg32>
+</domain>
+
</database>
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c
index 2d88e39..e32e680 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.c
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.c
@@ -128,6 +128,14 @@ static void virtio_gpu_remove(struct virtio_device *vdev)
drm_dev_put(dev);
}
+static void virtio_gpu_shutdown(struct virtio_device *vdev)
+{
+ /*
+ * drm does its own synchronization on shutdown.
+ * Do nothing here, opt out of device reset.
+ */
+}
+
static void virtio_gpu_config_changed(struct virtio_device *vdev)
{
struct drm_device *dev = vdev->priv;
@@ -162,6 +170,7 @@ static struct virtio_driver virtio_gpu_driver = {
.id_table = id_table,
.probe = virtio_gpu_probe,
.remove = virtio_gpu_remove,
+ .shutdown = virtio_gpu_shutdown,
.config_changed = virtio_gpu_config_changed
};
diff --git a/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h b/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h
index a255946..8cfcd33 100644
--- a/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h
+++ b/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h
@@ -41,6 +41,7 @@
#define GFX_OP_PIPE_CONTROL(len) ((0x3<<29)|(0x3<<27)|(0x2<<24)|((len)-2))
+#define PIPE_CONTROL0_L3_READ_ONLY_CACHE_INVALIDATE BIT(10) /* gen12 */
#define PIPE_CONTROL0_HDC_PIPELINE_FLUSH BIT(9) /* gen12 */
#define PIPE_CONTROL_COMMAND_CACHE_INVALIDATE (1<<29)
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 72ef0b6..9f8667e 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -585,6 +585,7 @@ struct xe_device {
INTEL_DRAM_DDR5,
INTEL_DRAM_LPDDR5,
INTEL_DRAM_GDDR,
+ INTEL_DRAM_GDDR_ECC,
} type;
u8 num_qgv_points;
u8 num_psf_gv_points;
diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c
index f67803e..f7a2026 100644
--- a/drivers/gpu/drm/xe/xe_dma_buf.c
+++ b/drivers/gpu/drm/xe/xe_dma_buf.c
@@ -145,10 +145,7 @@ static void xe_dma_buf_unmap(struct dma_buf_attachment *attach,
struct sg_table *sgt,
enum dma_data_direction dir)
{
- struct dma_buf *dma_buf = attach->dmabuf;
- struct xe_bo *bo = gem_to_xe_bo(dma_buf->priv);
-
- if (!xe_bo_is_vram(bo)) {
+ if (sg_page(sgt->sgl)) {
dma_unmap_sgtable(attach->dev, sgt, dir, 0);
sg_free_table(sgt);
kfree(sgt);
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index 03072e0..084cbde 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -322,6 +322,13 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt)
return 0;
}
+/*
+ * Ensure that roundup_pow_of_two(length) doesn't overflow.
+ * Note that roundup_pow_of_two() operates on unsigned long,
+ * not on u64.
+ */
+#define MAX_RANGE_TLB_INVALIDATION_LENGTH (rounddown_pow_of_two(ULONG_MAX))
+
/**
* xe_gt_tlb_invalidation_range - Issue a TLB invalidation on this GT for an
* address range
@@ -346,6 +353,7 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
struct xe_device *xe = gt_to_xe(gt);
#define MAX_TLB_INVALIDATION_LEN 7
u32 action[MAX_TLB_INVALIDATION_LEN];
+ u64 length = end - start;
int len = 0;
xe_gt_assert(gt, fence);
@@ -358,11 +366,11 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
action[len++] = XE_GUC_ACTION_TLB_INVALIDATION;
action[len++] = 0; /* seqno, replaced in send_tlb_invalidation */
- if (!xe->info.has_range_tlb_invalidation) {
+ if (!xe->info.has_range_tlb_invalidation ||
+ length > MAX_RANGE_TLB_INVALIDATION_LENGTH) {
action[len++] = MAKE_INVAL_OP(XE_GUC_TLB_INVAL_FULL);
} else {
u64 orig_start = start;
- u64 length = end - start;
u64 align;
if (length < SZ_4K)
diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c
index e7c9e09..7031542 100644
--- a/drivers/gpu/drm/xe/xe_guc_ads.c
+++ b/drivers/gpu/drm/xe/xe_guc_ads.c
@@ -490,24 +490,52 @@ static void fill_engine_enable_masks(struct xe_gt *gt,
engine_enable_mask(gt, XE_ENGINE_CLASS_OTHER));
}
-static void guc_prep_golden_lrc_null(struct xe_guc_ads *ads)
+/*
+ * Write the offsets corresponding to the golden LRCs. The actual data is
+ * populated later by guc_golden_lrc_populate()
+ */
+static void guc_golden_lrc_init(struct xe_guc_ads *ads)
{
struct xe_device *xe = ads_to_xe(ads);
+ struct xe_gt *gt = ads_to_gt(ads);
struct iosys_map info_map = IOSYS_MAP_INIT_OFFSET(ads_to_map(ads),
offsetof(struct __guc_ads_blob, system_info));
- u8 guc_class;
+ size_t alloc_size, real_size;
+ u32 addr_ggtt, offset;
+ int class;
- for (guc_class = 0; guc_class <= GUC_MAX_ENGINE_CLASSES; ++guc_class) {
+ offset = guc_ads_golden_lrc_offset(ads);
+ addr_ggtt = xe_bo_ggtt_addr(ads->bo) + offset;
+
+ for (class = 0; class < XE_ENGINE_CLASS_MAX; ++class) {
+ u8 guc_class;
+
+ guc_class = xe_engine_class_to_guc_class(class);
+
if (!info_map_read(xe, &info_map,
engine_enabled_masks[guc_class]))
continue;
+ real_size = xe_gt_lrc_size(gt, class);
+ alloc_size = PAGE_ALIGN(real_size);
+
+ /*
+ * This interface is slightly confusing. We need to pass the
+ * base address of the full golden context and the size of just
+ * the engine state, which is the section of the context image
+ * that starts after the execlists LRC registers. This is
+ * required to allow the GuC to restore just the engine state
+ * when a watchdog reset occurs.
+ * We calculate the engine state size by removing the size of
+ * what comes before it in the context image (which is identical
+ * on all engines).
+ */
ads_blob_write(ads, ads.eng_state_size[guc_class],
- guc_ads_golden_lrc_size(ads) -
- xe_lrc_skip_size(xe));
+ real_size - xe_lrc_skip_size(xe));
ads_blob_write(ads, ads.golden_context_lrca[guc_class],
- xe_bo_ggtt_addr(ads->bo) +
- guc_ads_golden_lrc_offset(ads));
+ addr_ggtt);
+
+ addr_ggtt += alloc_size;
}
}
@@ -857,7 +885,7 @@ void xe_guc_ads_populate_minimal(struct xe_guc_ads *ads)
xe_map_memset(ads_to_xe(ads), ads_to_map(ads), 0, 0, ads->bo->size);
guc_policies_init(ads);
- guc_prep_golden_lrc_null(ads);
+ guc_golden_lrc_init(ads);
guc_mapping_table_init_invalid(gt, &info_map);
guc_doorbell_init(ads);
@@ -883,7 +911,7 @@ void xe_guc_ads_populate(struct xe_guc_ads *ads)
guc_policies_init(ads);
fill_engine_enable_masks(gt, &info_map);
guc_mmio_reg_state_init(ads);
- guc_prep_golden_lrc_null(ads);
+ guc_golden_lrc_init(ads);
guc_mapping_table_init(gt, &info_map);
guc_capture_prep_lists(ads);
guc_doorbell_init(ads);
@@ -903,18 +931,22 @@ void xe_guc_ads_populate(struct xe_guc_ads *ads)
guc_ads_private_data_offset(ads));
}
-static void guc_populate_golden_lrc(struct xe_guc_ads *ads)
+/*
+ * After the golden LRC's are recorded for each engine class by the first
+ * submission, copy them to the ADS, as initialized earlier by
+ * guc_golden_lrc_init().
+ */
+static void guc_golden_lrc_populate(struct xe_guc_ads *ads)
{
struct xe_device *xe = ads_to_xe(ads);
struct xe_gt *gt = ads_to_gt(ads);
struct iosys_map info_map = IOSYS_MAP_INIT_OFFSET(ads_to_map(ads),
offsetof(struct __guc_ads_blob, system_info));
size_t total_size = 0, alloc_size, real_size;
- u32 addr_ggtt, offset;
+ u32 offset;
int class;
offset = guc_ads_golden_lrc_offset(ads);
- addr_ggtt = xe_bo_ggtt_addr(ads->bo) + offset;
for (class = 0; class < XE_ENGINE_CLASS_MAX; ++class) {
u8 guc_class;
@@ -931,26 +963,9 @@ static void guc_populate_golden_lrc(struct xe_guc_ads *ads)
alloc_size = PAGE_ALIGN(real_size);
total_size += alloc_size;
- /*
- * This interface is slightly confusing. We need to pass the
- * base address of the full golden context and the size of just
- * the engine state, which is the section of the context image
- * that starts after the execlists LRC registers. This is
- * required to allow the GuC to restore just the engine state
- * when a watchdog reset occurs.
- * We calculate the engine state size by removing the size of
- * what comes before it in the context image (which is identical
- * on all engines).
- */
- ads_blob_write(ads, ads.eng_state_size[guc_class],
- real_size - xe_lrc_skip_size(xe));
- ads_blob_write(ads, ads.golden_context_lrca[guc_class],
- addr_ggtt);
-
xe_map_memcpy_to(xe, ads_to_map(ads), offset,
gt->default_lrc[class], real_size);
- addr_ggtt += alloc_size;
offset += alloc_size;
}
@@ -959,7 +974,7 @@ static void guc_populate_golden_lrc(struct xe_guc_ads *ads)
void xe_guc_ads_populate_post_load(struct xe_guc_ads *ads)
{
- guc_populate_golden_lrc(ads);
+ guc_golden_lrc_populate(ads);
}
static int guc_ads_action_update_policies(struct xe_guc_ads *ads, u32 policy_offset)
diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index 8521531..43b1192 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -1070,6 +1070,7 @@ int xe_guc_pc_start(struct xe_guc_pc *pc)
if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING,
SLPC_RESET_EXTENDED_TIMEOUT_MS)) {
xe_gt_err(gt, "GuC PC Start failed: Dynamic GT frequency control and GT sleep states are now disabled.\n");
+ ret = -EIO;
goto out;
}
diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c
index c3cc0fa..57b7195 100644
--- a/drivers/gpu/drm/xe/xe_hmm.c
+++ b/drivers/gpu/drm/xe/xe_hmm.c
@@ -19,29 +19,6 @@ static u64 xe_npages_in_range(unsigned long start, unsigned long end)
return (end - start) >> PAGE_SHIFT;
}
-/**
- * xe_mark_range_accessed() - mark a range is accessed, so core mm
- * have such information for memory eviction or write back to
- * hard disk
- * @range: the range to mark
- * @write: if write to this range, we mark pages in this range
- * as dirty
- */
-static void xe_mark_range_accessed(struct hmm_range *range, bool write)
-{
- struct page *page;
- u64 i, npages;
-
- npages = xe_npages_in_range(range->start, range->end);
- for (i = 0; i < npages; i++) {
- page = hmm_pfn_to_page(range->hmm_pfns[i]);
- if (write)
- set_page_dirty_lock(page);
-
- mark_page_accessed(page);
- }
-}
-
static int xe_alloc_sg(struct xe_device *xe, struct sg_table *st,
struct hmm_range *range, struct rw_semaphore *notifier_sem)
{
@@ -331,7 +308,6 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma,
if (ret)
goto out_unlock;
- xe_mark_range_accessed(&hmm_range, write);
userptr->sg = &userptr->sgt;
xe_hmm_userptr_set_mapped(uvma);
userptr->notifier_seq = hmm_range.notifier_seq;
diff --git a/drivers/gpu/drm/xe/xe_hw_engine.c b/drivers/gpu/drm/xe/xe_hw_engine.c
index 8c05fd3..93241fd 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine.c
+++ b/drivers/gpu/drm/xe/xe_hw_engine.c
@@ -389,12 +389,6 @@ xe_hw_engine_setup_default_lrc_state(struct xe_hw_engine *hwe)
blit_cctl_val,
XE_RTP_ACTION_FLAG(ENGINE_BASE)))
},
- /* Use Fixed slice CCS mode */
- { XE_RTP_NAME("RCU_MODE_FIXED_SLICE_CCS_MODE"),
- XE_RTP_RULES(FUNC(xe_hw_engine_match_fixed_cslice_mode)),
- XE_RTP_ACTIONS(FIELD_SET(RCU_MODE, RCU_MODE_FIXED_SLICE_CCS_MODE,
- RCU_MODE_FIXED_SLICE_CCS_MODE))
- },
/* Disable WMTP if HW doesn't support it */
{ XE_RTP_NAME("DISABLE_WMTP_ON_UNSUPPORTED_HW"),
XE_RTP_RULES(FUNC(xe_rtp_cfeg_wmtp_disabled)),
@@ -461,6 +455,12 @@ hw_engine_setup_default_state(struct xe_hw_engine *hwe)
XE_RTP_ACTIONS(SET(CSFE_CHICKEN1(0), CS_PRIORITY_MEM_READ,
XE_RTP_ACTION_FLAG(ENGINE_BASE)))
},
+ /* Use Fixed slice CCS mode */
+ { XE_RTP_NAME("RCU_MODE_FIXED_SLICE_CCS_MODE"),
+ XE_RTP_RULES(FUNC(xe_hw_engine_match_fixed_cslice_mode)),
+ XE_RTP_ACTIONS(FIELD_SET(RCU_MODE, RCU_MODE_FIXED_SLICE_CCS_MODE,
+ RCU_MODE_FIXED_SLICE_CCS_MODE))
+ },
};
xe_rtp_process_to_sr(&ctx, engine_entries, ARRAY_SIZE(engine_entries), &hwe->reg_sr);
diff --git a/drivers/gpu/drm/xe/xe_hw_engine_class_sysfs.c b/drivers/gpu/drm/xe/xe_hw_engine_class_sysfs.c
index b53e8d2..a440442 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine_class_sysfs.c
+++ b/drivers/gpu/drm/xe/xe_hw_engine_class_sysfs.c
@@ -32,14 +32,61 @@ bool xe_hw_engine_timeout_in_range(u64 timeout, u64 min, u64 max)
return timeout >= min && timeout <= max;
}
-static void kobj_xe_hw_engine_release(struct kobject *kobj)
+static void xe_hw_engine_sysfs_kobj_release(struct kobject *kobj)
{
kfree(kobj);
}
+static ssize_t xe_hw_engine_class_sysfs_attr_show(struct kobject *kobj,
+ struct attribute *attr,
+ char *buf)
+{
+ struct xe_device *xe = kobj_to_xe(kobj);
+ struct kobj_attribute *kattr;
+ ssize_t ret = -EIO;
+
+ kattr = container_of(attr, struct kobj_attribute, attr);
+ if (kattr->show) {
+ xe_pm_runtime_get(xe);
+ ret = kattr->show(kobj, kattr, buf);
+ xe_pm_runtime_put(xe);
+ }
+
+ return ret;
+}
+
+static ssize_t xe_hw_engine_class_sysfs_attr_store(struct kobject *kobj,
+ struct attribute *attr,
+ const char *buf,
+ size_t count)
+{
+ struct xe_device *xe = kobj_to_xe(kobj);
+ struct kobj_attribute *kattr;
+ ssize_t ret = -EIO;
+
+ kattr = container_of(attr, struct kobj_attribute, attr);
+ if (kattr->store) {
+ xe_pm_runtime_get(xe);
+ ret = kattr->store(kobj, kattr, buf, count);
+ xe_pm_runtime_put(xe);
+ }
+
+ return ret;
+}
+
+static const struct sysfs_ops xe_hw_engine_class_sysfs_ops = {
+ .show = xe_hw_engine_class_sysfs_attr_show,
+ .store = xe_hw_engine_class_sysfs_attr_store,
+};
+
static const struct kobj_type kobj_xe_hw_engine_type = {
- .release = kobj_xe_hw_engine_release,
- .sysfs_ops = &kobj_sysfs_ops
+ .release = xe_hw_engine_sysfs_kobj_release,
+ .sysfs_ops = &xe_hw_engine_class_sysfs_ops,
+};
+
+static const struct kobj_type kobj_xe_hw_engine_type_def = {
+ .release = xe_hw_engine_sysfs_kobj_release,
+ .sysfs_ops = &kobj_sysfs_ops,
};
static ssize_t job_timeout_max_store(struct kobject *kobj,
@@ -543,7 +590,7 @@ static int xe_add_hw_engine_class_defaults(struct xe_device *xe,
if (!kobj)
return -ENOMEM;
- kobject_init(kobj, &kobj_xe_hw_engine_type);
+ kobject_init(kobj, &kobj_xe_hw_engine_type_def);
err = kobject_add(kobj, parent, "%s", ".defaults");
if (err)
goto err_object;
@@ -559,57 +606,6 @@ static int xe_add_hw_engine_class_defaults(struct xe_device *xe,
return err;
}
-static void xe_hw_engine_sysfs_kobj_release(struct kobject *kobj)
-{
- kfree(kobj);
-}
-
-static ssize_t xe_hw_engine_class_sysfs_attr_show(struct kobject *kobj,
- struct attribute *attr,
- char *buf)
-{
- struct xe_device *xe = kobj_to_xe(kobj);
- struct kobj_attribute *kattr;
- ssize_t ret = -EIO;
-
- kattr = container_of(attr, struct kobj_attribute, attr);
- if (kattr->show) {
- xe_pm_runtime_get(xe);
- ret = kattr->show(kobj, kattr, buf);
- xe_pm_runtime_put(xe);
- }
-
- return ret;
-}
-
-static ssize_t xe_hw_engine_class_sysfs_attr_store(struct kobject *kobj,
- struct attribute *attr,
- const char *buf,
- size_t count)
-{
- struct xe_device *xe = kobj_to_xe(kobj);
- struct kobj_attribute *kattr;
- ssize_t ret = -EIO;
-
- kattr = container_of(attr, struct kobj_attribute, attr);
- if (kattr->store) {
- xe_pm_runtime_get(xe);
- ret = kattr->store(kobj, kattr, buf, count);
- xe_pm_runtime_put(xe);
- }
-
- return ret;
-}
-
-static const struct sysfs_ops xe_hw_engine_class_sysfs_ops = {
- .show = xe_hw_engine_class_sysfs_attr_show,
- .store = xe_hw_engine_class_sysfs_attr_store,
-};
-
-static const struct kobj_type xe_hw_engine_sysfs_kobj_type = {
- .release = xe_hw_engine_sysfs_kobj_release,
- .sysfs_ops = &xe_hw_engine_class_sysfs_ops,
-};
static void hw_engine_class_sysfs_fini(void *arg)
{
@@ -640,7 +636,7 @@ int xe_hw_engine_class_sysfs_init(struct xe_gt *gt)
if (!kobj)
return -ENOMEM;
- kobject_init(kobj, &xe_hw_engine_sysfs_kobj_type);
+ kobject_init(kobj, &kobj_xe_hw_engine_type);
err = kobject_add(kobj, gt->sysfs, "engines");
if (err)
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index df4282c..5a3e890 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -1177,7 +1177,7 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
err_sync:
/* Sync partial copies if any. FIXME: job_mutex? */
if (fence) {
- dma_fence_wait(m->fence, false);
+ dma_fence_wait(fence, false);
dma_fence_put(fence);
}
@@ -1547,7 +1547,7 @@ void xe_migrate_wait(struct xe_migrate *m)
static u32 pte_update_cmd_size(u64 size)
{
u32 num_dword;
- u64 entries = DIV_ROUND_UP(size, XE_PAGE_SIZE);
+ u64 entries = DIV_U64_ROUND_UP(size, XE_PAGE_SIZE);
XE_WARN_ON(size > MAX_PREEMPTDISABLE_TRANSFER);
/*
@@ -1558,7 +1558,7 @@ static u32 pte_update_cmd_size(u64 size)
* 2 dword for the page table's physical location
* 2*n dword for value of pte to fill (each pte entry is 2 dwords)
*/
- num_dword = (1 + 2) * DIV_ROUND_UP(entries, 0x1ff);
+ num_dword = (1 + 2) * DIV_U64_ROUND_UP(entries, 0x1ff);
num_dword += entries * 2;
return num_dword;
diff --git a/drivers/gpu/drm/xe/xe_pxp_debugfs.c b/drivers/gpu/drm/xe/xe_pxp_debugfs.c
index ccfbacf..525a2f6 100644
--- a/drivers/gpu/drm/xe/xe_pxp_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_pxp_debugfs.c
@@ -66,9 +66,18 @@ static int pxp_terminate(struct seq_file *m, void *data)
{
struct xe_pxp *pxp = node_to_pxp(m->private);
struct drm_printer p = drm_seq_file_printer(m);
+ int ready = xe_pxp_get_readiness_status(pxp);
- if (!xe_pxp_is_enabled(pxp))
- return -ENODEV;
+ if (ready < 0)
+ return ready; /* disabled or error occurred */
+ else if (!ready)
+ return -EBUSY; /* init still in progress */
+
+ /* no need for a termination if PXP is not active */
+ if (pxp->status != XE_PXP_ACTIVE) {
+ drm_printf(&p, "PXP not active\n");
+ return 0;
+ }
/* simulate a termination interrupt */
spin_lock_irq(&pxp->xe->irq.lock);
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index 917fc16..a7582b0 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -137,7 +137,8 @@ emit_pipe_control(u32 *dw, int i, u32 bit_group_0, u32 bit_group_1, u32 offset,
static int emit_pipe_invalidate(u32 mask_flags, bool invalidate_tlb, u32 *dw,
int i)
{
- u32 flags = PIPE_CONTROL_CS_STALL |
+ u32 flags0 = 0;
+ u32 flags1 = PIPE_CONTROL_CS_STALL |
PIPE_CONTROL_COMMAND_CACHE_INVALIDATE |
PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE |
PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE |
@@ -148,11 +149,15 @@ static int emit_pipe_invalidate(u32 mask_flags, bool invalidate_tlb, u32 *dw,
PIPE_CONTROL_STORE_DATA_INDEX;
if (invalidate_tlb)
- flags |= PIPE_CONTROL_TLB_INVALIDATE;
+ flags1 |= PIPE_CONTROL_TLB_INVALIDATE;
- flags &= ~mask_flags;
+ flags1 &= ~mask_flags;
- return emit_pipe_control(dw, i, 0, flags, LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR, 0);
+ if (flags1 & PIPE_CONTROL_VF_CACHE_INVALIDATE)
+ flags0 |= PIPE_CONTROL0_L3_READ_ONLY_CACHE_INVALIDATE;
+
+ return emit_pipe_control(dw, i, flags0, flags1,
+ LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR, 0);
}
static int emit_store_imm_ppgtt_posted(u64 addr, u64 value,
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index 3e829c87..f8c1285 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -696,11 +696,14 @@ static int xe_svm_alloc_vram(struct xe_vm *vm, struct xe_tile *tile,
list_for_each_entry(block, blocks, link)
block->private = vr;
+ xe_bo_get(bo);
err = drm_gpusvm_migrate_to_devmem(&vm->svm.gpusvm, &range->base,
&bo->devmem_allocation, ctx);
- xe_bo_unlock(bo);
if (err)
- xe_bo_put(bo); /* Creation ref */
+ xe_svm_devmem_release(&bo->devmem_allocation);
+
+ xe_bo_unlock(bo);
+ xe_bo_put(bo);
unlock:
mmap_read_unlock(mm);
diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
index 0c738af..9b9e176 100644
--- a/drivers/gpu/drm/xe/xe_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
@@ -32,8 +32,10 @@
GRAPHICS_VERSION(3001)
14022293748 GRAPHICS_VERSION(2001)
GRAPHICS_VERSION(2004)
+ GRAPHICS_VERSION_RANGE(3000, 3001)
22019794406 GRAPHICS_VERSION(2001)
GRAPHICS_VERSION(2004)
+ GRAPHICS_VERSION_RANGE(3000, 3001)
22019338487 MEDIA_VERSION(2000)
GRAPHICS_VERSION(2001)
MEDIA_VERSION(3000), MEDIA_STEP(A0, B0), FUNC(xe_rtp_match_not_sriov_vf)
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index b3b11be..59792e0 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -307,7 +307,7 @@ void __init hv_get_partition_id(void)
local_irq_save(flags);
output = *this_cpu_ptr(hyperv_pcpu_input_arg);
- status = hv_do_hypercall(HVCALL_GET_PARTITION_ID, NULL, &output);
+ status = hv_do_hypercall(HVCALL_GET_PARTITION_ID, NULL, output);
pt_id = output->partition_id;
local_irq_restore(flags);
@@ -566,9 +566,11 @@ int hv_common_cpu_die(unsigned int cpu)
* originally allocated memory is reused in hv_common_cpu_init().
*/
- synic_eventring_tail = this_cpu_ptr(hv_synic_eventring_tail);
- kfree(*synic_eventring_tail);
- *synic_eventring_tail = NULL;
+ if (hv_root_partition()) {
+ synic_eventring_tail = this_cpu_ptr(hv_synic_eventring_tail);
+ kfree(*synic_eventring_tail);
+ *synic_eventring_tail = NULL;
+ }
return 0;
}
diff --git a/drivers/hwtracing/intel_th/Kconfig b/drivers/hwtracing/intel_th/Kconfig
index 4b63593..4f7d2b6 100644
--- a/drivers/hwtracing/intel_th/Kconfig
+++ b/drivers/hwtracing/intel_th/Kconfig
@@ -60,6 +60,7 @@
config INTEL_TH_MSU
tristate "Intel(R) Trace Hub Memory Storage Unit"
+ depends on MMU
help
Memory Storage Unit (MSU) trace output device enables
storing STP traces to system memory. It supports single
diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index bf99d79..7163950 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -19,6 +19,7 @@
#include <linux/io.h>
#include <linux/workqueue.h>
#include <linux/dma-mapping.h>
+#include <linux/pfn_t.h>
#ifdef CONFIG_X86
#include <asm/set_memory.h>
@@ -976,7 +977,6 @@ static void msc_buffer_contig_free(struct msc *msc)
for (off = 0; off < msc->nr_pages << PAGE_SHIFT; off += PAGE_SIZE) {
struct page *page = virt_to_page(msc->base + off);
- page->mapping = NULL;
__free_page(page);
}
@@ -1158,9 +1158,6 @@ static void __msc_buffer_win_free(struct msc *msc, struct msc_window *win)
int i;
for_each_sg(win->sgt->sgl, sg, win->nr_segs, i) {
- struct page *page = msc_sg_page(sg);
-
- page->mapping = NULL;
dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE,
sg_virt(sg), sg_dma_address(sg));
}
@@ -1601,22 +1598,10 @@ static void msc_mmap_close(struct vm_area_struct *vma)
{
struct msc_iter *iter = vma->vm_file->private_data;
struct msc *msc = iter->msc;
- unsigned long pg;
if (!atomic_dec_and_mutex_lock(&msc->mmap_count, &msc->buf_mutex))
return;
- /* drop page _refcounts */
- for (pg = 0; pg < msc->nr_pages; pg++) {
- struct page *page = msc_buffer_get_page(msc, pg);
-
- if (WARN_ON_ONCE(!page))
- continue;
-
- if (page->mapping)
- page->mapping = NULL;
- }
-
/* last mapping -- drop user_count */
atomic_dec(&msc->user_count);
mutex_unlock(&msc->buf_mutex);
@@ -1626,16 +1611,14 @@ static vm_fault_t msc_mmap_fault(struct vm_fault *vmf)
{
struct msc_iter *iter = vmf->vma->vm_file->private_data;
struct msc *msc = iter->msc;
+ struct page *page;
- vmf->page = msc_buffer_get_page(msc, vmf->pgoff);
- if (!vmf->page)
+ page = msc_buffer_get_page(msc, vmf->pgoff);
+ if (!page)
return VM_FAULT_SIGBUS;
- get_page(vmf->page);
- vmf->page->mapping = vmf->vma->vm_file->f_mapping;
- vmf->page->index = vmf->pgoff;
-
- return 0;
+ get_page(page);
+ return vmf_insert_mixed(vmf->vma, vmf->address, page_to_pfn_t(page));
}
static const struct vm_operations_struct msc_mmap_ops = {
@@ -1676,7 +1659,7 @@ static int intel_th_msc_mmap(struct file *file, struct vm_area_struct *vma)
atomic_dec(&msc->user_count);
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
- vm_flags_set(vma, VM_DONTEXPAND | VM_DONTCOPY);
+ vm_flags_set(vma, VM_DONTEXPAND | VM_DONTCOPY | VM_MIXEDMAP);
vma->vm_ops = &msc_mmap_ops;
return ret;
}
diff --git a/drivers/i2c/busses/i2c-cros-ec-tunnel.c b/drivers/i2c/busses/i2c-cros-ec-tunnel.c
index 43bf90d..208ce4f 100644
--- a/drivers/i2c/busses/i2c-cros-ec-tunnel.c
+++ b/drivers/i2c/busses/i2c-cros-ec-tunnel.c
@@ -247,6 +247,9 @@ static int ec_i2c_probe(struct platform_device *pdev)
u32 remote_bus;
int err;
+ if (!ec)
+ return dev_err_probe(dev, -EPROBE_DEFER, "couldn't find parent EC device\n");
+
if (!ec->cmd_xfer) {
dev_err(dev, "Missing sendrecv\n");
return -EINVAL;
diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c
index 0d4b393..342d47e 100644
--- a/drivers/i2c/busses/i2c-imx-lpi2c.c
+++ b/drivers/i2c/busses/i2c-imx-lpi2c.c
@@ -1380,9 +1380,9 @@ static int lpi2c_imx_probe(struct platform_device *pdev)
return 0;
rpm_disable:
- pm_runtime_put(&pdev->dev);
- pm_runtime_disable(&pdev->dev);
pm_runtime_dont_use_autosuspend(&pdev->dev);
+ pm_runtime_put_sync(&pdev->dev);
+ pm_runtime_disable(&pdev->dev);
return ret;
}
diff --git a/drivers/i2c/i2c-atr.c b/drivers/i2c/i2c-atr.c
index 8fe9ddf..783fb8d 100644
--- a/drivers/i2c/i2c-atr.c
+++ b/drivers/i2c/i2c-atr.c
@@ -8,12 +8,12 @@
* Originally based on i2c-mux.c
*/
-#include <linux/fwnode.h>
#include <linux/i2c-atr.h>
#include <linux/i2c.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/mutex.h>
+#include <linux/property.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
diff --git a/drivers/iio/accel/adis16201.c b/drivers/iio/accel/adis16201.c
index 8601b9a8..5127e58 100644
--- a/drivers/iio/accel/adis16201.c
+++ b/drivers/iio/accel/adis16201.c
@@ -211,9 +211,9 @@ static const struct iio_chan_spec adis16201_channels[] = {
BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14),
ADIS_AUX_ADC_CHAN(ADIS16201_AUX_ADC_REG, ADIS16201_SCAN_AUX_ADC, 0, 12),
ADIS_INCLI_CHAN(X, ADIS16201_XINCL_OUT_REG, ADIS16201_SCAN_INCLI_X,
- BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14),
+ BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 12),
ADIS_INCLI_CHAN(Y, ADIS16201_YINCL_OUT_REG, ADIS16201_SCAN_INCLI_Y,
- BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14),
+ BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 12),
IIO_CHAN_SOFT_TIMESTAMP(7)
};
diff --git a/drivers/iio/accel/adxl355_core.c b/drivers/iio/accel/adxl355_core.c
index e8cd21fa..cbac622 100644
--- a/drivers/iio/accel/adxl355_core.c
+++ b/drivers/iio/accel/adxl355_core.c
@@ -231,7 +231,7 @@ struct adxl355_data {
u8 transf_buf[3];
struct {
u8 buf[14];
- s64 ts;
+ aligned_s64 ts;
} buffer;
} __aligned(IIO_DMA_MINALIGN);
};
diff --git a/drivers/iio/accel/adxl367.c b/drivers/iio/accel/adxl367.c
index add4053..0c04b2b 100644
--- a/drivers/iio/accel/adxl367.c
+++ b/drivers/iio/accel/adxl367.c
@@ -601,18 +601,14 @@ static int _adxl367_set_odr(struct adxl367_state *st, enum adxl367_odr odr)
if (ret)
return ret;
+ st->odr = odr;
+
/* Activity timers depend on ODR */
ret = _adxl367_set_act_time_ms(st, st->act_time_ms);
if (ret)
return ret;
- ret = _adxl367_set_inact_time_ms(st, st->inact_time_ms);
- if (ret)
- return ret;
-
- st->odr = odr;
-
- return 0;
+ return _adxl367_set_inact_time_ms(st, st->inact_time_ms);
}
static int adxl367_set_odr(struct iio_dev *indio_dev, enum adxl367_odr odr)
diff --git a/drivers/iio/accel/fxls8962af-core.c b/drivers/iio/accel/fxls8962af-core.c
index 48e4282..bf1d392 100644
--- a/drivers/iio/accel/fxls8962af-core.c
+++ b/drivers/iio/accel/fxls8962af-core.c
@@ -1226,8 +1226,11 @@ int fxls8962af_core_probe(struct device *dev, struct regmap *regmap, int irq)
if (ret)
return ret;
- if (device_property_read_bool(dev, "wakeup-source"))
- device_init_wakeup(dev, true);
+ if (device_property_read_bool(dev, "wakeup-source")) {
+ ret = devm_device_init_wakeup(dev);
+ if (ret)
+ return dev_err_probe(dev, ret, "Failed to init wakeup\n");
+ }
return devm_iio_device_register(dev, indio_dev);
}
diff --git a/drivers/iio/adc/ad7266.c b/drivers/iio/adc/ad7266.c
index 1855975..7fef272 100644
--- a/drivers/iio/adc/ad7266.c
+++ b/drivers/iio/adc/ad7266.c
@@ -45,7 +45,7 @@ struct ad7266_state {
*/
struct {
__be16 sample[2];
- s64 timestamp;
+ aligned_s64 timestamp;
} data __aligned(IIO_DMA_MINALIGN);
};
diff --git a/drivers/iio/adc/ad7380.c b/drivers/iio/adc/ad7380.c
index 4fcb49f..aef8509 100644
--- a/drivers/iio/adc/ad7380.c
+++ b/drivers/iio/adc/ad7380.c
@@ -1211,6 +1211,9 @@ static int ad7380_offload_buffer_predisable(struct iio_dev *indio_dev)
struct ad7380_state *st = iio_priv(indio_dev);
int ret;
+ spi_offload_trigger_disable(st->offload, st->offload_trigger);
+ spi_unoptimize_message(&st->offload_msg);
+
if (st->seq) {
ret = regmap_update_bits(st->regmap,
AD7380_REG_ADDR_CONFIG1,
@@ -1222,10 +1225,6 @@ static int ad7380_offload_buffer_predisable(struct iio_dev *indio_dev)
st->seq = false;
}
- spi_offload_trigger_disable(st->offload, st->offload_trigger);
-
- spi_unoptimize_message(&st->offload_msg);
-
return 0;
}
@@ -1611,11 +1610,25 @@ static int ad7380_write_event_config(struct iio_dev *indio_dev,
return ret;
}
-static int ad7380_get_alert_th(struct ad7380_state *st,
+static int ad7380_get_alert_th(struct iio_dev *indio_dev,
+ const struct iio_chan_spec *chan,
enum iio_event_direction dir,
int *val)
{
- int ret, tmp;
+ struct ad7380_state *st = iio_priv(indio_dev);
+ const struct iio_scan_type *scan_type;
+ int ret, tmp, shift;
+
+ scan_type = iio_get_current_scan_type(indio_dev, chan);
+ if (IS_ERR(scan_type))
+ return PTR_ERR(scan_type);
+
+ /*
+ * The register value is 12-bits and is compared to the most significant
+ * bits of raw value, therefore a shift is required to convert this to
+ * the same scale as the raw value.
+ */
+ shift = scan_type->realbits - 12;
switch (dir) {
case IIO_EV_DIR_RISING:
@@ -1625,7 +1638,7 @@ static int ad7380_get_alert_th(struct ad7380_state *st,
if (ret)
return ret;
- *val = FIELD_GET(AD7380_ALERT_HIGH_TH, tmp);
+ *val = FIELD_GET(AD7380_ALERT_HIGH_TH, tmp) << shift;
return IIO_VAL_INT;
case IIO_EV_DIR_FALLING:
ret = regmap_read(st->regmap,
@@ -1634,7 +1647,7 @@ static int ad7380_get_alert_th(struct ad7380_state *st,
if (ret)
return ret;
- *val = FIELD_GET(AD7380_ALERT_LOW_TH, tmp);
+ *val = FIELD_GET(AD7380_ALERT_LOW_TH, tmp) << shift;
return IIO_VAL_INT;
default:
return -EINVAL;
@@ -1648,7 +1661,6 @@ static int ad7380_read_event_value(struct iio_dev *indio_dev,
enum iio_event_info info,
int *val, int *val2)
{
- struct ad7380_state *st = iio_priv(indio_dev);
int ret;
switch (info) {
@@ -1656,7 +1668,7 @@ static int ad7380_read_event_value(struct iio_dev *indio_dev,
if (!iio_device_claim_direct(indio_dev))
return -EBUSY;
- ret = ad7380_get_alert_th(st, dir, val);
+ ret = ad7380_get_alert_th(indio_dev, chan, dir, val);
iio_device_release_direct(indio_dev);
return ret;
diff --git a/drivers/iio/adc/ad7606.c b/drivers/iio/adc/ad7606.c
index 1a314fd..703556e 100644
--- a/drivers/iio/adc/ad7606.c
+++ b/drivers/iio/adc/ad7606.c
@@ -1236,9 +1236,11 @@ static int ad7616_sw_mode_setup(struct iio_dev *indio_dev)
st->write_scale = ad7616_write_scale_sw;
st->write_os = &ad7616_write_os_sw;
- ret = st->bops->sw_mode_config(indio_dev);
- if (ret)
- return ret;
+ if (st->bops->sw_mode_config) {
+ ret = st->bops->sw_mode_config(indio_dev);
+ if (ret)
+ return ret;
+ }
/* Activate Burst mode and SEQEN MODE */
return ad7606_write_mask(st, AD7616_CONFIGURATION_REGISTER,
@@ -1268,6 +1270,9 @@ static int ad7606b_sw_mode_setup(struct iio_dev *indio_dev)
st->write_scale = ad7606_write_scale_sw;
st->write_os = &ad7606_write_os_sw;
+ if (!st->bops->sw_mode_config)
+ return 0;
+
return st->bops->sw_mode_config(indio_dev);
}
diff --git a/drivers/iio/adc/ad7606_spi.c b/drivers/iio/adc/ad7606_spi.c
index 885bf0b..179115e 100644
--- a/drivers/iio/adc/ad7606_spi.c
+++ b/drivers/iio/adc/ad7606_spi.c
@@ -131,7 +131,7 @@ static int ad7606_spi_reg_read(struct ad7606_state *st, unsigned int addr)
{
.tx_buf = &st->d16[0],
.len = 2,
- .cs_change = 0,
+ .cs_change = 1,
}, {
.rx_buf = &st->d16[1],
.len = 2,
diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c
index 5a86300..5e0be36 100644
--- a/drivers/iio/adc/ad7768-1.c
+++ b/drivers/iio/adc/ad7768-1.c
@@ -168,7 +168,7 @@ struct ad7768_state {
union {
struct {
__be32 chan;
- s64 timestamp;
+ aligned_s64 timestamp;
} scan;
__be32 d32;
u8 d8[2];
diff --git a/drivers/iio/adc/dln2-adc.c b/drivers/iio/adc/dln2-adc.c
index a1e48a7..359e26e 100644
--- a/drivers/iio/adc/dln2-adc.c
+++ b/drivers/iio/adc/dln2-adc.c
@@ -466,7 +466,7 @@ static irqreturn_t dln2_adc_trigger_h(int irq, void *p)
struct iio_dev *indio_dev = pf->indio_dev;
struct {
__le16 values[DLN2_ADC_MAX_CHANNELS];
- int64_t timestamp_space;
+ aligned_s64 timestamp_space;
} data;
struct dln2_adc_get_all_vals dev_data;
struct dln2_adc *dln2 = iio_priv(indio_dev);
diff --git a/drivers/iio/adc/qcom-spmi-iadc.c b/drivers/iio/adc/qcom-spmi-iadc.c
index 7fb8b24..b64a8a4 100644
--- a/drivers/iio/adc/qcom-spmi-iadc.c
+++ b/drivers/iio/adc/qcom-spmi-iadc.c
@@ -543,7 +543,9 @@ static int iadc_probe(struct platform_device *pdev)
else
return ret;
} else {
- device_init_wakeup(iadc->dev, 1);
+ ret = devm_device_init_wakeup(iadc->dev);
+ if (ret)
+ return dev_err_probe(iadc->dev, ret, "Failed to init wakeup\n");
}
ret = iadc_update_offset(iadc);
diff --git a/drivers/iio/adc/rockchip_saradc.c b/drivers/iio/adc/rockchip_saradc.c
index 9a099df..5e28bd2 100644
--- a/drivers/iio/adc/rockchip_saradc.c
+++ b/drivers/iio/adc/rockchip_saradc.c
@@ -520,15 +520,6 @@ static int rockchip_saradc_probe(struct platform_device *pdev)
if (info->reset)
rockchip_saradc_reset_controller(info->reset);
- /*
- * Use a default value for the converter clock.
- * This may become user-configurable in the future.
- */
- ret = clk_set_rate(info->clk, info->data->clk_rate);
- if (ret < 0)
- return dev_err_probe(&pdev->dev, ret,
- "failed to set adc clk rate\n");
-
ret = regulator_enable(info->vref);
if (ret < 0)
return dev_err_probe(&pdev->dev, ret,
@@ -555,6 +546,14 @@ static int rockchip_saradc_probe(struct platform_device *pdev)
if (IS_ERR(info->clk))
return dev_err_probe(&pdev->dev, PTR_ERR(info->clk),
"failed to get adc clock\n");
+ /*
+ * Use a default value for the converter clock.
+ * This may become user-configurable in the future.
+ */
+ ret = clk_set_rate(info->clk, info->data->clk_rate);
+ if (ret < 0)
+ return dev_err_probe(&pdev->dev, ret,
+ "failed to set adc clk rate\n");
platform_set_drvdata(pdev, indio_dev);
diff --git a/drivers/iio/chemical/pms7003.c b/drivers/iio/chemical/pms7003.c
index d0bd949..e05ce1f 100644
--- a/drivers/iio/chemical/pms7003.c
+++ b/drivers/iio/chemical/pms7003.c
@@ -5,7 +5,6 @@
* Copyright (c) Tomasz Duszynski <tduszyns@gmail.com>
*/
-#include <linux/unaligned.h>
#include <linux/completion.h>
#include <linux/device.h>
#include <linux/errno.h>
@@ -19,6 +18,8 @@
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/serdev.h>
+#include <linux/types.h>
+#include <linux/unaligned.h>
#define PMS7003_DRIVER_NAME "pms7003"
@@ -76,7 +77,7 @@ struct pms7003_state {
/* Used to construct scan to push to the IIO buffer */
struct {
u16 data[3]; /* PM1, PM2P5, PM10 */
- s64 ts;
+ aligned_s64 ts;
} scan;
};
diff --git a/drivers/iio/chemical/sps30.c b/drivers/iio/chemical/sps30.c
index 6f4f2ba..a788814 100644
--- a/drivers/iio/chemical/sps30.c
+++ b/drivers/iio/chemical/sps30.c
@@ -108,7 +108,7 @@ static irqreturn_t sps30_trigger_handler(int irq, void *p)
int ret;
struct {
s32 data[4]; /* PM1, PM2P5, PM4, PM10 */
- s64 ts;
+ aligned_s64 ts;
} scan;
mutex_lock(&state->lock);
diff --git a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
index ad1882f..2055a03 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
@@ -66,6 +66,10 @@ static struct {
{HID_USAGE_SENSOR_HUMIDITY, 0, 1000, 0},
{HID_USAGE_SENSOR_HINGE, 0, 0, 17453293},
{HID_USAGE_SENSOR_HINGE, HID_USAGE_SENSOR_UNITS_DEGREES, 0, 17453293},
+
+ {HID_USAGE_SENSOR_HUMAN_PRESENCE, 0, 1, 0},
+ {HID_USAGE_SENSOR_HUMAN_PROXIMITY, 0, 1, 0},
+ {HID_USAGE_SENSOR_HUMAN_ATTENTION, 0, 1, 0},
};
static void simple_div(int dividend, int divisor, int *whole,
diff --git a/drivers/iio/imu/adis16550.c b/drivers/iio/imu/adis16550.c
index b14ea89..28f0dbd 100644
--- a/drivers/iio/imu/adis16550.c
+++ b/drivers/iio/imu/adis16550.c
@@ -836,7 +836,7 @@ static irqreturn_t adis16550_trigger_handler(int irq, void *p)
u16 dummy;
bool valid;
struct iio_poll_func *pf = p;
- __be32 data[ADIS16550_MAX_SCAN_DATA];
+ __be32 data[ADIS16550_MAX_SCAN_DATA] __aligned(8);
struct iio_dev *indio_dev = pf->indio_dev;
struct adis16550 *st = iio_priv(indio_dev);
struct adis *adis = iio_device_get_drvdata(indio_dev);
diff --git a/drivers/iio/imu/bmi270/bmi270_core.c b/drivers/iio/imu/bmi270/bmi270_core.c
index a86be5a..2e4469f 100644
--- a/drivers/iio/imu/bmi270/bmi270_core.c
+++ b/drivers/iio/imu/bmi270/bmi270_core.c
@@ -918,8 +918,7 @@ static int bmi270_configure_imu(struct bmi270_data *data)
FIELD_PREP(BMI270_ACC_CONF_ODR_MSK,
BMI270_ACC_CONF_ODR_100HZ) |
FIELD_PREP(BMI270_ACC_CONF_BWP_MSK,
- BMI270_ACC_CONF_BWP_NORMAL_MODE) |
- BMI270_PWR_CONF_ADV_PWR_SAVE_MSK);
+ BMI270_ACC_CONF_BWP_NORMAL_MODE));
if (ret)
return dev_err_probe(dev, ret, "Failed to configure accelerometer");
@@ -927,8 +926,7 @@ static int bmi270_configure_imu(struct bmi270_data *data)
FIELD_PREP(BMI270_GYR_CONF_ODR_MSK,
BMI270_GYR_CONF_ODR_200HZ) |
FIELD_PREP(BMI270_GYR_CONF_BWP_MSK,
- BMI270_GYR_CONF_BWP_NORMAL_MODE) |
- BMI270_PWR_CONF_ADV_PWR_SAVE_MSK);
+ BMI270_GYR_CONF_BWP_NORMAL_MODE));
if (ret)
return dev_err_probe(dev, ret, "Failed to configure gyroscope");
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
index 3d3b27f..273196e 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
@@ -50,7 +50,7 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p)
u16 fifo_count;
u32 fifo_period;
s64 timestamp;
- u8 data[INV_MPU6050_OUTPUT_DATA_SIZE];
+ u8 data[INV_MPU6050_OUTPUT_DATA_SIZE] __aligned(8);
size_t i, nb;
mutex_lock(&st->lock);
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
index 0a7cd8c..8a9d259 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
@@ -392,6 +392,9 @@ int st_lsm6dsx_read_fifo(struct st_lsm6dsx_hw *hw)
if (fifo_status & cpu_to_le16(ST_LSM6DSX_FIFO_EMPTY_MASK))
return 0;
+ if (!pattern_len)
+ pattern_len = ST_LSM6DSX_SAMPLE_SIZE;
+
fifo_len = (le16_to_cpu(fifo_status) & fifo_diff_mask) *
ST_LSM6DSX_CHAN_SIZE;
fifo_len = (fifo_len / pattern_len) * pattern_len;
@@ -623,6 +626,9 @@ int st_lsm6dsx_read_tagged_fifo(struct st_lsm6dsx_hw *hw)
if (!fifo_len)
return 0;
+ if (!pattern_len)
+ pattern_len = ST_LSM6DSX_TAGGED_SAMPLE_SIZE;
+
for (read_len = 0; read_len < fifo_len; read_len += pattern_len) {
err = st_lsm6dsx_read_block(hw,
ST_LSM6DSX_REG_FIFO_OUT_TAG_ADDR,
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c
index 4fdcc2a..96c6106 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c
@@ -2719,8 +2719,11 @@ int st_lsm6dsx_probe(struct device *dev, int irq, int hw_id,
}
if (device_property_read_bool(dev, "wakeup-source") ||
- (pdata && pdata->wakeup_source))
- device_init_wakeup(dev, true);
+ (pdata && pdata->wakeup_source)) {
+ err = devm_device_init_wakeup(dev);
+ if (err)
+ return dev_err_probe(dev, err, "Failed to init wakeup\n");
+ }
return 0;
}
diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c
index 76b76d1..4c65b32 100644
--- a/drivers/iio/light/hid-sensor-prox.c
+++ b/drivers/iio/light/hid-sensor-prox.c
@@ -34,9 +34,9 @@ struct prox_state {
struct iio_chan_spec channels[MAX_CHANNELS];
u32 channel2usage[MAX_CHANNELS];
u32 human_presence[MAX_CHANNELS];
- int scale_pre_decml;
- int scale_post_decml;
- int scale_precision;
+ int scale_pre_decml[MAX_CHANNELS];
+ int scale_post_decml[MAX_CHANNELS];
+ int scale_precision[MAX_CHANNELS];
unsigned long scan_mask[2]; /* One entry plus one terminator. */
int num_channels;
};
@@ -116,13 +116,15 @@ static int prox_read_raw(struct iio_dev *indio_dev,
ret_type = IIO_VAL_INT;
break;
case IIO_CHAN_INFO_SCALE:
- *val = prox_state->scale_pre_decml;
- *val2 = prox_state->scale_post_decml;
- ret_type = prox_state->scale_precision;
+ if (chan->scan_index >= prox_state->num_channels)
+ return -EINVAL;
+
+ *val = prox_state->scale_pre_decml[chan->scan_index];
+ *val2 = prox_state->scale_post_decml[chan->scan_index];
+ ret_type = prox_state->scale_precision[chan->scan_index];
break;
case IIO_CHAN_INFO_OFFSET:
- *val = hid_sensor_convert_exponent(
- prox_state->prox_attr[chan->scan_index].unit_expo);
+ *val = 0;
ret_type = IIO_VAL_INT;
break;
case IIO_CHAN_INFO_SAMP_FREQ:
@@ -249,6 +251,10 @@ static int prox_parse_report(struct platform_device *pdev,
st->prox_attr[index].size);
dev_dbg(&pdev->dev, "prox %x:%x\n", st->prox_attr[index].index,
st->prox_attr[index].report_id);
+ st->scale_precision[index] =
+ hid_sensor_format_scale(usage_id, &st->prox_attr[index],
+ &st->scale_pre_decml[index],
+ &st->scale_post_decml[index]);
index++;
}
diff --git a/drivers/iio/light/opt3001.c b/drivers/iio/light/opt3001.c
index 65b2958..393a3d2 100644
--- a/drivers/iio/light/opt3001.c
+++ b/drivers/iio/light/opt3001.c
@@ -788,8 +788,9 @@ static irqreturn_t opt3001_irq(int irq, void *_iio)
int ret;
bool wake_result_ready_queue = false;
enum iio_chan_type chan_type = opt->chip_info->chan_type;
+ bool ok_to_ignore_lock = opt->ok_to_ignore_lock;
- if (!opt->ok_to_ignore_lock)
+ if (!ok_to_ignore_lock)
mutex_lock(&opt->lock);
ret = i2c_smbus_read_word_swapped(opt->client, OPT3001_CONFIGURATION);
@@ -826,7 +827,7 @@ static irqreturn_t opt3001_irq(int irq, void *_iio)
}
out:
- if (!opt->ok_to_ignore_lock)
+ if (!ok_to_ignore_lock)
mutex_unlock(&opt->lock);
if (wake_result_ready_queue)
diff --git a/drivers/iio/magnetometer/ak8974.c b/drivers/iio/magnetometer/ak8974.c
index 08975c6..7bc341c 100644
--- a/drivers/iio/magnetometer/ak8974.c
+++ b/drivers/iio/magnetometer/ak8974.c
@@ -535,8 +535,8 @@ static int ak8974_detect(struct ak8974 *ak8974)
fab_data2, sizeof(fab_data2));
for (i = 0; i < 3; ++i) {
- static const char axis[3] = "XYZ";
- static const char pgaxis[6] = "ZYZXYX";
+ static const char axis[] = "XYZ";
+ static const char pgaxis[] = "ZYZXYX";
unsigned offz = le16_to_cpu(fab_data2[i]) & 0x7F;
unsigned fine = le16_to_cpu(fab_data1[i]);
unsigned sens = le16_to_cpu(fab_data1[i + 3]);
diff --git a/drivers/iio/pressure/mprls0025pa.h b/drivers/iio/pressure/mprls0025pa.h
index 9d5c30a..d62a018 100644
--- a/drivers/iio/pressure/mprls0025pa.h
+++ b/drivers/iio/pressure/mprls0025pa.h
@@ -34,16 +34,6 @@ struct iio_dev;
struct mpr_data;
struct mpr_ops;
-/**
- * struct mpr_chan
- * @pres: pressure value
- * @ts: timestamp
- */
-struct mpr_chan {
- s32 pres;
- s64 ts;
-};
-
enum mpr_func_id {
MPR_FUNCTION_A,
MPR_FUNCTION_B,
@@ -69,6 +59,8 @@ enum mpr_func_id {
* reading in a loop until data is ready
* @completion: handshake from irq to read
* @chan: channel values for buffered mode
+ * @chan.pres: pressure value
+ * @chan.ts: timestamp
* @buffer: raw conversion data
*/
struct mpr_data {
@@ -87,7 +79,10 @@ struct mpr_data {
struct gpio_desc *gpiod_reset;
int irq;
struct completion completion;
- struct mpr_chan chan;
+ struct {
+ s32 pres;
+ aligned_s64 ts;
+ } chan;
u8 buffer[MPR_MEASUREMENT_RD_SIZE] __aligned(IIO_DMA_MINALIGN);
};
diff --git a/drivers/iio/temperature/maxim_thermocouple.c b/drivers/iio/temperature/maxim_thermocouple.c
index c28a7a6..555a61e 100644
--- a/drivers/iio/temperature/maxim_thermocouple.c
+++ b/drivers/iio/temperature/maxim_thermocouple.c
@@ -121,9 +121,9 @@ static const struct maxim_thermocouple_chip maxim_thermocouple_chips[] = {
struct maxim_thermocouple_data {
struct spi_device *spi;
const struct maxim_thermocouple_chip *chip;
+ char tc_type;
u8 buffer[16] __aligned(IIO_DMA_MINALIGN);
- char tc_type;
};
static int maxim_thermocouple_read(struct maxim_thermocouple_data *data,
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index fedcdb5..ab31eef 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -72,6 +72,8 @@ static const char * const cma_events[] = {
static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid,
enum ib_gid_type gid_type);
+static void cma_netevent_work_handler(struct work_struct *_work);
+
const char *__attribute_const__ rdma_event_msg(enum rdma_cm_event_type event)
{
size_t index = event;
@@ -1047,6 +1049,7 @@ __rdma_create_id(struct net *net, rdma_cm_event_handler event_handler,
get_random_bytes(&id_priv->seq_num, sizeof id_priv->seq_num);
id_priv->id.route.addr.dev_addr.net = get_net(net);
id_priv->seq_num &= 0x00ffffff;
+ INIT_WORK(&id_priv->id.net_work, cma_netevent_work_handler);
rdma_restrack_new(&id_priv->res, RDMA_RESTRACK_CM_ID);
if (parent)
@@ -5241,7 +5244,6 @@ static int cma_netevent_callback(struct notifier_block *self,
if (!memcmp(current_id->id.route.addr.dev_addr.dst_dev_addr,
neigh->ha, ETH_ALEN))
continue;
- INIT_WORK(¤t_id->id.net_work, cma_netevent_work_handler);
cma_id_get(current_id);
queue_work(cma_wq, ¤t_id->id.net_work);
}
diff --git a/drivers/infiniband/core/ucaps.c b/drivers/infiniband/core/ucaps.c
index 6853c6d..de5cb8b 100644
--- a/drivers/infiniband/core/ucaps.c
+++ b/drivers/infiniband/core/ucaps.c
@@ -170,7 +170,7 @@ int ib_create_ucap(enum rdma_user_cap type)
ucap->dev.class = &ucaps_class;
ucap->dev.devt = MKDEV(MAJOR(ucaps_base_dev), type);
ucap->dev.release = ucap_dev_release;
- ret = dev_set_name(&ucap->dev, ucap_names[type]);
+ ret = dev_set_name(&ucap->dev, "%s", ucap_names[type]);
if (ret)
goto err_device;
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index e9fa22d..c48ef60 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -76,12 +76,14 @@ static inline int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
npfns = (end - start) >> PAGE_SHIFT;
umem_odp->pfn_list = kvcalloc(
- npfns, sizeof(*umem_odp->pfn_list), GFP_KERNEL);
+ npfns, sizeof(*umem_odp->pfn_list),
+ GFP_KERNEL | __GFP_NOWARN);
if (!umem_odp->pfn_list)
return -ENOMEM;
umem_odp->dma_list = kvcalloc(
- ndmas, sizeof(*umem_odp->dma_list), GFP_KERNEL);
+ ndmas, sizeof(*umem_odp->dma_list),
+ GFP_KERNEL | __GFP_NOWARN);
if (!umem_odp->dma_list) {
ret = -ENOMEM;
goto out_pfn_list;
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 9082b3f..0638013 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -1774,10 +1774,7 @@ int bnxt_re_destroy_srq(struct ib_srq *ib_srq, struct ib_udata *udata)
ib_srq);
struct bnxt_re_dev *rdev = srq->rdev;
struct bnxt_qplib_srq *qplib_srq = &srq->qplib_srq;
- struct bnxt_qplib_nq *nq = NULL;
- if (qplib_srq->cq)
- nq = qplib_srq->cq->nq;
if (rdev->chip_ctx->modes.toggle_bits & BNXT_QPLIB_SRQ_TOGGLE_BIT) {
free_page((unsigned long)srq->uctx_srq_page);
hash_del(&srq->hash_entry);
@@ -1785,8 +1782,6 @@ int bnxt_re_destroy_srq(struct ib_srq *ib_srq, struct ib_udata *udata)
bnxt_qplib_destroy_srq(&rdev->qplib_res, qplib_srq);
ib_umem_release(srq->umem);
atomic_dec(&rdev->stats.res.srq_count);
- if (nq)
- nq->budget--;
return 0;
}
@@ -1827,7 +1822,6 @@ int bnxt_re_create_srq(struct ib_srq *ib_srq,
struct ib_udata *udata)
{
struct bnxt_qplib_dev_attr *dev_attr;
- struct bnxt_qplib_nq *nq = NULL;
struct bnxt_re_ucontext *uctx;
struct bnxt_re_dev *rdev;
struct bnxt_re_srq *srq;
@@ -1873,7 +1867,6 @@ int bnxt_re_create_srq(struct ib_srq *ib_srq,
srq->qplib_srq.eventq_hw_ring_id = rdev->nqr->nq[0].ring_id;
srq->qplib_srq.sg_info.pgsize = PAGE_SIZE;
srq->qplib_srq.sg_info.pgshft = PAGE_SHIFT;
- nq = &rdev->nqr->nq[0];
if (udata) {
rc = bnxt_re_init_user_srq(rdev, pd, srq, udata);
@@ -1908,8 +1901,6 @@ int bnxt_re_create_srq(struct ib_srq *ib_srq,
goto fail;
}
}
- if (nq)
- nq->budget++;
active_srqs = atomic_inc_return(&rdev->stats.res.srq_count);
if (active_srqs > rdev->stats.res.srq_watermark)
rdev->stats.res.srq_watermark = active_srqs;
@@ -3079,7 +3070,6 @@ int bnxt_re_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
ib_umem_release(cq->umem);
atomic_dec(&rdev->stats.res.cq_count);
- nq->budget--;
kfree(cq->cql);
return 0;
}
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index cf89a8d..8d0b63d 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -763,7 +763,7 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev)
if (ret)
return ret;
}
- dma_set_max_seg_size(dev, UINT_MAX);
+ dma_set_max_seg_size(dev, SZ_2G);
ret = ib_register_device(ib_dev, "hns_%d", dev);
if (ret) {
dev_err(dev, "ib_register_device failed!\n");
diff --git a/drivers/infiniband/hw/mlx5/fs.c b/drivers/infiniband/hw/mlx5/fs.c
index 251246c..0ff9f18 100644
--- a/drivers/infiniband/hw/mlx5/fs.c
+++ b/drivers/infiniband/hw/mlx5/fs.c
@@ -3461,7 +3461,6 @@ DECLARE_UVERBS_NAMED_OBJECT(
&UVERBS_METHOD(MLX5_IB_METHOD_STEERING_ANCHOR_DESTROY));
const struct uapi_definition mlx5_ib_flow_defs[] = {
-#if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
UAPI_DEF_CHAIN_OBJ_TREE_NAMED(
MLX5_IB_OBJECT_FLOW_MATCHER),
UAPI_DEF_CHAIN_OBJ_TREE(
@@ -3472,7 +3471,6 @@ const struct uapi_definition mlx5_ib_flow_defs[] = {
UAPI_DEF_CHAIN_OBJ_TREE_NAMED(
MLX5_IB_OBJECT_STEERING_ANCHOR,
UAPI_DEF_IS_OBJ_SUPPORTED(mlx5_ib_shared_ft_allowed)),
-#endif
{},
};
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c
index 4ddcd58..11eca39 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_main.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c
@@ -397,7 +397,7 @@ static void *usnic_ib_device_add(struct pci_dev *dev)
if (!us_ibdev) {
usnic_err("Device %s context alloc failed\n",
netdev_name(pci_get_drvdata(dev)));
- return ERR_PTR(-EFAULT);
+ return NULL;
}
us_ibdev->ufdev = usnic_fwd_dev_alloc(dev);
@@ -517,8 +517,8 @@ static struct usnic_ib_dev *usnic_ib_discover_pf(struct usnic_vnic *vnic)
}
us_ibdev = usnic_ib_device_add(parent_pci);
- if (IS_ERR_OR_NULL(us_ibdev)) {
- us_ibdev = us_ibdev ? us_ibdev : ERR_PTR(-EFAULT);
+ if (!us_ibdev) {
+ us_ibdev = ERR_PTR(-EFAULT);
goto out;
}
@@ -586,10 +586,10 @@ static int usnic_ib_pci_probe(struct pci_dev *pdev,
}
pf = usnic_ib_discover_pf(vf->vnic);
- if (IS_ERR_OR_NULL(pf)) {
- usnic_err("Failed to discover pf of vnic %s with err%ld\n",
- pci_name(pdev), PTR_ERR(pf));
- err = pf ? PTR_ERR(pf) : -EFAULT;
+ if (IS_ERR(pf)) {
+ err = PTR_ERR(pf);
+ usnic_err("Failed to discover pf of vnic %s with err%d\n",
+ pci_name(pdev), err);
goto out_clean_vnic;
}
diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index feb386d..0bc3fbb 100644
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -140,6 +140,12 @@ static inline int qp_mtu(struct rxe_qp *qp)
return IB_MTU_4096;
}
+static inline bool is_odp_mr(struct rxe_mr *mr)
+{
+ return IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) && mr->umem &&
+ mr->umem->is_odp;
+}
+
void free_rd_atomic_resource(struct resp_res *res);
static inline void rxe_advance_resp_resource(struct rxe_qp *qp)
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index 868d2f0..432d864 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -323,7 +323,7 @@ int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr,
return err;
}
- if (mr->umem->is_odp)
+ if (is_odp_mr(mr))
return rxe_odp_mr_copy(mr, iova, addr, length, dir);
else
return rxe_mr_copy_xarray(mr, iova, addr, length, dir);
@@ -536,7 +536,7 @@ int rxe_mr_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value)
u64 *va;
/* ODP is not supported right now. WIP. */
- if (mr->umem->is_odp)
+ if (is_odp_mr(mr))
return RESPST_ERR_UNSUPPORTED_OPCODE;
/* See IBA oA19-28 */
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 54ba9ee..5d9174e 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -650,7 +650,7 @@ static enum resp_states process_flush(struct rxe_qp *qp,
struct resp_res *res = qp->resp.res;
/* ODP is not supported right now. WIP. */
- if (mr->umem->is_odp)
+ if (is_odp_mr(mr))
return RESPST_ERR_UNSUPPORTED_OPCODE;
/* oA19-14, oA19-15 */
@@ -706,7 +706,7 @@ static enum resp_states atomic_reply(struct rxe_qp *qp,
if (!res->replay) {
u64 iova = qp->resp.va + qp->resp.offset;
- if (mr->umem->is_odp)
+ if (is_odp_mr(mr))
err = rxe_odp_atomic_op(mr, iova, pkt->opcode,
atmeth_comp(pkt),
atmeth_swap_add(pkt),
diff --git a/drivers/input/joystick/magellan.c b/drivers/input/joystick/magellan.c
index 2eaa25c..7622638 100644
--- a/drivers/input/joystick/magellan.c
+++ b/drivers/input/joystick/magellan.c
@@ -48,7 +48,7 @@ struct magellan {
static int magellan_crunch_nibbles(unsigned char *data, int count)
{
- static unsigned char nibbles[16] = "0AB3D56GH9:K<MN?";
+ static const unsigned char nibbles[16] __nonstring = "0AB3D56GH9:K<MN?";
do {
if (data[count] == nibbles[data[count] & 0xf])
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index c33e6f3..c933e47 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -387,6 +387,7 @@ static const struct xpad_device {
{ 0x2dc8, 0x3106, "8BitDo Ultimate Wireless / Pro 2 Wired Controller", 0, XTYPE_XBOX360 },
{ 0x2dc8, 0x3109, "8BitDo Ultimate Wireless Bluetooth", 0, XTYPE_XBOX360 },
{ 0x2dc8, 0x310a, "8BitDo Ultimate 2C Wireless Controller", 0, XTYPE_XBOX360 },
+ { 0x2dc8, 0x310b, "8BitDo Ultimate 2 Wireless Controller", 0, XTYPE_XBOX360 },
{ 0x2dc8, 0x6001, "8BitDo SN30 Pro", 0, XTYPE_XBOX360 },
{ 0x2e24, 0x0652, "Hyperkin Duke X-Box One pad", 0, XTYPE_XBOXONE },
{ 0x2e24, 0x1688, "Hyperkin X91 X-Box One pad", 0, XTYPE_XBOXONE },
diff --git a/drivers/input/keyboard/mtk-pmic-keys.c b/drivers/input/keyboard/mtk-pmic-keys.c
index 5ad6be9..061d483 100644
--- a/drivers/input/keyboard/mtk-pmic-keys.c
+++ b/drivers/input/keyboard/mtk-pmic-keys.c
@@ -147,8 +147,8 @@ static void mtk_pmic_keys_lp_reset_setup(struct mtk_pmic_keys *keys,
u32 value, mask;
int error;
- kregs_home = keys->keys[MTK_PMIC_HOMEKEY_INDEX].regs;
- kregs_pwr = keys->keys[MTK_PMIC_PWRKEY_INDEX].regs;
+ kregs_home = ®s->keys_regs[MTK_PMIC_HOMEKEY_INDEX];
+ kregs_pwr = ®s->keys_regs[MTK_PMIC_PWRKEY_INDEX];
error = of_property_read_u32(keys->dev->of_node, "power-off-time-sec",
&long_press_debounce);
diff --git a/drivers/input/misc/sparcspkr.c b/drivers/input/misc/sparcspkr.c
index 8d7303f..1cfadd7 100644
--- a/drivers/input/misc/sparcspkr.c
+++ b/drivers/input/misc/sparcspkr.c
@@ -74,9 +74,14 @@ static int bbc_spkr_event(struct input_dev *dev, unsigned int type, unsigned int
return -1;
switch (code) {
- case SND_BELL: if (value) value = 1000;
- case SND_TONE: break;
- default: return -1;
+ case SND_BELL:
+ if (value)
+ value = 1000;
+ break;
+ case SND_TONE:
+ break;
+ default:
+ return -1;
}
if (value > 20 && value < 32767)
@@ -109,9 +114,14 @@ static int grover_spkr_event(struct input_dev *dev, unsigned int type, unsigned
return -1;
switch (code) {
- case SND_BELL: if (value) value = 1000;
- case SND_TONE: break;
- default: return -1;
+ case SND_BELL:
+ if (value)
+ value = 1000;
+ break;
+ case SND_TONE:
+ break;
+ default:
+ return -1;
}
if (value > 20 && value < 32767)
diff --git a/drivers/input/touchscreen/cyttsp5.c b/drivers/input/touchscreen/cyttsp5.c
index eafe5a9..071b7c9 100644
--- a/drivers/input/touchscreen/cyttsp5.c
+++ b/drivers/input/touchscreen/cyttsp5.c
@@ -580,7 +580,7 @@ static int cyttsp5_power_control(struct cyttsp5 *ts, bool on)
int rc;
SET_CMD_REPORT_TYPE(cmd[0], 0);
- SET_CMD_REPORT_ID(cmd[0], HID_POWER_SLEEP);
+ SET_CMD_REPORT_ID(cmd[0], state);
SET_CMD_OPCODE(cmd[1], HID_CMD_SET_POWER);
rc = cyttsp5_write(ts, HID_COMMAND_REG, cmd, sizeof(cmd));
@@ -870,13 +870,16 @@ static int cyttsp5_probe(struct device *dev, struct regmap *regmap, int irq,
ts->input->phys = ts->phys;
input_set_drvdata(ts->input, ts);
- /* Reset the gpio to be in a reset state */
+ /* Assert gpio to be in a reset state */
ts->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
if (IS_ERR(ts->reset_gpio)) {
error = PTR_ERR(ts->reset_gpio);
dev_err(dev, "Failed to request reset gpio, error %d\n", error);
return error;
}
+
+ fsleep(10); /* Ensure long-enough reset pulse (minimum 10us). */
+
gpiod_set_value_cansleep(ts->reset_gpio, 0);
/* Need a delay to have device up */
diff --git a/drivers/input/touchscreen/stmpe-ts.c b/drivers/input/touchscreen/stmpe-ts.c
index a94a199..af0fb38 100644
--- a/drivers/input/touchscreen/stmpe-ts.c
+++ b/drivers/input/touchscreen/stmpe-ts.c
@@ -366,12 +366,7 @@ static struct platform_driver stmpe_ts_driver = {
};
module_platform_driver(stmpe_ts_driver);
-static const struct of_device_id stmpe_ts_ids[] = {
- { .compatible = "st,stmpe-ts", },
- { },
-};
-MODULE_DEVICE_TABLE(of, stmpe_ts_ids);
-
+MODULE_ALIAS("platform:stmpe-ts");
MODULE_AUTHOR("Luotao Fu <l.fu@pengutronix.de>");
MODULE_DESCRIPTION("STMPEXXX touchscreen driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index be8761b..f34209b 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -3869,6 +3869,9 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
struct iommu_dev_data *dev_data;
+ if (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)))
+ return -EINVAL;
+
if (ir_data->iommu == NULL)
return -EINVAL;
@@ -3879,21 +3882,11 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
* we should not modify the IRTE
*/
if (!dev_data || !dev_data->use_vapic)
- return 0;
+ return -EINVAL;
ir_data->cfg = irqd_cfg(data);
pi_data->ir_data = ir_data;
- /* Note:
- * SVM tries to set up for VAPIC mode, but we are in
- * legacy mode. So, we force legacy mode instead.
- */
- if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)) {
- pr_debug("%s: Fall back to using intr legacy remap\n",
- __func__);
- pi_data->is_guest_mode = false;
- }
-
pi_data->prev_ga_tag = ir_data->cached_ga_tag;
if (pi_data->is_guest_mode) {
ir_data->ga_root_ptr = (pi_data->base >> 12);
diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
index d525ab4..dd7d030 100644
--- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
+++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
@@ -487,17 +487,6 @@ static int tegra241_cmdqv_hw_reset(struct arm_smmu_device *smmu)
/* VCMDQ Resource Helpers */
-static void tegra241_vcmdq_free_smmu_cmdq(struct tegra241_vcmdq *vcmdq)
-{
- struct arm_smmu_queue *q = &vcmdq->cmdq.q;
- size_t nents = 1 << q->llq.max_n_shift;
- size_t qsz = nents << CMDQ_ENT_SZ_SHIFT;
-
- if (!q->base)
- return;
- dmam_free_coherent(vcmdq->cmdqv->smmu.dev, qsz, q->base, q->base_dma);
-}
-
static int tegra241_vcmdq_alloc_smmu_cmdq(struct tegra241_vcmdq *vcmdq)
{
struct arm_smmu_device *smmu = &vcmdq->cmdqv->smmu;
@@ -560,7 +549,8 @@ static void tegra241_vintf_free_lvcmdq(struct tegra241_vintf *vintf, u16 lidx)
struct tegra241_vcmdq *vcmdq = vintf->lvcmdqs[lidx];
char header[64];
- tegra241_vcmdq_free_smmu_cmdq(vcmdq);
+ /* Note that the lvcmdq queue memory space is managed by devres */
+
tegra241_vintf_deinit_lvcmdq(vintf, lidx);
dev_dbg(vintf->cmdqv->dev,
@@ -768,13 +758,13 @@ static int tegra241_cmdqv_init_structures(struct arm_smmu_device *smmu)
vintf = kzalloc(sizeof(*vintf), GFP_KERNEL);
if (!vintf)
- goto out_fallback;
+ return -ENOMEM;
/* Init VINTF0 for in-kernel use */
ret = tegra241_cmdqv_init_vintf(cmdqv, 0, vintf);
if (ret) {
dev_err(cmdqv->dev, "failed to init vintf0: %d\n", ret);
- goto free_vintf;
+ return ret;
}
/* Preallocate logical VCMDQs to VINTF0 */
@@ -783,24 +773,12 @@ static int tegra241_cmdqv_init_structures(struct arm_smmu_device *smmu)
vcmdq = tegra241_vintf_alloc_lvcmdq(vintf, lidx);
if (IS_ERR(vcmdq))
- goto free_lvcmdq;
+ return PTR_ERR(vcmdq);
}
/* Now, we are ready to run all the impl ops */
smmu->impl_ops = &tegra241_cmdqv_impl_ops;
return 0;
-
-free_lvcmdq:
- for (lidx--; lidx >= 0; lidx--)
- tegra241_vintf_free_lvcmdq(vintf, lidx);
- tegra241_cmdqv_deinit_vintf(cmdqv, vintf->idx);
-free_vintf:
- kfree(vintf);
-out_fallback:
- dev_info(smmu->impl_dev, "Falling back to standard SMMU CMDQ\n");
- smmu->options &= ~ARM_SMMU_OPT_TEGRA241_CMDQV;
- tegra241_cmdqv_remove(smmu);
- return 0;
}
#ifdef CONFIG_IOMMU_DEBUGFS
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index cb7e29d..a775e4d 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1754,7 +1754,7 @@ static size_t cookie_msi_granule(const struct iommu_domain *domain)
return PAGE_SIZE;
default:
BUG();
- };
+ }
}
static struct list_head *cookie_msi_pages(const struct iommu_domain *domain)
@@ -1766,7 +1766,7 @@ static struct list_head *cookie_msi_pages(const struct iommu_domain *domain)
return &domain->msi_cookie->msi_page_list;
default:
BUG();
- };
+ }
}
static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 69e23e01..317266a 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -832,7 +832,7 @@ static int __maybe_unused exynos_sysmmu_suspend(struct device *dev)
struct exynos_iommu_owner *owner = dev_iommu_priv_get(master);
mutex_lock(&owner->rpm_lock);
- if (&data->domain->domain != &exynos_identity_domain) {
+ if (data->domain) {
dev_dbg(data->sysmmu, "saving state\n");
__sysmmu_disable(data);
}
@@ -850,7 +850,7 @@ static int __maybe_unused exynos_sysmmu_resume(struct device *dev)
struct exynos_iommu_owner *owner = dev_iommu_priv_get(master);
mutex_lock(&owner->rpm_lock);
- if (&data->domain->domain != &exynos_identity_domain) {
+ if (data->domain) {
dev_dbg(data->sysmmu, "restoring state\n");
__sysmmu_enable(data);
}
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 6e67cc6..b29da2d 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3835,7 +3835,6 @@ static void intel_iommu_release_device(struct device *dev)
intel_pasid_free_table(dev);
intel_iommu_debugfs_remove_dev(info);
kfree(info);
- set_dma_ops(dev, NULL);
}
static void intel_iommu_get_resv_regions(struct device *device,
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index ea3ca52..3bc2a03 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -1287,43 +1287,44 @@ static struct irq_chip intel_ir_chip = {
};
/*
- * With posted MSIs, all vectors are multiplexed into a single notification
- * vector. Devices MSIs are then dispatched in a demux loop where
- * EOIs can be coalesced as well.
+ * With posted MSIs, the MSI vectors are multiplexed into a single notification
+ * vector, and only the notification vector is sent to the APIC IRR. Device
+ * MSIs are then dispatched in a demux loop that harvests the MSIs from the
+ * CPU's Posted Interrupt Request bitmap. I.e. Posted MSIs never get sent to
+ * the APIC IRR, and thus do not need an EOI. The notification handler instead
+ * performs a single EOI after processing the PIR.
*
- * "INTEL-IR-POST" IRQ chip does not do EOI on ACK, thus the dummy irq_ack()
- * function. Instead EOI is performed by the posted interrupt notification
- * handler.
+ * Note! Pending SMP/CPU affinity changes, which are per MSI, must still be
+ * honored, only the APIC EOI is omitted.
*
* For the example below, 3 MSIs are coalesced into one CPU notification. Only
- * one apic_eoi() is needed.
+ * one apic_eoi() is needed, but each MSI needs to process pending changes to
+ * its CPU affinity.
*
* __sysvec_posted_msi_notification()
* irq_enter();
* handle_edge_irq()
* irq_chip_ack_parent()
- * dummy(); // No EOI
+ * irq_move_irq(); // No EOI
* handle_irq_event()
* driver_handler()
* handle_edge_irq()
* irq_chip_ack_parent()
- * dummy(); // No EOI
+ * irq_move_irq(); // No EOI
* handle_irq_event()
* driver_handler()
* handle_edge_irq()
* irq_chip_ack_parent()
- * dummy(); // No EOI
+ * irq_move_irq(); // No EOI
* handle_irq_event()
* driver_handler()
* apic_eoi()
* irq_exit()
+ *
*/
-
-static void dummy_ack(struct irq_data *d) { }
-
static struct irq_chip intel_ir_chip_post_msi = {
.name = "INTEL-IR-POST",
- .irq_ack = dummy_ack,
+ .irq_ack = irq_move_irq,
.irq_set_affinity = intel_ir_set_affinity,
.irq_compose_msi_msg = intel_ir_compose_msi_msg,
.irq_set_vcpu_affinity = intel_ir_set_vcpu_affinity,
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index c8033ca..4f91a74 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -538,6 +538,9 @@ static void iommu_deinit_device(struct device *dev)
dev->iommu_group = NULL;
module_put(ops->owner);
dev_iommu_free(dev);
+#ifdef CONFIG_IOMMU_DMA
+ dev->dma_iommu = false;
+#endif
}
static struct iommu_domain *pasid_array_entry_to_domain(void *entry)
@@ -2717,7 +2720,8 @@ int report_iommu_fault(struct iommu_domain *domain, struct device *dev,
* if upper layers showed interest and installed a fault handler,
* invoke it.
*/
- if (domain->handler)
+ if (domain->cookie_type == IOMMU_COOKIE_FAULT_HANDLER &&
+ domain->handler)
ret = domain->handler(domain, dev, iova, flags,
domain->handler_token);
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 074daf1..e424b27 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -1081,31 +1081,24 @@ static int ipmmu_probe(struct platform_device *pdev)
}
}
+ platform_set_drvdata(pdev, mmu);
/*
* Register the IPMMU to the IOMMU subsystem in the following cases:
* - R-Car Gen2 IPMMU (all devices registered)
* - R-Car Gen3 IPMMU (leaf devices only - skip root IPMMU-MM device)
*/
- if (!mmu->features->has_cache_leaf_nodes || !ipmmu_is_root(mmu)) {
- ret = iommu_device_sysfs_add(&mmu->iommu, &pdev->dev, NULL,
- dev_name(&pdev->dev));
- if (ret)
- return ret;
+ if (mmu->features->has_cache_leaf_nodes && ipmmu_is_root(mmu))
+ return 0;
- ret = iommu_device_register(&mmu->iommu, &ipmmu_ops, &pdev->dev);
- if (ret)
- return ret;
- }
+ ret = iommu_device_sysfs_add(&mmu->iommu, &pdev->dev, NULL, dev_name(&pdev->dev));
+ if (ret)
+ return ret;
- /*
- * We can't create the ARM mapping here as it requires the bus to have
- * an IOMMU, which only happens when bus_set_iommu() is called in
- * ipmmu_init() after the probe function returns.
- */
+ ret = iommu_device_register(&mmu->iommu, &ipmmu_ops, &pdev->dev);
+ if (ret)
+ iommu_device_sysfs_remove(&mmu->iommu);
- platform_set_drvdata(pdev, mmu);
-
- return 0;
+ return ret;
}
static void ipmmu_remove(struct platform_device *pdev)
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 034b0e6..df98d0c 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -1372,15 +1372,6 @@ static int mtk_iommu_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, data);
mutex_init(&data->mutex);
- ret = iommu_device_sysfs_add(&data->iommu, dev, NULL,
- "mtk-iommu.%pa", &ioaddr);
- if (ret)
- goto out_link_remove;
-
- ret = iommu_device_register(&data->iommu, &mtk_iommu_ops, dev);
- if (ret)
- goto out_sysfs_remove;
-
if (MTK_IOMMU_HAS_FLAG(data->plat_data, SHARE_PGTABLE)) {
list_add_tail(&data->list, data->plat_data->hw_list);
data->hw_list = data->plat_data->hw_list;
@@ -1390,19 +1381,28 @@ static int mtk_iommu_probe(struct platform_device *pdev)
data->hw_list = &data->hw_list_head;
}
+ ret = iommu_device_sysfs_add(&data->iommu, dev, NULL,
+ "mtk-iommu.%pa", &ioaddr);
+ if (ret)
+ goto out_list_del;
+
+ ret = iommu_device_register(&data->iommu, &mtk_iommu_ops, dev);
+ if (ret)
+ goto out_sysfs_remove;
+
if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
ret = component_master_add_with_match(dev, &mtk_iommu_com_ops, match);
if (ret)
- goto out_list_del;
+ goto out_device_unregister;
}
return ret;
-out_list_del:
- list_del(&data->list);
+out_device_unregister:
iommu_device_unregister(&data->iommu);
out_sysfs_remove:
iommu_device_sysfs_remove(&data->iommu);
-out_link_remove:
+out_list_del:
+ list_del(&data->list);
if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM))
device_link_remove(data->smicomm_dev, dev);
out_runtime_disable:
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index cec05e4..08bb3b0 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -114,8 +114,8 @@
config BCM2712_MIP
tristate "Broadcom BCM2712 MSI-X Interrupt Peripheral support"
- depends on ARCH_BRCMSTB || COMPILE_TEST
- default m if ARCH_BRCMSTB
+ depends on ARCH_BRCMSTB || ARCH_BCM2835 || COMPILE_TEST
+ default m if ARCH_BRCMSTB || ARCH_BCM2835
depends on ARM_GIC
select GENERIC_IRQ_CHIP
select IRQ_DOMAIN_HIERARCHY
diff --git a/drivers/irqchip/irq-bcm2712-mip.c b/drivers/irqchip/irq-bcm2712-mip.c
index 49a19db..4cce242 100644
--- a/drivers/irqchip/irq-bcm2712-mip.c
+++ b/drivers/irqchip/irq-bcm2712-mip.c
@@ -163,6 +163,7 @@ static const struct irq_domain_ops mip_middle_domain_ops = {
static const struct msi_parent_ops mip_msi_parent_ops = {
.supported_flags = MIP_MSI_FLAGS_SUPPORTED,
.required_flags = MIP_MSI_FLAGS_REQUIRED,
+ .chip_flags = MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
.bus_select_token = DOMAIN_BUS_GENERIC_MSI,
.bus_select_mask = MATCH_PCI_MSI,
.prefix = "MIP-MSI-",
diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c
index c698948..dc98c39 100644
--- a/drivers/irqchip/irq-gic-v2m.c
+++ b/drivers/irqchip/irq-gic-v2m.c
@@ -421,7 +421,7 @@ static int __init gicv2m_of_init(struct fwnode_handle *parent_handle,
#ifdef CONFIG_ACPI
static int acpi_num_msi;
-static __init struct fwnode_handle *gicv2m_get_fwnode(struct device *dev)
+static struct fwnode_handle *gicv2m_get_fwnode(struct device *dev)
{
struct v2m_data *data;
diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c
index 3d5b5fd..0f0fd7d 100644
--- a/drivers/irqchip/irq-renesas-rzv2h.c
+++ b/drivers/irqchip/irq-renesas-rzv2h.c
@@ -170,6 +170,14 @@ static void rzv2h_tint_irq_endisable(struct irq_data *d, bool enable)
else
tssr &= ~ICU_TSSR_TIEN(tssel_n, priv->info->field_width);
writel_relaxed(tssr, priv->base + priv->info->t_offs + ICU_TSSR(k));
+
+ /*
+ * A glitch in the edge detection circuit can cause a spurious
+ * interrupt. Clear the status flag after setting the ICU_TSSRk
+ * registers, which is recommended by the hardware manual as a
+ * countermeasure.
+ */
+ writel_relaxed(BIT(tint_nr), priv->base + priv->info->t_offs + ICU_TSCLR);
}
static void rzv2h_icu_irq_disable(struct irq_data *d)
diff --git a/drivers/irqchip/irq-sg2042-msi.c b/drivers/irqchip/irq-sg2042-msi.c
index ee682e8..375b55a 100644
--- a/drivers/irqchip/irq-sg2042-msi.c
+++ b/drivers/irqchip/irq-sg2042-msi.c
@@ -151,6 +151,7 @@ static const struct irq_domain_ops sg2042_msi_middle_domain_ops = {
static const struct msi_parent_ops sg2042_msi_parent_ops = {
.required_flags = SG2042_MSI_FLAGS_REQUIRED,
.supported_flags = SG2042_MSI_FLAGS_SUPPORTED,
+ .chip_flags = MSI_CHIP_FLAG_SET_ACK,
.bus_select_mask = MATCH_PCI_MSI,
.bus_select_token = DOMAIN_BUS_NEXUS,
.prefix = "SG2042-",
diff --git a/drivers/mcb/mcb-parse.c b/drivers/mcb/mcb-parse.c
index 02a680c..bf0d7d5 100644
--- a/drivers/mcb/mcb-parse.c
+++ b/drivers/mcb/mcb-parse.c
@@ -96,7 +96,7 @@ static int chameleon_parse_gdd(struct mcb_bus *bus,
ret = mcb_device_register(bus, mdev);
if (ret < 0)
- goto err;
+ return ret;
return 0;
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 06f809e..ddb37f6 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -139,7 +139,7 @@
tristate "RAID-4/RAID-5/RAID-6 mode"
depends on BLK_DEV_MD
select RAID6_PQ
- select LIBCRC32C
+ select CRC32
select ASYNC_MEMCPY
select ASYNC_XOR
select ASYNC_PQ
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index e42f140..813b38a 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -546,7 +546,7 @@ static struct uuid_entry *uuid_find(struct cache_set *c, const char *uuid)
static struct uuid_entry *uuid_find_empty(struct cache_set *c)
{
- static const char zero_uuid[16] = "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0";
+ static const char zero_uuid[16] = { 0 };
return uuid_find(c, zero_uuid);
}
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 9c8ed65..f0b5a69 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -68,6 +68,8 @@
#define LIST_DIRTY 1
#define LIST_SIZE 2
+#define SCAN_RESCHED_CYCLE 16
+
/*--------------------------------------------------------------*/
/*
@@ -2424,7 +2426,12 @@ static void __scan(struct dm_bufio_client *c)
atomic_long_dec(&c->need_shrink);
freed++;
- cond_resched();
+
+ if (unlikely(freed % SCAN_RESCHED_CYCLE == 0)) {
+ dm_bufio_unlock(c);
+ cond_resched();
+ dm_bufio_lock(c);
+ }
}
}
}
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 2a283fe..cc3d389 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -5164,7 +5164,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
BUG_ON(!RB_EMPTY_ROOT(&ic->in_progress));
BUG_ON(!list_empty(&ic->wait_list));
- if (ic->mode == 'B')
+ if (ic->mode == 'B' && ic->bitmap_flush_work.work.func)
cancel_delayed_work_sync(&ic->bitmap_flush_work);
if (ic->metadata_wq)
destroy_workqueue(ic->metadata_wq);
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 35100a4..9e175c5 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -523,9 +523,10 @@ static char **realloc_argv(unsigned int *size, char **old_argv)
gfp = GFP_NOIO;
}
argv = kmalloc_array(new_size, sizeof(*argv), gfp);
- if (argv && old_argv) {
- memcpy(argv, old_argv, *size * sizeof(*argv));
+ if (argv) {
*size = new_size;
+ if (old_argv)
+ memcpy(argv, old_argv, *size * sizeof(*argv));
}
kfree(old_argv);
@@ -1049,7 +1050,6 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *
unsigned int min_pool_size = 0, pool_size;
struct dm_md_mempools *pools;
unsigned int bioset_flags = 0;
- bool mempool_needs_integrity = t->integrity_supported;
if (unlikely(type == DM_TYPE_NONE)) {
DMERR("no table type is set, can't allocate mempools");
@@ -1074,8 +1074,6 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *
per_io_data_size = max(per_io_data_size, ti->per_io_data_size);
min_pool_size = max(min_pool_size, ti->num_flush_bios);
-
- mempool_needs_integrity |= ti->mempool_needs_integrity;
}
pool_size = max(dm_get_reserved_bio_based_ios(), min_pool_size);
front_pad = roundup(per_io_data_size,
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index 44ec9b1..37b08f2 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -2357,9 +2357,8 @@ static int bitmap_get_stats(void *data, struct md_bitmap_stats *stats)
if (!bitmap)
return -ENOENT;
- if (bitmap->mddev->bitmap_info.external)
- return -ENOENT;
- if (!bitmap->storage.sb_page) /* no superblock */
+ if (!bitmap->mddev->bitmap_info.external &&
+ !bitmap->storage.sb_page)
return -EINVAL;
sb = kmap_local_page(bitmap->storage.sb_page);
stats->sync_size = le64_to_cpu(sb->sync_size);
diff --git a/drivers/md/persistent-data/Kconfig b/drivers/md/persistent-data/Kconfig
index f4f948b..dbb97a7 100644
--- a/drivers/md/persistent-data/Kconfig
+++ b/drivers/md/persistent-data/Kconfig
@@ -2,7 +2,7 @@
config DM_PERSISTENT_DATA
tristate
depends on BLK_DEV_DM
- select LIBCRC32C
+ select CRC32
select DM_BUFIO
help
Library providing immutable on-disk data structure support for
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 0efc03c..de9bccb 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -2200,14 +2200,9 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
if (!rdev_set_badblocks(rdev, sect, s, 0))
abort = 1;
}
- if (abort) {
- conf->recovery_disabled =
- mddev->recovery_disabled;
- set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- md_done_sync(mddev, r1_bio->sectors, 0);
- put_buf(r1_bio);
+ if (abort)
return 0;
- }
+
/* Try next page */
sectors -= s;
sect += s;
@@ -2346,10 +2341,21 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
int disks = conf->raid_disks * 2;
struct bio *wbio;
- if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
- /* ouch - failed to read all of that. */
- if (!fix_sync_read_error(r1_bio))
+ if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) {
+ /*
+ * ouch - failed to read all of that.
+ * No need to fix read error for check/repair
+ * because all member disks are read.
+ */
+ if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) ||
+ !fix_sync_read_error(r1_bio)) {
+ conf->recovery_disabled = mddev->recovery_disabled;
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+ md_done_sync(mddev, r1_bio->sectors, 0);
+ put_buf(r1_bio);
return;
+ }
+ }
if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
process_checks(r1_bio);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 846c5f2..ba32bac 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1735,6 +1735,7 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
* The discard bio returns only first r10bio finishes
*/
if (first_copy) {
+ md_account_bio(mddev, &bio);
r10_bio->master_bio = bio;
set_bit(R10BIO_Discard, &r10_bio->state);
first_copy = false;
diff --git a/drivers/media/cec/i2c/Kconfig b/drivers/media/cec/i2c/Kconfig
index b9d2164..c31abc2 100644
--- a/drivers/media/cec/i2c/Kconfig
+++ b/drivers/media/cec/i2c/Kconfig
@@ -16,6 +16,7 @@
config CEC_NXP_TDA9950
tristate "NXP Semiconductors TDA9950/TDA998X HDMI CEC"
+ depends on I2C
select CEC_NOTIFIER
select CEC_CORE
default DRM_I2C_NXP_TDA998X
diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index e576b21..e45ba12 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -1149,8 +1149,11 @@
config VIDEO_LT6911UXE
tristate "Lontium LT6911UXE decoder"
- depends on ACPI && VIDEO_DEV
+ depends on ACPI && VIDEO_DEV && I2C
select V4L2_FWNODE
+ select V4L2_CCI_I2C
+ select MEDIA_CONTROLLER
+ select VIDEO_V4L2_SUBDEV_API
help
This is a Video4Linux2 sensor-level driver for the Lontium
LT6911UXE HDMI to MIPI CSI-2 bridge.
diff --git a/drivers/media/platform/synopsys/hdmirx/Kconfig b/drivers/media/platform/synopsys/hdmirx/Kconfig
index 27e6706..4321f98 100644
--- a/drivers/media/platform/synopsys/hdmirx/Kconfig
+++ b/drivers/media/platform/synopsys/hdmirx/Kconfig
@@ -2,6 +2,7 @@
config VIDEO_SYNOPSYS_HDMIRX
tristate "Synopsys DesignWare HDMI Receiver driver"
+ depends on ARCH_ROCKCHIP || COMPILE_TEST
depends on VIDEO_DEV
select MEDIA_CONTROLLER
select VIDEO_V4L2_SUBDEV_API
diff --git a/drivers/media/test-drivers/vivid/Kconfig b/drivers/media/test-drivers/vivid/Kconfig
index e95edc0..cc47007 100644
--- a/drivers/media/test-drivers/vivid/Kconfig
+++ b/drivers/media/test-drivers/vivid/Kconfig
@@ -32,7 +32,8 @@
config VIDEO_VIVID_OSD
bool "Enable Framebuffer for testing Output Overlay"
- depends on VIDEO_VIVID && FB
+ depends on VIDEO_VIVID && FB_CORE
+ depends on VIDEO_VIVID=m || FB_CORE=y
default y
select FB_IOMEM_HELPERS
help
diff --git a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c
index 0475630..98d3d12 100644
--- a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c
+++ b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c
@@ -37,6 +37,7 @@
struct pci1xxxx_gpio {
struct auxiliary_device *aux_dev;
void __iomem *reg_base;
+ raw_spinlock_t wa_lock;
struct gpio_chip gpio;
spinlock_t lock;
int irq_base;
@@ -167,7 +168,7 @@ static void pci1xxxx_gpio_irq_ack(struct irq_data *data)
unsigned long flags;
spin_lock_irqsave(&priv->lock, flags);
- pci1xxx_assign_bit(priv->reg_base, INTR_STAT_OFFSET(gpio), (gpio % 32), true);
+ writel(BIT(gpio % 32), priv->reg_base + INTR_STAT_OFFSET(gpio));
spin_unlock_irqrestore(&priv->lock, flags);
}
@@ -257,6 +258,7 @@ static irqreturn_t pci1xxxx_gpio_irq_handler(int irq, void *dev_id)
struct pci1xxxx_gpio *priv = dev_id;
struct gpio_chip *gc = &priv->gpio;
unsigned long int_status = 0;
+ unsigned long wa_flags;
unsigned long flags;
u8 pincount;
int bit;
@@ -280,7 +282,9 @@ static irqreturn_t pci1xxxx_gpio_irq_handler(int irq, void *dev_id)
writel(BIT(bit), priv->reg_base + INTR_STATUS_OFFSET(gpiobank));
spin_unlock_irqrestore(&priv->lock, flags);
irq = irq_find_mapping(gc->irq.domain, (bit + (gpiobank * 32)));
- handle_nested_irq(irq);
+ raw_spin_lock_irqsave(&priv->wa_lock, wa_flags);
+ generic_handle_irq(irq);
+ raw_spin_unlock_irqrestore(&priv->wa_lock, wa_flags);
}
}
spin_lock_irqsave(&priv->lock, flags);
diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index a5f88ec..bc40b94 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -117,6 +117,7 @@
#define MEI_DEV_ID_LNL_M 0xA870 /* Lunar Lake Point M */
+#define MEI_DEV_ID_PTL_H 0xE370 /* Panther Lake H */
#define MEI_DEV_ID_PTL_P 0xE470 /* Panther Lake P */
/*
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index d6ff9d8..3f9c60b 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -124,6 +124,7 @@ static const struct pci_device_id mei_me_pci_tbl[] = {
{MEI_PCI_DEVICE(MEI_DEV_ID_LNL_M, MEI_ME_PCH15_CFG)},
+ {MEI_PCI_DEVICE(MEI_DEV_ID_PTL_H, MEI_ME_PCH15_CFG)},
{MEI_PCI_DEVICE(MEI_DEV_ID_PTL_P, MEI_ME_PCH15_CFG)},
/* required last entry */
diff --git a/drivers/misc/mei/vsc-tp.c b/drivers/misc/mei/vsc-tp.c
index 7be1649..da26a08 100644
--- a/drivers/misc/mei/vsc-tp.c
+++ b/drivers/misc/mei/vsc-tp.c
@@ -36,20 +36,24 @@
#define VSC_TP_XFER_TIMEOUT_BYTES 700
#define VSC_TP_PACKET_PADDING_SIZE 1
#define VSC_TP_PACKET_SIZE(pkt) \
- (sizeof(struct vsc_tp_packet) + le16_to_cpu((pkt)->len) + VSC_TP_CRC_SIZE)
+ (sizeof(struct vsc_tp_packet_hdr) + le16_to_cpu((pkt)->hdr.len) + VSC_TP_CRC_SIZE)
#define VSC_TP_MAX_PACKET_SIZE \
- (sizeof(struct vsc_tp_packet) + VSC_TP_MAX_MSG_SIZE + VSC_TP_CRC_SIZE)
+ (sizeof(struct vsc_tp_packet_hdr) + VSC_TP_MAX_MSG_SIZE + VSC_TP_CRC_SIZE)
#define VSC_TP_MAX_XFER_SIZE \
(VSC_TP_MAX_PACKET_SIZE + VSC_TP_XFER_TIMEOUT_BYTES)
#define VSC_TP_NEXT_XFER_LEN(len, offset) \
- (len + sizeof(struct vsc_tp_packet) + VSC_TP_CRC_SIZE - offset + VSC_TP_PACKET_PADDING_SIZE)
+ (len + sizeof(struct vsc_tp_packet_hdr) + VSC_TP_CRC_SIZE - offset + VSC_TP_PACKET_PADDING_SIZE)
-struct vsc_tp_packet {
+struct vsc_tp_packet_hdr {
__u8 sync;
__u8 cmd;
__le16 len;
__le32 seq;
- __u8 buf[] __counted_by(len);
+};
+
+struct vsc_tp_packet {
+ struct vsc_tp_packet_hdr hdr;
+ __u8 buf[VSC_TP_MAX_XFER_SIZE - sizeof(struct vsc_tp_packet_hdr)];
};
struct vsc_tp {
@@ -67,8 +71,8 @@ struct vsc_tp {
u32 seq;
/* command buffer */
- void *tx_buf;
- void *rx_buf;
+ struct vsc_tp_packet *tx_buf;
+ struct vsc_tp_packet *rx_buf;
atomic_t assert_cnt;
wait_queue_head_t xfer_wait;
@@ -158,12 +162,12 @@ static int vsc_tp_dev_xfer(struct vsc_tp *tp, void *obuf, void *ibuf, size_t len
static int vsc_tp_xfer_helper(struct vsc_tp *tp, struct vsc_tp_packet *pkt,
void *ibuf, u16 ilen)
{
- int ret, offset = 0, cpy_len, src_len, dst_len = sizeof(struct vsc_tp_packet);
+ int ret, offset = 0, cpy_len, src_len, dst_len = sizeof(struct vsc_tp_packet_hdr);
int next_xfer_len = VSC_TP_PACKET_SIZE(pkt) + VSC_TP_XFER_TIMEOUT_BYTES;
- u8 *src, *crc_src, *rx_buf = tp->rx_buf;
+ u8 *src, *crc_src, *rx_buf = (u8 *)tp->rx_buf;
int count_down = VSC_TP_MAX_XFER_COUNT;
u32 recv_crc = 0, crc = ~0;
- struct vsc_tp_packet ack;
+ struct vsc_tp_packet_hdr ack;
u8 *dst = (u8 *)&ack;
bool synced = false;
@@ -280,10 +284,10 @@ int vsc_tp_xfer(struct vsc_tp *tp, u8 cmd, const void *obuf, size_t olen,
guard(mutex)(&tp->mutex);
- pkt->sync = VSC_TP_PACKET_SYNC;
- pkt->cmd = cmd;
- pkt->len = cpu_to_le16(olen);
- pkt->seq = cpu_to_le32(++tp->seq);
+ pkt->hdr.sync = VSC_TP_PACKET_SYNC;
+ pkt->hdr.cmd = cmd;
+ pkt->hdr.len = cpu_to_le16(olen);
+ pkt->hdr.seq = cpu_to_le32(++tp->seq);
memcpy(pkt->buf, obuf, olen);
crc = ~crc32(~0, (u8 *)pkt, sizeof(pkt) + olen);
@@ -320,7 +324,7 @@ int vsc_tp_rom_xfer(struct vsc_tp *tp, const void *obuf, void *ibuf, size_t len)
guard(mutex)(&tp->mutex);
/* rom xfer is big endian */
- cpu_to_be32_array(tp->tx_buf, obuf, words);
+ cpu_to_be32_array((u32 *)tp->tx_buf, obuf, words);
ret = read_poll_timeout(gpiod_get_value_cansleep, ret,
!ret, VSC_TP_ROM_XFER_POLL_DELAY_US,
@@ -336,7 +340,7 @@ int vsc_tp_rom_xfer(struct vsc_tp *tp, const void *obuf, void *ibuf, size_t len)
return ret;
if (ibuf)
- be32_to_cpu_array(ibuf, tp->rx_buf, words);
+ be32_to_cpu_array(ibuf, (u32 *)tp->rx_buf, words);
return ret;
}
@@ -490,11 +494,11 @@ static int vsc_tp_probe(struct spi_device *spi)
if (!tp)
return -ENOMEM;
- tp->tx_buf = devm_kzalloc(dev, VSC_TP_MAX_XFER_SIZE, GFP_KERNEL);
+ tp->tx_buf = devm_kzalloc(dev, sizeof(*tp->tx_buf), GFP_KERNEL);
if (!tp->tx_buf)
return -ENOMEM;
- tp->rx_buf = devm_kzalloc(dev, VSC_TP_MAX_XFER_SIZE, GFP_KERNEL);
+ tp->rx_buf = devm_kzalloc(dev, sizeof(*tp->rx_buf), GFP_KERNEL);
if (!tp->rx_buf)
return -ENOMEM;
diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c
index d294850..c4e5e2c 100644
--- a/drivers/misc/pci_endpoint_test.c
+++ b/drivers/misc/pci_endpoint_test.c
@@ -122,7 +122,6 @@ struct pci_endpoint_test {
struct pci_endpoint_test_data {
enum pci_barno test_reg_bar;
size_t alignment;
- int irq_type;
};
static inline u32 pci_endpoint_test_readl(struct pci_endpoint_test *test,
@@ -948,7 +947,6 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
test_reg_bar = data->test_reg_bar;
test->test_reg_bar = test_reg_bar;
test->alignment = data->alignment;
- test->irq_type = data->irq_type;
}
init_completion(&test->irq_raised);
@@ -970,10 +968,6 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
pci_set_master(pdev);
- ret = pci_endpoint_test_alloc_irq_vectors(test, test->irq_type);
- if (ret)
- goto err_disable_irq;
-
for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) {
if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) {
base = pci_ioremap_bar(pdev, bar);
@@ -1009,10 +1003,6 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
goto err_ida_remove;
}
- ret = pci_endpoint_test_request_irq(test);
- if (ret)
- goto err_kfree_test_name;
-
pci_endpoint_test_get_capabilities(test);
misc_device = &test->miscdev;
@@ -1020,7 +1010,7 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
misc_device->name = kstrdup(name, GFP_KERNEL);
if (!misc_device->name) {
ret = -ENOMEM;
- goto err_release_irq;
+ goto err_kfree_test_name;
}
misc_device->parent = &pdev->dev;
misc_device->fops = &pci_endpoint_test_fops;
@@ -1036,9 +1026,6 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
err_kfree_name:
kfree(misc_device->name);
-err_release_irq:
- pci_endpoint_test_release_irq(test);
-
err_kfree_test_name:
kfree(test->name);
@@ -1051,8 +1038,6 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
pci_iounmap(pdev, test->bar[bar]);
}
-err_disable_irq:
- pci_endpoint_test_free_irq_vectors(test);
pci_release_regions(pdev);
err_disable_pdev:
@@ -1092,23 +1077,19 @@ static void pci_endpoint_test_remove(struct pci_dev *pdev)
static const struct pci_endpoint_test_data default_data = {
.test_reg_bar = BAR_0,
.alignment = SZ_4K,
- .irq_type = PCITEST_IRQ_TYPE_MSI,
};
static const struct pci_endpoint_test_data am654_data = {
.test_reg_bar = BAR_2,
.alignment = SZ_64K,
- .irq_type = PCITEST_IRQ_TYPE_MSI,
};
static const struct pci_endpoint_test_data j721e_data = {
.alignment = 256,
- .irq_type = PCITEST_IRQ_TYPE_MSI,
};
static const struct pci_endpoint_test_data rk3588_data = {
.alignment = SZ_64K,
- .irq_type = PCITEST_IRQ_TYPE_MSI,
};
/*
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 6824131..264e11f 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -691,8 +691,8 @@
config MMC_SDHI
tristate "Renesas SDHI SD/SDIO controller support"
depends on SUPERH || ARCH_RENESAS || COMPILE_TEST
+ depends on (RESET_CONTROLLER && REGULATOR) || !OF
select MMC_TMIO_CORE
- select RESET_CONTROLLER if ARCH_RENESAS
help
This provides support for the SDHI SD/SDIO controller found in
Renesas SuperH, ARM and ARM64 based SoCs
diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index fa6526b..8c83e20 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -1179,7 +1179,7 @@ int renesas_sdhi_probe(struct platform_device *pdev,
if (IS_ERR(rdev)) {
dev_err(dev, "regulator register failed err=%ld", PTR_ERR(rdev));
ret = PTR_ERR(rdev);
- goto efree;
+ goto edisclk;
}
priv->rdev = rdev;
}
@@ -1243,26 +1243,26 @@ int renesas_sdhi_probe(struct platform_device *pdev,
num_irqs = platform_irq_count(pdev);
if (num_irqs < 0) {
ret = num_irqs;
- goto eirq;
+ goto edisclk;
}
/* There must be at least one IRQ source */
if (!num_irqs) {
ret = -ENXIO;
- goto eirq;
+ goto edisclk;
}
for (i = 0; i < num_irqs; i++) {
irq = platform_get_irq(pdev, i);
if (irq < 0) {
ret = irq;
- goto eirq;
+ goto edisclk;
}
ret = devm_request_irq(&pdev->dev, irq, tmio_mmc_irq, 0,
dev_name(&pdev->dev), host);
if (ret)
- goto eirq;
+ goto edisclk;
}
ret = tmio_mmc_host_probe(host);
@@ -1274,8 +1274,6 @@ int renesas_sdhi_probe(struct platform_device *pdev,
return ret;
-eirq:
- tmio_mmc_host_remove(host);
edisclk:
renesas_sdhi_clk_disable(host);
efree:
diff --git a/drivers/mtd/inftlcore.c b/drivers/mtd/inftlcore.c
index 9739387..58c6e17 100644
--- a/drivers/mtd/inftlcore.c
+++ b/drivers/mtd/inftlcore.c
@@ -482,10 +482,11 @@ static inline u16 INFTL_findwriteunit(struct INFTLrecord *inftl, unsigned block)
silly = MAX_LOOPS;
while (thisEUN <= inftl->lastEUN) {
- inftl_read_oob(mtd, (thisEUN * inftl->EraseSize) +
- blockofs, 8, &retlen, (char *)&bci);
-
- status = bci.Status | bci.Status1;
+ if (inftl_read_oob(mtd, (thisEUN * inftl->EraseSize) +
+ blockofs, 8, &retlen, (char *)&bci) < 0)
+ status = SECTOR_IGNORE;
+ else
+ status = bci.Status | bci.Status1;
pr_debug("INFTL: status of block %d in EUN %d is %x\n",
block , writeEUN, status);
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index db516a4..44913ff 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -3,11 +3,8 @@
nandcore-objs := core.o bbt.o
obj-$(CONFIG_MTD_NAND_CORE) += nandcore.o
obj-$(CONFIG_MTD_NAND_ECC_MEDIATEK) += ecc-mtk.o
-ifeq ($(CONFIG_SPI_QPIC_SNAND),y)
obj-$(CONFIG_SPI_QPIC_SNAND) += qpic_common.o
-else
obj-$(CONFIG_MTD_NAND_QCOM) += qpic_common.o
-endif
obj-y += onenand/
obj-y += raw/
obj-y += spi/
diff --git a/drivers/mtd/nand/raw/r852.c b/drivers/mtd/nand/raw/r852.c
index b07c2f8..918974d 100644
--- a/drivers/mtd/nand/raw/r852.c
+++ b/drivers/mtd/nand/raw/r852.c
@@ -387,6 +387,9 @@ static int r852_wait(struct nand_chip *chip)
static int r852_ready(struct nand_chip *chip)
{
struct r852_device *dev = r852_get_dev(nand_to_mtd(chip));
+ if (dev->card_unstable)
+ return 0;
+
return !(r852_read_reg(dev, R852_CARD_STA) & R852_CARD_STA_BUSY);
}
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 950d8e4..8ea183d 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -850,8 +850,9 @@ static int bond_check_dev_link(struct bonding *bond,
struct net_device *slave_dev, int reporting)
{
const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
- struct ifreq ifr;
struct mii_ioctl_data *mii;
+ struct ifreq ifr;
+ int ret;
if (!reporting && !netif_running(slave_dev))
return 0;
@@ -860,9 +861,13 @@ static int bond_check_dev_link(struct bonding *bond,
return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0;
/* Try to get link status using Ethtool first. */
- if (slave_dev->ethtool_ops->get_link)
- return slave_dev->ethtool_ops->get_link(slave_dev) ?
- BMSR_LSTATUS : 0;
+ if (slave_dev->ethtool_ops->get_link) {
+ netdev_lock_ops(slave_dev);
+ ret = slave_dev->ethtool_ops->get_link(slave_dev);
+ netdev_unlock_ops(slave_dev);
+
+ return ret ? BMSR_LSTATUS : 0;
+ }
/* Ethtool can't be used, fallback to MII ioctls. */
if (slave_ops->ndo_eth_ioctl) {
diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index 46201c1..7107a37 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -902,15 +902,16 @@ static int rkcanfd_probe(struct platform_device *pdev)
priv->can.data_bittiming_const = &rkcanfd_data_bittiming_const;
priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
CAN_CTRLMODE_BERR_REPORTING;
- if (!(priv->devtype_data.quirks & RKCANFD_QUIRK_CANFD_BROKEN))
- priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD;
priv->can.do_set_mode = rkcanfd_set_mode;
priv->can.do_get_berr_counter = rkcanfd_get_berr_counter;
priv->ndev = ndev;
match = device_get_match_data(&pdev->dev);
- if (match)
+ if (match) {
priv->devtype_data = *(struct rkcanfd_devtype_data *)match;
+ if (!(priv->devtype_data.quirks & RKCANFD_QUIRK_CANFD_BROKEN))
+ priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD;
+ }
err = can_rx_offload_add_manual(ndev, &priv->offload,
RKCANFD_NAPI_WEIGHT);
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 61d164f..e5ba718 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -737,6 +737,15 @@ static void b53_enable_mib(struct b53_device *dev)
b53_write8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, gc);
}
+static void b53_enable_stp(struct b53_device *dev)
+{
+ u8 gc;
+
+ b53_read8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, &gc);
+ gc |= GC_RX_BPDU_EN;
+ b53_write8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, gc);
+}
+
static u16 b53_default_pvid(struct b53_device *dev)
{
if (is5325(dev) || is5365(dev))
@@ -876,6 +885,7 @@ static int b53_switch_reset(struct b53_device *dev)
}
b53_enable_mib(dev);
+ b53_enable_stp(dev);
return b53_flush_arl(dev, FAST_AGE_STATIC);
}
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index d70399b..c5d6628 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -2419,6 +2419,9 @@ mt7531_setup_common(struct dsa_switch *ds)
struct mt7530_priv *priv = ds->priv;
int ret, i;
+ ds->assisted_learning_on_cpu_port = true;
+ ds->mtu_enforcement_ingress = true;
+
mt753x_trap_frames(priv);
/* Enable and reset MIB counters */
@@ -2571,9 +2574,6 @@ mt7531_setup(struct dsa_switch *ds)
if (ret)
return ret;
- ds->assisted_learning_on_cpu_port = true;
- ds->mtu_enforcement_ingress = true;
-
return 0;
}
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 29a89ab..08db846 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -1852,6 +1852,8 @@ static int mv88e6xxx_vtu_get(struct mv88e6xxx_chip *chip, u16 vid,
if (!chip->info->ops->vtu_getnext)
return -EOPNOTSUPP;
+ memset(entry, 0, sizeof(*entry));
+
entry->vid = vid ? vid - 1 : mv88e6xxx_max_vid(chip);
entry->valid = false;
@@ -1960,7 +1962,16 @@ static int mv88e6xxx_mst_put(struct mv88e6xxx_chip *chip, u8 sid)
struct mv88e6xxx_mst *mst, *tmp;
int err;
- if (!sid)
+ /* If the SID is zero, it is for a VLAN mapped to the default MSTI,
+ * and mv88e6xxx_stu_setup() made sure it is always present, and thus,
+ * should not be removed here.
+ *
+ * If the chip lacks STU support, numerically the "sid" variable will
+ * happen to also be zero, but we don't want to rely on that fact, so
+ * we explicitly test that first. In that case, there is also nothing
+ * to do here.
+ */
+ if (!mv88e6xxx_has_stu(chip) || !sid)
return 0;
list_for_each_entry_safe(mst, tmp, &chip->msts, node) {
diff --git a/drivers/net/dsa/mv88e6xxx/devlink.c b/drivers/net/dsa/mv88e6xxx/devlink.c
index 795c8df..195460a 100644
--- a/drivers/net/dsa/mv88e6xxx/devlink.c
+++ b/drivers/net/dsa/mv88e6xxx/devlink.c
@@ -736,7 +736,8 @@ void mv88e6xxx_teardown_devlink_regions_global(struct dsa_switch *ds)
int i;
for (i = 0; i < ARRAY_SIZE(mv88e6xxx_regions); i++)
- dsa_devlink_region_destroy(chip->regions[i]);
+ if (chip->regions[i])
+ dsa_devlink_region_destroy(chip->regions[i]);
}
void mv88e6xxx_teardown_devlink_regions_port(struct dsa_switch *ds, int port)
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 940f1b7..7b35d24 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -1543,7 +1543,7 @@ static void vsc9959_tas_clock_adjust(struct ocelot *ocelot)
struct tc_taprio_qopt_offload *taprio;
struct ocelot_port *ocelot_port;
struct timespec64 base_ts;
- int port;
+ int i, port;
u32 val;
mutex_lock(&ocelot->fwd_domain_lock);
@@ -1575,6 +1575,9 @@ static void vsc9959_tas_clock_adjust(struct ocelot *ocelot)
QSYS_PARAM_CFG_REG_3_BASE_TIME_SEC_MSB_M,
QSYS_PARAM_CFG_REG_3);
+ for (i = 0; i < taprio->num_entries; i++)
+ vsc9959_tas_gcl_set(ocelot, i, &taprio->entries[i]);
+
ocelot_rmw(ocelot, QSYS_TAS_PARAM_CFG_CTRL_CONFIG_CHANGE,
QSYS_TAS_PARAM_CFG_CTRL_CONFIG_CHANGE,
QSYS_TAS_PARAM_CFG_CTRL);
diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c
index c83a0a8..506f682 100644
--- a/drivers/net/ethernet/amd/pds_core/adminq.c
+++ b/drivers/net/ethernet/amd/pds_core/adminq.c
@@ -5,11 +5,6 @@
#include "core.h"
-struct pdsc_wait_context {
- struct pdsc_qcq *qcq;
- struct completion wait_completion;
-};
-
static int pdsc_process_notifyq(struct pdsc_qcq *qcq)
{
union pds_core_notifyq_comp *comp;
@@ -109,10 +104,10 @@ void pdsc_process_adminq(struct pdsc_qcq *qcq)
q_info = &q->info[q->tail_idx];
q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1);
- /* Copy out the completion data */
- memcpy(q_info->dest, comp, sizeof(*comp));
-
- complete_all(&q_info->wc->wait_completion);
+ if (!completion_done(&q_info->completion)) {
+ memcpy(q_info->dest, comp, sizeof(*comp));
+ complete(&q_info->completion);
+ }
if (cq->tail_idx == cq->num_descs - 1)
cq->done_color = !cq->done_color;
@@ -162,8 +157,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data)
static int __pdsc_adminq_post(struct pdsc *pdsc,
struct pdsc_qcq *qcq,
union pds_core_adminq_cmd *cmd,
- union pds_core_adminq_comp *comp,
- struct pdsc_wait_context *wc)
+ union pds_core_adminq_comp *comp)
{
struct pdsc_queue *q = &qcq->q;
struct pdsc_q_info *q_info;
@@ -205,9 +199,9 @@ static int __pdsc_adminq_post(struct pdsc *pdsc,
/* Post the request */
index = q->head_idx;
q_info = &q->info[index];
- q_info->wc = wc;
q_info->dest = comp;
memcpy(q_info->desc, cmd, sizeof(*cmd));
+ reinit_completion(&q_info->completion);
dev_dbg(pdsc->dev, "head_idx %d tail_idx %d\n",
q->head_idx, q->tail_idx);
@@ -231,16 +225,13 @@ int pdsc_adminq_post(struct pdsc *pdsc,
union pds_core_adminq_comp *comp,
bool fast_poll)
{
- struct pdsc_wait_context wc = {
- .wait_completion =
- COMPLETION_INITIALIZER_ONSTACK(wc.wait_completion),
- };
unsigned long poll_interval = 1;
unsigned long poll_jiffies;
unsigned long time_limit;
unsigned long time_start;
unsigned long time_done;
unsigned long remaining;
+ struct completion *wc;
int err = 0;
int index;
@@ -250,20 +241,19 @@ int pdsc_adminq_post(struct pdsc *pdsc,
return -ENXIO;
}
- wc.qcq = &pdsc->adminqcq;
- index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp, &wc);
+ index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp);
if (index < 0) {
err = index;
goto err_out;
}
+ wc = &pdsc->adminqcq.q.info[index].completion;
time_start = jiffies;
time_limit = time_start + HZ * pdsc->devcmd_timeout;
do {
/* Timeslice the actual wait to catch IO errors etc early */
poll_jiffies = msecs_to_jiffies(poll_interval);
- remaining = wait_for_completion_timeout(&wc.wait_completion,
- poll_jiffies);
+ remaining = wait_for_completion_timeout(wc, poll_jiffies);
if (remaining)
break;
@@ -292,9 +282,11 @@ int pdsc_adminq_post(struct pdsc *pdsc,
dev_dbg(pdsc->dev, "%s: elapsed %d msecs\n",
__func__, jiffies_to_msecs(time_done - time_start));
- /* Check the results */
- if (time_after_eq(time_done, time_limit))
+ /* Check the results and clear an un-completed timeout */
+ if (time_after_eq(time_done, time_limit) && !completion_done(wc)) {
err = -ETIMEDOUT;
+ complete(wc);
+ }
dev_dbg(pdsc->dev, "read admin queue completion idx %d:\n", index);
dynamic_hex_dump("comp ", DUMP_PREFIX_OFFSET, 16, 1,
diff --git a/drivers/net/ethernet/amd/pds_core/auxbus.c b/drivers/net/ethernet/amd/pds_core/auxbus.c
index eeb72b1..92f359f 100644
--- a/drivers/net/ethernet/amd/pds_core/auxbus.c
+++ b/drivers/net/ethernet/amd/pds_core/auxbus.c
@@ -107,9 +107,6 @@ int pds_client_adminq_cmd(struct pds_auxiliary_dev *padev,
dev_dbg(pf->dev, "%s: %s opcode %d\n",
__func__, dev_name(&padev->aux_dev.dev), req->opcode);
- if (pf->state)
- return -ENXIO;
-
/* Wrap the client's request */
cmd.client_request.opcode = PDS_AQ_CMD_CLIENT_CMD;
cmd.client_request.client_id = cpu_to_le16(padev->client_id);
@@ -189,7 +186,6 @@ void pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf,
pds_client_unregister(pf, padev->client_id);
auxiliary_device_delete(&padev->aux_dev);
auxiliary_device_uninit(&padev->aux_dev);
- padev->client_id = 0;
*pd_ptr = NULL;
mutex_unlock(&pf->config_lock);
diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index 1eb0d92..9512aa4 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -167,8 +167,10 @@ static void pdsc_q_map(struct pdsc_queue *q, void *base, dma_addr_t base_pa)
q->base = base;
q->base_pa = base_pa;
- for (i = 0, cur = q->info; i < q->num_descs; i++, cur++)
+ for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) {
cur->desc = base + (i * q->desc_size);
+ init_completion(&cur->completion);
+ }
}
static void pdsc_cq_map(struct pdsc_cq *cq, void *base, dma_addr_t base_pa)
@@ -325,10 +327,7 @@ static int pdsc_core_init(struct pdsc *pdsc)
size_t sz;
int err;
- /* Scale the descriptor ring length based on number of CPUs and VFs */
- numdescs = max_t(int, PDSC_ADMINQ_MIN_LENGTH, num_online_cpus());
- numdescs += 2 * pci_sriov_get_totalvfs(pdsc->pdev);
- numdescs = roundup_pow_of_two(numdescs);
+ numdescs = PDSC_ADMINQ_MAX_LENGTH;
err = pdsc_qcq_alloc(pdsc, PDS_CORE_QTYPE_ADMINQ, 0, "adminq",
PDS_CORE_QCQ_F_CORE | PDS_CORE_QCQ_F_INTR,
numdescs,
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index 0bf320c..0b53a1f 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -16,7 +16,7 @@
#define PDSC_WATCHDOG_SECS 5
#define PDSC_QUEUE_NAME_MAX_SZ 16
-#define PDSC_ADMINQ_MIN_LENGTH 16 /* must be a power of two */
+#define PDSC_ADMINQ_MAX_LENGTH 16 /* must be a power of two */
#define PDSC_NOTIFYQ_LENGTH 64 /* must be a power of two */
#define PDSC_TEARDOWN_RECOVERY false
#define PDSC_TEARDOWN_REMOVING true
@@ -96,7 +96,7 @@ struct pdsc_q_info {
unsigned int bytes;
unsigned int nbufs;
struct pdsc_buf_info bufs[PDS_CORE_MAX_FRAGS];
- struct pdsc_wait_context *wc;
+ struct completion completion;
void *dest;
};
diff --git a/drivers/net/ethernet/amd/pds_core/debugfs.c b/drivers/net/ethernet/amd/pds_core/debugfs.c
index ac37a4e..04c5e3a 100644
--- a/drivers/net/ethernet/amd/pds_core/debugfs.c
+++ b/drivers/net/ethernet/amd/pds_core/debugfs.c
@@ -154,8 +154,9 @@ void pdsc_debugfs_add_qcq(struct pdsc *pdsc, struct pdsc_qcq *qcq)
debugfs_create_u32("index", 0400, intr_dentry, &intr->index);
debugfs_create_u32("vector", 0400, intr_dentry, &intr->vector);
- intr_ctrl_regset = kzalloc(sizeof(*intr_ctrl_regset),
- GFP_KERNEL);
+ intr_ctrl_regset = devm_kzalloc(pdsc->dev,
+ sizeof(*intr_ctrl_regset),
+ GFP_KERNEL);
if (!intr_ctrl_regset)
return;
intr_ctrl_regset->regs = intr_ctrl_regs;
diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c
index c5c787d..d8dc39d 100644
--- a/drivers/net/ethernet/amd/pds_core/devlink.c
+++ b/drivers/net/ethernet/amd/pds_core/devlink.c
@@ -105,7 +105,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
.fw_control.opcode = PDS_CORE_CMD_FW_CONTROL,
.fw_control.oper = PDS_CORE_FW_GET_LIST,
};
- struct pds_core_fw_list_info fw_list;
+ struct pds_core_fw_list_info fw_list = {};
struct pdsc *pdsc = devlink_priv(dl);
union pds_core_dev_comp comp;
char buf[32];
@@ -118,8 +118,6 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
if (!err)
memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list));
mutex_unlock(&pdsc->devcmd_lock);
- if (err && err != -EIO)
- return err;
listlen = min(fw_list.num_fw_slots, ARRAY_SIZE(fw_list.fw_names));
for (i = 0; i < listlen; i++) {
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
index 230726d..d41b58f 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
@@ -373,8 +373,13 @@ static int xgbe_map_rx_buffer(struct xgbe_prv_data *pdata,
}
/* Set up the header page info */
- xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
- XGBE_SKB_ALLOC_SIZE);
+ if (pdata->netdev->features & NETIF_F_RXCSUM) {
+ xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
+ XGBE_SKB_ALLOC_SIZE);
+ } else {
+ xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
+ pdata->rx_buf_size);
+ }
/* Set up the buffer page info */
xgbe_set_buffer_data(&rdata->rx.buf, &ring->rx_buf_pa,
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index f393228..f1b0fb0 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -320,6 +320,18 @@ static void xgbe_config_sph_mode(struct xgbe_prv_data *pdata)
XGMAC_IOWRITE_BITS(pdata, MAC_RCR, HDSMS, XGBE_SPH_HDSMS_SIZE);
}
+static void xgbe_disable_sph_mode(struct xgbe_prv_data *pdata)
+{
+ unsigned int i;
+
+ for (i = 0; i < pdata->channel_count; i++) {
+ if (!pdata->channel[i]->rx_ring)
+ break;
+
+ XGMAC_DMA_IOWRITE_BITS(pdata->channel[i], DMA_CH_CR, SPH, 0);
+ }
+}
+
static int xgbe_write_rss_reg(struct xgbe_prv_data *pdata, unsigned int type,
unsigned int index, unsigned int val)
{
@@ -3545,8 +3557,12 @@ static int xgbe_init(struct xgbe_prv_data *pdata)
xgbe_config_tx_coalesce(pdata);
xgbe_config_rx_buffer_size(pdata);
xgbe_config_tso_mode(pdata);
- xgbe_config_sph_mode(pdata);
- xgbe_config_rss(pdata);
+
+ if (pdata->netdev->features & NETIF_F_RXCSUM) {
+ xgbe_config_sph_mode(pdata);
+ xgbe_config_rss(pdata);
+ }
+
desc_if->wrapper_tx_desc_init(pdata);
desc_if->wrapper_rx_desc_init(pdata);
xgbe_enable_dma_interrupts(pdata);
@@ -3702,5 +3718,9 @@ void xgbe_init_function_ptrs_dev(struct xgbe_hw_if *hw_if)
hw_if->disable_vxlan = xgbe_disable_vxlan;
hw_if->set_vxlan_id = xgbe_set_vxlan_id;
+ /* For Split Header*/
+ hw_if->enable_sph = xgbe_config_sph_mode;
+ hw_if->disable_sph = xgbe_disable_sph_mode;
+
DBGPR("<--xgbe_init_function_ptrs\n");
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index d84a310..8e09ad8 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -2257,10 +2257,17 @@ static int xgbe_set_features(struct net_device *netdev,
if (ret)
return ret;
- if ((features & NETIF_F_RXCSUM) && !rxcsum)
+ if ((features & NETIF_F_RXCSUM) && !rxcsum) {
+ hw_if->enable_sph(pdata);
+ hw_if->enable_vxlan(pdata);
hw_if->enable_rx_csum(pdata);
- else if (!(features & NETIF_F_RXCSUM) && rxcsum)
+ schedule_work(&pdata->restart_work);
+ } else if (!(features & NETIF_F_RXCSUM) && rxcsum) {
+ hw_if->disable_sph(pdata);
+ hw_if->disable_vxlan(pdata);
hw_if->disable_rx_csum(pdata);
+ schedule_work(&pdata->restart_work);
+ }
if ((features & NETIF_F_HW_VLAN_CTAG_RX) && !rxvlan)
hw_if->enable_rx_vlan_stripping(pdata);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index d85386c..ed5d43c 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -865,6 +865,10 @@ struct xgbe_hw_if {
void (*enable_vxlan)(struct xgbe_prv_data *);
void (*disable_vxlan)(struct xgbe_prv_data *);
void (*set_vxlan_id)(struct xgbe_prv_data *);
+
+ /* For Split Header */
+ void (*enable_sph)(struct xgbe_prv_data *pdata);
+ void (*disable_sph)(struct xgbe_prv_data *pdata);
};
/* This structure represents implementation specific routines for an
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index eeec8bf..1bd4313 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -143,7 +143,7 @@
depends on PTP_1588_CLOCK_OPTIONAL
select FW_LOADER
select ZLIB_INFLATE
- select LIBCRC32C
+ select CRC32
select MDIO
help
This driver supports Broadcom NetXtremeII 10 gigabit Ethernet cards.
@@ -207,7 +207,7 @@
depends on PCI
depends on PTP_1588_CLOCK_OPTIONAL
select FW_LOADER
- select LIBCRC32C
+ select CRC32
select NET_DEVLINK
select PAGE_POOL
select DIMLIB
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 8725e1e..86a5de4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -787,7 +787,7 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
dev_kfree_skb_any(skb);
tx_kick_pending:
if (BNXT_TX_PTP_IS_SET(lflags)) {
- txr->tx_buf_ring[txr->tx_prod].is_ts_pkt = 0;
+ txr->tx_buf_ring[RING_TX(bp, txr->tx_prod)].is_ts_pkt = 0;
atomic64_inc(&bp->ptp_cfg->stats.ts_err);
if (!(bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP))
/* set SKB to err so PTP worker will clean up */
@@ -795,7 +795,7 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
}
if (txr->kick_pending)
bnxt_txr_db_kick(bp, txr, txr->tx_prod);
- txr->tx_buf_ring[txr->tx_prod].skb = NULL;
+ txr->tx_buf_ring[RING_TX(bp, txr->tx_prod)].skb = NULL;
dev_core_stats_tx_dropped_inc(dev);
return NETDEV_TX_OK;
}
@@ -2015,6 +2015,7 @@ static struct sk_buff *bnxt_rx_vlan(struct sk_buff *skb, u8 cmp_type,
}
return skb;
vlan_err:
+ skb_mark_for_recycle(skb);
dev_kfree_skb(skb);
return NULL;
}
@@ -3414,6 +3415,9 @@ static void bnxt_free_tx_skbs(struct bnxt *bp)
bnxt_free_one_tx_ring_skbs(bp, txr, i);
}
+
+ if (bp->ptp_cfg && !(bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP))
+ bnxt_ptp_free_txts_skbs(bp->ptp_cfg);
}
static void bnxt_free_one_rx_ring(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
@@ -11599,6 +11603,9 @@ static void bnxt_init_napi(struct bnxt *bp)
poll_fn = bnxt_poll_p5;
else if (BNXT_CHIP_TYPE_NITRO_A0(bp))
cp_nr_rings--;
+
+ set_bit(BNXT_STATE_NAPI_DISABLED, &bp->state);
+
for (i = 0; i < cp_nr_rings; i++) {
bnapi = bp->bnapi[i];
netif_napi_add_config_locked(bp->dev, &bnapi->napi, poll_fn,
@@ -12318,12 +12325,15 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
{
struct hwrm_func_drv_if_change_output *resp;
struct hwrm_func_drv_if_change_input *req;
- bool fw_reset = !bp->irq_tbl;
bool resc_reinit = false;
bool caps_change = false;
int rc, retry = 0;
+ bool fw_reset;
u32 flags = 0;
+ fw_reset = (bp->fw_reset_state == BNXT_FW_RESET_STATE_ABORT);
+ bp->fw_reset_state = 0;
+
if (!(bp->fw_cap & BNXT_FW_CAP_IF_CHANGE))
return 0;
@@ -12392,13 +12402,8 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
return rc;
}
+ /* IRQ will be initialized later in bnxt_request_irq()*/
bnxt_clear_int_mode(bp);
- rc = bnxt_init_int_mode(bp);
- if (rc) {
- clear_bit(BNXT_STATE_FW_RESET_DET, &bp->state);
- netdev_err(bp->dev, "init int mode failed\n");
- return rc;
- }
}
rc = bnxt_cancel_reservations(bp, fw_reset);
}
@@ -12797,8 +12802,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
/* VF-reps may need to be re-opened after the PF is re-opened */
if (BNXT_PF(bp))
bnxt_vf_reps_open(bp);
- if (bp->ptp_cfg && !(bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP))
- WRITE_ONCE(bp->ptp_cfg->tx_avail, BNXT_MAX_TX_TS);
bnxt_ptp_init_rtc(bp, true);
bnxt_ptp_cfg_tstamp_filters(bp);
if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
@@ -14833,7 +14836,7 @@ static void bnxt_fw_reset_abort(struct bnxt *bp, int rc)
clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF)
bnxt_dl_health_fw_status_update(bp, false);
- bp->fw_reset_state = 0;
+ bp->fw_reset_state = BNXT_FW_RESET_STATE_ABORT;
netif_close(bp->dev);
}
@@ -16003,8 +16006,8 @@ static void bnxt_remove_one(struct pci_dev *pdev)
bnxt_rdma_aux_device_del(bp);
- bnxt_ptp_clear(bp);
unregister_netdev(dev);
+ bnxt_ptp_clear(bp);
bnxt_rdma_aux_device_uninit(bp);
@@ -16931,10 +16934,9 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
if (!err)
result = PCI_ERS_RESULT_RECOVERED;
+ /* IRQ will be initialized later in bnxt_io_resume */
bnxt_ulp_irq_stop(bp);
bnxt_clear_int_mode(bp);
- err = bnxt_init_int_mode(bp);
- bnxt_ulp_irq_restart(bp, err);
}
reset_exit:
@@ -16963,10 +16965,13 @@ static void bnxt_io_resume(struct pci_dev *pdev)
err = bnxt_hwrm_func_qcaps(bp);
if (!err) {
- if (netif_running(netdev))
+ if (netif_running(netdev)) {
err = bnxt_open(netdev);
- else
+ } else {
err = bnxt_reserve_rings(bp, true);
+ if (!err)
+ err = bnxt_init_int_mode(bp);
+ }
}
if (!err)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 21726cf..bc8b3b7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2614,6 +2614,7 @@ struct bnxt {
#define BNXT_FW_RESET_STATE_POLL_FW 4
#define BNXT_FW_RESET_STATE_OPENING 5
#define BNXT_FW_RESET_STATE_POLL_FW_DOWN 6
+#define BNXT_FW_RESET_STATE_ABORT 7
u16 fw_reset_min_dsecs;
#define BNXT_DFLT_FW_RST_MIN_DSECS 20
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
index 5576e7c..a000d3f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
@@ -110,20 +110,30 @@ static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg,
}
}
- if (info->dest_buf) {
- if ((info->seg_start + off + len) <=
- BNXT_COREDUMP_BUF_LEN(info->buf_len)) {
- memcpy(info->dest_buf + off, dma_buf, len);
- } else {
- rc = -ENOBUFS;
- break;
- }
- }
-
if (cmn_req->req_type ==
cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE))
info->dest_buf_size += len;
+ if (info->dest_buf) {
+ if ((info->seg_start + off + len) <=
+ BNXT_COREDUMP_BUF_LEN(info->buf_len)) {
+ u16 copylen = min_t(u16, len,
+ info->dest_buf_size - off);
+
+ memcpy(info->dest_buf + off, dma_buf, copylen);
+ if (copylen < len)
+ break;
+ } else {
+ rc = -ENOBUFS;
+ if (cmn_req->req_type ==
+ cpu_to_le16(HWRM_DBG_COREDUMP_LIST)) {
+ kfree(info->dest_buf);
+ info->dest_buf = NULL;
+ }
+ break;
+ }
+ }
+
if (!(cmn_resp->flags & HWRM_DBG_CMN_FLAGS_MORE))
break;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 48dd592..f5d490b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2062,6 +2062,17 @@ static int bnxt_get_regs_len(struct net_device *dev)
return reg_len;
}
+#define BNXT_PCIE_32B_ENTRY(start, end) \
+ { offsetof(struct pcie_ctx_hw_stats, start), \
+ offsetof(struct pcie_ctx_hw_stats, end) }
+
+static const struct {
+ u16 start;
+ u16 end;
+} bnxt_pcie_32b_entries[] = {
+ BNXT_PCIE_32B_ENTRY(pcie_ltssm_histogram[0], pcie_ltssm_histogram[3]),
+};
+
static void bnxt_get_regs(struct net_device *dev, struct ethtool_regs *regs,
void *_p)
{
@@ -2094,12 +2105,27 @@ static void bnxt_get_regs(struct net_device *dev, struct ethtool_regs *regs,
req->pcie_stat_host_addr = cpu_to_le64(hw_pcie_stats_addr);
rc = hwrm_req_send(bp, req);
if (!rc) {
- __le64 *src = (__le64 *)hw_pcie_stats;
- u64 *dst = (u64 *)(_p + BNXT_PXP_REG_LEN);
- int i;
+ u8 *dst = (u8 *)(_p + BNXT_PXP_REG_LEN);
+ u8 *src = (u8 *)hw_pcie_stats;
+ int i, j;
- for (i = 0; i < sizeof(*hw_pcie_stats) / sizeof(__le64); i++)
- dst[i] = le64_to_cpu(src[i]);
+ for (i = 0, j = 0; i < sizeof(*hw_pcie_stats); ) {
+ if (i >= bnxt_pcie_32b_entries[j].start &&
+ i <= bnxt_pcie_32b_entries[j].end) {
+ u32 *dst32 = (u32 *)(dst + i);
+
+ *dst32 = le32_to_cpu(*(__le32 *)(src + i));
+ i += 4;
+ if (i > bnxt_pcie_32b_entries[j].end &&
+ j < ARRAY_SIZE(bnxt_pcie_32b_entries) - 1)
+ j++;
+ } else {
+ u64 *dst64 = (u64 *)(dst + i);
+
+ *dst64 = le64_to_cpu(*(__le64 *)(src + i));
+ i += 8;
+ }
+ }
}
hwrm_req_drop(bp, req);
}
@@ -4991,6 +5017,7 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
if (!bp->num_tests || !BNXT_PF(bp))
return;
+ memset(buf, 0, sizeof(u64) * bp->num_tests);
if (etest->flags & ETH_TEST_FL_OFFLINE &&
bnxt_ulp_registered(bp->edev)) {
etest->flags |= ETH_TEST_FL_FAILED;
@@ -4998,7 +5025,6 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
return;
}
- memset(buf, 0, sizeof(u64) * bp->num_tests);
if (!netif_running(dev)) {
etest->flags |= ETH_TEST_FL_FAILED;
return;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index 2d4e19b..0669d43 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -794,6 +794,27 @@ static long bnxt_ptp_ts_aux_work(struct ptp_clock_info *ptp_info)
return HZ;
}
+void bnxt_ptp_free_txts_skbs(struct bnxt_ptp_cfg *ptp)
+{
+ struct bnxt_ptp_tx_req *txts_req;
+ u16 cons = ptp->txts_cons;
+
+ /* make sure ptp aux worker finished with
+ * possible BNXT_STATE_OPEN set
+ */
+ ptp_cancel_worker_sync(ptp->ptp_clock);
+
+ ptp->tx_avail = BNXT_MAX_TX_TS;
+ while (cons != ptp->txts_prod) {
+ txts_req = &ptp->txts_req[cons];
+ if (!IS_ERR_OR_NULL(txts_req->tx_skb))
+ dev_kfree_skb_any(txts_req->tx_skb);
+ cons = NEXT_TXTS(cons);
+ }
+ ptp->txts_cons = cons;
+ ptp_schedule_worker(ptp->ptp_clock, 0);
+}
+
int bnxt_ptp_get_txts_prod(struct bnxt_ptp_cfg *ptp, u16 *prod)
{
spin_lock_bh(&ptp->ptp_tx_lock);
@@ -1105,7 +1126,6 @@ int bnxt_ptp_init(struct bnxt *bp)
void bnxt_ptp_clear(struct bnxt *bp)
{
struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
- int i;
if (!ptp)
return;
@@ -1117,12 +1137,5 @@ void bnxt_ptp_clear(struct bnxt *bp)
kfree(ptp->ptp_info.pin_config);
ptp->ptp_info.pin_config = NULL;
- for (i = 0; i < BNXT_MAX_TX_TS; i++) {
- if (ptp->txts_req[i].tx_skb) {
- dev_kfree_skb_any(ptp->txts_req[i].tx_skb);
- ptp->txts_req[i].tx_skb = NULL;
- }
- }
-
bnxt_unmap_ptp_regs(bp);
}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
index a95f05e..0481161 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
@@ -162,6 +162,7 @@ int bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp);
void bnxt_ptp_reapply_pps(struct bnxt *bp);
int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr);
int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr);
+void bnxt_ptp_free_txts_skbs(struct bnxt_ptp_cfg *ptp);
int bnxt_ptp_get_txts_prod(struct bnxt_ptp_cfg *ptp, u16 *prod);
void bnxt_get_tx_ts_p5(struct bnxt *bp, struct sk_buff *skb, u16 prod);
int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts);
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index ca742cc..7dae5aa 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -70,8 +70,8 @@
depends on 64BIT && PCI
depends on PCI
depends on PTP_1588_CLOCK_OPTIONAL
+ select CRC32
select FW_LOADER
- select LIBCRC32C
select LIQUIDIO_CORE
select NET_DEVLINK
help
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index 7f3f5af..1546c3d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -2270,6 +2270,7 @@ int cxgb4_init_ethtool_filters(struct adapter *adap)
eth_filter->port[i].bmap = bitmap_zalloc(nentries, GFP_KERNEL);
if (!eth_filter->port[i].bmap) {
ret = -ENOMEM;
+ kvfree(eth_filter->port[i].loc_array);
goto free_eth_finfo;
}
}
diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index d88fbec..232e839 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -352,7 +352,7 @@ parse_eeprom (struct net_device *dev)
eth_hw_addr_set(dev, psrom->mac_addr);
if (np->chip_id == CHIP_IP1000A) {
- np->led_mode = psrom->led_mode;
+ np->led_mode = le16_to_cpu(psrom->led_mode);
return 0;
}
diff --git a/drivers/net/ethernet/dlink/dl2k.h b/drivers/net/ethernet/dlink/dl2k.h
index 195dc6c..0e33e2e 100644
--- a/drivers/net/ethernet/dlink/dl2k.h
+++ b/drivers/net/ethernet/dlink/dl2k.h
@@ -335,7 +335,7 @@ typedef struct t_SROM {
u16 sub_system_id; /* 0x06 */
u16 pci_base_1; /* 0x08 (IP1000A only) */
u16 pci_base_2; /* 0x0a (IP1000A only) */
- u16 led_mode; /* 0x0c (IP1000A only) */
+ __le16 led_mode; /* 0x0c (IP1000A only) */
u16 reserved1[9]; /* 0x0e-0x1f */
u8 mac_addr[6]; /* 0x20-0x25 */
u8 reserved2[10]; /* 0x26-0x2f */
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 2106861..3ee52f4 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -1850,6 +1850,16 @@ static void enetc_xdp_drop(struct enetc_bdr *rx_ring, int rx_ring_first,
}
}
+static void enetc_bulk_flip_buff(struct enetc_bdr *rx_ring, int rx_ring_first,
+ int rx_ring_last)
+{
+ while (rx_ring_first != rx_ring_last) {
+ enetc_flip_rx_buff(rx_ring,
+ &rx_ring->rx_swbd[rx_ring_first]);
+ enetc_bdr_idx_inc(rx_ring, &rx_ring_first);
+ }
+}
+
static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
struct napi_struct *napi, int work_limit,
struct bpf_prog *prog)
@@ -1868,11 +1878,10 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
while (likely(rx_frm_cnt < work_limit)) {
union enetc_rx_bd *rxbd, *orig_rxbd;
- int orig_i, orig_cleaned_cnt;
struct xdp_buff xdp_buff;
struct sk_buff *skb;
+ int orig_i, err;
u32 bd_status;
- int err;
rxbd = enetc_rxbd(rx_ring, i);
bd_status = le32_to_cpu(rxbd->r.lstatus);
@@ -1887,7 +1896,6 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
break;
orig_rxbd = rxbd;
- orig_cleaned_cnt = cleaned_cnt;
orig_i = i;
enetc_build_xdp_buff(rx_ring, bd_status, &rxbd, &i,
@@ -1915,15 +1923,21 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
rx_ring->stats.xdp_drops++;
break;
case XDP_PASS:
- rxbd = orig_rxbd;
- cleaned_cnt = orig_cleaned_cnt;
- i = orig_i;
-
- skb = enetc_build_skb(rx_ring, bd_status, &rxbd,
- &i, &cleaned_cnt,
- ENETC_RXB_DMA_SIZE_XDP);
- if (unlikely(!skb))
+ skb = xdp_build_skb_from_buff(&xdp_buff);
+ /* Probably under memory pressure, stop NAPI */
+ if (unlikely(!skb)) {
+ enetc_xdp_drop(rx_ring, orig_i, i);
+ rx_ring->stats.xdp_drops++;
goto out;
+ }
+
+ enetc_get_offloads(rx_ring, orig_rxbd, skb);
+
+ /* These buffers are about to be owned by the stack.
+ * Update our buffer cache (the rx_swbd array elements)
+ * with their other page halves.
+ */
+ enetc_bulk_flip_buff(rx_ring, orig_i, i);
napi_gro_receive(napi, skb);
break;
@@ -1965,11 +1979,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
enetc_xdp_drop(rx_ring, orig_i, i);
rx_ring->stats.xdp_redirect_failures++;
} else {
- while (orig_i != i) {
- enetc_flip_rx_buff(rx_ring,
- &rx_ring->rx_swbd[orig_i]);
- enetc_bdr_idx_inc(rx_ring, &orig_i);
- }
+ enetc_bulk_flip_buff(rx_ring, orig_i, i);
xdp_redirect_frm_cnt++;
rx_ring->stats.xdp_redirect++;
}
@@ -3362,7 +3372,8 @@ static int enetc_int_vector_init(struct enetc_ndev_priv *priv, int i,
bdr->buffer_offset = ENETC_RXB_PAD;
priv->rx_ring[i] = bdr;
- err = xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0);
+ err = __xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0,
+ ENETC_RXB_DMA_SIZE_XDP);
if (err)
goto free_vector;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index a86cfeb..17e9bdd 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -714,7 +714,12 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
txq->bd.cur = bdp;
/* Trigger transmission start */
- writel(0, txq->bd.reg_desc_active);
+ if (!(fep->quirks & FEC_QUIRK_ERR007885) ||
+ !readl(txq->bd.reg_desc_active) ||
+ !readl(txq->bd.reg_desc_active) ||
+ !readl(txq->bd.reg_desc_active) ||
+ !readl(txq->bd.reg_desc_active))
+ writel(0, txq->bd.reg_desc_active);
return 0;
}
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
index f8cdab6..7725cb0 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
@@ -108,14 +108,16 @@ struct hbg_irq_info {
bool re_enable;
bool need_print;
bool need_reset;
- u64 count;
- void (*irq_handle)(struct hbg_priv *priv, struct hbg_irq_info *info);
+ void (*irq_handle)(struct hbg_priv *priv,
+ const struct hbg_irq_info *info);
};
struct hbg_vector {
char name[HBG_VECTOR_NUM][32];
- struct hbg_irq_info *info_array;
+
+ u64 *stats_array;
+ const struct hbg_irq_info *info_array;
u32 info_array_len;
};
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c
index 5e0ba4d..01ad82d 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c
@@ -61,7 +61,7 @@ static int hbg_dbg_irq_info(struct seq_file *s, void *unused)
{
struct net_device *netdev = dev_get_drvdata(s->private);
struct hbg_priv *priv = netdev_priv(netdev);
- struct hbg_irq_info *info;
+ const struct hbg_irq_info *info;
u32 i;
for (i = 0; i < priv->vectors.info_array_len; i++) {
@@ -73,7 +73,7 @@ static int hbg_dbg_irq_info(struct seq_file *s, void *unused)
info->mask)),
str_true_false(info->need_reset),
str_true_false(info->need_print),
- info->count);
+ priv->vectors.stats_array[i]);
}
return 0;
@@ -106,6 +106,7 @@ static int hbg_dbg_nic_state(struct seq_file *s, void *unused)
{
struct net_device *netdev = dev_get_drvdata(s->private);
struct hbg_priv *priv = netdev_priv(netdev);
+ bool np_link_fail;
seq_printf(s, "event handling state: %s\n",
state_str_true_false(priv, HBG_NIC_STATE_EVENT_HANDLING));
@@ -117,8 +118,10 @@ static int hbg_dbg_nic_state(struct seq_file *s, void *unused)
reset_type_str[priv->reset_type]);
seq_printf(s, "need reset state: %s\n",
state_str_true_false(priv, HBG_NIC_STATE_NEED_RESET));
- seq_printf(s, "np_link fail state: %s\n",
- state_str_true_false(priv, HBG_NIC_STATE_NP_LINK_FAIL));
+
+ np_link_fail = !hbg_reg_read_field(priv, HBG_REG_AN_NEG_STATE_ADDR,
+ HBG_REG_AN_NEG_STATE_NP_LINK_OK_B);
+ seq_printf(s, "np_link fail state: %s\n", str_true_false(np_link_fail));
return 0;
}
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.c
index d61c03f..f23fb59 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.c
@@ -234,7 +234,7 @@ static u64 hbg_get_irq_stats(struct hbg_vector *vectors, u32 mask)
for (i = 0; i < vectors->info_array_len; i++)
if (vectors->info_array[i].mask == mask)
- return vectors->info_array[i].count;
+ return vectors->stats_array[i];
return 0;
}
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
index 4e8cb66..a0bcfb5 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
@@ -26,12 +26,15 @@ static void hbg_restore_mac_table(struct hbg_priv *priv)
static void hbg_restore_user_def_settings(struct hbg_priv *priv)
{
+ /* The index of host mac is always 0. */
+ u64 rx_pause_addr = ether_addr_to_u64(priv->filter.mac_table[0].addr);
struct ethtool_pauseparam *pause_param = &priv->user_def.pause_param;
hbg_restore_mac_table(priv);
hbg_hw_set_mtu(priv, priv->netdev->mtu);
hbg_hw_set_pause_enable(priv, pause_param->tx_pause,
pause_param->rx_pause);
+ hbg_hw_set_rx_pause_mac_addr(priv, rx_pause_addr);
}
int hbg_rebuild(struct hbg_priv *priv)
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c
index 74a1803..9b65eef 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c
@@ -234,6 +234,10 @@ void hbg_hw_set_mac_filter_enable(struct hbg_priv *priv, u32 enable)
{
hbg_reg_write_field(priv, HBG_REG_REC_FILT_CTRL_ADDR,
HBG_REG_REC_FILT_CTRL_UC_MATCH_EN_B, enable);
+
+ /* only uc filter is supported, so set all bits of mc mask reg to 1 */
+ hbg_reg_write64(priv, HBG_REG_STATION_ADDR_LOW_MSK_0, U64_MAX);
+ hbg_reg_write64(priv, HBG_REG_STATION_ADDR_LOW_MSK_1, U64_MAX);
}
void hbg_hw_set_pause_enable(struct hbg_priv *priv, u32 tx_en, u32 rx_en)
@@ -242,6 +246,9 @@ void hbg_hw_set_pause_enable(struct hbg_priv *priv, u32 tx_en, u32 rx_en)
HBG_REG_PAUSE_ENABLE_TX_B, tx_en);
hbg_reg_write_field(priv, HBG_REG_PAUSE_ENABLE_ADDR,
HBG_REG_PAUSE_ENABLE_RX_B, rx_en);
+
+ hbg_reg_write_field(priv, HBG_REG_REC_FILT_CTRL_ADDR,
+ HBG_REG_REC_FILT_CTRL_PAUSE_FRM_PASS_B, rx_en);
}
void hbg_hw_get_pause_enable(struct hbg_priv *priv, u32 *tx_en, u32 *rx_en)
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c
index e79e9ab..8af0bc4 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c
@@ -6,7 +6,7 @@
#include "hbg_hw.h"
static void hbg_irq_handle_err(struct hbg_priv *priv,
- struct hbg_irq_info *irq_info)
+ const struct hbg_irq_info *irq_info)
{
if (irq_info->need_print)
dev_err(&priv->pdev->dev,
@@ -17,30 +17,30 @@ static void hbg_irq_handle_err(struct hbg_priv *priv,
}
static void hbg_irq_handle_tx(struct hbg_priv *priv,
- struct hbg_irq_info *irq_info)
+ const struct hbg_irq_info *irq_info)
{
napi_schedule(&priv->tx_ring.napi);
}
static void hbg_irq_handle_rx(struct hbg_priv *priv,
- struct hbg_irq_info *irq_info)
+ const struct hbg_irq_info *irq_info)
{
napi_schedule(&priv->rx_ring.napi);
}
static void hbg_irq_handle_rx_buf_val(struct hbg_priv *priv,
- struct hbg_irq_info *irq_info)
+ const struct hbg_irq_info *irq_info)
{
priv->stats.rx_fifo_less_empty_thrsld_cnt++;
}
#define HBG_IRQ_I(name, handle) \
- {#name, HBG_INT_MSK_##name##_B, false, false, false, 0, handle}
+ {#name, HBG_INT_MSK_##name##_B, false, false, false, handle}
#define HBG_ERR_IRQ_I(name, need_print, ndde_reset) \
{#name, HBG_INT_MSK_##name##_B, true, need_print, \
- ndde_reset, 0, hbg_irq_handle_err}
+ ndde_reset, hbg_irq_handle_err}
-static struct hbg_irq_info hbg_irqs[] = {
+static const struct hbg_irq_info hbg_irqs[] = {
HBG_IRQ_I(RX, hbg_irq_handle_rx),
HBG_IRQ_I(TX, hbg_irq_handle_tx),
HBG_ERR_IRQ_I(TX_PKT_CPL, true, true),
@@ -64,7 +64,7 @@ static struct hbg_irq_info hbg_irqs[] = {
static irqreturn_t hbg_irq_handle(int irq_num, void *p)
{
- struct hbg_irq_info *info;
+ const struct hbg_irq_info *info;
struct hbg_priv *priv = p;
u32 status;
u32 i;
@@ -79,7 +79,7 @@ static irqreturn_t hbg_irq_handle(int irq_num, void *p)
hbg_hw_irq_enable(priv, info->mask, false);
hbg_hw_irq_clear(priv, info->mask);
- info->count++;
+ priv->vectors.stats_array[i]++;
if (info->irq_handle)
info->irq_handle(priv, info);
@@ -132,6 +132,12 @@ int hbg_irq_init(struct hbg_priv *priv)
irq_names_map[i]);
}
+ vectors->stats_array = devm_kcalloc(&priv->pdev->dev,
+ ARRAY_SIZE(hbg_irqs),
+ sizeof(u64), GFP_KERNEL);
+ if (!vectors->stats_array)
+ return -ENOMEM;
+
vectors->info_array = hbg_irqs;
vectors->info_array_len = ARRAY_SIZE(hbg_irqs);
return 0;
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
index 2ac5454..2e64dc1 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
@@ -21,7 +21,7 @@
static void hbg_all_irq_enable(struct hbg_priv *priv, bool enabled)
{
- struct hbg_irq_info *info;
+ const struct hbg_irq_info *info;
u32 i;
for (i = 0; i < priv->vectors.info_array_len; i++) {
@@ -203,12 +203,12 @@ static int hbg_net_change_mtu(struct net_device *netdev, int new_mtu)
if (netif_running(netdev))
return -EBUSY;
- hbg_hw_set_mtu(priv, new_mtu);
- WRITE_ONCE(netdev->mtu, new_mtu);
-
dev_dbg(&priv->pdev->dev,
"change mtu from %u to %u\n", netdev->mtu, new_mtu);
+ hbg_hw_set_mtu(priv, new_mtu);
+ WRITE_ONCE(netdev->mtu, new_mtu);
+
return 0;
}
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c
index f29a937..42b0083 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c
@@ -2,6 +2,7 @@
// Copyright (c) 2024 Hisilicon Limited.
#include <linux/phy.h>
+#include <linux/rtnetlink.h>
#include "hbg_common.h"
#include "hbg_hw.h"
#include "hbg_mdio.h"
@@ -133,12 +134,17 @@ void hbg_fix_np_link_fail(struct hbg_priv *priv)
{
struct device *dev = &priv->pdev->dev;
+ rtnl_lock();
+
if (priv->stats.np_link_fail_cnt >= HBG_NP_LINK_FAIL_RETRY_TIMES) {
dev_err(dev, "failed to fix the MAC link status\n");
priv->stats.np_link_fail_cnt = 0;
- return;
+ goto unlock;
}
+ if (!priv->mac.phydev->link)
+ goto unlock;
+
priv->stats.np_link_fail_cnt++;
dev_err(dev, "failed to link between MAC and PHY, try to fix...\n");
@@ -147,6 +153,9 @@ void hbg_fix_np_link_fail(struct hbg_priv *priv)
*/
hbg_phy_stop(priv);
hbg_phy_start(priv);
+
+unlock:
+ rtnl_unlock();
}
static void hbg_phy_adjust_link(struct net_device *netdev)
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
index cc2cc61..a6e7f5e 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
@@ -68,6 +68,7 @@
#define HBG_REG_TRANSMIT_CTRL_AN_EN_B BIT(5)
#define HBG_REG_REC_FILT_CTRL_ADDR (HBG_REG_SGMII_BASE + 0x0064)
#define HBG_REG_REC_FILT_CTRL_UC_MATCH_EN_B BIT(0)
+#define HBG_REG_REC_FILT_CTRL_PAUSE_FRM_PASS_B BIT(4)
#define HBG_REG_RX_OCTETS_TOTAL_OK_ADDR (HBG_REG_SGMII_BASE + 0x0080)
#define HBG_REG_RX_OCTETS_BAD_ADDR (HBG_REG_SGMII_BASE + 0x0084)
#define HBG_REG_RX_UC_PKTS_ADDR (HBG_REG_SGMII_BASE + 0x0088)
@@ -134,6 +135,8 @@
#define HBG_REG_STATION_ADDR_HIGH_4_ADDR (HBG_REG_SGMII_BASE + 0x0224)
#define HBG_REG_STATION_ADDR_LOW_5_ADDR (HBG_REG_SGMII_BASE + 0x0228)
#define HBG_REG_STATION_ADDR_HIGH_5_ADDR (HBG_REG_SGMII_BASE + 0x022C)
+#define HBG_REG_STATION_ADDR_LOW_MSK_0 (HBG_REG_SGMII_BASE + 0x0230)
+#define HBG_REG_STATION_ADDR_LOW_MSK_1 (HBG_REG_SGMII_BASE + 0x0238)
/* PCU */
#define HBG_REG_TX_FIFO_THRSLD_ADDR (HBG_REG_SGMII_BASE + 0x0420)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 09749e9..4e5d8bc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -61,7 +61,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = {
.name = "tm_qset",
.cmd = HNAE3_DBG_CMD_TM_QSET,
.dentry = HNS3_DBG_DENTRY_TM,
- .buf_len = HNS3_DBG_READ_LEN,
+ .buf_len = HNS3_DBG_READ_LEN_1MB,
.init = hns3_dbg_common_file_init,
},
{
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 9ff797f..b03b8758 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -473,20 +473,14 @@ static void hns3_mask_vector_irq(struct hns3_enet_tqp_vector *tqp_vector,
writel(mask_en, tqp_vector->mask_addr);
}
-static void hns3_vector_enable(struct hns3_enet_tqp_vector *tqp_vector)
+static void hns3_irq_enable(struct hns3_enet_tqp_vector *tqp_vector)
{
napi_enable(&tqp_vector->napi);
enable_irq(tqp_vector->vector_irq);
-
- /* enable vector */
- hns3_mask_vector_irq(tqp_vector, 1);
}
-static void hns3_vector_disable(struct hns3_enet_tqp_vector *tqp_vector)
+static void hns3_irq_disable(struct hns3_enet_tqp_vector *tqp_vector)
{
- /* disable vector */
- hns3_mask_vector_irq(tqp_vector, 0);
-
disable_irq(tqp_vector->vector_irq);
napi_disable(&tqp_vector->napi);
cancel_work_sync(&tqp_vector->rx_group.dim.work);
@@ -707,11 +701,42 @@ static int hns3_set_rx_cpu_rmap(struct net_device *netdev)
return 0;
}
+static void hns3_enable_irqs_and_tqps(struct net_device *netdev)
+{
+ struct hns3_nic_priv *priv = netdev_priv(netdev);
+ struct hnae3_handle *h = priv->ae_handle;
+ u16 i;
+
+ for (i = 0; i < priv->vector_num; i++)
+ hns3_irq_enable(&priv->tqp_vector[i]);
+
+ for (i = 0; i < priv->vector_num; i++)
+ hns3_mask_vector_irq(&priv->tqp_vector[i], 1);
+
+ for (i = 0; i < h->kinfo.num_tqps; i++)
+ hns3_tqp_enable(h->kinfo.tqp[i]);
+}
+
+static void hns3_disable_irqs_and_tqps(struct net_device *netdev)
+{
+ struct hns3_nic_priv *priv = netdev_priv(netdev);
+ struct hnae3_handle *h = priv->ae_handle;
+ u16 i;
+
+ for (i = 0; i < h->kinfo.num_tqps; i++)
+ hns3_tqp_disable(h->kinfo.tqp[i]);
+
+ for (i = 0; i < priv->vector_num; i++)
+ hns3_mask_vector_irq(&priv->tqp_vector[i], 0);
+
+ for (i = 0; i < priv->vector_num; i++)
+ hns3_irq_disable(&priv->tqp_vector[i]);
+}
+
static int hns3_nic_net_up(struct net_device *netdev)
{
struct hns3_nic_priv *priv = netdev_priv(netdev);
struct hnae3_handle *h = priv->ae_handle;
- int i, j;
int ret;
ret = hns3_nic_reset_all_ring(h);
@@ -720,23 +745,13 @@ static int hns3_nic_net_up(struct net_device *netdev)
clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
- /* enable the vectors */
- for (i = 0; i < priv->vector_num; i++)
- hns3_vector_enable(&priv->tqp_vector[i]);
-
- /* enable rcb */
- for (j = 0; j < h->kinfo.num_tqps; j++)
- hns3_tqp_enable(h->kinfo.tqp[j]);
+ hns3_enable_irqs_and_tqps(netdev);
/* start the ae_dev */
ret = h->ae_algo->ops->start ? h->ae_algo->ops->start(h) : 0;
if (ret) {
set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
- while (j--)
- hns3_tqp_disable(h->kinfo.tqp[j]);
-
- for (j = i - 1; j >= 0; j--)
- hns3_vector_disable(&priv->tqp_vector[j]);
+ hns3_disable_irqs_and_tqps(netdev);
}
return ret;
@@ -823,17 +838,9 @@ static void hns3_reset_tx_queue(struct hnae3_handle *h)
static void hns3_nic_net_down(struct net_device *netdev)
{
struct hns3_nic_priv *priv = netdev_priv(netdev);
- struct hnae3_handle *h = hns3_get_handle(netdev);
const struct hnae3_ae_ops *ops;
- int i;
- /* disable vectors */
- for (i = 0; i < priv->vector_num; i++)
- hns3_vector_disable(&priv->tqp_vector[i]);
-
- /* disable rcb */
- for (i = 0; i < h->kinfo.num_tqps; i++)
- hns3_tqp_disable(h->kinfo.tqp[i]);
+ hns3_disable_irqs_and_tqps(netdev);
/* stop ae_dev */
ops = priv->ae_handle->ae_algo->ops;
@@ -5864,8 +5871,6 @@ int hns3_set_channels(struct net_device *netdev,
void hns3_external_lb_prepare(struct net_device *ndev, bool if_running)
{
struct hns3_nic_priv *priv = netdev_priv(ndev);
- struct hnae3_handle *h = priv->ae_handle;
- int i;
if (!if_running)
return;
@@ -5876,11 +5881,7 @@ void hns3_external_lb_prepare(struct net_device *ndev, bool if_running)
netif_carrier_off(ndev);
netif_tx_disable(ndev);
- for (i = 0; i < priv->vector_num; i++)
- hns3_vector_disable(&priv->tqp_vector[i]);
-
- for (i = 0; i < h->kinfo.num_tqps; i++)
- hns3_tqp_disable(h->kinfo.tqp[i]);
+ hns3_disable_irqs_and_tqps(ndev);
/* delay ring buffer clearing to hns3_reset_notify_uninit_enet
* during reset process, because driver may not be able
@@ -5896,7 +5897,6 @@ void hns3_external_lb_restore(struct net_device *ndev, bool if_running)
{
struct hns3_nic_priv *priv = netdev_priv(ndev);
struct hnae3_handle *h = priv->ae_handle;
- int i;
if (!if_running)
return;
@@ -5912,11 +5912,7 @@ void hns3_external_lb_restore(struct net_device *ndev, bool if_running)
clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
- for (i = 0; i < priv->vector_num; i++)
- hns3_vector_enable(&priv->tqp_vector[i]);
-
- for (i = 0; i < h->kinfo.num_tqps; i++)
- hns3_tqp_enable(h->kinfo.tqp[i]);
+ hns3_enable_irqs_and_tqps(ndev);
netif_tx_wake_all_queues(ndev);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
index 59cc922..ec581d4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
@@ -440,6 +440,13 @@ static int hclge_ptp_create_clock(struct hclge_dev *hdev)
ptp->info.settime64 = hclge_ptp_settime;
ptp->info.n_alarm = 0;
+
+ spin_lock_init(&ptp->lock);
+ ptp->io_base = hdev->hw.hw.io_base + HCLGE_PTP_REG_OFFSET;
+ ptp->ts_cfg.rx_filter = HWTSTAMP_FILTER_NONE;
+ ptp->ts_cfg.tx_type = HWTSTAMP_TX_OFF;
+ hdev->ptp = ptp;
+
ptp->clock = ptp_clock_register(&ptp->info, &hdev->pdev->dev);
if (IS_ERR(ptp->clock)) {
dev_err(&hdev->pdev->dev,
@@ -451,12 +458,6 @@ static int hclge_ptp_create_clock(struct hclge_dev *hdev)
return -ENODEV;
}
- spin_lock_init(&ptp->lock);
- ptp->io_base = hdev->hw.hw.io_base + HCLGE_PTP_REG_OFFSET;
- ptp->ts_cfg.rx_filter = HWTSTAMP_FILTER_NONE;
- ptp->ts_cfg.tx_type = HWTSTAMP_TX_OFF;
- hdev->ptp = ptp;
-
return 0;
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 9ba7677..dada42e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1292,9 +1292,8 @@ static void hclgevf_sync_vlan_filter(struct hclgevf_dev *hdev)
rtnl_unlock();
}
-static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
+static int hclgevf_en_hw_strip_rxvtag_cmd(struct hclgevf_dev *hdev, bool enable)
{
- struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
struct hclge_vf_to_pf_msg send_msg;
hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_VLAN,
@@ -1303,6 +1302,19 @@ static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0);
}
+static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
+{
+ struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+ int ret;
+
+ ret = hclgevf_en_hw_strip_rxvtag_cmd(hdev, enable);
+ if (ret)
+ return ret;
+
+ hdev->rxvtag_strip_en = enable;
+ return 0;
+}
+
static int hclgevf_reset_tqp(struct hnae3_handle *handle)
{
#define HCLGEVF_RESET_ALL_QUEUE_DONE 1U
@@ -2204,12 +2216,13 @@ static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev)
tc_valid, tc_size);
}
-static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev)
+static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev,
+ bool rxvtag_strip_en)
{
struct hnae3_handle *nic = &hdev->nic;
int ret;
- ret = hclgevf_en_hw_strip_rxvtag(nic, true);
+ ret = hclgevf_en_hw_strip_rxvtag(nic, rxvtag_strip_en);
if (ret) {
dev_err(&hdev->pdev->dev,
"failed to enable rx vlan offload, ret = %d\n", ret);
@@ -2879,7 +2892,7 @@ static int hclgevf_reset_hdev(struct hclgevf_dev *hdev)
if (ret)
return ret;
- ret = hclgevf_init_vlan_config(hdev);
+ ret = hclgevf_init_vlan_config(hdev, hdev->rxvtag_strip_en);
if (ret) {
dev_err(&hdev->pdev->dev,
"failed(%d) to initialize VLAN config\n", ret);
@@ -2994,7 +3007,7 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
goto err_config;
}
- ret = hclgevf_init_vlan_config(hdev);
+ ret = hclgevf_init_vlan_config(hdev, true);
if (ret) {
dev_err(&hdev->pdev->dev,
"failed(%d) to initialize VLAN config\n", ret);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index cccef32..0208425 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -253,6 +253,7 @@ struct hclgevf_dev {
int *vector_irq;
bool gro_en;
+ bool rxvtag_strip_en;
unsigned long vlan_del_fail_bmap[BITS_TO_LONGS(VLAN_N_VID)];
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
index 69d5b1a..59323c0 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -2345,15 +2345,15 @@ ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size,
cmd->set_flags |= ICE_AQC_TX_TOPO_FLAGS_SRC_RAM |
ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW;
- if (hw->mac_type == ICE_MAC_GENERIC_3K_E825)
- desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
} else {
ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_tx_topo);
cmd->get_flags = ICE_AQC_TX_TOPO_GET_RAM;
- }
- if (hw->mac_type != ICE_MAC_GENERIC_3K_E825)
- desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+ if (hw->mac_type == ICE_MAC_E810 ||
+ hw->mac_type == ICE_MAC_GENERIC)
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+ }
status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
if (status)
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
index 7752920..1cca9b2 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
@@ -2097,6 +2097,11 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg)
pf = vf->pf;
dev = ice_pf_to_dev(pf);
vf_vsi = ice_get_vf_vsi(vf);
+ if (!vf_vsi) {
+ dev_err(dev, "Can not get FDIR vf_vsi for VF %u\n", vf->vf_id);
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto err_exit;
+ }
#define ICE_VF_MAX_FDIR_FILTERS 128
if (!ice_fdir_num_avail_fltr(&pf->hw, vf_vsi) ||
diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h
index 66544fa..aef0e97 100644
--- a/drivers/net/ethernet/intel/idpf/idpf.h
+++ b/drivers/net/ethernet/intel/idpf/idpf.h
@@ -629,13 +629,13 @@ bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all,
VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V4 |\
VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V6)
-#define IDPF_CAP_RX_CSUM_L4V4 (\
- VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_TCP |\
- VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_UDP)
+#define IDPF_CAP_TX_CSUM_L4V4 (\
+ VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_TCP |\
+ VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_UDP)
-#define IDPF_CAP_RX_CSUM_L4V6 (\
- VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_TCP |\
- VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_UDP)
+#define IDPF_CAP_TX_CSUM_L4V6 (\
+ VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_TCP |\
+ VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_UDP)
#define IDPF_CAP_RX_CSUM (\
VIRTCHNL2_CAP_RX_CSUM_L3_IPV4 |\
@@ -644,11 +644,9 @@ bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all,
VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_TCP |\
VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_UDP)
-#define IDPF_CAP_SCTP_CSUM (\
+#define IDPF_CAP_TX_SCTP_CSUM (\
VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_SCTP |\
- VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_SCTP |\
- VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_SCTP |\
- VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_SCTP)
+ VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_SCTP)
#define IDPF_CAP_TUNNEL_TX_CSUM (\
VIRTCHNL2_CAP_TX_CSUM_L3_SINGLE_TUNNEL |\
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index aa755de..82f09b4 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -703,8 +703,10 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
{
struct idpf_adapter *adapter = vport->adapter;
struct idpf_vport_config *vport_config;
+ netdev_features_t other_offloads = 0;
+ netdev_features_t csum_offloads = 0;
+ netdev_features_t tso_offloads = 0;
netdev_features_t dflt_features;
- netdev_features_t offloads = 0;
struct idpf_netdev_priv *np;
struct net_device *netdev;
u16 idx = vport->idx;
@@ -766,53 +768,32 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
if (idpf_is_cap_ena_all(adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS))
dflt_features |= NETIF_F_RXHASH;
- if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM_L4V4))
- dflt_features |= NETIF_F_IP_CSUM;
- if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM_L4V6))
- dflt_features |= NETIF_F_IPV6_CSUM;
+ if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_CSUM_L4V4))
+ csum_offloads |= NETIF_F_IP_CSUM;
+ if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_CSUM_L4V6))
+ csum_offloads |= NETIF_F_IPV6_CSUM;
if (idpf_is_cap_ena(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM))
- dflt_features |= NETIF_F_RXCSUM;
- if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_SCTP_CSUM))
- dflt_features |= NETIF_F_SCTP_CRC;
+ csum_offloads |= NETIF_F_RXCSUM;
+ if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_SCTP_CSUM))
+ csum_offloads |= NETIF_F_SCTP_CRC;
if (idpf_is_cap_ena(adapter, IDPF_SEG_CAPS, VIRTCHNL2_CAP_SEG_IPV4_TCP))
- dflt_features |= NETIF_F_TSO;
+ tso_offloads |= NETIF_F_TSO;
if (idpf_is_cap_ena(adapter, IDPF_SEG_CAPS, VIRTCHNL2_CAP_SEG_IPV6_TCP))
- dflt_features |= NETIF_F_TSO6;
+ tso_offloads |= NETIF_F_TSO6;
if (idpf_is_cap_ena_all(adapter, IDPF_SEG_CAPS,
VIRTCHNL2_CAP_SEG_IPV4_UDP |
VIRTCHNL2_CAP_SEG_IPV6_UDP))
- dflt_features |= NETIF_F_GSO_UDP_L4;
+ tso_offloads |= NETIF_F_GSO_UDP_L4;
if (idpf_is_cap_ena_all(adapter, IDPF_RSC_CAPS, IDPF_CAP_RSC))
- offloads |= NETIF_F_GRO_HW;
- /* advertise to stack only if offloads for encapsulated packets is
- * supported
- */
- if (idpf_is_cap_ena(vport->adapter, IDPF_SEG_CAPS,
- VIRTCHNL2_CAP_SEG_TX_SINGLE_TUNNEL)) {
- offloads |= NETIF_F_GSO_UDP_TUNNEL |
- NETIF_F_GSO_GRE |
- NETIF_F_GSO_GRE_CSUM |
- NETIF_F_GSO_PARTIAL |
- NETIF_F_GSO_UDP_TUNNEL_CSUM |
- NETIF_F_GSO_IPXIP4 |
- NETIF_F_GSO_IPXIP6 |
- 0;
-
- if (!idpf_is_cap_ena_all(vport->adapter, IDPF_CSUM_CAPS,
- IDPF_CAP_TUNNEL_TX_CSUM))
- netdev->gso_partial_features |=
- NETIF_F_GSO_UDP_TUNNEL_CSUM;
-
- netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
- offloads |= NETIF_F_TSO_MANGLEID;
- }
+ other_offloads |= NETIF_F_GRO_HW;
if (idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_LOOPBACK))
- offloads |= NETIF_F_LOOPBACK;
+ other_offloads |= NETIF_F_LOOPBACK;
- netdev->features |= dflt_features;
- netdev->hw_features |= dflt_features | offloads;
- netdev->hw_enc_features |= dflt_features | offloads;
+ netdev->features |= dflt_features | csum_offloads | tso_offloads;
+ netdev->hw_features |= netdev->features | other_offloads;
+ netdev->vlan_features |= netdev->features | other_offloads;
+ netdev->hw_enc_features |= dflt_features | other_offloads;
idpf_set_ethtool_ops(netdev);
netif_set_affinity_auto(netdev);
SET_NETDEV_DEV(netdev, &adapter->pdev->dev);
@@ -1132,11 +1113,9 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
num_max_q = max(max_q->max_txq, max_q->max_rxq);
vport->q_vector_idxs = kcalloc(num_max_q, sizeof(u16), GFP_KERNEL);
- if (!vport->q_vector_idxs) {
- kfree(vport);
+ if (!vport->q_vector_idxs)
+ goto free_vport;
- return NULL;
- }
idpf_vport_init(vport, max_q);
/* This alloc is done separate from the LUT because it's not strictly
@@ -1146,11 +1125,9 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
*/
rss_data = &adapter->vport_config[idx]->user_config.rss_data;
rss_data->rss_key = kzalloc(rss_data->rss_key_size, GFP_KERNEL);
- if (!rss_data->rss_key) {
- kfree(vport);
+ if (!rss_data->rss_key)
+ goto free_vector_idxs;
- return NULL;
- }
/* Initialize default rss key */
netdev_rss_key_fill((void *)rss_data->rss_key, rss_data->rss_key_size);
@@ -1163,6 +1140,13 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
adapter->next_vport = idpf_get_free_slot(adapter);
return vport;
+
+free_vector_idxs:
+ kfree(vport->q_vector_idxs);
+free_vport:
+ kfree(vport);
+
+ return NULL;
}
/**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c
index bec4a02..b357130 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_main.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_main.c
@@ -89,6 +89,7 @@ static void idpf_shutdown(struct pci_dev *pdev)
{
struct idpf_adapter *adapter = pci_get_drvdata(pdev);
+ cancel_delayed_work_sync(&adapter->serv_task);
cancel_delayed_work_sync(&adapter->vc_event_task);
idpf_vc_core_deinit(adapter);
idpf_deinit_dflt_mbx(adapter);
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index c35cc5c..2f265c0 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -319,6 +319,7 @@ struct igc_adapter {
struct timespec64 prev_ptp_time; /* Pre-reset PTP clock */
ktime_t ptp_reset_start; /* Reset time in clock mono */
struct system_time_snapshot snapshot;
+ struct mutex ptm_lock; /* Only allow one PTM transaction at a time */
char fw_version[32];
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 8e44990..d19325b 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -574,7 +574,10 @@
#define IGC_PTM_CTRL_SHRT_CYC(usec) (((usec) & 0x3f) << 2)
#define IGC_PTM_CTRL_PTM_TO(usec) (((usec) & 0xff) << 8)
-#define IGC_PTM_SHORT_CYC_DEFAULT 1 /* Default short cycle interval */
+/* A short cycle time of 1us theoretically should work, but appears to be too
+ * short in practice.
+ */
+#define IGC_PTM_SHORT_CYC_DEFAULT 4 /* Default short cycle interval */
#define IGC_PTM_CYC_TIME_DEFAULT 5 /* Default PTM cycle time */
#define IGC_PTM_TIMEOUT_DEFAULT 255 /* Default timeout for PTM errors */
@@ -593,6 +596,7 @@
#define IGC_PTM_STAT_T4M1_OVFL BIT(3) /* T4 minus T1 overflow */
#define IGC_PTM_STAT_ADJUST_1ST BIT(4) /* 1588 timer adjusted during 1st PTM cycle */
#define IGC_PTM_STAT_ADJUST_CYC BIT(5) /* 1588 timer adjusted during non-1st PTM cycle */
+#define IGC_PTM_STAT_ALL GENMASK(5, 0) /* Used to clear all status */
/* PCIe PTM Cycle Control */
#define IGC_PTM_CYCLE_CTRL_CYC_TIME(msec) ((msec) & 0x3ff) /* PTM Cycle Time (msec) */
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index f133037..b1669d7 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -7231,6 +7231,7 @@ static int igc_probe(struct pci_dev *pdev,
err_register:
igc_release_hw_control(adapter);
+ igc_ptp_stop(adapter);
err_eeprom:
if (!igc_check_reset_block(hw))
igc_reset_phy(hw);
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 946edba..efc7b30 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -974,45 +974,62 @@ static void igc_ptm_log_error(struct igc_adapter *adapter, u32 ptm_stat)
}
}
+/* The PTM lock: adapter->ptm_lock must be held when calling igc_ptm_trigger() */
+static void igc_ptm_trigger(struct igc_hw *hw)
+{
+ u32 ctrl;
+
+ /* To "manually" start the PTM cycle we need to set the
+ * trigger (TRIG) bit
+ */
+ ctrl = rd32(IGC_PTM_CTRL);
+ ctrl |= IGC_PTM_CTRL_TRIG;
+ wr32(IGC_PTM_CTRL, ctrl);
+ /* Perform flush after write to CTRL register otherwise
+ * transaction may not start
+ */
+ wrfl();
+}
+
+/* The PTM lock: adapter->ptm_lock must be held when calling igc_ptm_reset() */
+static void igc_ptm_reset(struct igc_hw *hw)
+{
+ u32 ctrl;
+
+ ctrl = rd32(IGC_PTM_CTRL);
+ ctrl &= ~IGC_PTM_CTRL_TRIG;
+ wr32(IGC_PTM_CTRL, ctrl);
+ /* Write to clear all status */
+ wr32(IGC_PTM_STAT, IGC_PTM_STAT_ALL);
+}
+
static int igc_phc_get_syncdevicetime(ktime_t *device,
struct system_counterval_t *system,
void *ctx)
{
- u32 stat, t2_curr_h, t2_curr_l, ctrl;
struct igc_adapter *adapter = ctx;
struct igc_hw *hw = &adapter->hw;
+ u32 stat, t2_curr_h, t2_curr_l;
int err, count = 100;
ktime_t t1, t2_curr;
- /* Get a snapshot of system clocks to use as historic value. */
- ktime_get_snapshot(&adapter->snapshot);
-
+ /* Doing this in a loop because in the event of a
+ * badly timed (ha!) system clock adjustment, we may
+ * get PTM errors from the PCI root, but these errors
+ * are transitory. Repeating the process returns valid
+ * data eventually.
+ */
do {
- /* Doing this in a loop because in the event of a
- * badly timed (ha!) system clock adjustment, we may
- * get PTM errors from the PCI root, but these errors
- * are transitory. Repeating the process returns valid
- * data eventually.
- */
+ /* Get a snapshot of system clocks to use as historic value. */
+ ktime_get_snapshot(&adapter->snapshot);
- /* To "manually" start the PTM cycle we need to clear and
- * then set again the TRIG bit.
- */
- ctrl = rd32(IGC_PTM_CTRL);
- ctrl &= ~IGC_PTM_CTRL_TRIG;
- wr32(IGC_PTM_CTRL, ctrl);
- ctrl |= IGC_PTM_CTRL_TRIG;
- wr32(IGC_PTM_CTRL, ctrl);
-
- /* The cycle only starts "for real" when software notifies
- * that it has read the registers, this is done by setting
- * VALID bit.
- */
- wr32(IGC_PTM_STAT, IGC_PTM_STAT_VALID);
+ igc_ptm_trigger(hw);
err = readx_poll_timeout(rd32, IGC_PTM_STAT, stat,
stat, IGC_PTM_STAT_SLEEP,
IGC_PTM_STAT_TIMEOUT);
+ igc_ptm_reset(hw);
+
if (err < 0) {
netdev_err(adapter->netdev, "Timeout reading IGC_PTM_STAT register\n");
return err;
@@ -1021,15 +1038,7 @@ static int igc_phc_get_syncdevicetime(ktime_t *device,
if ((stat & IGC_PTM_STAT_VALID) == IGC_PTM_STAT_VALID)
break;
- if (stat & ~IGC_PTM_STAT_VALID) {
- /* An error occurred, log it. */
- igc_ptm_log_error(adapter, stat);
- /* The STAT register is write-1-to-clear (W1C),
- * so write the previous error status to clear it.
- */
- wr32(IGC_PTM_STAT, stat);
- continue;
- }
+ igc_ptm_log_error(adapter, stat);
} while (--count);
if (!count) {
@@ -1061,9 +1070,16 @@ static int igc_ptp_getcrosststamp(struct ptp_clock_info *ptp,
{
struct igc_adapter *adapter = container_of(ptp, struct igc_adapter,
ptp_caps);
+ int ret;
- return get_device_system_crosststamp(igc_phc_get_syncdevicetime,
- adapter, &adapter->snapshot, cts);
+ /* This blocks until any in progress PTM transactions complete */
+ mutex_lock(&adapter->ptm_lock);
+
+ ret = get_device_system_crosststamp(igc_phc_get_syncdevicetime,
+ adapter, &adapter->snapshot, cts);
+ mutex_unlock(&adapter->ptm_lock);
+
+ return ret;
}
static int igc_ptp_getcyclesx64(struct ptp_clock_info *ptp,
@@ -1162,6 +1178,7 @@ void igc_ptp_init(struct igc_adapter *adapter)
spin_lock_init(&adapter->ptp_tx_lock);
spin_lock_init(&adapter->free_timer_lock);
spin_lock_init(&adapter->tmreg_lock);
+ mutex_init(&adapter->ptm_lock);
adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
@@ -1174,6 +1191,7 @@ void igc_ptp_init(struct igc_adapter *adapter)
if (IS_ERR(adapter->ptp_clock)) {
adapter->ptp_clock = NULL;
netdev_err(netdev, "ptp_clock_register failed\n");
+ mutex_destroy(&adapter->ptm_lock);
} else if (adapter->ptp_clock) {
netdev_info(netdev, "PHC added\n");
adapter->ptp_flags |= IGC_PTP_ENABLED;
@@ -1203,10 +1221,12 @@ static void igc_ptm_stop(struct igc_adapter *adapter)
struct igc_hw *hw = &adapter->hw;
u32 ctrl;
+ mutex_lock(&adapter->ptm_lock);
ctrl = rd32(IGC_PTM_CTRL);
ctrl &= ~IGC_PTM_CTRL_EN;
wr32(IGC_PTM_CTRL, ctrl);
+ mutex_unlock(&adapter->ptm_lock);
}
/**
@@ -1237,13 +1257,18 @@ void igc_ptp_suspend(struct igc_adapter *adapter)
**/
void igc_ptp_stop(struct igc_adapter *adapter)
{
+ if (!(adapter->ptp_flags & IGC_PTP_ENABLED))
+ return;
+
igc_ptp_suspend(adapter);
+ adapter->ptp_flags &= ~IGC_PTP_ENABLED;
if (adapter->ptp_clock) {
ptp_clock_unregister(adapter->ptp_clock);
netdev_info(adapter->netdev, "PHC removed\n");
adapter->ptp_flags &= ~IGC_PTP_ENABLED;
}
+ mutex_destroy(&adapter->ptm_lock);
}
/**
@@ -1255,13 +1280,18 @@ void igc_ptp_stop(struct igc_adapter *adapter)
void igc_ptp_reset(struct igc_adapter *adapter)
{
struct igc_hw *hw = &adapter->hw;
- u32 cycle_ctrl, ctrl;
+ u32 cycle_ctrl, ctrl, stat;
unsigned long flags;
u32 timadj;
+ if (!(adapter->ptp_flags & IGC_PTP_ENABLED))
+ return;
+
/* reset the tstamp_config */
igc_ptp_set_timestamp_mode(adapter, &adapter->tstamp_config);
+ mutex_lock(&adapter->ptm_lock);
+
spin_lock_irqsave(&adapter->tmreg_lock, flags);
switch (adapter->hw.mac.type) {
@@ -1290,14 +1320,19 @@ void igc_ptp_reset(struct igc_adapter *adapter)
ctrl = IGC_PTM_CTRL_EN |
IGC_PTM_CTRL_START_NOW |
IGC_PTM_CTRL_SHRT_CYC(IGC_PTM_SHORT_CYC_DEFAULT) |
- IGC_PTM_CTRL_PTM_TO(IGC_PTM_TIMEOUT_DEFAULT) |
- IGC_PTM_CTRL_TRIG;
+ IGC_PTM_CTRL_PTM_TO(IGC_PTM_TIMEOUT_DEFAULT);
wr32(IGC_PTM_CTRL, ctrl);
/* Force the first cycle to run. */
- wr32(IGC_PTM_STAT, IGC_PTM_STAT_VALID);
+ igc_ptm_trigger(hw);
+ if (readx_poll_timeout_atomic(rd32, IGC_PTM_STAT, stat,
+ stat, IGC_PTM_STAT_SLEEP,
+ IGC_PTM_STAT_TIMEOUT))
+ netdev_err(adapter->netdev, "Timeout reading IGC_PTM_STAT register\n");
+
+ igc_ptm_reset(hw);
break;
default:
/* No work to do. */
@@ -1314,5 +1349,7 @@ void igc_ptp_reset(struct igc_adapter *adapter)
out:
spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
+ mutex_unlock(&adapter->ptm_lock);
+
wrfl();
}
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
index 0a679e9..24499bb 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
@@ -1223,7 +1223,7 @@ static void octep_hb_timeout_task(struct work_struct *work)
miss_cnt);
rtnl_lock();
if (netif_running(oct->netdev))
- octep_stop(oct->netdev);
+ dev_close(oct->netdev);
rtnl_unlock();
}
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
index 18c922d..ccb69bc 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
@@ -835,7 +835,9 @@ static void octep_vf_tx_timeout(struct net_device *netdev, unsigned int txqueue)
struct octep_vf_device *oct = netdev_priv(netdev);
netdev_hold(netdev, NULL, GFP_ATOMIC);
- schedule_work(&oct->tx_timeout_task);
+ if (!schedule_work(&oct->tx_timeout_task))
+ netdev_put(netdev, NULL);
+
}
static int octep_vf_set_mac(struct net_device *netdev, void *p)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
index 0f844c1..35acc07 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
@@ -165,6 +165,11 @@ static void __otx2_qos_txschq_cfg(struct otx2_nic *pfvf,
otx2_config_sched_shaping(pfvf, node, cfg, &num_regs);
} else if (level == NIX_TXSCH_LVL_TL2) {
+ /* configure parent txschq */
+ cfg->reg[num_regs] = NIX_AF_TL2X_PARENT(node->schq);
+ cfg->regval[num_regs] = (u64)hw->tx_link << 16;
+ num_regs++;
+
/* configure link cfg */
if (level == pfvf->qos.link_cfg_lvl) {
cfg->reg[num_regs] = NIX_AF_TL3_TL2X_LINKX_CFG(node->schq, hw->tx_link);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
index 04e08e0..7153a71 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
@@ -67,6 +67,8 @@ static int rvu_rep_mcam_flow_init(struct rep_dev *rep)
rsp = (struct npc_mcam_alloc_entry_rsp *)otx2_mbox_get_rsp
(&priv->mbox.mbox, 0, &req->hdr);
+ if (IS_ERR(rsp))
+ goto exit;
for (ent = 0; ent < rsp->count; ent++)
rep->flow_cfg->flow_ent[ent + allocated] = rsp->entry_list[ent];
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 43197b2..8fda4ce 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -269,12 +269,8 @@ static const char * const mtk_clks_source_name[] = {
"ethwarp_wocpu2",
"ethwarp_wocpu1",
"ethwarp_wocpu0",
- "top_usxgmii0_sel",
- "top_usxgmii1_sel",
"top_sgm0_sel",
"top_sgm1_sel",
- "top_xfi_phy0_xtal_sel",
- "top_xfi_phy1_xtal_sel",
"top_eth_gmii_sel",
"top_eth_refck_50m_sel",
"top_eth_sys_200m_sel",
@@ -734,7 +730,7 @@ static void mtk_set_queue_speed(struct mtk_eth *eth, unsigned int idx,
case SPEED_100:
val |= MTK_QTX_SCH_MAX_RATE_EN |
FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 103) |
- FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 3);
+ FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 3) |
FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 1);
break;
case SPEED_1000:
@@ -757,13 +753,13 @@ static void mtk_set_queue_speed(struct mtk_eth *eth, unsigned int idx,
case SPEED_100:
val |= MTK_QTX_SCH_MAX_RATE_EN |
FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 1) |
- FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 5);
+ FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 5) |
FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 1);
break;
case SPEED_1000:
val |= MTK_QTX_SCH_MAX_RATE_EN |
- FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 10) |
- FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 5) |
+ FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 1) |
+ FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 6) |
FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 10);
break;
default:
@@ -871,9 +867,25 @@ static const struct phylink_mac_ops mtk_phylink_ops = {
.mac_enable_tx_lpi = mtk_mac_enable_tx_lpi,
};
+static void mtk_mdio_config(struct mtk_eth *eth)
+{
+ u32 val;
+
+ /* Configure MDC Divider */
+ val = FIELD_PREP(PPSC_MDC_CFG, eth->mdc_divider);
+
+ /* Configure MDC Turbo Mode */
+ if (mtk_is_netsys_v3_or_greater(eth))
+ mtk_m32(eth, 0, MISC_MDC_TURBO, MTK_MAC_MISC_V3);
+ else
+ val |= PPSC_MDC_TURBO;
+
+ mtk_m32(eth, PPSC_MDC_CFG, val, MTK_PPSC);
+}
+
static int mtk_mdio_init(struct mtk_eth *eth)
{
- unsigned int max_clk = 2500000, divider;
+ unsigned int max_clk = 2500000;
struct device_node *mii_np;
int ret;
u32 val;
@@ -908,20 +920,9 @@ static int mtk_mdio_init(struct mtk_eth *eth)
}
max_clk = val;
}
- divider = min_t(unsigned int, DIV_ROUND_UP(MDC_MAX_FREQ, max_clk), 63);
-
- /* Configure MDC Turbo Mode */
- if (mtk_is_netsys_v3_or_greater(eth))
- mtk_m32(eth, 0, MISC_MDC_TURBO, MTK_MAC_MISC_V3);
-
- /* Configure MDC Divider */
- val = FIELD_PREP(PPSC_MDC_CFG, divider);
- if (!mtk_is_netsys_v3_or_greater(eth))
- val |= PPSC_MDC_TURBO;
- mtk_m32(eth, PPSC_MDC_CFG, val, MTK_PPSC);
-
- dev_dbg(eth->dev, "MDC is running on %d Hz\n", MDC_MAX_FREQ / divider);
-
+ eth->mdc_divider = min_t(unsigned int, DIV_ROUND_UP(MDC_MAX_FREQ, max_clk), 63);
+ mtk_mdio_config(eth);
+ dev_dbg(eth->dev, "MDC is running on %d Hz\n", MDC_MAX_FREQ / eth->mdc_divider);
ret = of_mdiobus_register(eth->mii_bus, mii_np);
err_put_node:
@@ -2247,14 +2248,18 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
ring->data[idx] = new_data;
rxd->rxd1 = (unsigned int)dma_addr;
release_desc:
+ if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA)) {
+ if (unlikely(dma_addr == DMA_MAPPING_ERROR))
+ addr64 = FIELD_GET(RX_DMA_ADDR64_MASK,
+ rxd->rxd2);
+ else
+ addr64 = RX_DMA_PREP_ADDR64(dma_addr);
+ }
+
if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
rxd->rxd2 = RX_DMA_LSO;
else
- rxd->rxd2 = RX_DMA_PREP_PLEN0(ring->buf_size);
-
- if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA) &&
- likely(dma_addr != DMA_MAPPING_ERROR))
- rxd->rxd2 |= RX_DMA_PREP_ADDR64(dma_addr);
+ rxd->rxd2 = RX_DMA_PREP_PLEN0(ring->buf_size) | addr64;
ring->calc_idx = idx;
done++;
@@ -3315,7 +3320,7 @@ static int mtk_start_dma(struct mtk_eth *eth)
if (mtk_is_netsys_v2_or_greater(eth))
val |= MTK_MUTLI_CNT | MTK_RESV_BUF |
MTK_WCOMP_EN | MTK_DMAD_WR_WDONE |
- MTK_CHK_DDONE_EN | MTK_LEAKY_BUCKET_EN;
+ MTK_CHK_DDONE_EN;
else
val |= MTK_RX_BT_32DWORDS;
mtk_w32(eth, val, reg_map->qdma.glo_cfg);
@@ -3974,6 +3979,10 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
else
mtk_hw_reset(eth);
+ /* No MT7628/88 support yet */
+ if (reset && !MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
+ mtk_mdio_config(eth);
+
if (mtk_is_netsys_v3_or_greater(eth)) {
/* Set FE to PDMAv2 if necessary */
val = mtk_r32(eth, MTK_FE_GLO_MISC);
@@ -4034,11 +4043,27 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
mtk_w32(eth, 0x21021000, MTK_FE_INT_GRP);
if (mtk_is_netsys_v3_or_greater(eth)) {
- /* PSE should not drop port1, port8 and port9 packets */
- mtk_w32(eth, 0x00000302, PSE_DROP_CFG);
+ /* PSE dummy page mechanism */
+ mtk_w32(eth, PSE_DUMMY_WORK_GDM(1) | PSE_DUMMY_WORK_GDM(2) |
+ PSE_DUMMY_WORK_GDM(3) | DUMMY_PAGE_THR, PSE_DUMY_REQ);
+
+ /* PSE free buffer drop threshold */
+ mtk_w32(eth, 0x00600009, PSE_IQ_REV(8));
+
+ /* PSE should not drop port8, port9 and port13 packets from
+ * WDMA Tx
+ */
+ mtk_w32(eth, 0x00002300, PSE_DROP_CFG);
+
+ /* PSE should drop packets to port8, port9 and port13 on WDMA Rx
+ * ring full
+ */
+ mtk_w32(eth, 0x00002300, PSE_PPE_DROP(0));
+ mtk_w32(eth, 0x00002300, PSE_PPE_DROP(1));
+ mtk_w32(eth, 0x00002300, PSE_PPE_DROP(2));
/* GDM and CDM Threshold */
- mtk_w32(eth, 0x00000707, MTK_CDMW0_THRES);
+ mtk_w32(eth, 0x08000707, MTK_CDMW0_THRES);
mtk_w32(eth, 0x00000077, MTK_CDMW1_THRES);
/* Disable GDM1 RX CRC stripping */
@@ -4055,7 +4080,7 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
mtk_w32(eth, 0x00000300, PSE_DROP_CFG);
/* PSE should drop packets to port 8/9 on WDMA Rx ring full */
- mtk_w32(eth, 0x00000300, PSE_PPE0_DROP);
+ mtk_w32(eth, 0x00000300, PSE_PPE_DROP(0));
/* PSE Free Queue Flow Control */
mtk_w32(eth, 0x01fa01f4, PSE_FQFC_CFG2);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 90a377a..88ef2e9 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -151,7 +151,15 @@
#define PSE_FQFC_CFG1 0x100
#define PSE_FQFC_CFG2 0x104
#define PSE_DROP_CFG 0x108
-#define PSE_PPE0_DROP 0x110
+#define PSE_PPE_DROP(x) (0x110 + ((x) * 0x4))
+
+/* PSE Last FreeQ Page Request Control */
+#define PSE_DUMY_REQ 0x10C
+/* PSE_DUMY_REQ is not a typo but actually called like that also in
+ * MediaTek's datasheet
+ */
+#define PSE_DUMMY_WORK_GDM(x) BIT(16 + (x))
+#define DUMMY_PAGE_THR 0x1
/* PSE Input Queue Reservation Register*/
#define PSE_IQ_REV(x) (0x140 + (((x) - 1) << 2))
@@ -1271,6 +1279,7 @@ struct mtk_eth {
struct clk *clks[MTK_CLK_MAX];
struct mii_bus *mii_bus;
+ unsigned int mdc_divider;
struct work_struct pending_work;
unsigned long state;
diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
index 76f202d..b175119 100644
--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -1163,6 +1163,7 @@ static int mtk_star_tx_poll(struct napi_struct *napi, int budget)
struct net_device *ndev = priv->ndev;
unsigned int head = ring->head;
unsigned int entry = ring->tail;
+ unsigned long flags;
while (entry != head && count < (MTK_STAR_RING_NUM_DESCS - 1)) {
ret = mtk_star_tx_complete_one(priv);
@@ -1182,9 +1183,9 @@ static int mtk_star_tx_poll(struct napi_struct *napi, int budget)
netif_wake_queue(ndev);
if (napi_complete(napi)) {
- spin_lock(&priv->lock);
+ spin_lock_irqsave(&priv->lock, flags);
mtk_star_enable_dma_irq(priv, false, true);
- spin_unlock(&priv->lock);
+ spin_unlock_irqrestore(&priv->lock, flags);
}
return 0;
@@ -1341,16 +1342,16 @@ static int mtk_star_rx(struct mtk_star_priv *priv, int budget)
static int mtk_star_rx_poll(struct napi_struct *napi, int budget)
{
struct mtk_star_priv *priv;
+ unsigned long flags;
int work_done = 0;
priv = container_of(napi, struct mtk_star_priv, rx_napi);
work_done = mtk_star_rx(priv, budget);
- if (work_done < budget) {
- napi_complete_done(napi, work_done);
- spin_lock(&priv->lock);
+ if (work_done < budget && napi_complete_done(napi, work_done)) {
+ spin_lock_irqsave(&priv->lock, flags);
mtk_star_enable_dma_irq(priv, true, false);
- spin_unlock(&priv->lock);
+ spin_unlock_irqrestore(&priv->lock, flags);
}
return work_done;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 532c7fa..dbd9482 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -176,6 +176,7 @@ static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx)
priv = ptpsq->txqsq.priv;
+ rtnl_lock();
mutex_lock(&priv->state_lock);
chs = &priv->channels;
netdev = priv->netdev;
@@ -183,22 +184,19 @@ static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx)
carrier_ok = netif_carrier_ok(netdev);
netif_carrier_off(netdev);
- rtnl_lock();
mlx5e_deactivate_priv_channels(priv);
- rtnl_unlock();
mlx5e_ptp_close(chs->ptp);
err = mlx5e_ptp_open(priv, &chs->params, chs->c[0]->lag_port, &chs->ptp);
- rtnl_lock();
mlx5e_activate_priv_channels(priv);
- rtnl_unlock();
/* return carrier back if needed */
if (carrier_ok)
netif_carrier_on(netdev);
mutex_unlock(&priv->state_lock);
+ rtnl_unlock();
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
index 5c762a7..7a18a46 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
@@ -165,9 +165,6 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
struct flow_match_enc_keyid enc_keyid;
void *misc_c, *misc_v;
- misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
- misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
-
if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID))
return 0;
@@ -182,6 +179,30 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
err = mlx5e_tc_tun_parse_vxlan_gbp_option(priv, spec, f);
if (err)
return err;
+
+ /* We can't mix custom tunnel headers with symbolic ones and we
+ * don't have a symbolic field name for GBP, so we use custom
+ * tunnel headers in this case. We need hardware support to
+ * match on custom tunnel headers, but we already know it's
+ * supported because the previous call successfully checked for
+ * that.
+ */
+ misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+ misc_parameters_5);
+ misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+ misc_parameters_5);
+
+ /* Shift by 8 to account for the reserved bits in the vxlan
+ * header after the VNI.
+ */
+ MLX5_SET(fte_match_set_misc5, misc_c, tunnel_header_1,
+ be32_to_cpu(enc_keyid.mask->keyid) << 8);
+ MLX5_SET(fte_match_set_misc5, misc_v, tunnel_header_1,
+ be32_to_cpu(enc_keyid.key->keyid) << 8);
+
+ spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_5;
+
+ return 0;
}
/* match on VNI is required */
@@ -195,6 +216,11 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
return -EOPNOTSUPP;
}
+ misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+ misc_parameters);
+ misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+ misc_parameters);
+
MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni,
be32_to_cpu(enc_keyid.mask->keyid));
MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 9ba9960..f1d908f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1750,9 +1750,6 @@ extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr
!list_is_first(&attr->list, &flow->attrs))
return 0;
- if (flow_flag_test(flow, SLOW))
- return 0;
-
esw_attr = attr->esw_attr;
if (!esw_attr->split_count ||
esw_attr->split_count == esw_attr->out_count - 1)
@@ -1766,7 +1763,7 @@ extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr
for (i = esw_attr->split_count; i < esw_attr->out_count; i++) {
/* external dest with encap is considered as internal by firmware */
if (esw_attr->dests[i].vport == MLX5_VPORT_UPLINK &&
- !(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP_VALID))
+ !(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP))
ext_dest = true;
else
int_dest = true;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index a6a8eea..0e3a977 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -3533,7 +3533,9 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
int err;
mutex_init(&esw->offloads.termtbl_mutex);
- mlx5_rdma_enable_roce(esw->dev);
+ err = mlx5_rdma_enable_roce(esw->dev);
+ if (err)
+ goto err_roce;
err = mlx5_esw_host_number_init(esw);
if (err)
@@ -3594,6 +3596,7 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
esw_offloads_metadata_uninit(esw);
err_metadata:
mlx5_rdma_disable_roce(esw->dev);
+err_roce:
mutex_destroy(&esw->offloads.termtbl_mutex);
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
index eb3bd9c..ca9ecec 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
@@ -637,10 +637,6 @@ struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev,
bool use_l4_type;
int err;
- ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
- if (!ttc)
- return ERR_PTR(-ENOMEM);
-
switch (params->ns_type) {
case MLX5_FLOW_NAMESPACE_PORT_SEL:
use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
@@ -654,7 +650,16 @@ struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev,
return ERR_PTR(-EINVAL);
}
+ ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
+ if (!ttc)
+ return ERR_PTR(-ENOMEM);
+
ns = mlx5_get_flow_namespace(dev, params->ns_type);
+ if (!ns) {
+ kvfree(ttc);
+ return ERR_PTR(-EOPNOTSUPP);
+ }
+
groups = use_l4_type ? &inner_ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
&inner_ttc_groups[TTC_GROUPS_DEFAULT];
@@ -710,10 +715,6 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
bool use_l4_type;
int err;
- ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
- if (!ttc)
- return ERR_PTR(-ENOMEM);
-
switch (params->ns_type) {
case MLX5_FLOW_NAMESPACE_PORT_SEL:
use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
@@ -727,7 +728,16 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
return ERR_PTR(-EINVAL);
}
+ ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
+ if (!ttc)
+ return ERR_PTR(-ENOMEM);
+
ns = mlx5_get_flow_namespace(dev, params->ns_type);
+ if (!ns) {
+ kvfree(ttc);
+ return ERR_PTR(-EOPNOTSUPP);
+ }
+
groups = use_l4_type ? &ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
&ttc_groups[TTC_GROUPS_DEFAULT];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
index a42f6cd..5c552b7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
@@ -118,8 +118,8 @@ static void mlx5_rdma_make_default_gid(struct mlx5_core_dev *dev, union ib_gid *
static int mlx5_rdma_add_roce_addr(struct mlx5_core_dev *dev)
{
+ u8 mac[ETH_ALEN] = {};
union ib_gid gid;
- u8 mac[ETH_ALEN];
mlx5_rdma_make_default_gid(dev, &gid);
return mlx5_core_roce_gid_set(dev, 0,
@@ -140,17 +140,17 @@ void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev)
mlx5_nic_vport_disable_roce(dev);
}
-void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
+int mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
{
int err;
if (!MLX5_CAP_GEN(dev, roce))
- return;
+ return 0;
err = mlx5_nic_vport_enable_roce(dev);
if (err) {
mlx5_core_err(dev, "Failed to enable RoCE: %d\n", err);
- return;
+ return err;
}
err = mlx5_rdma_add_roce_addr(dev);
@@ -165,10 +165,11 @@ void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
goto del_roce_addr;
}
- return;
+ return err;
del_roce_addr:
mlx5_rdma_del_roce_addr(dev);
disable_roce:
mlx5_nic_vport_disable_roce(dev);
+ return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.h b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
index 750cff2..3d9e76c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
@@ -8,12 +8,12 @@
#ifdef CONFIG_MLX5_ESWITCH
-void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev);
+int mlx5_rdma_enable_roce(struct mlx5_core_dev *dev);
void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev);
#else /* CONFIG_MLX5_ESWITCH */
-static inline void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) {}
+static inline int mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) { return 0; }
static inline void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev) {}
#endif /* CONFIG_MLX5_ESWITCH */
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 23760b6..e2d6bfb 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1815,6 +1815,7 @@ static void lan743x_tx_frame_add_lso(struct lan743x_tx *tx,
if (nr_frags <= 0) {
tx->frame_data0 |= TX_DESC_DATA0_LS_;
tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+ tx->frame_last = tx->frame_first;
}
tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
tx_descriptor->data0 = cpu_to_le32(tx->frame_data0);
@@ -1884,6 +1885,7 @@ static int lan743x_tx_frame_add_fragment(struct lan743x_tx *tx,
tx->frame_first = 0;
tx->frame_data0 = 0;
tx->frame_tail = 0;
+ tx->frame_last = 0;
return -ENOMEM;
}
@@ -1924,16 +1926,18 @@ static void lan743x_tx_frame_end(struct lan743x_tx *tx,
TX_DESC_DATA0_DTYPE_DATA_) {
tx->frame_data0 |= TX_DESC_DATA0_LS_;
tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+ tx->frame_last = tx->frame_tail;
}
- tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
- buffer_info = &tx->buffer_info[tx->frame_tail];
+ tx_descriptor = &tx->ring_cpu_ptr[tx->frame_last];
+ buffer_info = &tx->buffer_info[tx->frame_last];
buffer_info->skb = skb;
if (time_stamp)
buffer_info->flags |= TX_BUFFER_INFO_FLAG_TIMESTAMP_REQUESTED;
if (ignore_sync)
buffer_info->flags |= TX_BUFFER_INFO_FLAG_IGNORE_SYNC;
+ tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
tx_descriptor->data0 = cpu_to_le32(tx->frame_data0);
tx->frame_tail = lan743x_tx_next_index(tx, tx->frame_tail);
tx->last_tail = tx->frame_tail;
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index 7f73d66..db5fc73 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -980,6 +980,7 @@ struct lan743x_tx {
u32 frame_first;
u32 frame_data0;
u32 frame_tail;
+ u32 frame_last;
struct lan743x_tx_buffer_info *buffer_info;
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index ef93df5..08bee56 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -830,6 +830,7 @@ EXPORT_SYMBOL(ocelot_vlan_prepare);
int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
bool untagged)
{
+ struct ocelot_port *ocelot_port = ocelot->ports[port];
int err;
/* Ignore VID 0 added to our RX filter by the 8021q module, since
@@ -849,6 +850,11 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
ocelot_bridge_vlan_find(ocelot, vid));
if (err)
return err;
+ } else if (ocelot_port->pvid_vlan &&
+ ocelot_bridge_vlan_find(ocelot, vid) == ocelot_port->pvid_vlan) {
+ err = ocelot_port_set_pvid(ocelot, port, NULL);
+ if (err)
+ return err;
}
/* Untagged egress vlan clasification */
diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 2aacc19..55b8d36 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -1925,8 +1925,8 @@ static u16 rtase_calc_time_mitigation(u32 time_us)
time_us = min_t(int, time_us, RTASE_MITI_MAX_TIME);
- msb = fls(time_us);
- if (msb >= RTASE_MITI_COUNT_BIT_NUM) {
+ if (time_us > RTASE_MITI_TIME_COUNT_MASK) {
+ msb = fls(time_us);
time_unit = msb - RTASE_MITI_COUNT_BIT_NUM;
time_count = time_us >> (msb - RTASE_MITI_COUNT_BIT_NUM);
} else {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
index 967a162..0c011a4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
@@ -320,8 +320,8 @@ enum rtc_control {
/* PTP and timestamping registers */
-#define GMAC3_X_ATSNS GENMASK(19, 16)
-#define GMAC3_X_ATSNS_SHIFT 16
+#define GMAC3_X_ATSNS GENMASK(29, 25)
+#define GMAC3_X_ATSNS_SHIFT 25
#define GMAC_PTP_TCR_ATSFC BIT(24)
#define GMAC_PTP_TCR_ATSEN0 BIT(25)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index a8b901c..56b76aa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -553,7 +553,7 @@ void dwmac1000_get_ptptime(void __iomem *ptpaddr, u64 *ptp_time)
u64 ns;
ns = readl(ptpaddr + GMAC_PTP_ATNR);
- ns += readl(ptpaddr + GMAC_PTP_ATSR) * NSEC_PER_SEC;
+ ns += (u64)readl(ptpaddr + GMAC_PTP_ATSR) * NSEC_PER_SEC;
*ptp_time = ns;
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index 0f59aa9..e2840fa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -222,7 +222,7 @@ static void get_ptptime(void __iomem *ptpaddr, u64 *ptp_time)
u64 ns;
ns = readl(ptpaddr + PTP_ATNR);
- ns += readl(ptpaddr + PTP_ATSR) * NSEC_PER_SEC;
+ ns += (u64)readl(ptpaddr + PTP_ATSR) * NSEC_PER_SEC;
*ptp_time = ns;
}
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 73c07f1..379b6e9 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -9064,6 +9064,8 @@ static void niu_try_msix(struct niu *np, u8 *ldg_num_map)
msi_vec[i].entry = i;
}
+ pdev->dev_flags |= PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST;
+
num_irqs = pci_enable_msix_range(pdev, msi_vec, 1, num_irqs);
if (num_irqs < 0) {
np->flags &= ~NIU_FLAGS_MSIX;
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index c9fd347..1e6d233 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -2666,7 +2666,7 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
of_property_read_bool(port_np, "ti,mac-only");
/* get phy/link info */
- port->slave.port_np = port_np;
+ port->slave.port_np = of_node_get(port_np);
ret = of_get_phy_mode(port_np, &port->slave.phy_if);
if (ret) {
dev_err(dev, "%pOF read phy-mode err %d\n",
@@ -2720,6 +2720,17 @@ static void am65_cpsw_nuss_phylink_cleanup(struct am65_cpsw_common *common)
}
}
+static void am65_cpsw_remove_dt(struct am65_cpsw_common *common)
+{
+ struct am65_cpsw_port *port;
+ int i;
+
+ for (i = 0; i < common->port_num; i++) {
+ port = &common->ports[i];
+ of_node_put(port->slave.port_np);
+ }
+}
+
static int
am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx)
{
@@ -3622,6 +3633,7 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
am65_cpsw_nuss_cleanup_ndev(common);
am65_cpsw_nuss_phylink_cleanup(common);
am65_cpts_release(common->cpts);
+ am65_cpsw_remove_dt(common);
err_of_clear:
if (common->mdio_dev)
of_platform_device_destroy(common->mdio_dev, NULL);
@@ -3661,6 +3673,7 @@ static void am65_cpsw_nuss_remove(struct platform_device *pdev)
am65_cpsw_nuss_phylink_cleanup(common);
am65_cpts_release(common->cpts);
am65_cpsw_disable_serdes_phy(common);
+ am65_cpsw_remove_dt(common);
if (common->mdio_dev)
of_platform_device_destroy(common->mdio_dev, NULL);
diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c
index b4a34c5..2a1c433 100644
--- a/drivers/net/ethernet/ti/icssg/icss_iep.c
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.c
@@ -412,6 +412,22 @@ static int icss_iep_perout_enable_hw(struct icss_iep *iep,
int ret;
u64 cmp;
+ if (!on) {
+ /* Disable CMP 1 */
+ regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+ IEP_CMP_CFG_CMP_EN(1), 0);
+
+ /* clear CMP regs */
+ regmap_write(iep->map, ICSS_IEP_CMP1_REG0, 0);
+ if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
+ regmap_write(iep->map, ICSS_IEP_CMP1_REG1, 0);
+
+ /* Disable sync */
+ regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0);
+
+ return 0;
+ }
+
/* Calculate width of the signal for PPS/PEROUT handling */
ts.tv_sec = req->on.sec;
ts.tv_nsec = req->on.nsec;
@@ -430,64 +446,39 @@ static int icss_iep_perout_enable_hw(struct icss_iep *iep,
if (ret)
return ret;
- if (on) {
- /* Configure CMP */
- regmap_write(iep->map, ICSS_IEP_CMP1_REG0, lower_32_bits(cmp));
- if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
- regmap_write(iep->map, ICSS_IEP_CMP1_REG1, upper_32_bits(cmp));
- /* Configure SYNC, based on req on width */
- regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG,
- div_u64(ns_width, iep->def_inc));
- regmap_write(iep->map, ICSS_IEP_SYNC0_PERIOD_REG, 0);
- regmap_write(iep->map, ICSS_IEP_SYNC_START_REG,
- div_u64(ns_start, iep->def_inc));
- regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0); /* one-shot mode */
- /* Enable CMP 1 */
- regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
- IEP_CMP_CFG_CMP_EN(1), IEP_CMP_CFG_CMP_EN(1));
- } else {
- /* Disable CMP 1 */
- regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
- IEP_CMP_CFG_CMP_EN(1), 0);
-
- /* clear regs */
- regmap_write(iep->map, ICSS_IEP_CMP1_REG0, 0);
- if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
- regmap_write(iep->map, ICSS_IEP_CMP1_REG1, 0);
- }
+ /* Configure CMP */
+ regmap_write(iep->map, ICSS_IEP_CMP1_REG0, lower_32_bits(cmp));
+ if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
+ regmap_write(iep->map, ICSS_IEP_CMP1_REG1, upper_32_bits(cmp));
+ /* Configure SYNC, based on req on width */
+ regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG,
+ div_u64(ns_width, iep->def_inc));
+ regmap_write(iep->map, ICSS_IEP_SYNC0_PERIOD_REG, 0);
+ regmap_write(iep->map, ICSS_IEP_SYNC_START_REG,
+ div_u64(ns_start, iep->def_inc));
+ regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0); /* one-shot mode */
+ /* Enable CMP 1 */
+ regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+ IEP_CMP_CFG_CMP_EN(1), IEP_CMP_CFG_CMP_EN(1));
} else {
- if (on) {
- u64 start_ns;
+ u64 start_ns;
- iep->period = ((u64)req->period.sec * NSEC_PER_SEC) +
- req->period.nsec;
- start_ns = ((u64)req->period.sec * NSEC_PER_SEC)
- + req->period.nsec;
- icss_iep_update_to_next_boundary(iep, start_ns);
+ iep->period = ((u64)req->period.sec * NSEC_PER_SEC) +
+ req->period.nsec;
+ start_ns = ((u64)req->period.sec * NSEC_PER_SEC)
+ + req->period.nsec;
+ icss_iep_update_to_next_boundary(iep, start_ns);
- regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG,
- div_u64(ns_width, iep->def_inc));
- regmap_write(iep->map, ICSS_IEP_SYNC_START_REG,
- div_u64(ns_start, iep->def_inc));
- /* Enable Sync in single shot mode */
- regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG,
- IEP_SYNC_CTRL_SYNC_N_EN(0) | IEP_SYNC_CTRL_SYNC_EN);
- /* Enable CMP 1 */
- regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
- IEP_CMP_CFG_CMP_EN(1), IEP_CMP_CFG_CMP_EN(1));
- } else {
- /* Disable CMP 1 */
- regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
- IEP_CMP_CFG_CMP_EN(1), 0);
-
- /* clear CMP regs */
- regmap_write(iep->map, ICSS_IEP_CMP1_REG0, 0);
- if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
- regmap_write(iep->map, ICSS_IEP_CMP1_REG1, 0);
-
- /* Disable sync */
- regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0);
- }
+ regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG,
+ div_u64(ns_width, iep->def_inc));
+ regmap_write(iep->map, ICSS_IEP_SYNC_START_REG,
+ div_u64(ns_start, iep->def_inc));
+ /* Enable Sync in single shot mode */
+ regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG,
+ IEP_SYNC_CTRL_SYNC_N_EN(0) | IEP_SYNC_CTRL_SYNC_EN);
+ /* Enable CMP 1 */
+ regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+ IEP_CMP_CFG_CMP_EN(1), IEP_CMP_CFG_CMP_EN(1));
}
return 0;
@@ -498,11 +489,21 @@ static int icss_iep_perout_enable(struct icss_iep *iep,
{
int ret = 0;
+ if (!on)
+ goto disable;
+
/* Reject requests with unsupported flags */
if (req->flags & ~(PTP_PEROUT_DUTY_CYCLE |
PTP_PEROUT_PHASE))
return -EOPNOTSUPP;
+ /* Set default "on" time (1ms) for the signal if not passed by the app */
+ if (!(req->flags & PTP_PEROUT_DUTY_CYCLE)) {
+ req->on.sec = 0;
+ req->on.nsec = NSEC_PER_MSEC;
+ }
+
+disable:
mutex_lock(&iep->ptp_clk_mutex);
if (iep->pps_enabled) {
@@ -513,12 +514,6 @@ static int icss_iep_perout_enable(struct icss_iep *iep,
if (iep->perout_enabled == !!on)
goto exit;
- /* Set default "on" time (1ms) for the signal if not passed by the app */
- if (!(req->flags & PTP_PEROUT_DUTY_CYCLE)) {
- req->on.sec = 0;
- req->on.nsec = NSEC_PER_MSEC;
- }
-
ret = icss_iep_perout_enable_hw(iep, req, on);
if (!ret)
iep->perout_enabled = !!on;
diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index 14002b0..b4be76e 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -583,7 +583,7 @@ u32 emac_xmit_xdp_frame(struct prueth_emac *emac,
first_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool);
if (!first_desc) {
netdev_dbg(ndev, "xdp tx: failed to allocate descriptor\n");
- goto drop_free_descs; /* drop */
+ return ICSSG_XDP_CONSUMED; /* drop */
}
if (page) { /* already DMA mapped by page_pool */
@@ -671,8 +671,10 @@ static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp,
q_idx = smp_processor_id() % emac->tx_ch_num;
result = emac_xmit_xdp_frame(emac, xdpf, page, q_idx);
- if (result == ICSSG_XDP_CONSUMED)
+ if (result == ICSSG_XDP_CONSUMED) {
+ ndev->stats.tx_dropped++;
goto drop;
+ }
dev_sw_netstats_rx_add(ndev, xdpf->len);
return result;
@@ -1215,9 +1217,6 @@ void prueth_reset_rx_chan(struct prueth_rx_chn *chn,
prueth_rx_cleanup);
if (disable)
k3_udma_glue_disable_rx_chn(chn->rx_chn);
-
- page_pool_destroy(chn->pg_pool);
- chn->pg_pool = NULL;
}
EXPORT_SYMBOL_GPL(prueth_reset_rx_chan);
diff --git a/drivers/net/ethernet/vertexcom/mse102x.c b/drivers/net/ethernet/vertexcom/mse102x.c
index 89dc4c4..e4d993f 100644
--- a/drivers/net/ethernet/vertexcom/mse102x.c
+++ b/drivers/net/ethernet/vertexcom/mse102x.c
@@ -6,6 +6,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/if_vlan.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/kernel.h>
@@ -33,7 +34,7 @@
#define CMD_CTR (0x2 << CMD_SHIFT)
#define CMD_MASK GENMASK(15, CMD_SHIFT)
-#define LEN_MASK GENMASK(CMD_SHIFT - 1, 0)
+#define LEN_MASK GENMASK(CMD_SHIFT - 2, 0)
#define DET_CMD_LEN 4
#define DET_SOF_LEN 2
@@ -262,7 +263,7 @@ static int mse102x_tx_frame_spi(struct mse102x_net *mse, struct sk_buff *txp,
}
static int mse102x_rx_frame_spi(struct mse102x_net *mse, u8 *buff,
- unsigned int frame_len)
+ unsigned int frame_len, bool drop)
{
struct mse102x_net_spi *mses = to_mse102x_spi(mse);
struct spi_transfer *xfer = &mses->spi_xfer;
@@ -280,6 +281,9 @@ static int mse102x_rx_frame_spi(struct mse102x_net *mse, u8 *buff,
netdev_err(mse->ndev, "%s: spi_sync() failed: %d\n",
__func__, ret);
mse->stats.xfer_err++;
+ } else if (drop) {
+ netdev_dbg(mse->ndev, "%s: Drop frame\n", __func__);
+ ret = -EINVAL;
} else if (*sof != cpu_to_be16(DET_SOF)) {
netdev_dbg(mse->ndev, "%s: SPI start of frame is invalid (0x%04x)\n",
__func__, *sof);
@@ -307,6 +311,7 @@ static void mse102x_rx_pkt_spi(struct mse102x_net *mse)
struct sk_buff *skb;
unsigned int rxalign;
unsigned int rxlen;
+ bool drop = false;
__be16 rx = 0;
u16 cmd_resp;
u8 *rxpkt;
@@ -329,7 +334,8 @@ static void mse102x_rx_pkt_spi(struct mse102x_net *mse)
net_dbg_ratelimited("%s: Unexpected response (0x%04x)\n",
__func__, cmd_resp);
mse->stats.invalid_rts++;
- return;
+ drop = true;
+ goto drop;
}
net_dbg_ratelimited("%s: Unexpected response to first CMD\n",
@@ -337,12 +343,20 @@ static void mse102x_rx_pkt_spi(struct mse102x_net *mse)
}
rxlen = cmd_resp & LEN_MASK;
- if (!rxlen) {
- net_dbg_ratelimited("%s: No frame length defined\n", __func__);
+ if (rxlen < ETH_ZLEN || rxlen > VLAN_ETH_FRAME_LEN) {
+ net_dbg_ratelimited("%s: Invalid frame length: %d\n", __func__,
+ rxlen);
mse->stats.invalid_len++;
- return;
+ drop = true;
}
+ /* In case of a invalid CMD_RTS, the frame must be consumed anyway.
+ * So assume the maximum possible frame length.
+ */
+drop:
+ if (drop)
+ rxlen = VLAN_ETH_FRAME_LEN;
+
rxalign = ALIGN(rxlen + DET_SOF_LEN + DET_DFT_LEN, 4);
skb = netdev_alloc_skb_ip_align(mse->ndev, rxalign);
if (!skb)
@@ -353,7 +367,7 @@ static void mse102x_rx_pkt_spi(struct mse102x_net *mse)
* They are copied, but ignored.
*/
rxpkt = skb_put(skb, rxlen) - DET_SOF_LEN;
- if (mse102x_rx_frame_spi(mse, rxpkt, rxlen)) {
+ if (mse102x_rx_frame_spi(mse, rxpkt, rxlen, drop)) {
mse->ndev->stats.rx_errors++;
dev_kfree_skb(skb);
return;
@@ -509,6 +523,7 @@ static irqreturn_t mse102x_irq(int irq, void *_mse)
static int mse102x_net_open(struct net_device *ndev)
{
struct mse102x_net *mse = netdev_priv(ndev);
+ struct mse102x_net_spi *mses = to_mse102x_spi(mse);
int ret;
ret = request_threaded_irq(ndev->irq, NULL, mse102x_irq, IRQF_ONESHOT,
@@ -524,6 +539,13 @@ static int mse102x_net_open(struct net_device *ndev)
netif_carrier_on(ndev);
+ /* The SPI interrupt can stuck in case of pending packet(s).
+ * So poll for possible packet(s) to re-arm the interrupt.
+ */
+ mutex_lock(&mses->lock);
+ mse102x_rx_pkt_spi(mse);
+ mutex_unlock(&mses->lock);
+
netif_dbg(mse, ifup, ndev, "network device up\n");
return 0;
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 00b0b31..e69eaa6 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -310,7 +310,8 @@ static bool wx_alloc_mapped_page(struct wx_ring *rx_ring,
return true;
page = page_pool_dev_alloc_pages(rx_ring->page_pool);
- WARN_ON(!page);
+ if (unlikely(!page))
+ return false;
dma = page_pool_get_dma_addr(page);
bi->page_dma = dma;
@@ -546,7 +547,8 @@ static void wx_rx_checksum(struct wx_ring *ring,
return;
/* Hardware can't guarantee csum if IPv6 Dest Header found */
- if (dptype.prot != WX_DEC_PTYPE_PROT_SCTP && WX_RXD_IPV6EX(rx_desc))
+ if (dptype.prot != WX_DEC_PTYPE_PROT_SCTP &&
+ wx_test_staterr(rx_desc, WX_RXD_STAT_IPV6EX))
return;
/* if L4 checksum error */
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index 5b230ecb..4c545b2 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -513,6 +513,7 @@ enum WX_MSCA_CMD_value {
#define WX_RXD_STAT_L4CS BIT(7) /* L4 xsum calculated */
#define WX_RXD_STAT_IPCS BIT(8) /* IP xsum calculated */
#define WX_RXD_STAT_OUTERIPCS BIT(10) /* Cloud IP xsum calculated*/
+#define WX_RXD_STAT_IPV6EX BIT(12) /* IPv6 Dest Header */
#define WX_RXD_STAT_TS BIT(14) /* IEEE1588 Time Stamp */
#define WX_RXD_ERR_OUTERIPER BIT(26) /* CRC IP Header error */
@@ -589,8 +590,6 @@ enum wx_l2_ptypes {
#define WX_RXD_PKTTYPE(_rxd) \
((le32_to_cpu((_rxd)->wb.lower.lo_dword.data) >> 9) & 0xFF)
-#define WX_RXD_IPV6EX(_rxd) \
- ((le32_to_cpu((_rxd)->wb.lower.lo_dword.data) >> 6) & 0x1)
/*********************** Transmit Descriptor Config Masks ****************/
#define WX_TXD_STAT_DD BIT(0) /* Descriptor Done */
#define WX_TXD_DTYP_DATA 0 /* Adv Data Descriptor */
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
index a615921..91b3055 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
@@ -625,7 +625,7 @@ static int ngbe_probe(struct pci_dev *pdev,
/* setup the private structure */
err = ngbe_sw_init(wx);
if (err)
- goto err_free_mac_table;
+ goto err_pci_release_regions;
/* check if flash load is done after hw power up */
err = wx_check_flash_load(wx, NGBE_SPI_ILDR_STATUS_PERST);
@@ -719,6 +719,7 @@ static int ngbe_probe(struct pci_dev *pdev,
err_clear_interrupt_scheme:
wx_clear_interrupt_scheme(wx);
err_free_mac_table:
+ kfree(wx->rss_key);
kfree(wx->mac_table);
err_pci_release_regions:
pci_release_selected_regions(pdev,
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
index a2e245e3..38206a4 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
@@ -611,7 +611,7 @@ static int txgbe_probe(struct pci_dev *pdev,
/* setup the private structure */
err = txgbe_sw_init(wx);
if (err)
- goto err_free_mac_table;
+ goto err_pci_release_regions;
/* check if flash load is done after hw power up */
err = wx_check_flash_load(wx, TXGBE_SPI_ILDR_STATUS_PERST);
@@ -769,6 +769,7 @@ static int txgbe_probe(struct pci_dev *pdev,
wx_clear_interrupt_scheme(wx);
wx_control_hw(wx, false);
err_free_mac_table:
+ kfree(wx->rss_key);
kfree(wx->mac_table);
err_pci_release_regions:
pci_release_selected_regions(pdev,
diff --git a/drivers/net/mdio/mdio-mux-meson-gxl.c b/drivers/net/mdio/mdio-mux-meson-gxl.c
index 00c6624..3dd12a8 100644
--- a/drivers/net/mdio/mdio-mux-meson-gxl.c
+++ b/drivers/net/mdio/mdio-mux-meson-gxl.c
@@ -17,6 +17,7 @@
#define REG2_LEDACT GENMASK(23, 22)
#define REG2_LEDLINK GENMASK(25, 24)
#define REG2_DIV4SEL BIT(27)
+#define REG2_REVERSED BIT(28)
#define REG2_ADCBYPASS BIT(30)
#define REG2_CLKINSEL BIT(31)
#define ETH_REG3 0x4
@@ -65,7 +66,7 @@ static void gxl_enable_internal_mdio(struct gxl_mdio_mux *priv)
* The only constraint is that it must match the one in
* drivers/net/phy/meson-gxl.c to properly match the PHY.
*/
- writel(FIELD_PREP(REG2_PHYID, EPHY_GXL_ID),
+ writel(REG2_REVERSED | FIELD_PREP(REG2_PHYID, EPHY_GXL_ID),
priv->regs + ETH_REG2);
/* Enable the internal phy */
diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
index 14f3615..e32013e 100644
--- a/drivers/net/phy/dp83822.c
+++ b/drivers/net/phy/dp83822.c
@@ -730,7 +730,7 @@ static int dp83822_phy_reset(struct phy_device *phydev)
return phydev->drv->config_init(phydev);
}
-#ifdef CONFIG_OF_MDIO
+#if IS_ENABLED(CONFIG_OF_MDIO)
static const u32 tx_amplitude_100base_tx_gain[] = {
80, 82, 83, 85, 87, 88, 90, 92,
93, 95, 97, 98, 100, 102, 103, 105,
diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c
index 0e17cc4..93de88c 100644
--- a/drivers/net/phy/microchip.c
+++ b/drivers/net/phy/microchip.c
@@ -37,47 +37,6 @@ static int lan88xx_write_page(struct phy_device *phydev, int page)
return __phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, page);
}
-static int lan88xx_phy_config_intr(struct phy_device *phydev)
-{
- int rc;
-
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
- /* unmask all source and clear them before enable */
- rc = phy_write(phydev, LAN88XX_INT_MASK, 0x7FFF);
- rc = phy_read(phydev, LAN88XX_INT_STS);
- rc = phy_write(phydev, LAN88XX_INT_MASK,
- LAN88XX_INT_MASK_MDINTPIN_EN_ |
- LAN88XX_INT_MASK_LINK_CHANGE_);
- } else {
- rc = phy_write(phydev, LAN88XX_INT_MASK, 0);
- if (rc)
- return rc;
-
- /* Ack interrupts after they have been disabled */
- rc = phy_read(phydev, LAN88XX_INT_STS);
- }
-
- return rc < 0 ? rc : 0;
-}
-
-static irqreturn_t lan88xx_handle_interrupt(struct phy_device *phydev)
-{
- int irq_status;
-
- irq_status = phy_read(phydev, LAN88XX_INT_STS);
- if (irq_status < 0) {
- phy_error(phydev);
- return IRQ_NONE;
- }
-
- if (!(irq_status & LAN88XX_INT_STS_LINK_CHANGE_))
- return IRQ_NONE;
-
- phy_trigger_machine(phydev);
-
- return IRQ_HANDLED;
-}
-
static int lan88xx_suspend(struct phy_device *phydev)
{
struct lan88xx_priv *priv = phydev->priv;
@@ -528,8 +487,9 @@ static struct phy_driver microchip_phy_driver[] = {
.config_aneg = lan88xx_config_aneg,
.link_change_notify = lan88xx_link_change_notify,
- .config_intr = lan88xx_phy_config_intr,
- .handle_interrupt = lan88xx_handle_interrupt,
+ /* Interrupt handling is broken, do not define related
+ * functions to force polling.
+ */
.suspend = lan88xx_suspend,
.resume = genphy_resume,
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 675fbd2..cc1bfd2 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -244,6 +244,46 @@ static bool phy_drv_wol_enabled(struct phy_device *phydev)
return wol.wolopts != 0;
}
+static void phy_link_change(struct phy_device *phydev, bool up)
+{
+ struct net_device *netdev = phydev->attached_dev;
+
+ if (up)
+ netif_carrier_on(netdev);
+ else
+ netif_carrier_off(netdev);
+ phydev->adjust_link(netdev);
+ if (phydev->mii_ts && phydev->mii_ts->link_state)
+ phydev->mii_ts->link_state(phydev->mii_ts, phydev);
+}
+
+/**
+ * phy_uses_state_machine - test whether consumer driver uses PAL state machine
+ * @phydev: the target PHY device structure
+ *
+ * Ultimately, this aims to indirectly determine whether the PHY is attached
+ * to a consumer which uses the state machine by calling phy_start() and
+ * phy_stop().
+ *
+ * When the PHY driver consumer uses phylib, it must have previously called
+ * phy_connect_direct() or one of its derivatives, so that phy_prepare_link()
+ * has set up a hook for monitoring state changes.
+ *
+ * When the PHY driver is used by the MAC driver consumer through phylink (the
+ * only other provider of a phy_link_change() method), using the PHY state
+ * machine is not optional.
+ *
+ * Return: true if consumer calls phy_start() and phy_stop(), false otherwise.
+ */
+static bool phy_uses_state_machine(struct phy_device *phydev)
+{
+ if (phydev->phy_link_change == phy_link_change)
+ return phydev->attached_dev && phydev->adjust_link;
+
+ /* phydev->phy_link_change is implicitly phylink_phy_change() */
+ return true;
+}
+
static bool mdio_bus_phy_may_suspend(struct phy_device *phydev)
{
struct device_driver *drv = phydev->mdio.dev.driver;
@@ -310,7 +350,7 @@ static __maybe_unused int mdio_bus_phy_suspend(struct device *dev)
* may call phy routines that try to grab the same lock, and that may
* lead to a deadlock.
*/
- if (phydev->attached_dev && phydev->adjust_link)
+ if (phy_uses_state_machine(phydev))
phy_stop_machine(phydev);
if (!mdio_bus_phy_may_suspend(phydev))
@@ -364,7 +404,7 @@ static __maybe_unused int mdio_bus_phy_resume(struct device *dev)
}
}
- if (phydev->attached_dev && phydev->adjust_link)
+ if (phy_uses_state_machine(phydev))
phy_start_machine(phydev);
return 0;
@@ -1055,19 +1095,6 @@ struct phy_device *phy_find_first(struct mii_bus *bus)
}
EXPORT_SYMBOL(phy_find_first);
-static void phy_link_change(struct phy_device *phydev, bool up)
-{
- struct net_device *netdev = phydev->attached_dev;
-
- if (up)
- netif_carrier_on(netdev);
- else
- netif_carrier_off(netdev);
- phydev->adjust_link(netdev);
- if (phydev->mii_ts && phydev->mii_ts->link_state)
- phydev->mii_ts->link_state(phydev->mii_ts, phydev);
-}
-
/**
* phy_prepare_link - prepares the PHY layer to monitor link status
* @phydev: target phy_device struct
diff --git a/drivers/net/phy/phy_led_triggers.c b/drivers/net/phy/phy_led_triggers.c
index bd3c955..6089369 100644
--- a/drivers/net/phy/phy_led_triggers.c
+++ b/drivers/net/phy/phy_led_triggers.c
@@ -93,9 +93,8 @@ int phy_led_triggers_register(struct phy_device *phy)
if (!phy->phy_num_led_triggers)
return 0;
- phy->led_link_trigger = devm_kzalloc(&phy->mdio.dev,
- sizeof(*phy->led_link_trigger),
- GFP_KERNEL);
+ phy->led_link_trigger = kzalloc(sizeof(*phy->led_link_trigger),
+ GFP_KERNEL);
if (!phy->led_link_trigger) {
err = -ENOMEM;
goto out_clear;
@@ -105,10 +104,9 @@ int phy_led_triggers_register(struct phy_device *phy)
if (err)
goto out_free_link;
- phy->phy_led_triggers = devm_kcalloc(&phy->mdio.dev,
- phy->phy_num_led_triggers,
- sizeof(struct phy_led_trigger),
- GFP_KERNEL);
+ phy->phy_led_triggers = kcalloc(phy->phy_num_led_triggers,
+ sizeof(struct phy_led_trigger),
+ GFP_KERNEL);
if (!phy->phy_led_triggers) {
err = -ENOMEM;
goto out_unreg_link;
@@ -129,11 +127,11 @@ int phy_led_triggers_register(struct phy_device *phy)
out_unreg:
while (i--)
phy_led_trigger_unregister(&phy->phy_led_triggers[i]);
- devm_kfree(&phy->mdio.dev, phy->phy_led_triggers);
+ kfree(phy->phy_led_triggers);
out_unreg_link:
phy_led_trigger_unregister(phy->led_link_trigger);
out_free_link:
- devm_kfree(&phy->mdio.dev, phy->led_link_trigger);
+ kfree(phy->led_link_trigger);
phy->led_link_trigger = NULL;
out_clear:
phy->phy_num_led_triggers = 0;
@@ -147,8 +145,13 @@ void phy_led_triggers_unregister(struct phy_device *phy)
for (i = 0; i < phy->phy_num_led_triggers; i++)
phy_led_trigger_unregister(&phy->phy_led_triggers[i]);
+ kfree(phy->phy_led_triggers);
+ phy->phy_led_triggers = NULL;
- if (phy->led_link_trigger)
+ if (phy->led_link_trigger) {
phy_led_trigger_unregister(phy->led_link_trigger);
+ kfree(phy->led_link_trigger);
+ phy->led_link_trigger = NULL;
+ }
}
EXPORT_SYMBOL_GPL(phy_led_triggers_unregister);
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index b68369e..1bdd5d8 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -81,6 +81,7 @@ struct phylink {
unsigned int pcs_state;
bool link_failed;
+ bool suspend_link_up;
bool major_config_failed;
bool mac_supports_eee_ops;
bool mac_supports_eee;
@@ -2545,14 +2546,16 @@ void phylink_suspend(struct phylink *pl, bool mac_wol)
/* Stop the resolver bringing the link up */
__set_bit(PHYLINK_DISABLE_MAC_WOL, &pl->phylink_disable_state);
- /* Disable the carrier, to prevent transmit timeouts,
- * but one would hope all packets have been sent. This
- * also means phylink_resolve() will do nothing.
- */
- if (pl->netdev)
- netif_carrier_off(pl->netdev);
- else
+ pl->suspend_link_up = phylink_link_is_up(pl);
+ if (pl->suspend_link_up) {
+ /* Disable the carrier, to prevent transmit timeouts,
+ * but one would hope all packets have been sent. This
+ * also means phylink_resolve() will do nothing.
+ */
+ if (pl->netdev)
+ netif_carrier_off(pl->netdev);
pl->old_link_state = false;
+ }
/* We do not call mac_link_down() here as we want the
* link to remain up to receive the WoL packets.
@@ -2603,15 +2606,18 @@ void phylink_resume(struct phylink *pl)
if (test_bit(PHYLINK_DISABLE_MAC_WOL, &pl->phylink_disable_state)) {
/* Wake-on-Lan enabled, MAC handling */
- /* Call mac_link_down() so we keep the overall state balanced.
- * Do this under the state_mutex lock for consistency. This
- * will cause a "Link Down" message to be printed during
- * resume, which is harmless - the true link state will be
- * printed when we run a resolve.
- */
- mutex_lock(&pl->state_mutex);
- phylink_link_down(pl);
- mutex_unlock(&pl->state_mutex);
+ if (pl->suspend_link_up) {
+ /* Call mac_link_down() so we keep the overall state
+ * balanced. Do this under the state_mutex lock for
+ * consistency. This will cause a "Link Down" message
+ * to be printed during resume, which is harmless -
+ * the true link state will be printed when we run a
+ * resolve.
+ */
+ mutex_lock(&pl->state_mutex);
+ phylink_link_down(pl);
+ mutex_unlock(&pl->state_mutex);
+ }
/* Re-apply the link parameters so that all the settings get
* restored to the MAC.
diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c
index 644e99f..9c49321 100644
--- a/drivers/net/ppp/ppp_synctty.c
+++ b/drivers/net/ppp/ppp_synctty.c
@@ -506,6 +506,11 @@ ppp_sync_txmunge(struct syncppp *ap, struct sk_buff *skb)
unsigned char *data;
int islcp;
+ /* Ensure we can safely access protocol field and LCP code */
+ if (!pskb_may_pull(skb, 3)) {
+ kfree_skb(skb);
+ return NULL;
+ }
data = skb->data;
proto = get_unaligned_be16(data);
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index bb0bf14..7b3739b 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -630,16 +630,6 @@ static const struct driver_info zte_rndis_info = {
.tx_fixup = rndis_tx_fixup,
};
-static const struct driver_info wwan_rndis_info = {
- .description = "Mobile Broadband RNDIS device",
- .flags = FLAG_WWAN | FLAG_POINTTOPOINT | FLAG_FRAMING_RN | FLAG_NO_SETINT,
- .bind = rndis_bind,
- .unbind = rndis_unbind,
- .status = rndis_status,
- .rx_fixup = rndis_rx_fixup,
- .tx_fixup = rndis_tx_fixup,
-};
-
/*-------------------------------------------------------------------------*/
static const struct usb_device_id products [] = {
@@ -676,11 +666,9 @@ static const struct usb_device_id products [] = {
USB_INTERFACE_INFO(USB_CLASS_WIRELESS_CONTROLLER, 1, 3),
.driver_info = (unsigned long) &rndis_info,
}, {
- /* Mobile Broadband Modem, seen in Novatel Verizon USB730L and
- * Telit FN990A (RNDIS)
- */
+ /* Novatel Verizon USB730L */
USB_INTERFACE_INFO(USB_CLASS_MISC, 4, 1),
- .driver_info = (unsigned long)&wwan_rndis_info,
+ .driver_info = (unsigned long) &rndis_info,
},
{ }, // END
};
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7e46172..848fab5 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3342,7 +3342,8 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
}
-static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
+static void __virtnet_rx_pause(struct virtnet_info *vi,
+ struct receive_queue *rq)
{
bool running = netif_running(vi->dev);
@@ -3352,17 +3353,63 @@ static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
}
}
-static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq)
+static void virtnet_rx_pause_all(struct virtnet_info *vi)
+{
+ int i;
+
+ /*
+ * Make sure refill_work does not run concurrently to
+ * avoid napi_disable race which leads to deadlock.
+ */
+ disable_delayed_refill(vi);
+ cancel_delayed_work_sync(&vi->refill);
+ for (i = 0; i < vi->max_queue_pairs; i++)
+ __virtnet_rx_pause(vi, &vi->rq[i]);
+}
+
+static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
+{
+ /*
+ * Make sure refill_work does not run concurrently to
+ * avoid napi_disable race which leads to deadlock.
+ */
+ disable_delayed_refill(vi);
+ cancel_delayed_work_sync(&vi->refill);
+ __virtnet_rx_pause(vi, rq);
+}
+
+static void __virtnet_rx_resume(struct virtnet_info *vi,
+ struct receive_queue *rq,
+ bool refill)
{
bool running = netif_running(vi->dev);
- if (!try_fill_recv(vi, rq, GFP_KERNEL))
+ if (refill && !try_fill_recv(vi, rq, GFP_KERNEL))
schedule_delayed_work(&vi->refill, 0);
if (running)
virtnet_napi_enable(rq);
}
+static void virtnet_rx_resume_all(struct virtnet_info *vi)
+{
+ int i;
+
+ enable_delayed_refill(vi);
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ if (i < vi->curr_queue_pairs)
+ __virtnet_rx_resume(vi, &vi->rq[i], true);
+ else
+ __virtnet_rx_resume(vi, &vi->rq[i], false);
+ }
+}
+
+static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq)
+{
+ enable_delayed_refill(vi);
+ __virtnet_rx_resume(vi, rq, true);
+}
+
static int virtnet_rx_resize(struct virtnet_info *vi,
struct receive_queue *rq, u32 ring_num)
{
@@ -5959,12 +6006,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
if (prog)
bpf_prog_add(prog, vi->max_queue_pairs - 1);
+ virtnet_rx_pause_all(vi);
+
/* Make sure NAPI is not using any XDP TX queues for RX. */
if (netif_running(dev)) {
- for (i = 0; i < vi->max_queue_pairs; i++) {
- virtnet_napi_disable(&vi->rq[i]);
+ for (i = 0; i < vi->max_queue_pairs; i++)
virtnet_napi_tx_disable(&vi->sq[i]);
- }
}
if (!prog) {
@@ -5996,13 +6043,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
vi->xdp_enabled = false;
}
+ virtnet_rx_resume_all(vi);
for (i = 0; i < vi->max_queue_pairs; i++) {
if (old_prog)
bpf_prog_put(old_prog);
- if (netif_running(dev)) {
- virtnet_napi_enable(&vi->rq[i]);
+ if (netif_running(dev))
virtnet_napi_tx_enable(&vi->sq[i]);
- }
}
return 0;
@@ -6014,11 +6060,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog);
}
+ virtnet_rx_resume_all(vi);
if (netif_running(dev)) {
- for (i = 0; i < vi->max_queue_pairs; i++) {
- virtnet_napi_enable(&vi->rq[i]);
+ for (i = 0; i < vi->max_queue_pairs; i++)
virtnet_napi_tx_enable(&vi->sq[i]);
- }
}
if (prog)
bpf_prog_sub(prog, vi->max_queue_pairs - 1);
diff --git a/drivers/net/vmxnet3/vmxnet3_xdp.c b/drivers/net/vmxnet3/vmxnet3_xdp.c
index 616ecc3..5f47049 100644
--- a/drivers/net/vmxnet3/vmxnet3_xdp.c
+++ b/drivers/net/vmxnet3/vmxnet3_xdp.c
@@ -397,7 +397,7 @@ vmxnet3_process_xdp(struct vmxnet3_adapter *adapter,
xdp_init_buff(&xdp, PAGE_SIZE, &rq->xdp_rxq);
xdp_prepare_buff(&xdp, page_address(page), rq->page_pool->p.offset,
- rbi->len, false);
+ rcd->len, false);
xdp_buff_clear_frags_flag(&xdp);
xdp_prog = rcu_dereference(rq->adapter->xdp_bpf_prog);
diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c
index 6e6e9f0..06d19e9 100644
--- a/drivers/net/vxlan/vxlan_vnifilter.c
+++ b/drivers/net/vxlan/vxlan_vnifilter.c
@@ -627,7 +627,11 @@ static void vxlan_vni_delete_group(struct vxlan_dev *vxlan,
* default dst remote_ip previously added for this vni
*/
if (!vxlan_addr_any(&vninode->remote_ip) ||
- !vxlan_addr_any(&dst->remote_ip))
+ !vxlan_addr_any(&dst->remote_ip)) {
+ u32 hash_index = fdb_head_index(vxlan, all_zeros_mac,
+ vninode->vni);
+
+ spin_lock_bh(&vxlan->hash_lock[hash_index]);
__vxlan_fdb_delete(vxlan, all_zeros_mac,
(vxlan_addr_any(&vninode->remote_ip) ?
dst->remote_ip : vninode->remote_ip),
@@ -635,6 +639,8 @@ static void vxlan_vni_delete_group(struct vxlan_dev *vxlan,
vninode->vni, vninode->vni,
dst->remote_ifindex,
true);
+ spin_unlock_bh(&vxlan->hash_lock[hash_index]);
+ }
if (vxlan->dev->flags & IFF_UP) {
if (vxlan_addr_multicast(&vninode->remote_ip) &&
diff --git a/drivers/net/wireless/ath/carl9170/fw.c b/drivers/net/wireless/ath/carl9170/fw.c
index 4c1aecd..419f553 100644
--- a/drivers/net/wireless/ath/carl9170/fw.c
+++ b/drivers/net/wireless/ath/carl9170/fw.c
@@ -15,7 +15,7 @@
#include "fwcmd.h"
#include "version.h"
-static const u8 otus_magic[4] = { OTUS_MAGIC };
+static const u8 otus_magic[4] __nonstring = { OTUS_MAGIC };
static const void *carl9170_fw_find_desc(struct ar9170 *ar, const u8 descid[4],
const unsigned int len, const u8 compatible_revision)
diff --git a/drivers/net/wireless/atmel/at76c50x-usb.c b/drivers/net/wireless/atmel/at76c50x-usb.c
index 4f01189..6842c2b 100644
--- a/drivers/net/wireless/atmel/at76c50x-usb.c
+++ b/drivers/net/wireless/atmel/at76c50x-usb.c
@@ -2552,7 +2552,7 @@ static void at76_disconnect(struct usb_interface *interface)
wiphy_info(priv->hw->wiphy, "disconnecting\n");
at76_delete_device(priv);
- usb_put_dev(priv->udev);
+ usb_put_dev(interface_to_usbdev(interface));
dev_info(&interface->dev, "disconnected\n");
}
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
index cfcf01e..f26e467 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
@@ -561,8 +561,10 @@ struct brcmf_mp_device *brcmf_get_module_param(struct device *dev,
if (!found) {
/* No platform data for this device, try OF and DMI data */
brcmf_dmi_probe(settings, chip, chiprev);
- if (brcmf_of_probe(dev, bus_type, settings) == -EPROBE_DEFER)
+ if (brcmf_of_probe(dev, bus_type, settings) == -EPROBE_DEFER) {
+ kfree(settings);
return ERR_PTR(-EPROBE_DEFER);
+ }
brcmf_acpi_probe(dev, bus_type, settings);
}
return settings;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
index 2821c27..d06c724 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
@@ -896,14 +896,16 @@ brcmf_usb_dl_writeimage(struct brcmf_usbdev_info *devinfo, u8 *fw, int fwlen)
}
/* 1) Prepare USB boot loader for runtime image */
- brcmf_usb_dl_cmd(devinfo, DL_START, &state, sizeof(state));
+ err = brcmf_usb_dl_cmd(devinfo, DL_START, &state, sizeof(state));
+ if (err)
+ goto fail;
rdlstate = le32_to_cpu(state.state);
rdlbytes = le32_to_cpu(state.bytes);
/* 2) Check we are in the Waiting state */
if (rdlstate != DL_WAITING) {
- brcmf_err("Failed to DL_START\n");
+ brcmf_err("Invalid DL state: %u\n", rdlstate);
err = -EINVAL;
goto fail;
}
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
index 670031f..59af369 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
@@ -142,8 +142,6 @@ const struct iwl_cfg_trans_params iwl_sc_trans_cfg = {
.ltr_delay = IWL_CFG_TRANS_LTR_DELAY_2500US,
};
-const char iwl_sp_name[] = "Intel(R) Wi-Fi 7 BE213 160MHz";
-
const struct iwl_cfg iwl_cfg_sc = {
.fw_name_mac = "sc",
IWL_DEVICE_SC,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index b9bd89b..acafee5 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -2,7 +2,7 @@
/*
* Copyright (C) 2005-2014, 2018-2021 Intel Corporation
* Copyright (C) 2016-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2025 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
*/
#ifndef __IWL_CONFIG_H__
#define __IWL_CONFIG_H__
@@ -451,8 +451,11 @@ struct iwl_cfg {
#define IWL_CFG_RF_ID_HR 0x7
#define IWL_CFG_RF_ID_HR1 0x4
-#define IWL_CFG_BW_NO_LIM (U16_MAX - 1)
-#define IWL_CFG_BW_ANY U16_MAX
+#define IWL_CFG_NO_160 0x1
+#define IWL_CFG_160 0x0
+
+#define IWL_CFG_NO_320 0x1
+#define IWL_CFG_320 0x0
#define IWL_CFG_CORES_BT 0x0
#define IWL_CFG_CORES_BT_GNSS 0x5
@@ -464,7 +467,7 @@ struct iwl_cfg {
#define IWL_CFG_IS_JACKET 0x1
#define IWL_SUBDEVICE_RF_ID(subdevice) ((u16)((subdevice) & 0x00F0) >> 4)
-#define IWL_SUBDEVICE_BW_LIM(subdevice) ((u16)((subdevice) & 0x0200) >> 9)
+#define IWL_SUBDEVICE_NO_160(subdevice) ((u16)((subdevice) & 0x0200) >> 9)
#define IWL_SUBDEVICE_CORES(subdevice) ((u16)((subdevice) & 0x1C00) >> 10)
struct iwl_dev_info {
@@ -472,10 +475,10 @@ struct iwl_dev_info {
u16 subdevice;
u16 mac_type;
u16 rf_type;
- u16 bw_limit;
u8 mac_step;
u8 rf_step;
u8 rf_id;
+ u8 no_160;
u8 cores;
u8 cdb;
u8 jacket;
@@ -489,7 +492,7 @@ extern const unsigned int iwl_dev_info_table_size;
const struct iwl_dev_info *
iwl_pci_find_dev_info(u16 device, u16 subsystem_device,
u16 mac_type, u8 mac_step, u16 rf_type, u8 cdb,
- u8 jacket, u8 rf_id, u8 bw_limit, u8 cores, u8 rf_step);
+ u8 jacket, u8 rf_id, u8 no_160, u8 cores, u8 rf_step);
extern const struct pci_device_id iwl_hw_card_ids[];
#endif
@@ -550,7 +553,6 @@ extern const char iwl_ax231_name[];
extern const char iwl_ax411_name[];
extern const char iwl_fm_name[];
extern const char iwl_wh_name[];
-extern const char iwl_sp_name[];
extern const char iwl_gl_name[];
extern const char iwl_mtp_name[];
extern const char iwl_dr_name[];
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
index be9e464..3ff493e 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
@@ -148,6 +148,7 @@
* during a error FW error.
*/
#define CSR_FUNC_SCRATCH_INIT_VALUE (0x01010101)
+#define CSR_FUNC_SCRATCH_POWER_OFF_MASK 0xFFFF
/* Bits for CSR_HW_IF_CONFIG_REG */
#define CSR_HW_IF_CONFIG_REG_MSK_MAC_STEP_DASH (0x0000000F)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index cd1b004..c381511 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
/*
- * Copyright (C) 2005-2014, 2018-2023, 2025 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2023 Intel Corporation
* Copyright (C) 2013-2015 Intel Mobile Communications GmbH
* Copyright (C) 2016-2017 Intel Deutschland GmbH
*/
@@ -944,8 +944,7 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_MASK);
break;
case NL80211_BAND_6GHZ:
- if (!trans->reduced_cap_sku &&
- trans->bw_limit >= 320) {
+ if (!trans->reduced_cap_sku) {
iftype_data->eht_cap.eht_cap_elem.phy_cap_info[0] |=
IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ;
iftype_data->eht_cap.eht_cap_elem.phy_cap_info[1] |=
@@ -1095,22 +1094,19 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
iftype_data->eht_cap.eht_mcs_nss_supp.bw._320.rx_tx_mcs13_max_nss = 0;
}
- if (trans->bw_limit < 160)
+ if (trans->no_160)
iftype_data->he_cap.he_cap_elem.phy_cap_info[0] &=
~IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G;
- if (trans->bw_limit < 320 || trans->reduced_cap_sku) {
+ if (trans->reduced_cap_sku) {
memset(&iftype_data->eht_cap.eht_mcs_nss_supp.bw._320, 0,
sizeof(iftype_data->eht_cap.eht_mcs_nss_supp.bw._320));
- iftype_data->eht_cap.eht_cap_elem.phy_cap_info[2] &=
- ~IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK;
- }
-
- if (trans->reduced_cap_sku) {
iftype_data->eht_cap.eht_mcs_nss_supp.bw._80.rx_tx_mcs13_max_nss = 0;
iftype_data->eht_cap.eht_mcs_nss_supp.bw._160.rx_tx_mcs13_max_nss = 0;
iftype_data->eht_cap.eht_cap_elem.phy_cap_info[8] &=
~IEEE80211_EHT_PHY_CAP8_RX_4096QAM_WIDER_BW_DL_OFDMA;
+ iftype_data->eht_cap.eht_cap_elem.phy_cap_info[2] &=
+ ~IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK;
}
}
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
index c1607b6..e7b2e08 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
@@ -21,6 +21,7 @@ struct iwl_trans_dev_restart_data {
struct list_head list;
unsigned int restart_count;
time64_t last_error;
+ bool backoff;
char name[];
};
@@ -125,13 +126,20 @@ iwl_trans_determine_restart_mode(struct iwl_trans *trans)
if (!data)
return at_least;
- if (ktime_get_boottime_seconds() - data->last_error >=
+ if (!data->backoff &&
+ ktime_get_boottime_seconds() - data->last_error >=
IWL_TRANS_RESET_OK_TIME)
data->restart_count = 0;
index = data->restart_count;
- if (index >= ARRAY_SIZE(escalation_list))
+ if (index >= ARRAY_SIZE(escalation_list)) {
index = ARRAY_SIZE(escalation_list) - 1;
+ if (!data->backoff) {
+ data->backoff = true;
+ return IWL_RESET_MODE_BACKOFF;
+ }
+ data->backoff = false;
+ }
return max(at_least, escalation_list[index]);
}
@@ -140,7 +148,8 @@ iwl_trans_determine_restart_mode(struct iwl_trans *trans)
static void iwl_trans_restart_wk(struct work_struct *wk)
{
- struct iwl_trans *trans = container_of(wk, typeof(*trans), restart.wk);
+ struct iwl_trans *trans = container_of(wk, typeof(*trans),
+ restart.wk.work);
struct iwl_trans_reprobe *reprobe;
enum iwl_reset_mode mode;
@@ -168,6 +177,12 @@ static void iwl_trans_restart_wk(struct work_struct *wk)
return;
mode = iwl_trans_determine_restart_mode(trans);
+ if (mode == IWL_RESET_MODE_BACKOFF) {
+ IWL_ERR(trans, "Too many device errors - delay next reset\n");
+ queue_delayed_work(system_unbound_wq, &trans->restart.wk,
+ IWL_TRANS_RESET_DELAY);
+ return;
+ }
iwl_trans_inc_restart_count(trans->dev);
@@ -227,7 +242,7 @@ struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
trans->dev = dev;
trans->num_rx_queues = 1;
- INIT_WORK(&trans->restart.wk, iwl_trans_restart_wk);
+ INIT_DELAYED_WORK(&trans->restart.wk, iwl_trans_restart_wk);
return trans;
}
@@ -271,7 +286,7 @@ int iwl_trans_init(struct iwl_trans *trans)
void iwl_trans_free(struct iwl_trans *trans)
{
- cancel_work_sync(&trans->restart.wk);
+ cancel_delayed_work_sync(&trans->restart.wk);
kmem_cache_destroy(trans->dev_cmd_pool);
}
@@ -403,7 +418,7 @@ void iwl_trans_op_mode_leave(struct iwl_trans *trans)
iwl_trans_pcie_op_mode_leave(trans);
- cancel_work_sync(&trans->restart.wk);
+ cancel_delayed_work_sync(&trans->restart.wk);
trans->op_mode = NULL;
@@ -540,7 +555,6 @@ void __releases(nic_access)
iwl_trans_release_nic_access(struct iwl_trans *trans)
{
iwl_trans_pcie_release_nic_access(trans);
- __release(nic_access);
}
IWL_EXPORT_SYMBOL(iwl_trans_release_nic_access);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 25fb4c5..ce4954b 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
/*
- * Copyright (C) 2005-2014, 2018-2023, 2025 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2023 Intel Corporation
* Copyright (C) 2013-2015 Intel Mobile Communications GmbH
* Copyright (C) 2016-2017 Intel Deutschland GmbH
*/
@@ -876,7 +876,7 @@ struct iwl_txq {
* only valid for discrete (not integrated) NICs
* @invalid_tx_cmd: invalid TX command buffer
* @reduced_cap_sku: reduced capability supported SKU
- * @bw_limit: the max bandwidth
+ * @no_160: device not supporting 160 MHz
* @step_urm: STEP is in URM, no support for MCS>9 in 320 MHz
* @restart: restart worker data
* @restart.wk: restart worker
@@ -911,8 +911,7 @@ struct iwl_trans {
char hw_id_str[52];
u32 sku_id[3];
bool reduced_cap_sku;
- u16 bw_limit;
- bool step_urm;
+ u8 no_160:1, step_urm:1;
u8 dsbr_urm_fw_dependent:1,
dsbr_urm_permanent:1;
@@ -962,7 +961,7 @@ struct iwl_trans {
struct iwl_dma_ptr invalid_tx_cmd;
struct {
- struct work_struct wk;
+ struct delayed_work wk;
struct iwl_fw_error_dump_mode mode;
bool during_reset;
} restart;
@@ -1163,7 +1162,7 @@ static inline void iwl_trans_schedule_reset(struct iwl_trans *trans,
*/
trans->restart.during_reset = test_bit(STATUS_IN_SW_RESET,
&trans->status);
- queue_work(system_unbound_wq, &trans->restart.wk);
+ queue_delayed_work(system_unbound_wq, &trans->restart.wk, 0);
}
static inline void iwl_trans_fw_error(struct iwl_trans *trans,
@@ -1262,6 +1261,9 @@ enum iwl_reset_mode {
IWL_RESET_MODE_RESCAN,
IWL_RESET_MODE_FUNC_RESET,
IWL_RESET_MODE_PROD_RESET,
+
+ /* keep last - special backoff value */
+ IWL_RESET_MODE_BACKOFF,
};
void iwl_trans_pcie_reset(struct iwl_trans *trans, enum iwl_reset_mode mode);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/agg.c b/drivers/net/wireless/intel/iwlwifi/mld/agg.c
index db9e0f04..687a945 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/agg.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/agg.c
@@ -124,9 +124,9 @@ void iwl_mld_handle_bar_frame_release_notif(struct iwl_mld *mld,
rcu_read_lock();
baid_data = rcu_dereference(mld->fw_id_to_ba[baid]);
- if (!IWL_FW_CHECK(mld, !baid_data,
- "Got valid BAID %d but not allocated, invalid BAR release!\n",
- baid))
+ if (IWL_FW_CHECK(mld, !baid_data,
+ "Got valid BAID %d but not allocated, invalid BAR release!\n",
+ baid))
goto out_unlock;
if (IWL_FW_CHECK(mld, tid != baid_data->tid ||
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/d3.c b/drivers/net/wireless/intel/iwlwifi/mld/d3.c
index 5a7207a..ee99298 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/d3.c
@@ -1099,7 +1099,8 @@ iwl_mld_set_netdetect_info(struct iwl_mld *mld,
if (!match)
return;
- netdetect_info->matches[netdetect_info->n_matches++] = match;
+ netdetect_info->matches[netdetect_info->n_matches] = match;
+ netdetect_info->n_matches++;
/* We inverted the order of the SSIDs in the scan
* request, so invert the index here.
@@ -1116,9 +1117,11 @@ iwl_mld_set_netdetect_info(struct iwl_mld *mld,
for_each_set_bit(j,
(unsigned long *)&matches[i].matching_channels[0],
- sizeof(matches[i].matching_channels))
- match->channels[match->n_channels++] =
+ sizeof(matches[i].matching_channels)) {
+ match->channels[match->n_channels] =
netdetect_cfg->channels[j]->center_freq;
+ match->n_channels++;
+ }
}
}
@@ -1895,7 +1898,6 @@ int iwl_mld_wowlan_resume(struct iwl_mld *mld)
int link_id;
int ret;
bool fw_err = false;
- bool keep_connection;
lockdep_assert_wiphy(mld->wiphy);
@@ -1965,7 +1967,7 @@ int iwl_mld_wowlan_resume(struct iwl_mld *mld)
iwl_mld_process_netdetect_res(mld, bss_vif, &resume_data);
mld->netdetect = false;
} else {
- keep_connection =
+ bool keep_connection =
iwl_mld_process_wowlan_status(mld, bss_vif,
resume_data.wowlan_status);
@@ -1973,11 +1975,10 @@ int iwl_mld_wowlan_resume(struct iwl_mld *mld)
if (keep_connection)
iwl_mld_unblock_emlsr(mld, bss_vif,
IWL_MLD_EMLSR_BLOCKED_WOWLAN);
+ else
+ ieee80211_resume_disconnect(bss_vif);
}
- if (!mld->netdetect && !keep_connection)
- ieee80211_resume_disconnect(bss_vif);
-
goto out;
err:
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
index 453ce2b..93f9f78e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
@@ -396,8 +396,8 @@ static ssize_t iwl_dbgfs_tas_get_status_read(struct iwl_mld *mld, char *buf,
.data[0] = &cmd,
};
struct iwl_dhc_tas_status_resp *resp = NULL;
+ u32 resp_len = 0;
ssize_t pos = 0;
- u32 resp_len;
u32 status;
int ret;
@@ -949,8 +949,9 @@ void iwl_mld_add_vif_debugfs(struct ieee80211_hw *hw,
snprintf(name, sizeof(name), "%pd", vif->debugfs_dir);
snprintf(target, sizeof(target), "../../../%pd3/iwlmld",
vif->debugfs_dir);
- mld_vif->dbgfs_slink =
- debugfs_create_symlink(name, mld->debugfs_dir, target);
+ if (!mld_vif->dbgfs_slink)
+ mld_vif->dbgfs_slink =
+ debugfs_create_symlink(name, mld->debugfs_dir, target);
if (iwlmld_mod_params.power_scheme != IWL_POWER_SCHEME_CAM &&
vif->type == NL80211_IFTYPE_STATION) {
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/fw.c b/drivers/net/wireless/intel/iwlwifi/mld/fw.c
index 62da137..4b083d4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/fw.c
@@ -333,19 +333,22 @@ int iwl_mld_load_fw(struct iwl_mld *mld)
ret = iwl_trans_start_hw(mld->trans);
if (ret)
- return ret;
+ goto err;
ret = iwl_mld_run_fw_init_sequence(mld);
if (ret)
- return ret;
+ goto err;
ret = iwl_mld_init_mcc(mld);
if (ret)
- return ret;
+ goto err;
mld->fw_status.running = true;
return 0;
+err:
+ iwl_mld_stop_fw(mld);
+ return ret;
}
void iwl_mld_stop_fw(struct iwl_mld *mld)
@@ -358,6 +361,10 @@ void iwl_mld_stop_fw(struct iwl_mld *mld)
iwl_trans_stop_device(mld->trans);
+ wiphy_work_cancel(mld->wiphy, &mld->async_handlers_wk);
+
+ iwl_mld_purge_async_handlers_list(mld);
+
mld->fw_status.running = false;
}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/iface.h b/drivers/net/wireless/intel/iwlwifi/mld/iface.h
index d1d56b0..ec14d07 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/iface.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/iface.h
@@ -166,7 +166,7 @@ struct iwl_mld_vif {
struct iwl_mld_emlsr emlsr;
-#if CONFIG_PM_SLEEP
+#ifdef CONFIG_PM_SLEEP
struct iwl_mld_wowlan_data wowlan_data;
#endif
#ifdef CONFIG_IWLWIFI_DEBUGFS
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
index 6851064..68d97d3 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
@@ -475,8 +475,8 @@ static
int iwl_mld_mac80211_start(struct ieee80211_hw *hw)
{
struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
- int ret;
bool in_d3 = false;
+ int ret = 0;
lockdep_assert_wiphy(mld->wiphy);
@@ -537,7 +537,8 @@ void iwl_mld_mac80211_stop(struct ieee80211_hw *hw, bool suspend)
/* if the suspend flow fails the fw is in error. Stop it here, and it
* will be started upon wakeup
*/
- if (!suspend || iwl_mld_no_wowlan_suspend(mld))
+ if (!suspend ||
+ (IS_ENABLED(CONFIG_PM_SLEEP) && iwl_mld_no_wowlan_suspend(mld)))
iwl_mld_stop_fw(mld);
/* HW is stopped, no more coming RX. OTOH, the worker can't run as the
@@ -650,6 +651,7 @@ void iwl_mld_mac80211_remove_interface(struct ieee80211_hw *hw,
#ifdef CONFIG_IWLWIFI_DEBUGFS
debugfs_remove(iwl_mld_vif_from_mac80211(vif)->dbgfs_slink);
+ iwl_mld_vif_from_mac80211(vif)->dbgfs_slink = NULL;
#endif
iwl_mld_rm_vif(mld, vif);
@@ -1943,6 +1945,7 @@ static void iwl_mld_sta_rc_update(struct ieee80211_hw *hw,
}
}
+#ifdef CONFIG_PM_SLEEP
static void iwl_mld_set_wakeup(struct ieee80211_hw *hw, bool enabled)
{
struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
@@ -1994,6 +1997,7 @@ static int iwl_mld_resume(struct ieee80211_hw *hw)
return 0;
}
+#endif
static int iwl_mld_alloc_ptk_pn(struct iwl_mld *mld,
struct iwl_mld_sta *mld_sta,
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.c b/drivers/net/wireless/intel/iwlwifi/mld/mld.c
index d4a99ae..73d2166 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mld.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.c
@@ -75,6 +75,7 @@ void iwl_construct_mld(struct iwl_mld *mld, struct iwl_trans *trans,
/* Setup async RX handling */
spin_lock_init(&mld->async_handlers_lock);
+ INIT_LIST_HEAD(&mld->async_handlers_list);
wiphy_work_init(&mld->async_handlers_wk,
iwl_mld_async_handlers_wk);
@@ -414,9 +415,14 @@ iwl_op_mode_mld_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
wiphy_unlock(mld->wiphy);
rtnl_unlock();
iwl_fw_flush_dumps(&mld->fwrt);
- goto free_hw;
+ goto err;
}
+ /* We are about to stop the FW. Notifications may require an
+ * operational FW, so handle them all here before we stop.
+ */
+ wiphy_work_flush(mld->wiphy, &mld->async_handlers_wk);
+
iwl_mld_stop_fw(mld);
wiphy_unlock(mld->wiphy);
@@ -455,7 +461,8 @@ iwl_op_mode_mld_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
iwl_mld_leds_exit(mld);
free_nvm:
kfree(mld->nvm_data);
-free_hw:
+err:
+ iwl_trans_op_mode_leave(mld->trans);
ieee80211_free_hw(mld->hw);
return ERR_PTR(ret);
}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.h b/drivers/net/wireless/intel/iwlwifi/mld/mld.h
index 5eceaaf..a4a16da 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mld.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.h
@@ -298,11 +298,6 @@ iwl_cleanup_mld(struct iwl_mld *mld)
#endif
iwl_mld_low_latency_restart_cleanup(mld);
-
- /* Empty the list of async notification handlers so we won't process
- * notifications from the dead fw after the reconfig flow.
- */
- iwl_mld_purge_async_handlers_list(mld);
}
enum iwl_power_scheme {
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 93446c3..debeea2 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
/*
- * Copyright (C) 2005-2014, 2018-2025 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2024 Intel Corporation
* Copyright (C) 2013-2015 Intel Mobile Communications GmbH
* Copyright (C) 2016-2017 Intel Deutschland GmbH
*/
@@ -552,17 +552,16 @@ MODULE_DEVICE_TABLE(pci, iwl_hw_card_ids);
EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_hw_card_ids);
#define _IWL_DEV_INFO(_device, _subdevice, _mac_type, _mac_step, _rf_type, \
- _rf_id, _rf_step, _bw_limit, _cores, _cdb, _cfg, _name) \
+ _rf_id, _rf_step, _no_160, _cores, _cdb, _cfg, _name) \
{ .device = (_device), .subdevice = (_subdevice), .cfg = &(_cfg), \
.name = _name, .mac_type = _mac_type, .rf_type = _rf_type, .rf_step = _rf_step, \
- .bw_limit = _bw_limit, .cores = _cores, .rf_id = _rf_id, \
+ .no_160 = _no_160, .cores = _cores, .rf_id = _rf_id, \
.mac_step = _mac_step, .cdb = _cdb, .jacket = IWL_CFG_ANY }
#define IWL_DEV_INFO(_device, _subdevice, _cfg, _name) \
_IWL_DEV_INFO(_device, _subdevice, IWL_CFG_ANY, IWL_CFG_ANY, \
- IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, \
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_ANY, \
- _cfg, _name)
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, \
+ IWL_CFG_ANY, _cfg, _name)
VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
#if IS_ENABLED(CONFIG_IWLMVM)
@@ -725,66 +724,66 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_2ac_cfg_soc, iwl9461_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_2ac_cfg_soc, iwl9461_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_2ac_cfg_soc, iwl9462_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_2ac_cfg_soc, iwl9462_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_2ac_cfg_soc, iwl9560_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_2ac_cfg_soc, iwl9560_name),
_IWL_DEV_INFO(0x2526, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_TH, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT_GNSS, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT_GNSS, IWL_CFG_NO_CDB,
iwl9260_2ac_cfg, iwl9270_160_name),
_IWL_DEV_INFO(0x2526, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_TH, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT_GNSS, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT_GNSS, IWL_CFG_NO_CDB,
iwl9260_2ac_cfg, iwl9270_name),
_IWL_DEV_INFO(0x271B, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_TH1, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9260_2ac_cfg, iwl9162_160_name),
_IWL_DEV_INFO(0x271B, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_TH1, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9260_2ac_cfg, iwl9162_name),
_IWL_DEV_INFO(0x2526, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_TH, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9260_2ac_cfg, iwl9260_160_name),
_IWL_DEV_INFO(0x2526, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_TH, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9260_2ac_cfg, iwl9260_name),
/* Qu with Jf */
@@ -792,132 +791,132 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_b0_jf_b0_cfg, iwl9461_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_b0_jf_b0_cfg, iwl9461_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_b0_jf_b0_cfg, iwl9462_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_b0_jf_b0_cfg, iwl9462_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_b0_jf_b0_cfg, iwl9560_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_b0_jf_b0_cfg, iwl9560_name),
_IWL_DEV_INFO(IWL_CFG_ANY, 0x1551,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_b0_jf_b0_cfg, iwl9560_killer_1550s_name),
_IWL_DEV_INFO(IWL_CFG_ANY, 0x1552,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_b0_jf_b0_cfg, iwl9560_killer_1550i_name),
/* Qu C step */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_c0_jf_b0_cfg, iwl9461_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_c0_jf_b0_cfg, iwl9461_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_c0_jf_b0_cfg, iwl9462_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_c0_jf_b0_cfg, iwl9462_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_c0_jf_b0_cfg, iwl9560_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_c0_jf_b0_cfg, iwl9560_name),
_IWL_DEV_INFO(IWL_CFG_ANY, 0x1551,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_c0_jf_b0_cfg, iwl9560_killer_1550s_name),
_IWL_DEV_INFO(IWL_CFG_ANY, 0x1552,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_c0_jf_b0_cfg, iwl9560_killer_1550i_name),
/* QuZ */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_quz_a0_jf_b0_cfg, iwl9461_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_quz_a0_jf_b0_cfg, iwl9461_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_quz_a0_jf_b0_cfg, iwl9462_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_quz_a0_jf_b0_cfg, iwl9462_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_quz_a0_jf_b0_cfg, iwl9560_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_quz_a0_jf_b0_cfg, iwl9560_name),
_IWL_DEV_INFO(IWL_CFG_ANY, 0x1551,
IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_quz_a0_jf_b0_cfg, iwl9560_killer_1550s_name),
_IWL_DEV_INFO(IWL_CFG_ANY, 0x1552,
IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_quz_a0_jf_b0_cfg, iwl9560_killer_1550i_name),
/* Qu with Hr */
@@ -925,189 +924,189 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_qu_b0_hr1_b0, iwl_ax101_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_qu_b0_hr_b0, iwl_ax203_name),
/* Qu C step */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_qu_c0_hr1_b0, iwl_ax101_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_qu_c0_hr_b0, iwl_ax203_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_qu_c0_hr_b0, iwl_ax201_name),
/* QuZ */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_quz_a0_hr1_b0, iwl_ax101_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QUZ, SILICON_B_STEP,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_quz_a0_hr_b0, iwl_ax203_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QUZ, SILICON_B_STEP,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_quz_a0_hr_b0, iwl_ax201_name),
/* Ma */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_MA, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_ma, iwl_ax201_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_MA, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_ma, iwl_ax211_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_MA, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_ma, iwl_ax231_name),
/* So with Hr */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_so_a0_hr_a0, iwl_ax203_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_so_a0_hr_a0, iwl_ax101_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_so_a0_hr_a0, iwl_ax201_name),
/* So-F with Hr */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_so_a0_hr_a0, iwl_ax203_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_so_a0_hr_a0, iwl_ax101_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_so_a0_hr_a0, iwl_ax201_name),
/* So-F with Gf */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_CDB,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_CDB,
iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_name),
/* SoF with JF2 */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9560_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9560_name),
/* SoF with JF */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9461_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9462_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9461_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9462_name),
/* So with GF */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_CDB,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_CDB,
iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_name),
/* So with JF2 */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9560_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9560_name),
/* So with JF */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9461_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9462_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9461_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9462_name),
#endif /* CONFIG_IWLMVM */
@@ -1116,13 +1115,13 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_bz, iwl_ax201_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_bz, iwl_ax211_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
@@ -1134,119 +1133,104 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_bz, iwl_wh_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_bz, iwl_ax201_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_bz, iwl_ax211_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_bz, iwl_fm_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_bz, iwl_wh_name),
/* Ga (Gl) */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_GL, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_320, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_gl, iwl_gl_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_GL, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
- 160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_320, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_gl, iwl_mtp_name),
/* Sc */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_sc, iwl_ax211_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_sc, iwl_fm_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_sc, iwl_wh_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
- IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
- 160, IWL_CFG_ANY, IWL_CFG_ANY,
- iwl_cfg_sc, iwl_sp_name),
- _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_sc2, iwl_ax211_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_sc2, iwl_fm_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_sc2, iwl_wh_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
- IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
- 160, IWL_CFG_ANY, IWL_CFG_ANY,
- iwl_cfg_sc2, iwl_sp_name),
- _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_sc2f, iwl_ax211_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_sc2f, iwl_fm_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_sc2f, iwl_wh_name),
- _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
- IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
- 160, IWL_CFG_ANY, IWL_CFG_ANY,
- iwl_cfg_sc2f, iwl_sp_name),
/* Dr */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_DR, IWL_CFG_ANY,
IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_dr, iwl_dr_name),
/* Br */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_BR, IWL_CFG_ANY,
IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_br, iwl_br_name),
#endif /* CONFIG_IWLMLD */
};
@@ -1398,7 +1382,7 @@ static int map_crf_id(struct iwl_trans *iwl_trans)
VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info *
iwl_pci_find_dev_info(u16 device, u16 subsystem_device,
u16 mac_type, u8 mac_step, u16 rf_type, u8 cdb,
- u8 jacket, u8 rf_id, u8 bw_limit, u8 cores, u8 rf_step)
+ u8 jacket, u8 rf_id, u8 no_160, u8 cores, u8 rf_step)
{
int num_devices = ARRAY_SIZE(iwl_dev_info_table);
int i;
@@ -1441,15 +1425,8 @@ iwl_pci_find_dev_info(u16 device, u16 subsystem_device,
dev_info->rf_id != rf_id)
continue;
- /*
- * Check that bw_limit have the same "boolean" value since
- * IWL_SUBDEVICE_BW_LIM can only return a boolean value and
- * dev_info->bw_limit encodes a non-boolean value.
- * dev_info->bw_limit == IWL_CFG_BW_NO_LIM must be equal to
- * !bw_limit to have a match.
- */
- if (dev_info->bw_limit != IWL_CFG_BW_ANY &&
- (dev_info->bw_limit == IWL_CFG_BW_NO_LIM) == !!bw_limit)
+ if (dev_info->no_160 != (u8)IWL_CFG_ANY &&
+ dev_info->no_160 != no_160)
continue;
if (dev_info->cores != (u8)IWL_CFG_ANY &&
@@ -1587,13 +1564,13 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
CSR_HW_RFID_IS_CDB(iwl_trans->hw_rf_id),
CSR_HW_RFID_IS_JACKET(iwl_trans->hw_rf_id),
IWL_SUBDEVICE_RF_ID(pdev->subsystem_device),
- IWL_SUBDEVICE_BW_LIM(pdev->subsystem_device),
+ IWL_SUBDEVICE_NO_160(pdev->subsystem_device),
IWL_SUBDEVICE_CORES(pdev->subsystem_device),
CSR_HW_RFID_STEP(iwl_trans->hw_rf_id));
if (dev_info) {
iwl_trans->cfg = dev_info->cfg;
iwl_trans->name = dev_info->name;
- iwl_trans->bw_limit = dev_info->bw_limit;
+ iwl_trans->no_160 = dev_info->no_160 == IWL_CFG_NO_160;
}
#if IS_ENABLED(CONFIG_IWLMVM)
@@ -1759,11 +1736,27 @@ static int _iwl_pci_resume(struct device *device, bool restore)
* Scratch value was altered, this means the device was powered off, we
* need to reset it completely.
* Note: MAC (bits 0:7) will be cleared upon suspend even with wowlan,
- * so assume that any bits there mean that the device is usable.
+ * but not bits [15:8]. So if we have bits set in lower word, assume
+ * the device is alive.
+ * For older devices, just try silently to grab the NIC.
*/
- if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ &&
- !iwl_read32(trans, CSR_FUNC_SCRATCH))
- device_was_powered_off = true;
+ if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
+ if (!(iwl_read32(trans, CSR_FUNC_SCRATCH) &
+ CSR_FUNC_SCRATCH_POWER_OFF_MASK))
+ device_was_powered_off = true;
+ } else {
+ /*
+ * bh are re-enabled by iwl_trans_pcie_release_nic_access,
+ * so re-enable them if _iwl_trans_pcie_grab_nic_access fails.
+ */
+ local_bh_disable();
+ if (_iwl_trans_pcie_grab_nic_access(trans, true)) {
+ iwl_trans_pcie_release_nic_access(trans);
+ } else {
+ device_was_powered_off = true;
+ local_bh_enable();
+ }
+ }
if (restore || device_was_powered_off) {
trans->state = IWL_TRANS_NO_FW;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 45460f9..114a919 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -558,10 +558,10 @@ void iwl_trans_pcie_free(struct iwl_trans *trans);
void iwl_trans_pcie_free_pnvm_dram_regions(struct iwl_dram_regions *dram_regions,
struct device *dev);
-bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans);
-#define _iwl_trans_pcie_grab_nic_access(trans) \
+bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans, bool silent);
+#define _iwl_trans_pcie_grab_nic_access(trans, silent) \
__cond_lock(nic_access_nobh, \
- likely(__iwl_trans_pcie_grab_nic_access(trans)))
+ likely(__iwl_trans_pcie_grab_nic_access(trans, silent)))
void iwl_trans_pcie_check_product_reset_status(struct pci_dev *pdev);
void iwl_trans_pcie_check_product_reset_mode(struct pci_dev *pdev);
@@ -1105,7 +1105,8 @@ void iwl_trans_pcie_set_bits_mask(struct iwl_trans *trans, u32 reg,
int iwl_trans_pcie_read_config32(struct iwl_trans *trans, u32 ofs,
u32 *val);
bool iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans);
-void iwl_trans_pcie_release_nic_access(struct iwl_trans *trans);
+void __releases(nic_access_nobh)
+iwl_trans_pcie_release_nic_access(struct iwl_trans *trans);
/* transport gen 1 exported functions */
void iwl_trans_pcie_fw_alive(struct iwl_trans *trans, u32 scd_addr);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
index 3ece34e..472f26f 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
@@ -147,8 +147,14 @@ static void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans)
return;
if (trans->state >= IWL_TRANS_FW_STARTED &&
- trans_pcie->fw_reset_handshake)
+ trans_pcie->fw_reset_handshake) {
+ /*
+ * Reset handshake can dump firmware on timeout, but that
+ * should assume that the firmware is already dead.
+ */
+ trans->state = IWL_TRANS_NO_FW;
iwl_trans_pcie_fw_reset_handshake(trans);
+ }
trans_pcie->is_down = true;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index c917ed4..102a612 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -2351,7 +2351,8 @@ void iwl_trans_pcie_reset(struct iwl_trans *trans, enum iwl_reset_mode mode)
struct iwl_trans_pcie_removal *removal;
char _msg = 0, *msg = &_msg;
- if (WARN_ON(mode < IWL_RESET_MODE_REMOVE_ONLY))
+ if (WARN_ON(mode < IWL_RESET_MODE_REMOVE_ONLY ||
+ mode == IWL_RESET_MODE_BACKOFF))
return;
if (test_bit(STATUS_TRANS_DEAD, &trans->status))
@@ -2405,7 +2406,7 @@ EXPORT_SYMBOL(iwl_trans_pcie_reset);
* This version doesn't disable BHs but rather assumes they're
* already disabled.
*/
-bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
+bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans, bool silent)
{
int ret;
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -2457,6 +2458,11 @@ bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
if (unlikely(ret < 0)) {
u32 cntrl = iwl_read32(trans, CSR_GP_CNTRL);
+ if (silent) {
+ spin_unlock(&trans_pcie->reg_lock);
+ return false;
+ }
+
WARN_ONCE(1,
"Timeout waiting for hardware access (CSR_GP_CNTRL 0x%08x)\n",
cntrl);
@@ -2488,7 +2494,7 @@ bool iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
bool ret;
local_bh_disable();
- ret = __iwl_trans_pcie_grab_nic_access(trans);
+ ret = __iwl_trans_pcie_grab_nic_access(trans, false);
if (ret) {
/* keep BHs disabled until iwl_trans_pcie_release_nic_access */
return ret;
@@ -2497,7 +2503,8 @@ bool iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
return false;
}
-void iwl_trans_pcie_release_nic_access(struct iwl_trans *trans)
+void __releases(nic_access_nobh)
+iwl_trans_pcie_release_nic_access(struct iwl_trans *trans)
{
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -2524,6 +2531,7 @@ void iwl_trans_pcie_release_nic_access(struct iwl_trans *trans)
* scheduled on different CPUs (after we drop reg_lock).
*/
out:
+ __release(nic_access_nobh);
spin_unlock_bh(&trans_pcie->reg_lock);
}
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index bb90bcf..9fc4e98 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -1021,7 +1021,7 @@ static int iwl_pcie_set_cmd_in_flight(struct iwl_trans *trans,
* returned. This needs to be done only on NICs that have
* apmg_wake_up_wa set (see above.)
*/
- if (!_iwl_trans_pcie_grab_nic_access(trans))
+ if (!_iwl_trans_pcie_grab_nic_access(trans, false))
return -EIO;
/*
diff --git a/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c b/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c
index 7ef5e89..d0bda23 100644
--- a/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c
+++ b/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c
@@ -2,7 +2,7 @@
/*
* KUnit tests for the iwlwifi device info table
*
- * Copyright (C) 2023-2025 Intel Corporation
+ * Copyright (C) 2023-2024 Intel Corporation
*/
#include <kunit/test.h>
#include <linux/pci.h>
@@ -13,9 +13,9 @@ MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING");
static void iwl_pci_print_dev_info(const char *pfx, const struct iwl_dev_info *di)
{
- printk(KERN_DEBUG "%sdev=%.4x,subdev=%.4x,mac_type=%.4x,mac_step=%.4x,rf_type=%.4x,cdb=%d,jacket=%d,rf_id=%.2x,bw_limit=%d,cores=%.2x\n",
+ printk(KERN_DEBUG "%sdev=%.4x,subdev=%.4x,mac_type=%.4x,mac_step=%.4x,rf_type=%.4x,cdb=%d,jacket=%d,rf_id=%.2x,no_160=%d,cores=%.2x\n",
pfx, di->device, di->subdevice, di->mac_type, di->mac_step,
- di->rf_type, di->cdb, di->jacket, di->rf_id, di->bw_limit,
+ di->rf_type, di->cdb, di->jacket, di->rf_id, di->no_160,
di->cores);
}
@@ -31,13 +31,8 @@ static void devinfo_table_order(struct kunit *test)
di->mac_type, di->mac_step,
di->rf_type, di->cdb,
di->jacket, di->rf_id,
- di->bw_limit != IWL_CFG_BW_NO_LIM,
- di->cores, di->rf_step);
- if (!ret) {
- iwl_pci_print_dev_info("No entry found for: ", di);
- KUNIT_FAIL(test,
- "No entry found for entry at index %d\n", idx);
- } else if (ret != di) {
+ di->no_160, di->cores, di->rf_step);
+ if (ret != di) {
iwl_pci_print_dev_info("searched: ", di);
iwl_pci_print_dev_info("found: ", ret);
KUNIT_FAIL(test,
diff --git a/drivers/net/wireless/purelifi/plfxlc/mac.c b/drivers/net/wireless/purelifi/plfxlc/mac.c
index eae93ef..82d1bf7 100644
--- a/drivers/net/wireless/purelifi/plfxlc/mac.c
+++ b/drivers/net/wireless/purelifi/plfxlc/mac.c
@@ -102,7 +102,6 @@ int plfxlc_mac_init_hw(struct ieee80211_hw *hw)
void plfxlc_mac_release(struct plfxlc_mac *mac)
{
plfxlc_chip_release(&mac->chip);
- lockdep_assert_held(&mac->lock);
}
int plfxlc_op_start(struct ieee80211_hw *hw)
diff --git a/drivers/net/wireless/ti/wl1251/tx.c b/drivers/net/wireless/ti/wl1251/tx.c
index 474b603..adb4840 100644
--- a/drivers/net/wireless/ti/wl1251/tx.c
+++ b/drivers/net/wireless/ti/wl1251/tx.c
@@ -342,8 +342,10 @@ void wl1251_tx_work(struct work_struct *work)
while ((skb = skb_dequeue(&wl->tx_queue))) {
if (!woken_up) {
ret = wl1251_ps_elp_wakeup(wl);
- if (ret < 0)
+ if (ret < 0) {
+ skb_queue_head(&wl->tx_queue, skb);
goto out;
+ }
woken_up = true;
}
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index fc52d5c..5091e1f 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -985,20 +985,27 @@ static u32 xennet_run_xdp(struct netfront_queue *queue, struct page *pdata,
act = bpf_prog_run_xdp(prog, xdp);
switch (act) {
case XDP_TX:
- get_page(pdata);
xdpf = xdp_convert_buff_to_frame(xdp);
- err = xennet_xdp_xmit(queue->info->netdev, 1, &xdpf, 0);
- if (unlikely(!err))
- xdp_return_frame_rx_napi(xdpf);
- else if (unlikely(err < 0))
+ if (unlikely(!xdpf)) {
trace_xdp_exception(queue->info->netdev, prog, act);
+ break;
+ }
+ get_page(pdata);
+ err = xennet_xdp_xmit(queue->info->netdev, 1, &xdpf, 0);
+ if (unlikely(err <= 0)) {
+ if (err < 0)
+ trace_xdp_exception(queue->info->netdev, prog, act);
+ xdp_return_frame_rx_napi(xdpf);
+ }
break;
case XDP_REDIRECT:
get_page(pdata);
err = xdp_do_redirect(queue->info->netdev, xdp, prog);
*need_xdp_flush = true;
- if (unlikely(err))
+ if (unlikely(err)) {
trace_xdp_exception(queue->info->netdev, prog, act);
+ xdp_return_buff(xdp);
+ }
break;
case XDP_PASS:
case XDP_DROP:
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index cc23035..eb6ea8a 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4295,6 +4295,15 @@ static void nvme_scan_work(struct work_struct *work)
nvme_scan_ns_sequential(ctrl);
}
mutex_unlock(&ctrl->scan_lock);
+
+ /* Requeue if we have missed AENs */
+ if (test_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events))
+ nvme_queue_scan(ctrl);
+#ifdef CONFIG_NVME_MULTIPATH
+ else if (ctrl->ana_log_buf)
+ /* Re-read the ANA log page to not miss updates */
+ queue_work(nvme_wq, &ctrl->ana_work);
+#endif
}
/*
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 89be591..250f3da 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -427,7 +427,7 @@ static bool nvme_available_path(struct nvme_ns_head *head)
struct nvme_ns *ns;
if (!test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags))
- return NULL;
+ return false;
list_for_each_entry_srcu(ns, &head->list, siblings,
srcu_read_lock_held(&head->srcu)) {
@@ -1051,6 +1051,13 @@ void nvme_mpath_add_sysfs_link(struct nvme_ns_head *head)
list_for_each_entry_rcu(ns, &head->list, siblings) {
/*
+ * Ensure that ns path disk node is already added otherwise we
+ * may get invalid kobj name for target
+ */
+ if (!test_bit(GD_ADDED, &ns->disk->state))
+ continue;
+
+ /*
* Avoid creating link if it already exists for the given path.
* When path ana state transitions from optimized to non-
* optimized or vice-versa, the nvme_mpath_set_live() is
@@ -1065,13 +1072,6 @@ void nvme_mpath_add_sysfs_link(struct nvme_ns_head *head)
if (test_and_set_bit(NVME_NS_SYSFS_ATTR_LINK, &ns->flags))
continue;
- /*
- * Ensure that ns path disk node is already added otherwise we
- * may get invalid kobj name for target
- */
- if (!test_bit(GD_ADDED, &ns->disk->state))
- continue;
-
target = disk_to_dev(ns->disk);
/*
* Create sysfs link from head gendisk kobject @kobj to the
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 26c459f..72d2602 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1803,6 +1803,8 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid,
ret = PTR_ERR(sock_file);
goto err_destroy_mutex;
}
+
+ sk_net_refcnt_upgrade(queue->sock->sk);
nvme_tcp_reclassify_socket(queue->sock);
/* Single syn retry */
diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c
index 0b0645a..cef8d77 100644
--- a/drivers/nvme/target/auth.c
+++ b/drivers/nvme/target/auth.c
@@ -240,7 +240,7 @@ void nvmet_auth_sq_free(struct nvmet_sq *sq)
{
cancel_delayed_work(&sq->auth_expired_work);
#ifdef CONFIG_NVME_TARGET_TCP_TLS
- sq->tls_key = 0;
+ sq->tls_key = NULL;
#endif
kfree(sq->dhchap_c1);
sq->dhchap_c1 = NULL;
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 71f8d06..245475c 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -324,6 +324,9 @@ int nvmet_enable_port(struct nvmet_port *port)
lockdep_assert_held(&nvmet_config_sem);
+ if (port->disc_addr.trtype == NVMF_TRTYPE_MAX)
+ return -EINVAL;
+
ops = nvmet_transports[port->disc_addr.trtype];
if (!ops) {
up_write(&nvmet_config_sem);
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 7318b73..7b50130 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -995,16 +995,6 @@ nvmet_fc_hostport_get(struct nvmet_fc_hostport *hostport)
return kref_get_unless_zero(&hostport->ref);
}
-static void
-nvmet_fc_free_hostport(struct nvmet_fc_hostport *hostport)
-{
- /* if LLDD not implemented, leave as NULL */
- if (!hostport || !hostport->hosthandle)
- return;
-
- nvmet_fc_hostport_put(hostport);
-}
-
static struct nvmet_fc_hostport *
nvmet_fc_match_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
{
@@ -1028,33 +1018,24 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
struct nvmet_fc_hostport *newhost, *match = NULL;
unsigned long flags;
+ /*
+ * Caller holds a reference on tgtport.
+ */
+
/* if LLDD not implemented, leave as NULL */
if (!hosthandle)
return NULL;
- /*
- * take reference for what will be the newly allocated hostport if
- * we end up using a new allocation
- */
- if (!nvmet_fc_tgtport_get(tgtport))
- return ERR_PTR(-EINVAL);
-
spin_lock_irqsave(&tgtport->lock, flags);
match = nvmet_fc_match_hostport(tgtport, hosthandle);
spin_unlock_irqrestore(&tgtport->lock, flags);
- if (match) {
- /* no new allocation - release reference */
- nvmet_fc_tgtport_put(tgtport);
+ if (match)
return match;
- }
newhost = kzalloc(sizeof(*newhost), GFP_KERNEL);
- if (!newhost) {
- /* no new allocation - release reference */
- nvmet_fc_tgtport_put(tgtport);
+ if (!newhost)
return ERR_PTR(-ENOMEM);
- }
spin_lock_irqsave(&tgtport->lock, flags);
match = nvmet_fc_match_hostport(tgtport, hosthandle);
@@ -1063,6 +1044,7 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
kfree(newhost);
newhost = match;
} else {
+ nvmet_fc_tgtport_get(tgtport);
newhost->tgtport = tgtport;
newhost->hosthandle = hosthandle;
INIT_LIST_HEAD(&newhost->host_list);
@@ -1076,20 +1058,14 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
}
static void
-nvmet_fc_delete_assoc(struct nvmet_fc_tgt_assoc *assoc)
-{
- nvmet_fc_delete_target_assoc(assoc);
- nvmet_fc_tgt_a_put(assoc);
-}
-
-static void
nvmet_fc_delete_assoc_work(struct work_struct *work)
{
struct nvmet_fc_tgt_assoc *assoc =
container_of(work, struct nvmet_fc_tgt_assoc, del_work);
struct nvmet_fc_tgtport *tgtport = assoc->tgtport;
- nvmet_fc_delete_assoc(assoc);
+ nvmet_fc_delete_target_assoc(assoc);
+ nvmet_fc_tgt_a_put(assoc);
nvmet_fc_tgtport_put(tgtport);
}
@@ -1097,7 +1073,8 @@ static void
nvmet_fc_schedule_delete_assoc(struct nvmet_fc_tgt_assoc *assoc)
{
nvmet_fc_tgtport_get(assoc->tgtport);
- queue_work(nvmet_wq, &assoc->del_work);
+ if (!queue_work(nvmet_wq, &assoc->del_work))
+ nvmet_fc_tgtport_put(assoc->tgtport);
}
static bool
@@ -1143,6 +1120,7 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
goto out_ida;
assoc->tgtport = tgtport;
+ nvmet_fc_tgtport_get(tgtport);
assoc->a_id = idx;
INIT_LIST_HEAD(&assoc->a_list);
kref_init(&assoc->ref);
@@ -1190,7 +1168,7 @@ nvmet_fc_target_assoc_free(struct kref *ref)
/* Send Disconnect now that all i/o has completed */
nvmet_fc_xmt_disconnect_assoc(assoc);
- nvmet_fc_free_hostport(assoc->hostport);
+ nvmet_fc_hostport_put(assoc->hostport);
spin_lock_irqsave(&tgtport->lock, flags);
oldls = assoc->rcv_disconn;
spin_unlock_irqrestore(&tgtport->lock, flags);
@@ -1244,6 +1222,8 @@ nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc)
dev_info(tgtport->dev,
"{%d:%d} Association deleted\n",
tgtport->fc_target_port.port_num, assoc->a_id);
+
+ nvmet_fc_tgtport_put(tgtport);
}
static struct nvmet_fc_tgt_assoc *
@@ -1455,11 +1435,6 @@ nvmet_fc_free_tgtport(struct kref *ref)
struct nvmet_fc_tgtport *tgtport =
container_of(ref, struct nvmet_fc_tgtport, ref);
struct device *dev = tgtport->dev;
- unsigned long flags;
-
- spin_lock_irqsave(&nvmet_fc_tgtlock, flags);
- list_del(&tgtport->tgt_list);
- spin_unlock_irqrestore(&nvmet_fc_tgtlock, flags);
nvmet_fc_free_ls_iodlist(tgtport);
@@ -1620,6 +1595,11 @@ int
nvmet_fc_unregister_targetport(struct nvmet_fc_target_port *target_port)
{
struct nvmet_fc_tgtport *tgtport = targetport_to_tgtport(target_port);
+ unsigned long flags;
+
+ spin_lock_irqsave(&nvmet_fc_tgtlock, flags);
+ list_del(&tgtport->tgt_list);
+ spin_unlock_irqrestore(&nvmet_fc_tgtlock, flags);
nvmet_fc_portentry_unbind_tgt(tgtport);
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index e1abb27..641201e 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -208,6 +208,7 @@ struct fcloop_lport {
struct nvme_fc_local_port *localport;
struct list_head lport_list;
struct completion unreg_done;
+ refcount_t ref;
};
struct fcloop_lport_priv {
@@ -239,7 +240,7 @@ struct fcloop_nport {
struct fcloop_tport *tport;
struct fcloop_lport *lport;
struct list_head nport_list;
- struct kref ref;
+ refcount_t ref;
u64 node_name;
u64 port_name;
u32 port_role;
@@ -274,7 +275,7 @@ struct fcloop_fcpreq {
u32 inistate;
bool active;
bool aborted;
- struct kref ref;
+ refcount_t ref;
struct work_struct fcp_rcv_work;
struct work_struct abort_rcv_work;
struct work_struct tio_done_work;
@@ -478,7 +479,7 @@ fcloop_t2h_xmt_ls_rsp(struct nvme_fc_local_port *localport,
if (targetport) {
tport = targetport->private;
spin_lock(&tport->lock);
- list_add_tail(&tport->ls_list, &tls_req->ls_list);
+ list_add_tail(&tls_req->ls_list, &tport->ls_list);
spin_unlock(&tport->lock);
queue_work(nvmet_wq, &tport->ls_work);
}
@@ -534,24 +535,18 @@ fcloop_tgt_discovery_evt(struct nvmet_fc_target_port *tgtport)
}
static void
-fcloop_tfcp_req_free(struct kref *ref)
-{
- struct fcloop_fcpreq *tfcp_req =
- container_of(ref, struct fcloop_fcpreq, ref);
-
- kfree(tfcp_req);
-}
-
-static void
fcloop_tfcp_req_put(struct fcloop_fcpreq *tfcp_req)
{
- kref_put(&tfcp_req->ref, fcloop_tfcp_req_free);
+ if (!refcount_dec_and_test(&tfcp_req->ref))
+ return;
+
+ kfree(tfcp_req);
}
static int
fcloop_tfcp_req_get(struct fcloop_fcpreq *tfcp_req)
{
- return kref_get_unless_zero(&tfcp_req->ref);
+ return refcount_inc_not_zero(&tfcp_req->ref);
}
static void
@@ -748,7 +743,7 @@ fcloop_fcp_req(struct nvme_fc_local_port *localport,
INIT_WORK(&tfcp_req->fcp_rcv_work, fcloop_fcp_recv_work);
INIT_WORK(&tfcp_req->abort_rcv_work, fcloop_fcp_abort_recv_work);
INIT_WORK(&tfcp_req->tio_done_work, fcloop_tgt_fcprqst_done_work);
- kref_init(&tfcp_req->ref);
+ refcount_set(&tfcp_req->ref, 1);
queue_work(nvmet_wq, &tfcp_req->fcp_rcv_work);
@@ -1001,24 +996,39 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport,
}
static void
-fcloop_nport_free(struct kref *ref)
+fcloop_lport_put(struct fcloop_lport *lport)
{
- struct fcloop_nport *nport =
- container_of(ref, struct fcloop_nport, ref);
+ unsigned long flags;
- kfree(nport);
+ if (!refcount_dec_and_test(&lport->ref))
+ return;
+
+ spin_lock_irqsave(&fcloop_lock, flags);
+ list_del(&lport->lport_list);
+ spin_unlock_irqrestore(&fcloop_lock, flags);
+
+ kfree(lport);
+}
+
+static int
+fcloop_lport_get(struct fcloop_lport *lport)
+{
+ return refcount_inc_not_zero(&lport->ref);
}
static void
fcloop_nport_put(struct fcloop_nport *nport)
{
- kref_put(&nport->ref, fcloop_nport_free);
+ if (!refcount_dec_and_test(&nport->ref))
+ return;
+
+ kfree(nport);
}
static int
fcloop_nport_get(struct fcloop_nport *nport)
{
- return kref_get_unless_zero(&nport->ref);
+ return refcount_inc_not_zero(&nport->ref);
}
static void
@@ -1029,6 +1039,8 @@ fcloop_localport_delete(struct nvme_fc_local_port *localport)
/* release any threads waiting for the unreg to complete */
complete(&lport->unreg_done);
+
+ fcloop_lport_put(lport);
}
static void
@@ -1140,6 +1152,7 @@ fcloop_create_local_port(struct device *dev, struct device_attribute *attr,
lport->localport = localport;
INIT_LIST_HEAD(&lport->lport_list);
+ refcount_set(&lport->ref, 1);
spin_lock_irqsave(&fcloop_lock, flags);
list_add_tail(&lport->lport_list, &fcloop_lports);
@@ -1156,13 +1169,6 @@ fcloop_create_local_port(struct device *dev, struct device_attribute *attr,
return ret ? ret : count;
}
-
-static void
-__unlink_local_port(struct fcloop_lport *lport)
-{
- list_del(&lport->lport_list);
-}
-
static int
__wait_localport_unreg(struct fcloop_lport *lport)
{
@@ -1175,8 +1181,6 @@ __wait_localport_unreg(struct fcloop_lport *lport)
if (!ret)
wait_for_completion(&lport->unreg_done);
- kfree(lport);
-
return ret;
}
@@ -1199,8 +1203,9 @@ fcloop_delete_local_port(struct device *dev, struct device_attribute *attr,
list_for_each_entry(tlport, &fcloop_lports, lport_list) {
if (tlport->localport->node_name == nodename &&
tlport->localport->port_name == portname) {
+ if (!fcloop_lport_get(tlport))
+ break;
lport = tlport;
- __unlink_local_port(lport);
break;
}
}
@@ -1210,6 +1215,7 @@ fcloop_delete_local_port(struct device *dev, struct device_attribute *attr,
return -ENOENT;
ret = __wait_localport_unreg(lport);
+ fcloop_lport_put(lport);
return ret ? ret : count;
}
@@ -1249,7 +1255,7 @@ fcloop_alloc_nport(const char *buf, size_t count, bool remoteport)
newnport->port_role = opts->roles;
if (opts->mask & NVMF_OPT_FCADDR)
newnport->port_id = opts->fcaddr;
- kref_init(&newnport->ref);
+ refcount_set(&newnport->ref, 1);
spin_lock_irqsave(&fcloop_lock, flags);
@@ -1637,17 +1643,17 @@ static void __exit fcloop_exit(void)
for (;;) {
lport = list_first_entry_or_null(&fcloop_lports,
typeof(*lport), lport_list);
- if (!lport)
+ if (!lport || !fcloop_lport_get(lport))
break;
- __unlink_local_port(lport);
-
spin_unlock_irqrestore(&fcloop_lock, flags);
ret = __wait_localport_unreg(lport);
if (ret)
pr_warn("%s: Failed deleting local port\n", __func__);
+ fcloop_lport_put(lport);
+
spin_lock_irqsave(&fcloop_lock, flags);
}
diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c
index 51c27b3..7fab7f3 100644
--- a/drivers/nvme/target/pci-epf.c
+++ b/drivers/nvme/target/pci-epf.c
@@ -1648,16 +1648,17 @@ static int nvmet_pci_epf_process_sq(struct nvmet_pci_epf_ctrl *ctrl,
{
struct nvmet_pci_epf_iod *iod;
int ret, n = 0;
+ u16 head = sq->head;
sq->tail = nvmet_pci_epf_bar_read32(ctrl, sq->db);
- while (sq->head != sq->tail && (!ctrl->sq_ab || n < ctrl->sq_ab)) {
+ while (head != sq->tail && (!ctrl->sq_ab || n < ctrl->sq_ab)) {
iod = nvmet_pci_epf_alloc_iod(sq);
if (!iod)
break;
/* Get the NVMe command submitted by the host. */
ret = nvmet_pci_epf_transfer(ctrl, &iod->cmd,
- sq->pci_addr + sq->head * sq->qes,
+ sq->pci_addr + head * sq->qes,
sq->qes, DMA_FROM_DEVICE);
if (ret) {
/* Not much we can do... */
@@ -1666,12 +1667,13 @@ static int nvmet_pci_epf_process_sq(struct nvmet_pci_epf_ctrl *ctrl,
}
dev_dbg(ctrl->dev, "SQ[%u]: head %u, tail %u, command %s\n",
- sq->qid, sq->head, sq->tail,
+ sq->qid, head, sq->tail,
nvmet_pci_epf_iod_name(iod));
- sq->head++;
- if (sq->head == sq->depth)
- sq->head = 0;
+ head++;
+ if (head == sq->depth)
+ head = 0;
+ WRITE_ONCE(sq->head, head);
n++;
queue_work_on(WORK_CPU_UNBOUND, sq->iod_wq, &iod->work);
@@ -1761,8 +1763,17 @@ static void nvmet_pci_epf_cq_work(struct work_struct *work)
if (!iod)
break;
- /* Post the IOD completion entry. */
+ /*
+ * Post the IOD completion entry. If the IOD request was
+ * executed (req->execute() called), the CQE is already
+ * initialized. However, the IOD may have been failed before
+ * that, leaving the CQE not properly initialized. So always
+ * initialize it here.
+ */
cqe = &iod->cqe;
+ cqe->sq_head = cpu_to_le16(READ_ONCE(iod->sq->head));
+ cqe->sq_id = cpu_to_le16(iod->sq->qid);
+ cqe->command_id = iod->cmd.common.command_id;
cqe->status = cpu_to_le16((iod->status << 1) | cq->phase);
dev_dbg(ctrl->dev,
@@ -1800,6 +1811,21 @@ static void nvmet_pci_epf_cq_work(struct work_struct *work)
NVMET_PCI_EPF_CQ_RETRY_INTERVAL);
}
+static void nvmet_pci_epf_clear_ctrl_config(struct nvmet_pci_epf_ctrl *ctrl)
+{
+ struct nvmet_ctrl *tctrl = ctrl->tctrl;
+
+ /* Initialize controller status. */
+ tctrl->csts = 0;
+ ctrl->csts = 0;
+ nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CSTS, ctrl->csts);
+
+ /* Initialize controller configuration and start polling. */
+ tctrl->cc = 0;
+ ctrl->cc = 0;
+ nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CC, ctrl->cc);
+}
+
static int nvmet_pci_epf_enable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
{
u64 pci_addr, asq, acq;
@@ -1865,18 +1891,20 @@ static int nvmet_pci_epf_enable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
return 0;
err:
- ctrl->csts = 0;
+ nvmet_pci_epf_clear_ctrl_config(ctrl);
return -EINVAL;
}
-static void nvmet_pci_epf_disable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
+static void nvmet_pci_epf_disable_ctrl(struct nvmet_pci_epf_ctrl *ctrl,
+ bool shutdown)
{
int qid;
if (!ctrl->enabled)
return;
- dev_info(ctrl->dev, "Disabling controller\n");
+ dev_info(ctrl->dev, "%s controller\n",
+ shutdown ? "Shutting down" : "Disabling");
ctrl->enabled = false;
cancel_delayed_work_sync(&ctrl->poll_sqs);
@@ -1893,6 +1921,11 @@ static void nvmet_pci_epf_disable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
nvmet_pci_epf_delete_cq(ctrl->tctrl, 0);
ctrl->csts &= ~NVME_CSTS_RDY;
+ if (shutdown) {
+ ctrl->csts |= NVME_CSTS_SHST_CMPLT;
+ ctrl->cc &= ~NVME_CC_ENABLE;
+ nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CC, ctrl->cc);
+ }
}
static void nvmet_pci_epf_poll_cc_work(struct work_struct *work)
@@ -1919,12 +1952,10 @@ static void nvmet_pci_epf_poll_cc_work(struct work_struct *work)
}
if (!nvmet_cc_en(new_cc) && nvmet_cc_en(old_cc))
- nvmet_pci_epf_disable_ctrl(ctrl);
+ nvmet_pci_epf_disable_ctrl(ctrl, false);
- if (nvmet_cc_shn(new_cc) && !nvmet_cc_shn(old_cc)) {
- nvmet_pci_epf_disable_ctrl(ctrl);
- ctrl->csts |= NVME_CSTS_SHST_CMPLT;
- }
+ if (nvmet_cc_shn(new_cc) && !nvmet_cc_shn(old_cc))
+ nvmet_pci_epf_disable_ctrl(ctrl, true);
if (!nvmet_cc_shn(new_cc) && nvmet_cc_shn(old_cc))
ctrl->csts &= ~NVME_CSTS_SHST_CMPLT;
@@ -1963,16 +1994,10 @@ static void nvmet_pci_epf_init_bar(struct nvmet_pci_epf_ctrl *ctrl)
/* Clear Controller Memory Buffer Supported (CMBS). */
ctrl->cap &= ~(0x1ULL << 57);
- /* Controller configuration. */
- ctrl->cc = tctrl->cc & (~NVME_CC_ENABLE);
-
- /* Controller status. */
- ctrl->csts = ctrl->tctrl->csts;
-
nvmet_pci_epf_bar_write64(ctrl, NVME_REG_CAP, ctrl->cap);
nvmet_pci_epf_bar_write32(ctrl, NVME_REG_VS, tctrl->subsys->ver);
- nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CSTS, ctrl->csts);
- nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CC, ctrl->cc);
+
+ nvmet_pci_epf_clear_ctrl_config(ctrl);
}
static int nvmet_pci_epf_create_ctrl(struct nvmet_pci_epf *nvme_epf,
@@ -2070,14 +2095,22 @@ static int nvmet_pci_epf_create_ctrl(struct nvmet_pci_epf *nvme_epf,
static void nvmet_pci_epf_start_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
{
+
+ dev_info(ctrl->dev, "PCI link up\n");
+ ctrl->link_up = true;
+
schedule_delayed_work(&ctrl->poll_cc, NVMET_PCI_EPF_CC_POLL_INTERVAL);
}
static void nvmet_pci_epf_stop_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
{
+ dev_info(ctrl->dev, "PCI link down\n");
+ ctrl->link_up = false;
+
cancel_delayed_work_sync(&ctrl->poll_cc);
- nvmet_pci_epf_disable_ctrl(ctrl);
+ nvmet_pci_epf_disable_ctrl(ctrl, false);
+ nvmet_pci_epf_clear_ctrl_config(ctrl);
}
static void nvmet_pci_epf_destroy_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
@@ -2300,10 +2333,8 @@ static int nvmet_pci_epf_epc_init(struct pci_epf *epf)
if (ret)
goto out_clear_bar;
- if (!epc_features->linkup_notifier) {
- ctrl->link_up = true;
+ if (!epc_features->linkup_notifier)
nvmet_pci_epf_start_ctrl(&nvme_epf->ctrl);
- }
return 0;
@@ -2319,7 +2350,6 @@ static void nvmet_pci_epf_epc_deinit(struct pci_epf *epf)
struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf);
struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl;
- ctrl->link_up = false;
nvmet_pci_epf_destroy_ctrl(ctrl);
nvmet_pci_epf_deinit_dma(nvme_epf);
@@ -2331,7 +2361,6 @@ static int nvmet_pci_epf_link_up(struct pci_epf *epf)
struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf);
struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl;
- ctrl->link_up = true;
nvmet_pci_epf_start_ctrl(ctrl);
return 0;
@@ -2342,7 +2371,6 @@ static int nvmet_pci_epf_link_down(struct pci_epf *epf)
struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf);
struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl;
- ctrl->link_up = false;
nvmet_pci_epf_stop_ctrl(ctrl);
return 0;
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index fff85bb..e206efc 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -594,9 +594,11 @@ static int nvmem_cell_info_to_nvmem_cell_entry_nodup(struct nvmem_device *nvmem,
cell->nbits = info->nbits;
cell->np = info->np;
- if (cell->nbits)
+ if (cell->nbits) {
cell->bytes = DIV_ROUND_UP(cell->nbits + cell->bit_offset,
BITS_PER_BYTE);
+ cell->raw_len = ALIGN(cell->bytes, nvmem->word_size);
+ }
if (!IS_ALIGNED(cell->offset, nvmem->stride)) {
dev_err(&nvmem->dev,
@@ -605,6 +607,18 @@ static int nvmem_cell_info_to_nvmem_cell_entry_nodup(struct nvmem_device *nvmem,
return -EINVAL;
}
+ if (!IS_ALIGNED(cell->raw_len, nvmem->word_size)) {
+ dev_err(&nvmem->dev,
+ "cell %s raw len %zd unaligned to nvmem word size %d\n",
+ cell->name ?: "<unknown>", cell->raw_len,
+ nvmem->word_size);
+
+ if (info->raw_len)
+ return -EINVAL;
+
+ cell->raw_len = ALIGN(cell->raw_len, nvmem->word_size);
+ }
+
return 0;
}
@@ -837,7 +851,9 @@ static int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_nod
if (addr && len == (2 * sizeof(u32))) {
info.bit_offset = be32_to_cpup(addr++);
info.nbits = be32_to_cpup(addr);
- if (info.bit_offset >= BITS_PER_BYTE || info.nbits < 1) {
+ if (info.bit_offset >= BITS_PER_BYTE * info.bytes ||
+ info.nbits < 1 ||
+ info.bit_offset + info.nbits > BITS_PER_BYTE * info.bytes) {
dev_err(dev, "nvmem: invalid bits on %pOF\n", child);
of_node_put(child);
return -EINVAL;
@@ -1630,21 +1646,29 @@ EXPORT_SYMBOL_GPL(nvmem_cell_put);
static void nvmem_shift_read_buffer_in_place(struct nvmem_cell_entry *cell, void *buf)
{
u8 *p, *b;
- int i, extra, bit_offset = cell->bit_offset;
+ int i, extra, bytes_offset;
+ int bit_offset = cell->bit_offset;
p = b = buf;
- if (bit_offset) {
+
+ bytes_offset = bit_offset / BITS_PER_BYTE;
+ b += bytes_offset;
+ bit_offset %= BITS_PER_BYTE;
+
+ if (bit_offset % BITS_PER_BYTE) {
/* First shift */
- *b++ >>= bit_offset;
+ *p = *b++ >> bit_offset;
/* setup rest of the bytes if any */
for (i = 1; i < cell->bytes; i++) {
/* Get bits from next byte and shift them towards msb */
- *p |= *b << (BITS_PER_BYTE - bit_offset);
+ *p++ |= *b << (BITS_PER_BYTE - bit_offset);
- p = b;
- *b++ >>= bit_offset;
+ *p = *b++ >> bit_offset;
}
+ } else if (p != b) {
+ memmove(p, b, cell->bytes - bytes_offset);
+ p += cell->bytes - 1;
} else {
/* point to the msb */
p += cell->bytes - 1;
diff --git a/drivers/nvmem/qfprom.c b/drivers/nvmem/qfprom.c
index 116a39e..a872c640 100644
--- a/drivers/nvmem/qfprom.c
+++ b/drivers/nvmem/qfprom.c
@@ -321,19 +321,32 @@ static int qfprom_reg_read(void *context,
unsigned int reg, void *_val, size_t bytes)
{
struct qfprom_priv *priv = context;
- u8 *val = _val;
- int i = 0, words = bytes;
+ u32 *val = _val;
void __iomem *base = priv->qfpcorrected;
+ int words = DIV_ROUND_UP(bytes, sizeof(u32));
+ int i;
if (read_raw_data && priv->qfpraw)
base = priv->qfpraw;
- while (words--)
- *val++ = readb(base + reg + i++);
+ for (i = 0; i < words; i++)
+ *val++ = readl(base + reg + i * sizeof(u32));
return 0;
}
+/* Align reads to word boundary */
+static void qfprom_fixup_dt_cell_info(struct nvmem_device *nvmem,
+ struct nvmem_cell_info *cell)
+{
+ unsigned int byte_offset = cell->offset % sizeof(u32);
+
+ cell->bit_offset += byte_offset * BITS_PER_BYTE;
+ cell->offset -= byte_offset;
+ if (byte_offset && !cell->nbits)
+ cell->nbits = cell->bytes * BITS_PER_BYTE;
+}
+
static void qfprom_runtime_disable(void *data)
{
pm_runtime_disable(data);
@@ -358,10 +371,11 @@ static int qfprom_probe(struct platform_device *pdev)
struct nvmem_config econfig = {
.name = "qfprom",
.add_legacy_fixed_of_cells = true,
- .stride = 1,
- .word_size = 1,
+ .stride = 4,
+ .word_size = 4,
.id = NVMEM_DEVID_AUTO,
.reg_read = qfprom_reg_read,
+ .fixup_dt_cell_info = qfprom_fixup_dt_cell_info,
};
struct device *dev = &pdev->dev;
struct resource *res;
diff --git a/drivers/nvmem/rockchip-otp.c b/drivers/nvmem/rockchip-otp.c
index ebc3f0b..d88f12c 100644
--- a/drivers/nvmem/rockchip-otp.c
+++ b/drivers/nvmem/rockchip-otp.c
@@ -59,7 +59,6 @@
#define RK3588_OTPC_AUTO_EN 0x08
#define RK3588_OTPC_INT_ST 0x84
#define RK3588_OTPC_DOUT0 0x20
-#define RK3588_NO_SECURE_OFFSET 0x300
#define RK3588_NBYTES 4
#define RK3588_BURST_NUM 1
#define RK3588_BURST_SHIFT 8
@@ -69,6 +68,7 @@
struct rockchip_data {
int size;
+ int read_offset;
const char * const *clks;
int num_clks;
nvmem_reg_read_t reg_read;
@@ -196,7 +196,7 @@ static int rk3588_otp_read(void *context, unsigned int offset,
addr_start = round_down(offset, RK3588_NBYTES) / RK3588_NBYTES;
addr_end = round_up(offset + bytes, RK3588_NBYTES) / RK3588_NBYTES;
addr_len = addr_end - addr_start;
- addr_start += RK3588_NO_SECURE_OFFSET;
+ addr_start += otp->data->read_offset / RK3588_NBYTES;
buf = kzalloc(array_size(addr_len, RK3588_NBYTES), GFP_KERNEL);
if (!buf)
@@ -274,12 +274,21 @@ static const struct rockchip_data px30_data = {
.reg_read = px30_otp_read,
};
+static const struct rockchip_data rk3576_data = {
+ .size = 0x100,
+ .read_offset = 0x700,
+ .clks = px30_otp_clocks,
+ .num_clks = ARRAY_SIZE(px30_otp_clocks),
+ .reg_read = rk3588_otp_read,
+};
+
static const char * const rk3588_otp_clocks[] = {
"otp", "apb_pclk", "phy", "arb",
};
static const struct rockchip_data rk3588_data = {
.size = 0x400,
+ .read_offset = 0xc00,
.clks = rk3588_otp_clocks,
.num_clks = ARRAY_SIZE(rk3588_otp_clocks),
.reg_read = rk3588_otp_read,
@@ -295,6 +304,10 @@ static const struct of_device_id rockchip_otp_match[] = {
.data = &px30_data,
},
{
+ .compatible = "rockchip,rk3576-otp",
+ .data = &rk3576_data,
+ },
+ {
.compatible = "rockchip,rk3588-otp",
.data = &rk3588_data,
},
diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c
index 6569ba3..8b88487 100644
--- a/drivers/pci/msi/msi.c
+++ b/drivers/pci/msi/msi.c
@@ -615,6 +615,9 @@ void msix_prepare_msi_desc(struct pci_dev *dev, struct msi_desc *desc)
void __iomem *addr = pci_msix_desc_addr(desc);
desc->pci.msi_attrib.can_mask = 1;
+ /* Workaround for SUN NIU insanity, which requires write before read */
+ if (dev->dev_flags & PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST)
+ writel(0, addr + PCI_MSIX_ENTRY_DATA);
desc->pci.msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
}
}
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 4d7c9f6..e77d5b53 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -5429,8 +5429,6 @@ static bool pci_bus_resettable(struct pci_bus *bus)
return false;
list_for_each_entry(dev, &bus->devices, bus_list) {
- if (!pci_reset_supported(dev))
- return false;
if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET ||
(dev->subordinate && !pci_bus_resettable(dev->subordinate)))
return false;
@@ -5507,8 +5505,6 @@ static bool pci_slot_resettable(struct pci_slot *slot)
list_for_each_entry(dev, &slot->bus->devices, bus_list) {
if (!dev->slot || dev->slot != slot)
continue;
- if (!pci_reset_supported(dev))
- return false;
if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET ||
(dev->subordinate && !pci_bus_resettable(dev->subordinate)))
return false;
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 8d610c1..94daca15a 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -1990,12 +1990,12 @@ static void quirk_huawei_pcie_sva(struct pci_dev *pdev)
device_create_managed_software_node(&pdev->dev, properties, NULL))
pci_warn(pdev, "could not add stall property");
}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa250, quirk_huawei_pcie_sva);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa251, quirk_huawei_pcie_sva);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa255, quirk_huawei_pcie_sva);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa256, quirk_huawei_pcie_sva);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa258, quirk_huawei_pcie_sva);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa259, quirk_huawei_pcie_sva);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0xa250, quirk_huawei_pcie_sva);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0xa251, quirk_huawei_pcie_sva);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0xa255, quirk_huawei_pcie_sva);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0xa256, quirk_huawei_pcie_sva);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0xa258, quirk_huawei_pcie_sva);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0xa259, quirk_huawei_pcie_sva);
/*
* It's possible for the MSI to get corrupted if SHPC and ACPI are used
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 54d6f4f..e994c54 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -187,6 +187,9 @@ static void pdev_sort_resources(struct pci_dev *dev, struct list_head *head)
panic("%s: kzalloc() failed!\n", __func__);
tmp->res = r;
tmp->dev = dev;
+ tmp->start = r->start;
+ tmp->end = r->end;
+ tmp->flags = r->flags;
/* Fallback is smallest one or list is empty */
n = head;
@@ -545,6 +548,7 @@ static void __assign_resources_sorted(struct list_head *head,
pci_dbg(dev, "%s %pR: releasing\n", res_name, res);
release_resource(res);
+ restore_dev_resource(dev_res);
}
/* Restore start/end/flags from saved list */
list_for_each_entry(save_res, &save_head, list)
diff --git a/drivers/phy/phy-can-transceiver.c b/drivers/phy/phy-can-transceiver.c
index 2bec706..f59caff 100644
--- a/drivers/phy/phy-can-transceiver.c
+++ b/drivers/phy/phy-can-transceiver.c
@@ -93,6 +93,16 @@ static const struct of_device_id can_transceiver_phy_ids[] = {
};
MODULE_DEVICE_TABLE(of, can_transceiver_phy_ids);
+/* Temporary wrapper until the multiplexer subsystem supports optional muxes */
+static inline struct mux_state *
+devm_mux_state_get_optional(struct device *dev, const char *mux_name)
+{
+ if (!of_property_present(dev->of_node, "mux-states"))
+ return NULL;
+
+ return devm_mux_state_get(dev, mux_name);
+}
+
static int can_transceiver_phy_probe(struct platform_device *pdev)
{
struct phy_provider *phy_provider;
@@ -114,13 +124,11 @@ static int can_transceiver_phy_probe(struct platform_device *pdev)
match = of_match_node(can_transceiver_phy_ids, pdev->dev.of_node);
drvdata = match->data;
- mux_state = devm_mux_state_get(dev, NULL);
- if (IS_ERR(mux_state)) {
- if (PTR_ERR(mux_state) == -EPROBE_DEFER)
- return PTR_ERR(mux_state);
- } else {
- can_transceiver_phy->mux_state = mux_state;
- }
+ mux_state = devm_mux_state_get_optional(dev, NULL);
+ if (IS_ERR(mux_state))
+ return PTR_ERR(mux_state);
+
+ can_transceiver_phy->mux_state = mux_state;
phy = devm_phy_create(dev, dev->of_node,
&can_transceiver_phy_ops);
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
index 45b3b79..b33e2e2 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
@@ -1754,7 +1754,8 @@ static void qmp_ufs_init_registers(struct qmp_ufs *qmp, const struct qmp_phy_cfg
qmp_ufs_init_all(qmp, &cfg->tbls_hs_overlay[i]);
}
- qmp_ufs_init_all(qmp, &cfg->tbls_hs_b);
+ if (qmp->mode == PHY_MODE_UFS_HS_B)
+ qmp_ufs_init_all(qmp, &cfg->tbls_hs_b);
}
static int qmp_ufs_com_init(struct qmp_ufs *qmp)
diff --git a/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c b/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c
index 08c78c1..28a052e 100644
--- a/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c
+++ b/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c
@@ -1653,7 +1653,7 @@ static __maybe_unused int samsung_mipi_dcphy_runtime_resume(struct device *dev)
return ret;
}
- clk_prepare_enable(samsung->ref_clk);
+ ret = clk_prepare_enable(samsung->ref_clk);
if (ret) {
dev_err(samsung->dev, "Failed to enable reference clock, %d\n", ret);
clk_disable_unprepare(samsung->pclk);
diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c
index fae6242..cc7b8a6 100644
--- a/drivers/phy/tegra/xusb-tegra186.c
+++ b/drivers/phy/tegra/xusb-tegra186.c
@@ -237,6 +237,8 @@
#define DATA0_VAL_PD BIT(1)
#define USE_XUSB_AO BIT(4)
+#define TEGRA_UTMI_PAD_MAX 4
+
#define TEGRA186_LANE(_name, _offset, _shift, _mask, _type) \
{ \
.name = _name, \
@@ -269,7 +271,7 @@ struct tegra186_xusb_padctl {
/* UTMI bias and tracking */
struct clk *usb2_trk_clk;
- unsigned int bias_pad_enable;
+ DECLARE_BITMAP(utmi_pad_enabled, TEGRA_UTMI_PAD_MAX);
/* padctl context */
struct tegra186_xusb_padctl_context context;
@@ -603,12 +605,8 @@ static void tegra186_utmi_bias_pad_power_on(struct tegra_xusb_padctl *padctl)
u32 value;
int err;
- mutex_lock(&padctl->lock);
-
- if (priv->bias_pad_enable++ > 0) {
- mutex_unlock(&padctl->lock);
+ if (!bitmap_empty(priv->utmi_pad_enabled, TEGRA_UTMI_PAD_MAX))
return;
- }
err = clk_prepare_enable(priv->usb2_trk_clk);
if (err < 0)
@@ -667,17 +665,8 @@ static void tegra186_utmi_bias_pad_power_off(struct tegra_xusb_padctl *padctl)
struct tegra186_xusb_padctl *priv = to_tegra186_xusb_padctl(padctl);
u32 value;
- mutex_lock(&padctl->lock);
-
- if (WARN_ON(priv->bias_pad_enable == 0)) {
- mutex_unlock(&padctl->lock);
+ if (!bitmap_empty(priv->utmi_pad_enabled, TEGRA_UTMI_PAD_MAX))
return;
- }
-
- if (--priv->bias_pad_enable > 0) {
- mutex_unlock(&padctl->lock);
- return;
- }
value = padctl_readl(padctl, XUSB_PADCTL_USB2_BIAS_PAD_CTL1);
value |= USB2_PD_TRK;
@@ -690,13 +679,13 @@ static void tegra186_utmi_bias_pad_power_off(struct tegra_xusb_padctl *padctl)
clk_disable_unprepare(priv->usb2_trk_clk);
}
- mutex_unlock(&padctl->lock);
}
static void tegra186_utmi_pad_power_on(struct phy *phy)
{
struct tegra_xusb_lane *lane = phy_get_drvdata(phy);
struct tegra_xusb_padctl *padctl = lane->pad->padctl;
+ struct tegra186_xusb_padctl *priv = to_tegra186_xusb_padctl(padctl);
struct tegra_xusb_usb2_port *port;
struct device *dev = padctl->dev;
unsigned int index = lane->index;
@@ -705,9 +694,16 @@ static void tegra186_utmi_pad_power_on(struct phy *phy)
if (!phy)
return;
+ mutex_lock(&padctl->lock);
+ if (test_bit(index, priv->utmi_pad_enabled)) {
+ mutex_unlock(&padctl->lock);
+ return;
+ }
+
port = tegra_xusb_find_usb2_port(padctl, index);
if (!port) {
dev_err(dev, "no port found for USB2 lane %u\n", index);
+ mutex_unlock(&padctl->lock);
return;
}
@@ -724,18 +720,28 @@ static void tegra186_utmi_pad_power_on(struct phy *phy)
value = padctl_readl(padctl, XUSB_PADCTL_USB2_OTG_PADX_CTL1(index));
value &= ~USB2_OTG_PD_DR;
padctl_writel(padctl, value, XUSB_PADCTL_USB2_OTG_PADX_CTL1(index));
+
+ set_bit(index, priv->utmi_pad_enabled);
+ mutex_unlock(&padctl->lock);
}
static void tegra186_utmi_pad_power_down(struct phy *phy)
{
struct tegra_xusb_lane *lane = phy_get_drvdata(phy);
struct tegra_xusb_padctl *padctl = lane->pad->padctl;
+ struct tegra186_xusb_padctl *priv = to_tegra186_xusb_padctl(padctl);
unsigned int index = lane->index;
u32 value;
if (!phy)
return;
+ mutex_lock(&padctl->lock);
+ if (!test_bit(index, priv->utmi_pad_enabled)) {
+ mutex_unlock(&padctl->lock);
+ return;
+ }
+
dev_dbg(padctl->dev, "power down UTMI pad %u\n", index);
value = padctl_readl(padctl, XUSB_PADCTL_USB2_OTG_PADX_CTL0(index));
@@ -748,7 +754,11 @@ static void tegra186_utmi_pad_power_down(struct phy *phy)
udelay(2);
+ clear_bit(index, priv->utmi_pad_enabled);
+
tegra186_utmi_bias_pad_power_off(padctl);
+
+ mutex_unlock(&padctl->lock);
}
static int tegra186_xusb_padctl_vbus_override(struct tegra_xusb_padctl *padctl,
diff --git a/drivers/platform/mellanox/mlxbf-bootctl.c b/drivers/platform/mellanox/mlxbf-bootctl.c
index b95dcb8..c18a5b9 100644
--- a/drivers/platform/mellanox/mlxbf-bootctl.c
+++ b/drivers/platform/mellanox/mlxbf-bootctl.c
@@ -333,9 +333,9 @@ static ssize_t secure_boot_fuse_state_show(struct device *dev,
else
status = valid ? "Invalid" : "Free";
}
- buf_len += sysfs_emit(buf + buf_len, "%d:%s ", key, status);
+ buf_len += sysfs_emit_at(buf, buf_len, "%d:%s ", key, status);
}
- buf_len += sysfs_emit(buf + buf_len, "\n");
+ buf_len += sysfs_emit_at(buf, buf_len, "\n");
return buf_len;
}
diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c
index d789d6c..0329faf 100644
--- a/drivers/platform/x86/amd/pmc/pmc.c
+++ b/drivers/platform/x86/amd/pmc/pmc.c
@@ -644,10 +644,9 @@ static void amd_pmc_s2idle_check(void)
struct smu_metrics table;
int rc;
- /* CZN: Ensure that future s0i3 entry attempts at least 10ms passed */
- if (pdev->cpu_id == AMD_CPU_ID_CZN && !get_metrics_table(pdev, &table) &&
- table.s0i3_last_entry_status)
- usleep_range(10000, 20000);
+ /* Avoid triggering OVP */
+ if (!get_metrics_table(pdev, &table) && table.s0i3_last_entry_status)
+ msleep(2500);
/* Dump the IdleMask before we add to the STB */
amd_pmc_idlemask_read(pdev, pdev->dev, NULL);
diff --git a/drivers/platform/x86/amd/pmf/auto-mode.c b/drivers/platform/x86/amd/pmf/auto-mode.c
index 02ff68b..a184922 100644
--- a/drivers/platform/x86/amd/pmf/auto-mode.c
+++ b/drivers/platform/x86/amd/pmf/auto-mode.c
@@ -120,9 +120,9 @@ static void amd_pmf_set_automode(struct amd_pmf_dev *dev, int idx,
amd_pmf_send_cmd(dev, SET_SPPT_APU_ONLY, false, pwr_ctrl->sppt_apu_only, NULL);
amd_pmf_send_cmd(dev, SET_STT_MIN_LIMIT, false, pwr_ctrl->stt_min, NULL);
amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false,
- pwr_ctrl->stt_skin_temp[STT_TEMP_APU], NULL);
+ fixp_q88_fromint(pwr_ctrl->stt_skin_temp[STT_TEMP_APU]), NULL);
amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false,
- pwr_ctrl->stt_skin_temp[STT_TEMP_HS2], NULL);
+ fixp_q88_fromint(pwr_ctrl->stt_skin_temp[STT_TEMP_HS2]), NULL);
if (is_apmf_func_supported(dev, APMF_FUNC_SET_FAN_IDX))
apmf_update_fan_idx(dev, config_store.mode_set[idx].fan_control.manual,
diff --git a/drivers/platform/x86/amd/pmf/cnqf.c b/drivers/platform/x86/amd/pmf/cnqf.c
index bc8899e..207a0b3 100644
--- a/drivers/platform/x86/amd/pmf/cnqf.c
+++ b/drivers/platform/x86/amd/pmf/cnqf.c
@@ -81,10 +81,10 @@ static int amd_pmf_set_cnqf(struct amd_pmf_dev *dev, int src, int idx,
amd_pmf_send_cmd(dev, SET_SPPT, false, pc->sppt, NULL);
amd_pmf_send_cmd(dev, SET_SPPT_APU_ONLY, false, pc->sppt_apu_only, NULL);
amd_pmf_send_cmd(dev, SET_STT_MIN_LIMIT, false, pc->stt_min, NULL);
- amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false, pc->stt_skin_temp[STT_TEMP_APU],
- NULL);
- amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false, pc->stt_skin_temp[STT_TEMP_HS2],
- NULL);
+ amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false,
+ fixp_q88_fromint(pc->stt_skin_temp[STT_TEMP_APU]), NULL);
+ amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false,
+ fixp_q88_fromint(pc->stt_skin_temp[STT_TEMP_HS2]), NULL);
if (is_apmf_func_supported(dev, APMF_FUNC_SET_FAN_IDX))
apmf_update_fan_idx(dev,
diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c
index a2cb2d5..9682110 100644
--- a/drivers/platform/x86/amd/pmf/core.c
+++ b/drivers/platform/x86/amd/pmf/core.c
@@ -176,6 +176,20 @@ static void __maybe_unused amd_pmf_dump_registers(struct amd_pmf_dev *dev)
dev_dbg(dev->dev, "AMD_PMF_REGISTER_MESSAGE:%x\n", value);
}
+/**
+ * fixp_q88_fromint: Convert integer to Q8.8
+ * @val: input value
+ *
+ * Converts an integer into binary fixed point format where 8 bits
+ * are used for integer and 8 bits are used for the decimal.
+ *
+ * Return: unsigned integer converted to Q8.8 format
+ */
+u32 fixp_q88_fromint(u32 val)
+{
+ return val << 8;
+}
+
int amd_pmf_send_cmd(struct amd_pmf_dev *dev, u8 message, bool get, u32 arg, u32 *data)
{
int rc;
diff --git a/drivers/platform/x86/amd/pmf/pmf.h b/drivers/platform/x86/amd/pmf/pmf.h
index e6bdee6..45b6023 100644
--- a/drivers/platform/x86/amd/pmf/pmf.h
+++ b/drivers/platform/x86/amd/pmf/pmf.h
@@ -777,6 +777,7 @@ int apmf_install_handler(struct amd_pmf_dev *pmf_dev);
int apmf_os_power_slider_update(struct amd_pmf_dev *dev, u8 flag);
int amd_pmf_set_dram_addr(struct amd_pmf_dev *dev, bool alloc_buffer);
int amd_pmf_notify_sbios_heartbeat_event_v2(struct amd_pmf_dev *dev, u8 flag);
+u32 fixp_q88_fromint(u32 val);
/* SPS Layer */
int amd_pmf_get_pprof_modes(struct amd_pmf_dev *pmf);
diff --git a/drivers/platform/x86/amd/pmf/sps.c b/drivers/platform/x86/amd/pmf/sps.c
index d308338..49e14ca 100644
--- a/drivers/platform/x86/amd/pmf/sps.c
+++ b/drivers/platform/x86/amd/pmf/sps.c
@@ -198,9 +198,11 @@ static void amd_pmf_update_slider_v2(struct amd_pmf_dev *dev, int idx)
amd_pmf_send_cmd(dev, SET_STT_MIN_LIMIT, false,
apts_config_store.val[idx].stt_min_limit, NULL);
amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false,
- apts_config_store.val[idx].stt_skin_temp_limit_apu, NULL);
+ fixp_q88_fromint(apts_config_store.val[idx].stt_skin_temp_limit_apu),
+ NULL);
amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false,
- apts_config_store.val[idx].stt_skin_temp_limit_hs2, NULL);
+ fixp_q88_fromint(apts_config_store.val[idx].stt_skin_temp_limit_hs2),
+ NULL);
}
void amd_pmf_update_slider(struct amd_pmf_dev *dev, bool op, int idx,
@@ -217,9 +219,11 @@ void amd_pmf_update_slider(struct amd_pmf_dev *dev, bool op, int idx,
amd_pmf_send_cmd(dev, SET_STT_MIN_LIMIT, false,
config_store.prop[src][idx].stt_min, NULL);
amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false,
- config_store.prop[src][idx].stt_skin_temp[STT_TEMP_APU], NULL);
+ fixp_q88_fromint(config_store.prop[src][idx].stt_skin_temp[STT_TEMP_APU]),
+ NULL);
amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false,
- config_store.prop[src][idx].stt_skin_temp[STT_TEMP_HS2], NULL);
+ fixp_q88_fromint(config_store.prop[src][idx].stt_skin_temp[STT_TEMP_HS2]),
+ NULL);
} else if (op == SLIDER_OP_GET) {
amd_pmf_send_cmd(dev, GET_SPL, true, ARG_NONE, &table->prop[src][idx].spl);
amd_pmf_send_cmd(dev, GET_FPPT, true, ARG_NONE, &table->prop[src][idx].fppt);
diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c
index a1e4387..14b99d8 100644
--- a/drivers/platform/x86/amd/pmf/tee-if.c
+++ b/drivers/platform/x86/amd/pmf/tee-if.c
@@ -123,7 +123,8 @@ static void amd_pmf_apply_policies(struct amd_pmf_dev *dev, struct ta_pmf_enact_
case PMF_POLICY_STT_SKINTEMP_APU:
if (dev->prev_data->stt_skintemp_apu != val) {
- amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false, val, NULL);
+ amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false,
+ fixp_q88_fromint(val), NULL);
dev_dbg(dev->dev, "update STT_SKINTEMP_APU: %u\n", val);
dev->prev_data->stt_skintemp_apu = val;
}
@@ -131,7 +132,8 @@ static void amd_pmf_apply_policies(struct amd_pmf_dev *dev, struct ta_pmf_enact_
case PMF_POLICY_STT_SKINTEMP_HS2:
if (dev->prev_data->stt_skintemp_hs2 != val) {
- amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false, val, NULL);
+ amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false,
+ fixp_q88_fromint(val), NULL);
dev_dbg(dev->dev, "update STT_SKINTEMP_HS2: %u\n", val);
dev->prev_data->stt_skintemp_hs2 = val;
}
diff --git a/drivers/platform/x86/asus-laptop.c b/drivers/platform/x86/asus-laptop.c
index d460dd1..a0a411b 100644
--- a/drivers/platform/x86/asus-laptop.c
+++ b/drivers/platform/x86/asus-laptop.c
@@ -426,11 +426,14 @@ static int asus_pega_lucid_set(struct asus_laptop *asus, int unit, bool enable)
static int pega_acc_axis(struct asus_laptop *asus, int curr, char *method)
{
+ unsigned long long val = (unsigned long long)curr;
+ acpi_status status;
int i, delta;
- unsigned long long val;
- for (i = 0; i < PEGA_ACC_RETRIES; i++) {
- acpi_evaluate_integer(asus->handle, method, NULL, &val);
+ for (i = 0; i < PEGA_ACC_RETRIES; i++) {
+ status = acpi_evaluate_integer(asus->handle, method, NULL, &val);
+ if (ACPI_FAILURE(status))
+ continue;
/* The output is noisy. From reading the ASL
* dissassembly, timeout errors are returned with 1's
* in the high word, and the lack of locking around
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 38ef778..0c697b4 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -304,6 +304,7 @@ struct asus_wmi {
u32 kbd_rgb_dev;
bool kbd_rgb_state_available;
+ bool oobe_state_available;
u8 throttle_thermal_policy_mode;
u32 throttle_thermal_policy_dev;
@@ -1826,7 +1827,7 @@ static int asus_wmi_led_init(struct asus_wmi *asus)
goto error;
}
- if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_OOBE)) {
+ if (asus->oobe_state_available) {
/*
* Disable OOBE state, so that e.g. the keyboard backlight
* works.
@@ -4723,6 +4724,7 @@ static int asus_wmi_add(struct platform_device *pdev)
asus->egpu_enable_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_EGPU);
asus->dgpu_disable_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_DGPU);
asus->kbd_rgb_state_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_TUF_RGB_STATE);
+ asus->oobe_state_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_OOBE);
asus->ally_mcu_usb_switch = acpi_has_method(NULL, ASUS_USB0_PWR_EC0_CSEE)
&& dmi_check_system(asus_ally_mcu_quirk);
@@ -4970,6 +4972,13 @@ static int asus_hotk_restore(struct device *device)
}
if (!IS_ERR_OR_NULL(asus->kbd_led.dev))
kbd_led_update(asus);
+ if (asus->oobe_state_available) {
+ /*
+ * Disable OOBE state, so that e.g. the keyboard backlight
+ * works.
+ */
+ asus_wmi_set_devstate(ASUS_WMI_DEVID_OOBE, 1, NULL);
+ }
if (asus_wmi_has_fnlock_key(asus))
asus_wmi_fnlock_update(asus);
diff --git a/drivers/platform/x86/dell/alienware-wmi-wmax.c b/drivers/platform/x86/dell/alienware-wmi-wmax.c
index 3d3014b..08b82c1 100644
--- a/drivers/platform/x86/dell/alienware-wmi-wmax.c
+++ b/drivers/platform/x86/dell/alienware-wmi-wmax.c
@@ -62,11 +62,43 @@ static struct awcc_quirks empty_quirks;
static const struct dmi_system_id awcc_dmi_table[] __initconst = {
{
+ .ident = "Alienware Area-51m R2",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Alienware Area-51m R2"),
+ },
+ .driver_data = &generic_quirks,
+ },
+ {
+ .ident = "Alienware m15 R7",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m15 R7"),
+ },
+ .driver_data = &generic_quirks,
+ },
+ {
+ .ident = "Alienware m16 R1",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m16 R1"),
+ },
+ .driver_data = &g_series_quirks,
+ },
+ {
.ident = "Alienware m16 R1 AMD",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m16 R1 AMD"),
},
+ .driver_data = &g_series_quirks,
+ },
+ {
+ .ident = "Alienware m16 R2",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m16 R2"),
+ },
.driver_data = &generic_quirks,
},
{
@@ -94,6 +126,14 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = {
.driver_data = &generic_quirks,
},
{
+ .ident = "Alienware x15 R2",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Alienware x15 R2"),
+ },
+ .driver_data = &generic_quirks,
+ },
+ {
.ident = "Alienware x17 R2",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
@@ -126,6 +166,14 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = {
.driver_data = &g_series_quirks,
},
{
+ .ident = "Dell Inc. G16 7630",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Dell G16 7630"),
+ },
+ .driver_data = &g_series_quirks,
+ },
+ {
.ident = "Dell Inc. G3 3500",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
@@ -149,6 +197,14 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = {
},
.driver_data = &g_series_quirks,
},
+ {
+ .ident = "Dell Inc. G5 5505",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "G5 5505"),
+ },
+ .driver_data = &g_series_quirks,
+ },
};
enum WMAX_THERMAL_INFORMATION_OPERATIONS {
@@ -607,12 +663,10 @@ static int thermal_profile_probe(void *drvdata, unsigned long *choices)
for (u32 i = 0; i < sys_desc[3]; i++) {
ret = wmax_thermal_information(priv->wdev, WMAX_OPERATION_LIST_IDS,
i + first_mode, &out_data);
-
- if (ret == -EIO)
- return ret;
-
if (ret == -EBADRQC)
break;
+ if (ret)
+ return ret;
if (!is_wmax_thermal_code(out_data))
continue;
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index 17a09b7..ede4835 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -1294,6 +1294,16 @@ static const struct key_entry ideapad_keymap[] = {
/* Specific to some newer models */
{ KE_KEY, 0x3e | IDEAPAD_WMI_KEY, { KEY_MICMUTE } },
{ KE_KEY, 0x3f | IDEAPAD_WMI_KEY, { KEY_RFKILL } },
+ /* Star- (User Assignable Key) */
+ { KE_KEY, 0x44 | IDEAPAD_WMI_KEY, { KEY_PROG1 } },
+ /* Eye */
+ { KE_KEY, 0x45 | IDEAPAD_WMI_KEY, { KEY_PROG3 } },
+ /* Performance toggle also Fn+Q, handled inside ideapad_wmi_notify() */
+ { KE_KEY, 0x3d | IDEAPAD_WMI_KEY, { KEY_PROG4 } },
+ /* shift + prtsc */
+ { KE_KEY, 0x2d | IDEAPAD_WMI_KEY, { KEY_CUT } },
+ { KE_KEY, 0x29 | IDEAPAD_WMI_KEY, { KEY_TOUCHPAD_TOGGLE } },
+ { KE_KEY, 0x2a | IDEAPAD_WMI_KEY, { KEY_ROOT_MENU } },
{ KE_END },
};
@@ -2080,6 +2090,12 @@ static void ideapad_wmi_notify(struct wmi_device *wdev, union acpi_object *data)
dev_dbg(&wdev->dev, "WMI fn-key event: 0x%llx\n",
data->integer.value);
+ /* performance button triggered by 0x3d */
+ if (data->integer.value == 0x3d && priv->dytc) {
+ platform_profile_cycle();
+ break;
+ }
+
/* 0x02 FnLock, 0x03 Esc */
if (data->integer.value == 0x02 || data->integer.value == 0x03)
ideapad_fn_lock_led_notify(priv, data->integer.value == 0x02);
diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c
index 88a1a9f..0b5e434 100644
--- a/drivers/platform/x86/intel/hid.c
+++ b/drivers/platform/x86/intel/hid.c
@@ -44,16 +44,17 @@ MODULE_LICENSE("GPL");
MODULE_AUTHOR("Alex Hung");
static const struct acpi_device_id intel_hid_ids[] = {
- {"INT33D5", 0},
- {"INTC1051", 0},
- {"INTC1054", 0},
- {"INTC1070", 0},
- {"INTC1076", 0},
- {"INTC1077", 0},
- {"INTC1078", 0},
- {"INTC107B", 0},
- {"INTC10CB", 0},
- {"", 0},
+ { "INT33D5" },
+ { "INTC1051" },
+ { "INTC1054" },
+ { "INTC1070" },
+ { "INTC1076" },
+ { "INTC1077" },
+ { "INTC1078" },
+ { "INTC107B" },
+ { "INTC10CB" },
+ { "INTC10CC" },
+ { }
};
MODULE_DEVICE_TABLE(acpi, intel_hid_ids);
diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c
index 40bbf8e..bdee5d0 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c
@@ -146,15 +146,13 @@ static int uncore_event_cpu_online(unsigned int cpu)
{
struct uncore_data *data;
int target;
+ int ret;
/* Check if there is an online cpu in the package for uncore MSR */
target = cpumask_any_and(&uncore_cpu_mask, topology_die_cpumask(cpu));
if (target < nr_cpu_ids)
return 0;
- /* Use this CPU on this die as a control CPU */
- cpumask_set_cpu(cpu, &uncore_cpu_mask);
-
data = uncore_get_instance(cpu);
if (!data)
return 0;
@@ -163,7 +161,14 @@ static int uncore_event_cpu_online(unsigned int cpu)
data->die_id = topology_die_id(cpu);
data->domain_id = UNCORE_DOMAIN_ID_INVALID;
- return uncore_freq_add_entry(data, cpu);
+ ret = uncore_freq_add_entry(data, cpu);
+ if (ret)
+ return ret;
+
+ /* Use this CPU on this die as a control CPU */
+ cpumask_set_cpu(cpu, &uncore_cpu_mask);
+
+ return 0;
}
static int uncore_event_cpu_offline(unsigned int cpu)
diff --git a/drivers/platform/x86/msi-wmi-platform.c b/drivers/platform/x86/msi-wmi-platform.c
index 9b5c7f8..dc5e987 100644
--- a/drivers/platform/x86/msi-wmi-platform.c
+++ b/drivers/platform/x86/msi-wmi-platform.c
@@ -10,6 +10,7 @@
#include <linux/acpi.h>
#include <linux/bits.h>
#include <linux/bitfield.h>
+#include <linux/cleanup.h>
#include <linux/debugfs.h>
#include <linux/device.h>
#include <linux/device/driver.h>
@@ -17,6 +18,7 @@
#include <linux/hwmon.h>
#include <linux/kernel.h>
#include <linux/module.h>
+#include <linux/mutex.h>
#include <linux/printk.h>
#include <linux/rwsem.h>
#include <linux/types.h>
@@ -76,8 +78,13 @@ enum msi_wmi_platform_method {
MSI_PLATFORM_GET_WMI = 0x1d,
};
-struct msi_wmi_platform_debugfs_data {
+struct msi_wmi_platform_data {
struct wmi_device *wdev;
+ struct mutex wmi_lock; /* Necessary when calling WMI methods */
+};
+
+struct msi_wmi_platform_debugfs_data {
+ struct msi_wmi_platform_data *data;
enum msi_wmi_platform_method method;
struct rw_semaphore buffer_lock; /* Protects debugfs buffer */
size_t length;
@@ -132,8 +139,9 @@ static int msi_wmi_platform_parse_buffer(union acpi_object *obj, u8 *output, siz
return 0;
}
-static int msi_wmi_platform_query(struct wmi_device *wdev, enum msi_wmi_platform_method method,
- u8 *input, size_t input_length, u8 *output, size_t output_length)
+static int msi_wmi_platform_query(struct msi_wmi_platform_data *data,
+ enum msi_wmi_platform_method method, u8 *input,
+ size_t input_length, u8 *output, size_t output_length)
{
struct acpi_buffer out = { ACPI_ALLOCATE_BUFFER, NULL };
struct acpi_buffer in = {
@@ -147,9 +155,15 @@ static int msi_wmi_platform_query(struct wmi_device *wdev, enum msi_wmi_platform
if (!input_length || !output_length)
return -EINVAL;
- status = wmidev_evaluate_method(wdev, 0x0, method, &in, &out);
- if (ACPI_FAILURE(status))
- return -EIO;
+ /*
+ * The ACPI control method responsible for handling the WMI method calls
+ * is not thread-safe. Because of this we have to do the locking ourself.
+ */
+ scoped_guard(mutex, &data->wmi_lock) {
+ status = wmidev_evaluate_method(data->wdev, 0x0, method, &in, &out);
+ if (ACPI_FAILURE(status))
+ return -EIO;
+ }
obj = out.pointer;
if (!obj)
@@ -170,22 +184,22 @@ static umode_t msi_wmi_platform_is_visible(const void *drvdata, enum hwmon_senso
static int msi_wmi_platform_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
int channel, long *val)
{
- struct wmi_device *wdev = dev_get_drvdata(dev);
+ struct msi_wmi_platform_data *data = dev_get_drvdata(dev);
u8 input[32] = { 0 };
u8 output[32];
- u16 data;
+ u16 value;
int ret;
- ret = msi_wmi_platform_query(wdev, MSI_PLATFORM_GET_FAN, input, sizeof(input), output,
+ ret = msi_wmi_platform_query(data, MSI_PLATFORM_GET_FAN, input, sizeof(input), output,
sizeof(output));
if (ret < 0)
return ret;
- data = get_unaligned_be16(&output[channel * 2 + 1]);
- if (!data)
+ value = get_unaligned_be16(&output[channel * 2 + 1]);
+ if (!value)
*val = 0;
else
- *val = 480000 / data;
+ *val = 480000 / value;
return 0;
}
@@ -231,7 +245,7 @@ static ssize_t msi_wmi_platform_write(struct file *fp, const char __user *input,
return ret;
down_write(&data->buffer_lock);
- ret = msi_wmi_platform_query(data->wdev, data->method, payload, data->length, data->buffer,
+ ret = msi_wmi_platform_query(data->data, data->method, payload, data->length, data->buffer,
data->length);
up_write(&data->buffer_lock);
@@ -277,17 +291,17 @@ static void msi_wmi_platform_debugfs_remove(void *data)
debugfs_remove_recursive(dir);
}
-static void msi_wmi_platform_debugfs_add(struct wmi_device *wdev, struct dentry *dir,
+static void msi_wmi_platform_debugfs_add(struct msi_wmi_platform_data *drvdata, struct dentry *dir,
const char *name, enum msi_wmi_platform_method method)
{
struct msi_wmi_platform_debugfs_data *data;
struct dentry *entry;
- data = devm_kzalloc(&wdev->dev, sizeof(*data), GFP_KERNEL);
+ data = devm_kzalloc(&drvdata->wdev->dev, sizeof(*data), GFP_KERNEL);
if (!data)
return;
- data->wdev = wdev;
+ data->data = drvdata;
data->method = method;
init_rwsem(&data->buffer_lock);
@@ -298,82 +312,82 @@ static void msi_wmi_platform_debugfs_add(struct wmi_device *wdev, struct dentry
entry = debugfs_create_file(name, 0600, dir, data, &msi_wmi_platform_debugfs_fops);
if (IS_ERR(entry))
- devm_kfree(&wdev->dev, data);
+ devm_kfree(&drvdata->wdev->dev, data);
}
-static void msi_wmi_platform_debugfs_init(struct wmi_device *wdev)
+static void msi_wmi_platform_debugfs_init(struct msi_wmi_platform_data *data)
{
struct dentry *dir;
char dir_name[64];
int ret, method;
- scnprintf(dir_name, ARRAY_SIZE(dir_name), "%s-%s", DRIVER_NAME, dev_name(&wdev->dev));
+ scnprintf(dir_name, ARRAY_SIZE(dir_name), "%s-%s", DRIVER_NAME, dev_name(&data->wdev->dev));
dir = debugfs_create_dir(dir_name, NULL);
if (IS_ERR(dir))
return;
- ret = devm_add_action_or_reset(&wdev->dev, msi_wmi_platform_debugfs_remove, dir);
+ ret = devm_add_action_or_reset(&data->wdev->dev, msi_wmi_platform_debugfs_remove, dir);
if (ret < 0)
return;
for (method = MSI_PLATFORM_GET_PACKAGE; method <= MSI_PLATFORM_GET_WMI; method++)
- msi_wmi_platform_debugfs_add(wdev, dir, msi_wmi_platform_debugfs_names[method - 1],
+ msi_wmi_platform_debugfs_add(data, dir, msi_wmi_platform_debugfs_names[method - 1],
method);
}
-static int msi_wmi_platform_hwmon_init(struct wmi_device *wdev)
+static int msi_wmi_platform_hwmon_init(struct msi_wmi_platform_data *data)
{
struct device *hdev;
- hdev = devm_hwmon_device_register_with_info(&wdev->dev, "msi_wmi_platform", wdev,
+ hdev = devm_hwmon_device_register_with_info(&data->wdev->dev, "msi_wmi_platform", data,
&msi_wmi_platform_chip_info, NULL);
return PTR_ERR_OR_ZERO(hdev);
}
-static int msi_wmi_platform_ec_init(struct wmi_device *wdev)
+static int msi_wmi_platform_ec_init(struct msi_wmi_platform_data *data)
{
u8 input[32] = { 0 };
u8 output[32];
u8 flags;
int ret;
- ret = msi_wmi_platform_query(wdev, MSI_PLATFORM_GET_EC, input, sizeof(input), output,
+ ret = msi_wmi_platform_query(data, MSI_PLATFORM_GET_EC, input, sizeof(input), output,
sizeof(output));
if (ret < 0)
return ret;
flags = output[MSI_PLATFORM_EC_FLAGS_OFFSET];
- dev_dbg(&wdev->dev, "EC RAM version %lu.%lu\n",
+ dev_dbg(&data->wdev->dev, "EC RAM version %lu.%lu\n",
FIELD_GET(MSI_PLATFORM_EC_MAJOR_MASK, flags),
FIELD_GET(MSI_PLATFORM_EC_MINOR_MASK, flags));
- dev_dbg(&wdev->dev, "EC firmware version %.28s\n",
+ dev_dbg(&data->wdev->dev, "EC firmware version %.28s\n",
&output[MSI_PLATFORM_EC_VERSION_OFFSET]);
if (!(flags & MSI_PLATFORM_EC_IS_TIGERLAKE)) {
if (!force)
return -ENODEV;
- dev_warn(&wdev->dev, "Loading on a non-Tigerlake platform\n");
+ dev_warn(&data->wdev->dev, "Loading on a non-Tigerlake platform\n");
}
return 0;
}
-static int msi_wmi_platform_init(struct wmi_device *wdev)
+static int msi_wmi_platform_init(struct msi_wmi_platform_data *data)
{
u8 input[32] = { 0 };
u8 output[32];
int ret;
- ret = msi_wmi_platform_query(wdev, MSI_PLATFORM_GET_WMI, input, sizeof(input), output,
+ ret = msi_wmi_platform_query(data, MSI_PLATFORM_GET_WMI, input, sizeof(input), output,
sizeof(output));
if (ret < 0)
return ret;
- dev_dbg(&wdev->dev, "WMI interface version %u.%u\n",
+ dev_dbg(&data->wdev->dev, "WMI interface version %u.%u\n",
output[MSI_PLATFORM_WMI_MAJOR_OFFSET],
output[MSI_PLATFORM_WMI_MINOR_OFFSET]);
@@ -381,7 +395,8 @@ static int msi_wmi_platform_init(struct wmi_device *wdev)
if (!force)
return -ENODEV;
- dev_warn(&wdev->dev, "Loading despite unsupported WMI interface version (%u.%u)\n",
+ dev_warn(&data->wdev->dev,
+ "Loading despite unsupported WMI interface version (%u.%u)\n",
output[MSI_PLATFORM_WMI_MAJOR_OFFSET],
output[MSI_PLATFORM_WMI_MINOR_OFFSET]);
}
@@ -391,19 +406,31 @@ static int msi_wmi_platform_init(struct wmi_device *wdev)
static int msi_wmi_platform_probe(struct wmi_device *wdev, const void *context)
{
+ struct msi_wmi_platform_data *data;
int ret;
- ret = msi_wmi_platform_init(wdev);
+ data = devm_kzalloc(&wdev->dev, sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ data->wdev = wdev;
+ dev_set_drvdata(&wdev->dev, data);
+
+ ret = devm_mutex_init(&wdev->dev, &data->wmi_lock);
if (ret < 0)
return ret;
- ret = msi_wmi_platform_ec_init(wdev);
+ ret = msi_wmi_platform_init(data);
if (ret < 0)
return ret;
- msi_wmi_platform_debugfs_init(wdev);
+ ret = msi_wmi_platform_ec_init(data);
+ if (ret < 0)
+ return ret;
- return msi_wmi_platform_hwmon_init(wdev);
+ msi_wmi_platform_debugfs_init(data);
+
+ return msi_wmi_platform_hwmon_init(data);
}
static const struct wmi_device_id msi_wmi_platform_id_table[] = {
diff --git a/drivers/platform/x86/x86-android-tablets/dmi.c b/drivers/platform/x86/x86-android-tablets/dmi.c
index 3e5fa3b..278c6d1 100644
--- a/drivers/platform/x86/x86-android-tablets/dmi.c
+++ b/drivers/platform/x86/x86-android-tablets/dmi.c
@@ -180,6 +180,18 @@ const struct dmi_system_id x86_android_tablet_ids[] __initconst = {
.driver_data = (void *)&peaq_c1010_info,
},
{
+ /* Vexia Edu Atla 10 tablet 5V version */
+ .matches = {
+ /* Having all 3 of these not set is somewhat unique */
+ DMI_MATCH(DMI_SYS_VENDOR, "To be filled by O.E.M."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "To be filled by O.E.M."),
+ DMI_MATCH(DMI_BOARD_NAME, "To be filled by O.E.M."),
+ /* Above strings are too generic, also match on BIOS date */
+ DMI_MATCH(DMI_BIOS_DATE, "05/14/2015"),
+ },
+ .driver_data = (void *)&vexia_edu_atla10_5v_info,
+ },
+ {
/* Vexia Edu Atla 10 tablet 9V version */
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
@@ -187,7 +199,7 @@ const struct dmi_system_id x86_android_tablet_ids[] __initconst = {
/* Above strings are too generic, also match on BIOS date */
DMI_MATCH(DMI_BIOS_DATE, "08/25/2014"),
},
- .driver_data = (void *)&vexia_edu_atla10_info,
+ .driver_data = (void *)&vexia_edu_atla10_9v_info,
},
{
/* Whitelabel (sold as various brands) TM800A550L */
diff --git a/drivers/platform/x86/x86-android-tablets/other.c b/drivers/platform/x86/x86-android-tablets/other.c
index 1d93d9e..f7bd9f8 100644
--- a/drivers/platform/x86/x86-android-tablets/other.c
+++ b/drivers/platform/x86/x86-android-tablets/other.c
@@ -599,62 +599,122 @@ const struct x86_dev_info whitelabel_tm800a550l_info __initconst = {
};
/*
- * Vexia EDU ATLA 10 tablet, Android 4.2 / 4.4 + Guadalinex Ubuntu tablet
+ * Vexia EDU ATLA 10 tablet 5V, Android 4.4 + Guadalinex Ubuntu tablet
* distributed to schools in the Spanish Andalucía region.
*/
-static const char * const crystal_cove_pwrsrc_psy[] = { "crystal_cove_pwrsrc" };
-
-static const struct property_entry vexia_edu_atla10_ulpmc_props[] = {
- PROPERTY_ENTRY_STRING_ARRAY("supplied-from", crystal_cove_pwrsrc_psy),
- { }
-};
-
-static const struct software_node vexia_edu_atla10_ulpmc_node = {
- .properties = vexia_edu_atla10_ulpmc_props,
-};
-
-static const char * const vexia_edu_atla10_accel_mount_matrix[] = {
- "0", "-1", "0",
- "1", "0", "0",
- "0", "0", "1"
-};
-
-static const struct property_entry vexia_edu_atla10_accel_props[] = {
- PROPERTY_ENTRY_STRING_ARRAY("mount-matrix", vexia_edu_atla10_accel_mount_matrix),
- { }
-};
-
-static const struct software_node vexia_edu_atla10_accel_node = {
- .properties = vexia_edu_atla10_accel_props,
-};
-
-static const struct property_entry vexia_edu_atla10_touchscreen_props[] = {
+static const struct property_entry vexia_edu_atla10_5v_touchscreen_props[] = {
PROPERTY_ENTRY_U32("hid-descr-addr", 0x0000),
PROPERTY_ENTRY_U32("post-reset-deassert-delay-ms", 120),
{ }
};
-static const struct software_node vexia_edu_atla10_touchscreen_node = {
- .properties = vexia_edu_atla10_touchscreen_props,
+static const struct software_node vexia_edu_atla10_5v_touchscreen_node = {
+ .properties = vexia_edu_atla10_5v_touchscreen_props,
};
-static const struct property_entry vexia_edu_atla10_pmic_props[] = {
+static const struct x86_i2c_client_info vexia_edu_atla10_5v_i2c_clients[] __initconst = {
+ {
+ /* kxcjk1013 accelerometer */
+ .board_info = {
+ .type = "kxcjk1013",
+ .addr = 0x0f,
+ .dev_name = "kxcjk1013",
+ },
+ .adapter_path = "\\_SB_.I2C3",
+ }, {
+ /* touchscreen controller */
+ .board_info = {
+ .type = "hid-over-i2c",
+ .addr = 0x38,
+ .dev_name = "FTSC1000",
+ .swnode = &vexia_edu_atla10_5v_touchscreen_node,
+ },
+ .adapter_path = "\\_SB_.I2C4",
+ .irq_data = {
+ .type = X86_ACPI_IRQ_TYPE_APIC,
+ .index = 0x44,
+ .trigger = ACPI_LEVEL_SENSITIVE,
+ .polarity = ACPI_ACTIVE_HIGH,
+ },
+ }
+};
+
+static struct gpiod_lookup_table vexia_edu_atla10_5v_ft5416_gpios = {
+ .dev_id = "i2c-FTSC1000",
+ .table = {
+ GPIO_LOOKUP("INT33FC:01", 26, "reset", GPIO_ACTIVE_LOW),
+ { }
+ },
+};
+
+static struct gpiod_lookup_table * const vexia_edu_atla10_5v_gpios[] = {
+ &vexia_edu_atla10_5v_ft5416_gpios,
+ NULL
+};
+
+const struct x86_dev_info vexia_edu_atla10_5v_info __initconst = {
+ .i2c_client_info = vexia_edu_atla10_5v_i2c_clients,
+ .i2c_client_count = ARRAY_SIZE(vexia_edu_atla10_5v_i2c_clients),
+ .gpiod_lookup_tables = vexia_edu_atla10_5v_gpios,
+};
+
+/*
+ * Vexia EDU ATLA 10 tablet 9V, Android 4.2 + Guadalinex Ubuntu tablet
+ * distributed to schools in the Spanish Andalucía region.
+ */
+static const char * const crystal_cove_pwrsrc_psy[] = { "crystal_cove_pwrsrc" };
+
+static const struct property_entry vexia_edu_atla10_9v_ulpmc_props[] = {
+ PROPERTY_ENTRY_STRING_ARRAY("supplied-from", crystal_cove_pwrsrc_psy),
+ { }
+};
+
+static const struct software_node vexia_edu_atla10_9v_ulpmc_node = {
+ .properties = vexia_edu_atla10_9v_ulpmc_props,
+};
+
+static const char * const vexia_edu_atla10_9v_accel_mount_matrix[] = {
+ "0", "-1", "0",
+ "1", "0", "0",
+ "0", "0", "1"
+};
+
+static const struct property_entry vexia_edu_atla10_9v_accel_props[] = {
+ PROPERTY_ENTRY_STRING_ARRAY("mount-matrix", vexia_edu_atla10_9v_accel_mount_matrix),
+ { }
+};
+
+static const struct software_node vexia_edu_atla10_9v_accel_node = {
+ .properties = vexia_edu_atla10_9v_accel_props,
+};
+
+static const struct property_entry vexia_edu_atla10_9v_touchscreen_props[] = {
+ PROPERTY_ENTRY_U32("hid-descr-addr", 0x0000),
+ PROPERTY_ENTRY_U32("post-reset-deassert-delay-ms", 120),
+ { }
+};
+
+static const struct software_node vexia_edu_atla10_9v_touchscreen_node = {
+ .properties = vexia_edu_atla10_9v_touchscreen_props,
+};
+
+static const struct property_entry vexia_edu_atla10_9v_pmic_props[] = {
PROPERTY_ENTRY_BOOL("linux,register-pwrsrc-power_supply"),
{ }
};
-static const struct software_node vexia_edu_atla10_pmic_node = {
- .properties = vexia_edu_atla10_pmic_props,
+static const struct software_node vexia_edu_atla10_9v_pmic_node = {
+ .properties = vexia_edu_atla10_9v_pmic_props,
};
-static const struct x86_i2c_client_info vexia_edu_atla10_i2c_clients[] __initconst = {
+static const struct x86_i2c_client_info vexia_edu_atla10_9v_i2c_clients[] __initconst = {
{
/* I2C attached embedded controller, used to access fuel-gauge */
.board_info = {
.type = "vexia_atla10_ec",
.addr = 0x76,
.dev_name = "ulpmc",
- .swnode = &vexia_edu_atla10_ulpmc_node,
+ .swnode = &vexia_edu_atla10_9v_ulpmc_node,
},
.adapter_path = "0000:00:18.1",
}, {
@@ -679,7 +739,7 @@ static const struct x86_i2c_client_info vexia_edu_atla10_i2c_clients[] __initcon
.type = "kxtj21009",
.addr = 0x0f,
.dev_name = "kxtj21009",
- .swnode = &vexia_edu_atla10_accel_node,
+ .swnode = &vexia_edu_atla10_9v_accel_node,
},
.adapter_path = "0000:00:18.5",
}, {
@@ -688,7 +748,7 @@ static const struct x86_i2c_client_info vexia_edu_atla10_i2c_clients[] __initcon
.type = "hid-over-i2c",
.addr = 0x38,
.dev_name = "FTSC1000",
- .swnode = &vexia_edu_atla10_touchscreen_node,
+ .swnode = &vexia_edu_atla10_9v_touchscreen_node,
},
.adapter_path = "0000:00:18.6",
.irq_data = {
@@ -703,7 +763,7 @@ static const struct x86_i2c_client_info vexia_edu_atla10_i2c_clients[] __initcon
.type = "intel_soc_pmic_crc",
.addr = 0x6e,
.dev_name = "intel_soc_pmic_crc",
- .swnode = &vexia_edu_atla10_pmic_node,
+ .swnode = &vexia_edu_atla10_9v_pmic_node,
},
.adapter_path = "0000:00:18.7",
.irq_data = {
@@ -715,7 +775,7 @@ static const struct x86_i2c_client_info vexia_edu_atla10_i2c_clients[] __initcon
}
};
-static const struct x86_serdev_info vexia_edu_atla10_serdevs[] __initconst = {
+static const struct x86_serdev_info vexia_edu_atla10_9v_serdevs[] __initconst = {
{
.ctrl.pci.devfn = PCI_DEVFN(0x1e, 3),
.ctrl_devname = "serial0",
@@ -723,7 +783,7 @@ static const struct x86_serdev_info vexia_edu_atla10_serdevs[] __initconst = {
},
};
-static struct gpiod_lookup_table vexia_edu_atla10_ft5416_gpios = {
+static struct gpiod_lookup_table vexia_edu_atla10_9v_ft5416_gpios = {
.dev_id = "i2c-FTSC1000",
.table = {
GPIO_LOOKUP("INT33FC:00", 60, "reset", GPIO_ACTIVE_LOW),
@@ -731,12 +791,12 @@ static struct gpiod_lookup_table vexia_edu_atla10_ft5416_gpios = {
},
};
-static struct gpiod_lookup_table * const vexia_edu_atla10_gpios[] = {
- &vexia_edu_atla10_ft5416_gpios,
+static struct gpiod_lookup_table * const vexia_edu_atla10_9v_gpios[] = {
+ &vexia_edu_atla10_9v_ft5416_gpios,
NULL
};
-static int __init vexia_edu_atla10_init(struct device *dev)
+static int __init vexia_edu_atla10_9v_init(struct device *dev)
{
struct pci_dev *pdev;
int ret;
@@ -760,13 +820,13 @@ static int __init vexia_edu_atla10_init(struct device *dev)
return 0;
}
-const struct x86_dev_info vexia_edu_atla10_info __initconst = {
- .i2c_client_info = vexia_edu_atla10_i2c_clients,
- .i2c_client_count = ARRAY_SIZE(vexia_edu_atla10_i2c_clients),
- .serdev_info = vexia_edu_atla10_serdevs,
- .serdev_count = ARRAY_SIZE(vexia_edu_atla10_serdevs),
- .gpiod_lookup_tables = vexia_edu_atla10_gpios,
- .init = vexia_edu_atla10_init,
+const struct x86_dev_info vexia_edu_atla10_9v_info __initconst = {
+ .i2c_client_info = vexia_edu_atla10_9v_i2c_clients,
+ .i2c_client_count = ARRAY_SIZE(vexia_edu_atla10_9v_i2c_clients),
+ .serdev_info = vexia_edu_atla10_9v_serdevs,
+ .serdev_count = ARRAY_SIZE(vexia_edu_atla10_9v_serdevs),
+ .gpiod_lookup_tables = vexia_edu_atla10_9v_gpios,
+ .init = vexia_edu_atla10_9v_init,
.use_pci = true,
};
diff --git a/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h b/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h
index 63a38a0..dcf8d49 100644
--- a/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h
+++ b/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h
@@ -127,7 +127,8 @@ extern const struct x86_dev_info nextbook_ares8_info;
extern const struct x86_dev_info nextbook_ares8a_info;
extern const struct x86_dev_info peaq_c1010_info;
extern const struct x86_dev_info whitelabel_tm800a550l_info;
-extern const struct x86_dev_info vexia_edu_atla10_info;
+extern const struct x86_dev_info vexia_edu_atla10_5v_info;
+extern const struct x86_dev_info vexia_edu_atla10_9v_info;
extern const struct x86_dev_info xiaomi_mipad2_info;
extern const struct dmi_system_id x86_android_tablet_ids[];
diff --git a/drivers/pmdomain/renesas/rcar-gen4-sysc.c b/drivers/pmdomain/renesas/rcar-gen4-sysc.c
index 66409cf..e001b5c 100644
--- a/drivers/pmdomain/renesas/rcar-gen4-sysc.c
+++ b/drivers/pmdomain/renesas/rcar-gen4-sysc.c
@@ -338,11 +338,6 @@ static int __init rcar_gen4_sysc_pd_init(void)
struct rcar_gen4_sysc_pd *pd;
size_t n;
- if (!area->name) {
- /* Skip NULLified area */
- continue;
- }
-
n = strlen(area->name) + 1;
pd = kzalloc(sizeof(*pd) + n, GFP_KERNEL);
if (!pd) {
diff --git a/drivers/pmdomain/renesas/rcar-sysc.c b/drivers/pmdomain/renesas/rcar-sysc.c
index dce1a6d..047495f 100644
--- a/drivers/pmdomain/renesas/rcar-sysc.c
+++ b/drivers/pmdomain/renesas/rcar-sysc.c
@@ -396,11 +396,6 @@ static int __init rcar_sysc_pd_init(void)
struct rcar_sysc_pd *pd;
size_t n;
- if (!area->name) {
- /* Skip NULLified area */
- continue;
- }
-
n = strlen(area->name) + 1;
pd = kzalloc(sizeof(*pd) + n, GFP_KERNEL);
if (!pd) {
diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c
index edb058c..439dd0b 100644
--- a/drivers/power/supply/power_supply_sysfs.c
+++ b/drivers/power/supply/power_supply_sysfs.c
@@ -33,7 +33,7 @@ struct power_supply_attr {
[POWER_SUPPLY_PROP_ ## _name] = \
{ \
.prop_name = #_name, \
- .attr_name = #_name "\0", \
+ .attr_name = #_name, \
.text_values = _text, \
.text_values_len = _len, \
}
diff --git a/drivers/pps/generators/pps_gen_tio.c b/drivers/pps/generators/pps_gen_tio.c
index 1d5ffe0..de00a85 100644
--- a/drivers/pps/generators/pps_gen_tio.c
+++ b/drivers/pps/generators/pps_gen_tio.c
@@ -230,7 +230,7 @@ static int pps_gen_tio_probe(struct platform_device *pdev)
hrtimer_setup(&tio->timer, hrtimer_callback, CLOCK_REALTIME,
HRTIMER_MODE_ABS);
spin_lock_init(&tio->lock);
- platform_set_drvdata(pdev, &tio);
+ platform_set_drvdata(pdev, tio);
return 0;
}
diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c
index 7945c6b..2ccdca4 100644
--- a/drivers/ptp/ptp_ocp.c
+++ b/drivers/ptp/ptp_ocp.c
@@ -2067,6 +2067,7 @@ ptp_ocp_signal_set(struct ptp_ocp *bp, int gen, struct ptp_ocp_signal *s)
if (!s->start) {
/* roundup() does not work on 32-bit systems */
s->start = DIV64_U64_ROUND_UP(start_ns, s->period);
+ s->start *= s->period;
s->start = ktime_add(s->start, s->phase);
}
@@ -2577,12 +2578,60 @@ static const struct ocp_sma_op ocp_fb_sma_op = {
.set_output = ptp_ocp_sma_fb_set_output,
};
+static int
+ptp_ocp_sma_adva_set_output(struct ptp_ocp *bp, int sma_nr, u32 val)
+{
+ u32 reg, mask, shift;
+ unsigned long flags;
+ u32 __iomem *gpio;
+
+ gpio = sma_nr > 2 ? &bp->sma_map1->gpio2 : &bp->sma_map2->gpio2;
+ shift = sma_nr & 1 ? 0 : 16;
+
+ mask = 0xffff << (16 - shift);
+
+ spin_lock_irqsave(&bp->lock, flags);
+
+ reg = ioread32(gpio);
+ reg = (reg & mask) | (val << shift);
+
+ iowrite32(reg, gpio);
+
+ spin_unlock_irqrestore(&bp->lock, flags);
+
+ return 0;
+}
+
+static int
+ptp_ocp_sma_adva_set_inputs(struct ptp_ocp *bp, int sma_nr, u32 val)
+{
+ u32 reg, mask, shift;
+ unsigned long flags;
+ u32 __iomem *gpio;
+
+ gpio = sma_nr > 2 ? &bp->sma_map2->gpio1 : &bp->sma_map1->gpio1;
+ shift = sma_nr & 1 ? 0 : 16;
+
+ mask = 0xffff << (16 - shift);
+
+ spin_lock_irqsave(&bp->lock, flags);
+
+ reg = ioread32(gpio);
+ reg = (reg & mask) | (val << shift);
+
+ iowrite32(reg, gpio);
+
+ spin_unlock_irqrestore(&bp->lock, flags);
+
+ return 0;
+}
+
static const struct ocp_sma_op ocp_adva_sma_op = {
.tbl = { ptp_ocp_adva_sma_in, ptp_ocp_adva_sma_out },
.init = ptp_ocp_sma_fb_init,
.get = ptp_ocp_sma_fb_get,
- .set_inputs = ptp_ocp_sma_fb_set_inputs,
- .set_output = ptp_ocp_sma_fb_set_output,
+ .set_inputs = ptp_ocp_sma_adva_set_inputs,
+ .set_output = ptp_ocp_sma_adva_set_output,
};
static int
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index a40c511..0387bd8 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -322,7 +322,7 @@ static int __pwm_set_waveform(struct pwm_device *pwm,
const struct pwm_ops *ops = chip->ops;
char wfhw[WFHWSIZE];
struct pwm_waveform wf_rounded;
- int err;
+ int err, ret_tohw;
BUG_ON(WFHWSIZE < ops->sizeof_wfhw);
@@ -332,16 +332,16 @@ static int __pwm_set_waveform(struct pwm_device *pwm,
if (!pwm_wf_valid(wf))
return -EINVAL;
- err = __pwm_round_waveform_tohw(chip, pwm, wf, &wfhw);
- if (err)
- return err;
+ ret_tohw = __pwm_round_waveform_tohw(chip, pwm, wf, &wfhw);
+ if (ret_tohw < 0)
+ return ret_tohw;
if ((IS_ENABLED(CONFIG_PWM_DEBUG) || exact) && wf->period_length_ns) {
err = __pwm_round_waveform_fromhw(chip, pwm, &wfhw, &wf_rounded);
if (err)
return err;
- if (IS_ENABLED(CONFIG_PWM_DEBUG) && !pwm_check_rounding(wf, &wf_rounded))
+ if (IS_ENABLED(CONFIG_PWM_DEBUG) && ret_tohw == 0 && !pwm_check_rounding(wf, &wf_rounded))
dev_err(&chip->dev, "Wrong rounding: requested %llu/%llu [+%llu], result %llu/%llu [+%llu]\n",
wf->duty_length_ns, wf->period_length_ns, wf->duty_offset_ns,
wf_rounded.duty_length_ns, wf_rounded.period_length_ns, wf_rounded.duty_offset_ns);
@@ -382,7 +382,8 @@ static int __pwm_set_waveform(struct pwm_device *pwm,
wf_rounded.duty_length_ns, wf_rounded.period_length_ns, wf_rounded.duty_offset_ns,
wf_set.duty_length_ns, wf_set.period_length_ns, wf_set.duty_offset_ns);
}
- return 0;
+
+ return ret_tohw;
}
/**
diff --git a/drivers/pwm/pwm-axi-pwmgen.c b/drivers/pwm/pwm-axi-pwmgen.c
index 4259a0db..4337c8f 100644
--- a/drivers/pwm/pwm-axi-pwmgen.c
+++ b/drivers/pwm/pwm-axi-pwmgen.c
@@ -75,6 +75,7 @@ static int axi_pwmgen_round_waveform_tohw(struct pwm_chip *chip,
{
struct axi_pwmgen_waveform *wfhw = _wfhw;
struct axi_pwmgen_ddata *ddata = axi_pwmgen_ddata_from_chip(chip);
+ int ret = 0;
if (wf->period_length_ns == 0) {
*wfhw = (struct axi_pwmgen_waveform){
@@ -91,12 +92,15 @@ static int axi_pwmgen_round_waveform_tohw(struct pwm_chip *chip,
if (wfhw->period_cnt == 0) {
/*
* The specified period is too short for the hardware.
- * Let's round .duty_cycle down to 0 to get a (somewhat)
- * valid result.
+ * So round up .period_cnt to 1 (i.e. the smallest
+ * possible period). With .duty_cycle and .duty_offset
+ * being less than or equal to .period, their rounded
+ * value must be 0.
*/
wfhw->period_cnt = 1;
wfhw->duty_cycle_cnt = 0;
wfhw->duty_offset_cnt = 0;
+ ret = 1;
} else {
wfhw->duty_cycle_cnt = min_t(u64,
mul_u64_u32_div(wf->duty_length_ns, ddata->clk_rate_hz, NSEC_PER_SEC),
@@ -111,7 +115,7 @@ static int axi_pwmgen_round_waveform_tohw(struct pwm_chip *chip,
pwm->hwpwm, wf->duty_length_ns, wf->period_length_ns, wf->duty_offset_ns,
ddata->clk_rate_hz, wfhw->period_cnt, wfhw->duty_cycle_cnt, wfhw->duty_offset_cnt);
- return 0;
+ return ret;
}
static int axi_pwmgen_round_waveform_fromhw(struct pwm_chip *chip, struct pwm_device *pwm,
diff --git a/drivers/pwm/pwm-fsl-ftm.c b/drivers/pwm/pwm-fsl-ftm.c
index 2510c10..c45a5fc 100644
--- a/drivers/pwm/pwm-fsl-ftm.c
+++ b/drivers/pwm/pwm-fsl-ftm.c
@@ -118,6 +118,9 @@ static unsigned int fsl_pwm_ticks_to_ns(struct fsl_pwm_chip *fpc,
unsigned long long exval;
rate = clk_get_rate(fpc->clk[fpc->period.clk_select]);
+ if (rate >> fpc->period.clk_ps == 0)
+ return 0;
+
exval = ticks;
exval *= 1000000000UL;
do_div(exval, rate >> fpc->period.clk_ps);
@@ -190,6 +193,9 @@ static unsigned int fsl_pwm_calculate_duty(struct fsl_pwm_chip *fpc,
unsigned int period = fpc->period.mod_period + 1;
unsigned int period_ns = fsl_pwm_ticks_to_ns(fpc, period);
+ if (!period_ns)
+ return 0;
+
duty = (unsigned long long)duty_ns * period;
do_div(duty, period_ns);
diff --git a/drivers/pwm/pwm-mediatek.c b/drivers/pwm/pwm-mediatek.c
index 01dfa0f..7eaab58 100644
--- a/drivers/pwm/pwm-mediatek.c
+++ b/drivers/pwm/pwm-mediatek.c
@@ -121,21 +121,25 @@ static int pwm_mediatek_config(struct pwm_chip *chip, struct pwm_device *pwm,
struct pwm_mediatek_chip *pc = to_pwm_mediatek_chip(chip);
u32 clkdiv = 0, cnt_period, cnt_duty, reg_width = PWMDWIDTH,
reg_thres = PWMTHRES;
+ unsigned long clk_rate;
u64 resolution;
int ret;
ret = pwm_mediatek_clk_enable(chip, pwm);
-
if (ret < 0)
return ret;
+ clk_rate = clk_get_rate(pc->clk_pwms[pwm->hwpwm]);
+ if (!clk_rate)
+ return -EINVAL;
+
/* Make sure we use the bus clock and not the 26MHz clock */
if (pc->soc->has_ck_26m_sel)
writel(0, pc->regs + PWM_CK_26M_SEL);
/* Using resolution in picosecond gets accuracy higher */
resolution = (u64)NSEC_PER_SEC * 1000;
- do_div(resolution, clk_get_rate(pc->clk_pwms[pwm->hwpwm]));
+ do_div(resolution, clk_rate);
cnt_period = DIV_ROUND_CLOSEST_ULL((u64)period_ns * 1000, resolution);
while (cnt_period > 8191) {
diff --git a/drivers/pwm/pwm-rcar.c b/drivers/pwm/pwm-rcar.c
index 2261789..578dbdd 100644
--- a/drivers/pwm/pwm-rcar.c
+++ b/drivers/pwm/pwm-rcar.c
@@ -8,6 +8,7 @@
* - The hardware cannot generate a 0% duty cycle.
*/
+#include <linux/bitfield.h>
#include <linux/clk.h>
#include <linux/err.h>
#include <linux/io.h>
@@ -102,23 +103,24 @@ static void rcar_pwm_set_clock_control(struct rcar_pwm_chip *rp,
rcar_pwm_write(rp, value, RCAR_PWMCR);
}
-static int rcar_pwm_set_counter(struct rcar_pwm_chip *rp, int div, int duty_ns,
- int period_ns)
+static int rcar_pwm_set_counter(struct rcar_pwm_chip *rp, int div, u64 duty_ns,
+ u64 period_ns)
{
- unsigned long long one_cycle, tmp; /* 0.01 nanoseconds */
+ unsigned long long tmp;
unsigned long clk_rate = clk_get_rate(rp->clk);
u32 cyc, ph;
- one_cycle = NSEC_PER_SEC * 100ULL << div;
- do_div(one_cycle, clk_rate);
+ /* div <= 24 == RCAR_PWM_MAX_DIVISION, so the shift doesn't overflow. */
+ tmp = mul_u64_u64_div_u64(period_ns, clk_rate, (u64)NSEC_PER_SEC << div);
+ if (tmp > FIELD_MAX(RCAR_PWMCNT_CYC0_MASK))
+ tmp = FIELD_MAX(RCAR_PWMCNT_CYC0_MASK);
- tmp = period_ns * 100ULL;
- do_div(tmp, one_cycle);
- cyc = (tmp << RCAR_PWMCNT_CYC0_SHIFT) & RCAR_PWMCNT_CYC0_MASK;
+ cyc = FIELD_PREP(RCAR_PWMCNT_CYC0_MASK, tmp);
- tmp = duty_ns * 100ULL;
- do_div(tmp, one_cycle);
- ph = tmp & RCAR_PWMCNT_PH0_MASK;
+ tmp = mul_u64_u64_div_u64(duty_ns, clk_rate, (u64)NSEC_PER_SEC << div);
+ if (tmp > FIELD_MAX(RCAR_PWMCNT_PH0_MASK))
+ tmp = FIELD_MAX(RCAR_PWMCNT_PH0_MASK);
+ ph = FIELD_PREP(RCAR_PWMCNT_PH0_MASK, tmp);
/* Avoid prohibited setting */
if (cyc == 0 || ph == 0)
diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c
index a59de4d..ec2c05c 100644
--- a/drivers/pwm/pwm-stm32.c
+++ b/drivers/pwm/pwm-stm32.c
@@ -103,22 +103,16 @@ static int stm32_pwm_round_waveform_tohw(struct pwm_chip *chip,
if (ret)
goto out;
- /*
- * calculate the best value for ARR for the given PSC, refuse if
- * the resulting period gets bigger than the requested one.
- */
arr = mul_u64_u64_div_u64(wf->period_length_ns, rate,
(u64)NSEC_PER_SEC * (wfhw->psc + 1));
if (arr <= wfhw->arr) {
/*
- * requested period is small than the currently
+ * requested period is smaller than the currently
* configured and unchangable period, report back the smallest
- * possible period, i.e. the current state; Initialize
- * ccr to anything valid.
+ * possible period, i.e. the current state and return 1
+ * to indicate the wrong rounding direction.
*/
- wfhw->ccr = 0;
ret = 1;
- goto out;
}
} else {
diff --git a/drivers/ras/amd/atl/internal.h b/drivers/ras/amd/atl/internal.h
index f9be26d..d096b58 100644
--- a/drivers/ras/amd/atl/internal.h
+++ b/drivers/ras/amd/atl/internal.h
@@ -362,4 +362,7 @@ static inline void atl_debug_on_bad_intlv_mode(struct addr_ctx *ctx)
atl_debug(ctx, "Unrecognized interleave mode: %u", ctx->map.intlv_mode);
}
+#define MI300_UMC_MCA_COL GENMASK(5, 1)
+#define MI300_UMC_MCA_ROW13 BIT(23)
+
#endif /* __AMD_ATL_INTERNAL_H__ */
diff --git a/drivers/ras/amd/atl/umc.c b/drivers/ras/amd/atl/umc.c
index dc8aa12..6e072b7 100644
--- a/drivers/ras/amd/atl/umc.c
+++ b/drivers/ras/amd/atl/umc.c
@@ -229,7 +229,6 @@ int get_umc_info_mi300(void)
* Additionally, the PC and Bank bits may be hashed. This must be accounted for before
* reconstructing the normalized address.
*/
-#define MI300_UMC_MCA_COL GENMASK(5, 1)
#define MI300_UMC_MCA_BANK GENMASK(9, 6)
#define MI300_UMC_MCA_ROW GENMASK(24, 10)
#define MI300_UMC_MCA_PC BIT(25)
@@ -320,7 +319,7 @@ static unsigned long convert_dram_to_norm_addr_mi300(unsigned long addr)
* See amd_atl::convert_dram_to_norm_addr_mi300() for MI300 address formats.
*/
#define MI300_NUM_COL BIT(HWEIGHT(MI300_UMC_MCA_COL))
-static void retire_row_mi300(struct atl_err *a_err)
+static void _retire_row_mi300(struct atl_err *a_err)
{
unsigned long addr;
struct page *p;
@@ -351,6 +350,22 @@ static void retire_row_mi300(struct atl_err *a_err)
}
}
+/*
+ * In addition to the column bits, the row[13] bit should also be included when
+ * calculating addresses affected by a physical row.
+ *
+ * Instead of running through another loop over a single bit, just run through
+ * the column bits twice and flip the row[13] bit in-between.
+ *
+ * See MI300_UMC_MCA_ROW for the row bits in MCA_ADDR_UMC value.
+ */
+static void retire_row_mi300(struct atl_err *a_err)
+{
+ _retire_row_mi300(a_err);
+ a_err->addr ^= MI300_UMC_MCA_ROW13;
+ _retire_row_mi300(a_err);
+}
+
void amd_retire_dram_row(struct atl_err *a_err)
{
if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous)
diff --git a/drivers/ras/amd/fmpm.c b/drivers/ras/amd/fmpm.c
index 90de737..8877c6f 100644
--- a/drivers/ras/amd/fmpm.c
+++ b/drivers/ras/amd/fmpm.c
@@ -250,6 +250,13 @@ static bool rec_has_valid_entries(struct fru_rec *rec)
return true;
}
+/*
+ * Row retirement is done on MI300 systems, and some bits are 'don't
+ * care' for comparing addresses with unique physical rows. This
+ * includes all column bits and the row[13] bit.
+ */
+#define MASK_ADDR(addr) ((addr) & ~(MI300_UMC_MCA_ROW13 | MI300_UMC_MCA_COL))
+
static bool fpds_equal(struct cper_fru_poison_desc *old, struct cper_fru_poison_desc *new)
{
/*
@@ -258,7 +265,7 @@ static bool fpds_equal(struct cper_fru_poison_desc *old, struct cper_fru_poison_
*
* Also, order the checks from most->least likely to fail to shortcut the code.
*/
- if (old->addr != new->addr)
+ if (MASK_ADDR(old->addr) != MASK_ADDR(new->addr))
return false;
if (old->hw_id != new->hw_id)
diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
index 21fa7ac..4904b83 100644
--- a/drivers/s390/virtio/virtio_ccw.c
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -302,11 +302,17 @@ static struct airq_info *new_airq_info(int index)
static unsigned long *get_airq_indicator(struct virtqueue *vqs[], int nvqs,
u64 *first, void **airq_info)
{
- int i, j;
+ int i, j, queue_idx, highest_queue_idx = -1;
struct airq_info *info;
unsigned long *indicator_addr = NULL;
unsigned long bit, flags;
+ /* Array entries without an actual queue pointer must be ignored. */
+ for (i = 0; i < nvqs; i++) {
+ if (vqs[i])
+ highest_queue_idx++;
+ }
+
for (i = 0; i < MAX_AIRQ_AREAS && !indicator_addr; i++) {
mutex_lock(&airq_areas_lock);
if (!airq_areas[i])
@@ -316,7 +322,7 @@ static unsigned long *get_airq_indicator(struct virtqueue *vqs[], int nvqs,
if (!info)
return NULL;
write_lock_irqsave(&info->lock, flags);
- bit = airq_iv_alloc(info->aiv, nvqs);
+ bit = airq_iv_alloc(info->aiv, highest_queue_idx + 1);
if (bit == -1UL) {
/* Not enough vacancies. */
write_unlock_irqrestore(&info->lock, flags);
@@ -325,8 +331,10 @@ static unsigned long *get_airq_indicator(struct virtqueue *vqs[], int nvqs,
*first = bit;
*airq_info = info;
indicator_addr = info->aiv->vector;
- for (j = 0; j < nvqs; j++) {
- airq_iv_set_ptr(info->aiv, bit + j,
+ for (j = 0, queue_idx = 0; j < nvqs; j++) {
+ if (!vqs[j])
+ continue;
+ airq_iv_set_ptr(info->aiv, bit + queue_idx++,
(unsigned long)vqs[j]);
}
write_unlock_irqrestore(&info->lock, flags);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 5cb1d3d..944cf2f 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -935,8 +935,28 @@ static void hisi_sas_phyup_work_common(struct work_struct *work,
container_of(work, typeof(*phy), works[event]);
struct hisi_hba *hisi_hba = phy->hisi_hba;
struct asd_sas_phy *sas_phy = &phy->sas_phy;
+ struct asd_sas_port *sas_port = sas_phy->port;
+ struct hisi_sas_port *port = phy->port;
+ struct device *dev = hisi_hba->dev;
+ struct domain_device *port_dev;
int phy_no = sas_phy->id;
+ if (!test_bit(HISI_SAS_RESETTING_BIT, &hisi_hba->flags) &&
+ sas_port && port && (port->id != phy->port_id)) {
+ dev_info(dev, "phy%d's hw port id changed from %d to %llu\n",
+ phy_no, port->id, phy->port_id);
+ port_dev = sas_port->port_dev;
+ if (port_dev && !dev_is_expander(port_dev->dev_type)) {
+ /*
+ * Set the device state to gone to block
+ * sending IO to the device.
+ */
+ set_bit(SAS_DEV_GONE, &port_dev->state);
+ hisi_sas_notify_phy_event(phy, HISI_PHYE_LINK_RESET);
+ return;
+ }
+ }
+
phy->wait_phyup_cnt = 0;
if (phy->identify.target_port_protocols == SAS_PROTOCOL_SSP)
hisi_hba->hw->sl_notify_ssp(hisi_hba, phy_no);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index a1fc400..1e98309 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -2501,6 +2501,7 @@ static void prep_ata_v2_hw(struct hisi_hba *hisi_hba,
struct hisi_sas_port *port = to_hisi_sas_port(sas_port);
struct sas_ata_task *ata_task = &task->ata_task;
struct sas_tmf_task *tmf = slot->tmf;
+ int phy_id;
u8 *buf_cmd;
int has_data = 0, hdr_tag = 0;
u32 dw0, dw1 = 0, dw2 = 0;
@@ -2508,10 +2509,14 @@ static void prep_ata_v2_hw(struct hisi_hba *hisi_hba,
/* create header */
/* dw0 */
dw0 = port->id << CMD_HDR_PORT_OFF;
- if (parent_dev && dev_is_expander(parent_dev->dev_type))
+ if (parent_dev && dev_is_expander(parent_dev->dev_type)) {
dw0 |= 3 << CMD_HDR_CMD_OFF;
- else
+ } else {
+ phy_id = device->phy->identify.phy_identifier;
+ dw0 |= (1U << phy_id) << CMD_HDR_PHY_ID_OFF;
+ dw0 |= CMD_HDR_FORCE_PHY_MSK;
dw0 |= 4 << CMD_HDR_CMD_OFF;
+ }
if (tmf && ata_task->force_phy) {
dw0 |= CMD_HDR_FORCE_PHY_MSK;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 2684d64..08dac9a 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -359,6 +359,10 @@
#define CMD_HDR_RESP_REPORT_MSK (0x1 << CMD_HDR_RESP_REPORT_OFF)
#define CMD_HDR_TLR_CTRL_OFF 6
#define CMD_HDR_TLR_CTRL_MSK (0x3 << CMD_HDR_TLR_CTRL_OFF)
+#define CMD_HDR_PHY_ID_OFF 8
+#define CMD_HDR_PHY_ID_MSK (0x1ff << CMD_HDR_PHY_ID_OFF)
+#define CMD_HDR_FORCE_PHY_OFF 17
+#define CMD_HDR_FORCE_PHY_MSK (0x1U << CMD_HDR_FORCE_PHY_OFF)
#define CMD_HDR_PORT_OFF 18
#define CMD_HDR_PORT_MSK (0xf << CMD_HDR_PORT_OFF)
#define CMD_HDR_PRIORITY_OFF 27
@@ -1429,15 +1433,21 @@ static void prep_ata_v3_hw(struct hisi_hba *hisi_hba,
struct hisi_sas_cmd_hdr *hdr = slot->cmd_hdr;
struct asd_sas_port *sas_port = device->port;
struct hisi_sas_port *port = to_hisi_sas_port(sas_port);
+ int phy_id;
u8 *buf_cmd;
int has_data = 0, hdr_tag = 0;
u32 dw1 = 0, dw2 = 0;
hdr->dw0 = cpu_to_le32(port->id << CMD_HDR_PORT_OFF);
- if (parent_dev && dev_is_expander(parent_dev->dev_type))
+ if (parent_dev && dev_is_expander(parent_dev->dev_type)) {
hdr->dw0 |= cpu_to_le32(3 << CMD_HDR_CMD_OFF);
- else
+ } else {
+ phy_id = device->phy->identify.phy_identifier;
+ hdr->dw0 |= cpu_to_le32((1U << phy_id)
+ << CMD_HDR_PHY_ID_OFF);
+ hdr->dw0 |= CMD_HDR_FORCE_PHY_MSK;
hdr->dw0 |= cpu_to_le32(4U << CMD_HDR_CMD_OFF);
+ }
switch (task->data_dir) {
case DMA_TO_DEVICE:
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index 088cc40..8ee2bfe 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -23,8 +23,8 @@
/*
* MegaRAID SAS Driver meta data
*/
-#define MEGASAS_VERSION "07.727.03.00-rc1"
-#define MEGASAS_RELDATE "Oct 03, 2023"
+#define MEGASAS_VERSION "07.734.00.00-rc1"
+#define MEGASAS_RELDATE "Apr 03, 2025"
#define MEGASAS_MSIX_NAME_LEN 32
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index c20447b..5e33d41 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -2103,6 +2103,9 @@ static int megasas_sdev_configure(struct scsi_device *sdev,
/* This sdev property may change post OCR */
megasas_set_dynamic_target_properties(sdev, lim, is_target_prop);
+ if (!MEGASAS_IS_LOGICAL(sdev))
+ sdev->no_vpd_size = 1;
+
mutex_unlock(&instance->reset_mutex);
return 0;
@@ -3662,8 +3665,10 @@ megasas_complete_cmd(struct megasas_instance *instance, struct megasas_cmd *cmd,
case MFI_STAT_SCSI_IO_FAILED:
case MFI_STAT_LD_INIT_IN_PROGRESS:
- cmd->scmd->result =
- (DID_ERROR << 16) | hdr->scsi_status;
+ if (hdr->scsi_status == 0xf0)
+ cmd->scmd->result = (DID_ERROR << 16) | SAM_STAT_CHECK_CONDITION;
+ else
+ cmd->scmd->result = (DID_ERROR << 16) | hdr->scsi_status;
break;
case MFI_STAT_SCSI_DONE_WITH_ERROR:
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 721860c..a6794f4 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -2043,7 +2043,10 @@ map_cmd_status(struct fusion_context *fusion,
case MFI_STAT_SCSI_IO_FAILED:
case MFI_STAT_LD_INIT_IN_PROGRESS:
- scmd->result = (DID_ERROR << 16) | ext_status;
+ if (ext_status == 0xf0)
+ scmd->result = (DID_ERROR << 16) | SAM_STAT_CHECK_CONDITION;
+ else
+ scmd->result = (DID_ERROR << 16) | ext_status;
break;
case MFI_STAT_SCSI_DONE_WITH_ERROR:
diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c
index 3fcb1ad..1d7901a 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_fw.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c
@@ -174,6 +174,9 @@ static void mpi3mr_print_event_data(struct mpi3mr_ioc *mrioc,
char *desc = NULL;
u16 event;
+ if (!(mrioc->logging_level & MPI3_DEBUG_EVENT))
+ return;
+
event = event_reply->event;
switch (event) {
@@ -451,6 +454,7 @@ int mpi3mr_process_admin_reply_q(struct mpi3mr_ioc *mrioc)
return 0;
}
+ atomic_set(&mrioc->admin_pend_isr, 0);
reply_desc = (struct mpi3_default_reply_descriptor *)mrioc->admin_reply_base +
admin_reply_ci;
@@ -565,7 +569,7 @@ int mpi3mr_process_op_reply_q(struct mpi3mr_ioc *mrioc,
WRITE_ONCE(op_req_q->ci, le16_to_cpu(reply_desc->request_queue_ci));
mpi3mr_process_op_reply_desc(mrioc, reply_desc, &reply_dma,
reply_qidx);
- atomic_dec(&op_reply_q->pend_ios);
+
if (reply_dma)
mpi3mr_repost_reply_buf(mrioc, reply_dma);
num_op_reply++;
@@ -2925,6 +2929,7 @@ static int mpi3mr_setup_admin_qpair(struct mpi3mr_ioc *mrioc)
mrioc->admin_reply_ci = 0;
mrioc->admin_reply_ephase = 1;
atomic_set(&mrioc->admin_reply_q_in_use, 0);
+ atomic_set(&mrioc->admin_pend_isr, 0);
if (!mrioc->admin_req_base) {
mrioc->admin_req_base = dma_alloc_coherent(&mrioc->pdev->dev,
@@ -4653,6 +4658,7 @@ void mpi3mr_memset_buffers(struct mpi3mr_ioc *mrioc)
if (mrioc->admin_reply_base)
memset(mrioc->admin_reply_base, 0, mrioc->admin_reply_q_sz);
atomic_set(&mrioc->admin_reply_q_in_use, 0);
+ atomic_set(&mrioc->admin_pend_isr, 0);
if (mrioc->init_cmds.reply) {
memset(mrioc->init_cmds.reply, 0, sizeof(*mrioc->init_cmds.reply));
diff --git a/drivers/scsi/myrb.c b/drivers/scsi/myrb.c
index dc4bd42..486db5b 100644
--- a/drivers/scsi/myrb.c
+++ b/drivers/scsi/myrb.c
@@ -891,7 +891,7 @@ static bool myrb_enable_mmio(struct myrb_hba *cb, mbox_mmio_init_t mmio_init_fn)
status = mmio_init_fn(pdev, base, &mbox);
if (status != MYRB_STATUS_SUCCESS) {
dev_err(&pdev->dev,
- "Failed to enable mailbox, statux %02X\n",
+ "Failed to enable mailbox, status %02X\n",
status);
return false;
}
diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c
index 183ce00..f706787 100644
--- a/drivers/scsi/pm8001/pm8001_sas.c
+++ b/drivers/scsi/pm8001/pm8001_sas.c
@@ -766,6 +766,7 @@ static void pm8001_dev_gone_notify(struct domain_device *dev)
spin_lock_irqsave(&pm8001_ha->lock, flags);
}
PM8001_CHIP_DISP->dereg_dev_req(pm8001_ha, device_id);
+ pm8001_ha->phy[pm8001_dev->attached_phy].phy_attached = 0;
pm8001_free_dev(pm8001_dev);
} else {
pm8001_dbg(pm8001_ha, DISC, "Found dev has gone.\n");
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 53daf92..518a252 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -707,26 +707,23 @@ void scsi_cdl_check(struct scsi_device *sdev)
*/
int scsi_cdl_enable(struct scsi_device *sdev, bool enable)
{
- struct scsi_mode_data data;
- struct scsi_sense_hdr sshdr;
- struct scsi_vpd *vpd;
- bool is_ata = false;
char buf[64];
+ bool is_ata;
int ret;
if (!sdev->cdl_supported)
return -EOPNOTSUPP;
rcu_read_lock();
- vpd = rcu_dereference(sdev->vpd_pg89);
- if (vpd)
- is_ata = true;
+ is_ata = rcu_dereference(sdev->vpd_pg89);
rcu_read_unlock();
/*
* For ATA devices, CDL needs to be enabled with a SET FEATURES command.
*/
if (is_ata) {
+ struct scsi_mode_data data;
+ struct scsi_sense_hdr sshdr;
char *buf_data;
int len;
@@ -735,16 +732,30 @@ int scsi_cdl_enable(struct scsi_device *sdev, bool enable)
if (ret)
return -EINVAL;
- /* Enable CDL using the ATA feature page */
+ /* Enable or disable CDL using the ATA feature page */
len = min_t(size_t, sizeof(buf),
data.length - data.header_length -
data.block_descriptor_length);
buf_data = buf + data.header_length +
data.block_descriptor_length;
- if (enable)
- buf_data[4] = 0x02;
- else
- buf_data[4] = 0;
+
+ /*
+ * If we want to enable CDL and CDL is already enabled on the
+ * device, do nothing. This avoids needlessly resetting the CDL
+ * statistics on the device as that is implied by the CDL enable
+ * action. Similar to this, there is no need to do anything if
+ * we want to disable CDL and CDL is already disabled.
+ */
+ if (enable) {
+ if ((buf_data[4] & 0x03) == 0x02)
+ goto out;
+ buf_data[4] &= ~0x03;
+ buf_data[4] |= 0x02;
+ } else {
+ if ((buf_data[4] & 0x03) == 0x00)
+ goto out;
+ buf_data[4] &= ~0x03;
+ }
ret = scsi_mode_select(sdev, 1, 0, buf_data, len, 5 * HZ, 3,
&data, &sshdr);
@@ -756,6 +767,7 @@ int scsi_cdl_enable(struct scsi_device *sdev, bool enable)
}
}
+out:
sdev->cdl_enable = enable;
return 0;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 0d29470..1b43013 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1253,8 +1253,12 @@ EXPORT_SYMBOL_GPL(scsi_alloc_request);
*/
static void scsi_cleanup_rq(struct request *rq)
{
+ struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
+
+ cmd->flags = 0;
+
if (rq->rq_flags & RQF_DONTPREP) {
- scsi_mq_uninit_cmd(blk_mq_rq_to_pdu(rq));
+ scsi_mq_uninit_cmd(cmd);
rq->rq_flags &= ~RQF_DONTPREP;
}
}
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 9c347c6..0b8c91b 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -3182,11 +3182,14 @@ iscsi_set_host_param(struct iscsi_transport *transport,
}
/* see similar check in iscsi_if_set_param() */
- if (strlen(data) > ev->u.set_host_param.len)
- return -EINVAL;
+ if (strlen(data) > ev->u.set_host_param.len) {
+ err = -EINVAL;
+ goto out;
+ }
err = transport->set_host_param(shost, ev->u.set_host_param.param,
data, ev->u.set_host_param.len);
+out:
scsi_host_put(shost);
return err;
}
diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c
index 64f6b22..aeb58a9 100644
--- a/drivers/scsi/scsi_transport_srp.c
+++ b/drivers/scsi/scsi_transport_srp.c
@@ -388,7 +388,7 @@ static void srp_reconnect_work(struct work_struct *work)
"reconnect attempt %d failed (%d)\n",
++rport->failed_reconnects, res);
delay = rport->reconnect_delay *
- min(100, max(1, rport->failed_reconnects - 10));
+ clamp(rport->failed_reconnects - 10, 1, 100);
if (delay > 0)
queue_delayed_work(system_long_wq,
&rport->reconnect_work, delay * HZ);
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 88135fd..8a26eca 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -19,6 +19,7 @@
#include <linux/bcd.h>
#include <linux/reboot.h>
#include <linux/cciss_ioctl.h>
+#include <linux/crash_dump.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_device.h>
@@ -5246,7 +5247,7 @@ static void pqi_calculate_io_resources(struct pqi_ctrl_info *ctrl_info)
ctrl_info->error_buffer_length =
ctrl_info->max_io_slots * PQI_ERROR_BUFFER_ELEMENT_LENGTH;
- if (reset_devices)
+ if (is_kdump_kernel())
max_transfer_size = min(ctrl_info->max_transfer_size,
PQI_MAX_TRANSFER_SIZE_KDUMP);
else
@@ -5275,7 +5276,7 @@ static void pqi_calculate_queue_resources(struct pqi_ctrl_info *ctrl_info)
u16 num_elements_per_iq;
u16 num_elements_per_oq;
- if (reset_devices) {
+ if (is_kdump_kernel()) {
num_queue_groups = 1;
} else {
int num_cpus;
@@ -8288,12 +8289,12 @@ static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info)
u32 product_id;
if (reset_devices) {
- if (pqi_is_fw_triage_supported(ctrl_info)) {
+ if (is_kdump_kernel() && pqi_is_fw_triage_supported(ctrl_info)) {
rc = sis_wait_for_fw_triage_completion(ctrl_info);
if (rc)
return rc;
}
- if (sis_is_ctrl_logging_supported(ctrl_info)) {
+ if (is_kdump_kernel() && sis_is_ctrl_logging_supported(ctrl_info)) {
sis_notify_kdump(ctrl_info);
rc = sis_wait_for_ctrl_logging_completion(ctrl_info);
if (rc)
@@ -8344,7 +8345,7 @@ static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info)
ctrl_info->product_id = (u8)product_id;
ctrl_info->product_revision = (u8)(product_id >> 8);
- if (reset_devices) {
+ if (is_kdump_kernel()) {
if (ctrl_info->max_outstanding_requests >
PQI_MAX_OUTSTANDING_REQUESTS_KDUMP)
ctrl_info->max_outstanding_requests =
@@ -8480,7 +8481,7 @@ static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info)
if (rc)
return rc;
- if (ctrl_info->ctrl_logging_supported && !reset_devices) {
+ if (ctrl_info->ctrl_logging_supported && !is_kdump_kernel()) {
pqi_host_setup_buffer(ctrl_info, &ctrl_info->ctrl_log_memory, PQI_CTRL_LOG_TOTAL_SIZE, PQI_CTRL_LOG_MIN_SIZE);
pqi_host_memory_update(ctrl_info, &ctrl_info->ctrl_log_memory, PQI_VENDOR_GENERAL_CTRL_LOG_MEMORY_UPDATE);
}
diff --git a/drivers/soc/samsung/exynos-usi.c b/drivers/soc/samsung/exynos-usi.c
index c5661ac..5f7bdf3 100644
--- a/drivers/soc/samsung/exynos-usi.c
+++ b/drivers/soc/samsung/exynos-usi.c
@@ -233,7 +233,7 @@ static void exynos_usi_unconfigure(void *data)
/* Make sure that we've stopped providing the clock to USI IP */
val = readl(usi->regs + USI_OPTION);
val &= ~USI_OPTION_CLKREQ_ON;
- val |= ~USI_OPTION_CLKSTOP_ON;
+ val |= USI_OPTION_CLKSTOP_ON;
writel(val, usi->regs + USI_OPTION);
/* Set USI block state to reset */
diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 6f8a200..39aecd3 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -122,6 +122,10 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
set_bit(SDW_GROUP13_DEV_NUM, bus->assigned);
set_bit(SDW_MASTER_DEV_NUM, bus->assigned);
+ ret = sdw_irq_create(bus, fwnode);
+ if (ret)
+ return ret;
+
/*
* SDW is an enumerable bus, but devices can be powered off. So,
* they won't be able to report as present.
@@ -138,6 +142,7 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
if (ret < 0) {
dev_err(bus->dev, "Finding slaves failed:%d\n", ret);
+ sdw_irq_delete(bus);
return ret;
}
@@ -156,10 +161,6 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
bus->params.curr_bank = SDW_BANK0;
bus->params.next_bank = SDW_BANK1;
- ret = sdw_irq_create(bus, fwnode);
- if (ret)
- return ret;
-
return 0;
}
EXPORT_SYMBOL(sdw_bus_master_add);
diff --git a/drivers/spi/spi-fsl-qspi.c b/drivers/spi/spi-fsl-qspi.c
index 5c59fdd..b5ecffc 100644
--- a/drivers/spi/spi-fsl-qspi.c
+++ b/drivers/spi/spi-fsl-qspi.c
@@ -949,24 +949,20 @@ static int fsl_qspi_probe(struct platform_device *pdev)
ret = devm_add_action_or_reset(dev, fsl_qspi_cleanup, q);
if (ret)
- goto err_destroy_mutex;
+ goto err_put_ctrl;
ret = devm_spi_register_controller(dev, ctlr);
if (ret)
- goto err_destroy_mutex;
+ goto err_put_ctrl;
return 0;
-err_destroy_mutex:
- mutex_destroy(&q->lock);
-
err_disable_clk:
fsl_qspi_clk_disable_unprep(q);
err_put_ctrl:
spi_controller_put(ctlr);
- dev_err(dev, "Freescale QuadSPI probe failed\n");
return ret;
}
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 832d6e900..c93d80a 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -1695,9 +1695,12 @@ static int spi_imx_transfer_one(struct spi_controller *controller,
struct spi_device *spi,
struct spi_transfer *transfer)
{
+ int ret;
struct spi_imx_data *spi_imx = spi_controller_get_devdata(spi->controller);
- spi_imx_setupxfer(spi, transfer);
+ ret = spi_imx_setupxfer(spi, transfer);
+ if (ret < 0)
+ return ret;
transfer->effective_speed_hz = spi_imx->spi_bus_clk;
/* flush rxfifo before transfer */
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index a31a1db..5db0639 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -596,7 +596,11 @@ u64 spi_mem_calc_op_duration(struct spi_mem_op *op)
ns_per_cycles = 1000000000 / op->max_freq;
ncycles += ((op->cmd.nbytes * 8) / op->cmd.buswidth) / (op->cmd.dtr ? 2 : 1);
ncycles += ((op->addr.nbytes * 8) / op->addr.buswidth) / (op->addr.dtr ? 2 : 1);
- ncycles += ((op->dummy.nbytes * 8) / op->dummy.buswidth) / (op->dummy.dtr ? 2 : 1);
+
+ /* Dummy bytes are optional for some SPI flash memory operations */
+ if (op->dummy.nbytes)
+ ncycles += ((op->dummy.nbytes * 8) / op->dummy.buswidth) / (op->dummy.dtr ? 2 : 1);
+
ncycles += ((op->data.nbytes * 8) / op->data.buswidth) / (op->data.dtr ? 2 : 1);
return ncycles * ns_per_cycles;
diff --git a/drivers/spi/spi-qpic-snand.c b/drivers/spi/spi-qpic-snand.c
index 17eb67e..94948c8 100644
--- a/drivers/spi/spi-qpic-snand.c
+++ b/drivers/spi/spi-qpic-snand.c
@@ -142,7 +142,7 @@ static void qcom_spi_set_read_loc_first(struct qcom_nand_controller *snandc,
else if (reg == NAND_READ_LOCATION_1)
snandc->regs->read_location1 = locreg_val;
else if (reg == NAND_READ_LOCATION_2)
- snandc->regs->read_location1 = locreg_val;
+ snandc->regs->read_location2 = locreg_val;
else if (reg == NAND_READ_LOCATION_3)
snandc->regs->read_location3 = locreg_val;
}
@@ -1307,8 +1307,7 @@ static int qcom_spi_send_cmdaddr(struct qcom_nand_controller *snandc,
snandc->qspi->addr1 = cpu_to_le32(s_op.addr1_reg << 16);
snandc->qspi->addr2 = cpu_to_le32(s_op.addr2_reg);
snandc->qspi->cmd = cpu_to_le32(cmd);
- qcom_spi_block_erase(snandc);
- return 0;
+ return qcom_spi_block_erase(snandc);
default:
break;
}
diff --git a/drivers/spi/spi-stm32-ospi.c b/drivers/spi/spi-stm32-ospi.c
index 6680220..9ec9823 100644
--- a/drivers/spi/spi-stm32-ospi.c
+++ b/drivers/spi/spi-stm32-ospi.c
@@ -960,6 +960,10 @@ static int stm32_ospi_probe(struct platform_device *pdev)
err_pm_enable:
pm_runtime_force_suspend(ospi->dev);
mutex_destroy(&ospi->lock);
+ if (ospi->dma_chtx)
+ dma_release_channel(ospi->dma_chtx);
+ if (ospi->dma_chrx)
+ dma_release_channel(ospi->dma_chrx);
return ret;
}
diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c
index fcbe864..f89826d 100644
--- a/drivers/spi/spi-sun4i.c
+++ b/drivers/spi/spi-sun4i.c
@@ -462,6 +462,7 @@ static int sun4i_spi_probe(struct platform_device *pdev)
sspi->host = host;
host->max_speed_hz = 100 * 1000 * 1000;
host->min_speed_hz = 3 * 1000;
+ host->use_gpio_descriptors = true;
host->set_cs = sun4i_spi_set_cs;
host->transfer_one = sun4i_spi_transfer_one;
host->num_chipselect = 4;
diff --git a/drivers/spi/spi-tegra210-quad.c b/drivers/spi/spi-tegra210-quad.c
index 08e49a8..64e1b2f 100644
--- a/drivers/spi/spi-tegra210-quad.c
+++ b/drivers/spi/spi-tegra210-quad.c
@@ -1117,9 +1117,9 @@ static int tegra_qspi_combined_seq_xfer(struct tegra_qspi *tqspi,
(&tqspi->xfer_completion,
QSPI_DMA_TIMEOUT);
- if (WARN_ON(ret == 0)) {
- dev_err(tqspi->dev, "QSPI Transfer failed with timeout: %d\n",
- ret);
+ if (WARN_ON_ONCE(ret == 0)) {
+ dev_err_ratelimited(tqspi->dev,
+ "QSPI Transfer failed with timeout\n");
if (tqspi->is_curr_dma_xfer &&
(tqspi->cur_direction & DATA_DIR_TX))
dmaengine_terminate_all
diff --git a/drivers/staging/axis-fifo/axis-fifo.c b/drivers/staging/axis-fifo/axis-fifo.c
index 7540c20..351f983 100644
--- a/drivers/staging/axis-fifo/axis-fifo.c
+++ b/drivers/staging/axis-fifo/axis-fifo.c
@@ -393,16 +393,14 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf,
bytes_available = ioread32(fifo->base_addr + XLLF_RLR_OFFSET);
if (!bytes_available) {
- dev_err(fifo->dt_device, "received a packet of length 0 - fifo core will be reset\n");
- reset_ip_core(fifo);
+ dev_err(fifo->dt_device, "received a packet of length 0\n");
ret = -EIO;
goto end_unlock;
}
if (bytes_available > len) {
- dev_err(fifo->dt_device, "user read buffer too small (available bytes=%zu user buffer bytes=%zu) - fifo core will be reset\n",
+ dev_err(fifo->dt_device, "user read buffer too small (available bytes=%zu user buffer bytes=%zu)\n",
bytes_available, len);
- reset_ip_core(fifo);
ret = -EINVAL;
goto end_unlock;
}
@@ -411,8 +409,7 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf,
/* this probably can't happen unless IP
* registers were previously mishandled
*/
- dev_err(fifo->dt_device, "received a packet that isn't word-aligned - fifo core will be reset\n");
- reset_ip_core(fifo);
+ dev_err(fifo->dt_device, "received a packet that isn't word-aligned\n");
ret = -EIO;
goto end_unlock;
}
@@ -433,7 +430,6 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf,
if (copy_to_user(buf + copied * sizeof(u32), tmp_buf,
copy * sizeof(u32))) {
- reset_ip_core(fifo);
ret = -EFAULT;
goto end_unlock;
}
@@ -542,7 +538,6 @@ static ssize_t axis_fifo_write(struct file *f, const char __user *buf,
if (copy_from_user(tmp_buf, buf + copied * sizeof(u32),
copy * sizeof(u32))) {
- reset_ip_core(fifo);
ret = -EFAULT;
goto end_unlock;
}
@@ -775,9 +770,6 @@ static int axis_fifo_parse_dt(struct axis_fifo *fifo)
goto end;
}
- /* IP sets TDFV to fifo depth - 4 so we will do the same */
- fifo->tx_fifo_depth -= 4;
-
ret = get_dts_property(fifo, "xlnx,use-rx-data", &fifo->has_rx_fifo);
if (ret) {
dev_err(fifo->dt_device, "missing xlnx,use-rx-data property\n");
diff --git a/drivers/staging/iio/adc/ad7816.c b/drivers/staging/iio/adc/ad7816.c
index 6c14d7b..081b17f 100644
--- a/drivers/staging/iio/adc/ad7816.c
+++ b/drivers/staging/iio/adc/ad7816.c
@@ -136,7 +136,7 @@ static ssize_t ad7816_store_mode(struct device *dev,
struct iio_dev *indio_dev = dev_to_iio_dev(dev);
struct ad7816_chip_info *chip = iio_priv(indio_dev);
- if (strcmp(buf, "full")) {
+ if (strcmp(buf, "full") == 0) {
gpiod_set_value(chip->rdwr_pin, 1);
chip->mode = AD7816_FULL;
} else {
diff --git a/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c b/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c
index b839b50..fa7ea4c 100644
--- a/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c
+++ b/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c
@@ -1900,6 +1900,7 @@ static int bcm2835_mmal_probe(struct vchiq_device *device)
__func__, ret);
goto free_dev;
}
+ dev->v4l2_dev.dev = &device->dev;
/* setup v4l controls */
ret = bcm2835_mmal_init_controls(dev, &dev->ctrl_handler);
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 1244ef3..620ba6e0 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -4263,8 +4263,8 @@ int iscsit_close_connection(
spin_unlock(&iscsit_global->ts_bitmap_lock);
iscsit_stop_timers_for_cmds(conn);
- iscsit_stop_nopin_response_timer(conn);
iscsit_stop_nopin_timer(conn);
+ iscsit_stop_nopin_response_timer(conn);
if (conn->conn_transport->iscsit_wait_conn)
conn->conn_transport->iscsit_wait_conn(conn);
diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c
index a55aaa8..2097aae 100644
--- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c
+++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c
@@ -485,7 +485,7 @@ static const struct pci_device_id proc_thermal_pci_ids[] = {
{ PCI_DEVICE_DATA(INTEL, ADL_THERMAL, PROC_THERMAL_FEATURE_RAPL |
PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_WT_REQ) },
{ PCI_DEVICE_DATA(INTEL, LNLM_THERMAL, PROC_THERMAL_FEATURE_MSI_SUPPORT |
- PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_DLVR |
+ PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_DLVR | PROC_THERMAL_FEATURE_DVFS |
PROC_THERMAL_FEATURE_WT_HINT | PROC_THERMAL_FEATURE_POWER_FLOOR) },
{ PCI_DEVICE_DATA(INTEL, MTLP_THERMAL, PROC_THERMAL_FEATURE_RAPL |
PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_DLVR |
@@ -495,8 +495,9 @@ static const struct pci_device_id proc_thermal_pci_ids[] = {
{ PCI_DEVICE_DATA(INTEL, RPL_THERMAL, PROC_THERMAL_FEATURE_RAPL |
PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_WT_REQ) },
{ PCI_DEVICE_DATA(INTEL, PTL_THERMAL, PROC_THERMAL_FEATURE_RAPL |
- PROC_THERMAL_FEATURE_DLVR | PROC_THERMAL_FEATURE_MSI_SUPPORT |
- PROC_THERMAL_FEATURE_WT_HINT | PROC_THERMAL_FEATURE_POWER_FLOOR) },
+ PROC_THERMAL_FEATURE_DLVR | PROC_THERMAL_FEATURE_DVFS |
+ PROC_THERMAL_FEATURE_MSI_SUPPORT | PROC_THERMAL_FEATURE_WT_HINT |
+ PROC_THERMAL_FEATURE_POWER_FLOOR) },
{ },
};
diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c
index dad63f2..3a028b7 100644
--- a/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c
+++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c
@@ -166,15 +166,18 @@ static const struct mmio_reg adl_dvfs_mmio_regs[] = {
{ 0, 0x5A40, 1, 0x1, 0}, /* rfi_disable */
};
+static const struct mapping_table *dlvr_mapping;
+static const struct mmio_reg *dlvr_mmio_regs_table;
+
#define RFIM_SHOW(suffix, table)\
static ssize_t suffix##_show(struct device *dev,\
struct device_attribute *attr,\
char *buf)\
{\
- const struct mapping_table *mapping = NULL;\
+ const struct mmio_reg *mmio_regs = dlvr_mmio_regs_table;\
+ const struct mapping_table *mapping = dlvr_mapping;\
struct proc_thermal_device *proc_priv;\
struct pci_dev *pdev = to_pci_dev(dev);\
- const struct mmio_reg *mmio_regs;\
const char **match_strs;\
int ret, err;\
u32 reg_val;\
@@ -186,12 +189,6 @@ static ssize_t suffix##_show(struct device *dev,\
mmio_regs = adl_dvfs_mmio_regs;\
} else if (table == 2) { \
match_strs = (const char **)dlvr_strings;\
- if (pdev->device == PCI_DEVICE_ID_INTEL_LNLM_THERMAL) {\
- mmio_regs = lnl_dlvr_mmio_regs;\
- mapping = lnl_dlvr_mapping;\
- } else {\
- mmio_regs = dlvr_mmio_regs;\
- } \
} else {\
match_strs = (const char **)fivr_strings;\
mmio_regs = tgl_fivr_mmio_regs;\
@@ -214,12 +211,12 @@ static ssize_t suffix##_store(struct device *dev,\
struct device_attribute *attr,\
const char *buf, size_t count)\
{\
- const struct mapping_table *mapping = NULL;\
+ const struct mmio_reg *mmio_regs = dlvr_mmio_regs_table;\
+ const struct mapping_table *mapping = dlvr_mapping;\
struct proc_thermal_device *proc_priv;\
struct pci_dev *pdev = to_pci_dev(dev);\
unsigned int input;\
const char **match_strs;\
- const struct mmio_reg *mmio_regs;\
int ret, err;\
u32 reg_val;\
u32 mask;\
@@ -230,12 +227,6 @@ static ssize_t suffix##_store(struct device *dev,\
mmio_regs = adl_dvfs_mmio_regs;\
} else if (table == 2) { \
match_strs = (const char **)dlvr_strings;\
- if (pdev->device == PCI_DEVICE_ID_INTEL_LNLM_THERMAL) {\
- mmio_regs = lnl_dlvr_mmio_regs;\
- mapping = lnl_dlvr_mapping;\
- } else {\
- mmio_regs = dlvr_mmio_regs;\
- } \
} else {\
match_strs = (const char **)fivr_strings;\
mmio_regs = tgl_fivr_mmio_regs;\
@@ -448,6 +439,16 @@ int proc_thermal_rfim_add(struct pci_dev *pdev, struct proc_thermal_device *proc
}
if (proc_priv->mmio_feature_mask & PROC_THERMAL_FEATURE_DLVR) {
+ switch (pdev->device) {
+ case PCI_DEVICE_ID_INTEL_LNLM_THERMAL:
+ case PCI_DEVICE_ID_INTEL_PTL_THERMAL:
+ dlvr_mmio_regs_table = lnl_dlvr_mmio_regs;
+ dlvr_mapping = lnl_dlvr_mapping;
+ break;
+ default:
+ dlvr_mmio_regs_table = dlvr_mmio_regs;
+ break;
+ }
ret = sysfs_create_group(&pdev->dev.kobj, &dlvr_attribute_group);
if (ret)
return ret;
diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c
index 1b137e0..3449945 100644
--- a/drivers/tty/serial/msm_serial.c
+++ b/drivers/tty/serial/msm_serial.c
@@ -1746,6 +1746,12 @@ msm_serial_early_console_setup_dm(struct earlycon_device *device,
if (!device->port.membase)
return -ENODEV;
+ /* Disable DM / single-character modes */
+ msm_write(&device->port, 0, UARTDM_DMEN);
+ msm_write(&device->port, MSM_UART_CR_CMD_RESET_RX, MSM_UART_CR);
+ msm_write(&device->port, MSM_UART_CR_CMD_RESET_TX, MSM_UART_CR);
+ msm_write(&device->port, MSM_UART_CR_TX_ENABLE, MSM_UART_CR);
+
device->con->write = msm_serial_early_write_dm;
return 0;
}
diff --git a/drivers/tty/serial/sifive.c b/drivers/tty/serial/sifive.c
index 5904a2d..054a8e6 100644
--- a/drivers/tty/serial/sifive.c
+++ b/drivers/tty/serial/sifive.c
@@ -563,8 +563,11 @@ static void sifive_serial_break_ctl(struct uart_port *port, int break_state)
static int sifive_serial_startup(struct uart_port *port)
{
struct sifive_serial_port *ssp = port_to_sifive_serial_port(port);
+ unsigned long flags;
+ uart_port_lock_irqsave(&ssp->port, &flags);
__ssp_enable_rxwm(ssp);
+ uart_port_unlock_irqrestore(&ssp->port, flags);
return 0;
}
@@ -572,9 +575,12 @@ static int sifive_serial_startup(struct uart_port *port)
static void sifive_serial_shutdown(struct uart_port *port)
{
struct sifive_serial_port *ssp = port_to_sifive_serial_port(port);
+ unsigned long flags;
+ uart_port_lock_irqsave(&ssp->port, &flags);
__ssp_disable_rxwm(ssp);
__ssp_disable_txwm(ssp);
+ uart_port_unlock_irqrestore(&ssp->port, flags);
}
/**
diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c
index 0bd6544..791e2f1 100644
--- a/drivers/tty/vt/selection.c
+++ b/drivers/tty/vt/selection.c
@@ -193,13 +193,12 @@ int set_selection_user(const struct tiocl_selection __user *sel,
return -EFAULT;
/*
- * TIOCL_SELCLEAR, TIOCL_SELPOINTER and TIOCL_SELMOUSEREPORT are OK to
- * use without CAP_SYS_ADMIN as they do not modify the selection.
+ * TIOCL_SELCLEAR and TIOCL_SELPOINTER are OK to use without
+ * CAP_SYS_ADMIN as they do not modify the selection.
*/
switch (v.sel_mode) {
case TIOCL_SELCLEAR:
case TIOCL_SELPOINTER:
- case TIOCL_SELMOUSEREPORT:
break;
default:
if (!capable(CAP_SYS_ADMIN))
diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c
index 240ce13..f1294c2 100644
--- a/drivers/ufs/core/ufs-mcq.c
+++ b/drivers/ufs/core/ufs-mcq.c
@@ -677,13 +677,6 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd)
unsigned long flags;
int err;
- if (!ufshcd_cmd_inflight(lrbp->cmd)) {
- dev_err(hba->dev,
- "%s: skip abort. cmd at tag %d already completed.\n",
- __func__, tag);
- return FAILED;
- }
-
/* Skip task abort in case previous aborts failed and report failure */
if (lrbp->req_abort_skip) {
dev_err(hba->dev, "%s: skip abort. tag %d failed earlier\n",
@@ -692,6 +685,11 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd)
}
hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd));
+ if (!hwq) {
+ dev_err(hba->dev, "%s: skip abort. cmd at tag %d already completed.\n",
+ __func__, tag);
+ return FAILED;
+ }
if (ufshcd_mcq_sqe_search(hba, hwq, tag)) {
/*
diff --git a/drivers/ufs/core/ufs-sysfs.c b/drivers/ufs/core/ufs-sysfs.c
index 90b5ab6..634cf16 100644
--- a/drivers/ufs/core/ufs-sysfs.c
+++ b/drivers/ufs/core/ufs-sysfs.c
@@ -466,6 +466,56 @@ static ssize_t critical_health_show(struct device *dev,
return sysfs_emit(buf, "%d\n", hba->critical_health_count);
}
+static ssize_t device_lvl_exception_count_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct ufs_hba *hba = dev_get_drvdata(dev);
+
+ if (hba->dev_info.wspecversion < 0x410)
+ return -EOPNOTSUPP;
+
+ return sysfs_emit(buf, "%u\n", atomic_read(&hba->dev_lvl_exception_count));
+}
+
+static ssize_t device_lvl_exception_count_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct ufs_hba *hba = dev_get_drvdata(dev);
+ unsigned int value;
+
+ if (kstrtouint(buf, 0, &value))
+ return -EINVAL;
+
+ /* the only supported usecase is to reset the dev_lvl_exception_count */
+ if (value)
+ return -EINVAL;
+
+ atomic_set(&hba->dev_lvl_exception_count, 0);
+
+ return count;
+}
+
+static ssize_t device_lvl_exception_id_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct ufs_hba *hba = dev_get_drvdata(dev);
+ u64 exception_id;
+ int err;
+
+ ufshcd_rpm_get_sync(hba);
+ err = ufshcd_read_device_lvl_exception_id(hba, &exception_id);
+ ufshcd_rpm_put_sync(hba);
+
+ if (err)
+ return err;
+
+ hba->dev_lvl_exception_id = exception_id;
+ return sysfs_emit(buf, "%llu\n", exception_id);
+}
+
static DEVICE_ATTR_RW(rpm_lvl);
static DEVICE_ATTR_RO(rpm_target_dev_state);
static DEVICE_ATTR_RO(rpm_target_link_state);
@@ -479,6 +529,8 @@ static DEVICE_ATTR_RW(wb_flush_threshold);
static DEVICE_ATTR_RW(rtc_update_ms);
static DEVICE_ATTR_RW(pm_qos_enable);
static DEVICE_ATTR_RO(critical_health);
+static DEVICE_ATTR_RW(device_lvl_exception_count);
+static DEVICE_ATTR_RO(device_lvl_exception_id);
static struct attribute *ufs_sysfs_ufshcd_attrs[] = {
&dev_attr_rpm_lvl.attr,
@@ -494,6 +546,8 @@ static struct attribute *ufs_sysfs_ufshcd_attrs[] = {
&dev_attr_rtc_update_ms.attr,
&dev_attr_pm_qos_enable.attr,
&dev_attr_critical_health.attr,
+ &dev_attr_device_lvl_exception_count.attr,
+ &dev_attr_device_lvl_exception_id.attr,
NULL
};
diff --git a/drivers/ufs/core/ufshcd-priv.h b/drivers/ufs/core/ufshcd-priv.h
index 10b4a19..d0a2c96 100644
--- a/drivers/ufs/core/ufshcd-priv.h
+++ b/drivers/ufs/core/ufshcd-priv.h
@@ -94,6 +94,7 @@ int ufshcd_exec_raw_upiu_cmd(struct ufs_hba *hba,
enum query_opcode desc_op);
int ufshcd_wb_toggle(struct ufs_hba *hba, bool enable);
+int ufshcd_read_device_lvl_exception_id(struct ufs_hba *hba, u64 *exception_id);
/* Wrapper functions for safely calling variant operations */
static inline const char *ufshcd_get_var_name(struct ufs_hba *hba)
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 0534390..7735421 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -278,6 +278,7 @@ static const struct ufs_dev_quirk ufs_fixups[] = {
.model = UFS_ANY_MODEL,
.quirk = UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM |
UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE |
+ UFS_DEVICE_QUIRK_PA_HIBER8TIME |
UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS },
{ .wmanufacturerid = UFS_VENDOR_SKHYNIX,
.model = UFS_ANY_MODEL,
@@ -3176,16 +3177,10 @@ static int ufshcd_wait_for_dev_cmd(struct ufs_hba *hba,
int err;
retry:
- time_left = wait_for_completion_timeout(hba->dev_cmd.complete,
+ time_left = wait_for_completion_timeout(&hba->dev_cmd.complete,
time_left);
if (likely(time_left)) {
- /*
- * The completion handler called complete() and the caller of
- * this function still owns the @lrbp tag so the code below does
- * not trigger any race conditions.
- */
- hba->dev_cmd.complete = NULL;
err = ufshcd_get_tr_ocs(lrbp, NULL);
if (!err)
err = ufshcd_dev_cmd_completion(hba, lrbp);
@@ -3199,7 +3194,6 @@ static int ufshcd_wait_for_dev_cmd(struct ufs_hba *hba,
/* successfully cleared the command, retry if needed */
if (ufshcd_clear_cmd(hba, lrbp->task_tag) == 0)
err = -EAGAIN;
- hba->dev_cmd.complete = NULL;
return err;
}
@@ -3215,11 +3209,9 @@ static int ufshcd_wait_for_dev_cmd(struct ufs_hba *hba,
spin_lock_irqsave(&hba->outstanding_lock, flags);
pending = test_bit(lrbp->task_tag,
&hba->outstanding_reqs);
- if (pending) {
- hba->dev_cmd.complete = NULL;
+ if (pending)
__clear_bit(lrbp->task_tag,
&hba->outstanding_reqs);
- }
spin_unlock_irqrestore(&hba->outstanding_lock, flags);
if (!pending) {
@@ -3237,8 +3229,6 @@ static int ufshcd_wait_for_dev_cmd(struct ufs_hba *hba,
spin_lock_irqsave(&hba->outstanding_lock, flags);
pending = test_bit(lrbp->task_tag,
&hba->outstanding_reqs);
- if (pending)
- hba->dev_cmd.complete = NULL;
spin_unlock_irqrestore(&hba->outstanding_lock, flags);
if (!pending) {
@@ -3272,13 +3262,9 @@ static void ufshcd_dev_man_unlock(struct ufs_hba *hba)
static int ufshcd_issue_dev_cmd(struct ufs_hba *hba, struct ufshcd_lrb *lrbp,
const u32 tag, int timeout)
{
- DECLARE_COMPLETION_ONSTACK(wait);
int err;
- hba->dev_cmd.complete = &wait;
-
ufshcd_add_query_upiu_trace(hba, UFS_QUERY_SEND, lrbp->ucd_req_ptr);
-
ufshcd_send_command(hba, tag, hba->dev_cmd_queue);
err = ufshcd_wait_for_dev_cmd(hba, lrbp, timeout);
@@ -5585,12 +5571,12 @@ void ufshcd_compl_one_cqe(struct ufs_hba *hba, int task_tag,
ufshcd_release_scsi_cmd(hba, lrbp);
/* Do not touch lrbp after scsi done */
scsi_done(cmd);
- } else if (hba->dev_cmd.complete) {
+ } else {
if (cqe) {
ocs = le32_to_cpu(cqe->status) & MASK_OCS;
lrbp->utr_descriptor_ptr->header.ocs = ocs;
}
- complete(hba->dev_cmd.complete);
+ complete(&hba->dev_cmd.complete);
}
}
@@ -5692,6 +5678,8 @@ static void ufshcd_mcq_compl_pending_transfer(struct ufs_hba *hba,
continue;
hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd));
+ if (!hwq)
+ continue;
if (force_compl) {
ufshcd_mcq_compl_all_cqes_lock(hba, hwq);
@@ -6013,6 +6001,42 @@ static void ufshcd_bkops_exception_event_handler(struct ufs_hba *hba)
__func__, err);
}
+int ufshcd_read_device_lvl_exception_id(struct ufs_hba *hba, u64 *exception_id)
+{
+ struct utp_upiu_query_v4_0 *upiu_resp;
+ struct ufs_query_req *request = NULL;
+ struct ufs_query_res *response = NULL;
+ int err;
+
+ if (hba->dev_info.wspecversion < 0x410)
+ return -EOPNOTSUPP;
+
+ ufshcd_hold(hba);
+ mutex_lock(&hba->dev_cmd.lock);
+
+ ufshcd_init_query(hba, &request, &response,
+ UPIU_QUERY_OPCODE_READ_ATTR,
+ QUERY_ATTR_IDN_DEV_LVL_EXCEPTION_ID, 0, 0);
+
+ request->query_func = UPIU_QUERY_FUNC_STANDARD_READ_REQUEST;
+
+ err = ufshcd_exec_dev_cmd(hba, DEV_CMD_TYPE_QUERY, QUERY_REQ_TIMEOUT);
+
+ if (err) {
+ dev_err(hba->dev, "%s: failed to read device level exception %d\n",
+ __func__, err);
+ goto out;
+ }
+
+ upiu_resp = (struct utp_upiu_query_v4_0 *)response;
+ *exception_id = get_unaligned_be64(&upiu_resp->osf3);
+out:
+ mutex_unlock(&hba->dev_cmd.lock);
+ ufshcd_release(hba);
+
+ return err;
+}
+
static int __ufshcd_wb_toggle(struct ufs_hba *hba, bool set, enum flag_idn idn)
{
u8 index;
@@ -6083,7 +6107,7 @@ int ufshcd_wb_toggle_buf_flush(struct ufs_hba *hba, bool enable)
return ret;
}
-static bool ufshcd_wb_presrv_usrspc_keep_vcc_on(struct ufs_hba *hba,
+static bool ufshcd_wb_curr_buff_threshold_check(struct ufs_hba *hba,
u32 avail_buf)
{
u32 cur_buf;
@@ -6165,15 +6189,13 @@ static bool ufshcd_wb_need_flush(struct ufs_hba *hba)
}
/*
- * The ufs device needs the vcc to be ON to flush.
* With user-space reduction enabled, it's enough to enable flush
* by checking only the available buffer. The threshold
* defined here is > 90% full.
* With user-space preserved enabled, the current-buffer
* should be checked too because the wb buffer size can reduce
* when disk tends to be full. This info is provided by current
- * buffer (dCurrentWriteBoosterBufferSize). There's no point in
- * keeping vcc on when current buffer is empty.
+ * buffer (dCurrentWriteBoosterBufferSize).
*/
index = ufshcd_wb_get_query_index(hba);
ret = ufshcd_query_attr_retry(hba, UPIU_QUERY_OPCODE_READ_ATTR,
@@ -6188,7 +6210,7 @@ static bool ufshcd_wb_need_flush(struct ufs_hba *hba)
if (!hba->dev_info.b_presrv_uspc_en)
return avail_buf <= UFS_WB_BUF_REMAIN_PERCENT(10);
- return ufshcd_wb_presrv_usrspc_keep_vcc_on(hba, avail_buf);
+ return ufshcd_wb_curr_buff_threshold_check(hba, avail_buf);
}
static void ufshcd_rpm_dev_flush_recheck_work(struct work_struct *work)
@@ -6240,6 +6262,11 @@ static void ufshcd_exception_event_handler(struct work_struct *work)
sysfs_notify(&hba->dev->kobj, NULL, "critical_health");
}
+ if (status & hba->ee_drv_mask & MASK_EE_DEV_LVL_EXCEPTION) {
+ atomic_inc(&hba->dev_lvl_exception_count);
+ sysfs_notify(&hba->dev->kobj, NULL, "device_lvl_exception_count");
+ }
+
ufs_debugfs_exception_event(hba, status);
}
@@ -7238,8 +7265,6 @@ static int ufshcd_issue_devman_upiu_cmd(struct ufs_hba *hba,
err = -EINVAL;
}
}
- ufshcd_add_query_upiu_trace(hba, err ? UFS_QUERY_ERR : UFS_QUERY_COMP,
- (struct utp_upiu_req *)lrbp->ucd_rsp_ptr);
return err;
}
@@ -8139,6 +8164,22 @@ static void ufshcd_temp_notif_probe(struct ufs_hba *hba, const u8 *desc_buf)
}
}
+static void ufshcd_device_lvl_exception_probe(struct ufs_hba *hba, u8 *desc_buf)
+{
+ u32 ext_ufs_feature;
+
+ if (hba->dev_info.wspecversion < 0x410)
+ return;
+
+ ext_ufs_feature = get_unaligned_be32(desc_buf +
+ DEVICE_DESC_PARAM_EXT_UFS_FEATURE_SUP);
+ if (!(ext_ufs_feature & UFS_DEV_LVL_EXCEPTION_SUP))
+ return;
+
+ atomic_set(&hba->dev_lvl_exception_count, 0);
+ ufshcd_enable_ee(hba, MASK_EE_DEV_LVL_EXCEPTION);
+}
+
static void ufshcd_set_rtt(struct ufs_hba *hba)
{
struct ufs_dev_info *dev_info = &hba->dev_info;
@@ -8339,6 +8380,8 @@ static int ufs_get_device_desc(struct ufs_hba *hba)
ufs_init_rtc(hba, desc_buf);
+ ufshcd_device_lvl_exception_probe(hba, desc_buf);
+
/*
* ufshcd_read_string_desc returns size of the string
* reset the error value
@@ -8428,6 +8471,31 @@ static int ufshcd_quirk_tune_host_pa_tactivate(struct ufs_hba *hba)
return ret;
}
+/**
+ * ufshcd_quirk_override_pa_h8time - Ensures proper adjustment of PA_HIBERN8TIME.
+ * @hba: per-adapter instance
+ *
+ * Some UFS devices require specific adjustments to the PA_HIBERN8TIME parameter
+ * to ensure proper hibernation timing. This function retrieves the current
+ * PA_HIBERN8TIME value and increments it by 100us.
+ */
+static void ufshcd_quirk_override_pa_h8time(struct ufs_hba *hba)
+{
+ u32 pa_h8time;
+ int ret;
+
+ ret = ufshcd_dme_get(hba, UIC_ARG_MIB(PA_HIBERN8TIME), &pa_h8time);
+ if (ret) {
+ dev_err(hba->dev, "Failed to get PA_HIBERN8TIME: %d\n", ret);
+ return;
+ }
+
+ /* Increment by 1 to increase hibernation time by 100 µs */
+ ret = ufshcd_dme_set(hba, UIC_ARG_MIB(PA_HIBERN8TIME), pa_h8time + 1);
+ if (ret)
+ dev_err(hba->dev, "Failed updating PA_HIBERN8TIME: %d\n", ret);
+}
+
static void ufshcd_tune_unipro_params(struct ufs_hba *hba)
{
ufshcd_vops_apply_dev_quirks(hba);
@@ -8438,6 +8506,9 @@ static void ufshcd_tune_unipro_params(struct ufs_hba *hba)
if (hba->dev_quirks & UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE)
ufshcd_quirk_tune_host_pa_tactivate(hba);
+
+ if (hba->dev_quirks & UFS_DEVICE_QUIRK_PA_HIBER8TIME)
+ ufshcd_quirk_override_pa_h8time(hba);
}
static void ufshcd_clear_dbg_ufs_stats(struct ufs_hba *hba)
@@ -10490,6 +10561,8 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
UFS_SLEEP_PWR_MODE,
UIC_LINK_HIBERN8_STATE);
+ init_completion(&hba->dev_cmd.complete);
+
err = ufshcd_hba_init(hba);
if (err)
goto out_error;
diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c
index d7539cd..3e545af 100644
--- a/drivers/ufs/host/ufs-exynos.c
+++ b/drivers/ufs/host/ufs-exynos.c
@@ -34,7 +34,7 @@
* Exynos's Vendor specific registers for UFSHCI
*/
#define HCI_TXPRDT_ENTRY_SIZE 0x00
-#define PRDT_PREFECT_EN BIT(31)
+#define PRDT_PREFETCH_EN BIT(31)
#define HCI_RXPRDT_ENTRY_SIZE 0x04
#define HCI_1US_TO_CNT_VAL 0x0C
#define CNT_VAL_1US_MASK 0x3FF
@@ -92,11 +92,16 @@
UIC_TRANSPORT_NO_CONNECTION_RX |\
UIC_TRANSPORT_BAD_TC)
-/* FSYS UFS Shareability */
-#define UFS_WR_SHARABLE BIT(2)
-#define UFS_RD_SHARABLE BIT(1)
-#define UFS_SHARABLE (UFS_WR_SHARABLE | UFS_RD_SHARABLE)
-#define UFS_SHAREABILITY_OFFSET 0x710
+/* UFS Shareability */
+#define UFS_EXYNOSAUTO_WR_SHARABLE BIT(2)
+#define UFS_EXYNOSAUTO_RD_SHARABLE BIT(1)
+#define UFS_EXYNOSAUTO_SHARABLE (UFS_EXYNOSAUTO_WR_SHARABLE | \
+ UFS_EXYNOSAUTO_RD_SHARABLE)
+#define UFS_GS101_WR_SHARABLE BIT(1)
+#define UFS_GS101_RD_SHARABLE BIT(0)
+#define UFS_GS101_SHARABLE (UFS_GS101_WR_SHARABLE | \
+ UFS_GS101_RD_SHARABLE)
+#define UFS_SHAREABILITY_OFFSET 0x710
/* Multi-host registers */
#define MHCTRL 0xC4
@@ -209,8 +214,8 @@ static int exynos_ufs_shareability(struct exynos_ufs *ufs)
/* IO Coherency setting */
if (ufs->sysreg) {
return regmap_update_bits(ufs->sysreg,
- ufs->shareability_reg_offset,
- UFS_SHARABLE, UFS_SHARABLE);
+ ufs->iocc_offset,
+ ufs->iocc_mask, ufs->iocc_val);
}
return 0;
@@ -957,6 +962,12 @@ static int exynos_ufs_phy_init(struct exynos_ufs *ufs)
}
phy_set_bus_width(generic_phy, ufs->avail_ln_rx);
+
+ if (generic_phy->power_count) {
+ phy_power_off(generic_phy);
+ phy_exit(generic_phy);
+ }
+
ret = phy_init(generic_phy);
if (ret) {
dev_err(hba->dev, "%s: phy init failed, ret = %d\n",
@@ -1049,9 +1060,14 @@ static int exynos_ufs_pre_link(struct ufs_hba *hba)
exynos_ufs_config_intr(ufs, DFES_DEF_L4_ERRS, UNIPRO_L4);
exynos_ufs_set_unipro_pclk_div(ufs);
+ exynos_ufs_setup_clocks(hba, true, PRE_CHANGE);
+
/* unipro */
exynos_ufs_config_unipro(ufs);
+ if (ufs->drv_data->pre_link)
+ ufs->drv_data->pre_link(ufs);
+
/* m-phy */
exynos_ufs_phy_init(ufs);
if (!(ufs->opts & EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR)) {
@@ -1059,11 +1075,6 @@ static int exynos_ufs_pre_link(struct ufs_hba *hba)
exynos_ufs_config_phy_cap_attr(ufs);
}
- exynos_ufs_setup_clocks(hba, true, PRE_CHANGE);
-
- if (ufs->drv_data->pre_link)
- ufs->drv_data->pre_link(ufs);
-
return 0;
}
@@ -1087,12 +1098,17 @@ static int exynos_ufs_post_link(struct ufs_hba *hba)
struct exynos_ufs *ufs = ufshcd_get_variant(hba);
struct phy *generic_phy = ufs->phy;
struct exynos_ufs_uic_attr *attr = ufs->drv_data->uic_attr;
+ u32 val = ilog2(DATA_UNIT_SIZE);
exynos_ufs_establish_connt(ufs);
exynos_ufs_fit_aggr_timeout(ufs);
hci_writel(ufs, 0xa, HCI_DATA_REORDER);
- hci_writel(ufs, ilog2(DATA_UNIT_SIZE), HCI_TXPRDT_ENTRY_SIZE);
+
+ if (hba->caps & UFSHCD_CAP_CRYPTO)
+ val |= PRDT_PREFETCH_EN;
+ hci_writel(ufs, val, HCI_TXPRDT_ENTRY_SIZE);
+
hci_writel(ufs, ilog2(DATA_UNIT_SIZE), HCI_RXPRDT_ENTRY_SIZE);
hci_writel(ufs, (1 << hba->nutrs) - 1, HCI_UTRL_NEXUS_TYPE);
hci_writel(ufs, (1 << hba->nutmrs) - 1, HCI_UTMRL_NEXUS_TYPE);
@@ -1168,12 +1184,22 @@ static int exynos_ufs_parse_dt(struct device *dev, struct exynos_ufs *ufs)
ufs->sysreg = NULL;
else {
if (of_property_read_u32_index(np, "samsung,sysreg", 1,
- &ufs->shareability_reg_offset)) {
+ &ufs->iocc_offset)) {
dev_warn(dev, "can't get an offset from sysreg. Set to default value\n");
- ufs->shareability_reg_offset = UFS_SHAREABILITY_OFFSET;
+ ufs->iocc_offset = UFS_SHAREABILITY_OFFSET;
}
}
+ ufs->iocc_mask = ufs->drv_data->iocc_mask;
+ /*
+ * no 'dma-coherent' property means the descriptors are
+ * non-cacheable so iocc shareability should be disabled.
+ */
+ if (of_dma_is_coherent(dev->of_node))
+ ufs->iocc_val = ufs->iocc_mask;
+ else
+ ufs->iocc_val = 0;
+
ufs->pclk_avail_min = PCLK_AVAIL_MIN;
ufs->pclk_avail_max = PCLK_AVAIL_MAX;
@@ -1497,6 +1523,14 @@ static int exynos_ufs_init(struct ufs_hba *hba)
return ret;
}
+static void exynos_ufs_exit(struct ufs_hba *hba)
+{
+ struct exynos_ufs *ufs = ufshcd_get_variant(hba);
+
+ phy_power_off(ufs->phy);
+ phy_exit(ufs->phy);
+}
+
static int exynos_ufs_host_reset(struct ufs_hba *hba)
{
struct exynos_ufs *ufs = ufshcd_get_variant(hba);
@@ -1667,6 +1701,12 @@ static void exynos_ufs_hibern8_notify(struct ufs_hba *hba,
}
}
+static int gs101_ufs_suspend(struct exynos_ufs *ufs)
+{
+ hci_writel(ufs, 0 << 0, HCI_GPIO_OUT);
+ return 0;
+}
+
static int exynos_ufs_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op,
enum ufs_notify_change_status status)
{
@@ -1675,6 +1715,9 @@ static int exynos_ufs_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op,
if (status == PRE_CHANGE)
return 0;
+ if (ufs->drv_data->suspend)
+ ufs->drv_data->suspend(ufs);
+
if (!ufshcd_is_link_active(hba))
phy_power_off(ufs->phy);
@@ -1952,6 +1995,7 @@ static int gs101_ufs_pre_pwr_change(struct exynos_ufs *ufs,
static const struct ufs_hba_variant_ops ufs_hba_exynos_ops = {
.name = "exynos_ufs",
.init = exynos_ufs_init,
+ .exit = exynos_ufs_exit,
.hce_enable_notify = exynos_ufs_hce_enable_notify,
.link_startup_notify = exynos_ufs_link_startup_notify,
.pwr_change_notify = exynos_ufs_pwr_change_notify,
@@ -1990,13 +2034,7 @@ static int exynos_ufs_probe(struct platform_device *pdev)
static void exynos_ufs_remove(struct platform_device *pdev)
{
- struct ufs_hba *hba = platform_get_drvdata(pdev);
- struct exynos_ufs *ufs = ufshcd_get_variant(hba);
-
ufshcd_pltfrm_remove(pdev);
-
- phy_power_off(ufs->phy);
- phy_exit(ufs->phy);
}
static struct exynos_ufs_uic_attr exynos7_uic_attr = {
@@ -2035,6 +2073,7 @@ static const struct exynos_ufs_drv_data exynosauto_ufs_drvs = {
.opts = EXYNOS_UFS_OPT_BROKEN_AUTO_CLK_CTRL |
EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR |
EXYNOS_UFS_OPT_BROKEN_RX_SEL_IDX,
+ .iocc_mask = UFS_EXYNOSAUTO_SHARABLE,
.drv_init = exynosauto_ufs_drv_init,
.post_hce_enable = exynosauto_ufs_post_hce_enable,
.pre_link = exynosauto_ufs_pre_link,
@@ -2136,10 +2175,12 @@ static const struct exynos_ufs_drv_data gs101_ufs_drvs = {
.opts = EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR |
EXYNOS_UFS_OPT_UFSPR_SECURE |
EXYNOS_UFS_OPT_TIMER_TICK_SELECT,
+ .iocc_mask = UFS_GS101_SHARABLE,
.drv_init = gs101_ufs_drv_init,
.pre_link = gs101_ufs_pre_link,
.post_link = gs101_ufs_post_link,
.pre_pwr_change = gs101_ufs_pre_pwr_change,
+ .suspend = gs101_ufs_suspend,
};
static const struct of_device_id exynos_ufs_of_match[] = {
diff --git a/drivers/ufs/host/ufs-exynos.h b/drivers/ufs/host/ufs-exynos.h
index aac5172..abe7e47 100644
--- a/drivers/ufs/host/ufs-exynos.h
+++ b/drivers/ufs/host/ufs-exynos.h
@@ -181,6 +181,7 @@ struct exynos_ufs_drv_data {
struct exynos_ufs_uic_attr *uic_attr;
unsigned int quirks;
unsigned int opts;
+ u32 iocc_mask;
/* SoC's specific operations */
int (*drv_init)(struct exynos_ufs *ufs);
int (*pre_link)(struct exynos_ufs *ufs);
@@ -191,6 +192,7 @@ struct exynos_ufs_drv_data {
const struct ufs_pa_layer_attr *pwr);
int (*pre_hce_enable)(struct exynos_ufs *ufs);
int (*post_hce_enable)(struct exynos_ufs *ufs);
+ int (*suspend)(struct exynos_ufs *ufs);
};
struct ufs_phy_time_cfg {
@@ -230,7 +232,9 @@ struct exynos_ufs {
ktime_t entry_hibern8_t;
const struct exynos_ufs_drv_data *drv_data;
struct regmap *sysreg;
- u32 shareability_reg_offset;
+ u32 iocc_offset;
+ u32 iocc_mask;
+ u32 iocc_val;
u32 opts;
#define EXYNOS_UFS_OPT_HAS_APB_CLK_CTRL BIT(0)
diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
index 1b37449..c0761cc 100644
--- a/drivers/ufs/host/ufs-qcom.c
+++ b/drivers/ufs/host/ufs-qcom.c
@@ -33,6 +33,10 @@
((((c) >> 16) & MCQ_QCFGPTR_MASK) * MCQ_QCFGPTR_UNIT)
#define MCQ_QCFG_SIZE 0x40
+/* De-emphasis for gear-5 */
+#define DEEMPHASIS_3_5_dB 0x04
+#define NO_DEEMPHASIS 0x0
+
enum {
TSTBUS_UAWM,
TSTBUS_UARM,
@@ -795,6 +799,23 @@ static int ufs_qcom_icc_update_bw(struct ufs_qcom_host *host)
return ufs_qcom_icc_set_bw(host, bw_table.mem_bw, bw_table.cfg_bw);
}
+static void ufs_qcom_set_tx_hs_equalizer(struct ufs_hba *hba, u32 gear, u32 tx_lanes)
+{
+ u32 equalizer_val;
+ int ret, i;
+
+ /* Determine the equalizer value based on the gear */
+ equalizer_val = (gear == 5) ? DEEMPHASIS_3_5_dB : NO_DEEMPHASIS;
+
+ for (i = 0; i < tx_lanes; i++) {
+ ret = ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(TX_HS_EQUALIZER, i),
+ equalizer_val);
+ if (ret)
+ dev_err(hba->dev, "%s: failed equalizer lane %d\n",
+ __func__, i);
+ }
+}
+
static int ufs_qcom_pwr_change_notify(struct ufs_hba *hba,
enum ufs_notify_change_status status,
const struct ufs_pa_layer_attr *dev_max_params,
@@ -846,6 +867,11 @@ static int ufs_qcom_pwr_change_notify(struct ufs_hba *hba,
dev_req_params->gear_tx,
PA_INITIAL_ADAPT);
}
+
+ if (hba->dev_quirks & UFS_DEVICE_QUIRK_PA_TX_DEEMPHASIS_TUNING)
+ ufs_qcom_set_tx_hs_equalizer(hba,
+ dev_req_params->gear_tx, dev_req_params->lane_tx);
+
break;
case POST_CHANGE:
if (ufs_qcom_cfg_timers(hba, false)) {
@@ -893,6 +919,16 @@ static int ufs_qcom_quirk_host_pa_saveconfigtime(struct ufs_hba *hba)
(pa_vs_config_reg1 | (1 << 12)));
}
+static void ufs_qcom_override_pa_tx_hsg1_sync_len(struct ufs_hba *hba)
+{
+ int err;
+
+ err = ufshcd_dme_peer_set(hba, UIC_ARG_MIB(PA_TX_HSG1_SYNC_LENGTH),
+ PA_TX_HSG1_SYNC_LENGTH_VAL);
+ if (err)
+ dev_err(hba->dev, "Failed (%d) set PA_TX_HSG1_SYNC_LENGTH\n", err);
+}
+
static int ufs_qcom_apply_dev_quirks(struct ufs_hba *hba)
{
int err = 0;
@@ -900,6 +936,9 @@ static int ufs_qcom_apply_dev_quirks(struct ufs_hba *hba)
if (hba->dev_quirks & UFS_DEVICE_QUIRK_HOST_PA_SAVECONFIGTIME)
err = ufs_qcom_quirk_host_pa_saveconfigtime(hba);
+ if (hba->dev_quirks & UFS_DEVICE_QUIRK_PA_TX_HSG1_SYNC_LENGTH)
+ ufs_qcom_override_pa_tx_hsg1_sync_len(hba);
+
return err;
}
@@ -914,6 +953,10 @@ static struct ufs_dev_quirk ufs_qcom_dev_fixups[] = {
{ .wmanufacturerid = UFS_VENDOR_WDC,
.model = UFS_ANY_MODEL,
.quirk = UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE },
+ { .wmanufacturerid = UFS_VENDOR_SAMSUNG,
+ .model = UFS_ANY_MODEL,
+ .quirk = UFS_DEVICE_QUIRK_PA_TX_HSG1_SYNC_LENGTH |
+ UFS_DEVICE_QUIRK_PA_TX_DEEMPHASIS_TUNING },
{}
};
diff --git a/drivers/ufs/host/ufs-qcom.h b/drivers/ufs/host/ufs-qcom.h
index d0e6ec9..05d4cb5 100644
--- a/drivers/ufs/host/ufs-qcom.h
+++ b/drivers/ufs/host/ufs-qcom.h
@@ -122,8 +122,11 @@ enum {
TMRLUT_HW_CGC_EN | OCSC_HW_CGC_EN)
/* QUniPro Vendor specific attributes */
+#define PA_TX_HSG1_SYNC_LENGTH 0x1552
#define PA_VS_CONFIG_REG1 0x9000
#define DME_VS_CORE_CLK_CTRL 0xD002
+#define TX_HS_EQUALIZER 0x0037
+
/* bit and mask definitions for DME_VS_CORE_CLK_CTRL attribute */
#define CLK_1US_CYCLES_MASK_V4 GENMASK(27, 16)
#define CLK_1US_CYCLES_MASK GENMASK(7, 0)
@@ -141,6 +144,21 @@ enum {
#define UNIPRO_CORE_CLK_FREQ_201_5_MHZ 202
#define UNIPRO_CORE_CLK_FREQ_403_MHZ 403
+/* TX_HSG1_SYNC_LENGTH attr value */
+#define PA_TX_HSG1_SYNC_LENGTH_VAL 0x4A
+
+/*
+ * Some ufs device vendors need a different TSync length.
+ * Enable this quirk to give an additional TX_HS_SYNC_LENGTH.
+ */
+#define UFS_DEVICE_QUIRK_PA_TX_HSG1_SYNC_LENGTH BIT(16)
+
+/*
+ * Some ufs device vendors need a different Deemphasis setting.
+ * Enable this quirk to tune TX Deemphasis parameters.
+ */
+#define UFS_DEVICE_QUIRK_PA_TX_DEEMPHASIS_TUNING BIT(17)
+
/* ICE allocator type to share AES engines among TX stream and RX stream */
#define ICE_ALLOCATOR_TYPE 2
diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c
index 694aa14..d9d8dc0 100644
--- a/drivers/usb/cdns3/cdns3-gadget.c
+++ b/drivers/usb/cdns3/cdns3-gadget.c
@@ -1963,6 +1963,7 @@ static irqreturn_t cdns3_device_thread_irq_handler(int irq, void *data)
unsigned int bit;
unsigned long reg;
+ local_bh_disable();
spin_lock_irqsave(&priv_dev->lock, flags);
reg = readl(&priv_dev->regs->usb_ists);
@@ -2004,6 +2005,7 @@ static irqreturn_t cdns3_device_thread_irq_handler(int irq, void *data)
irqend:
writel(~0, &priv_dev->regs->ep_ien);
spin_unlock_irqrestore(&priv_dev->lock, flags);
+ local_bh_enable();
return ret;
}
diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c
index 87f3108..4824a10 100644
--- a/drivers/usb/cdns3/cdnsp-gadget.c
+++ b/drivers/usb/cdns3/cdnsp-gadget.c
@@ -139,6 +139,26 @@ static void cdnsp_clear_port_change_bit(struct cdnsp_device *pdev,
(portsc & PORT_CHANGE_BITS), port_regs);
}
+static void cdnsp_set_apb_timeout_value(struct cdnsp_device *pdev)
+{
+ struct cdns *cdns = dev_get_drvdata(pdev->dev);
+ __le32 __iomem *reg;
+ void __iomem *base;
+ u32 offset = 0;
+ u32 val;
+
+ if (!cdns->override_apb_timeout)
+ return;
+
+ base = &pdev->cap_regs->hc_capbase;
+ offset = cdnsp_find_next_ext_cap(base, offset, D_XEC_PRE_REGS_CAP);
+ reg = base + offset + REG_CHICKEN_BITS_3_OFFSET;
+
+ val = le32_to_cpu(readl(reg));
+ val = CHICKEN_APB_TIMEOUT_SET(val, cdns->override_apb_timeout);
+ writel(cpu_to_le32(val), reg);
+}
+
static void cdnsp_set_chicken_bits_2(struct cdnsp_device *pdev, u32 bit)
{
__le32 __iomem *reg;
@@ -1773,6 +1793,8 @@ static void cdnsp_get_rev_cap(struct cdnsp_device *pdev)
reg += cdnsp_find_next_ext_cap(reg, 0, RTL_REV_CAP);
pdev->rev_cap = reg;
+ pdev->rtl_revision = readl(&pdev->rev_cap->rtl_revision);
+
dev_info(pdev->dev, "Rev: %08x/%08x, eps: %08x, buff: %08x/%08x\n",
readl(&pdev->rev_cap->ctrl_revision),
readl(&pdev->rev_cap->rtl_revision),
@@ -1798,6 +1820,15 @@ static int cdnsp_gen_setup(struct cdnsp_device *pdev)
pdev->hci_version = HC_VERSION(pdev->hcc_params);
pdev->hcc_params = readl(&pdev->cap_regs->hcc_params);
+ /*
+ * Override the APB timeout value to give the controller more time for
+ * enabling UTMI clock and synchronizing APB and UTMI clock domains.
+ * This fix is platform specific and is required to fixes issue with
+ * reading incorrect value from PORTSC register after resuming
+ * from L1 state.
+ */
+ cdnsp_set_apb_timeout_value(pdev);
+
cdnsp_get_rev_cap(pdev);
/* Make sure the Device Controller is halted. */
diff --git a/drivers/usb/cdns3/cdnsp-gadget.h b/drivers/usb/cdns3/cdnsp-gadget.h
index 84887df..12534be 100644
--- a/drivers/usb/cdns3/cdnsp-gadget.h
+++ b/drivers/usb/cdns3/cdnsp-gadget.h
@@ -520,6 +520,9 @@ struct cdnsp_rev_cap {
#define REG_CHICKEN_BITS_2_OFFSET 0x48
#define CHICKEN_XDMA_2_TP_CACHE_DIS BIT(28)
+#define REG_CHICKEN_BITS_3_OFFSET 0x4C
+#define CHICKEN_APB_TIMEOUT_SET(p, val) (((p) & ~GENMASK(21, 0)) | (val))
+
/* XBUF Extended Capability ID. */
#define XBUF_CAP_ID 0xCB
#define XBUF_RX_TAG_MASK_0_OFFSET 0x1C
@@ -1357,6 +1360,7 @@ struct cdnsp_port {
* @rev_cap: Controller Capabilities Registers.
* @hcs_params1: Cached register copies of read-only HCSPARAMS1
* @hcc_params: Cached register copies of read-only HCCPARAMS1
+ * @rtl_revision: Cached controller rtl revision.
* @setup: Temporary buffer for setup packet.
* @ep0_preq: Internal allocated request used during enumeration.
* @ep0_stage: ep0 stage during enumeration process.
@@ -1411,6 +1415,8 @@ struct cdnsp_device {
__u32 hcs_params1;
__u32 hcs_params3;
__u32 hcc_params;
+ #define RTL_REVISION_NEW_LPM 0x2700
+ __u32 rtl_revision;
/* Lock used in interrupt thread context. */
spinlock_t lock;
struct usb_ctrlrequest setup;
diff --git a/drivers/usb/cdns3/cdnsp-pci.c b/drivers/usb/cdns3/cdnsp-pci.c
index a511445..8c361b8 100644
--- a/drivers/usb/cdns3/cdnsp-pci.c
+++ b/drivers/usb/cdns3/cdnsp-pci.c
@@ -28,6 +28,8 @@
#define PCI_DRIVER_NAME "cdns-pci-usbssp"
#define PLAT_DRIVER_NAME "cdns-usbssp"
+#define CHICKEN_APB_TIMEOUT_VALUE 0x1C20
+
static struct pci_dev *cdnsp_get_second_fun(struct pci_dev *pdev)
{
/*
@@ -139,6 +141,14 @@ static int cdnsp_pci_probe(struct pci_dev *pdev,
cdnsp->otg_irq = pdev->irq;
}
+ /*
+ * Cadence PCI based platform require some longer timeout for APB
+ * to fixes domain clock synchronization issue after resuming
+ * controller from L1 state.
+ */
+ cdnsp->override_apb_timeout = CHICKEN_APB_TIMEOUT_VALUE;
+ pci_set_drvdata(pdev, cdnsp);
+
if (pci_is_enabled(func)) {
cdnsp->dev = dev;
cdnsp->gadget_init = cdnsp_gadget_init;
@@ -148,8 +158,6 @@ static int cdnsp_pci_probe(struct pci_dev *pdev,
goto free_cdnsp;
}
- pci_set_drvdata(pdev, cdnsp);
-
device_wakeup_enable(&pdev->dev);
if (pci_dev_run_wake(pdev))
pm_runtime_put_noidle(&pdev->dev);
diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c
index 4685252..fd06cb8 100644
--- a/drivers/usb/cdns3/cdnsp-ring.c
+++ b/drivers/usb/cdns3/cdnsp-ring.c
@@ -308,7 +308,8 @@ static bool cdnsp_ring_ep_doorbell(struct cdnsp_device *pdev,
writel(db_value, reg_addr);
- cdnsp_force_l0_go(pdev);
+ if (pdev->rtl_revision < RTL_REVISION_NEW_LPM)
+ cdnsp_force_l0_go(pdev);
/* Doorbell was set. */
return true;
diff --git a/drivers/usb/cdns3/core.h b/drivers/usb/cdns3/core.h
index 921cccf..801be9e 100644
--- a/drivers/usb/cdns3/core.h
+++ b/drivers/usb/cdns3/core.h
@@ -79,6 +79,8 @@ struct cdns3_platform_data {
* @pdata: platform data from glue layer
* @lock: spinlock structure
* @xhci_plat_data: xhci private data structure pointer
+ * @override_apb_timeout: hold value of APB timeout. For value 0 the default
+ * value in CHICKEN_BITS_3 will be preserved.
* @gadget_init: pointer to gadget initialization function
*/
struct cdns {
@@ -117,6 +119,7 @@ struct cdns {
struct cdns3_platform_data *pdata;
spinlock_t lock;
struct xhci_plat_priv *xhci_plat_data;
+ u32 override_apb_timeout;
int (*gadget_init)(struct cdns *cdns);
};
diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index 1a7fc63..4f8bfd2 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -336,6 +336,13 @@ static int ci_hdrc_imx_notify_event(struct ci_hdrc *ci, unsigned int event)
return ret;
}
+static void ci_hdrc_imx_disable_regulator(void *arg)
+{
+ struct ci_hdrc_imx_data *data = arg;
+
+ regulator_disable(data->hsic_pad_regulator);
+}
+
static int ci_hdrc_imx_probe(struct platform_device *pdev)
{
struct ci_hdrc_imx_data *data;
@@ -394,6 +401,13 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
"Failed to enable HSIC pad regulator\n");
goto err_put;
}
+ ret = devm_add_action_or_reset(dev,
+ ci_hdrc_imx_disable_regulator, data);
+ if (ret) {
+ dev_err(dev,
+ "Failed to add regulator devm action\n");
+ goto err_put;
+ }
}
}
@@ -432,11 +446,11 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
ret = imx_get_clks(dev);
if (ret)
- goto disable_hsic_regulator;
+ goto qos_remove_request;
ret = imx_prepare_enable_clks(dev);
if (ret)
- goto disable_hsic_regulator;
+ goto qos_remove_request;
ret = clk_prepare_enable(data->clk_wakeup);
if (ret)
@@ -470,7 +484,11 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
of_usb_get_phy_mode(np) == USBPHY_INTERFACE_MODE_ULPI) {
pdata.flags |= CI_HDRC_OVERRIDE_PHY_CONTROL;
data->override_phy_control = true;
- usb_phy_init(pdata.usb_phy);
+ ret = usb_phy_init(pdata.usb_phy);
+ if (ret) {
+ dev_err(dev, "Failed to init phy\n");
+ goto err_clk;
+ }
}
if (pdata.flags & CI_HDRC_SUPPORTS_RUNTIME_PM)
@@ -479,7 +497,7 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
ret = imx_usbmisc_init(data->usbmisc_data);
if (ret) {
dev_err(dev, "usbmisc init failed, ret=%d\n", ret);
- goto err_clk;
+ goto phy_shutdown;
}
data->ci_pdev = ci_hdrc_add_device(dev,
@@ -488,7 +506,7 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
if (IS_ERR(data->ci_pdev)) {
ret = PTR_ERR(data->ci_pdev);
dev_err_probe(dev, ret, "ci_hdrc_add_device failed\n");
- goto err_clk;
+ goto phy_shutdown;
}
if (data->usbmisc_data) {
@@ -522,19 +540,20 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
disable_device:
ci_hdrc_remove_device(data->ci_pdev);
+phy_shutdown:
+ if (data->override_phy_control)
+ usb_phy_shutdown(data->phy);
err_clk:
clk_disable_unprepare(data->clk_wakeup);
err_wakeup_clk:
imx_disable_unprepare_clks(dev);
-disable_hsic_regulator:
- if (data->hsic_pad_regulator)
- /* don't overwrite original ret (cf. EPROBE_DEFER) */
- regulator_disable(data->hsic_pad_regulator);
+qos_remove_request:
if (pdata.flags & CI_HDRC_PMQOS)
cpu_latency_qos_remove_request(&data->pm_qos_req);
data->ci_pdev = NULL;
err_put:
- put_device(data->usbmisc_data->dev);
+ if (data->usbmisc_data)
+ put_device(data->usbmisc_data->dev);
return ret;
}
@@ -556,10 +575,9 @@ static void ci_hdrc_imx_remove(struct platform_device *pdev)
clk_disable_unprepare(data->clk_wakeup);
if (data->plat_data->flags & CI_HDRC_PMQOS)
cpu_latency_qos_remove_request(&data->pm_qos_req);
- if (data->hsic_pad_regulator)
- regulator_disable(data->hsic_pad_regulator);
}
- put_device(data->usbmisc_data->dev);
+ if (data->usbmisc_data)
+ put_device(data->usbmisc_data->dev);
}
static void ci_hdrc_imx_shutdown(struct platform_device *pdev)
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index 86ee39d..16e7fa4 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -726,7 +726,7 @@ static int wdm_open(struct inode *inode, struct file *file)
rv = -EBUSY;
goto out;
}
-
+ smp_rmb(); /* ordered against wdm_wwan_port_stop() */
rv = usb_autopm_get_interface(desc->intf);
if (rv < 0) {
dev_err(&desc->intf->dev, "Error autopm - %d\n", rv);
@@ -829,6 +829,7 @@ static struct usb_class_driver wdm_class = {
static int wdm_wwan_port_start(struct wwan_port *port)
{
struct wdm_device *desc = wwan_port_get_drvdata(port);
+ int rv;
/* The interface is both exposed via the WWAN framework and as a
* legacy usbmisc chardev. If chardev is already open, just fail
@@ -848,7 +849,15 @@ static int wdm_wwan_port_start(struct wwan_port *port)
wwan_port_txon(port);
/* Start getting events */
- return usb_submit_urb(desc->validity, GFP_KERNEL);
+ rv = usb_submit_urb(desc->validity, GFP_KERNEL);
+ if (rv < 0) {
+ wwan_port_txoff(port);
+ desc->manage_power(desc->intf, 0);
+ /* this must be last lest we race with chardev open */
+ clear_bit(WDM_WWAN_IN_USE, &desc->flags);
+ }
+
+ return rv;
}
static void wdm_wwan_port_stop(struct wwan_port *port)
@@ -859,8 +868,10 @@ static void wdm_wwan_port_stop(struct wwan_port *port)
poison_urbs(desc);
desc->manage_power(desc->intf, 0);
clear_bit(WDM_READ, &desc->flags);
- clear_bit(WDM_WWAN_IN_USE, &desc->flags);
unpoison_urbs(desc);
+ smp_wmb(); /* ordered against wdm_open() */
+ /* this must be last lest we open a poisoned device */
+ clear_bit(WDM_WWAN_IN_USE, &desc->flags);
}
static void wdm_wwan_port_tx_complete(struct urb *urb)
@@ -868,7 +879,7 @@ static void wdm_wwan_port_tx_complete(struct urb *urb)
struct sk_buff *skb = urb->context;
struct wdm_device *desc = skb_shinfo(skb)->destructor_arg;
- usb_autopm_put_interface(desc->intf);
+ usb_autopm_put_interface_async(desc->intf);
wwan_port_txon(desc->wwanp);
kfree_skb(skb);
}
@@ -898,7 +909,7 @@ static int wdm_wwan_port_tx(struct wwan_port *port, struct sk_buff *skb)
req->bRequestType = (USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE);
req->bRequest = USB_CDC_SEND_ENCAPSULATED_COMMAND;
req->wValue = 0;
- req->wIndex = desc->inum;
+ req->wIndex = desc->inum; /* already converted */
req->wLength = cpu_to_le16(skb->len);
skb_shinfo(skb)->destructor_arg = desc;
diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c
index 34e46ef..634c3bc 100644
--- a/drivers/usb/class/usbtmc.c
+++ b/drivers/usb/class/usbtmc.c
@@ -1380,7 +1380,10 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf,
if (!buffer)
return -ENOMEM;
- mutex_lock(&data->io_mutex);
+ retval = mutex_lock_interruptible(&data->io_mutex);
+ if (retval < 0)
+ goto exit_nolock;
+
if (data->zombie) {
retval = -ENODEV;
goto exit;
@@ -1503,6 +1506,7 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf,
exit:
mutex_unlock(&data->io_mutex);
+exit_nolock:
kfree(buffer);
return retval;
}
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 8efbacc..36d3df7 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -369,6 +369,9 @@ static const struct usb_device_id usb_quirk_list[] = {
{ USB_DEVICE(0x0781, 0x5583), .driver_info = USB_QUIRK_NO_LPM },
{ USB_DEVICE(0x0781, 0x5591), .driver_info = USB_QUIRK_NO_LPM },
+ /* SanDisk Corp. SanDisk 3.2Gen1 */
+ { USB_DEVICE(0x0781, 0x55a3), .driver_info = USB_QUIRK_DELAY_INIT },
+
/* Realforce 87U Keyboard */
{ USB_DEVICE(0x0853, 0x011b), .driver_info = USB_QUIRK_NO_LPM },
@@ -383,6 +386,9 @@ static const struct usb_device_id usb_quirk_list[] = {
{ USB_DEVICE(0x0904, 0x6103), .driver_info =
USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
+ /* Silicon Motion Flash Drive */
+ { USB_DEVICE(0x090c, 0x1000), .driver_info = USB_QUIRK_DELAY_INIT },
+
/* Sound Devices USBPre2 */
{ USB_DEVICE(0x0926, 0x0202), .driver_info =
USB_QUIRK_ENDPOINT_IGNORE },
@@ -539,6 +545,9 @@ static const struct usb_device_id usb_quirk_list[] = {
{ USB_DEVICE(0x2040, 0x7200), .driver_info =
USB_QUIRK_CONFIG_INTF_STRINGS },
+ /* VLI disk */
+ { USB_DEVICE(0x2109, 0x0711), .driver_info = USB_QUIRK_NO_LPM },
+
/* Raydium Touchscreen */
{ USB_DEVICE(0x2386, 0x3114), .driver_info = USB_QUIRK_NO_LPM },
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index aaa39e6..27eae4c 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -1164,6 +1164,9 @@ struct dwc3_scratchpad_array {
* @gsbuscfg0_reqinfo: store GSBUSCFG0.DATRDREQINFO, DESRDREQINFO,
* DATWRREQINFO, and DESWRREQINFO value passed from
* glue driver.
+ * @wakeup_pending_funcs: Indicates whether any interface has requested for
+ * function wakeup in bitmap format where bit position
+ * represents interface_id.
*/
struct dwc3 {
struct work_struct drd_work;
@@ -1394,6 +1397,7 @@ struct dwc3 {
int num_ep_resized;
struct dentry *debug_root;
u32 gsbuscfg0_reqinfo;
+ u32 wakeup_pending_funcs;
};
#define INCRX_BURST_MODE 0
diff --git a/drivers/usb/dwc3/dwc3-xilinx.c b/drivers/usb/dwc3/dwc3-xilinx.c
index a33a42b..4ca7f62 100644
--- a/drivers/usb/dwc3/dwc3-xilinx.c
+++ b/drivers/usb/dwc3/dwc3-xilinx.c
@@ -207,15 +207,13 @@ static int dwc3_xlnx_init_zynqmp(struct dwc3_xlnx *priv_data)
skip_usb3_phy:
/* ulpi reset via gpio-modepin or gpio-framework driver */
- reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
+ reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
if (IS_ERR(reset_gpio)) {
return dev_err_probe(dev, PTR_ERR(reset_gpio),
"Failed to request reset GPIO\n");
}
if (reset_gpio) {
- /* Toggle ulpi to reset the phy. */
- gpiod_set_value_cansleep(reset_gpio, 1);
usleep_range(5000, 10000);
gpiod_set_value_cansleep(reset_gpio, 0);
usleep_range(5000, 10000);
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 47e73c4..3213612 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -276,8 +276,6 @@ int dwc3_send_gadget_generic_command(struct dwc3 *dwc, unsigned int cmd,
return ret;
}
-static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async);
-
/**
* dwc3_send_gadget_ep_cmd - issue an endpoint command
* @dep: the endpoint to which the command is going to be issued
@@ -2359,10 +2357,8 @@ static int dwc3_gadget_get_frame(struct usb_gadget *g)
return __dwc3_gadget_get_frame(dwc);
}
-static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async)
+static int __dwc3_gadget_wakeup(struct dwc3 *dwc)
{
- int retries;
-
int ret;
u32 reg;
@@ -2390,8 +2386,7 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async)
return -EINVAL;
}
- if (async)
- dwc3_gadget_enable_linksts_evts(dwc, true);
+ dwc3_gadget_enable_linksts_evts(dwc, true);
ret = dwc3_gadget_set_link_state(dwc, DWC3_LINK_STATE_RECOV);
if (ret < 0) {
@@ -2410,27 +2405,8 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async)
/*
* Since link status change events are enabled we will receive
- * an U0 event when wakeup is successful. So bail out.
+ * an U0 event when wakeup is successful.
*/
- if (async)
- return 0;
-
- /* poll until Link State changes to ON */
- retries = 20000;
-
- while (retries--) {
- reg = dwc3_readl(dwc->regs, DWC3_DSTS);
-
- /* in HS, means ON */
- if (DWC3_DSTS_USBLNKST(reg) == DWC3_LINK_STATE_U0)
- break;
- }
-
- if (DWC3_DSTS_USBLNKST(reg) != DWC3_LINK_STATE_U0) {
- dev_err(dwc->dev, "failed to send remote wakeup\n");
- return -EINVAL;
- }
-
return 0;
}
@@ -2451,7 +2427,7 @@ static int dwc3_gadget_wakeup(struct usb_gadget *g)
spin_unlock_irqrestore(&dwc->lock, flags);
return -EINVAL;
}
- ret = __dwc3_gadget_wakeup(dwc, true);
+ ret = __dwc3_gadget_wakeup(dwc);
spin_unlock_irqrestore(&dwc->lock, flags);
@@ -2479,14 +2455,10 @@ static int dwc3_gadget_func_wakeup(struct usb_gadget *g, int intf_id)
*/
link_state = dwc3_gadget_get_link_state(dwc);
if (link_state == DWC3_LINK_STATE_U3) {
- ret = __dwc3_gadget_wakeup(dwc, false);
- if (ret) {
- spin_unlock_irqrestore(&dwc->lock, flags);
- return -EINVAL;
- }
- dwc3_resume_gadget(dwc);
- dwc->suspended = false;
- dwc->link_state = DWC3_LINK_STATE_U0;
+ dwc->wakeup_pending_funcs |= BIT(intf_id);
+ ret = __dwc3_gadget_wakeup(dwc);
+ spin_unlock_irqrestore(&dwc->lock, flags);
+ return ret;
}
ret = dwc3_send_gadget_generic_command(dwc, DWC3_DGCMD_DEV_NOTIFICATION,
@@ -4353,6 +4325,8 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc,
{
enum dwc3_link_state next = evtinfo & DWC3_LINK_STATE_MASK;
unsigned int pwropt;
+ int ret;
+ int intf_id;
/*
* WORKAROUND: DWC3 < 2.50a have an issue when configured without
@@ -4428,7 +4402,7 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc,
switch (next) {
case DWC3_LINK_STATE_U0:
- if (dwc->gadget->wakeup_armed) {
+ if (dwc->gadget->wakeup_armed || dwc->wakeup_pending_funcs) {
dwc3_gadget_enable_linksts_evts(dwc, false);
dwc3_resume_gadget(dwc);
dwc->suspended = false;
@@ -4451,6 +4425,18 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc,
}
dwc->link_state = next;
+
+ /* Proceed with func wakeup if any interfaces that has requested */
+ while (dwc->wakeup_pending_funcs && (next == DWC3_LINK_STATE_U0)) {
+ intf_id = ffs(dwc->wakeup_pending_funcs) - 1;
+ ret = dwc3_send_gadget_generic_command(dwc, DWC3_DGCMD_DEV_NOTIFICATION,
+ DWC3_DGCMDPAR_DN_FUNC_WAKE |
+ DWC3_DGCMDPAR_INTF_SEL(intf_id));
+ if (ret)
+ dev_err(dwc->dev, "Failed to send DN wake for intf %d\n", intf_id);
+
+ dwc->wakeup_pending_funcs &= ~BIT(intf_id);
+ }
}
static void dwc3_gadget_suspend_interrupt(struct dwc3 *dwc,
@@ -4617,6 +4603,12 @@ static irqreturn_t dwc3_check_event_buf(struct dwc3_event_buffer *evt)
if (!count)
return IRQ_NONE;
+ if (count > evt->length) {
+ dev_err_ratelimited(dwc->dev, "invalid count(%u) > evt->length(%u)\n",
+ count, evt->length);
+ return IRQ_NONE;
+ }
+
evt->count = count;
evt->flags |= DWC3_EVENT_PENDING;
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 869ad99..8dbc132 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -2011,15 +2011,13 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)
if (f->get_status) {
status = f->get_status(f);
+
if (status < 0)
break;
- } else {
- /* Set D0 and D1 bits based on func wakeup capability */
- if (f->config->bmAttributes & USB_CONFIG_ATT_WAKEUP) {
- status |= USB_INTRF_STAT_FUNC_RW_CAP;
- if (f->func_wakeup_armed)
- status |= USB_INTRF_STAT_FUNC_RW;
- }
+
+ /* if D5 is not set, then device is not wakeup capable */
+ if (!(f->config->bmAttributes & USB_CONFIG_ATT_WAKEUP))
+ status &= ~(USB_INTRF_STAT_FUNC_RW_CAP | USB_INTRF_STAT_FUNC_RW);
}
put_unaligned_le16(status & 0x0000ffff, req->buf);
diff --git a/drivers/usb/gadget/function/f_ecm.c b/drivers/usb/gadget/function/f_ecm.c
index 80841de..0272263 100644
--- a/drivers/usb/gadget/function/f_ecm.c
+++ b/drivers/usb/gadget/function/f_ecm.c
@@ -892,6 +892,12 @@ static void ecm_resume(struct usb_function *f)
gether_resume(&ecm->port);
}
+static int ecm_get_status(struct usb_function *f)
+{
+ return (f->func_wakeup_armed ? USB_INTRF_STAT_FUNC_RW : 0) |
+ USB_INTRF_STAT_FUNC_RW_CAP;
+}
+
static void ecm_free(struct usb_function *f)
{
struct f_ecm *ecm;
@@ -960,6 +966,7 @@ static struct usb_function *ecm_alloc(struct usb_function_instance *fi)
ecm->port.func.disable = ecm_disable;
ecm->port.func.free_func = ecm_free;
ecm->port.func.suspend = ecm_suspend;
+ ecm->port.func.get_status = ecm_get_status;
ecm->port.func.resume = ecm_resume;
return &ecm->port.func;
diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c
index c7fdbc5..2957316 100644
--- a/drivers/usb/gadget/udc/tegra-xudc.c
+++ b/drivers/usb/gadget/udc/tegra-xudc.c
@@ -1749,6 +1749,10 @@ static int __tegra_xudc_ep_disable(struct tegra_xudc_ep *ep)
val = xudc_readl(xudc, CTRL);
val &= ~CTRL_RUN;
xudc_writel(xudc, val, CTRL);
+
+ val = xudc_readl(xudc, ST);
+ if (val & ST_RC)
+ xudc_writel(xudc, ST_RC, ST);
}
dev_info(xudc->dev, "ep %u disabled\n", ep->index);
diff --git a/drivers/usb/host/ohci-pci.c b/drivers/usb/host/ohci-pci.c
index 900ea0d..9f0a6b2 100644
--- a/drivers/usb/host/ohci-pci.c
+++ b/drivers/usb/host/ohci-pci.c
@@ -165,6 +165,25 @@ static int ohci_quirk_amd700(struct usb_hcd *hcd)
return 0;
}
+static int ohci_quirk_loongson(struct usb_hcd *hcd)
+{
+ struct pci_dev *pdev = to_pci_dev(hcd->self.controller);
+
+ /*
+ * Loongson's LS7A OHCI controller (rev 0x02) has a
+ * flaw. MMIO register with offset 0x60/64 is treated
+ * as legacy PS2-compatible keyboard/mouse interface.
+ * Since OHCI only use 4KB BAR resource, LS7A OHCI's
+ * 32KB BAR is wrapped around (the 2nd 4KB BAR space
+ * is the same as the 1st 4KB internally). So add 4KB
+ * offset (0x1000) to the OHCI registers as a quirk.
+ */
+ if (pdev->revision == 0x2)
+ hcd->regs += SZ_4K; /* SZ_4K = 0x1000 */
+
+ return 0;
+}
+
static int ohci_quirk_qemu(struct usb_hcd *hcd)
{
struct ohci_hcd *ohci = hcd_to_ohci(hcd);
@@ -225,6 +244,10 @@ static const struct pci_device_id ohci_pci_quirks[] = {
.driver_data = (unsigned long)ohci_quirk_amd700,
},
{
+ PCI_DEVICE(PCI_VENDOR_ID_LOONGSON, 0x7a24),
+ .driver_data = (unsigned long)ohci_quirk_loongson,
+ },
+ {
.vendor = PCI_VENDOR_ID_APPLE,
.device = 0x003f,
.subvendor = PCI_SUBVENDOR_ID_REDHAT_QUMRANET,
diff --git a/drivers/usb/host/uhci-platform.c b/drivers/usb/host/uhci-platform.c
index a7c9344..6231829 100644
--- a/drivers/usb/host/uhci-platform.c
+++ b/drivers/usb/host/uhci-platform.c
@@ -121,7 +121,7 @@ static int uhci_hcd_platform_probe(struct platform_device *pdev)
}
/* Get and enable clock if any specified */
- uhci->clk = devm_clk_get(&pdev->dev, NULL);
+ uhci->clk = devm_clk_get_optional(&pdev->dev, NULL);
if (IS_ERR(uhci->clk)) {
ret = PTR_ERR(uhci->clk);
goto err_rmr;
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index c0f2265..4863477 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -1878,9 +1878,10 @@ int xhci_bus_resume(struct usb_hcd *hcd)
int max_ports, port_index;
int sret;
u32 next_state;
- u32 temp, portsc;
+ u32 portsc;
struct xhci_hub *rhub;
struct xhci_port **ports;
+ bool disabled_irq = false;
rhub = xhci_get_rhub(hcd);
ports = rhub->ports;
@@ -1896,17 +1897,20 @@ int xhci_bus_resume(struct usb_hcd *hcd)
return -ESHUTDOWN;
}
- /* delay the irqs */
- temp = readl(&xhci->op_regs->command);
- temp &= ~CMD_EIE;
- writel(temp, &xhci->op_regs->command);
-
/* bus specific resume for ports we suspended at bus_suspend */
- if (hcd->speed >= HCD_USB3)
+ if (hcd->speed >= HCD_USB3) {
next_state = XDEV_U0;
- else
+ } else {
next_state = XDEV_RESUME;
-
+ if (bus_state->bus_suspended) {
+ /*
+ * prevent port event interrupts from interfering
+ * with usb2 port resume process
+ */
+ xhci_disable_interrupter(xhci->interrupters[0]);
+ disabled_irq = true;
+ }
+ }
port_index = max_ports;
while (port_index--) {
portsc = readl(ports[port_index]->addr);
@@ -1974,11 +1978,9 @@ int xhci_bus_resume(struct usb_hcd *hcd)
(void) readl(&xhci->op_regs->command);
bus_state->next_statechange = jiffies + msecs_to_jiffies(5);
- /* re-enable irqs */
- temp = readl(&xhci->op_regs->command);
- temp |= CMD_EIE;
- writel(temp, &xhci->op_regs->command);
- temp = readl(&xhci->op_regs->command);
+ /* re-enable interrupter */
+ if (disabled_irq)
+ xhci_enable_interrupter(xhci->interrupters[0]);
spin_unlock_irqrestore(&xhci->lock, flags);
return 0;
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 5d64c29..b906bc2 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -561,8 +561,8 @@ void xhci_ring_ep_doorbell(struct xhci_hcd *xhci,
* pointer command pending because the device can choose to start any
* stream once the endpoint is on the HW schedule.
*/
- if (ep_state & (EP_STOP_CMD_PENDING | SET_DEQ_PENDING | EP_HALTED |
- EP_CLEARING_TT | EP_STALLED))
+ if ((ep_state & EP_STOP_CMD_PENDING) || (ep_state & SET_DEQ_PENDING) ||
+ (ep_state & EP_HALTED) || (ep_state & EP_CLEARING_TT))
return;
trace_xhci_ring_ep_doorbell(slot_id, DB_VALUE(ep_index, stream_id));
@@ -2573,9 +2573,6 @@ static void process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep,
xhci_handle_halted_endpoint(xhci, ep, td, EP_SOFT_RESET);
return;
- case COMP_STALL_ERROR:
- ep->ep_state |= EP_STALLED;
- break;
default:
/* do nothing */
break;
@@ -2916,7 +2913,7 @@ static int handle_tx_event(struct xhci_hcd *xhci,
if (xhci_spurious_success_tx_event(xhci, ep_ring)) {
xhci_dbg(xhci, "Spurious event dma %pad, comp_code %u after %u\n",
&ep_trb_dma, trb_comp_code, ep_ring->old_trb_comp_code);
- ep_ring->old_trb_comp_code = trb_comp_code;
+ ep_ring->old_trb_comp_code = 0;
return 0;
}
@@ -3780,7 +3777,7 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
* enqueue a No Op TRB, this can prevent the Setup and Data Stage
* TRB to be breaked by the Link TRB.
*/
- if (trb_is_link(ep_ring->enqueue + 1)) {
+ if (last_trb_on_seg(ep_ring->enq_seg, ep_ring->enqueue + 1)) {
field = TRB_TYPE(TRB_TR_NOOP) | ep_ring->cycle_state;
queue_trb(xhci, ep_ring, false, 0, 0,
TRB_INTR_TARGET(0), field);
diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c
index b5c362c..0c7af44 100644
--- a/drivers/usb/host/xhci-tegra.c
+++ b/drivers/usb/host/xhci-tegra.c
@@ -1364,6 +1364,7 @@ static void tegra_xhci_id_work(struct work_struct *work)
tegra->otg_usb3_port = tegra_xusb_padctl_get_usb3_companion(tegra->padctl,
tegra->otg_usb2_port);
+ pm_runtime_get_sync(tegra->dev);
if (tegra->host_mode) {
/* switch to host mode */
if (tegra->otg_usb3_port >= 0) {
@@ -1393,6 +1394,7 @@ static void tegra_xhci_id_work(struct work_struct *work)
}
tegra_xhci_set_port_power(tegra, true, true);
+ pm_runtime_mark_last_busy(tegra->dev);
} else {
if (tegra->otg_usb3_port >= 0)
@@ -1400,6 +1402,7 @@ static void tegra_xhci_id_work(struct work_struct *work)
tegra_xhci_set_port_power(tegra, true, false);
}
+ pm_runtime_put_autosuspend(tegra->dev);
}
#if IS_ENABLED(CONFIG_PM) || IS_ENABLED(CONFIG_PM_SLEEP)
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 0452b8d..90eb491 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -322,7 +322,7 @@ static void xhci_zero_64b_regs(struct xhci_hcd *xhci)
xhci_info(xhci, "Fault detected\n");
}
-static int xhci_enable_interrupter(struct xhci_interrupter *ir)
+int xhci_enable_interrupter(struct xhci_interrupter *ir)
{
u32 iman;
@@ -335,7 +335,7 @@ static int xhci_enable_interrupter(struct xhci_interrupter *ir)
return 0;
}
-static int xhci_disable_interrupter(struct xhci_interrupter *ir)
+int xhci_disable_interrupter(struct xhci_interrupter *ir)
{
u32 iman;
@@ -1605,11 +1605,6 @@ static int xhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag
goto free_priv;
}
- /* Class driver might not be aware ep halted due to async URB giveback */
- if (*ep_state & EP_STALLED)
- dev_dbg(&urb->dev->dev, "URB %p queued before clearing halt\n",
- urb);
-
switch (usb_endpoint_type(&urb->ep->desc)) {
case USB_ENDPOINT_XFER_CONTROL:
@@ -1770,8 +1765,8 @@ static int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
goto done;
}
- /* In these cases no commands are pending but the endpoint is stopped */
- if (ep->ep_state & (EP_CLEARING_TT | EP_STALLED)) {
+ /* In this case no commands are pending but the endpoint is stopped */
+ if (ep->ep_state & EP_CLEARING_TT) {
/* and cancelled TDs can be given back right away */
xhci_dbg(xhci, "Invalidating TDs instantly on slot %d ep %d in state 0x%x\n",
urb->dev->slot_id, ep_index, ep->ep_state);
@@ -3209,11 +3204,8 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd,
ep = &vdev->eps[ep_index];
- spin_lock_irqsave(&xhci->lock, flags);
-
- ep->ep_state &= ~EP_STALLED;
-
/* Bail out if toggle is already being cleared by a endpoint reset */
+ spin_lock_irqsave(&xhci->lock, flags);
if (ep->ep_state & EP_HARD_CLEAR_TOGGLE) {
ep->ep_state &= ~EP_HARD_CLEAR_TOGGLE;
spin_unlock_irqrestore(&xhci->lock, flags);
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 37860f1..242ab9f 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -664,7 +664,7 @@ struct xhci_virt_ep {
unsigned int err_count;
unsigned int ep_state;
#define SET_DEQ_PENDING (1 << 0)
-#define EP_HALTED (1 << 1) /* Halted host ep handling */
+#define EP_HALTED (1 << 1) /* For stall handling */
#define EP_STOP_CMD_PENDING (1 << 2) /* For URB cancellation */
/* Transitioning the endpoint to using streams, don't enqueue URBs */
#define EP_GETTING_STREAMS (1 << 3)
@@ -675,7 +675,6 @@ struct xhci_virt_ep {
#define EP_SOFT_CLEAR_TOGGLE (1 << 7)
/* usb_hub_clear_tt_buffer is in progress */
#define EP_CLEARING_TT (1 << 8)
-#define EP_STALLED (1 << 9) /* For stall handling */
/* ---- Related to URB cancellation ---- */
struct list_head cancelled_td_list;
struct xhci_hcd *xhci;
@@ -1891,6 +1890,8 @@ int xhci_alloc_tt_info(struct xhci_hcd *xhci,
struct usb_tt *tt, gfp_t mem_flags);
int xhci_set_interrupter_moderation(struct xhci_interrupter *ir,
u32 imod_interval);
+int xhci_enable_interrupter(struct xhci_interrupter *ir);
+int xhci_disable_interrupter(struct xhci_interrupter *ir);
/* xHCI ring, segment, TRB, and TD functions */
dma_addr_t xhci_trb_virt_to_dma(struct xhci_segment *seg, union xhci_trb *trb);
diff --git a/drivers/usb/misc/onboard_usb_dev.c b/drivers/usb/misc/onboard_usb_dev.c
index 75ac3c6..f5372dfa 100644
--- a/drivers/usb/misc/onboard_usb_dev.c
+++ b/drivers/usb/misc/onboard_usb_dev.c
@@ -569,8 +569,14 @@ static void onboard_dev_usbdev_disconnect(struct usb_device *udev)
}
static const struct usb_device_id onboard_dev_id_table[] = {
- { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6504) }, /* CYUSB33{0,1,2}x/CYUSB230x 3.0 HUB */
- { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6506) }, /* CYUSB33{0,1,2}x/CYUSB230x 2.0 HUB */
+ { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6500) }, /* CYUSB330x 3.0 HUB */
+ { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6502) }, /* CYUSB330x 2.0 HUB */
+ { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6503) }, /* CYUSB33{0,1}x 2.0 HUB, Vendor Mode */
+ { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6504) }, /* CYUSB331x 3.0 HUB */
+ { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6506) }, /* CYUSB331x 2.0 HUB */
+ { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6507) }, /* CYUSB332x 2.0 HUB, Vendor Mode */
+ { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6508) }, /* CYUSB332x 3.0 HUB */
+ { USB_DEVICE(VENDOR_ID_CYPRESS, 0x650a) }, /* CYUSB332x 2.0 HUB */
{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6570) }, /* CY7C6563x 2.0 HUB */
{ USB_DEVICE(VENDOR_ID_GENESYS, 0x0608) }, /* Genesys Logic GL850G USB 2.0 HUB */
{ USB_DEVICE(VENDOR_ID_GENESYS, 0x0610) }, /* Genesys Logic GL852G USB 2.0 HUB */
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 9b34e23b7..6ac7a0a 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1093,6 +1093,8 @@ static const struct usb_device_id id_table_combined[] = {
{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602E_PID, 1) },
{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602E_PID, 2) },
{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602E_PID, 3) },
+ /* Abacus Electrics */
+ { USB_DEVICE(FTDI_VID, ABACUS_OPTICAL_PROBE_PID) },
{ } /* Terminating entry */
};
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 52be47d..9acb6f8 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -443,6 +443,11 @@
#define LINX_FUTURE_2_PID 0xF44C /* Linx future device */
/*
+ * Abacus Electrics
+ */
+#define ABACUS_OPTICAL_PROBE_PID 0xf458 /* ABACUS ELECTRICS Optical Probe */
+
+/*
* Oceanic product ids
*/
#define FTDI_OCEANIC_PID 0xF460 /* Oceanic dive instrument */
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 5cd26da..27879cc 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -611,6 +611,7 @@ static void option_instat_callback(struct urb *urb);
/* Sierra Wireless products */
#define SIERRA_VENDOR_ID 0x1199
#define SIERRA_PRODUCT_EM9191 0x90d3
+#define SIERRA_PRODUCT_EM9291 0x90e3
/* UNISOC (Spreadtrum) products */
#define UNISOC_VENDOR_ID 0x1782
@@ -2432,6 +2433,8 @@ static const struct usb_device_id option_ids[] = {
{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x30) },
{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x40) },
{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0, 0) },
+ { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9291, 0xff, 0xff, 0x30) },
+ { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9291, 0xff, 0xff, 0x40) },
{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) },
{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) },
{ USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0530, 0xff), /* TCL IK512 MBIM */
diff --git a/drivers/usb/serial/usb-serial-simple.c b/drivers/usb/serial/usb-serial-simple.c
index 2c12449..a0afaf2 100644
--- a/drivers/usb/serial/usb-serial-simple.c
+++ b/drivers/usb/serial/usb-serial-simple.c
@@ -100,6 +100,11 @@ DEVICE(nokia, NOKIA_IDS);
{ USB_DEVICE(0x09d7, 0x0100) } /* NovAtel FlexPack GPS */
DEVICE_N(novatel_gps, NOVATEL_IDS, 3);
+/* OWON electronic test and measurement equipment driver */
+#define OWON_IDS() \
+ { USB_DEVICE(0x5345, 0x1234) } /* HDS200 oscilloscopes and others */
+DEVICE(owon, OWON_IDS);
+
/* Siemens USB/MPI adapter */
#define SIEMENS_IDS() \
{ USB_DEVICE(0x908, 0x0004) }
@@ -134,6 +139,7 @@ static struct usb_serial_driver * const serial_drivers[] = {
&motorola_tetra_device,
&nokia_device,
&novatel_gps_device,
+ &owon_device,
&siemens_mpi_device,
&suunto_device,
&vivopay_device,
@@ -153,6 +159,7 @@ static const struct usb_device_id id_table[] = {
MOTOROLA_TETRA_IDS(),
NOKIA_IDS(),
NOVATEL_IDS(),
+ OWON_IDS(),
SIEMENS_IDS(),
SUUNTO_IDS(),
VIVOPAY_IDS(),
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index 1f8c9b1..d460d71 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -83,6 +83,13 @@ UNUSUAL_DEV(0x0bc2, 0x331a, 0x0000, 0x9999,
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_NO_REPORT_LUNS),
+/* Reported-by: Oliver Neukum <oneukum@suse.com> */
+UNUSUAL_DEV(0x125f, 0xa94a, 0x0160, 0x0160,
+ "ADATA",
+ "Portable HDD CH94",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_NO_ATA_1X),
+
/* Reported-by: Benjamin Tissoires <benjamin.tissoires@redhat.com> */
UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x9999,
"Initio Corporation",
diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index 9c76c3d..67a533e 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -1052,9 +1052,11 @@ struct typec_partner *typec_register_partner(struct typec_port *port,
partner->usb_mode = USB_MODE_USB3;
}
+ mutex_lock(&port->partner_link_lock);
ret = device_register(&partner->dev);
if (ret) {
dev_err(&port->dev, "failed to register partner (%d)\n", ret);
+ mutex_unlock(&port->partner_link_lock);
put_device(&partner->dev);
return ERR_PTR(ret);
}
@@ -1063,6 +1065,7 @@ struct typec_partner *typec_register_partner(struct typec_port *port,
typec_partner_link_device(partner, port->usb2_dev);
if (port->usb3_dev)
typec_partner_link_device(partner, port->usb3_dev);
+ mutex_unlock(&port->partner_link_lock);
return partner;
}
@@ -1083,12 +1086,18 @@ void typec_unregister_partner(struct typec_partner *partner)
port = to_typec_port(partner->dev.parent);
- if (port->usb2_dev)
+ mutex_lock(&port->partner_link_lock);
+ if (port->usb2_dev) {
typec_partner_unlink_device(partner, port->usb2_dev);
- if (port->usb3_dev)
+ port->usb2_dev = NULL;
+ }
+ if (port->usb3_dev) {
typec_partner_unlink_device(partner, port->usb3_dev);
+ port->usb3_dev = NULL;
+ }
device_unregister(&partner->dev);
+ mutex_unlock(&port->partner_link_lock);
}
EXPORT_SYMBOL_GPL(typec_unregister_partner);
@@ -2041,10 +2050,11 @@ static struct typec_partner *typec_get_partner(struct typec_port *port)
static void typec_partner_attach(struct typec_connector *con, struct device *dev)
{
struct typec_port *port = container_of(con, struct typec_port, con);
- struct typec_partner *partner = typec_get_partner(port);
+ struct typec_partner *partner;
struct usb_device *udev = to_usb_device(dev);
enum usb_mode usb_mode;
+ mutex_lock(&port->partner_link_lock);
if (udev->speed < USB_SPEED_SUPER) {
usb_mode = USB_MODE_USB2;
port->usb2_dev = dev;
@@ -2053,18 +2063,22 @@ static void typec_partner_attach(struct typec_connector *con, struct device *dev
port->usb3_dev = dev;
}
+ partner = typec_get_partner(port);
if (partner) {
typec_partner_set_usb_mode(partner, usb_mode);
typec_partner_link_device(partner, dev);
put_device(&partner->dev);
}
+ mutex_unlock(&port->partner_link_lock);
}
static void typec_partner_deattach(struct typec_connector *con, struct device *dev)
{
struct typec_port *port = container_of(con, struct typec_port, con);
- struct typec_partner *partner = typec_get_partner(port);
+ struct typec_partner *partner;
+ mutex_lock(&port->partner_link_lock);
+ partner = typec_get_partner(port);
if (partner) {
typec_partner_unlink_device(partner, dev);
put_device(&partner->dev);
@@ -2074,6 +2088,7 @@ static void typec_partner_deattach(struct typec_connector *con, struct device *d
port->usb2_dev = NULL;
else if (port->usb3_dev == dev)
port->usb3_dev = NULL;
+ mutex_unlock(&port->partner_link_lock);
}
/**
@@ -2614,6 +2629,7 @@ struct typec_port *typec_register_port(struct device *parent,
ida_init(&port->mode_ids);
mutex_init(&port->port_type_lock);
+ mutex_init(&port->partner_link_lock);
port->id = id;
port->ops = cap->ops;
diff --git a/drivers/usb/typec/class.h b/drivers/usb/typec/class.h
index b3076a2..db2fe96 100644
--- a/drivers/usb/typec/class.h
+++ b/drivers/usb/typec/class.h
@@ -59,6 +59,7 @@ struct typec_port {
enum typec_port_type port_type;
enum usb_mode usb_mode;
struct mutex port_type_lock;
+ struct mutex partner_link_lock;
enum typec_orientation orientation;
struct typec_switch *sw;
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index a99db4e..8adf6f9 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -5965,7 +5965,7 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1,
case SNK_TRY_WAIT_DEBOUNCE:
if (!tcpm_port_is_sink(port)) {
port->max_wait = 0;
- tcpm_set_state(port, SRC_TRYWAIT, 0);
+ tcpm_set_state(port, SRC_TRYWAIT, PD_T_PD_DEBOUNCE);
}
break;
case SRC_TRY_WAIT:
diff --git a/drivers/usb/typec/ucsi/displayport.c b/drivers/usb/typec/ucsi/displayport.c
index 420af51..8aae80b 100644
--- a/drivers/usb/typec/ucsi/displayport.c
+++ b/drivers/usb/typec/ucsi/displayport.c
@@ -54,7 +54,8 @@ static int ucsi_displayport_enter(struct typec_altmode *alt, u32 *vdo)
u8 cur = 0;
int ret;
- mutex_lock(&dp->con->lock);
+ if (!ucsi_con_mutex_lock(dp->con))
+ return -ENOTCONN;
if (!dp->override && dp->initialized) {
const struct typec_altmode *p = typec_altmode_get_partner(alt);
@@ -100,7 +101,7 @@ static int ucsi_displayport_enter(struct typec_altmode *alt, u32 *vdo)
schedule_work(&dp->work);
ret = 0;
err_unlock:
- mutex_unlock(&dp->con->lock);
+ ucsi_con_mutex_unlock(dp->con);
return ret;
}
@@ -112,7 +113,8 @@ static int ucsi_displayport_exit(struct typec_altmode *alt)
u64 command;
int ret = 0;
- mutex_lock(&dp->con->lock);
+ if (!ucsi_con_mutex_lock(dp->con))
+ return -ENOTCONN;
if (!dp->override) {
const struct typec_altmode *p = typec_altmode_get_partner(alt);
@@ -144,7 +146,7 @@ static int ucsi_displayport_exit(struct typec_altmode *alt)
schedule_work(&dp->work);
out_unlock:
- mutex_unlock(&dp->con->lock);
+ ucsi_con_mutex_unlock(dp->con);
return ret;
}
@@ -202,20 +204,21 @@ static int ucsi_displayport_vdm(struct typec_altmode *alt,
int cmd = PD_VDO_CMD(header);
int svdm_version;
- mutex_lock(&dp->con->lock);
+ if (!ucsi_con_mutex_lock(dp->con))
+ return -ENOTCONN;
if (!dp->override && dp->initialized) {
const struct typec_altmode *p = typec_altmode_get_partner(alt);
dev_warn(&p->dev,
"firmware doesn't support alternate mode overriding\n");
- mutex_unlock(&dp->con->lock);
+ ucsi_con_mutex_unlock(dp->con);
return -EOPNOTSUPP;
}
svdm_version = typec_altmode_get_svdm_version(alt);
if (svdm_version < 0) {
- mutex_unlock(&dp->con->lock);
+ ucsi_con_mutex_unlock(dp->con);
return svdm_version;
}
@@ -259,7 +262,7 @@ static int ucsi_displayport_vdm(struct typec_altmode *alt,
break;
}
- mutex_unlock(&dp->con->lock);
+ ucsi_con_mutex_unlock(dp->con);
return 0;
}
@@ -296,6 +299,8 @@ void ucsi_displayport_remove_partner(struct typec_altmode *alt)
if (!dp)
return;
+ cancel_work_sync(&dp->work);
+
dp->data.conf = 0;
dp->data.status = 0;
dp->initialized = false;
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index e8c7e9d..01ce858 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -1923,6 +1923,40 @@ void ucsi_set_drvdata(struct ucsi *ucsi, void *data)
EXPORT_SYMBOL_GPL(ucsi_set_drvdata);
/**
+ * ucsi_con_mutex_lock - Acquire the connector mutex
+ * @con: The connector interface to lock
+ *
+ * Returns true on success, false if the connector is disconnected
+ */
+bool ucsi_con_mutex_lock(struct ucsi_connector *con)
+{
+ bool mutex_locked = false;
+ bool connected = true;
+
+ while (connected && !mutex_locked) {
+ mutex_locked = mutex_trylock(&con->lock) != 0;
+ connected = UCSI_CONSTAT(con, CONNECTED);
+ if (connected && !mutex_locked)
+ msleep(20);
+ }
+
+ connected = connected && con->partner;
+ if (!connected && mutex_locked)
+ mutex_unlock(&con->lock);
+
+ return connected;
+}
+
+/**
+ * ucsi_con_mutex_unlock - Release the connector mutex
+ * @con: The connector interface to unlock
+ */
+void ucsi_con_mutex_unlock(struct ucsi_connector *con)
+{
+ mutex_unlock(&con->lock);
+}
+
+/**
* ucsi_create - Allocate UCSI instance
* @dev: Device interface to the PPM (Platform Policy Manager)
* @ops: I/O routines
diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h
index 3a2c176..9c5278a 100644
--- a/drivers/usb/typec/ucsi/ucsi.h
+++ b/drivers/usb/typec/ucsi/ucsi.h
@@ -94,6 +94,8 @@ int ucsi_register(struct ucsi *ucsi);
void ucsi_unregister(struct ucsi *ucsi);
void *ucsi_get_drvdata(struct ucsi *ucsi);
void ucsi_set_drvdata(struct ucsi *ucsi, void *data);
+bool ucsi_con_mutex_lock(struct ucsi_connector *con);
+void ucsi_con_mutex_unlock(struct ucsi_connector *con);
void ucsi_connector_change(struct ucsi *ucsi, u8 num);
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index 1443739..8f02f23 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -1815,7 +1815,7 @@ int vfio_config_init(struct vfio_pci_core_device *vdev)
}
if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx ||
- vdev->pdev->irq == IRQ_NOTCONNECTED)
+ !vdev->pdev->irq || vdev->pdev->irq == IRQ_NOTCONNECTED)
vconfig[PCI_INTERRUPT_PIN] = 0;
ret = vfio_cap_init(vdev);
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index f6f5a7a..26bcf3a 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -627,6 +627,9 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
int ret;
llnode = llist_del_all(&svq->completion_list);
+
+ mutex_lock(&svq->vq.mutex);
+
llist_for_each_entry_safe(cmd, t, llnode, tvc_completion_list) {
se_cmd = &cmd->tvc_se_cmd;
@@ -660,6 +663,8 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
vhost_scsi_release_cmd_res(se_cmd);
}
+ mutex_unlock(&svq->vq.mutex);
+
if (signal)
vhost_signal(&svq->vs->dev, &svq->vq);
}
@@ -994,39 +999,66 @@ static void vhost_scsi_target_queue_cmd(struct vhost_scsi_nexus *nexus,
static void
vhost_scsi_send_status(struct vhost_scsi *vs, struct vhost_virtqueue *vq,
- int head, unsigned int out, u8 status)
+ struct vhost_scsi_ctx *vc, u8 status)
{
- struct virtio_scsi_cmd_resp __user *resp;
struct virtio_scsi_cmd_resp rsp;
+ struct iov_iter iov_iter;
int ret;
memset(&rsp, 0, sizeof(rsp));
rsp.status = status;
- resp = vq->iov[out].iov_base;
- ret = __copy_to_user(resp, &rsp, sizeof(rsp));
- if (!ret)
- vhost_add_used_and_signal(&vs->dev, vq, head, 0);
+
+ iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[vc->out], vc->in,
+ sizeof(rsp));
+
+ ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter);
+
+ if (likely(ret == sizeof(rsp)))
+ vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
else
pr_err("Faulted on virtio_scsi_cmd_resp\n");
}
+#define TYPE_IO_CMD 0
+#define TYPE_CTRL_TMF 1
+#define TYPE_CTRL_AN 2
+
static void
vhost_scsi_send_bad_target(struct vhost_scsi *vs,
struct vhost_virtqueue *vq,
- int head, unsigned out)
+ struct vhost_scsi_ctx *vc, int type)
{
- struct virtio_scsi_cmd_resp __user *resp;
- struct virtio_scsi_cmd_resp rsp;
+ union {
+ struct virtio_scsi_cmd_resp cmd;
+ struct virtio_scsi_ctrl_tmf_resp tmf;
+ struct virtio_scsi_ctrl_an_resp an;
+ } rsp;
+ struct iov_iter iov_iter;
+ size_t rsp_size;
int ret;
memset(&rsp, 0, sizeof(rsp));
- rsp.response = VIRTIO_SCSI_S_BAD_TARGET;
- resp = vq->iov[out].iov_base;
- ret = __copy_to_user(resp, &rsp, sizeof(rsp));
- if (!ret)
- vhost_add_used_and_signal(&vs->dev, vq, head, 0);
+
+ if (type == TYPE_IO_CMD) {
+ rsp_size = sizeof(struct virtio_scsi_cmd_resp);
+ rsp.cmd.response = VIRTIO_SCSI_S_BAD_TARGET;
+ } else if (type == TYPE_CTRL_TMF) {
+ rsp_size = sizeof(struct virtio_scsi_ctrl_tmf_resp);
+ rsp.tmf.response = VIRTIO_SCSI_S_BAD_TARGET;
+ } else {
+ rsp_size = sizeof(struct virtio_scsi_ctrl_an_resp);
+ rsp.an.response = VIRTIO_SCSI_S_BAD_TARGET;
+ }
+
+ iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[vc->out], vc->in,
+ rsp_size);
+
+ ret = copy_to_iter(&rsp, rsp_size, &iov_iter);
+
+ if (likely(ret == rsp_size))
+ vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
else
- pr_err("Faulted on virtio_scsi_cmd_resp\n");
+ pr_err("Faulted on virtio scsi type=%d\n", type);
}
static int
@@ -1390,9 +1422,9 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
if (ret == -ENXIO)
break;
else if (ret == -EIO)
- vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out);
+ vhost_scsi_send_bad_target(vs, vq, &vc, TYPE_IO_CMD);
else if (ret == -ENOMEM)
- vhost_scsi_send_status(vs, vq, vc.head, vc.out,
+ vhost_scsi_send_status(vs, vq, &vc,
SAM_STAT_TASK_SET_FULL);
} while (likely(!vhost_exceeds_weight(vq, ++c, 0)));
out:
@@ -1432,8 +1464,11 @@ static void vhost_scsi_tmf_resp_work(struct vhost_work *work)
else
resp_code = VIRTIO_SCSI_S_FUNCTION_REJECTED;
+ mutex_lock(&tmf->svq->vq.mutex);
vhost_scsi_send_tmf_resp(tmf->vhost, &tmf->svq->vq, tmf->in_iovs,
tmf->vq_desc, &tmf->resp_iov, resp_code);
+ mutex_unlock(&tmf->svq->vq.mutex);
+
vhost_scsi_release_tmf_res(tmf);
}
@@ -1623,7 +1658,10 @@ vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
if (ret == -ENXIO)
break;
else if (ret == -EIO)
- vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out);
+ vhost_scsi_send_bad_target(vs, vq, &vc,
+ v_req.type == VIRTIO_SCSI_T_TMF ?
+ TYPE_CTRL_TMF :
+ TYPE_CTRL_AN);
} while (likely(!vhost_exceeds_weight(vq, ++c, 0)));
out:
mutex_unlock(&vq->mutex);
diff --git a/drivers/virt/coco/tsm.c b/drivers/virt/coco/tsm.c
index 9432d4e..096f4f7 100644
--- a/drivers/virt/coco/tsm.c
+++ b/drivers/virt/coco/tsm.c
@@ -15,6 +15,7 @@
static struct tsm_provider {
const struct tsm_ops *ops;
void *data;
+ atomic_t count;
} provider;
static DECLARE_RWSEM(tsm_rwsem);
@@ -92,6 +93,10 @@ static ssize_t tsm_report_privlevel_store(struct config_item *cfg,
if (rc)
return rc;
+ guard(rwsem_write)(&tsm_rwsem);
+ if (!provider.ops)
+ return -ENXIO;
+
/*
* The valid privilege levels that a TSM might accept, if it accepts a
* privilege level setting at all, are a max of TSM_PRIVLEVEL_MAX (see
@@ -101,7 +106,6 @@ static ssize_t tsm_report_privlevel_store(struct config_item *cfg,
if (provider.ops->privlevel_floor > val || val > TSM_PRIVLEVEL_MAX)
return -EINVAL;
- guard(rwsem_write)(&tsm_rwsem);
rc = try_advance_write_generation(report);
if (rc)
return rc;
@@ -115,6 +119,10 @@ static ssize_t tsm_report_privlevel_floor_show(struct config_item *cfg,
char *buf)
{
guard(rwsem_read)(&tsm_rwsem);
+
+ if (!provider.ops)
+ return -ENXIO;
+
return sysfs_emit(buf, "%u\n", provider.ops->privlevel_floor);
}
CONFIGFS_ATTR_RO(tsm_report_, privlevel_floor);
@@ -217,6 +225,9 @@ CONFIGFS_ATTR_RO(tsm_report_, generation);
static ssize_t tsm_report_provider_show(struct config_item *cfg, char *buf)
{
guard(rwsem_read)(&tsm_rwsem);
+ if (!provider.ops)
+ return -ENXIO;
+
return sysfs_emit(buf, "%s\n", provider.ops->name);
}
CONFIGFS_ATTR_RO(tsm_report_, provider);
@@ -421,12 +432,20 @@ static struct config_item *tsm_report_make_item(struct config_group *group,
if (!state)
return ERR_PTR(-ENOMEM);
+ atomic_inc(&provider.count);
config_item_init_type_name(&state->cfg, name, &tsm_report_type);
return &state->cfg;
}
+static void tsm_report_drop_item(struct config_group *group, struct config_item *item)
+{
+ config_item_put(item);
+ atomic_dec(&provider.count);
+}
+
static struct configfs_group_operations tsm_report_group_ops = {
.make_item = tsm_report_make_item,
+ .drop_item = tsm_report_drop_item,
};
static const struct config_item_type tsm_reports_type = {
@@ -459,6 +478,11 @@ int tsm_register(const struct tsm_ops *ops, void *priv)
return -EBUSY;
}
+ if (atomic_read(&provider.count)) {
+ pr_err("configfs/tsm not empty\n");
+ return -EBUSY;
+ }
+
provider.ops = ops;
provider.data = priv;
return 0;
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 150753c..95d5d79 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -407,6 +407,12 @@ static void virtio_dev_shutdown(struct device *_d)
if (!drv)
return;
+ /* If the driver has its own shutdown method, use that. */
+ if (drv->shutdown) {
+ drv->shutdown(dev);
+ return;
+ }
+
/*
* Some devices get wedged if you kick them after they are
* reset. Mark all vqs as broken to make sure we don't.
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 5eaade7..d50fe03 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -247,7 +247,7 @@ virtio_pci_admin_cmd_dev_parts_objects_enable(struct virtio_device *virtio_dev)
sg_init_one(&data_sg, get_data, sizeof(*get_data));
sg_init_one(&result_sg, result, sizeof(*result));
cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_DEVICE_CAP_GET);
- cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+ cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SELF);
cmd.data_sg = &data_sg;
cmd.result_sg = &result_sg;
ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
@@ -305,7 +305,7 @@ static void virtio_pci_admin_cmd_cap_init(struct virtio_device *virtio_dev)
sg_init_one(&result_sg, data, sizeof(*data));
cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_CAP_ID_LIST_QUERY);
- cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+ cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SELF);
cmd.result_sg = &result_sg;
ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index fdd2d2b..b784aab 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -2650,7 +2650,7 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
struct vring_virtqueue *vq = to_vvq(_vq);
if (vq->event_triggered)
- vq->event_triggered = false;
+ data_race(vq->event_triggered = false);
return vq->packed_ring ? virtqueue_enable_cb_delayed_packed(_vq) :
virtqueue_enable_cb_delayed_split(_vq);
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index f7d6f479..24f4858 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -278,7 +278,7 @@
config XEN_ACPI_PROCESSOR
tristate "Xen ACPI processor"
- depends on XEN && XEN_PV_DOM0 && X86 && ACPI_PROCESSOR && CPU_FREQ
+ depends on XEN && XEN_DOM0 && X86 && ACPI_PROCESSOR && CPU_FREQ
default m
help
This ACPI processor uploads Power Management information to the Xen
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 65d4e7f..8c85280 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -679,7 +679,7 @@ void xen_free_ballooned_pages(unsigned int nr_pages, struct page **pages)
}
EXPORT_SYMBOL(xen_free_ballooned_pages);
-static void __init balloon_add_regions(void)
+static int __init balloon_add_regions(void)
{
unsigned long start_pfn, pages;
unsigned long pfn, extra_pfn_end;
@@ -702,26 +702,38 @@ static void __init balloon_add_regions(void)
for (pfn = start_pfn; pfn < extra_pfn_end; pfn++)
balloon_append(pfn_to_page(pfn));
- balloon_stats.total_pages += extra_pfn_end - start_pfn;
+ /*
+ * Extra regions are accounted for in the physmap, but need
+ * decreasing from current_pages to balloon down the initial
+ * allocation, because they are already accounted for in
+ * total_pages.
+ */
+ if (extra_pfn_end - start_pfn >= balloon_stats.current_pages) {
+ WARN(1, "Extra pages underflow current target");
+ return -ERANGE;
+ }
+ balloon_stats.current_pages -= extra_pfn_end - start_pfn;
}
+
+ return 0;
}
static int __init balloon_init(void)
{
struct task_struct *task;
+ int rc;
if (!xen_domain())
return -ENODEV;
pr_info("Initialising balloon driver\n");
-#ifdef CONFIG_XEN_PV
- balloon_stats.current_pages = xen_pv_domain()
- ? min(xen_start_info->nr_pages - xen_released_pages, max_pfn)
- : get_num_physpages();
-#else
- balloon_stats.current_pages = get_num_physpages();
-#endif
+ if (xen_released_pages >= get_num_physpages()) {
+ WARN(1, "Released pages underflow current target");
+ return -ERANGE;
+ }
+
+ balloon_stats.current_pages = get_num_physpages() - xen_released_pages;
balloon_stats.target_pages = balloon_stats.current_pages;
balloon_stats.balloon_low = 0;
balloon_stats.balloon_high = 0;
@@ -738,7 +750,9 @@ static int __init balloon_init(void)
register_sysctl_init("xen/balloon", balloon_table);
#endif
- balloon_add_regions();
+ rc = balloon_add_regions();
+ if (rc)
+ return rc;
task = kthread_run(balloon_thread, NULL, "xen-balloon");
if (IS_ERR(task)) {
diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c
index fcb335b..6d18192 100644
--- a/drivers/xen/xenbus/xenbus_probe_frontend.c
+++ b/drivers/xen/xenbus/xenbus_probe_frontend.c
@@ -513,4 +513,5 @@ static int __init boot_wait_for_devices(void)
late_initcall(boot_wait_for_devices);
#endif
+MODULE_DESCRIPTION("Xen PV-device frontend support");
MODULE_LICENSE("GPL");
diff --git a/fs/Kconfig b/fs/Kconfig
index c718b2e..5b4847b 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -368,6 +368,7 @@
config LOCKD
tristate
depends on FILE_LOCKING
+ select CRC32
select GRACE_PERIOD
config LOCKD_V4
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index 691e0ae..8c61307 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -348,9 +348,9 @@ static int afs_dynroot_readdir(struct file *file, struct dir_context *ctx)
}
if ((unsigned long long)ctx->pos <= AFS_MAX_DYNROOT_CELL_INO) {
- rcu_read_lock();
+ down_read(&net->cells_lock);
ret = afs_dynroot_readdir_cells(net, ctx);
- rcu_read_unlock();
+ up_read(&net->cells_lock);
}
return ret;
}
diff --git a/fs/bcachefs/Kconfig b/fs/bcachefs/Kconfig
index bf1c94e..07709b0 100644
--- a/fs/bcachefs/Kconfig
+++ b/fs/bcachefs/Kconfig
@@ -4,7 +4,7 @@
depends on BLOCK
select EXPORTFS
select CLOSURES
- select LIBCRC32C
+ select CRC32
select CRC64
select FS_POSIX_ACL
select LZ4_COMPRESS
@@ -15,10 +15,9 @@
select ZLIB_INFLATE
select ZSTD_COMPRESS
select ZSTD_DECOMPRESS
- select CRYPTO
select CRYPTO_LIB_SHA256
- select CRYPTO_CHACHA20
- select CRYPTO_POLY1305
+ select CRYPTO_LIB_CHACHA
+ select CRYPTO_LIB_POLY1305
select KEYS
select RAID6_PQ
select XOR_BLOCKS
diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c
index 7c930ef..effafc3 100644
--- a/fs/bcachefs/alloc_foreground.c
+++ b/fs/bcachefs/alloc_foreground.c
@@ -1425,6 +1425,8 @@ int bch2_alloc_sectors_start_trans(struct btree_trans *trans,
open_bucket_for_each(c, &wp->ptrs, ob, i)
wp->sectors_free = min(wp->sectors_free, ob->sectors_free);
+ wp->sectors_free = rounddown(wp->sectors_free, block_sectors(c));
+
BUG_ON(!wp->sectors_free || wp->sectors_free == UINT_MAX);
return 0;
diff --git a/fs/bcachefs/alloc_foreground.h b/fs/bcachefs/alloc_foreground.h
index 69ec6a0..4c1e33c 100644
--- a/fs/bcachefs/alloc_foreground.h
+++ b/fs/bcachefs/alloc_foreground.h
@@ -110,7 +110,9 @@ static inline void bch2_alloc_sectors_done_inlined(struct bch_fs *c, struct writ
unsigned i;
open_bucket_for_each(c, &wp->ptrs, ob, i)
- ob_push(c, !ob->sectors_free ? &ptrs : &keep, ob);
+ ob_push(c, ob->sectors_free < block_sectors(c)
+ ? &ptrs
+ : &keep, ob);
wp->ptrs = keep;
mutex_unlock(&wp->lock);
diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index 5d9f208..75f7408 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -788,6 +788,8 @@ struct bch_fs {
unsigned long errors_silent[BITS_TO_LONGS(BCH_FSCK_ERR_MAX)];
u64 btrees_lost_data;
} sb;
+ DARRAY(enum bcachefs_metadata_version)
+ incompat_versions_requested;
#ifdef CONFIG_UNICODE
struct unicode_map *cf_encoding;
@@ -981,8 +983,8 @@ struct bch_fs {
mempool_t compress_workspace[BCH_COMPRESSION_OPT_NR];
size_t zstd_workspace_size;
- struct crypto_sync_skcipher *chacha20;
- struct crypto_shash *poly1305;
+ struct bch_key chacha20_key;
+ bool chacha20_key_set;
atomic64_t key_version;
diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index a3db328..d6e4a49 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -366,6 +366,10 @@ static inline void bkey_init(struct bkey *k)
#define __BKEY_PADDED(key, pad) \
struct bkey_i key; __u64 key ## _pad[pad]
+enum bch_bkey_type_flags {
+ BKEY_TYPE_strict_btree_checks = BIT(0),
+};
+
/*
* - DELETED keys are used internally to mark keys that should be ignored but
* override keys in composition order. Their version number is ignored.
@@ -383,46 +387,46 @@ static inline void bkey_init(struct bkey *k)
*
* - WHITEOUT: for hash table btrees
*/
-#define BCH_BKEY_TYPES() \
- x(deleted, 0) \
- x(whiteout, 1) \
- x(error, 2) \
- x(cookie, 3) \
- x(hash_whiteout, 4) \
- x(btree_ptr, 5) \
- x(extent, 6) \
- x(reservation, 7) \
- x(inode, 8) \
- x(inode_generation, 9) \
- x(dirent, 10) \
- x(xattr, 11) \
- x(alloc, 12) \
- x(quota, 13) \
- x(stripe, 14) \
- x(reflink_p, 15) \
- x(reflink_v, 16) \
- x(inline_data, 17) \
- x(btree_ptr_v2, 18) \
- x(indirect_inline_data, 19) \
- x(alloc_v2, 20) \
- x(subvolume, 21) \
- x(snapshot, 22) \
- x(inode_v2, 23) \
- x(alloc_v3, 24) \
- x(set, 25) \
- x(lru, 26) \
- x(alloc_v4, 27) \
- x(backpointer, 28) \
- x(inode_v3, 29) \
- x(bucket_gens, 30) \
- x(snapshot_tree, 31) \
- x(logged_op_truncate, 32) \
- x(logged_op_finsert, 33) \
- x(accounting, 34) \
- x(inode_alloc_cursor, 35)
+#define BCH_BKEY_TYPES() \
+ x(deleted, 0, 0) \
+ x(whiteout, 1, 0) \
+ x(error, 2, 0) \
+ x(cookie, 3, 0) \
+ x(hash_whiteout, 4, BKEY_TYPE_strict_btree_checks) \
+ x(btree_ptr, 5, BKEY_TYPE_strict_btree_checks) \
+ x(extent, 6, BKEY_TYPE_strict_btree_checks) \
+ x(reservation, 7, BKEY_TYPE_strict_btree_checks) \
+ x(inode, 8, BKEY_TYPE_strict_btree_checks) \
+ x(inode_generation, 9, BKEY_TYPE_strict_btree_checks) \
+ x(dirent, 10, BKEY_TYPE_strict_btree_checks) \
+ x(xattr, 11, BKEY_TYPE_strict_btree_checks) \
+ x(alloc, 12, BKEY_TYPE_strict_btree_checks) \
+ x(quota, 13, BKEY_TYPE_strict_btree_checks) \
+ x(stripe, 14, BKEY_TYPE_strict_btree_checks) \
+ x(reflink_p, 15, BKEY_TYPE_strict_btree_checks) \
+ x(reflink_v, 16, BKEY_TYPE_strict_btree_checks) \
+ x(inline_data, 17, BKEY_TYPE_strict_btree_checks) \
+ x(btree_ptr_v2, 18, BKEY_TYPE_strict_btree_checks) \
+ x(indirect_inline_data, 19, BKEY_TYPE_strict_btree_checks) \
+ x(alloc_v2, 20, BKEY_TYPE_strict_btree_checks) \
+ x(subvolume, 21, BKEY_TYPE_strict_btree_checks) \
+ x(snapshot, 22, BKEY_TYPE_strict_btree_checks) \
+ x(inode_v2, 23, BKEY_TYPE_strict_btree_checks) \
+ x(alloc_v3, 24, BKEY_TYPE_strict_btree_checks) \
+ x(set, 25, 0) \
+ x(lru, 26, BKEY_TYPE_strict_btree_checks) \
+ x(alloc_v4, 27, BKEY_TYPE_strict_btree_checks) \
+ x(backpointer, 28, BKEY_TYPE_strict_btree_checks) \
+ x(inode_v3, 29, BKEY_TYPE_strict_btree_checks) \
+ x(bucket_gens, 30, BKEY_TYPE_strict_btree_checks) \
+ x(snapshot_tree, 31, BKEY_TYPE_strict_btree_checks) \
+ x(logged_op_truncate, 32, BKEY_TYPE_strict_btree_checks) \
+ x(logged_op_finsert, 33, BKEY_TYPE_strict_btree_checks) \
+ x(accounting, 34, BKEY_TYPE_strict_btree_checks) \
+ x(inode_alloc_cursor, 35, BKEY_TYPE_strict_btree_checks)
enum bch_bkey_type {
-#define x(name, nr) KEY_TYPE_##name = nr,
+#define x(name, nr, ...) KEY_TYPE_##name = nr,
BCH_BKEY_TYPES()
#undef x
KEY_TYPE_MAX,
@@ -863,6 +867,7 @@ LE64_BITMASK(BCH_SB_VERSION_INCOMPAT_ALLOWED,
LE64_BITMASK(BCH_SB_SHARD_INUMS_NBITS, struct bch_sb, flags[6], 0, 4);
LE64_BITMASK(BCH_SB_WRITE_ERROR_TIMEOUT,struct bch_sb, flags[6], 4, 14);
LE64_BITMASK(BCH_SB_CSUM_ERR_RETRY_NR, struct bch_sb, flags[6], 14, 20);
+LE64_BITMASK(BCH_SB_CASEFOLD, struct bch_sb, flags[6], 22, 23);
static inline __u64 BCH_SB_COMPRESSION_TYPE(const struct bch_sb *sb)
{
diff --git a/fs/bcachefs/bkey_methods.c b/fs/bcachefs/bkey_methods.c
index 15c9357..00d05cc 100644
--- a/fs/bcachefs/bkey_methods.c
+++ b/fs/bcachefs/bkey_methods.c
@@ -21,7 +21,7 @@
#include "xattr.h"
const char * const bch2_bkey_types[] = {
-#define x(name, nr) #name,
+#define x(name, nr, ...) #name,
BCH_BKEY_TYPES()
#undef x
NULL
@@ -115,7 +115,7 @@ static bool key_type_set_merge(struct bch_fs *c, struct bkey_s l, struct bkey_s_
})
const struct bkey_ops bch2_bkey_ops[] = {
-#define x(name, nr) [KEY_TYPE_##name] = bch2_bkey_ops_##name,
+#define x(name, nr, ...) [KEY_TYPE_##name] = bch2_bkey_ops_##name,
BCH_BKEY_TYPES()
#undef x
};
@@ -155,6 +155,12 @@ static u64 bch2_key_types_allowed[] = {
#undef x
};
+static const enum bch_bkey_type_flags bch2_bkey_type_flags[] = {
+#define x(name, nr, flags) [KEY_TYPE_##name] = flags,
+ BCH_BKEY_TYPES()
+#undef x
+};
+
const char *bch2_btree_node_type_str(enum btree_node_type type)
{
return type == BKEY_TYPE_btree ? "internal btree node" : bch2_btree_id_str(type - 1);
@@ -177,8 +183,18 @@ int __bch2_bkey_validate(struct bch_fs *c, struct bkey_s_c k,
if (type >= BKEY_TYPE_NR)
return 0;
- bkey_fsck_err_on(k.k->type < KEY_TYPE_MAX &&
- (type == BKEY_TYPE_btree || (from.flags & BCH_VALIDATE_commit)) &&
+ enum bch_bkey_type_flags bkey_flags = k.k->type < KEY_TYPE_MAX
+ ? bch2_bkey_type_flags[k.k->type]
+ : 0;
+
+ bool strict_key_type_allowed =
+ (from.flags & BCH_VALIDATE_commit) ||
+ type == BKEY_TYPE_btree ||
+ (from.btree < BTREE_ID_NR &&
+ (bkey_flags & BKEY_TYPE_strict_btree_checks));
+
+ bkey_fsck_err_on(strict_key_type_allowed &&
+ k.k->type < KEY_TYPE_MAX &&
!(bch2_key_types_allowed[type] & BIT_ULL(k.k->type)),
c, bkey_invalid_type_for_btree,
"invalid key type for btree %s (%s)",
diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index e34e959..59fa527 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -2577,7 +2577,10 @@ struct bkey_s_c bch2_btree_iter_peek_prev_min(struct btree_trans *trans, struct
struct bpos end)
{
if ((iter->flags & (BTREE_ITER_is_extents|BTREE_ITER_filter_snapshots)) &&
- !bkey_eq(iter->pos, POS_MAX)) {
+ !bkey_eq(iter->pos, POS_MAX) &&
+ !((iter->flags & BTREE_ITER_is_extents) &&
+ iter->pos.offset == U64_MAX)) {
+
/*
* bkey_start_pos(), for extents, is not monotonically
* increasing until after filtering for snapshots:
@@ -2602,7 +2605,7 @@ struct bkey_s_c bch2_btree_iter_peek_prev_min(struct btree_trans *trans, struct
bch2_trans_verify_not_unlocked_or_in_restart(trans);
bch2_btree_iter_verify_entry_exit(iter);
- EBUG_ON((iter->flags & BTREE_ITER_filter_snapshots) && bpos_eq(end, POS_MIN));
+ EBUG_ON((iter->flags & BTREE_ITER_filter_snapshots) && iter->pos.inode != end.inode);
int ret = trans_maybe_inject_restart(trans, _RET_IP_);
if (unlikely(ret)) {
diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c
index d1ad1a7..7d6c971 100644
--- a/fs/bcachefs/btree_journal_iter.c
+++ b/fs/bcachefs/btree_journal_iter.c
@@ -644,8 +644,6 @@ void bch2_btree_and_journal_iter_init_node_iter(struct btree_trans *trans,
*/
static int journal_sort_key_cmp(const void *_l, const void *_r)
{
- cond_resched();
-
const struct journal_key *l = _l;
const struct journal_key *r = _r;
@@ -689,7 +687,8 @@ void bch2_journal_keys_put(struct bch_fs *c)
static void __journal_keys_sort(struct journal_keys *keys)
{
- sort(keys->data, keys->nr, sizeof(keys->data[0]), journal_sort_key_cmp, NULL);
+ sort_nonatomic(keys->data, keys->nr, sizeof(keys->data[0]),
+ journal_sort_key_cmp, NULL);
cond_resched();
diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c
index 8c9fdb7..86acf03 100644
--- a/fs/bcachefs/btree_node_scan.c
+++ b/fs/bcachefs/btree_node_scan.c
@@ -183,7 +183,7 @@ static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca,
return;
if (bch2_csum_type_is_encryption(BSET_CSUM_TYPE(&bn->keys))) {
- if (!c->chacha20)
+ if (!c->chacha20_key_set)
return;
struct nonce nonce = btree_nonce(&bn->keys, 0);
@@ -398,7 +398,7 @@ int bch2_scan_for_btree_nodes(struct bch_fs *c)
bch2_print_string_as_lines(KERN_INFO, buf.buf);
}
- sort(f->nodes.data, f->nodes.nr, sizeof(f->nodes.data[0]), found_btree_node_cmp_cookie, NULL);
+ sort_nonatomic(f->nodes.data, f->nodes.nr, sizeof(f->nodes.data[0]), found_btree_node_cmp_cookie, NULL);
dst = 0;
darray_for_each(f->nodes, i) {
@@ -418,7 +418,7 @@ int bch2_scan_for_btree_nodes(struct bch_fs *c)
}
f->nodes.nr = dst;
- sort(f->nodes.data, f->nodes.nr, sizeof(f->nodes.data[0]), found_btree_node_cmp_pos, NULL);
+ sort_nonatomic(f->nodes.data, f->nodes.nr, sizeof(f->nodes.data[0]), found_btree_node_cmp_pos, NULL);
if (0 && c->opts.verbose) {
printbuf_reset(&buf);
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index 55fbeeb..44b5fe4 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -1221,7 +1221,7 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
ret = bch2_disk_reservation_get(c, &as->disk_res,
(nr_nodes[0] + nr_nodes[1]) * btree_sectors(c),
- c->opts.metadata_replicas,
+ READ_ONCE(c->opts.metadata_replicas),
disk_res_flags);
if (ret)
goto err;
diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c
index adbe576..0941fb2 100644
--- a/fs/bcachefs/btree_write_buffer.c
+++ b/fs/bcachefs/btree_write_buffer.c
@@ -428,10 +428,10 @@ static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans)
*/
trace_and_count(c, write_buffer_flush_slowpath, trans, slowpath, wb->flushing.keys.nr);
- sort(wb->flushing.keys.data,
- wb->flushing.keys.nr,
- sizeof(wb->flushing.keys.data[0]),
- wb_key_seq_cmp, NULL);
+ sort_nonatomic(wb->flushing.keys.data,
+ wb->flushing.keys.nr,
+ sizeof(wb->flushing.keys.data[0]),
+ wb_key_seq_cmp, NULL);
darray_for_each(wb->flushing.keys, i) {
if (!i->journal_seq)
diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c
index fea61e6..4ef261e 100644
--- a/fs/bcachefs/buckets.c
+++ b/fs/bcachefs/buckets.c
@@ -37,7 +37,8 @@ void bch2_dev_usage_read_fast(struct bch_dev *ca, struct bch_dev_usage *usage)
void bch2_dev_usage_full_read_fast(struct bch_dev *ca, struct bch_dev_usage_full *usage)
{
memset(usage, 0, sizeof(*usage));
- acc_u64s_percpu((u64 *) usage, (u64 __percpu *) ca->usage, dev_usage_u64s());
+ acc_u64s_percpu((u64 *) usage, (u64 __percpu *) ca->usage,
+ sizeof(struct bch_dev_usage_full) / sizeof(u64));
}
static u64 reserve_factor(u64 r)
diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h
index 1c38b16..8d75b27 100644
--- a/fs/bcachefs/buckets.h
+++ b/fs/bcachefs/buckets.h
@@ -242,11 +242,6 @@ static inline u64 dev_buckets_available(struct bch_dev *ca,
/* Filesystem usage: */
-static inline unsigned dev_usage_u64s(void)
-{
- return sizeof(struct bch_dev_usage) / sizeof(u64);
-}
-
struct bch_fs_usage_short
bch2_fs_usage_read_short(struct bch_fs *);
diff --git a/fs/bcachefs/checksum.c b/fs/bcachefs/checksum.c
index 3726689..d0a34a0 100644
--- a/fs/bcachefs/checksum.c
+++ b/fs/bcachefs/checksum.c
@@ -7,17 +7,12 @@
#include "super-io.h"
#include <linux/crc32c.h>
-#include <linux/crypto.h>
#include <linux/xxhash.h>
#include <linux/key.h>
#include <linux/random.h>
#include <linux/ratelimit.h>
-#include <linux/scatterlist.h>
-#include <crypto/algapi.h>
#include <crypto/chacha.h>
-#include <crypto/hash.h>
#include <crypto/poly1305.h>
-#include <crypto/skcipher.h>
#include <keys/user-type.h>
/*
@@ -96,116 +91,40 @@ static void bch2_checksum_update(struct bch2_checksum_state *state, const void *
}
}
-static inline int do_encrypt_sg(struct crypto_sync_skcipher *tfm,
- struct nonce nonce,
- struct scatterlist *sg, size_t len)
+static void bch2_chacha20_init(u32 state[CHACHA_STATE_WORDS],
+ const struct bch_key *key, struct nonce nonce)
{
- SYNC_SKCIPHER_REQUEST_ON_STACK(req, tfm);
+ u32 key_words[CHACHA_KEY_SIZE / sizeof(u32)];
- skcipher_request_set_sync_tfm(req, tfm);
- skcipher_request_set_callback(req, 0, NULL, NULL);
- skcipher_request_set_crypt(req, sg, sg, len, nonce.d);
+ BUILD_BUG_ON(sizeof(key_words) != sizeof(*key));
+ memcpy(key_words, key, sizeof(key_words));
+ le32_to_cpu_array(key_words, ARRAY_SIZE(key_words));
- int ret = crypto_skcipher_encrypt(req);
- if (ret)
- pr_err("got error %i from crypto_skcipher_encrypt()", ret);
+ BUILD_BUG_ON(sizeof(nonce) != CHACHA_IV_SIZE);
+ chacha_init(state, key_words, (const u8 *)nonce.d);
- return ret;
+ memzero_explicit(key_words, sizeof(key_words));
}
-static inline int do_encrypt(struct crypto_sync_skcipher *tfm,
- struct nonce nonce,
- void *buf, size_t len)
+static void bch2_chacha20(const struct bch_key *key, struct nonce nonce,
+ void *data, size_t len)
{
- if (!is_vmalloc_addr(buf)) {
- struct scatterlist sg = {};
+ u32 state[CHACHA_STATE_WORDS];
- sg_mark_end(&sg);
- sg_set_page(&sg, virt_to_page(buf), len, offset_in_page(buf));
- return do_encrypt_sg(tfm, nonce, &sg, len);
- } else {
- DARRAY_PREALLOCATED(struct scatterlist, 4) sgl;
- size_t sgl_len = 0;
- int ret;
-
- darray_init(&sgl);
-
- while (len) {
- unsigned offset = offset_in_page(buf);
- struct scatterlist sg = {
- .page_link = (unsigned long) vmalloc_to_page(buf),
- .offset = offset,
- .length = min(len, PAGE_SIZE - offset),
- };
-
- if (darray_push(&sgl, sg)) {
- sg_mark_end(&darray_last(sgl));
- ret = do_encrypt_sg(tfm, nonce, sgl.data, sgl_len);
- if (ret)
- goto err;
-
- nonce = nonce_add(nonce, sgl_len);
- sgl_len = 0;
- sgl.nr = 0;
- BUG_ON(darray_push(&sgl, sg));
- }
-
- buf += sg.length;
- len -= sg.length;
- sgl_len += sg.length;
- }
-
- sg_mark_end(&darray_last(sgl));
- ret = do_encrypt_sg(tfm, nonce, sgl.data, sgl_len);
-err:
- darray_exit(&sgl);
- return ret;
- }
+ bch2_chacha20_init(state, key, nonce);
+ chacha20_crypt(state, data, data, len);
+ memzero_explicit(state, sizeof(state));
}
-int bch2_chacha_encrypt_key(struct bch_key *key, struct nonce nonce,
- void *buf, size_t len)
+static void bch2_poly1305_init(struct poly1305_desc_ctx *desc,
+ struct bch_fs *c, struct nonce nonce)
{
- struct crypto_sync_skcipher *chacha20 =
- crypto_alloc_sync_skcipher("chacha20", 0, 0);
- int ret;
-
- ret = PTR_ERR_OR_ZERO(chacha20);
- if (ret) {
- pr_err("error requesting chacha20 cipher: %s", bch2_err_str(ret));
- return ret;
- }
-
- ret = crypto_skcipher_setkey(&chacha20->base,
- (void *) key, sizeof(*key));
- if (ret) {
- pr_err("error from crypto_skcipher_setkey(): %s", bch2_err_str(ret));
- goto err;
- }
-
- ret = do_encrypt(chacha20, nonce, buf, len);
-err:
- crypto_free_sync_skcipher(chacha20);
- return ret;
-}
-
-static int gen_poly_key(struct bch_fs *c, struct shash_desc *desc,
- struct nonce nonce)
-{
- u8 key[POLY1305_KEY_SIZE];
- int ret;
+ u8 key[POLY1305_KEY_SIZE] = { 0 };
nonce.d[3] ^= BCH_NONCE_POLY;
- memset(key, 0, sizeof(key));
- ret = do_encrypt(c->chacha20, nonce, key, sizeof(key));
- if (ret)
- return ret;
-
- desc->tfm = c->poly1305;
- crypto_shash_init(desc);
- crypto_shash_update(desc, key, sizeof(key));
- return 0;
+ bch2_chacha20(&c->chacha20_key, nonce, key, sizeof(key));
+ poly1305_init(desc, key);
}
struct bch_csum bch2_checksum(struct bch_fs *c, unsigned type,
@@ -230,14 +149,13 @@ struct bch_csum bch2_checksum(struct bch_fs *c, unsigned type,
case BCH_CSUM_chacha20_poly1305_80:
case BCH_CSUM_chacha20_poly1305_128: {
- SHASH_DESC_ON_STACK(desc, c->poly1305);
+ struct poly1305_desc_ctx dctx;
u8 digest[POLY1305_DIGEST_SIZE];
struct bch_csum ret = { 0 };
- gen_poly_key(c, desc, nonce);
-
- crypto_shash_update(desc, data, len);
- crypto_shash_final(desc, digest);
+ bch2_poly1305_init(&dctx, c, nonce);
+ poly1305_update(&dctx, data, len);
+ poly1305_final(&dctx, digest);
memcpy(&ret, digest, bch_crc_bytes[type]);
return ret;
@@ -253,11 +171,12 @@ int bch2_encrypt(struct bch_fs *c, unsigned type,
if (!bch2_csum_type_is_encryption(type))
return 0;
- if (bch2_fs_inconsistent_on(!c->chacha20,
+ if (bch2_fs_inconsistent_on(!c->chacha20_key_set,
c, "attempting to encrypt without encryption key"))
return -BCH_ERR_no_encryption_key;
- return do_encrypt(c->chacha20, nonce, data, len);
+ bch2_chacha20(&c->chacha20_key, nonce, data, len);
+ return 0;
}
static struct bch_csum __bch2_checksum_bio(struct bch_fs *c, unsigned type,
@@ -296,26 +215,26 @@ static struct bch_csum __bch2_checksum_bio(struct bch_fs *c, unsigned type,
case BCH_CSUM_chacha20_poly1305_80:
case BCH_CSUM_chacha20_poly1305_128: {
- SHASH_DESC_ON_STACK(desc, c->poly1305);
+ struct poly1305_desc_ctx dctx;
u8 digest[POLY1305_DIGEST_SIZE];
struct bch_csum ret = { 0 };
- gen_poly_key(c, desc, nonce);
+ bch2_poly1305_init(&dctx, c, nonce);
#ifdef CONFIG_HIGHMEM
__bio_for_each_segment(bv, bio, *iter, *iter) {
void *p = kmap_local_page(bv.bv_page) + bv.bv_offset;
- crypto_shash_update(desc, p, bv.bv_len);
+ poly1305_update(&dctx, p, bv.bv_len);
kunmap_local(p);
}
#else
__bio_for_each_bvec(bv, bio, *iter, *iter)
- crypto_shash_update(desc,
+ poly1305_update(&dctx,
page_address(bv.bv_page) + bv.bv_offset,
bv.bv_len);
#endif
- crypto_shash_final(desc, digest);
+ poly1305_final(&dctx, digest);
memcpy(&ret, digest, bch_crc_bytes[type]);
return ret;
@@ -338,43 +257,33 @@ int __bch2_encrypt_bio(struct bch_fs *c, unsigned type,
{
struct bio_vec bv;
struct bvec_iter iter;
- DARRAY_PREALLOCATED(struct scatterlist, 4) sgl;
- size_t sgl_len = 0;
+ u32 chacha_state[CHACHA_STATE_WORDS];
int ret = 0;
- if (bch2_fs_inconsistent_on(!c->chacha20,
+ if (bch2_fs_inconsistent_on(!c->chacha20_key_set,
c, "attempting to encrypt without encryption key"))
return -BCH_ERR_no_encryption_key;
- darray_init(&sgl);
+ bch2_chacha20_init(chacha_state, &c->chacha20_key, nonce);
bio_for_each_segment(bv, bio, iter) {
- struct scatterlist sg = {
- .page_link = (unsigned long) bv.bv_page,
- .offset = bv.bv_offset,
- .length = bv.bv_len,
- };
+ void *p;
- if (darray_push(&sgl, sg)) {
- sg_mark_end(&darray_last(sgl));
- ret = do_encrypt_sg(c->chacha20, nonce, sgl.data, sgl_len);
- if (ret)
- goto err;
-
- nonce = nonce_add(nonce, sgl_len);
- sgl_len = 0;
- sgl.nr = 0;
-
- BUG_ON(darray_push(&sgl, sg));
+ /*
+ * chacha_crypt() assumes that the length is a multiple of
+ * CHACHA_BLOCK_SIZE on any non-final call.
+ */
+ if (!IS_ALIGNED(bv.bv_len, CHACHA_BLOCK_SIZE)) {
+ bch_err_ratelimited(c, "bio not aligned for encryption");
+ ret = -EIO;
+ break;
}
- sgl_len += sg.length;
+ p = bvec_kmap_local(&bv);
+ chacha20_crypt(chacha_state, p, p, bv.bv_len);
+ kunmap_local(p);
}
-
- sg_mark_end(&darray_last(sgl));
- ret = do_encrypt_sg(c->chacha20, nonce, sgl.data, sgl_len);
-err:
- darray_exit(&sgl);
+ memzero_explicit(chacha_state, sizeof(chacha_state));
return ret;
}
@@ -650,10 +559,7 @@ int bch2_decrypt_sb_key(struct bch_fs *c,
}
/* decrypt real key: */
- ret = bch2_chacha_encrypt_key(&user_key, bch2_sb_key_nonce(c),
- &sb_key, sizeof(sb_key));
- if (ret)
- goto err;
+ bch2_chacha20(&user_key, bch2_sb_key_nonce(c), &sb_key, sizeof(sb_key));
if (bch2_key_is_encrypted(&sb_key)) {
bch_err(c, "incorrect encryption key");
@@ -668,31 +574,6 @@ int bch2_decrypt_sb_key(struct bch_fs *c,
return ret;
}
-static int bch2_alloc_ciphers(struct bch_fs *c)
-{
- if (c->chacha20)
- return 0;
-
- struct crypto_sync_skcipher *chacha20 = crypto_alloc_sync_skcipher("chacha20", 0, 0);
- int ret = PTR_ERR_OR_ZERO(chacha20);
- if (ret) {
- bch_err(c, "error requesting chacha20 module: %s", bch2_err_str(ret));
- return ret;
- }
-
- struct crypto_shash *poly1305 = crypto_alloc_shash("poly1305", 0, 0);
- ret = PTR_ERR_OR_ZERO(poly1305);
- if (ret) {
- bch_err(c, "error requesting poly1305 module: %s", bch2_err_str(ret));
- crypto_free_sync_skcipher(chacha20);
- return ret;
- }
-
- c->chacha20 = chacha20;
- c->poly1305 = poly1305;
- return 0;
-}
-
#if 0
/*
@@ -797,35 +678,21 @@ int bch2_enable_encryption(struct bch_fs *c, bool keyed)
void bch2_fs_encryption_exit(struct bch_fs *c)
{
- if (c->poly1305)
- crypto_free_shash(c->poly1305);
- if (c->chacha20)
- crypto_free_sync_skcipher(c->chacha20);
+ memzero_explicit(&c->chacha20_key, sizeof(c->chacha20_key));
}
int bch2_fs_encryption_init(struct bch_fs *c)
{
struct bch_sb_field_crypt *crypt;
- struct bch_key key;
- int ret = 0;
+ int ret;
crypt = bch2_sb_field_get(c->disk_sb.sb, crypt);
if (!crypt)
- goto out;
+ return 0;
- ret = bch2_alloc_ciphers(c);
+ ret = bch2_decrypt_sb_key(c, crypt, &c->chacha20_key);
if (ret)
- goto out;
-
- ret = bch2_decrypt_sb_key(c, crypt, &key);
- if (ret)
- goto out;
-
- ret = crypto_skcipher_setkey(&c->chacha20->base,
- (void *) &key.key, sizeof(key.key));
- if (ret)
- goto out;
-out:
- memzero_explicit(&key, sizeof(key));
- return ret;
+ return ret;
+ c->chacha20_key_set = true;
+ return 0;
}
diff --git a/fs/bcachefs/checksum.h b/fs/bcachefs/checksum.h
index 4ac251c..1310782 100644
--- a/fs/bcachefs/checksum.h
+++ b/fs/bcachefs/checksum.h
@@ -69,7 +69,6 @@ static inline void bch2_csum_err_msg(struct printbuf *out,
bch2_csum_to_text(out, type, expected);
}
-int bch2_chacha_encrypt_key(struct bch_key *, struct nonce, void *, size_t);
int bch2_request_key(struct bch_sb *, struct bch_key *);
#ifndef __KERNEL__
int bch2_revoke_key(struct bch_sb *);
@@ -156,7 +155,7 @@ static inline bool bch2_checksum_type_valid(const struct bch_fs *c,
if (type >= BCH_CSUM_NR)
return false;
- if (bch2_csum_type_is_encryption(type) && !c->chacha20)
+ if (bch2_csum_type_is_encryption(type) && !c->chacha20_key_set)
return false;
return true;
diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c
index de02ebf..b211c97 100644
--- a/fs/bcachefs/data_update.c
+++ b/fs/bcachefs/data_update.c
@@ -607,7 +607,7 @@ void bch2_data_update_inflight_to_text(struct printbuf *out, struct data_update
prt_newline(out);
printbuf_indent_add(out, 2);
bch2_data_update_opts_to_text(out, m->op.c, &m->op.opts, &m->data_opts);
- prt_printf(out, "read_done:\t\%u\n", m->read_done);
+ prt_printf(out, "read_done:\t%u\n", m->read_done);
bch2_write_op_to_text(out, &m->op);
printbuf_indent_sub(out, 2);
}
diff --git a/fs/bcachefs/dirent.c b/fs/bcachefs/dirent.c
index bf53a02..92ee59d 100644
--- a/fs/bcachefs/dirent.c
+++ b/fs/bcachefs/dirent.c
@@ -13,8 +13,8 @@
#include <linux/dcache.h>
-static int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *info,
- const struct qstr *str, struct qstr *out_cf)
+int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *info,
+ const struct qstr *str, struct qstr *out_cf)
{
*out_cf = (struct qstr) QSTR_INIT(NULL, 0);
@@ -35,18 +35,6 @@ static int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *
#endif
}
-static inline int bch2_maybe_casefold(struct btree_trans *trans,
- const struct bch_hash_info *info,
- const struct qstr *str, struct qstr *out_cf)
-{
- if (likely(!info->cf_encoding)) {
- *out_cf = *str;
- return 0;
- } else {
- return bch2_casefold(trans, info, str, out_cf);
- }
-}
-
static unsigned bch2_dirent_name_bytes(struct bkey_s_c_dirent d)
{
if (bkey_val_bytes(d.k) < offsetof(struct bch_dirent, d_name))
@@ -287,8 +275,8 @@ static void dirent_init_casefolded_name(struct bkey_i_dirent *dirent,
EBUG_ON(!dirent->v.d_casefold);
EBUG_ON(!cf_name->len);
- dirent->v.d_cf_name_block.d_name_len = name->len;
- dirent->v.d_cf_name_block.d_cf_name_len = cf_name->len;
+ dirent->v.d_cf_name_block.d_name_len = cpu_to_le16(name->len);
+ dirent->v.d_cf_name_block.d_cf_name_len = cpu_to_le16(cf_name->len);
memcpy(&dirent->v.d_cf_name_block.d_names[0], name->name, name->len);
memcpy(&dirent->v.d_cf_name_block.d_names[name->len], cf_name->name, cf_name->len);
memset(&dirent->v.d_cf_name_block.d_names[name->len + cf_name->len], 0,
diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h
index 0880772..9838a7b 100644
--- a/fs/bcachefs/dirent.h
+++ b/fs/bcachefs/dirent.h
@@ -23,6 +23,21 @@ struct bch_fs;
struct bch_hash_info;
struct bch_inode_info;
+int bch2_casefold(struct btree_trans *, const struct bch_hash_info *,
+ const struct qstr *, struct qstr *);
+
+static inline int bch2_maybe_casefold(struct btree_trans *trans,
+ const struct bch_hash_info *info,
+ const struct qstr *str, struct qstr *out_cf)
+{
+ if (likely(!info->cf_encoding)) {
+ *out_cf = *str;
+ return 0;
+ } else {
+ return bch2_casefold(trans, info, str, out_cf);
+ }
+}
+
struct qstr bch2_dirent_get_name(struct bkey_s_c_dirent d);
static inline unsigned dirent_val_u64s(unsigned len, unsigned cf_len)
diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h
index c8696f0..a615e48 100644
--- a/fs/bcachefs/errcode.h
+++ b/fs/bcachefs/errcode.h
@@ -287,7 +287,7 @@
x(EIO, mark_stripe) \
x(EIO, stripe_reconstruct) \
x(EIO, key_type_error) \
- x(EIO, extent_poisened) \
+ x(EIO, extent_poisoned) \
x(EIO, missing_indirect_extent) \
x(EIO, invalidate_stripe_to_dev) \
x(EIO, no_encryption_key) \
diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c
index baf5dfb..925b0b5 100644
--- a/fs/bcachefs/error.c
+++ b/fs/bcachefs/error.c
@@ -272,9 +272,6 @@ static struct fsck_err_state *fsck_err_get(struct bch_fs *c,
{
struct fsck_err_state *s;
- if (!test_bit(BCH_FS_fsck_running, &c->flags))
- return NULL;
-
list_for_each_entry(s, &c->fsck_error_msgs, list)
if (s->id == id) {
/*
@@ -639,14 +636,14 @@ int __bch2_bkey_fsck_err(struct bch_fs *c,
return ret;
}
-void bch2_flush_fsck_errs(struct bch_fs *c)
+static void __bch2_flush_fsck_errs(struct bch_fs *c, bool print)
{
struct fsck_err_state *s, *n;
mutex_lock(&c->fsck_error_msgs_lock);
list_for_each_entry_safe(s, n, &c->fsck_error_msgs, list) {
- if (s->ratelimited && s->last_msg)
+ if (print && s->ratelimited && s->last_msg)
bch_err(c, "Saw %llu errors like:\n %s", s->nr, s->last_msg);
list_del(&s->list);
@@ -657,6 +654,16 @@ void bch2_flush_fsck_errs(struct bch_fs *c)
mutex_unlock(&c->fsck_error_msgs_lock);
}
+void bch2_flush_fsck_errs(struct bch_fs *c)
+{
+ __bch2_flush_fsck_errs(c, true);
+}
+
+void bch2_free_fsck_errs(struct bch_fs *c)
+{
+ __bch2_flush_fsck_errs(c, false);
+}
+
int bch2_inum_offset_err_msg_trans(struct btree_trans *trans, struct printbuf *out,
subvol_inum inum, u64 offset)
{
diff --git a/fs/bcachefs/error.h b/fs/bcachefs/error.h
index d0d024d..4a364fd 100644
--- a/fs/bcachefs/error.h
+++ b/fs/bcachefs/error.h
@@ -93,6 +93,7 @@ int __bch2_fsck_err(struct bch_fs *, struct btree_trans *,
_flags, BCH_FSCK_ERR_##_err_type, __VA_ARGS__)
void bch2_flush_fsck_errs(struct bch_fs *);
+void bch2_free_fsck_errs(struct bch_fs *);
#define fsck_err_wrap(_do) \
({ \
diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index ae7c7a1..dca2b84 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -139,7 +139,7 @@ int bch2_bkey_pick_read_device(struct bch_fs *c, struct bkey_s_c k,
struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
if (bch2_bkey_extent_ptrs_flags(ptrs) & BIT_ULL(BCH_EXTENT_FLAG_poisoned))
- return -BCH_ERR_extent_poisened;
+ return -BCH_ERR_extent_poisoned;
rcu_read_lock();
const union bch_extent_entry *entry;
diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c
index 19d4599..e3a75dc 100644
--- a/fs/bcachefs/fs-io-buffered.c
+++ b/fs/bcachefs/fs-io-buffered.c
@@ -225,11 +225,26 @@ static void bchfs_read(struct btree_trans *trans,
bch2_read_extent(trans, rbio, iter.pos,
data_btree, k, offset_into_extent, flags);
- swap(rbio->bio.bi_iter.bi_size, bytes);
+ /*
+ * Careful there's a landmine here if bch2_read_extent() ever
+ * starts returning transaction restarts here.
+ *
+ * We've changed rbio->bi_iter.bi_size to be "bytes we can read
+ * from this extent" with the swap call, and we restore it
+ * below. That restore needs to come before checking for
+ * errors.
+ *
+ * But unlike __bch2_read(), we use the rbio bvec iter, not one
+ * on the stack, so we can't do the restore right after the
+ * bch2_read_extent() call: we don't own that iterator anymore
+ * if BCH_READ_last_fragment is set, since we may have submitted
+ * that rbio instead of cloning it.
+ */
if (flags & BCH_READ_last_fragment)
break;
+ swap(rbio->bio.bi_iter.bi_size, bytes);
bio_advance(&rbio->bio, bytes);
err:
if (ret &&
diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c
index c1553e4..a82dfce 100644
--- a/fs/bcachefs/fs-ioctl.c
+++ b/fs/bcachefs/fs-ioctl.c
@@ -21,206 +21,6 @@
#define FSOP_GOING_FLAGS_LOGFLUSH 0x1 /* flush log but not data */
#define FSOP_GOING_FLAGS_NOLOGFLUSH 0x2 /* don't flush log nor data */
-struct flags_set {
- unsigned mask;
- unsigned flags;
-
- unsigned projid;
-
- bool set_projinherit;
- bool projinherit;
-};
-
-static int bch2_inode_flags_set(struct btree_trans *trans,
- struct bch_inode_info *inode,
- struct bch_inode_unpacked *bi,
- void *p)
-{
- struct bch_fs *c = inode->v.i_sb->s_fs_info;
- /*
- * We're relying on btree locking here for exclusion with other ioctl
- * calls - use the flags in the btree (@bi), not inode->i_flags:
- */
- struct flags_set *s = p;
- unsigned newflags = s->flags;
- unsigned oldflags = bi->bi_flags & s->mask;
-
- if (((newflags ^ oldflags) & (BCH_INODE_append|BCH_INODE_immutable)) &&
- !capable(CAP_LINUX_IMMUTABLE))
- return -EPERM;
-
- if (!S_ISREG(bi->bi_mode) &&
- !S_ISDIR(bi->bi_mode) &&
- (newflags & (BCH_INODE_nodump|BCH_INODE_noatime)) != newflags)
- return -EINVAL;
-
- if ((newflags ^ oldflags) & BCH_INODE_casefolded) {
-#ifdef CONFIG_UNICODE
- int ret = 0;
- /* Not supported on individual files. */
- if (!S_ISDIR(bi->bi_mode))
- return -EOPNOTSUPP;
-
- /*
- * Make sure the dir is empty, as otherwise we'd need to
- * rehash everything and update the dirent keys.
- */
- ret = bch2_empty_dir_trans(trans, inode_inum(inode));
- if (ret < 0)
- return ret;
-
- ret = bch2_request_incompat_feature(c,bcachefs_metadata_version_casefolding);
- if (ret)
- return ret;
-
- bch2_check_set_feature(c, BCH_FEATURE_casefolding);
-#else
- printk(KERN_ERR "Cannot use casefolding on a kernel without CONFIG_UNICODE\n");
- return -EOPNOTSUPP;
-#endif
- }
-
- if (s->set_projinherit) {
- bi->bi_fields_set &= ~(1 << Inode_opt_project);
- bi->bi_fields_set |= ((int) s->projinherit << Inode_opt_project);
- }
-
- bi->bi_flags &= ~s->mask;
- bi->bi_flags |= newflags;
-
- bi->bi_ctime = timespec_to_bch2_time(c, current_time(&inode->v));
- return 0;
-}
-
-static int bch2_ioc_getflags(struct bch_inode_info *inode, int __user *arg)
-{
- unsigned flags = map_flags(bch_flags_to_uflags, inode->ei_inode.bi_flags);
-
- return put_user(flags, arg);
-}
-
-static int bch2_ioc_setflags(struct bch_fs *c,
- struct file *file,
- struct bch_inode_info *inode,
- void __user *arg)
-{
- struct flags_set s = { .mask = map_defined(bch_flags_to_uflags) };
- unsigned uflags;
- int ret;
-
- if (get_user(uflags, (int __user *) arg))
- return -EFAULT;
-
- s.flags = map_flags_rev(bch_flags_to_uflags, uflags);
- if (uflags)
- return -EOPNOTSUPP;
-
- ret = mnt_want_write_file(file);
- if (ret)
- return ret;
-
- inode_lock(&inode->v);
- if (!inode_owner_or_capable(file_mnt_idmap(file), &inode->v)) {
- ret = -EACCES;
- goto setflags_out;
- }
-
- mutex_lock(&inode->ei_update_lock);
- ret = bch2_subvol_is_ro(c, inode->ei_inum.subvol) ?:
- bch2_write_inode(c, inode, bch2_inode_flags_set, &s,
- ATTR_CTIME);
- mutex_unlock(&inode->ei_update_lock);
-
-setflags_out:
- inode_unlock(&inode->v);
- mnt_drop_write_file(file);
- return ret;
-}
-
-static int bch2_ioc_fsgetxattr(struct bch_inode_info *inode,
- struct fsxattr __user *arg)
-{
- struct fsxattr fa = { 0 };
-
- fa.fsx_xflags = map_flags(bch_flags_to_xflags, inode->ei_inode.bi_flags);
-
- if (inode->ei_inode.bi_fields_set & (1 << Inode_opt_project))
- fa.fsx_xflags |= FS_XFLAG_PROJINHERIT;
-
- fa.fsx_projid = inode->ei_qid.q[QTYP_PRJ];
-
- if (copy_to_user(arg, &fa, sizeof(fa)))
- return -EFAULT;
-
- return 0;
-}
-
-static int fssetxattr_inode_update_fn(struct btree_trans *trans,
- struct bch_inode_info *inode,
- struct bch_inode_unpacked *bi,
- void *p)
-{
- struct flags_set *s = p;
-
- if (s->projid != bi->bi_project) {
- bi->bi_fields_set |= 1U << Inode_opt_project;
- bi->bi_project = s->projid;
- }
-
- return bch2_inode_flags_set(trans, inode, bi, p);
-}
-
-static int bch2_ioc_fssetxattr(struct bch_fs *c,
- struct file *file,
- struct bch_inode_info *inode,
- struct fsxattr __user *arg)
-{
- struct flags_set s = { .mask = map_defined(bch_flags_to_xflags) };
- struct fsxattr fa;
- int ret;
-
- if (copy_from_user(&fa, arg, sizeof(fa)))
- return -EFAULT;
-
- s.set_projinherit = true;
- s.projinherit = (fa.fsx_xflags & FS_XFLAG_PROJINHERIT) != 0;
- fa.fsx_xflags &= ~FS_XFLAG_PROJINHERIT;
-
- s.flags = map_flags_rev(bch_flags_to_xflags, fa.fsx_xflags);
- if (fa.fsx_xflags)
- return -EOPNOTSUPP;
-
- if (fa.fsx_projid >= U32_MAX)
- return -EINVAL;
-
- /*
- * inode fields accessible via the xattr interface are stored with a +1
- * bias, so that 0 means unset:
- */
- s.projid = fa.fsx_projid + 1;
-
- ret = mnt_want_write_file(file);
- if (ret)
- return ret;
-
- inode_lock(&inode->v);
- if (!inode_owner_or_capable(file_mnt_idmap(file), &inode->v)) {
- ret = -EACCES;
- goto err;
- }
-
- mutex_lock(&inode->ei_update_lock);
- ret = bch2_subvol_is_ro(c, inode->ei_inum.subvol) ?:
- bch2_set_projid(c, inode, fa.fsx_projid) ?:
- bch2_write_inode(c, inode, fssetxattr_inode_update_fn, &s,
- ATTR_CTIME);
- mutex_unlock(&inode->ei_update_lock);
-err:
- inode_unlock(&inode->v);
- mnt_drop_write_file(file);
- return ret;
-}
-
static int bch2_reinherit_attrs_fn(struct btree_trans *trans,
struct bch_inode_info *inode,
struct bch_inode_unpacked *bi,
@@ -558,23 +358,6 @@ long bch2_fs_file_ioctl(struct file *file, unsigned cmd, unsigned long arg)
long ret;
switch (cmd) {
- case FS_IOC_GETFLAGS:
- ret = bch2_ioc_getflags(inode, (int __user *) arg);
- break;
-
- case FS_IOC_SETFLAGS:
- ret = bch2_ioc_setflags(c, file, inode, (int __user *) arg);
- break;
-
- case FS_IOC_FSGETXATTR:
- ret = bch2_ioc_fsgetxattr(inode, (void __user *) arg);
- break;
-
- case FS_IOC_FSSETXATTR:
- ret = bch2_ioc_fssetxattr(c, file, inode,
- (void __user *) arg);
- break;
-
case BCHFS_IOC_REINHERIT_ATTRS:
ret = bch2_ioc_reinherit_attrs(c, file, inode,
(void __user *) arg);
diff --git a/fs/bcachefs/fs-ioctl.h b/fs/bcachefs/fs-ioctl.h
index ecd3bfd..a657e49 100644
--- a/fs/bcachefs/fs-ioctl.h
+++ b/fs/bcachefs/fs-ioctl.h
@@ -2,81 +2,6 @@
#ifndef _BCACHEFS_FS_IOCTL_H
#define _BCACHEFS_FS_IOCTL_H
-/* Inode flags: */
-
-/* bcachefs inode flags -> vfs inode flags: */
-static const __maybe_unused unsigned bch_flags_to_vfs[] = {
- [__BCH_INODE_sync] = S_SYNC,
- [__BCH_INODE_immutable] = S_IMMUTABLE,
- [__BCH_INODE_append] = S_APPEND,
- [__BCH_INODE_noatime] = S_NOATIME,
- [__BCH_INODE_casefolded] = S_CASEFOLD,
-};
-
-/* bcachefs inode flags -> FS_IOC_GETFLAGS: */
-static const __maybe_unused unsigned bch_flags_to_uflags[] = {
- [__BCH_INODE_sync] = FS_SYNC_FL,
- [__BCH_INODE_immutable] = FS_IMMUTABLE_FL,
- [__BCH_INODE_append] = FS_APPEND_FL,
- [__BCH_INODE_nodump] = FS_NODUMP_FL,
- [__BCH_INODE_noatime] = FS_NOATIME_FL,
- [__BCH_INODE_casefolded] = FS_CASEFOLD_FL,
-};
-
-/* bcachefs inode flags -> FS_IOC_FSGETXATTR: */
-static const __maybe_unused unsigned bch_flags_to_xflags[] = {
- [__BCH_INODE_sync] = FS_XFLAG_SYNC,
- [__BCH_INODE_immutable] = FS_XFLAG_IMMUTABLE,
- [__BCH_INODE_append] = FS_XFLAG_APPEND,
- [__BCH_INODE_nodump] = FS_XFLAG_NODUMP,
- [__BCH_INODE_noatime] = FS_XFLAG_NOATIME,
- //[__BCH_INODE_PROJINHERIT] = FS_XFLAG_PROJINHERIT;
-};
-
-#define set_flags(_map, _in, _out) \
-do { \
- unsigned _i; \
- \
- for (_i = 0; _i < ARRAY_SIZE(_map); _i++) \
- if ((_in) & (1 << _i)) \
- (_out) |= _map[_i]; \
- else \
- (_out) &= ~_map[_i]; \
-} while (0)
-
-#define map_flags(_map, _in) \
-({ \
- unsigned _out = 0; \
- \
- set_flags(_map, _in, _out); \
- _out; \
-})
-
-#define map_flags_rev(_map, _in) \
-({ \
- unsigned _i, _out = 0; \
- \
- for (_i = 0; _i < ARRAY_SIZE(_map); _i++) \
- if ((_in) & _map[_i]) { \
- (_out) |= 1 << _i; \
- (_in) &= ~_map[_i]; \
- } \
- (_out); \
-})
-
-#define map_defined(_map) \
-({ \
- unsigned _in = ~0; \
- \
- map_flags_rev(_map, _in); \
-})
-
-/* Set VFS inode flags from bcachefs inode: */
-static inline void bch2_inode_flags_to_vfs(struct bch_inode_info *inode)
-{
- set_flags(bch_flags_to_vfs, inode->ei_inode.bi_flags, inode->v.i_flags);
-}
-
long bch2_fs_file_ioctl(struct file *, unsigned, unsigned long);
long bch2_compat_fs_ioctl(struct file *, unsigned, unsigned long);
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index 5a41b1a..0f1d61a 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -33,6 +33,7 @@
#include <linux/backing-dev.h>
#include <linux/exportfs.h>
#include <linux/fiemap.h>
+#include <linux/fileattr.h>
#include <linux/fs_context.h>
#include <linux/module.h>
#include <linux/pagemap.h>
@@ -51,6 +52,22 @@ static void bch2_vfs_inode_init(struct btree_trans *, subvol_inum,
struct bch_inode_unpacked *,
struct bch_subvolume *);
+/* Set VFS inode flags from bcachefs inode: */
+static inline void bch2_inode_flags_to_vfs(struct bch_fs *c, struct bch_inode_info *inode)
+{
+ static const __maybe_unused unsigned bch_flags_to_vfs[] = {
+ [__BCH_INODE_sync] = S_SYNC,
+ [__BCH_INODE_immutable] = S_IMMUTABLE,
+ [__BCH_INODE_append] = S_APPEND,
+ [__BCH_INODE_noatime] = S_NOATIME,
+ };
+
+ set_flags(bch_flags_to_vfs, inode->ei_inode.bi_flags, inode->v.i_flags);
+
+ if (bch2_inode_casefold(c, &inode->ei_inode))
+ inode->v.i_flags |= S_CASEFOLD;
+}
+
void bch2_inode_update_after_write(struct btree_trans *trans,
struct bch_inode_info *inode,
struct bch_inode_unpacked *bi,
@@ -79,7 +96,7 @@ void bch2_inode_update_after_write(struct btree_trans *trans,
inode->ei_inode = *bi;
- bch2_inode_flags_to_vfs(inode);
+ bch2_inode_flags_to_vfs(c, inode);
}
int __must_check bch2_write_inode(struct bch_fs *c,
@@ -631,13 +648,18 @@ static struct bch_inode_info *bch2_lookup_trans(struct btree_trans *trans,
const struct qstr *name)
{
struct bch_fs *c = trans->c;
- struct btree_iter dirent_iter = {};
subvol_inum inum = {};
struct printbuf buf = PRINTBUF;
+ struct qstr lookup_name;
+ int ret = bch2_maybe_casefold(trans, dir_hash_info, name, &lookup_name);
+ if (ret)
+ return ERR_PTR(ret);
+
+ struct btree_iter dirent_iter = {};
struct bkey_s_c k = bch2_hash_lookup(trans, &dirent_iter, bch2_dirent_hash_desc,
- dir_hash_info, dir, name, 0);
- int ret = bkey_err(k);
+ dir_hash_info, dir, &lookup_name, 0);
+ ret = bkey_err(k);
if (ret)
return ERR_PTR(ret);
@@ -825,6 +847,11 @@ int __bch2_unlink(struct inode *vdir, struct dentry *dentry,
*/
set_nlink(&inode->v, 0);
}
+
+ if (IS_CASEFOLDED(vdir)) {
+ d_invalidate(dentry);
+ d_prune_aliases(&inode->v);
+ }
err:
bch2_trans_put(trans);
bch2_unlock_inodes(INODE_UPDATE_LOCK, dir, inode);
@@ -1235,10 +1262,20 @@ static int bch2_tmpfile(struct mnt_idmap *idmap,
return finish_open_simple(file, 0);
}
+struct bch_fiemap_extent {
+ struct bkey_buf kbuf;
+ unsigned flags;
+};
+
static int bch2_fill_extent(struct bch_fs *c,
struct fiemap_extent_info *info,
- struct bkey_s_c k, unsigned flags)
+ struct bch_fiemap_extent *fe)
{
+ struct bkey_s_c k = bkey_i_to_s_c(fe->kbuf.k);
+ unsigned flags = fe->flags;
+
+ BUG_ON(!k.k->size);
+
if (bkey_extent_is_direct_data(k.k)) {
struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
const union bch_extent_entry *entry;
@@ -1291,110 +1328,223 @@ static int bch2_fill_extent(struct bch_fs *c,
}
}
+/*
+ * Scan a range of an inode for data in pagecache.
+ *
+ * Intended to be retryable, so don't modify the output params until success is
+ * imminent.
+ */
+static int
+bch2_fiemap_hole_pagecache(struct inode *vinode, u64 *start, u64 *end,
+ bool nonblock)
+{
+ loff_t dstart, dend;
+
+ dstart = bch2_seek_pagecache_data(vinode, *start, *end, 0, nonblock);
+ if (dstart < 0)
+ return dstart;
+
+ if (dstart == *end) {
+ *start = dstart;
+ return 0;
+ }
+
+ dend = bch2_seek_pagecache_hole(vinode, dstart, *end, 0, nonblock);
+ if (dend < 0)
+ return dend;
+
+ /* race */
+ BUG_ON(dstart == dend);
+
+ *start = dstart;
+ *end = dend;
+ return 0;
+}
+
+/*
+ * Scan a range of pagecache that corresponds to a file mapping hole in the
+ * extent btree. If data is found, fake up an extent key so it looks like a
+ * delalloc extent to the rest of the fiemap processing code.
+ */
+static int
+bch2_next_fiemap_pagecache_extent(struct btree_trans *trans, struct bch_inode_info *inode,
+ u64 start, u64 end, struct bch_fiemap_extent *cur)
+{
+ struct bch_fs *c = trans->c;
+ struct bkey_i_extent *delextent;
+ struct bch_extent_ptr ptr = {};
+ loff_t dstart = start << 9, dend = end << 9;
+ int ret;
+
+ /*
+ * We hold btree locks here so we cannot block on folio locks without
+ * dropping trans locks first. Run a nonblocking scan for the common
+ * case of no folios over holes and fall back on failure.
+ *
+ * Note that dropping locks like this is technically racy against
+ * writeback inserting to the extent tree, but a non-sync fiemap scan is
+ * fundamentally racy with writeback anyways. Therefore, just report the
+ * range as delalloc regardless of whether we have to cycle trans locks.
+ */
+ ret = bch2_fiemap_hole_pagecache(&inode->v, &dstart, &dend, true);
+ if (ret == -EAGAIN)
+ ret = drop_locks_do(trans,
+ bch2_fiemap_hole_pagecache(&inode->v, &dstart, &dend, false));
+ if (ret < 0)
+ return ret;
+
+ /*
+ * Create a fake extent key in the buffer. We have to add a dummy extent
+ * pointer for the fill code to add an extent entry. It's explicitly
+ * zeroed to reflect delayed allocation (i.e. phys offset 0).
+ */
+ bch2_bkey_buf_realloc(&cur->kbuf, c, sizeof(*delextent) / sizeof(u64));
+ delextent = bkey_extent_init(cur->kbuf.k);
+ delextent->k.p = POS(inode->ei_inum.inum, dend >> 9);
+ delextent->k.size = (dend - dstart) >> 9;
+ bch2_bkey_append_ptr(&delextent->k_i, ptr);
+
+ cur->flags = FIEMAP_EXTENT_DELALLOC;
+
+ return 0;
+}
+
+static int bch2_next_fiemap_extent(struct btree_trans *trans,
+ struct bch_inode_info *inode,
+ u64 start, u64 end,
+ struct bch_fiemap_extent *cur)
+{
+ u32 snapshot;
+ int ret = bch2_subvolume_get_snapshot(trans, inode->ei_inum.subvol, &snapshot);
+ if (ret)
+ return ret;
+
+ struct btree_iter iter;
+ bch2_trans_iter_init(trans, &iter, BTREE_ID_extents,
+ SPOS(inode->ei_inum.inum, start, snapshot), 0);
+
+ struct bkey_s_c k =
+ bch2_btree_iter_peek_max(trans, &iter, POS(inode->ei_inum.inum, end));
+ ret = bkey_err(k);
+ if (ret)
+ goto err;
+
+ ret = bch2_next_fiemap_pagecache_extent(trans, inode, start, end, cur);
+ if (ret)
+ goto err;
+
+ struct bpos pagecache_start = bkey_start_pos(&cur->kbuf.k->k);
+
+ /*
+ * Does the pagecache or the btree take precedence?
+ *
+ * It _should_ be the pagecache, so that we correctly report delalloc
+ * extents when dirty in the pagecache (we're COW, after all).
+ *
+ * But we'd have to add per-sector writeback tracking to
+ * bch_folio_state, otherwise we report delalloc extents for clean
+ * cached data in the pagecache.
+ *
+ * We should do this, but even then fiemap won't report stable mappings:
+ * on bcachefs data moves around in the background (copygc, rebalance)
+ * and we don't provide a way for userspace to lock that out.
+ */
+ if (k.k &&
+ bkey_le(bpos_max(iter.pos, bkey_start_pos(k.k)),
+ pagecache_start)) {
+ bch2_bkey_buf_reassemble(&cur->kbuf, trans->c, k);
+ bch2_cut_front(iter.pos, cur->kbuf.k);
+ bch2_cut_back(POS(inode->ei_inum.inum, end), cur->kbuf.k);
+ cur->flags = 0;
+ } else if (k.k) {
+ bch2_cut_back(bkey_start_pos(k.k), cur->kbuf.k);
+ }
+
+ if (cur->kbuf.k->k.type == KEY_TYPE_reflink_p) {
+ unsigned sectors = cur->kbuf.k->k.size;
+ s64 offset_into_extent = 0;
+ enum btree_id data_btree = BTREE_ID_extents;
+ int ret = bch2_read_indirect_extent(trans, &data_btree, &offset_into_extent,
+ &cur->kbuf);
+ if (ret)
+ goto err;
+
+ struct bkey_i *k = cur->kbuf.k;
+ sectors = min_t(unsigned, sectors, k->k.size - offset_into_extent);
+
+ bch2_cut_front(POS(k->k.p.inode,
+ bkey_start_offset(&k->k) + offset_into_extent),
+ k);
+ bch2_key_resize(&k->k, sectors);
+ k->k.p = iter.pos;
+ k->k.p.offset += k->k.size;
+ }
+err:
+ bch2_trans_iter_exit(trans, &iter);
+ return ret;
+}
+
static int bch2_fiemap(struct inode *vinode, struct fiemap_extent_info *info,
u64 start, u64 len)
{
struct bch_fs *c = vinode->i_sb->s_fs_info;
struct bch_inode_info *ei = to_bch_ei(vinode);
struct btree_trans *trans;
- struct btree_iter iter;
- struct bkey_s_c k;
- struct bkey_buf cur, prev;
- bool have_extent = false;
+ struct bch_fiemap_extent cur, prev;
int ret = 0;
- ret = fiemap_prep(&ei->v, info, start, &len, FIEMAP_FLAG_SYNC);
+ ret = fiemap_prep(&ei->v, info, start, &len, 0);
if (ret)
return ret;
- struct bpos end = POS(ei->v.i_ino, (start + len) >> 9);
if (start + len < start)
return -EINVAL;
start >>= 9;
+ u64 end = (start + len) >> 9;
- bch2_bkey_buf_init(&cur);
- bch2_bkey_buf_init(&prev);
+ bch2_bkey_buf_init(&cur.kbuf);
+ bch2_bkey_buf_init(&prev.kbuf);
+ bkey_init(&prev.kbuf.k->k);
+
trans = bch2_trans_get(c);
- bch2_trans_iter_init(trans, &iter, BTREE_ID_extents,
- POS(ei->v.i_ino, start), 0);
-
- while (!ret || bch2_err_matches(ret, BCH_ERR_transaction_restart)) {
- enum btree_id data_btree = BTREE_ID_extents;
-
- bch2_trans_begin(trans);
-
- u32 snapshot;
- ret = bch2_subvolume_get_snapshot(trans, ei->ei_inum.subvol, &snapshot);
+ while (start < end) {
+ ret = lockrestart_do(trans,
+ bch2_next_fiemap_extent(trans, ei, start, end, &cur));
if (ret)
- continue;
+ goto err;
- bch2_btree_iter_set_snapshot(trans, &iter, snapshot);
+ BUG_ON(bkey_start_offset(&cur.kbuf.k->k) < start);
+ BUG_ON(cur.kbuf.k->k.p.offset > end);
- k = bch2_btree_iter_peek_max(trans, &iter, end);
- ret = bkey_err(k);
- if (ret)
- continue;
-
- if (!k.k)
+ if (bkey_start_offset(&cur.kbuf.k->k) == end)
break;
- if (!bkey_extent_is_data(k.k) &&
- k.k->type != KEY_TYPE_reservation) {
- bch2_btree_iter_advance(trans, &iter);
- continue;
- }
+ start = cur.kbuf.k->k.p.offset;
- s64 offset_into_extent = iter.pos.offset - bkey_start_offset(k.k);
- unsigned sectors = k.k->size - offset_into_extent;
-
- bch2_bkey_buf_reassemble(&cur, c, k);
-
- ret = bch2_read_indirect_extent(trans, &data_btree,
- &offset_into_extent, &cur);
- if (ret)
- continue;
-
- k = bkey_i_to_s_c(cur.k);
- bch2_bkey_buf_realloc(&prev, c, k.k->u64s);
-
- sectors = min_t(unsigned, sectors, k.k->size - offset_into_extent);
-
- bch2_cut_front(POS(k.k->p.inode,
- bkey_start_offset(k.k) +
- offset_into_extent),
- cur.k);
- bch2_key_resize(&cur.k->k, sectors);
- cur.k->k.p = iter.pos;
- cur.k->k.p.offset += cur.k->k.size;
-
- if (have_extent) {
+ if (!bkey_deleted(&prev.kbuf.k->k)) {
bch2_trans_unlock(trans);
- ret = bch2_fill_extent(c, info,
- bkey_i_to_s_c(prev.k), 0);
+ ret = bch2_fill_extent(c, info, &prev);
if (ret)
- break;
+ goto err;
}
- bkey_copy(prev.k, cur.k);
- have_extent = true;
-
- bch2_btree_iter_set_pos(trans, &iter,
- POS(iter.pos.inode, iter.pos.offset + sectors));
+ bch2_bkey_buf_copy(&prev.kbuf, c, cur.kbuf.k);
+ prev.flags = cur.flags;
}
- bch2_trans_iter_exit(trans, &iter);
- if (!ret && have_extent) {
+ if (!bkey_deleted(&prev.kbuf.k->k)) {
bch2_trans_unlock(trans);
- ret = bch2_fill_extent(c, info, bkey_i_to_s_c(prev.k),
- FIEMAP_EXTENT_LAST);
+ prev.flags |= FIEMAP_EXTENT_LAST;
+ ret = bch2_fill_extent(c, info, &prev);
}
-
+err:
bch2_trans_put(trans);
- bch2_bkey_buf_exit(&cur, c);
- bch2_bkey_buf_exit(&prev, c);
- return ret < 0 ? ret : 0;
+ bch2_bkey_buf_exit(&cur.kbuf, c);
+ bch2_bkey_buf_exit(&prev.kbuf, c);
+
+ return bch2_err_class(ret < 0 ? ret : 0);
}
static const struct vm_operations_struct bch_vm_ops = {
@@ -1449,6 +1599,165 @@ static int bch2_open(struct inode *vinode, struct file *file)
return generic_file_open(vinode, file);
}
+/* bcachefs inode flags -> FS_IOC_GETFLAGS: */
+static const __maybe_unused unsigned bch_flags_to_uflags[] = {
+ [__BCH_INODE_sync] = FS_SYNC_FL,
+ [__BCH_INODE_immutable] = FS_IMMUTABLE_FL,
+ [__BCH_INODE_append] = FS_APPEND_FL,
+ [__BCH_INODE_nodump] = FS_NODUMP_FL,
+ [__BCH_INODE_noatime] = FS_NOATIME_FL,
+};
+
+/* bcachefs inode flags -> FS_IOC_FSGETXATTR: */
+static const __maybe_unused unsigned bch_flags_to_xflags[] = {
+ [__BCH_INODE_sync] = FS_XFLAG_SYNC,
+ [__BCH_INODE_immutable] = FS_XFLAG_IMMUTABLE,
+ [__BCH_INODE_append] = FS_XFLAG_APPEND,
+ [__BCH_INODE_nodump] = FS_XFLAG_NODUMP,
+ [__BCH_INODE_noatime] = FS_XFLAG_NOATIME,
+};
+
+static int bch2_fileattr_get(struct dentry *dentry,
+ struct fileattr *fa)
+{
+ struct bch_inode_info *inode = to_bch_ei(d_inode(dentry));
+ struct bch_fs *c = inode->v.i_sb->s_fs_info;
+
+ fileattr_fill_xflags(fa, map_flags(bch_flags_to_xflags, inode->ei_inode.bi_flags));
+
+ if (inode->ei_inode.bi_fields_set & (1 << Inode_opt_project))
+ fa->fsx_xflags |= FS_XFLAG_PROJINHERIT;
+
+ if (bch2_inode_casefold(c, &inode->ei_inode))
+ fa->flags |= FS_CASEFOLD_FL;
+
+ fa->fsx_projid = inode->ei_qid.q[QTYP_PRJ];
+ return 0;
+}
+
+struct flags_set {
+ unsigned mask;
+ unsigned flags;
+ unsigned projid;
+ bool set_project;
+ bool set_casefold;
+ bool casefold;
+};
+
+static int fssetxattr_inode_update_fn(struct btree_trans *trans,
+ struct bch_inode_info *inode,
+ struct bch_inode_unpacked *bi,
+ void *p)
+{
+ struct bch_fs *c = trans->c;
+ struct flags_set *s = p;
+
+ /*
+ * We're relying on btree locking here for exclusion with other ioctl
+ * calls - use the flags in the btree (@bi), not inode->i_flags:
+ */
+ if (!S_ISREG(bi->bi_mode) &&
+ !S_ISDIR(bi->bi_mode) &&
+ (s->flags & (BCH_INODE_nodump|BCH_INODE_noatime)) != s->flags)
+ return -EINVAL;
+
+ if (s->casefold != bch2_inode_casefold(c, bi)) {
+#ifdef CONFIG_UNICODE
+ int ret = 0;
+ /* Not supported on individual files. */
+ if (!S_ISDIR(bi->bi_mode))
+ return -EOPNOTSUPP;
+
+ /*
+ * Make sure the dir is empty, as otherwise we'd need to
+ * rehash everything and update the dirent keys.
+ */
+ ret = bch2_empty_dir_trans(trans, inode_inum(inode));
+ if (ret < 0)
+ return ret;
+
+ ret = bch2_request_incompat_feature(c, bcachefs_metadata_version_casefolding);
+ if (ret)
+ return ret;
+
+ bch2_check_set_feature(c, BCH_FEATURE_casefolding);
+
+ bi->bi_casefold = s->casefold + 1;
+ bi->bi_fields_set |= BIT(Inode_opt_casefold);
+
+#else
+ printk(KERN_ERR "Cannot use casefolding on a kernel without CONFIG_UNICODE\n");
+ return -EOPNOTSUPP;
+#endif
+ }
+
+ if (s->set_project) {
+ bi->bi_project = s->projid;
+ bi->bi_fields_set |= BIT(Inode_opt_project);
+ }
+
+ bi->bi_flags &= ~s->mask;
+ bi->bi_flags |= s->flags;
+
+ bi->bi_ctime = timespec_to_bch2_time(c, current_time(&inode->v));
+ return 0;
+}
+
+static int bch2_fileattr_set(struct mnt_idmap *idmap,
+ struct dentry *dentry,
+ struct fileattr *fa)
+{
+ struct bch_inode_info *inode = to_bch_ei(d_inode(dentry));
+ struct bch_fs *c = inode->v.i_sb->s_fs_info;
+ struct flags_set s = {};
+ int ret;
+
+ if (fa->fsx_valid) {
+ fa->fsx_xflags &= ~FS_XFLAG_PROJINHERIT;
+
+ s.mask = map_defined(bch_flags_to_xflags);
+ s.flags |= map_flags_rev(bch_flags_to_xflags, fa->fsx_xflags);
+ if (fa->fsx_xflags)
+ return -EOPNOTSUPP;
+
+ if (fa->fsx_projid >= U32_MAX)
+ return -EINVAL;
+
+ /*
+ * inode fields accessible via the xattr interface are stored with a +1
+ * bias, so that 0 means unset:
+ */
+ if ((inode->ei_inode.bi_project ||
+ fa->fsx_projid) &&
+ inode->ei_inode.bi_project != fa->fsx_projid + 1) {
+ s.projid = fa->fsx_projid + 1;
+ s.set_project = true;
+ }
+ }
+
+ if (fa->flags_valid) {
+ s.mask = map_defined(bch_flags_to_uflags);
+
+ s.set_casefold = true;
+ s.casefold = (fa->flags & FS_CASEFOLD_FL) != 0;
+ fa->flags &= ~FS_CASEFOLD_FL;
+
+ s.flags |= map_flags_rev(bch_flags_to_uflags, fa->flags);
+ if (fa->flags)
+ return -EOPNOTSUPP;
+ }
+
+ mutex_lock(&inode->ei_update_lock);
+ ret = bch2_subvol_is_ro(c, inode->ei_inum.subvol) ?:
+ (s.set_project
+ ? bch2_set_projid(c, inode, fa->fsx_projid)
+ : 0) ?:
+ bch2_write_inode(c, inode, fssetxattr_inode_update_fn, &s,
+ ATTR_CTIME);
+ mutex_unlock(&inode->ei_update_lock);
+ return ret;
+}
+
static const struct file_operations bch_file_operations = {
.open = bch2_open,
.llseek = bch2_llseek,
@@ -1476,6 +1785,8 @@ static const struct inode_operations bch_file_inode_operations = {
.get_inode_acl = bch2_get_acl,
.set_acl = bch2_set_acl,
#endif
+ .fileattr_get = bch2_fileattr_get,
+ .fileattr_set = bch2_fileattr_set,
};
static const struct inode_operations bch_dir_inode_operations = {
@@ -1496,6 +1807,8 @@ static const struct inode_operations bch_dir_inode_operations = {
.get_inode_acl = bch2_get_acl,
.set_acl = bch2_set_acl,
#endif
+ .fileattr_get = bch2_fileattr_get,
+ .fileattr_set = bch2_fileattr_set,
};
static const struct file_operations bch_dir_file_operations = {
@@ -1518,6 +1831,8 @@ static const struct inode_operations bch_symlink_inode_operations = {
.get_inode_acl = bch2_get_acl,
.set_acl = bch2_set_acl,
#endif
+ .fileattr_get = bch2_fileattr_get,
+ .fileattr_set = bch2_fileattr_set,
};
static const struct inode_operations bch_special_inode_operations = {
@@ -1528,6 +1843,8 @@ static const struct inode_operations bch_special_inode_operations = {
.get_inode_acl = bch2_get_acl,
.set_acl = bch2_set_acl,
#endif
+ .fileattr_get = bch2_fileattr_get,
+ .fileattr_set = bch2_fileattr_set,
};
static const struct address_space_operations bch_address_space_operations = {
diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 18308f3..7b25ced 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -321,6 +321,31 @@ static inline bool inode_should_reattach(struct bch_inode_unpacked *inode)
inode->bi_subvol == BCACHEFS_ROOT_SUBVOL)
return false;
+ /*
+ * Subvolume roots are special: older versions of subvolume roots may be
+ * disconnected, it's only the newest version that matters.
+ *
+ * We only keep a single dirent pointing to a subvolume root, i.e.
+ * older versions of snapshots will not have a different dirent pointing
+ * to the same subvolume root.
+ *
+ * This is because dirents that point to subvolumes are only visible in
+ * the parent subvolume - versioning is not needed - and keeping them
+ * around would break fsck, because when we're crossing subvolumes we
+ * don't have a consistent snapshot ID to do check the inode <-> dirent
+ * relationships.
+ *
+ * Thus, a subvolume root that's been renamed after a snapshot will have
+ * a disconnected older version - that's expected.
+ *
+ * Note that taking a snapshot always updates the root inode (to update
+ * the dirent backpointer), so a subvolume root inode with
+ * BCH_INODE_has_child_snapshot is never visible.
+ */
+ if (inode->bi_subvol &&
+ (inode->bi_flags & BCH_INODE_has_child_snapshot))
+ return false;
+
return !inode->bi_dir && !(inode->bi_flags & BCH_INODE_unlinked);
}
@@ -1007,6 +1032,23 @@ static int check_inode_dirent_inode(struct btree_trans *trans,
if (ret && !bch2_err_matches(ret, ENOENT))
return ret;
+ if ((ret || dirent_points_to_inode_nowarn(d, inode)) &&
+ inode->bi_subvol &&
+ (inode->bi_flags & BCH_INODE_has_child_snapshot)) {
+ /* Older version of a renamed subvolume root: we won't have a
+ * correct dirent for it. That's expected, see
+ * inode_should_reattach().
+ *
+ * We don't clear the backpointer field when doing the rename
+ * because there might be arbitrarily many versions in older
+ * snapshots.
+ */
+ inode->bi_dir = 0;
+ inode->bi_dir_offset = 0;
+ *write_inode = true;
+ goto out;
+ }
+
if (fsck_err_on(ret,
trans, inode_points_to_missing_dirent,
"inode points to missing dirent\n%s",
@@ -1027,7 +1069,7 @@ static int check_inode_dirent_inode(struct btree_trans *trans,
inode->bi_dir_offset = 0;
*write_inode = true;
}
-
+out:
ret = 0;
fsck_err:
bch2_trans_iter_exit(trans, &dirent_iter);
diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h
index f82cfbf..c74af15 100644
--- a/fs/bcachefs/inode.h
+++ b/fs/bcachefs/inode.h
@@ -243,6 +243,14 @@ static inline unsigned bkey_inode_mode(struct bkey_s_c k)
}
}
+static inline bool bch2_inode_casefold(struct bch_fs *c, const struct bch_inode_unpacked *bi)
+{
+ /* inode apts are stored with a +1 bias: 0 means "unset, use fs opt" */
+ return bi->bi_casefold
+ ? bi->bi_casefold - 1
+ : c->opts.casefold;
+}
+
/* i_nlink: */
static inline unsigned nlink_bias(umode_t mode)
diff --git a/fs/bcachefs/inode_format.h b/fs/bcachefs/inode_format.h
index 117110a..87e193e 100644
--- a/fs/bcachefs/inode_format.h
+++ b/fs/bcachefs/inode_format.h
@@ -103,7 +103,8 @@ struct bch_inode_generation {
x(bi_parent_subvol, 32) \
x(bi_nocow, 8) \
x(bi_depth, 32) \
- x(bi_inodes_32bit, 8)
+ x(bi_inodes_32bit, 8) \
+ x(bi_casefold, 8)
/* subset of BCH_INODE_FIELDS */
#define BCH_INODE_OPTS() \
@@ -117,7 +118,8 @@ struct bch_inode_generation {
x(background_target, 16) \
x(erasure_code, 16) \
x(nocow, 8) \
- x(inodes_32bit, 8)
+ x(inodes_32bit, 8) \
+ x(casefold, 8)
enum inode_opt_id {
#define x(name, ...) \
@@ -137,8 +139,7 @@ enum inode_opt_id {
x(i_sectors_dirty, 6) \
x(unlinked, 7) \
x(backptr_untrusted, 8) \
- x(has_child_snapshot, 9) \
- x(casefolded, 10)
+ x(has_child_snapshot, 9)
/* bits 20+ reserved for packed fields below: */
diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c
index 417bb0c..def4a26 100644
--- a/fs/bcachefs/io_read.c
+++ b/fs/bcachefs/io_read.c
@@ -487,6 +487,8 @@ static void bch2_rbio_retry(struct work_struct *work)
.inum = rbio->read_pos.inode,
};
struct bch_io_failures failed = { .nr = 0 };
+ int orig_error = rbio->ret;
+
struct btree_trans *trans = bch2_trans_get(c);
trace_io_read_retry(&rbio->bio);
@@ -519,7 +521,9 @@ static void bch2_rbio_retry(struct work_struct *work)
if (ret) {
rbio->ret = ret;
rbio->bio.bi_status = BLK_STS_IOERR;
- } else {
+ } else if (orig_error != -BCH_ERR_data_read_retry_csum_err_maybe_userspace &&
+ orig_error != -BCH_ERR_data_read_ptr_stale_race &&
+ !failed.nr) {
struct printbuf buf = PRINTBUF;
lockrestart_do(trans,
@@ -977,7 +981,8 @@ int __bch2_read_extent(struct btree_trans *trans, struct bch_read_bio *orig,
goto err;
}
- if (unlikely(bch2_csum_type_is_encryption(pick.crc.csum_type)) && !c->chacha20) {
+ if (unlikely(bch2_csum_type_is_encryption(pick.crc.csum_type)) &&
+ !c->chacha20_key_set) {
struct printbuf buf = PRINTBUF;
bch2_read_err_msg_trans(trans, &buf, orig, read_pos);
prt_printf(&buf, "attempting to read encrypted data without encryption key\n ");
@@ -1344,14 +1349,16 @@ int __bch2_read(struct btree_trans *trans, struct bch_read_bio *rbio,
bch2_trans_iter_exit(trans, &iter);
- if (ret) {
- struct printbuf buf = PRINTBUF;
- lockrestart_do(trans,
- bch2_inum_offset_err_msg_trans(trans, &buf, inum,
- bvec_iter.bi_sector << 9));
- prt_printf(&buf, "read error: %s", bch2_err_str(ret));
- bch_err_ratelimited(c, "%s", buf.buf);
- printbuf_exit(&buf);
+ if (unlikely(ret)) {
+ if (ret != -BCH_ERR_extent_poisoned) {
+ struct printbuf buf = PRINTBUF;
+ lockrestart_do(trans,
+ bch2_inum_offset_err_msg_trans(trans, &buf, inum,
+ bvec_iter.bi_sector << 9));
+ prt_printf(&buf, "data read error: %s", bch2_err_str(ret));
+ bch_err_ratelimited(c, "%s", buf.buf);
+ printbuf_exit(&buf);
+ }
rbio->bio.bi_status = BLK_STS_IOERR;
rbio->ret = ret;
diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c
index d8f74b6..bb45d36 100644
--- a/fs/bcachefs/journal.c
+++ b/fs/bcachefs/journal.c
@@ -281,7 +281,24 @@ static void __journal_entry_close(struct journal *j, unsigned closed_val, bool t
sectors = vstruct_blocks_plus(buf->data, c->block_bits,
buf->u64s_reserved) << c->block_bits;
- BUG_ON(sectors > buf->sectors);
+ if (unlikely(sectors > buf->sectors)) {
+ struct printbuf err = PRINTBUF;
+ err.atomic++;
+
+ prt_printf(&err, "journal entry overran reserved space: %u > %u\n",
+ sectors, buf->sectors);
+ prt_printf(&err, "buf u64s %u u64s reserved %u cur_entry_u64s %u block_bits %u\n",
+ le32_to_cpu(buf->data->u64s), buf->u64s_reserved,
+ j->cur_entry_u64s,
+ c->block_bits);
+ prt_printf(&err, "fatal error - emergency read only");
+ bch2_journal_halt_locked(j);
+
+ bch_err(c, "%s", err.buf);
+ printbuf_exit(&err);
+ return;
+ }
+
buf->sectors = sectors;
/*
@@ -1462,8 +1479,6 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq)
j->last_empty_seq = cur_seq - 1; /* to match j->seq */
spin_lock(&j->lock);
-
- set_bit(JOURNAL_running, &j->flags);
j->last_flush_write = jiffies;
j->reservations.idx = journal_cur_seq(j);
@@ -1474,6 +1489,21 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq)
return 0;
}
+void bch2_journal_set_replay_done(struct journal *j)
+{
+ /*
+ * journal_space_available must happen before setting JOURNAL_running
+ * JOURNAL_running must happen before JOURNAL_replay_done
+ */
+ spin_lock(&j->lock);
+ bch2_journal_space_available(j);
+
+ set_bit(JOURNAL_need_flush_write, &j->flags);
+ set_bit(JOURNAL_running, &j->flags);
+ set_bit(JOURNAL_replay_done, &j->flags);
+ spin_unlock(&j->lock);
+}
+
/* init/exit: */
void bch2_dev_journal_exit(struct bch_dev *ca)
diff --git a/fs/bcachefs/journal.h b/fs/bcachefs/journal.h
index 4782877..641e20c 100644
--- a/fs/bcachefs/journal.h
+++ b/fs/bcachefs/journal.h
@@ -437,12 +437,6 @@ static inline int bch2_journal_error(struct journal *j)
struct bch_dev;
-static inline void bch2_journal_set_replay_done(struct journal *j)
-{
- BUG_ON(!test_bit(JOURNAL_running, &j->flags));
- set_bit(JOURNAL_replay_done, &j->flags);
-}
-
void bch2_journal_unblock(struct journal *);
void bch2_journal_block(struct journal *);
struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *, u64, bool *);
@@ -459,6 +453,7 @@ void bch2_dev_journal_stop(struct journal *, struct bch_dev *);
void bch2_fs_journal_stop(struct journal *);
int bch2_fs_journal_start(struct journal *, u64);
+void bch2_journal_set_replay_done(struct journal *);
void bch2_dev_journal_exit(struct bch_dev *);
int bch2_dev_journal_init(struct bch_dev *, struct bch_sb *);
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index 1b7961f..2a54ac7 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -1460,7 +1460,7 @@ int bch2_journal_read(struct bch_fs *c,
static void journal_advance_devs_to_next_bucket(struct journal *j,
struct dev_alloc_list *devs,
- unsigned sectors, u64 seq)
+ unsigned sectors, __le64 seq)
{
struct bch_fs *c = container_of(j, struct bch_fs, journal);
diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c
index 5d1547a..ea670c3 100644
--- a/fs/bcachefs/journal_reclaim.c
+++ b/fs/bcachefs/journal_reclaim.c
@@ -252,7 +252,10 @@ void bch2_journal_space_available(struct journal *j)
bch2_journal_set_watermark(j);
out:
- j->cur_entry_sectors = !ret ? j->space[journal_space_discarded].next_entry : 0;
+ j->cur_entry_sectors = !ret
+ ? round_down(j->space[journal_space_discarded].next_entry,
+ block_sectors(c))
+ : 0;
j->cur_entry_error = ret;
if (!ret)
diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c
index 159410c..9687337 100644
--- a/fs/bcachefs/movinggc.c
+++ b/fs/bcachefs/movinggc.c
@@ -356,6 +356,13 @@ static int bch2_copygc_thread(void *arg)
set_freezable();
+ /*
+ * Data move operations can't run until after check_snapshots has
+ * completed, and bch2_snapshot_is_ancestor() is available.
+ */
+ kthread_wait_freezable(c->recovery_pass_done > BCH_RECOVERY_PASS_check_snapshots ||
+ kthread_should_stop());
+
bch2_move_stats_init(&move_stats, "copygc");
bch2_moving_ctxt_init(&ctxt, c, NULL, &move_stats,
writepoint_ptr(&c->copygc_write_point),
diff --git a/fs/bcachefs/movinggc.h b/fs/bcachefs/movinggc.h
index ea181fe..d1885cf6 100644
--- a/fs/bcachefs/movinggc.h
+++ b/fs/bcachefs/movinggc.h
@@ -5,6 +5,15 @@
unsigned long bch2_copygc_wait_amount(struct bch_fs *);
void bch2_copygc_wait_to_text(struct printbuf *, struct bch_fs *);
+static inline void bch2_copygc_wakeup(struct bch_fs *c)
+{
+ rcu_read_lock();
+ struct task_struct *p = rcu_dereference(c->copygc_thread);
+ if (p)
+ wake_up_process(p);
+ rcu_read_unlock();
+}
+
void bch2_copygc_stop(struct bch_fs *);
int bch2_copygc_start(struct bch_fs *);
void bch2_fs_copygc_init(struct bch_fs *);
diff --git a/fs/bcachefs/namei.c b/fs/bcachefs/namei.c
index 0d65ea9..46f3c8b 100644
--- a/fs/bcachefs/namei.c
+++ b/fs/bcachefs/namei.c
@@ -47,10 +47,6 @@ int bch2_create_trans(struct btree_trans *trans,
if (ret)
goto err;
- /* Inherit casefold state from parent. */
- if (S_ISDIR(mode))
- new_inode->bi_flags |= dir_u->bi_flags & BCH_INODE_casefolded;
-
if (!(flags & BCH_CREATE_SNAPSHOT)) {
/* Normal create path - allocate a new inode: */
bch2_inode_init_late(new_inode, now, uid, gid, mode, rdev, dir_u);
diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h
index 4d06313..dfb1481 100644
--- a/fs/bcachefs/opts.h
+++ b/fs/bcachefs/opts.h
@@ -228,6 +228,11 @@ enum fsck_err_opts {
OPT_BOOL(), \
BCH_SB_ERASURE_CODE, false, \
NULL, "Enable erasure coding (DO NOT USE YET)") \
+ x(casefold, u8, \
+ OPT_FS|OPT_INODE|OPT_FORMAT, \
+ OPT_BOOL(), \
+ BCH_SB_CASEFOLD, false, \
+ NULL, "Dirent lookups are casefolded") \
x(inodes_32bit, u8, \
OPT_FS|OPT_INODE|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \
OPT_BOOL(), \
diff --git a/fs/bcachefs/rebalance.c b/fs/bcachefs/rebalance.c
index c63fa53..4ccdfc1 100644
--- a/fs/bcachefs/rebalance.c
+++ b/fs/bcachefs/rebalance.c
@@ -262,7 +262,7 @@ int bch2_set_rebalance_needs_scan(struct bch_fs *c, u64 inum)
int ret = bch2_trans_commit_do(c, NULL, NULL,
BCH_TRANS_COMMIT_no_enospc,
bch2_set_rebalance_needs_scan_trans(trans, inum));
- rebalance_wakeup(c);
+ bch2_rebalance_wakeup(c);
return ret;
}
@@ -581,6 +581,13 @@ static int bch2_rebalance_thread(void *arg)
set_freezable();
+ /*
+ * Data move operations can't run until after check_snapshots has
+ * completed, and bch2_snapshot_is_ancestor() is available.
+ */
+ kthread_wait_freezable(c->recovery_pass_done > BCH_RECOVERY_PASS_check_snapshots ||
+ kthread_should_stop());
+
bch2_moving_ctxt_init(&ctxt, c, NULL, &r->work_stats,
writepoint_ptr(&c->rebalance_write_point),
true);
@@ -664,7 +671,7 @@ void bch2_rebalance_stop(struct bch_fs *c)
c->rebalance.thread = NULL;
if (p) {
- /* for sychronizing with rebalance_wakeup() */
+ /* for sychronizing with bch2_rebalance_wakeup() */
synchronize_rcu();
kthread_stop(p);
diff --git a/fs/bcachefs/rebalance.h b/fs/bcachefs/rebalance.h
index 62a3859..e5e8eb4 100644
--- a/fs/bcachefs/rebalance.h
+++ b/fs/bcachefs/rebalance.h
@@ -37,7 +37,7 @@ int bch2_set_rebalance_needs_scan_trans(struct btree_trans *, u64);
int bch2_set_rebalance_needs_scan(struct bch_fs *, u64 inum);
int bch2_set_fs_needs_rebalance(struct bch_fs *);
-static inline void rebalance_wakeup(struct bch_fs *c)
+static inline void bch2_rebalance_wakeup(struct bch_fs *c)
{
struct task_struct *p;
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 79fd18a..d6c4ef8 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -18,6 +18,7 @@
#include "journal_seq_blacklist.h"
#include "logged_ops.h"
#include "move.h"
+#include "movinggc.h"
#include "namei.h"
#include "quota.h"
#include "rebalance.h"
@@ -389,9 +390,9 @@ int bch2_journal_replay(struct bch_fs *c)
* Now, replay any remaining keys in the order in which they appear in
* the journal, unpinning those journal entries as we go:
*/
- sort(keys_sorted.data, keys_sorted.nr,
- sizeof(keys_sorted.data[0]),
- journal_sort_seq_cmp, NULL);
+ sort_nonatomic(keys_sorted.data, keys_sorted.nr,
+ sizeof(keys_sorted.data[0]),
+ journal_sort_seq_cmp, NULL);
darray_for_each(keys_sorted, kp) {
cond_resched();
@@ -1125,14 +1126,17 @@ int bch2_fs_initialize(struct bch_fs *c)
* journal_res_get() will crash if called before this has
* set up the journal.pin FIFO and journal.cur pointer:
*/
- bch2_fs_journal_start(&c->journal, 1);
- set_bit(BCH_FS_accounting_replay_done, &c->flags);
- bch2_journal_set_replay_done(&c->journal);
+ ret = bch2_fs_journal_start(&c->journal, 1);
+ if (ret)
+ goto err;
ret = bch2_fs_read_write_early(c);
if (ret)
goto err;
+ set_bit(BCH_FS_accounting_replay_done, &c->flags);
+ bch2_journal_set_replay_done(&c->journal);
+
for_each_member_device(c, ca) {
ret = bch2_dev_usage_init(ca, false);
if (ret) {
@@ -1191,6 +1195,9 @@ int bch2_fs_initialize(struct bch_fs *c)
c->recovery_pass_done = BCH_RECOVERY_PASS_NR - 1;
+ bch2_copygc_wakeup(c);
+ bch2_rebalance_wakeup(c);
+
if (enabled_qtypes(c)) {
ret = bch2_fs_quota_read(c);
if (ret)
diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c
index 593ff14..22f72bb 100644
--- a/fs/bcachefs/recovery_passes.c
+++ b/fs/bcachefs/recovery_passes.c
@@ -12,6 +12,7 @@
#include "journal.h"
#include "lru.h"
#include "logged_ops.h"
+#include "movinggc.h"
#include "rebalance.h"
#include "recovery.h"
#include "recovery_passes.h"
@@ -262,49 +263,52 @@ int bch2_run_recovery_passes(struct bch_fs *c)
*/
c->opts.recovery_passes_exclude &= ~BCH_RECOVERY_PASS_set_may_go_rw;
- while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns) && !ret) {
- c->next_recovery_pass = c->curr_recovery_pass + 1;
+ spin_lock_irq(&c->recovery_pass_lock);
- spin_lock_irq(&c->recovery_pass_lock);
+ while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns) && !ret) {
+ unsigned prev_done = c->recovery_pass_done;
unsigned pass = c->curr_recovery_pass;
+ c->next_recovery_pass = pass + 1;
+
if (c->opts.recovery_pass_last &&
- c->curr_recovery_pass > c->opts.recovery_pass_last) {
- spin_unlock_irq(&c->recovery_pass_lock);
+ c->curr_recovery_pass > c->opts.recovery_pass_last)
break;
- }
- if (!should_run_recovery_pass(c, pass)) {
- c->curr_recovery_pass++;
- c->recovery_pass_done = max(c->recovery_pass_done, pass);
+ if (should_run_recovery_pass(c, pass)) {
spin_unlock_irq(&c->recovery_pass_lock);
- continue;
+ ret = bch2_run_recovery_pass(c, pass) ?:
+ bch2_journal_flush(&c->journal);
+
+ if (!ret && !test_bit(BCH_FS_error, &c->flags))
+ bch2_clear_recovery_pass_required(c, pass);
+ spin_lock_irq(&c->recovery_pass_lock);
+
+ if (c->next_recovery_pass < c->curr_recovery_pass) {
+ /*
+ * bch2_run_explicit_recovery_pass() was called: we
+ * can't always catch -BCH_ERR_restart_recovery because
+ * it may have been called from another thread (btree
+ * node read completion)
+ */
+ ret = 0;
+ c->recovery_passes_complete &= ~(~0ULL << c->curr_recovery_pass);
+ } else {
+ c->recovery_passes_complete |= BIT_ULL(pass);
+ c->recovery_pass_done = max(c->recovery_pass_done, pass);
+ }
}
- spin_unlock_irq(&c->recovery_pass_lock);
- ret = bch2_run_recovery_pass(c, pass) ?:
- bch2_journal_flush(&c->journal);
-
- if (!ret && !test_bit(BCH_FS_error, &c->flags))
- bch2_clear_recovery_pass_required(c, pass);
-
- spin_lock_irq(&c->recovery_pass_lock);
- if (c->next_recovery_pass < c->curr_recovery_pass) {
- /*
- * bch2_run_explicit_recovery_pass() was called: we
- * can't always catch -BCH_ERR_restart_recovery because
- * it may have been called from another thread (btree
- * node read completion)
- */
- ret = 0;
- c->recovery_passes_complete &= ~(~0ULL << c->curr_recovery_pass);
- } else {
- c->recovery_passes_complete |= BIT_ULL(pass);
- c->recovery_pass_done = max(c->recovery_pass_done, pass);
- }
c->curr_recovery_pass = c->next_recovery_pass;
- spin_unlock_irq(&c->recovery_pass_lock);
+
+ if (prev_done <= BCH_RECOVERY_PASS_check_snapshots &&
+ c->recovery_pass_done > BCH_RECOVERY_PASS_check_snapshots) {
+ bch2_copygc_wakeup(c);
+ bch2_rebalance_wakeup(c);
+ }
}
+ spin_unlock_irq(&c->recovery_pass_lock);
+
return ret;
}
diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h
index 5d43e35..dc53d25 100644
--- a/fs/bcachefs/sb-errors_format.h
+++ b/fs/bcachefs/sb-errors_format.h
@@ -290,8 +290,8 @@ enum bch_fsck_flags {
x(btree_node_bkey_bad_u64s, 260, 0) \
x(btree_node_topology_empty_interior_node, 261, 0) \
x(btree_ptr_v2_min_key_bad, 262, 0) \
- x(btree_root_unreadable_and_scan_found_nothing, 263, 0) \
- x(snapshot_node_missing, 264, 0) \
+ x(btree_root_unreadable_and_scan_found_nothing, 263, FSCK_AUTOFIX) \
+ x(snapshot_node_missing, 264, FSCK_AUTOFIX) \
x(dup_backpointer_to_bad_csum_extent, 265, 0) \
x(btree_bitmap_not_marked, 266, FSCK_AUTOFIX) \
x(sb_clean_entry_overrun, 267, 0) \
diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c
index b7de29a..fec569c 100644
--- a/fs/bcachefs/snapshot.c
+++ b/fs/bcachefs/snapshot.c
@@ -396,7 +396,7 @@ u32 bch2_snapshot_tree_oldest_subvol(struct bch_fs *c, u32 snapshot_root)
u32 subvol = 0, s;
rcu_read_lock();
- while (id) {
+ while (id && bch2_snapshot_exists(c, id)) {
s = snapshot_t(c, id)->subvol;
if (s && (!subvol || s < subvol))
diff --git a/fs/bcachefs/str_hash.h b/fs/bcachefs/str_hash.h
index 09a354a..0c1a005 100644
--- a/fs/bcachefs/str_hash.h
+++ b/fs/bcachefs/str_hash.h
@@ -33,7 +33,7 @@ bch2_str_hash_opt_to_type(struct bch_fs *c, enum bch_str_hash_opts opt)
struct bch_hash_info {
u8 type;
- struct unicode_map *cf_encoding;
+ struct unicode_map *cf_encoding;
/*
* For crc32 or crc64 string hashes the first key value of
* the siphash_key (k0) is used as the key.
@@ -44,11 +44,10 @@ struct bch_hash_info {
static inline struct bch_hash_info
bch2_hash_info_init(struct bch_fs *c, const struct bch_inode_unpacked *bi)
{
- /* XXX ick */
struct bch_hash_info info = {
.type = INODE_STR_HASH(bi),
#ifdef CONFIG_UNICODE
- .cf_encoding = !!(bi->bi_flags & BCH_INODE_casefolded) ? c->cf_encoding : NULL,
+ .cf_encoding = bch2_inode_casefold(c, bi) ? c->cf_encoding : NULL,
#endif
.siphash_key = { .k0 = bi->bi_hash_seed }
};
diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c
index e27422b..cb5d960 100644
--- a/fs/bcachefs/super-io.c
+++ b/fs/bcachefs/super-io.c
@@ -73,14 +73,30 @@ int bch2_set_version_incompat(struct bch_fs *c, enum bcachefs_metadata_version v
? 0
: -BCH_ERR_may_not_use_incompat_feature;
+ mutex_lock(&c->sb_lock);
if (!ret) {
- mutex_lock(&c->sb_lock);
SET_BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb,
max(BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb), version));
bch2_write_super(c);
- mutex_unlock(&c->sb_lock);
+ } else {
+ darray_for_each(c->incompat_versions_requested, i)
+ if (version == *i)
+ goto out;
+
+ darray_push(&c->incompat_versions_requested, version);
+ struct printbuf buf = PRINTBUF;
+ prt_str(&buf, "requested incompat feature ");
+ bch2_version_to_text(&buf, version);
+ prt_str(&buf, " currently not enabled");
+ prt_printf(&buf, "\n set version_upgrade=incompat to enable");
+
+ bch_notice(c, "%s", buf.buf);
+ printbuf_exit(&buf);
}
+out:
+ mutex_unlock(&c->sb_lock);
+
return ret;
}
@@ -1086,7 +1102,8 @@ int bch2_write_super(struct bch_fs *c)
prt_str(&buf, ")");
bch2_fs_fatal_error(c, ": %s", buf.buf);
printbuf_exit(&buf);
- return -BCH_ERR_sb_not_downgraded;
+ ret = -BCH_ERR_sb_not_downgraded;
+ goto out;
}
darray_for_each(online_devices, ca) {
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index a58edde43..e4ab059 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -70,14 +70,10 @@
#include <linux/percpu.h>
#include <linux/random.h>
#include <linux/sysfs.h>
-#include <crypto/hash.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Kent Overstreet <kent.overstreet@gmail.com>");
MODULE_DESCRIPTION("bcachefs filesystem");
-MODULE_SOFTDEP("pre: chacha20");
-MODULE_SOFTDEP("pre: poly1305");
-MODULE_SOFTDEP("pre: xxhash");
const char * const bch2_fs_flag_strs[] = {
#define x(n) #n,
@@ -422,32 +418,6 @@ bool bch2_fs_emergency_read_only_locked(struct bch_fs *c)
return ret;
}
-static int bch2_fs_read_write_late(struct bch_fs *c)
-{
- int ret;
-
- /*
- * Data move operations can't run until after check_snapshots has
- * completed, and bch2_snapshot_is_ancestor() is available.
- *
- * Ideally we'd start copygc/rebalance earlier instead of waiting for
- * all of recovery/fsck to complete:
- */
- ret = bch2_copygc_start(c);
- if (ret) {
- bch_err(c, "error starting copygc thread");
- return ret;
- }
-
- ret = bch2_rebalance_start(c);
- if (ret) {
- bch_err(c, "error starting rebalance thread");
- return ret;
- }
-
- return 0;
-}
-
static int __bch2_fs_read_write(struct bch_fs *c, bool early)
{
int ret;
@@ -470,29 +440,28 @@ static int __bch2_fs_read_write(struct bch_fs *c, bool early)
clear_bit(BCH_FS_clean_shutdown, &c->flags);
- /*
- * First journal write must be a flush write: after a clean shutdown we
- * don't read the journal, so the first journal write may end up
- * overwriting whatever was there previously, and there must always be
- * at least one non-flush write in the journal or recovery will fail:
- */
- set_bit(JOURNAL_need_flush_write, &c->journal.flags);
- set_bit(JOURNAL_running, &c->journal.flags);
-
__for_each_online_member(c, ca, BIT(BCH_MEMBER_STATE_rw), READ) {
bch2_dev_allocator_add(c, ca);
percpu_ref_reinit(&ca->io_ref[WRITE]);
}
bch2_recalc_capacity(c);
+ /*
+ * First journal write must be a flush write: after a clean shutdown we
+ * don't read the journal, so the first journal write may end up
+ * overwriting whatever was there previously, and there must always be
+ * at least one non-flush write in the journal or recovery will fail:
+ */
+ spin_lock(&c->journal.lock);
+ set_bit(JOURNAL_need_flush_write, &c->journal.flags);
+ set_bit(JOURNAL_running, &c->journal.flags);
+ bch2_journal_space_available(&c->journal);
+ spin_unlock(&c->journal.lock);
+
ret = bch2_fs_mark_dirty(c);
if (ret)
goto err;
- spin_lock(&c->journal.lock);
- bch2_journal_space_available(&c->journal);
- spin_unlock(&c->journal.lock);
-
ret = bch2_journal_reclaim_start(&c->journal);
if (ret)
goto err;
@@ -508,10 +477,17 @@ static int __bch2_fs_read_write(struct bch_fs *c, bool early)
atomic_long_inc(&c->writes[i]);
}
#endif
- if (!early) {
- ret = bch2_fs_read_write_late(c);
- if (ret)
- goto err;
+
+ ret = bch2_copygc_start(c);
+ if (ret) {
+ bch_err_msg(c, ret, "error starting copygc thread");
+ goto err;
+ }
+
+ ret = bch2_rebalance_start(c);
+ if (ret) {
+ bch_err_msg(c, ret, "error starting rebalance thread");
+ goto err;
}
bch2_do_discards(c);
@@ -557,6 +533,7 @@ static void __bch2_fs_free(struct bch_fs *c)
bch2_find_btree_nodes_exit(&c->found_btree_nodes);
bch2_free_pending_node_rewrites(c);
+ bch2_free_fsck_errs(c);
bch2_fs_accounting_exit(c);
bch2_fs_sb_errors_exit(c);
bch2_fs_counters_exit(c);
@@ -593,6 +570,7 @@ static void __bch2_fs_free(struct bch_fs *c)
free_percpu(c->online_reserved);
}
+ darray_exit(&c->incompat_versions_requested);
darray_exit(&c->btree_roots_extra);
free_percpu(c->pcpu);
free_percpu(c->usage);
@@ -1002,12 +980,6 @@ static void print_mount_opts(struct bch_fs *c)
prt_str(&p, "starting version ");
bch2_version_to_text(&p, c->sb.version);
- if (c->opts.read_only) {
- prt_str(&p, " opts=");
- first = false;
- prt_printf(&p, "ro");
- }
-
for (i = 0; i < bch2_opts_nr; i++) {
const struct bch_option *opt = &bch2_opt_table[i];
u64 v = bch2_opt_get_by_id(&c->opts, i);
@@ -1023,10 +995,49 @@ static void print_mount_opts(struct bch_fs *c)
bch2_opt_to_text(&p, c, c->disk_sb.sb, opt, v, OPT_SHOW_MOUNT_STYLE);
}
+ if (c->sb.version_incompat_allowed != c->sb.version) {
+ prt_printf(&p, "\n allowing incompatible features above ");
+ bch2_version_to_text(&p, c->sb.version_incompat_allowed);
+ }
+
bch_info(c, "%s", p.buf);
printbuf_exit(&p);
}
+static bool bch2_fs_may_start(struct bch_fs *c)
+{
+ struct bch_dev *ca;
+ unsigned i, flags = 0;
+
+ if (c->opts.very_degraded)
+ flags |= BCH_FORCE_IF_DEGRADED|BCH_FORCE_IF_LOST;
+
+ if (c->opts.degraded)
+ flags |= BCH_FORCE_IF_DEGRADED;
+
+ if (!c->opts.degraded &&
+ !c->opts.very_degraded) {
+ mutex_lock(&c->sb_lock);
+
+ for (i = 0; i < c->disk_sb.sb->nr_devices; i++) {
+ if (!bch2_member_exists(c->disk_sb.sb, i))
+ continue;
+
+ ca = bch2_dev_locked(c, i);
+
+ if (!bch2_dev_is_online(ca) &&
+ (ca->mi.state == BCH_MEMBER_STATE_rw ||
+ ca->mi.state == BCH_MEMBER_STATE_ro)) {
+ mutex_unlock(&c->sb_lock);
+ return false;
+ }
+ }
+ mutex_unlock(&c->sb_lock);
+ }
+
+ return bch2_have_enough_devs(c, bch2_online_devs(c), flags, true);
+}
+
int bch2_fs_start(struct bch_fs *c)
{
time64_t now = ktime_get_real_seconds();
@@ -1034,6 +1045,9 @@ int bch2_fs_start(struct bch_fs *c)
print_mount_opts(c);
+ if (!bch2_fs_may_start(c))
+ return -BCH_ERR_insufficient_devices_to_start;
+
down_write(&c->state_lock);
mutex_lock(&c->sb_lock);
@@ -1086,13 +1100,10 @@ int bch2_fs_start(struct bch_fs *c)
wake_up(&c->ro_ref_wait);
down_write(&c->state_lock);
- if (c->opts.read_only) {
+ if (c->opts.read_only)
bch2_fs_read_only(c);
- } else {
- ret = !test_bit(BCH_FS_rw, &c->flags)
- ? bch2_fs_read_write(c)
- : bch2_fs_read_write_late(c);
- }
+ else if (!test_bit(BCH_FS_rw, &c->flags))
+ ret = bch2_fs_read_write(c);
up_write(&c->state_lock);
err:
@@ -1504,7 +1515,7 @@ static int bch2_dev_attach_bdev(struct bch_fs *c, struct bch_sb_handle *sb)
printbuf_exit(&name);
- rebalance_wakeup(c);
+ bch2_rebalance_wakeup(c);
return 0;
}
@@ -1563,40 +1574,6 @@ bool bch2_dev_state_allowed(struct bch_fs *c, struct bch_dev *ca,
}
}
-static bool bch2_fs_may_start(struct bch_fs *c)
-{
- struct bch_dev *ca;
- unsigned i, flags = 0;
-
- if (c->opts.very_degraded)
- flags |= BCH_FORCE_IF_DEGRADED|BCH_FORCE_IF_LOST;
-
- if (c->opts.degraded)
- flags |= BCH_FORCE_IF_DEGRADED;
-
- if (!c->opts.degraded &&
- !c->opts.very_degraded) {
- mutex_lock(&c->sb_lock);
-
- for (i = 0; i < c->disk_sb.sb->nr_devices; i++) {
- if (!bch2_member_exists(c->disk_sb.sb, i))
- continue;
-
- ca = bch2_dev_locked(c, i);
-
- if (!bch2_dev_is_online(ca) &&
- (ca->mi.state == BCH_MEMBER_STATE_rw ||
- ca->mi.state == BCH_MEMBER_STATE_ro)) {
- mutex_unlock(&c->sb_lock);
- return false;
- }
- }
- mutex_unlock(&c->sb_lock);
- }
-
- return bch2_have_enough_devs(c, bch2_online_devs(c), flags, true);
-}
-
static void __bch2_dev_read_only(struct bch_fs *c, struct bch_dev *ca)
{
bch2_dev_io_ref_stop(ca, WRITE);
@@ -1650,7 +1627,7 @@ int __bch2_dev_set_state(struct bch_fs *c, struct bch_dev *ca,
if (new_state == BCH_MEMBER_STATE_rw)
__bch2_dev_read_write(c, ca);
- rebalance_wakeup(c);
+ bch2_rebalance_wakeup(c);
return ret;
}
@@ -1767,7 +1744,8 @@ int bch2_dev_remove(struct bch_fs *c, struct bch_dev *ca, int flags)
up_write(&c->state_lock);
return 0;
err:
- if (ca->mi.state == BCH_MEMBER_STATE_rw &&
+ if (test_bit(BCH_FS_rw, &c->flags) &&
+ ca->mi.state == BCH_MEMBER_STATE_rw &&
!percpu_ref_is_zero(&ca->io_ref[READ]))
__bch2_dev_read_write(c, ca);
up_write(&c->state_lock);
@@ -2231,11 +2209,6 @@ struct bch_fs *bch2_fs_open(char * const *devices, unsigned nr_devices,
}
up_write(&c->state_lock);
- if (!bch2_fs_may_start(c)) {
- ret = -BCH_ERR_insufficient_devices_to_start;
- goto err_print;
- }
-
if (!c->opts.nostart) {
ret = bch2_fs_start(c);
if (ret)
diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c
index e5f003c..82ee333 100644
--- a/fs/bcachefs/sysfs.c
+++ b/fs/bcachefs/sysfs.c
@@ -654,11 +654,10 @@ static ssize_t sysfs_opt_store(struct bch_fs *c,
bch2_set_rebalance_needs_scan(c, 0);
if (v && id == Opt_rebalance_enabled)
- rebalance_wakeup(c);
+ bch2_rebalance_wakeup(c);
- if (v && id == Opt_copygc_enabled &&
- c->copygc_thread)
- wake_up_process(c->copygc_thread);
+ if (v && id == Opt_copygc_enabled)
+ bch2_copygc_wakeup(c);
if (id == Opt_discard && !ca) {
mutex_lock(&c->sb_lock);
diff --git a/fs/bcachefs/tests.c b/fs/bcachefs/tests.c
index c265b10..782a05f 100644
--- a/fs/bcachefs/tests.c
+++ b/fs/bcachefs/tests.c
@@ -342,6 +342,8 @@ static int test_iterate_slots_extents(struct bch_fs *c, u64 nr)
*/
static int test_peek_end(struct bch_fs *c, u64 nr)
{
+ delete_test_keys(c);
+
struct btree_trans *trans = bch2_trans_get(c);
struct btree_iter iter;
struct bkey_s_c k;
@@ -362,6 +364,8 @@ static int test_peek_end(struct bch_fs *c, u64 nr)
static int test_peek_end_extents(struct bch_fs *c, u64 nr)
{
+ delete_test_keys(c);
+
struct btree_trans *trans = bch2_trans_get(c);
struct btree_iter iter;
struct bkey_s_c k;
diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h
index 6ba5071..3e52c7f 100644
--- a/fs/bcachefs/util.h
+++ b/fs/bcachefs/util.h
@@ -739,4 +739,42 @@ static inline void memcpy_swab(void *_dst, void *_src, size_t len)
*--dst = *src++;
}
+#define set_flags(_map, _in, _out) \
+do { \
+ unsigned _i; \
+ \
+ for (_i = 0; _i < ARRAY_SIZE(_map); _i++) \
+ if ((_in) & (1 << _i)) \
+ (_out) |= _map[_i]; \
+ else \
+ (_out) &= ~_map[_i]; \
+} while (0)
+
+#define map_flags(_map, _in) \
+({ \
+ unsigned _out = 0; \
+ \
+ set_flags(_map, _in, _out); \
+ _out; \
+})
+
+#define map_flags_rev(_map, _in) \
+({ \
+ unsigned _i, _out = 0; \
+ \
+ for (_i = 0; _i < ARRAY_SIZE(_map); _i++) \
+ if ((_in) & _map[_i]) { \
+ (_out) |= 1 << _i; \
+ (_in) &= ~_map[_i]; \
+ } \
+ (_out); \
+})
+
+#define map_defined(_map) \
+({ \
+ unsigned _in = ~0; \
+ \
+ map_flags_rev(_map, _in); \
+})
+
#endif /* _BCACHEFS_UTIL_H */
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index fa85155..73a2dfb 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -3,9 +3,9 @@
config BTRFS_FS
tristate "Btrfs filesystem support"
select BLK_CGROUP_PUNT_BIO
+ select CRC32
select CRYPTO
select CRYPTO_CRC32C
- select LIBCRC32C
select CRYPTO_XXHASH
select CRYPTO_SHA256
select CRYPTO_BLAKE2B
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 3dd555d..aa58e06 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3853,7 +3853,6 @@ static int write_dev_supers(struct btrfs_device *device,
atomic_inc(&device->sb_write_errors);
continue;
}
- ASSERT(folio_order(folio) == 0);
offset = offset_in_folio(folio, bytenr);
disk_super = folio_address(folio) + offset;
@@ -3926,7 +3925,6 @@ static int wait_dev_supers(struct btrfs_device *device, int max_mirrors)
/* If the folio has been removed, then we know it completed. */
if (IS_ERR(folio))
continue;
- ASSERT(folio_order(folio) == 0);
/* Folio will be unlocked once the write completes. */
folio_wait_locked(folio);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 197f5e5..8515c31 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2047,7 +2047,7 @@ static int submit_eb_subpage(struct folio *folio, struct writeback_control *wbc)
subpage->bitmaps)) {
spin_unlock_irqrestore(&subpage->lock, flags);
spin_unlock(&folio->mapping->i_private_lock);
- bit_start++;
+ bit_start += sectors_per_node;
continue;
}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 262a707..71b8a82 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2104,15 +2104,20 @@ static void btrfs_punch_hole_lock_range(struct inode *inode,
* will always return true.
* So here we need to do extra page alignment for
* filemap_range_has_page().
+ *
+ * And do not decrease page_lockend right now, as it can be 0.
*/
const u64 page_lockstart = round_up(lockstart, PAGE_SIZE);
- const u64 page_lockend = round_down(lockend + 1, PAGE_SIZE) - 1;
+ const u64 page_lockend = round_down(lockend + 1, PAGE_SIZE);
while (1) {
truncate_pagecache_range(inode, lockstart, lockend);
lock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend,
cached_state);
+ /* The same page or adjacent pages. */
+ if (page_lockend <= page_lockstart)
+ break;
/*
* We can't have ordered extents in the range, nor dirty/writeback
* pages, because we have locked the inode's VFS lock in exclusive
@@ -2124,7 +2129,7 @@ static void btrfs_punch_hole_lock_range(struct inode *inode,
* we do, unlock the range and retry.
*/
if (!filemap_range_has_page(inode->i_mapping, page_lockstart,
- page_lockend))
+ page_lockend - 1))
break;
unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index cc67d1a..bdafe4d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2129,12 +2129,13 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode,
/*
* If the found extent starts after requested offset, then
- * adjust extent_end to be right before this extent begins
+ * adjust cur_offset to be right before this extent begins.
*/
if (found_key.offset > cur_offset) {
- extent_end = found_key.offset;
- extent_type = 0;
- goto must_cow;
+ if (cow_start == (u64)-1)
+ cow_start = cur_offset;
+ cur_offset = found_key.offset;
+ goto next_slot;
}
/*
@@ -5681,8 +5682,10 @@ struct btrfs_inode *btrfs_iget(u64 ino, struct btrfs_root *root)
return inode;
path = btrfs_alloc_path();
- if (!path)
+ if (!path) {
+ iget_failed(&inode->vfs_inode);
return ERR_PTR(-ENOMEM);
+ }
ret = btrfs_read_locked_inode(inode, path);
btrfs_free_path(path);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index a13d81b..63aeacc 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -4902,6 +4902,8 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue
ret = btrfs_encoded_read(&kiocb, &data->iter, &data->args, &cached_state,
&disk_bytenr, &disk_io_size);
+ if (ret == -EAGAIN)
+ goto out_acct;
if (ret < 0 && ret != -EIOCBQUEUED)
goto out_free;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index f948f4f..e17bcb0 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3803,7 +3803,7 @@ static noinline_for_stack struct inode *create_reloc_inode(
if (ret) {
if (inode)
iput(&inode->vfs_inode);
- inode = ERR_PTR(ret);
+ return ERR_PTR(ret);
}
return &inode->vfs_inode;
}
diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
index 11dbd7b..c0a0b8b 100644
--- a/fs/btrfs/subpage.c
+++ b/fs/btrfs/subpage.c
@@ -204,7 +204,7 @@ static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info,
btrfs_blocks_per_folio(fs_info, folio); \
\
btrfs_subpage_assert(fs_info, folio, start, len); \
- __start_bit = offset_in_page(start) >> fs_info->sectorsize_bits; \
+ __start_bit = offset_in_folio(folio, start) >> fs_info->sectorsize_bits; \
__start_bit += blocks_per_folio * btrfs_bitmap_nr_##name; \
__start_bit; \
})
@@ -666,7 +666,7 @@ IMPLEMENT_BTRFS_PAGE_OPS(checked, folio_set_checked, folio_clear_checked,
btrfs_blocks_per_folio(fs_info, folio); \
const struct btrfs_subpage *subpage = folio_get_private(folio); \
\
- ASSERT(blocks_per_folio < BITS_PER_LONG); \
+ ASSERT(blocks_per_folio <= BITS_PER_LONG); \
*dst = bitmap_read(subpage->bitmaps, \
blocks_per_folio * btrfs_bitmap_nr_##name, \
blocks_per_folio); \
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 40709e2..7121d8c 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1139,8 +1139,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
subvol_name = btrfs_get_subvol_name_from_objectid(info,
btrfs_root_id(BTRFS_I(d_inode(dentry))->root));
if (!IS_ERR(subvol_name)) {
- seq_puts(seq, ",subvol=");
- seq_escape(seq, subvol_name, " \t\n\\");
+ seq_show_option(seq, "subvol", subvol_name);
kfree(subvol_name);
}
return 0;
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 43979891..2b66a61 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -2235,7 +2235,7 @@ int btrfs_verify_level_key(struct extent_buffer *eb,
btrfs_err(fs_info,
"tree level mismatch detected, bytenr=%llu level expected=%u has=%u",
eb->start, check->level, found_level);
- return -EIO;
+ return -EUCLEAN;
}
if (!check->has_first_key)
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index fb8b8b2..4a3e02b 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1277,7 +1277,7 @@ struct zone_info {
static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
struct zone_info *info, unsigned long *active,
- struct btrfs_chunk_map *map)
+ struct btrfs_chunk_map *map, bool new)
{
struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
struct btrfs_device *device;
@@ -1307,6 +1307,8 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
return 0;
}
+ ASSERT(!new || btrfs_dev_is_empty_zone(device, info->physical));
+
/* This zone will be used for allocation, so mark this zone non-empty. */
btrfs_dev_clear_zone_empty(device, info->physical);
@@ -1319,6 +1321,18 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
* to determine the allocation offset within the zone.
*/
WARN_ON(!IS_ALIGNED(info->physical, fs_info->zone_size));
+
+ if (new) {
+ sector_t capacity;
+
+ capacity = bdev_zone_capacity(device->bdev, info->physical >> SECTOR_SHIFT);
+ up_read(&dev_replace->rwsem);
+ info->alloc_offset = 0;
+ info->capacity = capacity << SECTOR_SHIFT;
+
+ return 0;
+ }
+
nofs_flag = memalloc_nofs_save();
ret = btrfs_get_dev_zone(device, info->physical, &zone);
memalloc_nofs_restore(nofs_flag);
@@ -1588,7 +1602,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
}
for (i = 0; i < map->num_stripes; i++) {
- ret = btrfs_load_zone_info(fs_info, i, &zone_info[i], active, map);
+ ret = btrfs_load_zone_info(fs_info, i, &zone_info[i], active, map, new);
if (ret)
goto out;
@@ -1659,7 +1673,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
* stripe.
*/
cache->alloc_offset = cache->zone_capacity;
- ret = 0;
}
out:
diff --git a/fs/buffer.c b/fs/buffer.c
index c7abb4a0..7be23ff 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -176,18 +176,8 @@ void end_buffer_write_sync(struct buffer_head *bh, int uptodate)
}
EXPORT_SYMBOL(end_buffer_write_sync);
-/*
- * Various filesystems appear to want __find_get_block to be non-blocking.
- * But it's the page lock which protects the buffers. To get around this,
- * we get exclusion from try_to_free_buffers with the blockdev mapping's
- * i_private_lock.
- *
- * Hack idea: for the blockdev mapping, i_private_lock contention
- * may be quite high. This code could TryLock the page, and if that
- * succeeds, there is no need to take i_private_lock.
- */
static struct buffer_head *
-__find_get_block_slow(struct block_device *bdev, sector_t block)
+__find_get_block_slow(struct block_device *bdev, sector_t block, bool atomic)
{
struct address_space *bd_mapping = bdev->bd_mapping;
const int blkbits = bd_mapping->host->i_blkbits;
@@ -204,10 +194,28 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
if (IS_ERR(folio))
goto out;
- spin_lock(&bd_mapping->i_private_lock);
+ /*
+ * Folio lock protects the buffers. Callers that cannot block
+ * will fallback to serializing vs try_to_free_buffers() via
+ * the i_private_lock.
+ */
+ if (atomic)
+ spin_lock(&bd_mapping->i_private_lock);
+ else
+ folio_lock(folio);
+
head = folio_buffers(folio);
if (!head)
goto out_unlock;
+ /*
+ * Upon a noref migration, the folio lock serializes here;
+ * otherwise bail.
+ */
+ if (test_bit_acquire(BH_Migrate, &head->b_state)) {
+ WARN_ON(!atomic);
+ goto out_unlock;
+ }
+
bh = head;
do {
if (!buffer_mapped(bh))
@@ -236,7 +244,10 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
1 << blkbits);
}
out_unlock:
- spin_unlock(&bd_mapping->i_private_lock);
+ if (atomic)
+ spin_unlock(&bd_mapping->i_private_lock);
+ else
+ folio_unlock(folio);
folio_put(folio);
out:
return ret;
@@ -656,7 +667,9 @@ EXPORT_SYMBOL(generic_buffers_fsync);
void write_boundary_block(struct block_device *bdev,
sector_t bblock, unsigned blocksize)
{
- struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize);
+ struct buffer_head *bh;
+
+ bh = __find_get_block_nonatomic(bdev, bblock + 1, blocksize);
if (bh) {
if (buffer_dirty(bh))
write_dirty_buffer(bh, 0);
@@ -1386,16 +1399,18 @@ lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size)
/*
* Perform a pagecache lookup for the matching buffer. If it's there, refresh
* it in the LRU and mark it as accessed. If it is not present then return
- * NULL
+ * NULL. Atomic context callers may also return NULL if the buffer is being
+ * migrated; similarly the page is not marked accessed either.
*/
-struct buffer_head *
-__find_get_block(struct block_device *bdev, sector_t block, unsigned size)
+static struct buffer_head *
+find_get_block_common(struct block_device *bdev, sector_t block,
+ unsigned size, bool atomic)
{
struct buffer_head *bh = lookup_bh_lru(bdev, block, size);
if (bh == NULL) {
/* __find_get_block_slow will mark the page accessed */
- bh = __find_get_block_slow(bdev, block);
+ bh = __find_get_block_slow(bdev, block, atomic);
if (bh)
bh_lru_install(bh);
} else
@@ -1403,8 +1418,23 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size)
return bh;
}
+
+struct buffer_head *
+__find_get_block(struct block_device *bdev, sector_t block, unsigned size)
+{
+ return find_get_block_common(bdev, block, size, true);
+}
EXPORT_SYMBOL(__find_get_block);
+/* same as __find_get_block() but allows sleeping contexts */
+struct buffer_head *
+__find_get_block_nonatomic(struct block_device *bdev, sector_t block,
+ unsigned size)
+{
+ return find_get_block_common(bdev, block, size, false);
+}
+EXPORT_SYMBOL(__find_get_block_nonatomic);
+
/**
* bdev_getblk - Get a buffer_head in a block device's buffer cache.
* @bdev: The block device.
@@ -1422,7 +1452,12 @@ EXPORT_SYMBOL(__find_get_block);
struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block,
unsigned size, gfp_t gfp)
{
- struct buffer_head *bh = __find_get_block(bdev, block, size);
+ struct buffer_head *bh;
+
+ if (gfpflags_allow_blocking(gfp))
+ bh = __find_get_block_nonatomic(bdev, block, size);
+ else
+ bh = __find_get_block(bdev, block, size);
might_alloc(gfp);
if (bh)
diff --git a/fs/cachefiles/key.c b/fs/cachefiles/key.c
index bf935e2..b485256 100644
--- a/fs/cachefiles/key.c
+++ b/fs/cachefiles/key.c
@@ -8,7 +8,7 @@
#include <linux/slab.h>
#include "internal.h"
-static const char cachefiles_charmap[64] =
+static const char cachefiles_charmap[64] __nonstring =
"0123456789" /* 0 - 9 */
"abcdefghijklmnopqrstuvwxyz" /* 10 - 35 */
"ABCDEFGHIJKLMNOPQRSTUVWXYZ" /* 36 - 61 */
diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
index 7249d70..3e7def3 100644
--- a/fs/ceph/Kconfig
+++ b/fs/ceph/Kconfig
@@ -3,7 +3,7 @@
tristate "Ceph distributed file system"
depends on INET
select CEPH_LIB
- select LIBCRC32C
+ select CRC32
select CRYPTO_AES
select CRYPTO
select NETFS_SUPPORT
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 6ac2bd5..06cd296 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -2367,7 +2367,7 @@ static int fill_fscrypt_truncate(struct inode *inode,
/* Try to writeback the dirty pagecaches */
if (issued & (CEPH_CAP_FILE_BUFFER)) {
- loff_t lend = orig_pos + CEPH_FSCRYPT_BLOCK_SHIFT - 1;
+ loff_t lend = orig_pos + CEPH_FSCRYPT_BLOCK_SIZE - 1;
ret = filemap_write_and_wait_range(inode->i_mapping,
orig_pos, lend);
diff --git a/fs/dax.c b/fs/dax.c
index af5045b..6763034 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -396,6 +396,7 @@ static inline unsigned long dax_folio_put(struct folio *folio)
order = folio_order(folio);
if (!order)
return 0;
+ folio_reset_order(folio);
for (i = 0; i < (1UL << order); i++) {
struct dev_pagemap *pgmap = page_pgmap(&folio->page);
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 42e4d6e..9c20d78 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -89,12 +89,12 @@ enum {
};
static const struct fs_parameter_spec devpts_param_specs[] = {
- fsparam_u32 ("gid", Opt_gid),
+ fsparam_gid ("gid", Opt_gid),
fsparam_s32 ("max", Opt_max),
fsparam_u32oct ("mode", Opt_mode),
fsparam_flag ("newinstance", Opt_newinstance),
fsparam_u32oct ("ptmxmode", Opt_ptmxmode),
- fsparam_u32 ("uid", Opt_uid),
+ fsparam_uid ("uid", Opt_uid),
{}
};
diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig
index 331e49c..8f68ec4 100644
--- a/fs/erofs/Kconfig
+++ b/fs/erofs/Kconfig
@@ -3,8 +3,8 @@
config EROFS_FS
tristate "EROFS filesystem support"
depends on BLOCK
+ select CRC32
select FS_IOMAP
- select LIBCRC32C
help
EROFS (Enhanced Read-Only File System) is a lightweight read-only
file system with modern designs (e.g. no buffer heads, inline
diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
index 9581e9b..767fb4a 100644
--- a/fs/erofs/erofs_fs.h
+++ b/fs/erofs/erofs_fs.h
@@ -56,7 +56,7 @@ struct erofs_super_block {
union {
__le16 rootnid_2b; /* nid of root directory */
__le16 blocks_hi; /* (48BIT on) blocks count MSB */
- } rb;
+ } __packed rb;
__le64 inos; /* total valid ino # (== f_files - f_favail) */
__le64 epoch; /* base seconds used for compact inodes */
__le32 fixed_nsec; /* fixed nanoseconds for compact inodes */
@@ -148,7 +148,7 @@ union erofs_inode_i_nb {
__le16 nlink; /* if EROFS_I_NLINK_1_BIT is unset */
__le16 blocks_hi; /* total blocks count MSB */
__le16 startblk_hi; /* starting block number MSB */
-};
+} __packed;
/* 32-byte reduced form of an ondisk inode */
struct erofs_inode_compact {
@@ -369,9 +369,9 @@ struct z_erofs_map_header {
* bit 7 : pack the whole file into packed inode
*/
__u8 h_clusterbits;
- };
+ } __packed;
__le16 h_extents_hi; /* extent count MSB */
- };
+ } __packed;
};
enum {
diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c
index bec4b56..60c7cc4 100644
--- a/fs/erofs/fileio.c
+++ b/fs/erofs/fileio.c
@@ -32,6 +32,8 @@ static void erofs_fileio_ki_complete(struct kiocb *iocb, long ret)
ret = 0;
}
if (rq->bio.bi_end_io) {
+ if (ret < 0 && !rq->bio.bi_status)
+ rq->bio.bi_status = errno_to_blk_status(ret);
rq->bio.bi_end_io(&rq->bio);
} else {
bio_for_each_folio_all(fi, &rq->bio) {
@@ -148,10 +150,10 @@ static int erofs_fileio_scan_folio(struct erofs_fileio *io, struct folio *folio)
io->rq->bio.bi_iter.bi_sector = io->dev.m_pa >> 9;
attached = 0;
}
- if (!attached++)
- erofs_onlinefolio_split(folio);
if (!bio_add_folio(&io->rq->bio, folio, len, cur))
goto io_retry;
+ if (!attached++)
+ erofs_onlinefolio_split(folio);
io->dev.m_pa += len;
}
cur += len;
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index cadec6b..da6ee7c 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -357,7 +357,6 @@ static void erofs_default_options(struct erofs_sb_info *sbi)
enum {
Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum,
Opt_device, Opt_fsid, Opt_domain_id, Opt_directio,
- Opt_err
};
static const struct constant_table erofs_param_cache_strategy[] = {
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 0671184d..5c061aa 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -725,7 +725,6 @@ static int z_erofs_register_pcluster(struct z_erofs_frontend *fe)
lockref_init(&pcl->lockref); /* one ref for this request */
pcl->algorithmformat = map->m_algorithmformat;
pcl->pclustersize = map->m_plen;
- pcl->pageofs_in = pageofs_in;
pcl->length = 0;
pcl->partial = true;
pcl->next = fe->head;
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 8de50df..14ea47f 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -559,7 +559,8 @@ static int z_erofs_map_blocks_ext(struct inode *inode,
pos += sizeof(__le64);
lstart = 0;
} else {
- lstart = map->m_la >> vi->z_lclusterbits;
+ lstart = round_down(map->m_la, 1 << vi->z_lclusterbits);
+ pos += (lstart >> vi->z_lclusterbits) * recsz;
pa = EROFS_NULL_ADDR;
}
@@ -614,7 +615,7 @@ static int z_erofs_map_blocks_ext(struct inode *inode,
if (last && (vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER)) {
map->m_flags |= EROFS_MAP_MAPPED | EROFS_MAP_FRAGMENT;
vi->z_fragmentoff = map->m_plen;
- if (recsz >= offsetof(struct z_erofs_extent, pstart_lo))
+ if (recsz > offsetof(struct z_erofs_extent, pstart_lo))
vi->z_fragmentoff |= map->m_pa << 32;
} else if (map->m_plen) {
map->m_flags |= EROFS_MAP_MAPPED |
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 1003768..4bc264b 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1996,6 +1996,14 @@ static int ep_try_send_events(struct eventpoll *ep,
return res;
}
+static int ep_schedule_timeout(ktime_t *to)
+{
+ if (to)
+ return ktime_after(*to, ktime_get());
+ else
+ return 1;
+}
+
/**
* ep_poll - Retrieves ready events, and delivers them to the caller-supplied
* event buffer.
@@ -2103,7 +2111,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
write_unlock_irq(&ep->lock);
- if (!eavail)
+ if (!eavail && ep_schedule_timeout(to))
timed_out = !schedule_hrtimeout_range(to, slack,
HRTIMER_MODE_ABS);
__set_current_state(TASK_RUNNING);
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 87ee3a1..e8c5525 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -351,10 +351,9 @@ int ext4_check_blockref(const char *function, unsigned int line,
{
__le32 *bref = p;
unsigned int blk;
+ journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
- if (ext4_has_feature_journal(inode->i_sb) &&
- (inode->i_ino ==
- le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum)))
+ if (journal && inode == journal->j_inode)
return 0;
while (bref < p+max) {
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 38bc8d7..e7ecc7c 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -691,7 +691,8 @@ static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino)
if (!bh || !buffer_uptodate(bh))
/*
* If the block is not in the buffer cache, then it
- * must have been written out.
+ * must have been written out, or, most unlikely, is
+ * being migrated - false failure should be OK here.
*/
goto out;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 1dc09ed..94c7d2d8 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -386,10 +386,11 @@ static int __check_block_validity(struct inode *inode, const char *func,
unsigned int line,
struct ext4_map_blocks *map)
{
- if (ext4_has_feature_journal(inode->i_sb) &&
- (inode->i_ino ==
- le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum)))
+ journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
+
+ if (journal && inode == journal->j_inode)
return 0;
+
if (!ext4_inode_block_valid(inode, map->m_pblk, map->m_len)) {
ext4_error_inode(inode, func, line, map->m_pblk,
"lblock %lu mapped to illegal pblock %llu "
@@ -4724,22 +4725,43 @@ static inline void ext4_inode_set_iversion_queried(struct inode *inode, u64 val)
inode_set_iversion_queried(inode, val);
}
-static const char *check_igot_inode(struct inode *inode, ext4_iget_flags flags)
-
+static int check_igot_inode(struct inode *inode, ext4_iget_flags flags,
+ const char *function, unsigned int line)
{
+ const char *err_str;
+
if (flags & EXT4_IGET_EA_INODE) {
- if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
- return "missing EA_INODE flag";
+ if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) {
+ err_str = "missing EA_INODE flag";
+ goto error;
+ }
if (ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
- EXT4_I(inode)->i_file_acl)
- return "ea_inode with extended attributes";
+ EXT4_I(inode)->i_file_acl) {
+ err_str = "ea_inode with extended attributes";
+ goto error;
+ }
} else {
- if ((EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
- return "unexpected EA_INODE flag";
+ if ((EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) {
+ /*
+ * open_by_handle_at() could provide an old inode number
+ * that has since been reused for an ea_inode; this does
+ * not indicate filesystem corruption
+ */
+ if (flags & EXT4_IGET_HANDLE)
+ return -ESTALE;
+ err_str = "unexpected EA_INODE flag";
+ goto error;
+ }
}
- if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD))
- return "unexpected bad inode w/o EXT4_IGET_BAD";
- return NULL;
+ if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD)) {
+ err_str = "unexpected bad inode w/o EXT4_IGET_BAD";
+ goto error;
+ }
+ return 0;
+
+error:
+ ext4_error_inode(inode, function, line, 0, err_str);
+ return -EFSCORRUPTED;
}
struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
@@ -4751,7 +4773,6 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
struct ext4_inode_info *ei;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
struct inode *inode;
- const char *err_str;
journal_t *journal = EXT4_SB(sb)->s_journal;
long ret;
loff_t size;
@@ -4780,10 +4801,10 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
if (!inode)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW)) {
- if ((err_str = check_igot_inode(inode, flags)) != NULL) {
- ext4_error_inode(inode, function, line, 0, err_str);
+ ret = check_igot_inode(inode, flags, function, line);
+ if (ret) {
iput(inode);
- return ERR_PTR(-EFSCORRUPTED);
+ return ERR_PTR(ret);
}
return inode;
}
@@ -5065,13 +5086,21 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
ret = -EFSCORRUPTED;
goto bad_inode;
}
- if ((err_str = check_igot_inode(inode, flags)) != NULL) {
- ext4_error_inode(inode, function, line, 0, err_str);
- ret = -EFSCORRUPTED;
- goto bad_inode;
+ ret = check_igot_inode(inode, flags, function, line);
+ /*
+ * -ESTALE here means there is nothing inherently wrong with the inode,
+ * it's just not an inode we can return for an fhandle lookup.
+ */
+ if (ret == -ESTALE) {
+ brelse(iloc.bh);
+ unlock_new_inode(inode);
+ iput(inode);
+ return ERR_PTR(-ESTALE);
}
-
+ if (ret)
+ goto bad_inode;
brelse(iloc.bh);
+
unlock_new_inode(inode);
return inode;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 0d523e9..1e98c5b 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3037,10 +3037,8 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
unsigned char blocksize_bits = min_t(unsigned char,
sb->s_blocksize_bits,
EXT4_MAX_BLOCK_LOG_SIZE);
- struct sg {
- struct ext4_group_info info;
- ext4_grpblk_t counters[EXT4_MAX_BLOCK_LOG_SIZE + 2];
- } sg;
+ DEFINE_RAW_FLEX(struct ext4_group_info, sg, bb_counters,
+ EXT4_MAX_BLOCK_LOG_SIZE + 2);
group--;
if (group == 0)
@@ -3048,7 +3046,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
" 2^0 2^1 2^2 2^3 2^4 2^5 2^6 "
" 2^7 2^8 2^9 2^10 2^11 2^12 2^13 ]\n");
- i = (blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) +
+ i = (blocksize_bits + 2) * sizeof(sg->bb_counters[0]) +
sizeof(struct ext4_group_info);
grinfo = ext4_get_group_info(sb, group);
@@ -3068,14 +3066,14 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
* We care only about free space counters in the group info and
* these are safe to access even after the buddy has been unloaded
*/
- memcpy(&sg, grinfo, i);
- seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free,
- sg.info.bb_fragments, sg.info.bb_first_free);
+ memcpy(sg, grinfo, i);
+ seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg->bb_free,
+ sg->bb_fragments, sg->bb_first_free);
for (i = 0; i <= 13; i++)
seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ?
- sg.info.bb_counters[i] : 0);
+ sg->bb_counters[i] : 0);
seq_puts(seq, " ]");
- if (EXT4_MB_GRP_BBITMAP_CORRUPT(&sg.info))
+ if (EXT4_MB_GRP_BBITMAP_CORRUPT(sg))
seq_puts(seq, " Block bitmap corrupted!");
seq_putc(seq, '\n');
return 0;
@@ -6644,7 +6642,8 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
for (i = 0; i < count; i++) {
cond_resched();
if (is_metadata)
- bh = sb_find_get_block(inode->i_sb, block + i);
+ bh = sb_find_get_block_nonatomic(inode->i_sb,
+ block + i);
ext4_forget(handle, is_metadata, inode, bh, block + i);
}
}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index cb5cb33..e9712e6 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1971,7 +1971,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
* split it in half by count; each resulting block will have at least
* half the space free.
*/
- if (i > 0)
+ if (i >= 0)
split = count - move;
else
split = count/2;
diff --git a/fs/file.c b/fs/file.c
index dc3f7e1..3a31466 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -26,7 +26,7 @@
#include "internal.h"
-bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt)
+static noinline bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt)
{
/*
* If the reference count was already in the dead zone, then this
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 2c7b24c..53c2626 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -1669,6 +1669,9 @@ static int virtio_fs_get_tree(struct fs_context *fsc)
unsigned int virtqueue_size;
int err = -EIO;
+ if (!fsc->source)
+ return invalf(fsc, "No source specified");
+
/* This gets a reference on virtio_fs object. This ptr gets installed
* in fc->iq->priv. Once fuse_conn is going away, it calls ->put()
* to drop the reference to this object.
diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig
index be7f87a..7bd231d1 100644
--- a/fs/gfs2/Kconfig
+++ b/fs/gfs2/Kconfig
@@ -4,7 +4,6 @@
select BUFFER_HEAD
select FS_POSIX_ACL
select CRC32
- select LIBCRC32C
select QUOTACTL
select FS_IOMAP
help
diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c
index 6add6eb..cb823a8 100644
--- a/fs/hfs/bnode.c
+++ b/fs/hfs/bnode.c
@@ -67,6 +67,12 @@ void hfs_bnode_read_key(struct hfs_bnode *node, void *key, int off)
else
key_len = tree->max_key_len + 1;
+ if (key_len > sizeof(hfs_btree_key) || key_len < 1) {
+ memset(key, 0, sizeof(hfs_btree_key));
+ pr_err("hfs: Invalid key length: %d\n", key_len);
+ return;
+ }
+
hfs_bnode_read(node, key, off, key_len);
}
diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c
index 87974d5..079ea80 100644
--- a/fs/hfsplus/bnode.c
+++ b/fs/hfsplus/bnode.c
@@ -67,6 +67,12 @@ void hfs_bnode_read_key(struct hfs_bnode *node, void *key, int off)
else
key_len = tree->max_key_len + 2;
+ if (key_len > sizeof(hfsplus_btree_key) || key_len < 1) {
+ memset(key, 0, sizeof(hfsplus_btree_key));
+ pr_err("hfsplus: Invalid key length: %d\n", key_len);
+ return;
+ }
+
hfs_bnode_read(node, key, off, key_len);
}
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 3155337..5b08bd41 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -259,7 +259,7 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio,
}
/* truncate len if we find any trailing uptodate block(s) */
- for ( ; i <= last; i++) {
+ while (++i <= last) {
if (ifs_block_is_uptodate(ifs, i)) {
plen -= (last - i + 1) * block_size;
last = i - 1;
diff --git a/fs/isofs/export.c b/fs/isofs/export.c
index 35768a6..421d247 100644
--- a/fs/isofs/export.c
+++ b/fs/isofs/export.c
@@ -180,7 +180,7 @@ static struct dentry *isofs_fh_to_parent(struct super_block *sb,
return NULL;
return isofs_export_iget(sb,
- fh_len > 2 ? ifid->parent_block : 0,
+ fh_len > 3 ? ifid->parent_block : 0,
ifid->parent_offset,
fh_len > 4 ? ifid->parent_generation : 0);
}
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index 0cf0fddb..1467f67 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -345,7 +345,8 @@ int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr,
bh = bh_in;
if (!bh) {
- bh = __find_get_block(bdev, blocknr, journal->j_blocksize);
+ bh = __find_get_block_nonatomic(bdev, blocknr,
+ journal->j_blocksize);
if (bh)
BUFFER_TRACE(bh, "found on hash");
}
@@ -355,7 +356,8 @@ int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr,
/* If there is a different buffer_head lying around in
* memory anywhere... */
- bh2 = __find_get_block(bdev, blocknr, journal->j_blocksize);
+ bh2 = __find_get_block_nonatomic(bdev, blocknr,
+ journal->j_blocksize);
if (bh2) {
/* ... and it has RevokeValid status... */
if (bh2 != bh && buffer_revokevalid(bh2))
@@ -464,7 +466,8 @@ void jbd2_journal_cancel_revoke(handle_t *handle, struct journal_head *jh)
* state machine will get very upset later on. */
if (need_cancel) {
struct buffer_head *bh2;
- bh2 = __find_get_block(bh->b_bdev, bh->b_blocknr, bh->b_size);
+ bh2 = __find_get_block_nonatomic(bh->b_bdev, bh->b_blocknr,
+ bh->b_size);
if (bh2) {
if (bh2 != bh)
clear_buffer_revoked(bh2);
@@ -492,9 +495,9 @@ void jbd2_clear_buffer_revoked_flags(journal_t *journal)
struct jbd2_revoke_record_s *record;
struct buffer_head *bh;
record = (struct jbd2_revoke_record_s *)list_entry;
- bh = __find_get_block(journal->j_fs_dev,
- record->blocknr,
- journal->j_blocksize);
+ bh = __find_get_block_nonatomic(journal->j_fs_dev,
+ record->blocknr,
+ journal->j_blocksize);
if (bh) {
clear_buffer_revoked(bh);
__brelse(bh);
diff --git a/fs/namei.c b/fs/namei.c
index 360a86c..84a0e0b 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -125,9 +125,9 @@
#define EMBEDDED_NAME_MAX (PATH_MAX - offsetof(struct filename, iname))
-static inline void initname(struct filename *name)
+static inline void initname(struct filename *name, const char __user *uptr)
{
- name->uptr = NULL;
+ name->uptr = uptr;
name->aname = NULL;
atomic_set(&name->refcnt, 1);
}
@@ -210,7 +210,7 @@ getname_flags(const char __user *filename, int flags)
return ERR_PTR(-ENAMETOOLONG);
}
}
- initname(result);
+ initname(result, filename);
audit_getname(result);
return result;
}
@@ -268,7 +268,7 @@ struct filename *getname_kernel(const char * filename)
return ERR_PTR(-ENAMETOOLONG);
}
memcpy((char *)result->name, filename, len);
- initname(result);
+ initname(result, NULL);
audit_getname(result);
return result;
}
@@ -1665,27 +1665,20 @@ static struct dentry *lookup_dcache(const struct qstr *name,
return dentry;
}
-/*
- * Parent directory has inode locked exclusive. This is one
- * and only case when ->lookup() gets called on non in-lookup
- * dentries - as the matter of fact, this only gets called
- * when directory is guaranteed to have no in-lookup children
- * at all.
- * Will return -ENOENT if name isn't found and LOOKUP_CREATE wasn't passed.
- * Will return -EEXIST if name is found and LOOKUP_EXCL was passed.
- */
-struct dentry *lookup_one_qstr_excl(const struct qstr *name,
- struct dentry *base,
- unsigned int flags)
+static struct dentry *lookup_one_qstr_excl_raw(const struct qstr *name,
+ struct dentry *base,
+ unsigned int flags)
{
- struct dentry *dentry = lookup_dcache(name, base, flags);
+ struct dentry *dentry;
struct dentry *old;
- struct inode *dir = base->d_inode;
+ struct inode *dir;
+ dentry = lookup_dcache(name, base, flags);
if (dentry)
- goto found;
+ return dentry;
/* Don't create child dentry for a dead directory. */
+ dir = base->d_inode;
if (unlikely(IS_DEADDIR(dir)))
return ERR_PTR(-ENOENT);
@@ -1698,7 +1691,24 @@ struct dentry *lookup_one_qstr_excl(const struct qstr *name,
dput(dentry);
dentry = old;
}
-found:
+ return dentry;
+}
+
+/*
+ * Parent directory has inode locked exclusive. This is one
+ * and only case when ->lookup() gets called on non in-lookup
+ * dentries - as the matter of fact, this only gets called
+ * when directory is guaranteed to have no in-lookup children
+ * at all.
+ * Will return -ENOENT if name isn't found and LOOKUP_CREATE wasn't passed.
+ * Will return -EEXIST if name is found and LOOKUP_EXCL was passed.
+ */
+struct dentry *lookup_one_qstr_excl(const struct qstr *name,
+ struct dentry *base, unsigned int flags)
+{
+ struct dentry *dentry;
+
+ dentry = lookup_one_qstr_excl_raw(name, base, flags);
if (IS_ERR(dentry))
return dentry;
if (d_is_negative(dentry) && !(flags & LOOKUP_CREATE)) {
@@ -2742,23 +2752,48 @@ static int filename_parentat(int dfd, struct filename *name,
/* does lookup, returns the object with parent locked */
static struct dentry *__kern_path_locked(int dfd, struct filename *name, struct path *path)
{
+ struct path parent_path __free(path_put) = {};
struct dentry *d;
struct qstr last;
int type, error;
- error = filename_parentat(dfd, name, 0, path, &last, &type);
+ error = filename_parentat(dfd, name, 0, &parent_path, &last, &type);
if (error)
return ERR_PTR(error);
- if (unlikely(type != LAST_NORM)) {
- path_put(path);
+ if (unlikely(type != LAST_NORM))
return ERR_PTR(-EINVAL);
- }
- inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT);
- d = lookup_one_qstr_excl(&last, path->dentry, 0);
+ inode_lock_nested(parent_path.dentry->d_inode, I_MUTEX_PARENT);
+ d = lookup_one_qstr_excl(&last, parent_path.dentry, 0);
if (IS_ERR(d)) {
- inode_unlock(path->dentry->d_inode);
- path_put(path);
+ inode_unlock(parent_path.dentry->d_inode);
+ return d;
}
+ path->dentry = no_free_ptr(parent_path.dentry);
+ path->mnt = no_free_ptr(parent_path.mnt);
+ return d;
+}
+
+struct dentry *kern_path_locked_negative(const char *name, struct path *path)
+{
+ struct path parent_path __free(path_put) = {};
+ struct filename *filename __free(putname) = getname_kernel(name);
+ struct dentry *d;
+ struct qstr last;
+ int type, error;
+
+ error = filename_parentat(AT_FDCWD, filename, 0, &parent_path, &last, &type);
+ if (error)
+ return ERR_PTR(error);
+ if (unlikely(type != LAST_NORM))
+ return ERR_PTR(-EINVAL);
+ inode_lock_nested(parent_path.dentry->d_inode, I_MUTEX_PARENT);
+ d = lookup_one_qstr_excl_raw(&last, parent_path.dentry, 0);
+ if (IS_ERR(d)) {
+ inode_unlock(parent_path.dentry->d_inode);
+ return d;
+ }
+ path->dentry = no_free_ptr(parent_path.dentry);
+ path->mnt = no_free_ptr(parent_path.mnt);
return d;
}
diff --git a/fs/namespace.c b/fs/namespace.c
index 14935a0..04a9bb9 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -787,15 +787,11 @@ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq)
return 0;
mnt = real_mount(bastard);
mnt_add_count(mnt, 1);
- smp_mb(); // see mntput_no_expire()
+ smp_mb(); // see mntput_no_expire() and do_umount()
if (likely(!read_seqretry(&mount_lock, seq)))
return 0;
- if (bastard->mnt_flags & MNT_SYNC_UMOUNT) {
- mnt_add_count(mnt, -1);
- return 1;
- }
lock_mount_hash();
- if (unlikely(bastard->mnt_flags & MNT_DOOMED)) {
+ if (unlikely(bastard->mnt_flags & (MNT_SYNC_UMOUNT | MNT_DOOMED))) {
mnt_add_count(mnt, -1);
unlock_mount_hash();
return 1;
@@ -1830,6 +1826,8 @@ static inline void namespace_lock(void)
down_write(&namespace_sem);
}
+DEFINE_GUARD(namespace_lock, struct rw_semaphore *, namespace_lock(), namespace_unlock())
+
enum umount_tree_flags {
UMOUNT_SYNC = 1,
UMOUNT_PROPAGATE = 2,
@@ -2046,6 +2044,7 @@ static int do_umount(struct mount *mnt, int flags)
umount_tree(mnt, UMOUNT_PROPAGATE);
retval = 0;
} else {
+ smp_mb(); // paired with __legitimize_mnt()
shrink_submounts(mnt);
retval = -EBUSY;
if (!propagate_mount_busy(mnt, 2)) {
@@ -2383,7 +2382,7 @@ void dissolve_on_fput(struct vfsmount *mnt)
return;
}
- scoped_guard(rwsem_write, &namespace_sem) {
+ scoped_guard(namespace_lock, &namespace_sem) {
ns = m->mnt_ns;
if (!must_dissolve(ns))
return;
@@ -2824,56 +2823,62 @@ static struct mountpoint *do_lock_mount(struct path *path, bool beneath)
struct vfsmount *mnt = path->mnt;
struct dentry *dentry;
struct mountpoint *mp = ERR_PTR(-ENOENT);
+ struct path under = {};
for (;;) {
- struct mount *m;
+ struct mount *m = real_mount(mnt);
if (beneath) {
- m = real_mount(mnt);
+ path_put(&under);
read_seqlock_excl(&mount_lock);
- dentry = dget(m->mnt_mountpoint);
+ under.mnt = mntget(&m->mnt_parent->mnt);
+ under.dentry = dget(m->mnt_mountpoint);
read_sequnlock_excl(&mount_lock);
+ dentry = under.dentry;
} else {
dentry = path->dentry;
}
inode_lock(dentry->d_inode);
- if (unlikely(cant_mount(dentry))) {
- inode_unlock(dentry->d_inode);
- goto out;
- }
-
namespace_lock();
- if (beneath && (!is_mounted(mnt) || m->mnt_mountpoint != dentry)) {
+ if (unlikely(cant_mount(dentry) || !is_mounted(mnt)))
+ break; // not to be mounted on
+
+ if (beneath && unlikely(m->mnt_mountpoint != dentry ||
+ &m->mnt_parent->mnt != under.mnt)) {
namespace_unlock();
inode_unlock(dentry->d_inode);
- goto out;
+ continue; // got moved
}
mnt = lookup_mnt(path);
- if (likely(!mnt))
+ if (unlikely(mnt)) {
+ namespace_unlock();
+ inode_unlock(dentry->d_inode);
+ path_put(path);
+ path->mnt = mnt;
+ path->dentry = dget(mnt->mnt_root);
+ continue; // got overmounted
+ }
+ mp = get_mountpoint(dentry);
+ if (IS_ERR(mp))
break;
-
- namespace_unlock();
- inode_unlock(dentry->d_inode);
- if (beneath)
- dput(dentry);
- path_put(path);
- path->mnt = mnt;
- path->dentry = dget(mnt->mnt_root);
+ if (beneath) {
+ /*
+ * @under duplicates the references that will stay
+ * at least until namespace_unlock(), so the path_put()
+ * below is safe (and OK to do under namespace_lock -
+ * we are not dropping the final references here).
+ */
+ path_put(&under);
+ }
+ return mp;
}
-
- mp = get_mountpoint(dentry);
- if (IS_ERR(mp)) {
- namespace_unlock();
- inode_unlock(dentry->d_inode);
- }
-
-out:
+ namespace_unlock();
+ inode_unlock(dentry->d_inode);
if (beneath)
- dput(dentry);
-
+ path_put(&under);
return mp;
}
@@ -2884,14 +2889,11 @@ static inline struct mountpoint *lock_mount(struct path *path)
static void unlock_mount(struct mountpoint *where)
{
- struct dentry *dentry = where->m_dentry;
-
+ inode_unlock(where->m_dentry->d_inode);
read_seqlock_excl(&mount_lock);
put_mountpoint(where);
read_sequnlock_excl(&mount_lock);
-
namespace_unlock();
- inode_unlock(dentry->d_inode);
}
static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp)
@@ -3713,15 +3715,14 @@ static int do_move_mount(struct path *old_path,
if (err)
goto out;
- if (is_anon_ns(ns))
- ns->mntns_flags &= ~MNTNS_PROPAGATING;
-
/* if the mount is moved, it should no longer be expire
* automatically */
list_del_init(&old->mnt_expire);
if (attached)
put_mountpoint(old_mp);
out:
+ if (is_anon_ns(ns))
+ ns->mntns_flags &= ~MNTNS_PROPAGATING;
unlock_mount(mp);
if (!err) {
if (attached) {
@@ -5189,8 +5190,8 @@ static void finish_mount_kattr(struct mount_kattr *kattr)
mnt_idmap_put(kattr->mnt_idmap);
}
-static int copy_mount_setattr(struct mount_attr __user *uattr, size_t usize,
- struct mount_kattr *kattr)
+static int wants_mount_setattr(struct mount_attr __user *uattr, size_t usize,
+ struct mount_kattr *kattr)
{
int ret;
struct mount_attr attr;
@@ -5213,9 +5214,13 @@ static int copy_mount_setattr(struct mount_attr __user *uattr, size_t usize,
if (attr.attr_set == 0 &&
attr.attr_clr == 0 &&
attr.propagation == 0)
- return 0;
+ return 0; /* Tell caller to not bother. */
- return build_mount_kattr(&attr, usize, kattr);
+ ret = build_mount_kattr(&attr, usize, kattr);
+ if (ret < 0)
+ return ret;
+
+ return 1;
}
SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path,
@@ -5247,8 +5252,8 @@ SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path,
if (flags & AT_RECURSIVE)
kattr.kflags |= MOUNT_KATTR_RECURSE;
- err = copy_mount_setattr(uattr, usize, &kattr);
- if (err)
+ err = wants_mount_setattr(uattr, usize, &kattr);
+ if (err <= 0)
return err;
err = user_path_at(dfd, path, kattr.lookup_flags, &target);
@@ -5282,15 +5287,17 @@ SYSCALL_DEFINE5(open_tree_attr, int, dfd, const char __user *, filename,
if (flags & AT_RECURSIVE)
kattr.kflags |= MOUNT_KATTR_RECURSE;
- ret = copy_mount_setattr(uattr, usize, &kattr);
- if (ret)
+ ret = wants_mount_setattr(uattr, usize, &kattr);
+ if (ret < 0)
return ret;
- ret = do_mount_setattr(&file->f_path, &kattr);
- if (ret)
- return ret;
+ if (ret) {
+ ret = do_mount_setattr(&file->f_path, &kattr);
+ if (ret)
+ return ret;
- finish_mount_kattr(&kattr);
+ finish_mount_kattr(&kattr);
+ }
}
fd = get_unused_fd_flags(flags & O_CLOEXEC);
diff --git a/fs/netfs/fscache_cache.c b/fs/netfs/fscache_cache.c
index 9397ed3..8f70f8d 100644
--- a/fs/netfs/fscache_cache.c
+++ b/fs/netfs/fscache_cache.c
@@ -372,7 +372,7 @@ void fscache_withdraw_cache(struct fscache_cache *cache)
EXPORT_SYMBOL(fscache_withdraw_cache);
#ifdef CONFIG_PROC_FS
-static const char fscache_cache_states[NR__FSCACHE_CACHE_STATE] = "-PAEW";
+static const char fscache_cache_states[NR__FSCACHE_CACHE_STATE] __nonstring = "-PAEW";
/*
* Generate a list of caches in /proc/fs/fscache/caches
diff --git a/fs/netfs/fscache_cookie.c b/fs/netfs/fscache_cookie.c
index d4d4b3a..3d56fc7 100644
--- a/fs/netfs/fscache_cookie.c
+++ b/fs/netfs/fscache_cookie.c
@@ -29,7 +29,7 @@ static LIST_HEAD(fscache_cookie_lru);
static DEFINE_SPINLOCK(fscache_cookie_lru_lock);
DEFINE_TIMER(fscache_cookie_lru_timer, fscache_cookie_lru_timed_out);
static DECLARE_WORK(fscache_cookie_lru_work, fscache_cookie_lru_worker);
-static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] = "-LCAIFUWRD";
+static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] __nonstring = "-LCAIFUWRD";
static unsigned int fscache_lru_cookie_timeout = 10 * HZ;
void fscache_print_cookie(struct fscache_cookie *cookie, char prefix)
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index 4e3e620..70ecc8f 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -127,11 +127,13 @@ static int __init netfs_init(void)
if (mempool_init_slab_pool(&netfs_subrequest_pool, 100, netfs_subrequest_slab) < 0)
goto error_subreqpool;
+#ifdef CONFIG_PROC_FS
if (!proc_mkdir("fs/netfs", NULL))
goto error_proc;
if (!proc_create_seq("fs/netfs/requests", S_IFREG | 0444, NULL,
&netfs_requests_seq_ops))
goto error_procfile;
+#endif
#ifdef CONFIG_FSCACHE_STATS
if (!proc_create_single("fs/netfs/stats", S_IFREG | 0444, NULL,
netfs_stats_show))
@@ -144,9 +146,11 @@ static int __init netfs_init(void)
return 0;
error_fscache:
+#ifdef CONFIG_PROC_FS
error_procfile:
remove_proc_subtree("fs/netfs", NULL);
error_proc:
+#endif
mempool_exit(&netfs_subrequest_pool);
error_subreqpool:
kmem_cache_destroy(netfs_subrequest_slab);
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index d3f7610..07932ce 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -2,6 +2,7 @@
config NFS_FS
tristate "NFS client support"
depends on INET && FILE_LOCKING && MULTIUSER
+ select CRC32
select LOCKD
select SUNRPC
select NFS_COMMON
@@ -196,7 +197,6 @@
config NFS_DEBUG
bool
depends on NFS_FS && SUNRPC_DEBUG
- select CRC32
default y
config NFS_DISABLE_UDP_SUPPORT
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index ec8d32d..6655e5f 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -899,18 +899,11 @@ u64 nfs_timespec_to_change_attr(const struct timespec64 *ts)
return ((u64)ts->tv_sec << 30) + ts->tv_nsec;
}
-#ifdef CONFIG_CRC32
static inline u32 nfs_stateid_hash(const nfs4_stateid *stateid)
{
return ~crc32_le(0xFFFFFFFF, &stateid->other[0],
NFS4_STATEID_OTHER_SIZE);
}
-#else
-static inline u32 nfs_stateid_hash(nfs4_stateid *stateid)
-{
- return 0;
-}
-#endif
static inline bool nfs_current_task_exiting(void)
{
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index 351616c..f9c291e 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -148,16 +148,12 @@ static inline void nfs4_copy_sessionid(struct nfs4_sessionid *dst,
memcpy(dst->data, src->data, NFS4_MAX_SESSIONID_LEN);
}
-#ifdef CONFIG_CRC32
/*
* nfs_session_id_hash - calculate the crc32 hash for the session id
* @session - pointer to session
*/
#define nfs_session_id_hash(sess_id) \
(~crc32_le(0xFFFFFFFF, &(sess_id)->data[0], sizeof((sess_id)->data)))
-#else
-#define nfs_session_id_hash(session) (0)
-#endif
#else /* defined(CONFIG_NFS_V4_1) */
static inline int nfs4_init_session(struct nfs_client *clp)
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 792d3fe..731a88f 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -4,6 +4,7 @@
depends on INET
depends on FILE_LOCKING
depends on FSNOTIFY
+ select CRC32
select LOCKD
select SUNRPC
select EXPORTFS
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 2041268..59a693f2 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5430,7 +5430,7 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
queued = nfsd4_run_cb(&dp->dl_recall);
WARN_ON_ONCE(!queued);
if (!queued)
- nfs4_put_stid(&dp->dl_stid);
+ refcount_dec(&dp->dl_stid.sc_count);
}
/* Called from break_lease() with flc_lock held. */
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index 876152a..5103c2f 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -267,7 +267,6 @@ static inline bool fh_fsid_match(const struct knfsd_fh *fh1,
return true;
}
-#ifdef CONFIG_CRC32
/**
* knfsd_fh_hash - calculate the crc32 hash for the filehandle
* @fh - pointer to filehandle
@@ -279,12 +278,6 @@ static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh)
{
return ~crc32_le(0xFFFFFFFF, fh->fh_raw, fh->fh_size);
}
-#else
-static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh)
-{
- return 0;
-}
-#endif
/**
* fh_clear_pre_post_attrs - Reset pre/post attributes
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index f2d840a..87f861e 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1961,12 +1961,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
return -EINVAL;
if (mark_cmd == FAN_MARK_FLUSH) {
- if (mark_type == FAN_MARK_MOUNT)
- fsnotify_clear_vfsmount_marks_by_group(group);
- else if (mark_type == FAN_MARK_FILESYSTEM)
- fsnotify_clear_sb_marks_by_group(group);
- else
- fsnotify_clear_inode_marks_by_group(group);
+ fsnotify_clear_marks_by_group(group, obj_type);
return 0;
}
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index b8ac85b..821cb78 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -6918,6 +6918,7 @@ static int ocfs2_grab_folios(struct inode *inode, loff_t start, loff_t end,
if (IS_ERR(folios[numfolios])) {
ret = PTR_ERR(folios[numfolios]);
mlog_errno(ret);
+ folios[numfolios] = NULL;
goto out;
}
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index f1b4b3e..e5f58ff 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -174,7 +174,7 @@ int ocfs2_recovery_init(struct ocfs2_super *osb)
struct ocfs2_recovery_map *rm;
mutex_init(&osb->recovery_lock);
- osb->disable_recovery = 0;
+ osb->recovery_state = OCFS2_REC_ENABLED;
osb->recovery_thread_task = NULL;
init_waitqueue_head(&osb->recovery_event);
@@ -190,31 +190,53 @@ int ocfs2_recovery_init(struct ocfs2_super *osb)
return 0;
}
-/* we can't grab the goofy sem lock from inside wait_event, so we use
- * memory barriers to make sure that we'll see the null task before
- * being woken up */
static int ocfs2_recovery_thread_running(struct ocfs2_super *osb)
{
- mb();
return osb->recovery_thread_task != NULL;
}
+static void ocfs2_recovery_disable(struct ocfs2_super *osb,
+ enum ocfs2_recovery_state state)
+{
+ mutex_lock(&osb->recovery_lock);
+ /*
+ * If recovery thread is not running, we can directly transition to
+ * final state.
+ */
+ if (!ocfs2_recovery_thread_running(osb)) {
+ osb->recovery_state = state + 1;
+ goto out_lock;
+ }
+ osb->recovery_state = state;
+ /* Wait for recovery thread to acknowledge state transition */
+ wait_event_cmd(osb->recovery_event,
+ !ocfs2_recovery_thread_running(osb) ||
+ osb->recovery_state >= state + 1,
+ mutex_unlock(&osb->recovery_lock),
+ mutex_lock(&osb->recovery_lock));
+out_lock:
+ mutex_unlock(&osb->recovery_lock);
+
+ /*
+ * At this point we know that no more recovery work can be queued so
+ * wait for any recovery completion work to complete.
+ */
+ if (osb->ocfs2_wq)
+ flush_workqueue(osb->ocfs2_wq);
+}
+
+void ocfs2_recovery_disable_quota(struct ocfs2_super *osb)
+{
+ ocfs2_recovery_disable(osb, OCFS2_REC_QUOTA_WANT_DISABLE);
+}
+
void ocfs2_recovery_exit(struct ocfs2_super *osb)
{
struct ocfs2_recovery_map *rm;
/* disable any new recovery threads and wait for any currently
* running ones to exit. Do this before setting the vol_state. */
- mutex_lock(&osb->recovery_lock);
- osb->disable_recovery = 1;
- mutex_unlock(&osb->recovery_lock);
- wait_event(osb->recovery_event, !ocfs2_recovery_thread_running(osb));
-
- /* At this point, we know that no more recovery threads can be
- * launched, so wait for any recovery completion work to
- * complete. */
- if (osb->ocfs2_wq)
- flush_workqueue(osb->ocfs2_wq);
+ ocfs2_recovery_disable(osb, OCFS2_REC_WANT_DISABLE);
/*
* Now that recovery is shut down, and the osb is about to be
@@ -1249,7 +1271,7 @@ static int ocfs2_force_read_journal(struct inode *inode)
}
for (i = 0; i < p_blocks; i++, p_blkno++) {
- bh = __find_get_block(osb->sb->s_bdev, p_blkno,
+ bh = __find_get_block_nonatomic(osb->sb->s_bdev, p_blkno,
osb->sb->s_blocksize);
/* block not cached. */
if (!bh)
@@ -1472,6 +1494,18 @@ static int __ocfs2_recovery_thread(void *arg)
}
}
restart:
+ if (quota_enabled) {
+ mutex_lock(&osb->recovery_lock);
+ /* Confirm that recovery thread will no longer recover quotas */
+ if (osb->recovery_state == OCFS2_REC_QUOTA_WANT_DISABLE) {
+ osb->recovery_state = OCFS2_REC_QUOTA_DISABLED;
+ wake_up(&osb->recovery_event);
+ }
+ if (osb->recovery_state >= OCFS2_REC_QUOTA_DISABLED)
+ quota_enabled = 0;
+ mutex_unlock(&osb->recovery_lock);
+ }
+
status = ocfs2_super_lock(osb, 1);
if (status < 0) {
mlog_errno(status);
@@ -1569,27 +1603,29 @@ static int __ocfs2_recovery_thread(void *arg)
ocfs2_free_replay_slots(osb);
osb->recovery_thread_task = NULL;
- mb(); /* sync with ocfs2_recovery_thread_running */
+ if (osb->recovery_state == OCFS2_REC_WANT_DISABLE)
+ osb->recovery_state = OCFS2_REC_DISABLED;
wake_up(&osb->recovery_event);
mutex_unlock(&osb->recovery_lock);
- if (quota_enabled)
- kfree(rm_quota);
+ kfree(rm_quota);
return status;
}
void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num)
{
+ int was_set = -1;
+
mutex_lock(&osb->recovery_lock);
+ if (osb->recovery_state < OCFS2_REC_WANT_DISABLE)
+ was_set = ocfs2_recovery_map_set(osb, node_num);
trace_ocfs2_recovery_thread(node_num, osb->node_num,
- osb->disable_recovery, osb->recovery_thread_task,
- osb->disable_recovery ?
- -1 : ocfs2_recovery_map_set(osb, node_num));
+ osb->recovery_state, osb->recovery_thread_task, was_set);
- if (osb->disable_recovery)
+ if (osb->recovery_state >= OCFS2_REC_WANT_DISABLE)
goto out;
if (osb->recovery_thread_task)
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index e3c3a35..6397170 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -148,6 +148,7 @@ void ocfs2_wait_for_recovery(struct ocfs2_super *osb);
int ocfs2_recovery_init(struct ocfs2_super *osb);
void ocfs2_recovery_exit(struct ocfs2_super *osb);
+void ocfs2_recovery_disable_quota(struct ocfs2_super *osb);
int ocfs2_compute_replay_slots(struct ocfs2_super *osb);
void ocfs2_free_replay_slots(struct ocfs2_super *osb);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 51c5276..6aaa94c 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -308,6 +308,21 @@ enum ocfs2_journal_trigger_type {
void ocfs2_initialize_journal_triggers(struct super_block *sb,
struct ocfs2_triggers triggers[]);
+enum ocfs2_recovery_state {
+ OCFS2_REC_ENABLED = 0,
+ OCFS2_REC_QUOTA_WANT_DISABLE,
+ /*
+ * Must be OCFS2_REC_QUOTA_WANT_DISABLE + 1 for
+ * ocfs2_recovery_disable_quota() to work.
+ */
+ OCFS2_REC_QUOTA_DISABLED,
+ OCFS2_REC_WANT_DISABLE,
+ /*
+ * Must be OCFS2_REC_WANT_DISABLE + 1 for ocfs2_recovery_exit() to work
+ */
+ OCFS2_REC_DISABLED,
+};
+
struct ocfs2_journal;
struct ocfs2_slot_info;
struct ocfs2_recovery_map;
@@ -370,7 +385,7 @@ struct ocfs2_super
struct ocfs2_recovery_map *recovery_map;
struct ocfs2_replay_map *replay_map;
struct task_struct *recovery_thread_task;
- int disable_recovery;
+ enum ocfs2_recovery_state recovery_state;
wait_queue_head_t checkpoint_event;
struct ocfs2_journal *journal;
unsigned long osb_commit_interval;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 2956d88..e272429 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -453,8 +453,7 @@ struct ocfs2_quota_recovery *ocfs2_begin_quota_recovery(
/* Sync changes in local quota file into global quota file and
* reinitialize local quota file.
- * The function expects local quota file to be already locked and
- * s_umount locked in shared mode. */
+ * The function expects local quota file to be already locked. */
static int ocfs2_recover_local_quota_file(struct inode *lqinode,
int type,
struct ocfs2_quota_recovery *rec)
@@ -588,7 +587,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
{
unsigned int ino[OCFS2_MAXQUOTAS] = { LOCAL_USER_QUOTA_SYSTEM_INODE,
LOCAL_GROUP_QUOTA_SYSTEM_INODE };
- struct super_block *sb = osb->sb;
struct ocfs2_local_disk_dqinfo *ldinfo;
struct buffer_head *bh;
handle_t *handle;
@@ -600,7 +598,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
printk(KERN_NOTICE "ocfs2: Finishing quota recovery on device (%s) for "
"slot %u\n", osb->dev_str, slot_num);
- down_read(&sb->s_umount);
for (type = 0; type < OCFS2_MAXQUOTAS; type++) {
if (list_empty(&(rec->r_list[type])))
continue;
@@ -677,7 +674,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
break;
}
out:
- up_read(&sb->s_umount);
kfree(rec);
return status;
}
@@ -843,8 +839,7 @@ static int ocfs2_local_free_info(struct super_block *sb, int type)
ocfs2_release_local_quota_bitmaps(&oinfo->dqi_chunk);
/*
- * s_umount held in exclusive mode protects us against racing with
- * recovery thread...
+ * ocfs2_dismount_volume() has already aborted quota recovery...
*/
if (oinfo->dqi_rec) {
ocfs2_free_quota_recovery(oinfo->dqi_rec);
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index f7b483f..6ac4dcd 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -698,10 +698,12 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
bg_bh = ocfs2_block_group_alloc_contig(osb, handle, alloc_inode,
ac, cl);
- if (PTR_ERR(bg_bh) == -ENOSPC)
+ if (PTR_ERR(bg_bh) == -ENOSPC) {
+ ac->ac_which = OCFS2_AC_USE_MAIN_DISCONTIG;
bg_bh = ocfs2_block_group_alloc_discontig(handle,
alloc_inode,
ac, cl);
+ }
if (IS_ERR(bg_bh)) {
status = PTR_ERR(bg_bh);
bg_bh = NULL;
@@ -1794,6 +1796,7 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
{
int status;
u16 chain;
+ u32 contig_bits;
u64 next_group;
struct inode *alloc_inode = ac->ac_inode;
struct buffer_head *group_bh = NULL;
@@ -1819,10 +1822,21 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
status = -ENOSPC;
/* for now, the chain search is a bit simplistic. We just use
* the 1st group with any empty bits. */
- while ((status = ac->ac_group_search(alloc_inode, group_bh,
- bits_wanted, min_bits,
- ac->ac_max_block,
- res)) == -ENOSPC) {
+ while (1) {
+ if (ac->ac_which == OCFS2_AC_USE_MAIN_DISCONTIG) {
+ contig_bits = le16_to_cpu(bg->bg_contig_free_bits);
+ if (!contig_bits)
+ contig_bits = ocfs2_find_max_contig_free_bits(bg->bg_bitmap,
+ le16_to_cpu(bg->bg_bits), 0);
+ if (bits_wanted > contig_bits && contig_bits >= min_bits)
+ bits_wanted = contig_bits;
+ }
+
+ status = ac->ac_group_search(alloc_inode, group_bh,
+ bits_wanted, min_bits,
+ ac->ac_max_block, res);
+ if (status != -ENOSPC)
+ break;
if (!bg->bg_next_group)
break;
@@ -1982,6 +1996,7 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
victim = ocfs2_find_victim_chain(cl);
ac->ac_chain = victim;
+search:
status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits,
res, &bits_left);
if (!status) {
@@ -2022,6 +2037,16 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
}
}
+ /* Chains can't supply the bits_wanted contiguous space.
+ * We should switch to using every single bit when allocating
+ * from the global bitmap. */
+ if (i == le16_to_cpu(cl->cl_next_free_rec) &&
+ status == -ENOSPC && ac->ac_which == OCFS2_AC_USE_MAIN) {
+ ac->ac_which = OCFS2_AC_USE_MAIN_DISCONTIG;
+ ac->ac_chain = victim;
+ goto search;
+ }
+
set_hint:
if (status != -ENOSPC) {
/* If the next search of this group is not likely to
@@ -2365,7 +2390,8 @@ int __ocfs2_claim_clusters(handle_t *handle,
BUG_ON(ac->ac_bits_given >= ac->ac_bits_wanted);
BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL
- && ac->ac_which != OCFS2_AC_USE_MAIN);
+ && ac->ac_which != OCFS2_AC_USE_MAIN
+ && ac->ac_which != OCFS2_AC_USE_MAIN_DISCONTIG);
if (ac->ac_which == OCFS2_AC_USE_LOCAL) {
WARN_ON(min_clusters > 1);
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index b481b83..bcf2ed4 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -29,6 +29,7 @@ struct ocfs2_alloc_context {
#define OCFS2_AC_USE_MAIN 2
#define OCFS2_AC_USE_INODE 3
#define OCFS2_AC_USE_META 4
+#define OCFS2_AC_USE_MAIN_DISCONTIG 5
u32 ac_which;
/* these are used by the chain search */
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 8bb5022..3d25339 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1812,6 +1812,9 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
/* Orphan scan should be stopped as early as possible */
ocfs2_orphan_scan_stop(osb);
+ /* Stop quota recovery so that we can disable quotas */
+ ocfs2_recovery_disable_quota(osb);
+
ocfs2_disable_quotas(osb);
/* All dquots should be freed by now */
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 969b4581..dfea7bd 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -48,8 +48,8 @@ static struct file *ovl_open_realfile(const struct file *file,
if (!inode_owner_or_capable(real_idmap, realinode))
flags &= ~O_NOATIME;
- realfile = backing_file_open(&file->f_path, flags, realpath,
- current_cred());
+ realfile = backing_file_open(file_user_path((struct file *) file),
+ flags, realpath, current_cred());
}
ovl_revert_creds(old_cred);
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 6f2f8f4..aef942a 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -541,8 +541,6 @@ int ovl_set_metacopy_xattr(struct ovl_fs *ofs, struct dentry *d,
bool ovl_is_metacopy_dentry(struct dentry *dentry);
char *ovl_get_redirect_xattr(struct ovl_fs *ofs, const struct path *path, int padding);
int ovl_ensure_verity_loaded(struct path *path);
-int ovl_get_verity_xattr(struct ovl_fs *ofs, const struct path *path,
- u8 *digest_buf, int *buf_length);
int ovl_validate_verity(struct ovl_fs *ofs,
struct path *metapath,
struct path *datapath);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index b63474d..e19940d 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1138,6 +1138,11 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb,
return ERR_PTR(-EINVAL);
}
+ if (ctx->nr == ctx->nr_data) {
+ pr_err("at least one non-data lowerdir is required\n");
+ return ERR_PTR(-EINVAL);
+ }
+
err = -EINVAL;
for (i = 0; i < ctx->nr; i++) {
l = &ctx->lower[i];
diff --git a/fs/smb/client/cifsencrypt.c b/fs/smb/client/cifsencrypt.c
index e69968e..35892df 100644
--- a/fs/smb/client/cifsencrypt.c
+++ b/fs/smb/client/cifsencrypt.c
@@ -704,18 +704,12 @@ cifs_crypto_secmech_release(struct TCP_Server_Info *server)
cifs_free_hash(&server->secmech.md5);
cifs_free_hash(&server->secmech.sha512);
- if (!SERVER_IS_CHAN(server)) {
- if (server->secmech.enc) {
- crypto_free_aead(server->secmech.enc);
- server->secmech.enc = NULL;
- }
-
- if (server->secmech.dec) {
- crypto_free_aead(server->secmech.dec);
- server->secmech.dec = NULL;
- }
- } else {
+ if (server->secmech.enc) {
+ crypto_free_aead(server->secmech.enc);
server->secmech.enc = NULL;
+ }
+ if (server->secmech.dec) {
+ crypto_free_aead(server->secmech.dec);
server->secmech.dec = NULL;
}
}
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 07c4688..3b32116 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -625,10 +625,8 @@ struct smb_version_operations {
bool (*is_status_io_timeout)(char *buf);
/* Check for STATUS_NETWORK_NAME_DELETED */
bool (*is_network_name_deleted)(char *buf, struct TCP_Server_Info *srv);
- int (*parse_reparse_point)(struct cifs_sb_info *cifs_sb,
- const char *full_path,
- struct kvec *rsp_iov,
- struct cifs_open_info_data *data);
+ struct reparse_data_buffer * (*get_reparse_point_buffer)(const struct kvec *rsp_iov,
+ u32 *plen);
int (*create_reparse_symlink)(const unsigned int xid,
struct inode *inode,
struct dentry *dentry,
diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h
index 48d0d6f..18d67ab 100644
--- a/fs/smb/client/cifspdu.h
+++ b/fs/smb/client/cifspdu.h
@@ -2256,6 +2256,8 @@ typedef struct {
#define FILE_SUPPORTS_ENCRYPTION 0x00020000
#define FILE_SUPPORTS_OBJECT_IDS 0x00010000
#define FILE_VOLUME_IS_COMPRESSED 0x00008000
+#define FILE_SUPPORTS_POSIX_UNLINK_RENAME 0x00000400
+#define FILE_RETURNS_CLEANUP_RESULT_INFO 0x00000200
#define FILE_SUPPORTS_REMOTE_STORAGE 0x00000100
#define FILE_SUPPORTS_REPARSE_POINTS 0x00000080
#define FILE_SUPPORTS_SPARSE_FILES 0x00000040
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index cfcc079..59f6fdf 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -163,6 +163,8 @@ extern int cifs_get_writable_path(struct cifs_tcon *tcon, const char *name,
extern struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *, bool);
extern int cifs_get_readable_path(struct cifs_tcon *tcon, const char *name,
struct cifsFileInfo **ret_file);
+extern int cifs_get_hardlink_path(struct cifs_tcon *tcon, struct inode *inode,
+ struct file *file);
extern unsigned int smbCalcSize(void *buf);
extern int decode_negTokenInit(unsigned char *security_blob, int length,
struct TCP_Server_Info *server);
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index f298e86..df976ce 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -300,7 +300,6 @@ cifs_abort_connection(struct TCP_Server_Info *server)
server->ssocket->flags);
sock_release(server->ssocket);
server->ssocket = NULL;
- put_net(cifs_net_ns(server));
}
server->sequence_number = 0;
server->session_estab = false;
@@ -1074,13 +1073,9 @@ clean_demultiplex_info(struct TCP_Server_Info *server)
msleep(125);
if (cifs_rdma_enabled(server))
smbd_destroy(server);
-
if (server->ssocket) {
sock_release(server->ssocket);
server->ssocket = NULL;
-
- /* Release netns reference for the socket. */
- put_net(cifs_net_ns(server));
}
if (!list_empty(&server->pending_mid_q)) {
@@ -1128,7 +1123,6 @@ clean_demultiplex_info(struct TCP_Server_Info *server)
*/
}
- /* Release netns reference for this server. */
put_net(cifs_net_ns(server));
kfree(server->leaf_fullpath);
kfree(server->hostname);
@@ -1774,8 +1768,6 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx,
tcp_ses->ops = ctx->ops;
tcp_ses->vals = ctx->vals;
-
- /* Grab netns reference for this server. */
cifs_set_net_ns(tcp_ses, get_net(current->nsproxy->net_ns));
tcp_ses->sign = ctx->sign;
@@ -1903,7 +1895,6 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx,
out_err_crypto_release:
cifs_crypto_secmech_release(tcp_ses);
- /* Release netns reference for this server. */
put_net(cifs_net_ns(tcp_ses));
out_err:
@@ -1912,10 +1903,8 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx,
cifs_put_tcp_session(tcp_ses->primary_server, false);
kfree(tcp_ses->hostname);
kfree(tcp_ses->leaf_fullpath);
- if (tcp_ses->ssocket) {
+ if (tcp_ses->ssocket)
sock_release(tcp_ses->ssocket);
- put_net(cifs_net_ns(tcp_ses));
- }
kfree(tcp_ses);
}
return ERR_PTR(rc);
@@ -2556,6 +2545,8 @@ static int match_tcon(struct cifs_tcon *tcon, struct smb3_fs_context *ctx)
return 0;
if (tcon->nodelete != ctx->nodelete)
return 0;
+ if (tcon->posix_extensions != ctx->linux_ext)
+ return 0;
return 1;
}
@@ -3357,24 +3348,20 @@ generic_ip_connect(struct TCP_Server_Info *server)
socket = server->ssocket;
} else {
struct net *net = cifs_net_ns(server);
+ struct sock *sk;
- rc = sock_create_kern(net, sfamily, SOCK_STREAM, IPPROTO_TCP, &server->ssocket);
+ rc = __sock_create(net, sfamily, SOCK_STREAM,
+ IPPROTO_TCP, &server->ssocket, 1);
if (rc < 0) {
cifs_server_dbg(VFS, "Error %d creating socket\n", rc);
return rc;
}
- /*
- * Grab netns reference for the socket.
- *
- * This reference will be released in several situations:
- * - In the failure path before the cifsd thread is started.
- * - In the all place where server->socket is released, it is
- * also set to NULL.
- * - Ultimately in clean_demultiplex_info(), during the final
- * teardown.
- */
- get_net(net);
+ sk = server->ssocket->sk;
+ __netns_tracker_free(net, &sk->ns_tracker, false);
+ sk->sk_net_refcnt = 1;
+ get_net_track(net, &sk->ns_tracker, GFP_KERNEL);
+ sock_inuse_add(net, 1);
/* BB other socket options to set KEEPALIVE, NODELAY? */
cifs_dbg(FYI, "Socket created\n");
@@ -3426,7 +3413,6 @@ generic_ip_connect(struct TCP_Server_Info *server)
if (rc < 0) {
cifs_dbg(FYI, "Error %d connecting to server\n", rc);
trace_smb3_connect_err(server->hostname, server->conn_id, &server->dstaddr, rc);
- put_net(cifs_net_ns(server));
sock_release(socket);
server->ssocket = NULL;
return rc;
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 8407fb1..9e8f404 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -1007,6 +1007,11 @@ int cifs_open(struct inode *inode, struct file *file)
} else {
_cifsFileInfo_put(cfile, true, false);
}
+ } else {
+ /* hard link on the defeered close file */
+ rc = cifs_get_hardlink_path(tcon, inode, file);
+ if (rc)
+ cifs_close_deferred_file(CIFS_I(inode));
}
if (server->oplocks)
@@ -2071,6 +2076,29 @@ cifs_move_llist(struct list_head *source, struct list_head *dest)
list_move(li, dest);
}
+int
+cifs_get_hardlink_path(struct cifs_tcon *tcon, struct inode *inode,
+ struct file *file)
+{
+ struct cifsFileInfo *open_file = NULL;
+ struct cifsInodeInfo *cinode = CIFS_I(inode);
+ int rc = 0;
+
+ spin_lock(&tcon->open_file_lock);
+ spin_lock(&cinode->open_file_lock);
+
+ list_for_each_entry(open_file, &cinode->openFileList, flist) {
+ if (file->f_flags == open_file->f_flags) {
+ rc = -EINVAL;
+ break;
+ }
+ }
+
+ spin_unlock(&cinode->open_file_lock);
+ spin_unlock(&tcon->open_file_lock);
+ return rc;
+}
+
void
cifs_free_llist(struct list_head *llist)
{
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index a00a9d9..75be4b4 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -1203,18 +1203,17 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data,
goto out;
}
break;
- case IO_REPARSE_TAG_MOUNT_POINT:
- cifs_create_junction_fattr(fattr, sb);
- rc = 0;
- goto out;
default:
/* Check for cached reparse point data */
if (data->symlink_target || data->reparse.buf) {
rc = 0;
- } else if (iov && server->ops->parse_reparse_point) {
- rc = server->ops->parse_reparse_point(cifs_sb,
- full_path,
- iov, data);
+ } else if (iov && server->ops->get_reparse_point_buffer) {
+ struct reparse_data_buffer *reparse_buf;
+ u32 reparse_len;
+
+ reparse_buf = server->ops->get_reparse_point_buffer(iov, &reparse_len);
+ rc = parse_reparse_point(reparse_buf, reparse_len,
+ cifs_sb, full_path, data);
/*
* If the reparse point was not handled but it is the
* name surrogate which points to directory, then treat
@@ -1228,6 +1227,16 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data,
cifs_create_junction_fattr(fattr, sb);
goto out;
}
+ /*
+ * If the reparse point is unsupported by the Linux SMB
+ * client then let it process by the SMB server. So mask
+ * the -EOPNOTSUPP error code. This will allow Linux SMB
+ * client to send SMB OPEN request to server. If server
+ * does not support this reparse point too then server
+ * will return error during open the path.
+ */
+ if (rc == -EOPNOTSUPP)
+ rc = 0;
}
if (data->reparse.tag == IO_REPARSE_TAG_SYMLINK && !rc) {
diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c
index 2b9e988..bb25e77 100644
--- a/fs/smb/client/reparse.c
+++ b/fs/smb/client/reparse.c
@@ -542,12 +542,12 @@ static int wsl_set_reparse_buf(struct reparse_data_buffer **buf,
kfree(symname_utf16);
return -ENOMEM;
}
- /* Flag 0x02000000 is unknown, but all wsl symlinks have this value */
- symlink_buf->Flags = cpu_to_le32(0x02000000);
- /* PathBuffer is in UTF-8 but without trailing null-term byte */
+ /* Version field must be set to 2 (MS-FSCC 2.1.2.7) */
+ symlink_buf->Version = cpu_to_le32(2);
+ /* Target for Version 2 is in UTF-8 but without trailing null-term byte */
symname_utf8_len = utf16s_to_utf8s((wchar_t *)symname_utf16, symname_utf16_len/2,
UTF16_LITTLE_ENDIAN,
- symlink_buf->PathBuffer,
+ symlink_buf->Target,
symname_utf8_maxlen);
*buf = (struct reparse_data_buffer *)symlink_buf;
buf_len = sizeof(struct reparse_wsl_symlink_data_buffer) + symname_utf8_len;
@@ -1016,29 +1016,36 @@ static int parse_reparse_wsl_symlink(struct reparse_wsl_symlink_data_buffer *buf
struct cifs_open_info_data *data)
{
int len = le16_to_cpu(buf->ReparseDataLength);
+ int data_offset = offsetof(typeof(*buf), Target) - offsetof(typeof(*buf), Version);
int symname_utf8_len;
__le16 *symname_utf16;
int symname_utf16_len;
- if (len <= sizeof(buf->Flags)) {
+ if (len <= data_offset) {
cifs_dbg(VFS, "srv returned malformed wsl symlink buffer\n");
return -EIO;
}
- /* PathBuffer is in UTF-8 but without trailing null-term byte */
- symname_utf8_len = len - sizeof(buf->Flags);
+ /* MS-FSCC 2.1.2.7 defines layout of the Target field only for Version 2. */
+ if (le32_to_cpu(buf->Version) != 2) {
+ cifs_dbg(VFS, "srv returned unsupported wsl symlink version %u\n", le32_to_cpu(buf->Version));
+ return -EIO;
+ }
+
+ /* Target for Version 2 is in UTF-8 but without trailing null-term byte */
+ symname_utf8_len = len - data_offset;
/*
* Check that buffer does not contain null byte
* because Linux cannot process symlink with null byte.
*/
- if (strnlen(buf->PathBuffer, symname_utf8_len) != symname_utf8_len) {
+ if (strnlen(buf->Target, symname_utf8_len) != symname_utf8_len) {
cifs_dbg(VFS, "srv returned null byte in wsl symlink target location\n");
return -EIO;
}
symname_utf16 = kzalloc(symname_utf8_len * 2, GFP_KERNEL);
if (!symname_utf16)
return -ENOMEM;
- symname_utf16_len = utf8s_to_utf16s(buf->PathBuffer, symname_utf8_len,
+ symname_utf16_len = utf8s_to_utf16s(buf->Target, symname_utf8_len,
UTF16_LITTLE_ENDIAN,
(wchar_t *) symname_utf16, symname_utf8_len * 2);
if (symname_utf16_len < 0) {
@@ -1062,8 +1069,6 @@ int parse_reparse_point(struct reparse_data_buffer *buf,
const char *full_path,
struct cifs_open_info_data *data)
{
- struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
-
data->reparse.buf = buf;
/* See MS-FSCC 2.1.2 */
@@ -1090,24 +1095,17 @@ int parse_reparse_point(struct reparse_data_buffer *buf,
}
return 0;
default:
- cifs_tcon_dbg(VFS | ONCE, "unhandled reparse tag: 0x%08x\n",
- le32_to_cpu(buf->ReparseTag));
return -EOPNOTSUPP;
}
}
-int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb,
- const char *full_path,
- struct kvec *rsp_iov,
- struct cifs_open_info_data *data)
+struct reparse_data_buffer *smb2_get_reparse_point_buffer(const struct kvec *rsp_iov,
+ u32 *plen)
{
- struct reparse_data_buffer *buf;
struct smb2_ioctl_rsp *io = rsp_iov->iov_base;
- u32 plen = le32_to_cpu(io->OutputCount);
-
- buf = (struct reparse_data_buffer *)((u8 *)io +
- le32_to_cpu(io->OutputOffset));
- return parse_reparse_point(buf, plen, cifs_sb, full_path, data);
+ *plen = le32_to_cpu(io->OutputCount);
+ return (struct reparse_data_buffer *)((u8 *)io +
+ le32_to_cpu(io->OutputOffset));
}
static bool wsl_to_fattr(struct cifs_open_info_data *data,
@@ -1233,16 +1231,6 @@ bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb,
bool ok;
switch (tag) {
- case IO_REPARSE_TAG_INTERNAL:
- if (!(fattr->cf_cifsattrs & ATTR_DIRECTORY))
- return false;
- fallthrough;
- case IO_REPARSE_TAG_DFS:
- case IO_REPARSE_TAG_DFSR:
- case IO_REPARSE_TAG_MOUNT_POINT:
- /* See cifs_create_junction_fattr() */
- fattr->cf_mode = S_IFDIR | 0711;
- break;
case IO_REPARSE_TAG_LX_SYMLINK:
case IO_REPARSE_TAG_LX_FIFO:
case IO_REPARSE_TAG_AF_UNIX:
@@ -1262,7 +1250,14 @@ bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb,
fattr->cf_mode |= S_IFLNK;
break;
default:
- return false;
+ if (!(fattr->cf_cifsattrs & ATTR_DIRECTORY))
+ return false;
+ if (!IS_REPARSE_TAG_NAME_SURROGATE(tag) &&
+ tag != IO_REPARSE_TAG_INTERNAL)
+ return false;
+ /* See cifs_create_junction_fattr() */
+ fattr->cf_mode = S_IFDIR | 0711;
+ break;
}
fattr->cf_dtype = S_DT(fattr->cf_mode);
diff --git a/fs/smb/client/reparse.h b/fs/smb/client/reparse.h
index c0be5ab..08de853 100644
--- a/fs/smb/client/reparse.h
+++ b/fs/smb/client/reparse.h
@@ -135,9 +135,6 @@ int smb2_create_reparse_symlink(const unsigned int xid, struct inode *inode,
int smb2_mknod_reparse(unsigned int xid, struct inode *inode,
struct dentry *dentry, struct cifs_tcon *tcon,
const char *full_path, umode_t mode, dev_t dev);
-int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb,
- const char *full_path,
- struct kvec *rsp_iov,
- struct cifs_open_info_data *data);
+struct reparse_data_buffer *smb2_get_reparse_point_buffer(const struct kvec *rsp_iov, u32 *len);
#endif /* _CIFS_REPARSE_H */
diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index f2ca596..b3fa9ee 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -680,6 +680,22 @@ unicode_oslm_strings(char **pbcc_area, const struct nls_table *nls_cp)
*pbcc_area = bcc_ptr;
}
+static void
+ascii_oslm_strings(char **pbcc_area, const struct nls_table *nls_cp)
+{
+ char *bcc_ptr = *pbcc_area;
+
+ strcpy(bcc_ptr, "Linux version ");
+ bcc_ptr += strlen("Linux version ");
+ strcpy(bcc_ptr, init_utsname()->release);
+ bcc_ptr += strlen(init_utsname()->release) + 1;
+
+ strcpy(bcc_ptr, CIFS_NETWORK_OPSYS);
+ bcc_ptr += strlen(CIFS_NETWORK_OPSYS) + 1;
+
+ *pbcc_area = bcc_ptr;
+}
+
static void unicode_domain_string(char **pbcc_area, struct cifs_ses *ses,
const struct nls_table *nls_cp)
{
@@ -704,6 +720,25 @@ static void unicode_domain_string(char **pbcc_area, struct cifs_ses *ses,
*pbcc_area = bcc_ptr;
}
+static void ascii_domain_string(char **pbcc_area, struct cifs_ses *ses,
+ const struct nls_table *nls_cp)
+{
+ char *bcc_ptr = *pbcc_area;
+ int len;
+
+ /* copy domain */
+ if (ses->domainName != NULL) {
+ len = strscpy(bcc_ptr, ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
+ if (WARN_ON_ONCE(len < 0))
+ len = CIFS_MAX_DOMAINNAME_LEN - 1;
+ bcc_ptr += len;
+ } /* else we send a null domain name so server will default to its own domain */
+ *bcc_ptr = 0;
+ bcc_ptr++;
+
+ *pbcc_area = bcc_ptr;
+}
+
static void unicode_ssetup_strings(char **pbcc_area, struct cifs_ses *ses,
const struct nls_table *nls_cp)
{
@@ -749,25 +784,10 @@ static void ascii_ssetup_strings(char **pbcc_area, struct cifs_ses *ses,
*bcc_ptr = 0;
bcc_ptr++; /* account for null termination */
- /* copy domain */
- if (ses->domainName != NULL) {
- len = strscpy(bcc_ptr, ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
- if (WARN_ON_ONCE(len < 0))
- len = CIFS_MAX_DOMAINNAME_LEN - 1;
- bcc_ptr += len;
- } /* else we send a null domain name so server will default to its own domain */
- *bcc_ptr = 0;
- bcc_ptr++;
-
/* BB check for overflow here */
- strcpy(bcc_ptr, "Linux version ");
- bcc_ptr += strlen("Linux version ");
- strcpy(bcc_ptr, init_utsname()->release);
- bcc_ptr += strlen(init_utsname()->release) + 1;
-
- strcpy(bcc_ptr, CIFS_NETWORK_OPSYS);
- bcc_ptr += strlen(CIFS_NETWORK_OPSYS) + 1;
+ ascii_domain_string(&bcc_ptr, ses, nls_cp);
+ ascii_oslm_strings(&bcc_ptr, nls_cp);
*pbcc_area = bcc_ptr;
}
@@ -1570,7 +1590,7 @@ sess_auth_kerberos(struct sess_data *sess_data)
sess_data->iov[1].iov_len = msg->secblob_len;
pSMB->req.SecurityBlobLength = cpu_to_le16(sess_data->iov[1].iov_len);
- if (ses->capabilities & CAP_UNICODE) {
+ if (pSMB->req.hdr.Flags2 & SMBFLG2_UNICODE) {
/* unicode strings must be word aligned */
if (!IS_ALIGNED(sess_data->iov[0].iov_len + sess_data->iov[1].iov_len, 2)) {
*bcc_ptr = 0;
@@ -1579,8 +1599,8 @@ sess_auth_kerberos(struct sess_data *sess_data)
unicode_oslm_strings(&bcc_ptr, sess_data->nls_cp);
unicode_domain_string(&bcc_ptr, ses, sess_data->nls_cp);
} else {
- /* BB: is this right? */
- ascii_ssetup_strings(&bcc_ptr, ses, sess_data->nls_cp);
+ ascii_oslm_strings(&bcc_ptr, sess_data->nls_cp);
+ ascii_domain_string(&bcc_ptr, ses, sess_data->nls_cp);
}
sess_data->iov[2].iov_len = (long) bcc_ptr -
diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index 26df807..0adeec6 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -568,6 +568,42 @@ static int cifs_query_path_info(const unsigned int xid,
data->reparse_point = le32_to_cpu(fi.Attributes) & ATTR_REPARSE;
}
+#ifdef CONFIG_CIFS_XATTR
+ /*
+ * For WSL CHR and BLK reparse points it is required to fetch
+ * EA $LXDEV which contains major and minor device numbers.
+ */
+ if (!rc && data->reparse_point) {
+ struct smb2_file_full_ea_info *ea;
+
+ ea = (struct smb2_file_full_ea_info *)data->wsl.eas;
+ rc = CIFSSMBQAllEAs(xid, tcon, full_path, SMB2_WSL_XATTR_DEV,
+ &ea->ea_data[SMB2_WSL_XATTR_NAME_LEN + 1],
+ SMB2_WSL_XATTR_DEV_SIZE, cifs_sb);
+ if (rc == SMB2_WSL_XATTR_DEV_SIZE) {
+ ea->next_entry_offset = cpu_to_le32(0);
+ ea->flags = 0;
+ ea->ea_name_length = SMB2_WSL_XATTR_NAME_LEN;
+ ea->ea_value_length = cpu_to_le16(SMB2_WSL_XATTR_DEV_SIZE);
+ memcpy(&ea->ea_data[0], SMB2_WSL_XATTR_DEV, SMB2_WSL_XATTR_NAME_LEN + 1);
+ data->wsl.eas_len = sizeof(*ea) + SMB2_WSL_XATTR_NAME_LEN + 1 +
+ SMB2_WSL_XATTR_DEV_SIZE;
+ rc = 0;
+ } else if (rc >= 0) {
+ /* It is an error if EA $LXDEV has wrong size. */
+ rc = -EINVAL;
+ } else {
+ /*
+ * In all other cases ignore error if fetching
+ * of EA $LXDEV failed. It is needed only for
+ * WSL CHR and BLK reparse points and wsl_to_fattr()
+ * handle the case when EA is missing.
+ */
+ rc = 0;
+ }
+ }
+#endif
+
return rc;
}
@@ -970,18 +1006,13 @@ static int cifs_query_symlink(const unsigned int xid,
return rc;
}
-static int cifs_parse_reparse_point(struct cifs_sb_info *cifs_sb,
- const char *full_path,
- struct kvec *rsp_iov,
- struct cifs_open_info_data *data)
+static struct reparse_data_buffer *cifs_get_reparse_point_buffer(const struct kvec *rsp_iov,
+ u32 *plen)
{
- struct reparse_data_buffer *buf;
TRANSACT_IOCTL_RSP *io = rsp_iov->iov_base;
- u32 plen = le16_to_cpu(io->ByteCount);
-
- buf = (struct reparse_data_buffer *)((__u8 *)&io->hdr.Protocol +
- le32_to_cpu(io->DataOffset));
- return parse_reparse_point(buf, plen, cifs_sb, full_path, data);
+ *plen = le16_to_cpu(io->ByteCount);
+ return (struct reparse_data_buffer *)((__u8 *)&io->hdr.Protocol +
+ le32_to_cpu(io->DataOffset));
}
static bool
@@ -1157,7 +1188,7 @@ struct smb_version_operations smb1_operations = {
.rename = CIFSSMBRename,
.create_hardlink = CIFSCreateHardLink,
.query_symlink = cifs_query_symlink,
- .parse_reparse_point = cifs_parse_reparse_point,
+ .get_reparse_point_buffer = cifs_get_reparse_point_buffer,
.open = cifs_open_file,
.set_fid = cifs_set_fid,
.close = cifs_close_file,
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 41d8cd2..2fe8eeb 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -4555,9 +4555,9 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf,
return rc;
}
} else {
- if (unlikely(!server->secmech.dec))
- return -EIO;
-
+ rc = smb3_crypto_aead_allocate(server);
+ if (unlikely(rc))
+ return rc;
tfm = server->secmech.dec;
}
@@ -5303,7 +5303,7 @@ struct smb_version_operations smb20_operations = {
.unlink = smb2_unlink,
.rename = smb2_rename_path,
.create_hardlink = smb2_create_hardlink,
- .parse_reparse_point = smb2_parse_reparse_point,
+ .get_reparse_point_buffer = smb2_get_reparse_point_buffer,
.query_mf_symlink = smb3_query_mf_symlink,
.create_mf_symlink = smb3_create_mf_symlink,
.create_reparse_symlink = smb2_create_reparse_symlink,
@@ -5406,7 +5406,7 @@ struct smb_version_operations smb21_operations = {
.unlink = smb2_unlink,
.rename = smb2_rename_path,
.create_hardlink = smb2_create_hardlink,
- .parse_reparse_point = smb2_parse_reparse_point,
+ .get_reparse_point_buffer = smb2_get_reparse_point_buffer,
.query_mf_symlink = smb3_query_mf_symlink,
.create_mf_symlink = smb3_create_mf_symlink,
.create_reparse_symlink = smb2_create_reparse_symlink,
@@ -5513,7 +5513,7 @@ struct smb_version_operations smb30_operations = {
.unlink = smb2_unlink,
.rename = smb2_rename_path,
.create_hardlink = smb2_create_hardlink,
- .parse_reparse_point = smb2_parse_reparse_point,
+ .get_reparse_point_buffer = smb2_get_reparse_point_buffer,
.query_mf_symlink = smb3_query_mf_symlink,
.create_mf_symlink = smb3_create_mf_symlink,
.create_reparse_symlink = smb2_create_reparse_symlink,
@@ -5629,7 +5629,7 @@ struct smb_version_operations smb311_operations = {
.unlink = smb2_unlink,
.rename = smb2_rename_path,
.create_hardlink = smb2_create_hardlink,
- .parse_reparse_point = smb2_parse_reparse_point,
+ .get_reparse_point_buffer = smb2_get_reparse_point_buffer,
.query_mf_symlink = smb3_query_mf_symlink,
.create_mf_symlink = smb3_create_mf_symlink,
.create_reparse_symlink = smb2_create_reparse_symlink,
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 81e05db..c4d52be 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -1252,15 +1252,8 @@ SMB2_negotiate(const unsigned int xid,
cifs_server_dbg(VFS, "Missing expected negotiate contexts\n");
}
- if (server->cipher_type && !rc) {
- if (!SERVER_IS_CHAN(server)) {
- rc = smb3_crypto_aead_allocate(server);
- } else {
- /* For channels, just reuse the primary server crypto secmech. */
- server->secmech.enc = server->primary_server->secmech.enc;
- server->secmech.dec = server->primary_server->secmech.dec;
- }
- }
+ if (server->cipher_type && !rc)
+ rc = smb3_crypto_aead_allocate(server);
neg_exit:
free_rsp_buf(resp_buftype, rsp);
return rc;
diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h
index 764dca8..f79a5165 100644
--- a/fs/smb/common/smb2pdu.h
+++ b/fs/smb/common/smb2pdu.h
@@ -1567,13 +1567,13 @@ struct reparse_nfs_data_buffer {
__u8 DataBuffer[];
} __packed;
-/* For IO_REPARSE_TAG_LX_SYMLINK */
+/* For IO_REPARSE_TAG_LX_SYMLINK - see MS-FSCC 2.1.2.7 */
struct reparse_wsl_symlink_data_buffer {
__le32 ReparseTag;
__le16 ReparseDataLength;
__u16 Reserved;
- __le32 Flags;
- __u8 PathBuffer[]; /* Variable Length UTF-8 string without nul-term */
+ __le32 Version; /* Always 2 */
+ __u8 Target[]; /* Variable Length UTF-8 string without nul-term */
} __packed;
struct validate_negotiate_info_req {
diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c
index 83caa38..b3d1210 100644
--- a/fs/smb/server/auth.c
+++ b/fs/smb/server/auth.c
@@ -550,7 +550,19 @@ int ksmbd_krb5_authenticate(struct ksmbd_session *sess, char *in_blob,
retval = -ENOMEM;
goto out;
}
- sess->user = user;
+
+ if (!sess->user) {
+ /* First successful authentication */
+ sess->user = user;
+ } else {
+ if (!ksmbd_compare_user(sess->user, user)) {
+ ksmbd_debug(AUTH, "different user tried to reuse session\n");
+ retval = -EPERM;
+ ksmbd_free_user(user);
+ goto out;
+ }
+ ksmbd_free_user(user);
+ }
memcpy(sess->sess_key, resp->payload, resp->session_key_len);
memcpy(out_blob, resp->payload + resp->session_key_len,
diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c
index c1f22c1..83764c2 100644
--- a/fs/smb/server/connection.c
+++ b/fs/smb/server/connection.c
@@ -39,8 +39,10 @@ void ksmbd_conn_free(struct ksmbd_conn *conn)
xa_destroy(&conn->sessions);
kvfree(conn->request_buf);
kfree(conn->preauth_info);
- if (atomic_dec_and_test(&conn->refcnt))
+ if (atomic_dec_and_test(&conn->refcnt)) {
+ ksmbd_free_transport(conn->transport);
kfree(conn);
+ }
}
/**
diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c
index 3f45f28..9dec4c2 100644
--- a/fs/smb/server/mgmt/user_session.c
+++ b/fs/smb/server/mgmt/user_session.c
@@ -59,10 +59,12 @@ static void ksmbd_session_rpc_clear_list(struct ksmbd_session *sess)
struct ksmbd_session_rpc *entry;
long index;
+ down_write(&sess->rpc_lock);
xa_for_each(&sess->rpc_handle_list, index, entry) {
xa_erase(&sess->rpc_handle_list, index);
__session_rpc_close(sess, entry);
}
+ up_write(&sess->rpc_lock);
xa_destroy(&sess->rpc_handle_list);
}
@@ -92,7 +94,7 @@ int ksmbd_session_rpc_open(struct ksmbd_session *sess, char *rpc_name)
{
struct ksmbd_session_rpc *entry, *old;
struct ksmbd_rpc_command *resp;
- int method;
+ int method, id;
method = __rpc_method(rpc_name);
if (!method)
@@ -102,26 +104,29 @@ int ksmbd_session_rpc_open(struct ksmbd_session *sess, char *rpc_name)
if (!entry)
return -ENOMEM;
+ down_read(&sess->rpc_lock);
entry->method = method;
- entry->id = ksmbd_ipc_id_alloc();
- if (entry->id < 0)
+ entry->id = id = ksmbd_ipc_id_alloc();
+ if (id < 0)
goto free_entry;
- old = xa_store(&sess->rpc_handle_list, entry->id, entry, KSMBD_DEFAULT_GFP);
+ old = xa_store(&sess->rpc_handle_list, id, entry, KSMBD_DEFAULT_GFP);
if (xa_is_err(old))
goto free_id;
- resp = ksmbd_rpc_open(sess, entry->id);
+ resp = ksmbd_rpc_open(sess, id);
if (!resp)
goto erase_xa;
+ up_read(&sess->rpc_lock);
kvfree(resp);
- return entry->id;
+ return id;
erase_xa:
xa_erase(&sess->rpc_handle_list, entry->id);
free_id:
ksmbd_rpc_id_free(entry->id);
free_entry:
kfree(entry);
+ up_read(&sess->rpc_lock);
return -EINVAL;
}
@@ -129,9 +134,11 @@ void ksmbd_session_rpc_close(struct ksmbd_session *sess, int id)
{
struct ksmbd_session_rpc *entry;
+ down_write(&sess->rpc_lock);
entry = xa_erase(&sess->rpc_handle_list, id);
if (entry)
__session_rpc_close(sess, entry);
+ up_write(&sess->rpc_lock);
}
int ksmbd_session_rpc_method(struct ksmbd_session *sess, int id)
@@ -439,6 +446,7 @@ static struct ksmbd_session *__session_create(int protocol)
sess->sequence_number = 1;
rwlock_init(&sess->tree_conns_lock);
atomic_set(&sess->refcnt, 2);
+ init_rwsem(&sess->rpc_lock);
ret = __init_smb2_session(sess);
if (ret)
diff --git a/fs/smb/server/mgmt/user_session.h b/fs/smb/server/mgmt/user_session.h
index f213483..c5749d6e 100644
--- a/fs/smb/server/mgmt/user_session.h
+++ b/fs/smb/server/mgmt/user_session.h
@@ -63,6 +63,7 @@ struct ksmbd_session {
rwlock_t tree_conns_lock;
atomic_t refcnt;
+ struct rw_semaphore rpc_lock;
};
static inline int test_session_flag(struct ksmbd_session *sess, int bit)
diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c
index f103b1b..81a29857 100644
--- a/fs/smb/server/oplock.c
+++ b/fs/smb/server/oplock.c
@@ -129,14 +129,6 @@ static void free_opinfo(struct oplock_info *opinfo)
kfree(opinfo);
}
-static inline void opinfo_free_rcu(struct rcu_head *rcu_head)
-{
- struct oplock_info *opinfo;
-
- opinfo = container_of(rcu_head, struct oplock_info, rcu_head);
- free_opinfo(opinfo);
-}
-
struct oplock_info *opinfo_get(struct ksmbd_file *fp)
{
struct oplock_info *opinfo;
@@ -157,8 +149,8 @@ static struct oplock_info *opinfo_get_list(struct ksmbd_inode *ci)
if (list_empty(&ci->m_op_list))
return NULL;
- rcu_read_lock();
- opinfo = list_first_or_null_rcu(&ci->m_op_list, struct oplock_info,
+ down_read(&ci->m_lock);
+ opinfo = list_first_entry(&ci->m_op_list, struct oplock_info,
op_entry);
if (opinfo) {
if (opinfo->conn == NULL ||
@@ -171,8 +163,7 @@ static struct oplock_info *opinfo_get_list(struct ksmbd_inode *ci)
}
}
}
-
- rcu_read_unlock();
+ up_read(&ci->m_lock);
return opinfo;
}
@@ -185,7 +176,7 @@ void opinfo_put(struct oplock_info *opinfo)
if (!atomic_dec_and_test(&opinfo->refcount))
return;
- call_rcu(&opinfo->rcu_head, opinfo_free_rcu);
+ free_opinfo(opinfo);
}
static void opinfo_add(struct oplock_info *opinfo)
@@ -193,7 +184,7 @@ static void opinfo_add(struct oplock_info *opinfo)
struct ksmbd_inode *ci = opinfo->o_fp->f_ci;
down_write(&ci->m_lock);
- list_add_rcu(&opinfo->op_entry, &ci->m_op_list);
+ list_add(&opinfo->op_entry, &ci->m_op_list);
up_write(&ci->m_lock);
}
@@ -207,7 +198,7 @@ static void opinfo_del(struct oplock_info *opinfo)
write_unlock(&lease_list_lock);
}
down_write(&ci->m_lock);
- list_del_rcu(&opinfo->op_entry);
+ list_del(&opinfo->op_entry);
up_write(&ci->m_lock);
}
@@ -1347,8 +1338,8 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp,
ci = fp->f_ci;
op = opinfo_get(fp);
- rcu_read_lock();
- list_for_each_entry_rcu(brk_op, &ci->m_op_list, op_entry) {
+ down_read(&ci->m_lock);
+ list_for_each_entry(brk_op, &ci->m_op_list, op_entry) {
if (brk_op->conn == NULL)
continue;
@@ -1358,7 +1349,6 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp,
if (ksmbd_conn_releasing(brk_op->conn))
continue;
- rcu_read_unlock();
if (brk_op->is_lease && (brk_op->o_lease->state &
(~(SMB2_LEASE_READ_CACHING_LE |
SMB2_LEASE_HANDLE_CACHING_LE)))) {
@@ -1388,9 +1378,8 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp,
oplock_break(brk_op, SMB2_OPLOCK_LEVEL_NONE, NULL);
next:
opinfo_put(brk_op);
- rcu_read_lock();
}
- rcu_read_unlock();
+ up_read(&ci->m_lock);
if (op)
opinfo_put(op);
diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h
index 3f64f07..9a56eaa 100644
--- a/fs/smb/server/oplock.h
+++ b/fs/smb/server/oplock.h
@@ -71,7 +71,6 @@ struct oplock_info {
struct list_head lease_entry;
wait_queue_head_t oplock_q; /* Other server threads */
wait_queue_head_t oplock_brk; /* oplock breaking wait */
- struct rcu_head rcu_head;
};
struct lease_break_info {
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index d24d95d..46aa082 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -1445,7 +1445,7 @@ static int ntlm_authenticate(struct ksmbd_work *work,
{
struct ksmbd_conn *conn = work->conn;
struct ksmbd_session *sess = work->sess;
- struct channel *chann = NULL;
+ struct channel *chann = NULL, *old;
struct ksmbd_user *user;
u64 prev_id;
int sz, rc;
@@ -1557,7 +1557,12 @@ static int ntlm_authenticate(struct ksmbd_work *work,
return -ENOMEM;
chann->conn = conn;
- xa_store(&sess->ksmbd_chann_list, (long)conn, chann, KSMBD_DEFAULT_GFP);
+ old = xa_store(&sess->ksmbd_chann_list, (long)conn, chann,
+ KSMBD_DEFAULT_GFP);
+ if (xa_is_err(old)) {
+ kfree(chann);
+ return xa_err(old);
+ }
}
}
@@ -1602,9 +1607,6 @@ static int krb5_authenticate(struct ksmbd_work *work,
if (prev_sess_id && prev_sess_id != sess->id)
destroy_previous_session(conn, sess->user, prev_sess_id);
- if (sess->state == SMB2_SESSION_VALID)
- ksmbd_free_user(sess->user);
-
retval = ksmbd_krb5_authenticate(sess, in_blob, in_len,
out_blob, &out_len);
if (retval) {
@@ -2247,10 +2249,6 @@ int smb2_session_logoff(struct ksmbd_work *work)
sess->state = SMB2_SESSION_EXPIRED;
up_write(&conn->session_lock);
- if (sess->user) {
- ksmbd_free_user(sess->user);
- sess->user = NULL;
- }
ksmbd_all_conn_set_status(sess_id, KSMBD_SESS_NEED_SETUP);
rsp->StructureSize = cpu_to_le16(4);
diff --git a/fs/smb/server/smb_common.h b/fs/smb/server/smb_common.h
index a3d8a90..d742ba7 100644
--- a/fs/smb/server/smb_common.h
+++ b/fs/smb/server/smb_common.h
@@ -72,6 +72,8 @@
#define FILE_SUPPORTS_ENCRYPTION 0x00020000
#define FILE_SUPPORTS_OBJECT_IDS 0x00010000
#define FILE_VOLUME_IS_COMPRESSED 0x00008000
+#define FILE_SUPPORTS_POSIX_UNLINK_RENAME 0x00000400
+#define FILE_RETURNS_CLEANUP_RESULT_INFO 0x00000200
#define FILE_SUPPORTS_REMOTE_STORAGE 0x00000100
#define FILE_SUPPORTS_REPARSE_POINTS 0x00000080
#define FILE_SUPPORTS_SPARSE_FILES 0x00000040
diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c
index 3f185ae..2a3e2b0 100644
--- a/fs/smb/server/transport_ipc.c
+++ b/fs/smb/server/transport_ipc.c
@@ -310,7 +310,11 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req)
server_conf.signing = req->signing;
server_conf.tcp_port = req->tcp_port;
server_conf.ipc_timeout = req->ipc_timeout * HZ;
- server_conf.deadtime = req->deadtime * SMB_ECHO_INTERVAL;
+ if (check_mul_overflow(req->deadtime, SMB_ECHO_INTERVAL,
+ &server_conf.deadtime)) {
+ ret = -EINVAL;
+ goto out;
+ }
server_conf.share_fake_fscaps = req->share_fake_fscaps;
ksmbd_init_domain(req->sub_auth);
@@ -337,6 +341,7 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req)
server_conf.bind_interfaces_only = req->bind_interfaces_only;
ret |= ksmbd_tcp_set_interfaces(KSMBD_STARTUP_CONFIG_INTERFACES(req),
req->ifc_list_sz);
+out:
if (ret) {
pr_err("Server configuration error: %s %s %s\n",
req->netbios_name, req->server_string,
diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c
index 7f38a3c..abedf51 100644
--- a/fs/smb/server/transport_tcp.c
+++ b/fs/smb/server/transport_tcp.c
@@ -93,15 +93,19 @@ static struct tcp_transport *alloc_transport(struct socket *client_sk)
return t;
}
+void ksmbd_free_transport(struct ksmbd_transport *kt)
+{
+ struct tcp_transport *t = TCP_TRANS(kt);
+
+ sock_release(t->sock);
+ kfree(t->iov);
+ kfree(t);
+}
+
static void free_transport(struct tcp_transport *t)
{
kernel_sock_shutdown(t->sock, SHUT_RDWR);
- sock_release(t->sock);
- t->sock = NULL;
-
ksmbd_conn_free(KSMBD_TRANS(t)->conn);
- kfree(t->iov);
- kfree(t);
}
/**
diff --git a/fs/smb/server/transport_tcp.h b/fs/smb/server/transport_tcp.h
index 8c9aa62..1e51675 100644
--- a/fs/smb/server/transport_tcp.h
+++ b/fs/smb/server/transport_tcp.h
@@ -8,6 +8,7 @@
int ksmbd_tcp_set_interfaces(char *ifc_list, int ifc_list_sz);
struct interface *ksmbd_find_netdev_name_iface_list(char *netdev_name);
+void ksmbd_free_transport(struct ksmbd_transport *kt);
int ksmbd_tcp_init(void);
void ksmbd_tcp_destroy(void);
diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index 8554aa5..391d07d 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -479,7 +479,8 @@ int ksmbd_vfs_write(struct ksmbd_work *work, struct ksmbd_file *fp,
int err = 0;
if (work->conn->connection_type) {
- if (!(fp->daccess & (FILE_WRITE_DATA_LE | FILE_APPEND_DATA_LE))) {
+ if (!(fp->daccess & (FILE_WRITE_DATA_LE | FILE_APPEND_DATA_LE)) ||
+ S_ISDIR(file_inode(fp->filp)->i_mode)) {
pr_err("no right to write(%pD)\n", fp->filp);
err = -EACCES;
goto out;
diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c
index 8d1f30d..1f8fa34 100644
--- a/fs/smb/server/vfs_cache.c
+++ b/fs/smb/server/vfs_cache.c
@@ -713,12 +713,8 @@ static bool tree_conn_fd_check(struct ksmbd_tree_connect *tcon,
static bool ksmbd_durable_scavenger_alive(void)
{
- mutex_lock(&durable_scavenger_lock);
- if (!durable_scavenger_running) {
- mutex_unlock(&durable_scavenger_lock);
+ if (!durable_scavenger_running)
return false;
- }
- mutex_unlock(&durable_scavenger_lock);
if (kthread_should_stop())
return false;
@@ -799,9 +795,7 @@ static int ksmbd_durable_scavenger(void *dummy)
break;
}
- mutex_lock(&durable_scavenger_lock);
durable_scavenger_running = false;
- mutex_unlock(&durable_scavenger_lock);
module_put(THIS_MODULE);
diff --git a/fs/splice.c b/fs/splice.c
index 90d4642..4d6df08 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -45,7 +45,7 @@
* here if set to avoid blocking other users of this pipe if splice is
* being done on it.
*/
-static noinline void noinline pipe_clear_nowait(struct file *file)
+static noinline void pipe_clear_nowait(struct file *file)
{
fmode_t fmode = READ_ONCE(file->f_mode);
diff --git a/fs/stat.c b/fs/stat.c
index f13308bf..3d92228 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -204,12 +204,25 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat,
STATX_ATTR_DAX);
idmap = mnt_idmap(path->mnt);
- if (inode->i_op->getattr)
- return inode->i_op->getattr(idmap, path, stat,
- request_mask,
- query_flags);
+ if (inode->i_op->getattr) {
+ int ret;
- generic_fillattr(idmap, request_mask, inode, stat);
+ ret = inode->i_op->getattr(idmap, path, stat, request_mask,
+ query_flags);
+ if (ret)
+ return ret;
+ } else {
+ generic_fillattr(idmap, request_mask, inode, stat);
+ }
+
+ /*
+ * If this is a block device inode, override the filesystem attributes
+ * with the block device specific parameters that need to be obtained
+ * from the bdev backing inode.
+ */
+ if (S_ISBLK(stat->mode))
+ bdev_statx(path, stat, request_mask);
+
return 0;
}
EXPORT_SYMBOL(vfs_getattr_nosec);
@@ -295,15 +308,6 @@ static int vfs_statx_path(struct path *path, int flags, struct kstat *stat,
if (path_mounted(path))
stat->attributes |= STATX_ATTR_MOUNT_ROOT;
stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT;
-
- /*
- * If this is a block device inode, override the filesystem
- * attributes with the block device specific parameters that need to be
- * obtained from the bdev backing inode.
- */
- if (S_ISBLK(stat->mode))
- bdev_statx(path, stat, request_mask);
-
return 0;
}
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index d80f943..22f4bf9 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1585,8 +1585,11 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
user_uffdio_copy = (struct uffdio_copy __user *) arg;
ret = -EAGAIN;
- if (atomic_read(&ctx->mmap_changing))
+ if (unlikely(atomic_read(&ctx->mmap_changing))) {
+ if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
+ return -EFAULT;
goto out;
+ }
ret = -EFAULT;
if (copy_from_user(&uffdio_copy, user_uffdio_copy,
@@ -1641,8 +1644,11 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg;
ret = -EAGAIN;
- if (atomic_read(&ctx->mmap_changing))
+ if (unlikely(atomic_read(&ctx->mmap_changing))) {
+ if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
+ return -EFAULT;
goto out;
+ }
ret = -EFAULT;
if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage,
@@ -1744,8 +1750,11 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
user_uffdio_continue = (struct uffdio_continue __user *)arg;
ret = -EAGAIN;
- if (atomic_read(&ctx->mmap_changing))
+ if (unlikely(atomic_read(&ctx->mmap_changing))) {
+ if (unlikely(put_user(ret, &user_uffdio_continue->mapped)))
+ return -EFAULT;
goto out;
+ }
ret = -EFAULT;
if (copy_from_user(&uffdio_continue, user_uffdio_continue,
@@ -1801,8 +1810,11 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long
user_uffdio_poison = (struct uffdio_poison __user *)arg;
ret = -EAGAIN;
- if (atomic_read(&ctx->mmap_changing))
+ if (unlikely(atomic_read(&ctx->mmap_changing))) {
+ if (unlikely(put_user(ret, &user_uffdio_poison->updated)))
+ return -EFAULT;
goto out;
+ }
ret = -EFAULT;
if (copy_from_user(&uffdio_poison, user_uffdio_poison,
@@ -1870,8 +1882,12 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx,
user_uffdio_move = (struct uffdio_move __user *) arg;
- if (atomic_read(&ctx->mmap_changing))
- return -EAGAIN;
+ ret = -EAGAIN;
+ if (unlikely(atomic_read(&ctx->mmap_changing))) {
+ if (unlikely(put_user(ret, &user_uffdio_move->move)))
+ return -EFAULT;
+ goto out;
+ }
if (copy_from_user(&uffdio_move, user_uffdio_move,
/* don't copy "move" last field */
diff --git a/fs/xattr.c b/fs/xattr.c
index 02bee14..8ec5b02 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -703,7 +703,7 @@ static int path_setxattrat(int dfd, const char __user *pathname,
return error;
filename = getname_maybe_null(pathname, at_flags);
- if (!filename) {
+ if (!filename && dfd >= 0) {
CLASS(fd, f)(dfd);
if (fd_empty(f))
error = -EBADF;
@@ -847,7 +847,7 @@ static ssize_t path_getxattrat(int dfd, const char __user *pathname,
return error;
filename = getname_maybe_null(pathname, at_flags);
- if (!filename) {
+ if (!filename && dfd >= 0) {
CLASS(fd, f)(dfd);
if (fd_empty(f))
return -EBADF;
@@ -1428,6 +1428,15 @@ static bool xattr_is_trusted(const char *name)
return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
}
+static bool xattr_is_maclabel(const char *name)
+{
+ const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
+
+ return !strncmp(name, XATTR_SECURITY_PREFIX,
+ XATTR_SECURITY_PREFIX_LEN) &&
+ security_ismaclabel(suffix);
+}
+
/**
* simple_xattr_list - list all xattr objects
* @inode: inode from which to get the xattrs
@@ -1460,6 +1469,17 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
if (err)
return err;
+ err = security_inode_listsecurity(inode, buffer, remaining_size);
+ if (err < 0)
+ return err;
+
+ if (buffer) {
+ if (remaining_size < err)
+ return -ERANGE;
+ buffer += err;
+ }
+ remaining_size -= err;
+
read_lock(&xattrs->lock);
for (rbp = rb_first(&xattrs->rb_root); rbp; rbp = rb_next(rbp)) {
xattr = rb_entry(rbp, struct simple_xattr, rb_node);
@@ -1468,6 +1488,10 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
if (!trusted && xattr_is_trusted(xattr->name))
continue;
+ /* skip MAC labels; these are provided by LSM above */
+ if (xattr_is_maclabel(xattr->name))
+ continue;
+
err = xattr_list_one(&buffer, &remaining_size, xattr->name);
if (err)
break;
diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index fffd6ff..ae0ca68 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -3,7 +3,7 @@
tristate "XFS filesystem support"
depends on BLOCK
select EXPORTFS
- select LIBCRC32C
+ select CRC32
select FS_IOMAP
help
XFS is a high performance journaling filesystem which originated
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 8e7f1b3..1a2b3f0 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -105,6 +105,7 @@ xfs_buf_free(
{
unsigned int size = BBTOB(bp->b_length);
+ might_sleep();
trace_xfs_buf_free(bp, _RET_IP_);
ASSERT(list_empty(&bp->b_lru));
diff --git a/fs/xfs/xfs_buf_mem.c b/fs/xfs/xfs_buf_mem.c
index b4ffd80..dcbfa27 100644
--- a/fs/xfs/xfs_buf_mem.c
+++ b/fs/xfs/xfs_buf_mem.c
@@ -165,7 +165,7 @@ xmbuf_map_backing_mem(
folio_set_dirty(folio);
folio_unlock(folio);
- bp->b_addr = folio_address(folio);
+ bp->b_addr = folio_address(folio) + offset_in_folio(folio, pos);
return 0;
}
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index edbc521..b4e32f0 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -1186,9 +1186,8 @@ xfs_qm_dqflush_done(
if (test_bit(XFS_LI_IN_AIL, &lip->li_flags) &&
(lip->li_lsn == qlip->qli_flush_lsn ||
test_bit(XFS_LI_FAILED, &lip->li_flags))) {
-
spin_lock(&ailp->ail_lock);
- xfs_clear_li_failed(lip);
+ clear_bit(XFS_LI_FAILED, &lip->li_flags);
if (lip->li_lsn == qlip->qli_flush_lsn) {
/* xfs_ail_update_finish() drops the AIL lock */
tail_lsn = xfs_ail_delete_one(ailp, lip);
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index a4bc164..414b27a 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -876,6 +876,7 @@ xfs_getfsmap_rtdev_rmapbt(
const struct xfs_fsmap *keys,
struct xfs_getfsmap_info *info)
{
+ struct xfs_fsmap key0 = *keys; /* struct copy */
struct xfs_mount *mp = tp->t_mountp;
struct xfs_rtgroup *rtg = NULL;
struct xfs_btree_cur *bt_cur = NULL;
@@ -887,32 +888,46 @@ xfs_getfsmap_rtdev_rmapbt(
int error = 0;
eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart + mp->m_sb.sb_rblocks);
- if (keys[0].fmr_physical >= eofs)
+ if (key0.fmr_physical >= eofs)
return 0;
+ /*
+ * On zoned filesystems with an internal rt volume, the volume comes
+ * immediately after the end of the data volume. However, the
+ * xfs_rtblock_t address space is relative to the start of the data
+ * device, which means that the first @rtstart fsblocks do not actually
+ * point anywhere. If a fsmap query comes in with the low key starting
+ * below @rtstart, report it as "owned by filesystem".
+ */
rtstart_daddr = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart);
- if (keys[0].fmr_physical < rtstart_daddr) {
+ if (xfs_has_zoned(mp) && key0.fmr_physical < rtstart_daddr) {
struct xfs_fsmap_irec frec = {
.owner = XFS_RMAP_OWN_FS,
.len_daddr = rtstart_daddr,
};
- /* Adjust the low key if we are continuing from where we left off. */
- if (keys[0].fmr_length > 0) {
- info->low_daddr = keys[0].fmr_physical + keys[0].fmr_length;
- return 0;
+ /*
+ * Adjust the start of the query range if we're picking up from
+ * a previous round, and only emit the record if we haven't
+ * already gone past.
+ */
+ key0.fmr_physical += key0.fmr_length;
+ if (key0.fmr_physical < rtstart_daddr) {
+ error = xfs_getfsmap_helper(tp, info, &frec);
+ if (error)
+ return error;
+
+ key0.fmr_physical = rtstart_daddr;
}
- /* Fabricate an rmap entry for space occupied by the data dev */
- error = xfs_getfsmap_helper(tp, info, &frec);
- if (error)
- return error;
+ /* Zero the other fields to avoid further adjustments. */
+ key0.fmr_owner = 0;
+ key0.fmr_offset = 0;
+ key0.fmr_length = 0;
}
- start_rtb = xfs_daddr_to_rtb(mp, rtstart_daddr + keys[0].fmr_physical);
- end_rtb = xfs_daddr_to_rtb(mp, rtstart_daddr +
- min(eofs - 1, keys[1].fmr_physical));
-
+ start_rtb = xfs_daddr_to_rtb(mp, key0.fmr_physical);
+ end_rtb = xfs_daddr_to_rtb(mp, min(eofs - 1, keys[1].fmr_physical));
info->missing_owner = XFS_FMR_OWN_FREE;
/*
@@ -920,12 +935,12 @@ xfs_getfsmap_rtdev_rmapbt(
* low to the fsmap low key and max out the high key to the end
* of the rtgroup.
*/
- info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset);
- error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]);
+ info->low.rm_offset = XFS_BB_TO_FSBT(mp, key0.fmr_offset);
+ error = xfs_fsmap_owner_to_rmap(&info->low, &key0);
if (error)
return error;
- info->low.rm_blockcount = XFS_BB_TO_FSBT(mp, keys[0].fmr_length);
- xfs_getfsmap_set_irec_flags(&info->low, &keys[0]);
+ info->low.rm_blockcount = XFS_BB_TO_FSBT(mp, key0.fmr_length);
+ xfs_getfsmap_set_irec_flags(&info->low, &key0);
/* Adjust the low key if we are continuing from where we left off. */
if (info->low.rm_blockcount == 0) {
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 40fc1bf..c6cb0b6 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -1089,13 +1089,7 @@ xfs_iflush_abort(
* state. Whilst the inode is in the AIL, it should have a valid buffer
* pointer for push operations to access - it is only safe to remove the
* inode from the buffer once it has been removed from the AIL.
- *
- * We also clear the failed bit before removing the item from the AIL
- * as xfs_trans_ail_delete()->xfs_clear_li_failed() will release buffer
- * references the inode item owns and needs to hold until we've fully
- * aborted the inode log item and detached it from the buffer.
*/
- clear_bit(XFS_LI_FAILED, &iip->ili_item.li_flags);
xfs_trans_ail_delete(&iip->ili_item, 0);
/*
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 6493bdb..980aabc 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -2888,7 +2888,7 @@ xlog_force_and_check_iclog(
*
* 1. the current iclog is active and has no data; the previous iclog
* is in the active or dirty state.
- * 2. the current iclog is drity, and the previous iclog is in the
+ * 2. the current iclog is dirty, and the previous iclog is in the
* active or dirty state.
*
* We may sleep if:
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 799b842..e5192c1 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -229,6 +229,7 @@ typedef struct xfs_mount {
bool m_finobt_nores; /* no per-AG finobt resv. */
bool m_update_sb; /* sb needs update in mount */
unsigned int m_max_open_zones;
+ unsigned int m_zonegc_low_space;
/*
* Bitsets of per-fs metadata that have been checked and/or are sick.
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index b7e82d8..7a5c5ef 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -718,8 +718,40 @@ max_open_zones_show(
}
XFS_SYSFS_ATTR_RO(max_open_zones);
+static ssize_t
+zonegc_low_space_store(
+ struct kobject *kobj,
+ const char *buf,
+ size_t count)
+{
+ int ret;
+ unsigned int val;
+
+ ret = kstrtouint(buf, 0, &val);
+ if (ret)
+ return ret;
+
+ if (val > 100)
+ return -EINVAL;
+
+ zoned_to_mp(kobj)->m_zonegc_low_space = val;
+
+ return count;
+}
+
+static ssize_t
+zonegc_low_space_show(
+ struct kobject *kobj,
+ char *buf)
+{
+ return sysfs_emit(buf, "%u\n",
+ zoned_to_mp(kobj)->m_zonegc_low_space);
+}
+XFS_SYSFS_ATTR_RW(zonegc_low_space);
+
static struct attribute *xfs_zoned_attrs[] = {
ATTR_LIST(max_open_zones),
+ ATTR_LIST(zonegc_low_space),
NULL,
};
ATTRIBUTE_GROUPS(xfs_zoned);
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 0fcb182..85a649f 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -909,10 +909,9 @@ xfs_trans_ail_delete(
return;
}
- /* xfs_ail_update_finish() drops the AIL lock */
- xfs_clear_li_failed(lip);
+ clear_bit(XFS_LI_FAILED, &lip->li_flags);
tail_lsn = xfs_ail_delete_one(ailp, lip);
- xfs_ail_update_finish(ailp, tail_lsn);
+ xfs_ail_update_finish(ailp, tail_lsn); /* drops the AIL lock */
}
int
diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h
index bd841df..f945f04 100644
--- a/fs/xfs/xfs_trans_priv.h
+++ b/fs/xfs/xfs_trans_priv.h
@@ -167,32 +167,4 @@ xfs_trans_ail_copy_lsn(
}
#endif
-static inline void
-xfs_clear_li_failed(
- struct xfs_log_item *lip)
-{
- struct xfs_buf *bp = lip->li_buf;
-
- ASSERT(test_bit(XFS_LI_IN_AIL, &lip->li_flags));
- lockdep_assert_held(&lip->li_ailp->ail_lock);
-
- if (test_and_clear_bit(XFS_LI_FAILED, &lip->li_flags)) {
- lip->li_buf = NULL;
- xfs_buf_rele(bp);
- }
-}
-
-static inline void
-xfs_set_li_failed(
- struct xfs_log_item *lip,
- struct xfs_buf *bp)
-{
- lockdep_assert_held(&lip->li_ailp->ail_lock);
-
- if (!test_and_set_bit(XFS_LI_FAILED, &lip->li_flags)) {
- xfs_buf_hold(bp);
- lip->li_buf = bp;
- }
-}
-
#endif /* __XFS_TRANS_PRIV_H__ */
diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
index 52af234..d509e49 100644
--- a/fs/xfs/xfs_zone_alloc.c
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -1201,6 +1201,13 @@ xfs_mount_zones(
xfs_set_freecounter(mp, XC_FREE_RTEXTENTS,
iz.available + iz.reclaimable);
+ /*
+ * The user may configure GC to free up a percentage of unused blocks.
+ * By default this is 0. GC will always trigger at the minimum level
+ * for keeping max_open_zones available for data placement.
+ */
+ mp->m_zonegc_low_space = 0;
+
error = xfs_zone_gc_mount(mp);
if (error)
goto out_free_zone_info;
diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c
index c5136ea..81c94dd 100644
--- a/fs/xfs/xfs_zone_gc.c
+++ b/fs/xfs/xfs_zone_gc.c
@@ -162,18 +162,36 @@ struct xfs_zone_gc_data {
/*
* We aim to keep enough zones free in stock to fully use the open zone limit
- * for data placement purposes.
+ * for data placement purposes. Additionally, the m_zonegc_low_space tunable
+ * can be set to make sure a fraction of the unused blocks are available for
+ * writing.
*/
bool
xfs_zoned_need_gc(
struct xfs_mount *mp)
{
+ s64 available, free, threshold;
+ s32 remainder;
+
if (!xfs_group_marked(mp, XG_TYPE_RTG, XFS_RTG_RECLAIMABLE))
return false;
- if (xfs_estimate_freecounter(mp, XC_FREE_RTAVAILABLE) <
+
+ available = xfs_estimate_freecounter(mp, XC_FREE_RTAVAILABLE);
+
+ if (available <
mp->m_groups[XG_TYPE_RTG].blocks *
(mp->m_max_open_zones - XFS_OPEN_GC_ZONES))
return true;
+
+ free = xfs_estimate_freecounter(mp, XC_FREE_RTEXTENTS);
+
+ threshold = div_s64_rem(free, 100, &remainder);
+ threshold = threshold * mp->m_zonegc_low_space +
+ remainder * div_s64(mp->m_zonegc_low_space, 100);
+
+ if (available < threshold)
+ return true;
+
return false;
}
diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h
index 451f6276..2fc8970 100644
--- a/include/acpi/actbl.h
+++ b/include/acpi/actbl.h
@@ -66,7 +66,7 @@
******************************************************************************/
struct acpi_table_header {
- char signature[ACPI_NAMESEG_SIZE]; /* ASCII table signature */
+ char signature[ACPI_NAMESEG_SIZE] __nonstring; /* ASCII table signature */
u32 length; /* Length of table in bytes, including this header */
u8 revision; /* ACPI Specification minor version number */
u8 checksum; /* To make sum of entire table == 0 */
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index 2aa83ee..a679883 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -10,6 +10,7 @@
#include <linux/atomic.h>
#include <linux/crypto.h>
+#include <linux/slab.h>
#include <linux/string.h>
/* Set this bit for virtual address instead of SG list. */
@@ -581,7 +582,10 @@ static inline struct ahash_request *ahash_request_alloc_noprof(
* ahash_request_free() - zeroize and free the request data structure
* @req: request data structure cipher handle to be freed
*/
-void ahash_request_free(struct ahash_request *req);
+static inline void ahash_request_free(struct ahash_request *req)
+{
+ kfree_sensitive(req);
+}
static inline struct ahash_request *ahash_request_cast(
struct crypto_async_request *req)
diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h
index 485e22c..052ac79 100644
--- a/include/crypto/internal/hash.h
+++ b/include/crypto/internal/hash.h
@@ -249,7 +249,7 @@ static inline struct crypto_shash *__crypto_shash_cast(struct crypto_tfm *tfm)
static inline bool ahash_request_chained(struct ahash_request *req)
{
- return crypto_request_chained(&req->base);
+ return false;
}
static inline bool ahash_request_isvirt(struct ahash_request *req)
diff --git a/include/cxl/features.h b/include/cxl/features.h
index a3bb346..5f7f842 100644
--- a/include/cxl/features.h
+++ b/include/cxl/features.h
@@ -66,7 +66,7 @@ struct cxl_memdev;
#ifdef CONFIG_CXL_FEATURES
inline struct cxl_features_state *to_cxlfs(struct cxl_dev_state *cxlds);
int devm_cxl_setup_features(struct cxl_dev_state *cxlds);
-int devm_cxl_setup_fwctl(struct cxl_memdev *cxlmd);
+int devm_cxl_setup_fwctl(struct device *host, struct cxl_memdev *cxlmd);
#else
static inline struct cxl_features_state *to_cxlfs(struct cxl_dev_state *cxlds)
{
@@ -78,7 +78,8 @@ static inline int devm_cxl_setup_features(struct cxl_dev_state *cxlds)
return -EOPNOTSUPP;
}
-static inline int devm_cxl_setup_fwctl(struct cxl_memdev *cxlmd)
+static inline int devm_cxl_setup_fwctl(struct device *host,
+ struct cxl_memdev *cxlmd)
{
return -EOPNOTSUPP;
}
diff --git a/include/drm/intel/pciids.h b/include/drm/intel/pciids.h
index 4736ea5..d212848 100644
--- a/include/drm/intel/pciids.h
+++ b/include/drm/intel/pciids.h
@@ -850,6 +850,7 @@
MACRO__(0xE20C, ## __VA_ARGS__), \
MACRO__(0xE20D, ## __VA_ARGS__), \
MACRO__(0xE210, ## __VA_ARGS__), \
+ MACRO__(0xE211, ## __VA_ARGS__), \
MACRO__(0xE212, ## __VA_ARGS__), \
MACRO__(0xE215, ## __VA_ARGS__), \
MACRO__(0xE216, ## __VA_ARGS__)
diff --git a/include/kunit/test.h b/include/kunit/test.h
index 0ffb97c..39c768f 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -67,7 +67,7 @@ enum kunit_status {
/*
* Speed Attribute is stored as an enum and separated into categories of
- * speed: very_slowm, slow, and normal. These speeds are relative to
+ * speed: very_slow, slow, and normal. These speeds are relative to
* other KUnit tests.
*
* Note: unset speed attribute acts as default of KUNIT_SPEED_NORMAL.
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 8e7af9a..e721148 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -249,6 +249,7 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode)
{
#ifdef CONFIG_LOCKDEP
WARN_ON_ONCE(debug_locks &&
+ (inode->i_sb->s_iflags & SB_I_CGROUPWB) &&
(!lockdep_is_held(&inode->i_lock) &&
!lockdep_is_held(&inode->i_mapping->i_pages.xa_lock) &&
!lockdep_is_held(&inode->i_wb->list_lock)));
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index e39c45b..9a1f0ee 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -712,23 +712,6 @@ static inline bool blk_queue_is_zoned(struct request_queue *q)
(q->limits.features & BLK_FEAT_ZONED);
}
-#ifdef CONFIG_BLK_DEV_ZONED
-static inline unsigned int disk_nr_zones(struct gendisk *disk)
-{
- return disk->nr_zones;
-}
-bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs);
-#else /* CONFIG_BLK_DEV_ZONED */
-static inline unsigned int disk_nr_zones(struct gendisk *disk)
-{
- return 0;
-}
-static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
-{
- return false;
-}
-#endif /* CONFIG_BLK_DEV_ZONED */
-
static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
{
if (!blk_queue_is_zoned(disk->queue))
@@ -736,11 +719,6 @@ static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
return sector >> ilog2(disk->queue->limits.chunk_sectors);
}
-static inline unsigned int bdev_nr_zones(struct block_device *bdev)
-{
- return disk_nr_zones(bdev->bd_disk);
-}
-
static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
{
return bdev->bd_disk->queue->limits.max_open_zones;
@@ -847,6 +825,51 @@ static inline u64 sb_bdev_nr_blocks(struct super_block *sb)
(sb->s_blocksize_bits - SECTOR_SHIFT);
}
+#ifdef CONFIG_BLK_DEV_ZONED
+static inline unsigned int disk_nr_zones(struct gendisk *disk)
+{
+ return disk->nr_zones;
+}
+bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs);
+
+/**
+ * disk_zone_capacity - returns the zone capacity of zone containing @sector
+ * @disk: disk to work with
+ * @sector: sector number within the querying zone
+ *
+ * Returns the zone capacity of a zone containing @sector. @sector can be any
+ * sector in the zone.
+ */
+static inline unsigned int disk_zone_capacity(struct gendisk *disk,
+ sector_t sector)
+{
+ sector_t zone_sectors = disk->queue->limits.chunk_sectors;
+
+ if (sector + zone_sectors >= get_capacity(disk))
+ return disk->last_zone_capacity;
+ return disk->zone_capacity;
+}
+static inline unsigned int bdev_zone_capacity(struct block_device *bdev,
+ sector_t pos)
+{
+ return disk_zone_capacity(bdev->bd_disk, pos);
+}
+#else /* CONFIG_BLK_DEV_ZONED */
+static inline unsigned int disk_nr_zones(struct gendisk *disk)
+{
+ return 0;
+}
+static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
+{
+ return false;
+}
+#endif /* CONFIG_BLK_DEV_ZONED */
+
+static inline unsigned int bdev_nr_zones(struct block_device *bdev)
+{
+ return disk_nr_zones(bdev->bd_disk);
+}
+
int bdev_disk_changed(struct gendisk *disk, bool invalidate);
void put_disk(struct gendisk *disk);
@@ -1614,6 +1637,7 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time)
return bio_end_io_acct_remapped(bio, start_time, bio->bi_bdev);
}
+int bdev_validate_blocksize(struct block_device *bdev, int block_size);
int set_blocksize(struct file *file, int size);
int lookup_bdev(const char *pathname, dev_t *dev);
@@ -1670,10 +1694,6 @@ int bd_prepare_to_claim(struct block_device *bdev, void *holder,
const struct blk_holder_ops *hops);
void bd_abort_claiming(struct block_device *bdev, void *holder);
-/* just for blk-cgroup, don't use elsewhere */
-struct block_device *blkdev_get_no_open(dev_t dev);
-void blkdev_put_no_open(struct block_device *bdev);
-
struct block_device *I_BDEV(struct inode *inode);
struct block_device *file_bdev(struct file *bdev_file);
bool disk_live(struct gendisk *disk);
@@ -1685,7 +1705,7 @@ int sync_blockdev(struct block_device *bdev);
int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend);
int sync_blockdev_nowait(struct block_device *bdev);
void sync_bdevs(bool wait);
-void bdev_statx(struct path *, struct kstat *, u32);
+void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask);
void printk_all_partitions(void);
int __init early_lookup_bdev(const char *pathname, dev_t *dev);
#else
@@ -1703,8 +1723,8 @@ static inline int sync_blockdev_nowait(struct block_device *bdev)
static inline void sync_bdevs(bool wait)
{
}
-static inline void bdev_statx(struct path *path, struct kstat *stat,
- u32 request_mask)
+static inline void bdev_statx(const struct path *path, struct kstat *stat,
+ u32 request_mask)
{
}
static inline void printk_all_partitions(void)
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index f0a4ad7..0029ff88 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -34,6 +34,7 @@ enum bh_state_bits {
BH_Meta, /* Buffer contains metadata */
BH_Prio, /* Buffer should be submitted with REQ_PRIO */
BH_Defer_Completion, /* Defer AIO completion to workqueue */
+ BH_Migrate, /* Buffer is being migrated (norefs) */
BH_PrivateStart,/* not a state bit, but the first bit available
* for private allocation by other entities
@@ -222,6 +223,8 @@ void __wait_on_buffer(struct buffer_head *);
wait_queue_head_t *bh_waitq_head(struct buffer_head *bh);
struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block,
unsigned size);
+struct buffer_head *__find_get_block_nonatomic(struct block_device *bdev,
+ sector_t block, unsigned size);
struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block,
unsigned size, gfp_t gfp);
void __brelse(struct buffer_head *);
@@ -397,6 +400,12 @@ sb_find_get_block(struct super_block *sb, sector_t block)
return __find_get_block(sb->s_bdev, block, sb->s_blocksize);
}
+static inline struct buffer_head *
+sb_find_get_block_nonatomic(struct super_block *sb, sector_t block)
+{
+ return __find_get_block_nonatomic(sb->s_bdev, block, sb->s_blocksize);
+}
+
static inline void
map_bh(struct buffer_head *bh, struct super_block *sb, sector_t block)
{
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index d55b300..50b14a5 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -490,9 +490,6 @@ extern void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *,
struct page **pages, u64 length,
u32 alignment, bool pages_from_pool,
bool own_pages);
-extern void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *,
- unsigned int which,
- struct ceph_pagelist *pagelist);
#ifdef CONFIG_BLOCK
void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req,
unsigned int which,
@@ -509,9 +506,6 @@ void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req,
void osd_req_op_extent_osd_iter(struct ceph_osd_request *osd_req,
unsigned int which, struct iov_iter *iter);
-extern void osd_req_op_cls_request_data_pagelist(struct ceph_osd_request *,
- unsigned int which,
- struct ceph_pagelist *pagelist);
extern void osd_req_op_cls_request_data_pages(struct ceph_osd_request *,
unsigned int which,
struct page **pages, u64 length,
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 485b651..5bc8f55 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -710,6 +710,7 @@ struct cgroup_subsys {
void (*css_released)(struct cgroup_subsys_state *css);
void (*css_free)(struct cgroup_subsys_state *css);
void (*css_reset)(struct cgroup_subsys_state *css);
+ void (*css_killed)(struct cgroup_subsys_state *css);
void (*css_rstat_flush)(struct cgroup_subsys_state *css, int cpu);
int (*css_extra_stat_show)(struct seq_file *seq,
struct cgroup_subsys_state *css);
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 28e999f..e7da3c3 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -344,7 +344,7 @@ static inline u64 cgroup_id(const struct cgroup *cgrp)
*/
static inline bool css_is_dying(struct cgroup_subsys_state *css)
{
- return !(css->flags & CSS_NO_REF) && percpu_ref_is_dying(&css->refcnt);
+ return css->flags & CSS_DYING;
}
static inline void cgroup_get(struct cgroup *cgrp)
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 8d1395f..e9f07e3 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -173,65 +173,59 @@ struct dentry_operations {
*/
/* d_flags entries */
-#define DCACHE_OP_HASH BIT(0)
-#define DCACHE_OP_COMPARE BIT(1)
-#define DCACHE_OP_REVALIDATE BIT(2)
-#define DCACHE_OP_DELETE BIT(3)
-#define DCACHE_OP_PRUNE BIT(4)
+enum dentry_flags {
+ DCACHE_OP_HASH = BIT(0),
+ DCACHE_OP_COMPARE = BIT(1),
+ DCACHE_OP_REVALIDATE = BIT(2),
+ DCACHE_OP_DELETE = BIT(3),
+ DCACHE_OP_PRUNE = BIT(4),
+ /*
+ * This dentry is possibly not currently connected to the dcache tree,
+ * in which case its parent will either be itself, or will have this
+ * flag as well. nfsd will not use a dentry with this bit set, but will
+ * first endeavour to clear the bit either by discovering that it is
+ * connected, or by performing lookup operations. Any filesystem which
+ * supports nfsd_operations MUST have a lookup function which, if it
+ * finds a directory inode with a DCACHE_DISCONNECTED dentry, will
+ * d_move that dentry into place and return that dentry rather than the
+ * passed one, typically using d_splice_alias.
+ */
+ DCACHE_DISCONNECTED = BIT(5),
+ DCACHE_REFERENCED = BIT(6), /* Recently used, don't discard. */
+ DCACHE_DONTCACHE = BIT(7), /* Purge from memory on final dput() */
+ DCACHE_CANT_MOUNT = BIT(8),
+ DCACHE_GENOCIDE = BIT(9),
+ DCACHE_SHRINK_LIST = BIT(10),
+ DCACHE_OP_WEAK_REVALIDATE = BIT(11),
+ /*
+ * this dentry has been "silly renamed" and has to be deleted on the
+ * last dput()
+ */
+ DCACHE_NFSFS_RENAMED = BIT(12),
+ DCACHE_FSNOTIFY_PARENT_WATCHED = BIT(13), /* Parent inode is watched by some fsnotify listener */
+ DCACHE_DENTRY_KILLED = BIT(14),
+ DCACHE_MOUNTED = BIT(15), /* is a mountpoint */
+ DCACHE_NEED_AUTOMOUNT = BIT(16), /* handle automount on this dir */
+ DCACHE_MANAGE_TRANSIT = BIT(17), /* manage transit from this dirent */
+ DCACHE_LRU_LIST = BIT(18),
+ DCACHE_ENTRY_TYPE = (7 << 19), /* bits 19..21 are for storing type: */
+ DCACHE_MISS_TYPE = (0 << 19), /* Negative dentry */
+ DCACHE_WHITEOUT_TYPE = (1 << 19), /* Whiteout dentry (stop pathwalk) */
+ DCACHE_DIRECTORY_TYPE = (2 << 19), /* Normal directory */
+ DCACHE_AUTODIR_TYPE = (3 << 19), /* Lookupless directory (presumed automount) */
+ DCACHE_REGULAR_TYPE = (4 << 19), /* Regular file type */
+ DCACHE_SPECIAL_TYPE = (5 << 19), /* Other file type */
+ DCACHE_SYMLINK_TYPE = (6 << 19), /* Symlink */
+ DCACHE_NOKEY_NAME = BIT(22), /* Encrypted name encoded without key */
+ DCACHE_OP_REAL = BIT(23),
+ DCACHE_PAR_LOOKUP = BIT(24), /* being looked up (with parent locked shared) */
+ DCACHE_DENTRY_CURSOR = BIT(25),
+ DCACHE_NORCU = BIT(26), /* No RCU delay for freeing */
+};
-#define DCACHE_DISCONNECTED BIT(5)
- /* This dentry is possibly not currently connected to the dcache tree, in
- * which case its parent will either be itself, or will have this flag as
- * well. nfsd will not use a dentry with this bit set, but will first
- * endeavour to clear the bit either by discovering that it is connected,
- * or by performing lookup operations. Any filesystem which supports
- * nfsd_operations MUST have a lookup function which, if it finds a
- * directory inode with a DCACHE_DISCONNECTED dentry, will d_move that
- * dentry into place and return that dentry rather than the passed one,
- * typically using d_splice_alias. */
-
-#define DCACHE_REFERENCED BIT(6) /* Recently used, don't discard. */
-
-#define DCACHE_DONTCACHE BIT(7) /* Purge from memory on final dput() */
-
-#define DCACHE_CANT_MOUNT BIT(8)
-#define DCACHE_GENOCIDE BIT(9)
-#define DCACHE_SHRINK_LIST BIT(10)
-
-#define DCACHE_OP_WEAK_REVALIDATE BIT(11)
-
-#define DCACHE_NFSFS_RENAMED BIT(12)
- /* this dentry has been "silly renamed" and has to be deleted on the last
- * dput() */
-#define DCACHE_FSNOTIFY_PARENT_WATCHED BIT(13)
- /* Parent inode is watched by some fsnotify listener */
-
-#define DCACHE_DENTRY_KILLED BIT(14)
-
-#define DCACHE_MOUNTED BIT(15) /* is a mountpoint */
-#define DCACHE_NEED_AUTOMOUNT BIT(16) /* handle automount on this dir */
-#define DCACHE_MANAGE_TRANSIT BIT(17) /* manage transit from this dirent */
#define DCACHE_MANAGED_DENTRY \
(DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT)
-#define DCACHE_LRU_LIST BIT(18)
-
-#define DCACHE_ENTRY_TYPE (7 << 19) /* bits 19..21 are for storing type: */
-#define DCACHE_MISS_TYPE (0 << 19) /* Negative dentry */
-#define DCACHE_WHITEOUT_TYPE (1 << 19) /* Whiteout dentry (stop pathwalk) */
-#define DCACHE_DIRECTORY_TYPE (2 << 19) /* Normal directory */
-#define DCACHE_AUTODIR_TYPE (3 << 19) /* Lookupless directory (presumed automount) */
-#define DCACHE_REGULAR_TYPE (4 << 19) /* Regular file type */
-#define DCACHE_SPECIAL_TYPE (5 << 19) /* Other file type */
-#define DCACHE_SYMLINK_TYPE (6 << 19) /* Symlink */
-
-#define DCACHE_NOKEY_NAME BIT(22) /* Encrypted name encoded without key */
-#define DCACHE_OP_REAL BIT(23)
-
-#define DCACHE_PAR_LOOKUP BIT(24) /* being looked up (with parent locked shared) */
-#define DCACHE_DENTRY_CURSOR BIT(25)
-#define DCACHE_NORCU BIT(26) /* No RCU delay for freeing */
-
extern seqlock_t rename_lock;
/*
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index b79925b..85ab710 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -629,10 +629,14 @@ static inline int dma_mmap_wc(struct device *dev,
#else
#define DEFINE_DMA_UNMAP_ADDR(ADDR_NAME)
#define DEFINE_DMA_UNMAP_LEN(LEN_NAME)
-#define dma_unmap_addr(PTR, ADDR_NAME) (0)
-#define dma_unmap_addr_set(PTR, ADDR_NAME, VAL) do { } while (0)
-#define dma_unmap_len(PTR, LEN_NAME) (0)
-#define dma_unmap_len_set(PTR, LEN_NAME, VAL) do { } while (0)
+#define dma_unmap_addr(PTR, ADDR_NAME) \
+ ({ typeof(PTR) __p __maybe_unused = PTR; 0; })
+#define dma_unmap_addr_set(PTR, ADDR_NAME, VAL) \
+ do { typeof(PTR) __p __maybe_unused = PTR; } while (0)
+#define dma_unmap_len(PTR, LEN_NAME) \
+ ({ typeof(PTR) __p __maybe_unused = PTR; 0; })
+#define dma_unmap_len_set(PTR, LEN_NAME, VAL) \
+ do { typeof(PTR) __p __maybe_unused = PTR; } while (0)
#endif
#endif /* _LINUX_DMA_MAPPING_H */
diff --git a/include/linux/file_ref.h b/include/linux/file_ref.h
index 7db62fb..31551e4 100644
--- a/include/linux/file_ref.h
+++ b/include/linux/file_ref.h
@@ -61,7 +61,6 @@ static inline void file_ref_init(file_ref_t *ref, unsigned long cnt)
atomic_long_set(&ref->refcnt, cnt - 1);
}
-bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt);
bool __file_ref_put(file_ref_t *ref, unsigned long cnt);
/**
@@ -178,20 +177,14 @@ static __always_inline __must_check bool file_ref_put(file_ref_t *ref)
*/
static __always_inline __must_check bool file_ref_put_close(file_ref_t *ref)
{
- long old, new;
+ long old;
old = atomic_long_read(&ref->refcnt);
- do {
- if (unlikely(old < 0))
- return __file_ref_put_badval(ref, old);
-
- if (old == FILE_REF_ONEREF)
- new = FILE_REF_DEAD;
- else
- new = old - 1;
- } while (!atomic_long_try_cmpxchg(&ref->refcnt, &old, new));
-
- return new == FILE_REF_DEAD;
+ if (likely(old == FILE_REF_ONEREF)) {
+ if (likely(atomic_long_try_cmpxchg(&ref->refcnt, &old, FILE_REF_DEAD)))
+ return true;
+ }
+ return file_ref_put(ref);
}
/**
diff --git a/include/linux/firmware/cirrus/cs_dsp_test_utils.h b/include/linux/firmware/cirrus/cs_dsp_test_utils.h
index 4f87a90..ecd821e 100644
--- a/include/linux/firmware/cirrus/cs_dsp_test_utils.h
+++ b/include/linux/firmware/cirrus/cs_dsp_test_utils.h
@@ -104,7 +104,6 @@ unsigned int cs_dsp_mock_num_dsp_words_to_num_packed_regs(unsigned int num_dsp_w
unsigned int cs_dsp_mock_xm_header_get_alg_base_in_words(struct cs_dsp_test *priv,
unsigned int alg_id,
int mem_type);
-unsigned int cs_dsp_mock_xm_header_get_fw_version_from_regmap(struct cs_dsp_test *priv);
unsigned int cs_dsp_mock_xm_header_get_fw_version(struct cs_dsp_mock_xm_header *header);
void cs_dsp_mock_xm_header_drop_from_regmap_cache(struct cs_dsp_test *priv);
int cs_dsp_mock_xm_header_write_to_regmap(struct cs_dsp_mock_xm_header *header);
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 6cd8d1d..fc27b53 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -907,21 +907,6 @@ extern void fsnotify_wait_marks_destroyed(void);
/* Clear all of the marks of a group attached to a given object type */
extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group,
unsigned int obj_type);
-/* run all the marks in a group, and clear all of the vfsmount marks */
-static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
-{
- fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT);
-}
-/* run all the marks in a group, and clear all of the inode marks */
-static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group)
-{
- fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE);
-}
-/* run all the marks in a group, and clear all of the sn marks */
-static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group)
-{
- fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB);
-}
extern void fsnotify_get_mark(struct fsnotify_mark *mark);
extern void fsnotify_put_mark(struct fsnotify_mark *mark);
extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info);
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 6fa0a26..097be89 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -2,6 +2,11 @@
/*
* fwnode.h - Firmware device node object handle type definition.
*
+ * This header file provides low-level data types and definitions for firmware
+ * and device property providers. The respective API header files supplied by
+ * them should contain all of the requisite data types and definitions for end
+ * users, so including it directly should not be necessary.
+ *
* Copyright (C) 2015, Intel Corporation
* Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
*/
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index 45b651c..8adc8e9 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -31,6 +31,7 @@ struct gpio_descs {
#define GPIOD_FLAGS_BIT_DIR_OUT BIT(1)
#define GPIOD_FLAGS_BIT_DIR_VAL BIT(2)
#define GPIOD_FLAGS_BIT_OPEN_DRAIN BIT(3)
+/* GPIOD_FLAGS_BIT_NONEXCLUSIVE is DEPRECATED, don't use in new code. */
#define GPIOD_FLAGS_BIT_NONEXCLUSIVE BIT(4)
/**
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 1adcba3..1ef867b 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -345,7 +345,7 @@ static inline void hrtimer_update_function(struct hrtimer *timer,
if (WARN_ON_ONCE(!function))
return;
#endif
- timer->function = function;
+ ACCESS_PRIVATE(timer, function) = function;
}
/* Forward a hrtimer so it expires after now: */
diff --git a/include/linux/irqchip/irq-davinci-aintc.h b/include/linux/irqchip/irq-davinci-aintc.h
deleted file mode 100644
index ea4e087..0000000
--- a/include/linux/irqchip/irq-davinci-aintc.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (C) 2019 Texas Instruments
- */
-
-#ifndef _LINUX_IRQ_DAVINCI_AINTC_
-#define _LINUX_IRQ_DAVINCI_AINTC_
-
-#include <linux/ioport.h>
-
-/**
- * struct davinci_aintc_config - configuration data for davinci-aintc driver.
- *
- * @reg: register range to map
- * @num_irqs: number of HW interrupts supported by the controller
- * @prios: an array of size num_irqs containing priority settings for
- * each interrupt
- */
-struct davinci_aintc_config {
- struct resource reg;
- unsigned int num_irqs;
- u8 *prios;
-};
-
-void davinci_aintc_init(const struct davinci_aintc_config *config);
-
-#endif /* _LINUX_IRQ_DAVINCI_AINTC_ */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 5438a1b..291d49b 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2382,7 +2382,7 @@ static inline bool kvm_is_visible_memslot(struct kvm_memory_slot *memslot)
struct kvm_vcpu *kvm_get_running_vcpu(void);
struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
-#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
+#if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS)
bool kvm_arch_has_irq_bypass(void);
int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *,
struct irq_bypass_producer *);
diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h
index 1a0bc35..16a2ee4 100644
--- a/include/linux/local_lock.h
+++ b/include/linux/local_lock.h
@@ -52,44 +52,23 @@
__local_unlock_irqrestore(lock, flags)
/**
- * localtry_lock_init - Runtime initialize a lock instance
+ * local_lock_init - Runtime initialize a lock instance
*/
-#define localtry_lock_init(lock) __localtry_lock_init(lock)
+#define local_trylock_init(lock) __local_trylock_init(lock)
/**
- * localtry_lock - Acquire a per CPU local lock
- * @lock: The lock variable
- */
-#define localtry_lock(lock) __localtry_lock(lock)
-
-/**
- * localtry_lock_irq - Acquire a per CPU local lock and disable interrupts
- * @lock: The lock variable
- */
-#define localtry_lock_irq(lock) __localtry_lock_irq(lock)
-
-/**
- * localtry_lock_irqsave - Acquire a per CPU local lock, save and disable
- * interrupts
- * @lock: The lock variable
- * @flags: Storage for interrupt flags
- */
-#define localtry_lock_irqsave(lock, flags) \
- __localtry_lock_irqsave(lock, flags)
-
-/**
- * localtry_trylock - Try to acquire a per CPU local lock.
+ * local_trylock - Try to acquire a per CPU local lock
* @lock: The lock variable
*
* The function can be used in any context such as NMI or HARDIRQ. Due to
* locking constrains it will _always_ fail to acquire the lock in NMI or
* HARDIRQ context on PREEMPT_RT.
*/
-#define localtry_trylock(lock) __localtry_trylock(lock)
+#define local_trylock(lock) __local_trylock(lock)
/**
- * localtry_trylock_irqsave - Try to acquire a per CPU local lock, save and disable
- * interrupts if acquired
+ * local_trylock_irqsave - Try to acquire a per CPU local lock, save and disable
+ * interrupts if acquired
* @lock: The lock variable
* @flags: Storage for interrupt flags
*
@@ -97,29 +76,8 @@
* locking constrains it will _always_ fail to acquire the lock in NMI or
* HARDIRQ context on PREEMPT_RT.
*/
-#define localtry_trylock_irqsave(lock, flags) \
- __localtry_trylock_irqsave(lock, flags)
-
-/**
- * local_unlock - Release a per CPU local lock
- * @lock: The lock variable
- */
-#define localtry_unlock(lock) __localtry_unlock(lock)
-
-/**
- * local_unlock_irq - Release a per CPU local lock and enable interrupts
- * @lock: The lock variable
- */
-#define localtry_unlock_irq(lock) __localtry_unlock_irq(lock)
-
-/**
- * localtry_unlock_irqrestore - Release a per CPU local lock and restore
- * interrupt flags
- * @lock: The lock variable
- * @flags: Interrupt flags to restore
- */
-#define localtry_unlock_irqrestore(lock, flags) \
- __localtry_unlock_irqrestore(lock, flags)
+#define local_trylock_irqsave(lock, flags) \
+ __local_trylock_irqsave(lock, flags)
DEFINE_GUARD(local_lock, local_lock_t __percpu*,
local_lock(_T),
diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h
index 67bd13d1..8d5ac16 100644
--- a/include/linux/local_lock_internal.h
+++ b/include/linux/local_lock_internal.h
@@ -15,10 +15,11 @@ typedef struct {
#endif
} local_lock_t;
+/* local_trylock() and local_trylock_irqsave() only work with local_trylock_t */
typedef struct {
local_lock_t llock;
- unsigned int acquired;
-} localtry_lock_t;
+ u8 acquired;
+} local_trylock_t;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
# define LOCAL_LOCK_DEBUG_INIT(lockname) \
@@ -29,6 +30,9 @@ typedef struct {
}, \
.owner = NULL,
+# define LOCAL_TRYLOCK_DEBUG_INIT(lockname) \
+ .llock = { LOCAL_LOCK_DEBUG_INIT((lockname).llock) },
+
static inline void local_lock_acquire(local_lock_t *l)
{
lock_map_acquire(&l->dep_map);
@@ -56,6 +60,7 @@ static inline void local_lock_debug_init(local_lock_t *l)
}
#else /* CONFIG_DEBUG_LOCK_ALLOC */
# define LOCAL_LOCK_DEBUG_INIT(lockname)
+# define LOCAL_TRYLOCK_DEBUG_INIT(lockname)
static inline void local_lock_acquire(local_lock_t *l) { }
static inline void local_trylock_acquire(local_lock_t *l) { }
static inline void local_lock_release(local_lock_t *l) { }
@@ -63,7 +68,7 @@ static inline void local_lock_debug_init(local_lock_t *l) { }
#endif /* !CONFIG_DEBUG_LOCK_ALLOC */
#define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) }
-#define INIT_LOCALTRY_LOCK(lockname) { .llock = { LOCAL_LOCK_DEBUG_INIT(lockname.llock) }}
+#define INIT_LOCAL_TRYLOCK(lockname) { LOCAL_TRYLOCK_DEBUG_INIT(lockname) }
#define __local_lock_init(lock) \
do { \
@@ -76,6 +81,8 @@ do { \
local_lock_debug_init(lock); \
} while (0)
+#define __local_trylock_init(lock) __local_lock_init(lock.llock)
+
#define __spinlock_nested_bh_init(lock) \
do { \
static struct lock_class_key __key; \
@@ -87,39 +94,105 @@ do { \
local_lock_debug_init(lock); \
} while (0)
+#define __local_lock_acquire(lock) \
+ do { \
+ local_trylock_t *tl; \
+ local_lock_t *l; \
+ \
+ l = (local_lock_t *)this_cpu_ptr(lock); \
+ tl = (local_trylock_t *)l; \
+ _Generic((lock), \
+ __percpu local_trylock_t *: ({ \
+ lockdep_assert(tl->acquired == 0); \
+ WRITE_ONCE(tl->acquired, 1); \
+ }), \
+ __percpu local_lock_t *: (void)0); \
+ local_lock_acquire(l); \
+ } while (0)
+
#define __local_lock(lock) \
do { \
preempt_disable(); \
- local_lock_acquire(this_cpu_ptr(lock)); \
+ __local_lock_acquire(lock); \
} while (0)
#define __local_lock_irq(lock) \
do { \
local_irq_disable(); \
- local_lock_acquire(this_cpu_ptr(lock)); \
+ __local_lock_acquire(lock); \
} while (0)
#define __local_lock_irqsave(lock, flags) \
do { \
local_irq_save(flags); \
- local_lock_acquire(this_cpu_ptr(lock)); \
+ __local_lock_acquire(lock); \
+ } while (0)
+
+#define __local_trylock(lock) \
+ ({ \
+ local_trylock_t *tl; \
+ \
+ preempt_disable(); \
+ tl = this_cpu_ptr(lock); \
+ if (READ_ONCE(tl->acquired)) { \
+ preempt_enable(); \
+ tl = NULL; \
+ } else { \
+ WRITE_ONCE(tl->acquired, 1); \
+ local_trylock_acquire( \
+ (local_lock_t *)tl); \
+ } \
+ !!tl; \
+ })
+
+#define __local_trylock_irqsave(lock, flags) \
+ ({ \
+ local_trylock_t *tl; \
+ \
+ local_irq_save(flags); \
+ tl = this_cpu_ptr(lock); \
+ if (READ_ONCE(tl->acquired)) { \
+ local_irq_restore(flags); \
+ tl = NULL; \
+ } else { \
+ WRITE_ONCE(tl->acquired, 1); \
+ local_trylock_acquire( \
+ (local_lock_t *)tl); \
+ } \
+ !!tl; \
+ })
+
+#define __local_lock_release(lock) \
+ do { \
+ local_trylock_t *tl; \
+ local_lock_t *l; \
+ \
+ l = (local_lock_t *)this_cpu_ptr(lock); \
+ tl = (local_trylock_t *)l; \
+ local_lock_release(l); \
+ _Generic((lock), \
+ __percpu local_trylock_t *: ({ \
+ lockdep_assert(tl->acquired == 1); \
+ WRITE_ONCE(tl->acquired, 0); \
+ }), \
+ __percpu local_lock_t *: (void)0); \
} while (0)
#define __local_unlock(lock) \
do { \
- local_lock_release(this_cpu_ptr(lock)); \
+ __local_lock_release(lock); \
preempt_enable(); \
} while (0)
#define __local_unlock_irq(lock) \
do { \
- local_lock_release(this_cpu_ptr(lock)); \
+ __local_lock_release(lock); \
local_irq_enable(); \
} while (0)
#define __local_unlock_irqrestore(lock, flags) \
do { \
- local_lock_release(this_cpu_ptr(lock)); \
+ __local_lock_release(lock); \
local_irq_restore(flags); \
} while (0)
@@ -132,104 +205,6 @@ do { \
#define __local_unlock_nested_bh(lock) \
local_lock_release(this_cpu_ptr(lock))
-/* localtry_lock_t variants */
-
-#define __localtry_lock_init(lock) \
-do { \
- __local_lock_init(&(lock)->llock); \
- WRITE_ONCE((lock)->acquired, 0); \
-} while (0)
-
-#define __localtry_lock(lock) \
- do { \
- localtry_lock_t *lt; \
- preempt_disable(); \
- lt = this_cpu_ptr(lock); \
- local_lock_acquire(<->llock); \
- WRITE_ONCE(lt->acquired, 1); \
- } while (0)
-
-#define __localtry_lock_irq(lock) \
- do { \
- localtry_lock_t *lt; \
- local_irq_disable(); \
- lt = this_cpu_ptr(lock); \
- local_lock_acquire(<->llock); \
- WRITE_ONCE(lt->acquired, 1); \
- } while (0)
-
-#define __localtry_lock_irqsave(lock, flags) \
- do { \
- localtry_lock_t *lt; \
- local_irq_save(flags); \
- lt = this_cpu_ptr(lock); \
- local_lock_acquire(<->llock); \
- WRITE_ONCE(lt->acquired, 1); \
- } while (0)
-
-#define __localtry_trylock(lock) \
- ({ \
- localtry_lock_t *lt; \
- bool _ret; \
- \
- preempt_disable(); \
- lt = this_cpu_ptr(lock); \
- if (!READ_ONCE(lt->acquired)) { \
- WRITE_ONCE(lt->acquired, 1); \
- local_trylock_acquire(<->llock); \
- _ret = true; \
- } else { \
- _ret = false; \
- preempt_enable(); \
- } \
- _ret; \
- })
-
-#define __localtry_trylock_irqsave(lock, flags) \
- ({ \
- localtry_lock_t *lt; \
- bool _ret; \
- \
- local_irq_save(flags); \
- lt = this_cpu_ptr(lock); \
- if (!READ_ONCE(lt->acquired)) { \
- WRITE_ONCE(lt->acquired, 1); \
- local_trylock_acquire(<->llock); \
- _ret = true; \
- } else { \
- _ret = false; \
- local_irq_restore(flags); \
- } \
- _ret; \
- })
-
-#define __localtry_unlock(lock) \
- do { \
- localtry_lock_t *lt; \
- lt = this_cpu_ptr(lock); \
- WRITE_ONCE(lt->acquired, 0); \
- local_lock_release(<->llock); \
- preempt_enable(); \
- } while (0)
-
-#define __localtry_unlock_irq(lock) \
- do { \
- localtry_lock_t *lt; \
- lt = this_cpu_ptr(lock); \
- WRITE_ONCE(lt->acquired, 0); \
- local_lock_release(<->llock); \
- local_irq_enable(); \
- } while (0)
-
-#define __localtry_unlock_irqrestore(lock, flags) \
- do { \
- localtry_lock_t *lt; \
- lt = this_cpu_ptr(lock); \
- WRITE_ONCE(lt->acquired, 0); \
- local_lock_release(<->llock); \
- local_irq_restore(flags); \
- } while (0)
-
#else /* !CONFIG_PREEMPT_RT */
/*
@@ -237,16 +212,18 @@ do { \
* critical section while staying preemptible.
*/
typedef spinlock_t local_lock_t;
-typedef spinlock_t localtry_lock_t;
+typedef spinlock_t local_trylock_t;
#define INIT_LOCAL_LOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname))
-#define INIT_LOCALTRY_LOCK(lockname) INIT_LOCAL_LOCK(lockname)
+#define INIT_LOCAL_TRYLOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname))
#define __local_lock_init(l) \
do { \
local_spin_lock_init((l)); \
} while (0)
+#define __local_trylock_init(l) __local_lock_init(l)
+
#define __local_lock(__lock) \
do { \
migrate_disable(); \
@@ -283,17 +260,7 @@ do { \
spin_unlock(this_cpu_ptr((lock))); \
} while (0)
-/* localtry_lock_t variants */
-
-#define __localtry_lock_init(lock) __local_lock_init(lock)
-#define __localtry_lock(lock) __local_lock(lock)
-#define __localtry_lock_irq(lock) __local_lock(lock)
-#define __localtry_lock_irqsave(lock, flags) __local_lock_irqsave(lock, flags)
-#define __localtry_unlock(lock) __local_unlock(lock)
-#define __localtry_unlock_irq(lock) __local_unlock(lock)
-#define __localtry_unlock_irqrestore(lock, flags) __local_unlock_irqrestore(lock, flags)
-
-#define __localtry_trylock(lock) \
+#define __local_trylock(lock) \
({ \
int __locked; \
\
@@ -308,11 +275,11 @@ do { \
__locked; \
})
-#define __localtry_trylock_irqsave(lock, flags) \
+#define __local_trylock_irqsave(lock, flags) \
({ \
typecheck(unsigned long, flags); \
flags = 0; \
- __localtry_trylock(lock); \
+ __local_trylock(lock); \
})
#endif /* CONFIG_PREEMPT_RT */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b7f13f0..bf55206 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1218,6 +1218,23 @@ static inline unsigned int folio_order(const struct folio *folio)
return folio_large_order(folio);
}
+/**
+ * folio_reset_order - Reset the folio order and derived _nr_pages
+ * @folio: The folio.
+ *
+ * Reset the order and derived _nr_pages to 0. Must only be used in the
+ * process of splitting large folios.
+ */
+static inline void folio_reset_order(struct folio *folio)
+{
+ if (WARN_ON_ONCE(!folio_test_large(folio)))
+ return;
+ folio->_flags_1 &= ~0xffUL;
+#ifdef NR_PAGES_IN_LARGE_FOLIO
+ folio->_nr_pages = 0;
+#endif
+}
+
#include <linux/huge_mm.h>
/*
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 25e80b2..6ccec1b 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -967,6 +967,9 @@ struct zone {
#ifdef CONFIG_UNACCEPTED_MEMORY
/* Pages to be accepted. All pages on the list are MAX_PAGE_ORDER */
struct list_head unaccepted_pages;
+
+ /* To be called once the last page in the zone is accepted */
+ struct work_struct unaccepted_cleanup;
#endif
/* zone flags, see below */
@@ -1499,8 +1502,6 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
bool zone_watermark_ok(struct zone *z, unsigned int order,
unsigned long mark, int highest_zoneidx,
unsigned int alloc_flags);
-bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
- unsigned long mark, int highest_zoneidx);
/*
* Memory initialization context, use to differentiate memory added by
* the platform statically or via memory hotplug interface.
diff --git a/include/linux/module.h b/include/linux/module.h
index d94b196..b332911 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -162,6 +162,8 @@ extern void cleanup_module(void);
#define __INITRODATA_OR_MODULE __INITRODATA
#endif /*CONFIG_MODULES*/
+struct module_kobject *lookup_or_create_module_kobject(const char *name);
+
/* Generic info of form tag = "info" */
#define MODULE_INFO(tag, info) __MODULE_INFO(tag, tag, info)
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index 1e74895..311f145 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -67,7 +67,7 @@
SPI_MEM_OP_ADDR(2, addr, 1), \
SPI_MEM_OP_DUMMY(ndummy, 1), \
SPI_MEM_OP_DATA_IN(len, buf, 1), \
- __VA_OPT__(SPI_MEM_OP_MAX_FREQ(__VA_ARGS__)))
+ SPI_MEM_OP_MAX_FREQ(__VA_ARGS__ + 0))
#define SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(addr, ndummy, buf, len) \
SPI_MEM_OP(SPI_MEM_OP_CMD(0x0b, 1), \
diff --git a/include/linux/namei.h b/include/linux/namei.h
index e304217..bbaf55f 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -62,6 +62,7 @@ extern struct dentry *kern_path_create(int, const char *, struct path *, unsigne
extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int);
extern void done_path_create(struct path *, struct dentry *);
extern struct dentry *kern_path_locked(const char *, struct path *);
+extern struct dentry *kern_path_locked_negative(const char *, struct path *);
extern struct dentry *user_path_locked_at(int , const char __user *, struct path *);
int vfs_path_parent_lookup(struct filename *filename, unsigned int flags,
struct path *parent, struct qstr *last, int *type,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index cf3b644..2d11d01 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4429,6 +4429,7 @@ void linkwatch_fire_event(struct net_device *dev);
* pending work list (if queued).
*/
void linkwatch_sync_dev(struct net_device *dev);
+void __linkwatch_sync_dev(struct net_device *dev);
/**
* netif_carrier_ok - test if carrier present
@@ -4974,6 +4975,7 @@ void dev_set_rx_mode(struct net_device *dev);
int dev_set_promiscuity(struct net_device *dev, int inc);
int netif_set_allmulti(struct net_device *dev, int inc, bool notify);
int dev_set_allmulti(struct net_device *dev, int inc);
+void netif_state_change(struct net_device *dev);
void netdev_state_change(struct net_device *dev);
void __netdev_notify_peers(struct net_device *dev);
void netdev_notify_peers(struct net_device *dev);
diff --git a/include/linux/nfs.h b/include/linux/nfs.h
index 9ad727d..0906a0b 100644
--- a/include/linux/nfs.h
+++ b/include/linux/nfs.h
@@ -55,7 +55,6 @@ enum nfs3_stable_how {
NFS_INVALID_STABLE_HOW = -1
};
-#ifdef CONFIG_CRC32
/**
* nfs_fhandle_hash - calculate the crc32 hash for the filehandle
* @fh - pointer to filehandle
@@ -67,10 +66,4 @@ static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh)
{
return ~crc32_le(0xFFFFFFFF, &fh->data[0], fh->size);
}
-#else /* CONFIG_CRC32 */
-static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh)
-{
- return 0;
-}
-#endif /* CONFIG_CRC32 */
#endif /* _LINUX_NFS_H */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 0e8e3fd..51e2bd6 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -245,6 +245,8 @@ enum pci_dev_flags {
PCI_DEV_FLAGS_NO_RELAXED_ORDERING = (__force pci_dev_flags_t) (1 << 11),
/* Device does honor MSI masking despite saying otherwise */
PCI_DEV_FLAGS_HAS_MSI_MASKING = (__force pci_dev_flags_t) (1 << 12),
+ /* Device requires write to PCI_MSIX_ENTRY_DATA before any MSIX reads */
+ PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST = (__force pci_dev_flags_t) (1 << 13),
};
enum pci_irq_reroute_variant {
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 5a9bf15..0069ba6 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -823,7 +823,6 @@ struct perf_event {
struct irq_work pending_disable_irq;
struct callback_head pending_task;
unsigned int pending_work;
- struct rcuwait pending_work_wait;
atomic_t event_limit;
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index e2b705c..b50447e 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1511,8 +1511,9 @@ static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
/*
* track_pfn_copy is called when a VM_PFNMAP VMA is about to get the page
- * tables copied during copy_page_range(). On success, stores the pfn to be
- * passed to untrack_pfn_copy().
+ * tables copied during copy_page_range(). Will store the pfn to be
+ * passed to untrack_pfn_copy() only if there is something to be untracked.
+ * Callers should initialize the pfn to 0.
*/
static inline int track_pfn_copy(struct vm_area_struct *dst_vma,
struct vm_area_struct *src_vma, unsigned long *pfn)
@@ -1522,7 +1523,9 @@ static inline int track_pfn_copy(struct vm_area_struct *dst_vma,
/*
* untrack_pfn_copy is called when a VM_PFNMAP VMA failed to copy during
- * copy_page_range(), but after track_pfn_copy() was already called.
+ * copy_page_range(), but after track_pfn_copy() was already called. Can
+ * be called even if track_pfn_copy() did not actually track anything:
+ * handled internally.
*/
static inline void untrack_pfn_copy(struct vm_area_struct *dst_vma,
unsigned long pfn)
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 1f5773a..30659b6 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -361,23 +361,29 @@ int mac_finish(struct phylink_config *config, unsigned int mode,
phy_interface_t iface);
/**
- * mac_link_down() - take the link down
+ * mac_link_down() - notification that the link has gone down
* @config: a pointer to a &struct phylink_config.
* @mode: link autonegotiation mode
* @interface: link &typedef phy_interface_t mode
*
- * If @mode is not an in-band negotiation mode (as defined by
- * phylink_autoneg_inband()), force the link down and disable any
- * Energy Efficient Ethernet MAC configuration. Interface type
- * selection must be done in mac_config().
+ * Notifies the MAC that the link has gone down. This will not be called
+ * unless mac_link_up() has been previously called.
+ *
+ * The MAC should stop processing packets for transmission and reception.
+ * phylink will have called netif_carrier_off() to notify the networking
+ * stack that the link has gone down, so MAC drivers should not make this
+ * call.
+ *
+ * If @mode is %MLO_AN_INBAND, then this function must not prevent the
+ * link coming up.
*/
void mac_link_down(struct phylink_config *config, unsigned int mode,
phy_interface_t interface);
/**
- * mac_link_up() - allow the link to come up
+ * mac_link_up() - notification that the link has come up
* @config: a pointer to a &struct phylink_config.
- * @phy: any attached phy
+ * @phy: any attached phy (deprecated - please use LPI interfaces)
* @mode: link autonegotiation mode
* @interface: link &typedef phy_interface_t mode
* @speed: link speed
@@ -385,7 +391,10 @@ void mac_link_down(struct phylink_config *config, unsigned int mode,
* @tx_pause: link transmit pause enablement status
* @rx_pause: link receive pause enablement status
*
- * Configure the MAC for an established link.
+ * Notifies the MAC that the link has come up, and the parameters of the
+ * link as seen from the MACs point of view. If mac_link_up() has been
+ * called previously, there will be an intervening call to mac_link_down()
+ * before this method will be subsequently called.
*
* @speed, @duplex, @tx_pause and @rx_pause indicate the finalised link
* settings, and should be used to configure the MAC block appropriately
@@ -397,9 +406,9 @@ void mac_link_down(struct phylink_config *config, unsigned int mode,
* that the user wishes to override the pause settings, and this should
* be allowed when considering the implementation of this method.
*
- * If in-band negotiation mode is disabled, allow the link to come up. If
- * @phy is non-%NULL, configure Energy Efficient Ethernet by calling
- * phy_init_eee() and perform appropriate MAC configuration for EEE.
+ * Once configured, the MAC may begin to process packets for transmission
+ * and reception.
+ *
* Interface type selection must be done in mac_config().
*/
void mac_link_up(struct phylink_config *config, struct phy_device *phy,
diff --git a/include/linux/platform_data/x86/intel_pmc_ipc.h b/include/linux/platform_data/x86/intel_pmc_ipc.h
index 6e603a8..1d34435 100644
--- a/include/linux/platform_data/x86/intel_pmc_ipc.h
+++ b/include/linux/platform_data/x86/intel_pmc_ipc.h
@@ -36,6 +36,7 @@ struct pmc_ipc_rbuf {
*/
static inline int intel_pmc_ipc(struct pmc_ipc_cmd *ipc_cmd, struct pmc_ipc_rbuf *rbuf)
{
+#ifdef CONFIG_ACPI
struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
union acpi_object params[PMC_IPCS_PARAM_COUNT] = {
{.type = ACPI_TYPE_INTEGER,},
@@ -89,6 +90,9 @@ static inline int intel_pmc_ipc(struct pmc_ipc_cmd *ipc_cmd, struct pmc_ipc_rbuf
}
return 0;
+#else
+ return -ENODEV;
+#endif /* CONFIG_ACPI */
}
#endif /* INTEL_PMC_IPC_H */
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index ccaaf4c..ea39dd2 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -240,6 +240,6 @@ rtnl_notify_needed(const struct net *net, u16 nlflags, u32 group)
return (nlflags & NLM_F_ECHO) || rtnl_has_listeners(net, group);
}
-void netdev_set_operstate(struct net_device *dev, int newstate);
+void netif_set_operstate(struct net_device *dev, int newstate);
#endif /* __LINUX_RTNETLINK_H */
diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index e39d4d5..785048a 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -51,7 +51,7 @@ struct tk_read_base {
* @offs_real: Offset clock monotonic -> clock realtime
* @offs_boot: Offset clock monotonic -> clock boottime
* @offs_tai: Offset clock monotonic -> clock tai
- * @tai_offset: The current UTC to TAI offset in seconds
+ * @coarse_nsec: The nanoseconds part for coarse time getters
* @tkr_raw: The readout base structure for CLOCK_MONOTONIC_RAW
* @raw_sec: CLOCK_MONOTONIC_RAW time in seconds
* @clock_was_set_seq: The sequence number of clock was set events
@@ -76,6 +76,7 @@ struct tk_read_base {
* ntp shifted nano seconds.
* @ntp_err_mult: Multiplication factor for scaled math conversion
* @skip_second_overflow: Flag used to avoid updating NTP twice with same second
+ * @tai_offset: The current UTC to TAI offset in seconds
*
* Note: For timespec(64) based interfaces wall_to_monotonic is what
* we need to add to xtime (or xtime corrected for sub jiffy times)
@@ -100,7 +101,7 @@ struct tk_read_base {
* which results in the following cacheline layout:
*
* 0: seqcount, tkr_mono
- * 1: xtime_sec ... tai_offset
+ * 1: xtime_sec ... coarse_nsec
* 2: tkr_raw, raw_sec
* 3,4: Internal variables
*
@@ -121,7 +122,7 @@ struct timekeeper {
ktime_t offs_real;
ktime_t offs_boot;
ktime_t offs_tai;
- s32 tai_offset;
+ u32 coarse_nsec;
/* Cacheline 2: */
struct tk_read_base tkr_raw;
@@ -144,6 +145,7 @@ struct timekeeper {
u32 ntp_error_shift;
u32 ntp_err_mult;
u32 skip_second_overflow;
+ s32 tai_offset;
};
#ifdef CONFIG_GENERIC_TIME_VSYSCALL
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 4d16c13..64cb4b0 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -220,6 +220,8 @@ size_t virtio_max_dma_size(const struct virtio_device *vdev);
* occurs.
* @reset_done: optional function to call after transport specific reset
* operation has finished.
+ * @shutdown: synchronize with the device on shutdown. If provided, replaces
+ * the virtio core implementation.
*/
struct virtio_driver {
struct device_driver driver;
@@ -237,6 +239,7 @@ struct virtio_driver {
int (*restore)(struct virtio_device *dev);
int (*reset_prepare)(struct virtio_device *dev);
int (*reset_done)(struct virtio_device *dev);
+ void (*shutdown)(struct virtio_device *dev);
};
#define drv_to_virtio(__drv) container_of_const(__drv, struct virtio_driver, driver)
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 31e9ffd..5ca8d4dd 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -61,6 +61,7 @@ struct vm_struct {
unsigned int nr_pages;
phys_addr_t phys_addr;
const void *caller;
+ unsigned long requested_size;
};
struct vmap_area {
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index a8586c3..7979920 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1931,6 +1931,8 @@ struct hci_cp_le_pa_create_sync {
__u8 sync_cte_type;
} __packed;
+#define HCI_OP_LE_PA_CREATE_SYNC_CANCEL 0x2045
+
#define HCI_OP_LE_PA_TERM_SYNC 0x2046
struct hci_cp_le_pa_term_sync {
__le16 handle;
@@ -2830,7 +2832,7 @@ struct hci_evt_le_create_big_complete {
__le16 bis_handle[];
} __packed;
-#define HCI_EVT_LE_BIG_SYNC_ESTABILISHED 0x1d
+#define HCI_EVT_LE_BIG_SYNC_ESTABLISHED 0x1d
struct hci_evt_le_big_sync_estabilished {
__u8 status;
__u8 handle;
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 5115da3..522d837 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1113,10 +1113,8 @@ static inline struct hci_conn *hci_conn_hash_lookup_bis(struct hci_dev *hdev,
return NULL;
}
-static inline struct hci_conn *hci_conn_hash_lookup_sid(struct hci_dev *hdev,
- __u8 sid,
- bdaddr_t *dst,
- __u8 dst_type)
+static inline struct hci_conn *
+hci_conn_hash_lookup_create_pa_sync(struct hci_dev *hdev)
{
struct hci_conn_hash *h = &hdev->conn_hash;
struct hci_conn *c;
@@ -1124,8 +1122,10 @@ static inline struct hci_conn *hci_conn_hash_lookup_sid(struct hci_dev *hdev,
rcu_read_lock();
list_for_each_entry_rcu(c, &h->list, list) {
- if (c->type != ISO_LINK || bacmp(&c->dst, dst) ||
- c->dst_type != dst_type || c->sid != sid)
+ if (c->type != ISO_LINK)
+ continue;
+
+ if (!test_bit(HCI_CONN_CREATE_PA_SYNC, &c->flags))
continue;
rcu_read_unlock();
@@ -1524,8 +1524,6 @@ bool hci_setup_sync(struct hci_conn *conn, __u16 handle);
void hci_sco_setup(struct hci_conn *conn, __u8 status);
bool hci_iso_setup_path(struct hci_conn *conn);
int hci_le_create_cis_pending(struct hci_dev *hdev);
-int hci_pa_create_sync_pending(struct hci_dev *hdev);
-int hci_le_big_create_sync_pending(struct hci_dev *hdev);
int hci_conn_check_create_cis(struct hci_conn *conn);
struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst,
@@ -1566,9 +1564,9 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst,
__u8 data_len, __u8 *data);
struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst,
__u8 dst_type, __u8 sid, struct bt_iso_qos *qos);
-int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon,
- struct bt_iso_qos *qos,
- __u16 sync_handle, __u8 num_bis, __u8 bis[]);
+int hci_conn_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon,
+ struct bt_iso_qos *qos, __u16 sync_handle,
+ __u8 num_bis, __u8 bis[]);
int hci_conn_check_link_mode(struct hci_conn *conn);
int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level);
int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type,
diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h
index 7e2cf0c..72558c8 100644
--- a/include/net/bluetooth/hci_sync.h
+++ b/include/net/bluetooth/hci_sync.h
@@ -185,3 +185,6 @@ int hci_connect_le_sync(struct hci_dev *hdev, struct hci_conn *conn);
int hci_cancel_connect_sync(struct hci_dev *hdev, struct hci_conn *conn);
int hci_le_conn_update_sync(struct hci_dev *hdev, struct hci_conn *conn,
struct hci_conn_params *params);
+
+int hci_connect_pa_sync(struct hci_dev *hdev, struct hci_conn *conn);
+int hci_connect_big_sync(struct hci_dev *hdev, struct hci_conn *conn);
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 5927910..6e68e35 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -45,6 +45,8 @@ struct fib_rule {
struct fib_rule_port_range dport_range;
u16 sport_mask;
u16 dport_mask;
+ u8 iif_is_l3_master;
+ u8 oif_is_l3_master;
struct rcu_head rcu;
};
diff --git a/include/net/flow.h b/include/net/flow.h
index 335bbc5..2a3f0c4 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -38,6 +38,7 @@ struct flowi_common {
__u8 flowic_flags;
#define FLOWI_FLAG_ANYSRC 0x01
#define FLOWI_FLAG_KNOWN_NH 0x02
+#define FLOWI_FLAG_L3MDEV_OIF 0x04
__u32 flowic_secid;
kuid_t flowic_uid;
__u32 flowic_multipath_hash;
diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h
index f7fe796..1eb8dad 100644
--- a/include/net/l3mdev.h
+++ b/include/net/l3mdev.h
@@ -59,6 +59,20 @@ int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net,
int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
struct fib_lookup_arg *arg);
+static inline
+bool l3mdev_fib_rule_iif_match(const struct flowi *fl, int iifindex)
+{
+ return !(fl->flowi_flags & FLOWI_FLAG_L3MDEV_OIF) &&
+ fl->flowi_l3mdev == iifindex;
+}
+
+static inline
+bool l3mdev_fib_rule_oif_match(const struct flowi *fl, int oifindex)
+{
+ return fl->flowi_flags & FLOWI_FLAG_L3MDEV_OIF &&
+ fl->flowi_l3mdev == oifindex;
+}
+
void l3mdev_update_flow(struct net *net, struct flowi *fl);
int l3mdev_master_ifindex_rcu(const struct net_device *dev);
@@ -327,6 +341,19 @@ int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
{
return 1;
}
+
+static inline
+bool l3mdev_fib_rule_iif_match(const struct flowi *fl, int iifindex)
+{
+ return false;
+}
+
+static inline
+bool l3mdev_fib_rule_oif_match(const struct flowi *fl, int oifindex)
+{
+ return false;
+}
+
static inline
void l3mdev_update_flow(struct net *net, struct flowi *fl)
{
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 31248cf..dcd288f 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -775,6 +775,7 @@ struct sctp_transport {
/* Reference counting. */
refcount_t refcnt;
+ __u32 dead:1,
/* RTO-Pending : A flag used to track if one of the DATA
* chunks sent to this address is currently being
* used to compute a RTT. If this flag is 0,
@@ -784,7 +785,7 @@ struct sctp_transport {
* calculation completes (i.e. the DATA chunk
* is SACK'd) clear this flag.
*/
- __u32 rto_pending:1,
+ rto_pending:1,
/*
* hb_sent : a flag that signals that we have a pending
diff --git a/include/net/sock.h b/include/net/sock.h
index 8daf1b3..694f954 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -339,6 +339,8 @@ struct sk_filter;
* @sk_txtime_unused: unused txtime flags
* @ns_tracker: tracker for netns reference
* @sk_user_frags: xarray of pages the user is holding a reference on.
+ * @sk_owner: reference to the real owner of the socket that calls
+ * sock_lock_init_class_and_name().
*/
struct sock {
/*
@@ -547,6 +549,10 @@ struct sock {
struct rcu_head sk_rcu;
netns_tracker ns_tracker;
struct xarray sk_user_frags;
+
+#if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES)
+ struct module *sk_owner;
+#endif
};
struct sock_bh_locked {
@@ -1583,6 +1589,35 @@ static inline void sk_mem_uncharge(struct sock *sk, int size)
sk_mem_reclaim(sk);
}
+#if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES)
+static inline void sk_owner_set(struct sock *sk, struct module *owner)
+{
+ __module_get(owner);
+ sk->sk_owner = owner;
+}
+
+static inline void sk_owner_clear(struct sock *sk)
+{
+ sk->sk_owner = NULL;
+}
+
+static inline void sk_owner_put(struct sock *sk)
+{
+ module_put(sk->sk_owner);
+}
+#else
+static inline void sk_owner_set(struct sock *sk, struct module *owner)
+{
+}
+
+static inline void sk_owner_clear(struct sock *sk)
+{
+}
+
+static inline void sk_owner_put(struct sock *sk)
+{
+}
+#endif
/*
* Macro so as to not evaluate some arguments when
* lockdep is not enabled.
@@ -1592,13 +1627,14 @@ static inline void sk_mem_uncharge(struct sock *sk, int size)
*/
#define sock_lock_init_class_and_name(sk, sname, skey, name, key) \
do { \
+ sk_owner_set(sk, THIS_MODULE); \
sk->sk_lock.owned = 0; \
init_waitqueue_head(&sk->sk_lock.wq); \
spin_lock_init(&(sk)->sk_lock.slock); \
debug_check_no_locks_freed((void *)&(sk)->sk_lock, \
- sizeof((sk)->sk_lock)); \
+ sizeof((sk)->sk_lock)); \
lockdep_set_class_and_name(&(sk)->sk_lock.slock, \
- (skey), (sname)); \
+ (skey), (sname)); \
lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0); \
} while (0)
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index a58ae75..e8bd6dd 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -71,9 +71,6 @@ struct xdp_sock {
*/
u32 tx_budget_spent;
- /* Protects generic receive. */
- spinlock_t rx_lock;
-
/* Statistics */
u64 rx_dropped;
u64 rx_queue_full;
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 39365fd..06ab2a3 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -236,7 +236,6 @@ struct xfrm_state {
/* Data for encapsulator */
struct xfrm_encap_tmpl *encap;
- struct sock __rcu *encap_sk;
/* NAT keepalive */
u32 nat_keepalive_interval; /* seconds */
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 1dcd4d7..cac56e6 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -53,6 +53,8 @@ struct xsk_buff_pool {
refcount_t users;
struct xdp_umem *umem;
struct work_struct work;
+ /* Protects generic receive in shared and non-shared umem mode. */
+ spinlock_t rx_lock;
struct list_head free_list;
struct list_head xskb_list;
u32 heads_cnt;
@@ -238,8 +240,8 @@ static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb,
return orig_addr;
offset = xskb->xdp.data - xskb->xdp.data_hard_start;
- orig_addr -= offset;
offset += pool->headroom;
+ orig_addr -= offset;
return orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
}
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index d42eae6..9013537 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -4790,7 +4790,14 @@ void roce_del_all_netdev_gids(struct ib_device *ib_dev,
struct ib_ucontext *ib_uverbs_get_ucontext_file(struct ib_uverbs_file *ufile);
+#if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
int uverbs_destroy_def_handler(struct uverbs_attr_bundle *attrs);
+#else
+static inline int uverbs_destroy_def_handler(struct uverbs_attr_bundle *attrs)
+{
+ return 0;
+}
+#endif
struct net_device *rdma_alloc_netdev(struct ib_device *device, u32 port_num,
enum rdma_netdev_t type, const char *name,
diff --git a/include/sound/soc_sdw_utils.h b/include/sound/soc_sdw_utils.h
index 36a4a1e..d8bd5d3 100644
--- a/include/sound/soc_sdw_utils.h
+++ b/include/sound/soc_sdw_utils.h
@@ -226,6 +226,7 @@ int asoc_sdw_cs_amp_init(struct snd_soc_card *card,
bool playback);
int asoc_sdw_cs_spk_feedback_rtd_init(struct snd_soc_pcm_runtime *rtd,
struct snd_soc_dai *dai);
+int asoc_sdw_cs35l56_volume_limit(struct snd_soc_card *card, const char *name_prefix);
/* MAXIM codec support */
int asoc_sdw_maxim_init(struct snd_soc_card *card,
diff --git a/include/sound/ump_convert.h b/include/sound/ump_convert.h
index d099ae2..682499b 100644
--- a/include/sound/ump_convert.h
+++ b/include/sound/ump_convert.h
@@ -19,7 +19,7 @@ struct ump_cvt_to_ump_bank {
/* context for converting from MIDI1 byte stream to UMP packet */
struct ump_cvt_to_ump {
/* MIDI1 intermediate buffer */
- unsigned char buf[4];
+ unsigned char buf[6]; /* up to 6 bytes for SysEx */
int len;
int cmd_bytes;
diff --git a/include/uapi/cxl/features.h b/include/uapi/cxl/features.h
index d6db898..490606d 100644
--- a/include/uapi/cxl/features.h
+++ b/include/uapi/cxl/features.h
@@ -8,10 +8,19 @@
#define _UAPI_CXL_FEATURES_H_
#include <linux/types.h>
-#ifndef __KERNEL__
-#include <uuid/uuid.h>
-#else
+
+typedef unsigned char __uapi_uuid_t[16];
+
+#ifdef __KERNEL__
#include <linux/uuid.h>
+/*
+ * Note, __uapi_uuid_t is 1-byte aligned on modern compilers and 4-byte
+ * aligned on others. Ensure that __uapi_uuid_t in a struct is placed at
+ * a 4-byte aligned offset, or the structure is packed, to ensure
+ * consistent padding.
+ */
+static_assert(sizeof(__uapi_uuid_t) == sizeof(uuid_t));
+#define __uapi_uuid_t uuid_t
#endif
/*
@@ -60,7 +69,7 @@ struct cxl_mbox_get_sup_feats_in {
* Get Supported Features Supported Feature Entry
*/
struct cxl_feat_entry {
- uuid_t uuid;
+ __uapi_uuid_t uuid;
__le16 id;
__le16 get_feat_size;
__le16 set_feat_size;
@@ -110,7 +119,7 @@ struct cxl_mbox_get_sup_feats_out {
* CXL spec r3.2 section 8.2.9.6.2 Table 8-99
*/
struct cxl_mbox_get_feat_in {
- uuid_t uuid;
+ __uapi_uuid_t uuid;
__le16 offset;
__le16 count;
__u8 selection;
@@ -143,7 +152,7 @@ enum cxl_get_feat_selection {
*/
struct cxl_mbox_set_feat_in {
__struct_group(cxl_mbox_set_feat_hdr, hdr, /* no attrs */,
- uuid_t uuid;
+ __uapi_uuid_t uuid;
__le32 flags;
__le16 offset;
__u8 version;
diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h
index fe24c34..30c8dad 100644
--- a/include/uapi/linux/ethtool_netlink_generated.h
+++ b/include/uapi/linux/ethtool_netlink_generated.h
@@ -31,11 +31,6 @@ enum ethtool_header_flags {
ETHTOOL_FLAG_STATS = 4,
};
-enum {
- ETHTOOL_PHY_UPSTREAM_TYPE_MAC,
- ETHTOOL_PHY_UPSTREAM_TYPE_PHY,
-};
-
enum ethtool_tcp_data_split {
ETHTOOL_TCP_DATA_SPLIT_UNKNOWN,
ETHTOOL_TCP_DATA_SPLIT_DISABLED,
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index ed2beb4..8f1fc12 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -1010,7 +1010,9 @@ struct io_uring_zcrx_ifq_reg {
__u64 region_ptr; /* struct io_uring_region_desc * */
struct io_uring_zcrx_offsets offsets;
- __u64 __resv[4];
+ __u32 zcrx_id;
+ __u32 __resv2;
+ __u64 __resv[3];
};
#ifdef __cplusplus
diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h
index d9d0cb8..f030adc 100644
--- a/include/uapi/linux/landlock.h
+++ b/include/uapi/linux/landlock.h
@@ -53,43 +53,70 @@ struct landlock_ruleset_attr {
__u64 scoped;
};
-/*
- * sys_landlock_create_ruleset() flags:
+/**
+ * DOC: landlock_create_ruleset_flags
*
- * - %LANDLOCK_CREATE_RULESET_VERSION: Get the highest supported Landlock ABI
- * version.
- * - %LANDLOCK_CREATE_RULESET_ERRATA: Get a bitmask of fixed issues.
+ * **Flags**
+ *
+ * %LANDLOCK_CREATE_RULESET_VERSION
+ * Get the highest supported Landlock ABI version (starting at 1).
+ *
+ * %LANDLOCK_CREATE_RULESET_ERRATA
+ * Get a bitmask of fixed issues for the current Landlock ABI version.
*/
/* clang-format off */
#define LANDLOCK_CREATE_RULESET_VERSION (1U << 0)
#define LANDLOCK_CREATE_RULESET_ERRATA (1U << 1)
/* clang-format on */
-/*
- * sys_landlock_restrict_self() flags:
+/**
+ * DOC: landlock_restrict_self_flags
*
- * - %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF: Do not create any log related to the
- * enforced restrictions. This should only be set by tools launching unknown
- * or untrusted programs (e.g. a sandbox tool, container runtime, system
- * service manager). Because programs sandboxing themselves should fix any
- * denied access, they should not set this flag to be aware of potential
- * issues reported by system's logs (i.e. audit).
- * - %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON: Explicitly ask to continue
- * logging denied access requests even after an :manpage:`execve(2)` call.
- * This flag should only be set if all the programs than can legitimately be
- * executed will not try to request a denied access (which could spam audit
- * logs).
- * - %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF: Do not create any log related
- * to the enforced restrictions coming from future nested domains created by
- * the caller or its descendants. This should only be set according to a
- * runtime configuration (i.e. not hardcoded) by programs launching other
- * unknown or untrusted programs that may create their own Landlock domains
- * and spam logs. The main use case is for container runtimes to enable users
- * to mute buggy sandboxed programs for a specific container image. Other use
- * cases include sandboxer tools and init systems. Unlike
- * %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF,
- * %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF does not impact the requested
- * restriction (if any) but only the future nested domains.
+ * **Flags**
+ *
+ * By default, denied accesses originating from programs that sandbox themselves
+ * are logged via the audit subsystem. Such events typically indicate unexpected
+ * behavior, such as bugs or exploitation attempts. However, to avoid excessive
+ * logging, access requests denied by a domain not created by the originating
+ * program are not logged by default. The rationale is that programs should know
+ * their own behavior, but not necessarily the behavior of other programs. This
+ * default configuration is suitable for most programs that sandbox themselves.
+ * For specific use cases, the following flags allow programs to modify this
+ * default logging behavior.
+ *
+ * The %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF and
+ * %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON flags apply to the newly created
+ * Landlock domain.
+ *
+ * %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF
+ * Disables logging of denied accesses originating from the thread creating
+ * the Landlock domain, as well as its children, as long as they continue
+ * running the same executable code (i.e., without an intervening
+ * :manpage:`execve(2)` call). This is intended for programs that execute
+ * unknown code without invoking :manpage:`execve(2)`, such as script
+ * interpreters. Programs that only sandbox themselves should not set this
+ * flag, so users can be notified of unauthorized access attempts via system
+ * logs.
+ *
+ * %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON
+ * Enables logging of denied accesses after an :manpage:`execve(2)` call,
+ * providing visibility into unauthorized access attempts by newly executed
+ * programs within the created Landlock domain. This flag is recommended
+ * only when all potential executables in the domain are expected to comply
+ * with the access restrictions, as excessive audit log entries could make
+ * it more difficult to identify critical events.
+ *
+ * %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF
+ * Disables logging of denied accesses originating from nested Landlock
+ * domains created by the caller or its descendants. This flag should be set
+ * according to runtime configuration, not hardcoded, to avoid suppressing
+ * important security events. It is useful for container runtimes or
+ * sandboxing tools that may launch programs which themselves create
+ * Landlock domains and could otherwise generate excessive logs. Unlike
+ * ``LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF``, this flag only affects
+ * future nested domains, not the one being created. It can also be used
+ * with a @ruleset_fd value of -1 to mute subdomain logs without creating a
+ * domain.
*/
/* clang-format off */
#define LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF (1U << 0)
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index b95dd84..d4b3e2a 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -28,10 +28,10 @@
/* Set current process as the (exclusive) owner of this file descriptor. This
* must be called before any other vhost command. Further calls to
- * VHOST_OWNER_SET fail until VHOST_OWNER_RESET is called. */
+ * VHOST_SET_OWNER fail until VHOST_RESET_OWNER is called. */
#define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01)
/* Give up ownership, and reset the device to default values.
- * Allows subsequent call to VHOST_OWNER_SET to succeed. */
+ * Allows subsequent call to VHOST_SET_OWNER to succeed. */
#define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
/* Set up/modify memory layout */
diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 8549d45..c691ac2 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -246,6 +246,7 @@ struct virtio_pci_cfg_cap {
#define VIRTIO_ADMIN_CMD_LIST_USE 0x1
/* Admin command group type. */
+#define VIRTIO_ADMIN_GROUP_TYPE_SELF 0x0
#define VIRTIO_ADMIN_GROUP_TYPE_SRIOV 0x1
/* Transitional device admin command. */
diff --git a/include/ufs/ufs.h b/include/ufs/ufs.h
index 8a24ed5..1c47136 100644
--- a/include/ufs/ufs.h
+++ b/include/ufs/ufs.h
@@ -180,7 +180,8 @@ enum attr_idn {
QUERY_ATTR_IDN_AVAIL_WB_BUFF_SIZE = 0x1D,
QUERY_ATTR_IDN_WB_BUFF_LIFE_TIME_EST = 0x1E,
QUERY_ATTR_IDN_CURR_WB_BUFF_SIZE = 0x1F,
- QUERY_ATTR_IDN_TIMESTAMP = 0x30
+ QUERY_ATTR_IDN_TIMESTAMP = 0x30,
+ QUERY_ATTR_IDN_DEV_LVL_EXCEPTION_ID = 0x34,
};
/* Descriptor idn for Query requests */
@@ -390,6 +391,7 @@ enum {
UFS_DEV_EXT_TEMP_NOTIF = BIT(6),
UFS_DEV_HPB_SUPPORT = BIT(7),
UFS_DEV_WRITE_BOOSTER_SUP = BIT(8),
+ UFS_DEV_LVL_EXCEPTION_SUP = BIT(12),
};
#define UFS_DEV_HPB_SUPPORT_VERSION 0x310
@@ -419,6 +421,7 @@ enum {
MASK_EE_TOO_LOW_TEMP = BIT(4),
MASK_EE_WRITEBOOSTER_EVENT = BIT(5),
MASK_EE_PERFORMANCE_THROTTLING = BIT(6),
+ MASK_EE_DEV_LVL_EXCEPTION = BIT(7),
MASK_EE_HEALTH_CRITICAL = BIT(9),
};
#define MASK_EE_URGENT_TEMP (MASK_EE_TOO_HIGH_TEMP | MASK_EE_TOO_LOW_TEMP)
diff --git a/include/ufs/ufs_quirks.h b/include/ufs/ufs_quirks.h
index 41ff44d..f52de5e 100644
--- a/include/ufs/ufs_quirks.h
+++ b/include/ufs/ufs_quirks.h
@@ -107,4 +107,10 @@ struct ufs_dev_quirk {
*/
#define UFS_DEVICE_QUIRK_DELAY_AFTER_LPM (1 << 11)
+/*
+ * Some ufs devices may need more time to be in hibern8 before exiting.
+ * Enable this quirk to give it an additional 100us.
+ */
+#define UFS_DEVICE_QUIRK_PA_HIBER8TIME (1 << 12)
+
#endif /* UFS_QUIRKS_H_ */
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index e3909cc..e928ed0 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -246,7 +246,7 @@ struct ufs_query {
struct ufs_dev_cmd {
enum dev_cmd_type type;
struct mutex lock;
- struct completion *complete;
+ struct completion complete;
struct ufs_query query;
};
@@ -968,6 +968,9 @@ enum ufshcd_mcq_opr {
* @pm_qos_req: PM QoS request handle
* @pm_qos_enabled: flag to check if pm qos is enabled
* @critical_health_count: count of critical health exceptions
+ * @dev_lvl_exception_count: count of device level exceptions since last reset
+ * @dev_lvl_exception_id: vendor specific information about the
+ * device level exception event.
*/
struct ufs_hba {
void __iomem *mmio_base;
@@ -1138,6 +1141,8 @@ struct ufs_hba {
bool pm_qos_enabled;
int critical_health_count;
+ atomic_t dev_lvl_exception_count;
+ u64 dev_lvl_exception_id;
};
/**
diff --git a/include/vdso/unaligned.h b/include/vdso/unaligned.h
index eee3d2a..ff0c06b 100644
--- a/include/vdso/unaligned.h
+++ b/include/vdso/unaligned.h
@@ -2,14 +2,14 @@
#ifndef __VDSO_UNALIGNED_H
#define __VDSO_UNALIGNED_H
-#define __get_unaligned_t(type, ptr) ({ \
- const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \
- __pptr->x; \
+#define __get_unaligned_t(type, ptr) ({ \
+ const struct { type x; } __packed * __get_pptr = (typeof(__get_pptr))(ptr); \
+ __get_pptr->x; \
})
-#define __put_unaligned_t(type, val, ptr) do { \
- struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \
- __pptr->x = (val); \
+#define __put_unaligned_t(type, val, ptr) do { \
+ struct { type x; } __packed * __put_pptr = (typeof(__put_pptr))(ptr); \
+ __put_pptr->x = (val); \
} while (0)
#endif /* __VDSO_UNALIGNED_H */
diff --git a/init/Kconfig b/init/Kconfig
index dd2ea3b..63f5974 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1555,6 +1555,16 @@
the unaligned access emulation.
see arch/parisc/kernel/unaligned.c for reference
+config SYSFS_SYSCALL
+ bool "Sysfs syscall support"
+ default n
+ help
+ sys_sysfs is an obsolete system call no longer supported in libc.
+ Note that disabling this option is more secure but might break
+ compatibility with some systems.
+
+ If unsure say N here.
+
config HAVE_PCSPKR_PLATFORM
bool
@@ -1599,16 +1609,6 @@
If unsure, leave the default option here.
-config SYSFS_SYSCALL
- bool "Sysfs syscall support" if EXPERT
- default y
- help
- sys_sysfs is an obsolete system call no longer supported in libc.
- Note that disabling this option is more secure but might break
- compatibility with some systems.
-
- If unsure say Y here.
-
config FHANDLE
bool "open by fhandle syscalls" if EXPERT
select EXPORTFS
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index c6209fe..a2b256e 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -872,10 +872,15 @@ bool io_req_post_cqe(struct io_kiocb *req, s32 res, u32 cflags)
lockdep_assert(!io_wq_current_is_worker());
lockdep_assert_held(&ctx->uring_lock);
- __io_cq_lock(ctx);
- posted = io_fill_cqe_aux(ctx, req->cqe.user_data, res, cflags);
+ if (!ctx->lockless_cq) {
+ spin_lock(&ctx->completion_lock);
+ posted = io_fill_cqe_aux(ctx, req->cqe.user_data, res, cflags);
+ spin_unlock(&ctx->completion_lock);
+ } else {
+ posted = io_fill_cqe_aux(ctx, req->cqe.user_data, res, cflags);
+ }
+
ctx->submit_state.cq_flush = true;
- __io_cq_unlock_post(ctx);
return posted;
}
@@ -1078,21 +1083,22 @@ static __cold void __io_fallback_tw(struct llist_node *node, bool sync)
while (node) {
req = container_of(node, struct io_kiocb, io_task_work.node);
node = node->next;
- if (sync && last_ctx != req->ctx) {
+ if (last_ctx != req->ctx) {
if (last_ctx) {
- flush_delayed_work(&last_ctx->fallback_work);
+ if (sync)
+ flush_delayed_work(&last_ctx->fallback_work);
percpu_ref_put(&last_ctx->refs);
}
last_ctx = req->ctx;
percpu_ref_get(&last_ctx->refs);
}
- if (llist_add(&req->io_task_work.node,
- &req->ctx->fallback_llist))
- schedule_delayed_work(&req->ctx->fallback_work, 1);
+ if (llist_add(&req->io_task_work.node, &last_ctx->fallback_llist))
+ schedule_delayed_work(&last_ctx->fallback_work, 1);
}
if (last_ctx) {
- flush_delayed_work(&last_ctx->fallback_work);
+ if (sync)
+ flush_delayed_work(&last_ctx->fallback_work);
percpu_ref_put(&last_ctx->refs);
}
}
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index 0981092..953d5e7 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -504,6 +504,8 @@ int io_provide_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe
p->nbufs = tmp;
p->addr = READ_ONCE(sqe->addr);
p->len = READ_ONCE(sqe->len);
+ if (!p->len)
+ return -EINVAL;
if (check_mul_overflow((unsigned long)p->len, (unsigned long)p->nbufs,
&size))
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 5e64a8b..f80a77c 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -175,6 +175,18 @@ void io_rsrc_cache_free(struct io_ring_ctx *ctx)
io_alloc_cache_free(&ctx->imu_cache, kfree);
}
+static void io_clear_table_tags(struct io_rsrc_data *data)
+{
+ int i;
+
+ for (i = 0; i < data->nr; i++) {
+ struct io_rsrc_node *node = data->nodes[i];
+
+ if (node)
+ node->tag = 0;
+ }
+}
+
__cold void io_rsrc_data_free(struct io_ring_ctx *ctx,
struct io_rsrc_data *data)
{
@@ -583,6 +595,7 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
io_file_table_set_alloc_range(ctx, 0, ctx->file_table.data.nr);
return 0;
fail:
+ io_clear_table_tags(&ctx->file_table.data);
io_sqe_files_unregister(ctx);
return ret;
}
@@ -902,8 +915,10 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
}
ctx->buf_table = data;
- if (ret)
+ if (ret) {
+ io_clear_table_tags(&ctx->buf_table);
io_sqe_buffers_unregister(ctx);
+ }
return ret;
}
@@ -1017,10 +1032,33 @@ static int validate_fixed_range(u64 buf_addr, size_t len,
return 0;
}
+static int io_import_kbuf(int ddir, struct iov_iter *iter,
+ struct io_mapped_ubuf *imu, size_t len, size_t offset)
+{
+ size_t count = len + offset;
+
+ iov_iter_bvec(iter, ddir, imu->bvec, imu->nr_bvecs, count);
+ iov_iter_advance(iter, offset);
+
+ if (count < imu->len) {
+ const struct bio_vec *bvec = iter->bvec;
+
+ while (len > bvec->bv_len) {
+ len -= bvec->bv_len;
+ bvec++;
+ }
+ iter->nr_segs = 1 + bvec - iter->bvec;
+ }
+ return 0;
+}
+
static int io_import_fixed(int ddir, struct iov_iter *iter,
struct io_mapped_ubuf *imu,
u64 buf_addr, size_t len)
{
+ const struct bio_vec *bvec;
+ size_t folio_mask;
+ unsigned nr_segs;
size_t offset;
int ret;
@@ -1032,56 +1070,35 @@ static int io_import_fixed(int ddir, struct iov_iter *iter,
if (!(imu->dir & (1 << ddir)))
return -EFAULT;
- /*
- * Might not be a start of buffer, set size appropriately
- * and advance us to the beginning.
- */
offset = buf_addr - imu->ubuf;
- iov_iter_bvec(iter, ddir, imu->bvec, imu->nr_bvecs, offset + len);
- if (offset) {
- /*
- * Don't use iov_iter_advance() here, as it's really slow for
- * using the latter parts of a big fixed buffer - it iterates
- * over each segment manually. We can cheat a bit here for user
- * registered nodes, because we know that:
- *
- * 1) it's a BVEC iter, we set it up
- * 2) all bvecs are the same in size, except potentially the
- * first and last bvec
- *
- * So just find our index, and adjust the iterator afterwards.
- * If the offset is within the first bvec (or the whole first
- * bvec, just use iov_iter_advance(). This makes it easier
- * since we can just skip the first segment, which may not
- * be folio_size aligned.
- */
- const struct bio_vec *bvec = imu->bvec;
+ if (imu->is_kbuf)
+ return io_import_kbuf(ddir, iter, imu, len, offset);
- /*
- * Kernel buffer bvecs, on the other hand, don't necessarily
- * have the size property of user registered ones, so we have
- * to use the slow iter advance.
- */
- if (offset < bvec->bv_len) {
- iter->count -= offset;
- iter->iov_offset = offset;
- } else if (imu->is_kbuf) {
- iov_iter_advance(iter, offset);
- } else {
- unsigned long seg_skip;
+ /*
+ * Don't use iov_iter_advance() here, as it's really slow for
+ * using the latter parts of a big fixed buffer - it iterates
+ * over each segment manually. We can cheat a bit here for user
+ * registered nodes, because we know that:
+ *
+ * 1) it's a BVEC iter, we set it up
+ * 2) all bvecs are the same in size, except potentially the
+ * first and last bvec
+ */
+ folio_mask = (1UL << imu->folio_shift) - 1;
+ bvec = imu->bvec;
+ if (offset >= bvec->bv_len) {
+ unsigned long seg_skip;
- /* skip first vec */
- offset -= bvec->bv_len;
- seg_skip = 1 + (offset >> imu->folio_shift);
-
- iter->bvec += seg_skip;
- iter->nr_segs -= seg_skip;
- iter->count -= bvec->bv_len + offset;
- iter->iov_offset = offset & ((1UL << imu->folio_shift) - 1);
- }
+ /* skip first vec */
+ offset -= bvec->bv_len;
+ seg_skip = 1 + (offset >> imu->folio_shift);
+ bvec += seg_skip;
+ offset &= folio_mask;
}
-
+ nr_segs = (offset + len + bvec->bv_offset + folio_mask) >> imu->folio_shift;
+ iov_iter_bvec(iter, ddir, bvec, nr_segs, len);
+ iter->iov_offset = offset;
return 0;
}
diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index 80d4a6f..fe86606 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -26,6 +26,11 @@
#include "zcrx.h"
#include "rsrc.h"
+static inline struct io_zcrx_ifq *io_pp_to_ifq(struct page_pool *pp)
+{
+ return pp->mp_priv;
+}
+
#define IO_DMA_ATTR (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
static void __io_zcrx_unmap_area(struct io_zcrx_ifq *ifq,
@@ -46,14 +51,21 @@ static void __io_zcrx_unmap_area(struct io_zcrx_ifq *ifq,
static void io_zcrx_unmap_area(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area)
{
+ guard(mutex)(&ifq->dma_lock);
+
if (area->is_mapped)
__io_zcrx_unmap_area(ifq, area, area->nia.num_niovs);
+ area->is_mapped = false;
}
static int io_zcrx_map_area(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area)
{
int i;
+ guard(mutex)(&ifq->dma_lock);
+ if (area->is_mapped)
+ return 0;
+
for (i = 0; i < area->nia.num_niovs; i++) {
struct net_iov *niov = &area->nia.niovs[i];
dma_addr_t dma;
@@ -181,7 +193,7 @@ static void io_zcrx_free_area(struct io_zcrx_area *area)
kvfree(area->nia.niovs);
kvfree(area->user_refs);
if (area->pages) {
- unpin_user_pages(area->pages, area->nia.num_niovs);
+ unpin_user_pages(area->pages, area->nr_folios);
kvfree(area->pages);
}
kfree(area);
@@ -192,7 +204,7 @@ static int io_zcrx_create_area(struct io_zcrx_ifq *ifq,
struct io_uring_zcrx_area_reg *area_reg)
{
struct io_zcrx_area *area;
- int i, ret, nr_pages;
+ int i, ret, nr_pages, nr_iovs;
struct iovec iov;
if (area_reg->flags || area_reg->rq_area_token)
@@ -220,27 +232,28 @@ static int io_zcrx_create_area(struct io_zcrx_ifq *ifq,
area->pages = NULL;
goto err;
}
- area->nia.num_niovs = nr_pages;
+ area->nr_folios = nr_iovs = nr_pages;
+ area->nia.num_niovs = nr_iovs;
- area->nia.niovs = kvmalloc_array(nr_pages, sizeof(area->nia.niovs[0]),
+ area->nia.niovs = kvmalloc_array(nr_iovs, sizeof(area->nia.niovs[0]),
GFP_KERNEL | __GFP_ZERO);
if (!area->nia.niovs)
goto err;
- area->freelist = kvmalloc_array(nr_pages, sizeof(area->freelist[0]),
+ area->freelist = kvmalloc_array(nr_iovs, sizeof(area->freelist[0]),
GFP_KERNEL | __GFP_ZERO);
if (!area->freelist)
goto err;
- for (i = 0; i < nr_pages; i++)
+ for (i = 0; i < nr_iovs; i++)
area->freelist[i] = i;
- area->user_refs = kvmalloc_array(nr_pages, sizeof(area->user_refs[0]),
+ area->user_refs = kvmalloc_array(nr_iovs, sizeof(area->user_refs[0]),
GFP_KERNEL | __GFP_ZERO);
if (!area->user_refs)
goto err;
- for (i = 0; i < nr_pages; i++) {
+ for (i = 0; i < nr_iovs; i++) {
struct net_iov *niov = &area->nia.niovs[i];
niov->owner = &area->nia;
@@ -248,7 +261,7 @@ static int io_zcrx_create_area(struct io_zcrx_ifq *ifq,
atomic_set(&area->user_refs[i], 0);
}
- area->free_count = nr_pages;
+ area->free_count = nr_iovs;
area->ifq = ifq;
/* we're only supporting one area per ifq for now */
area->area_id = 0;
@@ -274,6 +287,7 @@ static struct io_zcrx_ifq *io_zcrx_ifq_alloc(struct io_ring_ctx *ctx)
ifq->ctx = ctx;
spin_lock_init(&ifq->lock);
spin_lock_init(&ifq->rq_lock);
+ mutex_init(&ifq->dma_lock);
return ifq;
}
@@ -323,6 +337,7 @@ static void io_zcrx_ifq_free(struct io_zcrx_ifq *ifq)
put_device(ifq->dev);
io_free_rbuf_ring(ifq);
+ mutex_destroy(&ifq->dma_lock);
kfree(ifq);
}
@@ -353,7 +368,8 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
return -EFAULT;
if (copy_from_user(&rd, u64_to_user_ptr(reg.region_ptr), sizeof(rd)))
return -EFAULT;
- if (memchr_inv(®.__resv, 0, sizeof(reg.__resv)))
+ if (memchr_inv(®.__resv, 0, sizeof(reg.__resv)) ||
+ reg.__resv2 || reg.zcrx_id)
return -EINVAL;
if (reg.if_rxq == -1 || !reg.rq_entries || reg.flags)
return -EINVAL;
@@ -393,10 +409,6 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
goto err;
get_device(ifq->dev);
- ret = io_zcrx_map_area(ifq, ifq->area);
- if (ret)
- goto err;
-
mp_param.mp_ops = &io_uring_pp_zc_ops;
mp_param.mp_priv = ifq;
ret = net_mp_open_rxq(ifq->netdev, reg.if_rxq, &mp_param);
@@ -584,7 +596,7 @@ static void io_zcrx_refill_slow(struct page_pool *pp, struct io_zcrx_ifq *ifq)
static netmem_ref io_pp_zc_alloc_netmems(struct page_pool *pp, gfp_t gfp)
{
- struct io_zcrx_ifq *ifq = pp->mp_priv;
+ struct io_zcrx_ifq *ifq = io_pp_to_ifq(pp);
/* pp should already be ensuring that */
if (unlikely(pp->alloc.count))
@@ -616,7 +628,8 @@ static bool io_pp_zc_release_netmem(struct page_pool *pp, netmem_ref netmem)
static int io_pp_zc_init(struct page_pool *pp)
{
- struct io_zcrx_ifq *ifq = pp->mp_priv;
+ struct io_zcrx_ifq *ifq = io_pp_to_ifq(pp);
+ int ret;
if (WARN_ON_ONCE(!ifq))
return -EINVAL;
@@ -629,13 +642,17 @@ static int io_pp_zc_init(struct page_pool *pp)
if (pp->p.dma_dir != DMA_FROM_DEVICE)
return -EOPNOTSUPP;
+ ret = io_zcrx_map_area(ifq, ifq->area);
+ if (ret)
+ return ret;
+
percpu_ref_get(&ifq->ctx->refs);
return 0;
}
static void io_pp_zc_destroy(struct page_pool *pp)
{
- struct io_zcrx_ifq *ifq = pp->mp_priv;
+ struct io_zcrx_ifq *ifq = io_pp_to_ifq(pp);
struct io_zcrx_area *area = ifq->area;
if (WARN_ON_ONCE(area->free_count != area->nia.num_niovs))
@@ -664,6 +681,9 @@ static void io_pp_uninstall(void *mp_priv, struct netdev_rx_queue *rxq)
struct io_zcrx_ifq *ifq = mp_priv;
io_zcrx_drop_netdev(ifq);
+ if (ifq->area)
+ io_zcrx_unmap_area(ifq, ifq->area);
+
p->mp_ops = NULL;
p->mp_priv = NULL;
}
@@ -790,7 +810,7 @@ static int io_zcrx_recv_frag(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
niov = netmem_to_net_iov(frag->netmem);
if (niov->pp->mp_ops != &io_uring_pp_zc_ops ||
- niov->pp->mp_priv != ifq)
+ io_pp_to_ifq(niov->pp) != ifq)
return -EFAULT;
if (!io_zcrx_queue_cqe(req, niov, ifq, off + skb_frag_off(frag), len))
diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h
index 706cc73..f2bc811 100644
--- a/io_uring/zcrx.h
+++ b/io_uring/zcrx.h
@@ -15,6 +15,7 @@ struct io_zcrx_area {
bool is_mapped;
u16 area_id;
struct page **pages;
+ unsigned long nr_folios;
/* freelist */
spinlock_t freelist_lock ____cacheline_aligned_in_smp;
@@ -26,17 +27,18 @@ struct io_zcrx_ifq {
struct io_ring_ctx *ctx;
struct io_zcrx_area *area;
+ spinlock_t rq_lock ____cacheline_aligned_in_smp;
struct io_uring *rq_ring;
struct io_uring_zcrx_rqe *rqes;
- u32 rq_entries;
u32 cached_rq_head;
- spinlock_t rq_lock;
+ u32 rq_entries;
u32 if_rxq;
struct device *dev;
struct net_device *netdev;
netdevice_tracker netdev_tracker;
spinlock_t lock;
+ struct mutex dma_lock;
};
#if defined(CONFIG_IO_URING_ZCRX)
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 367eaf2..0ebbbe3 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -347,12 +347,17 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
/* Get path information necessary for adding watches. */
static int audit_get_nd(struct audit_watch *watch, struct path *parent)
{
- struct dentry *d = kern_path_locked(watch->path, parent);
+ struct dentry *d;
+
+ d = kern_path_locked_negative(watch->path, parent);
if (IS_ERR(d))
return PTR_ERR(d);
- /* update watch filter fields */
- watch->dev = d->d_sb->s_dev;
- watch->ino = d_backing_inode(d)->i_ino;
+
+ if (d_is_positive(d)) {
+ /* update watch filter fields */
+ watch->dev = d->d_sb->s_dev;
+ watch->ino = d_backing_inode(d)->i_ino;
+ }
inode_unlock(d_backing_inode(parent->dentry));
dput(d);
@@ -418,11 +423,10 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
/* caller expects mutex locked */
mutex_lock(&audit_filter_mutex);
- if (ret && ret != -ENOENT) {
+ if (ret) {
audit_put_watch(watch);
return ret;
}
- ret = 0;
/* either find an old parent or attach a new one */
parent = audit_find_parent(d_backing_inode(parent_path.dentry));
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 5a5adc6..92b606d 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -2189,7 +2189,7 @@ static long bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_
b = &htab->buckets[i];
rcu_read_lock();
head = &b->head;
- hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) {
+ hlist_nulls_for_each_entry_safe(elem, n, head, hash_node) {
key = elem->key;
if (is_percpu) {
/* current cpu value for percpu map */
diff --git a/kernel/bpf/preload/bpf_preload_kern.c b/kernel/bpf/preload/bpf_preload_kern.c
index 2fdf3c9..774e5a5 100644
--- a/kernel/bpf/preload/bpf_preload_kern.c
+++ b/kernel/bpf/preload/bpf_preload_kern.c
@@ -89,5 +89,6 @@ static void __exit fini(void)
}
late_initcall(load);
module_exit(fini);
+MODULE_IMPORT_NS("BPF_INTERNAL");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Embedded BPF programs for introspection in bpffs");
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index d869f51..9a5f943 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -9,13 +9,14 @@
#include <linux/slab.h>
#include <linux/btf_ids.h>
#include "percpu_freelist.h"
+#include <asm/rqspinlock.h>
#define QUEUE_STACK_CREATE_FLAG_MASK \
(BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
struct bpf_queue_stack {
struct bpf_map map;
- raw_spinlock_t lock;
+ rqspinlock_t lock;
u32 head, tail;
u32 size; /* max_entries + 1 */
@@ -78,7 +79,7 @@ static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr)
qs->size = size;
- raw_spin_lock_init(&qs->lock);
+ raw_res_spin_lock_init(&qs->lock);
return &qs->map;
}
@@ -98,12 +99,8 @@ static long __queue_map_get(struct bpf_map *map, void *value, bool delete)
int err = 0;
void *ptr;
- if (in_nmi()) {
- if (!raw_spin_trylock_irqsave(&qs->lock, flags))
- return -EBUSY;
- } else {
- raw_spin_lock_irqsave(&qs->lock, flags);
- }
+ if (raw_res_spin_lock_irqsave(&qs->lock, flags))
+ return -EBUSY;
if (queue_stack_map_is_empty(qs)) {
memset(value, 0, qs->map.value_size);
@@ -120,7 +117,7 @@ static long __queue_map_get(struct bpf_map *map, void *value, bool delete)
}
out:
- raw_spin_unlock_irqrestore(&qs->lock, flags);
+ raw_res_spin_unlock_irqrestore(&qs->lock, flags);
return err;
}
@@ -133,12 +130,8 @@ static long __stack_map_get(struct bpf_map *map, void *value, bool delete)
void *ptr;
u32 index;
- if (in_nmi()) {
- if (!raw_spin_trylock_irqsave(&qs->lock, flags))
- return -EBUSY;
- } else {
- raw_spin_lock_irqsave(&qs->lock, flags);
- }
+ if (raw_res_spin_lock_irqsave(&qs->lock, flags))
+ return -EBUSY;
if (queue_stack_map_is_empty(qs)) {
memset(value, 0, qs->map.value_size);
@@ -157,7 +150,7 @@ static long __stack_map_get(struct bpf_map *map, void *value, bool delete)
qs->head = index;
out:
- raw_spin_unlock_irqrestore(&qs->lock, flags);
+ raw_res_spin_unlock_irqrestore(&qs->lock, flags);
return err;
}
@@ -203,12 +196,8 @@ static long queue_stack_map_push_elem(struct bpf_map *map, void *value,
if (flags & BPF_NOEXIST || flags > BPF_EXIST)
return -EINVAL;
- if (in_nmi()) {
- if (!raw_spin_trylock_irqsave(&qs->lock, irq_flags))
- return -EBUSY;
- } else {
- raw_spin_lock_irqsave(&qs->lock, irq_flags);
- }
+ if (raw_res_spin_lock_irqsave(&qs->lock, irq_flags))
+ return -EBUSY;
if (queue_stack_map_is_full(qs)) {
if (!replace) {
@@ -227,7 +216,7 @@ static long queue_stack_map_push_elem(struct bpf_map *map, void *value,
qs->head = 0;
out:
- raw_spin_unlock_irqrestore(&qs->lock, irq_flags);
+ raw_res_spin_unlock_irqrestore(&qs->lock, irq_flags);
return err;
}
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 1499d8c..719d732 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -11,6 +11,7 @@
#include <linux/kmemleak.h>
#include <uapi/linux/btf.h>
#include <linux/btf_ids.h>
+#include <asm/rqspinlock.h>
#define RINGBUF_CREATE_FLAG_MASK (BPF_F_NUMA_NODE)
@@ -29,7 +30,7 @@ struct bpf_ringbuf {
u64 mask;
struct page **pages;
int nr_pages;
- raw_spinlock_t spinlock ____cacheline_aligned_in_smp;
+ rqspinlock_t spinlock ____cacheline_aligned_in_smp;
/* For user-space producer ring buffers, an atomic_t busy bit is used
* to synchronize access to the ring buffers in the kernel, rather than
* the spinlock that is used for kernel-producer ring buffers. This is
@@ -173,7 +174,7 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node)
if (!rb)
return NULL;
- raw_spin_lock_init(&rb->spinlock);
+ raw_res_spin_lock_init(&rb->spinlock);
atomic_set(&rb->busy, 0);
init_waitqueue_head(&rb->waitq);
init_irq_work(&rb->work, bpf_ringbuf_notify);
@@ -416,12 +417,8 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
cons_pos = smp_load_acquire(&rb->consumer_pos);
- if (in_nmi()) {
- if (!raw_spin_trylock_irqsave(&rb->spinlock, flags))
- return NULL;
- } else {
- raw_spin_lock_irqsave(&rb->spinlock, flags);
- }
+ if (raw_res_spin_lock_irqsave(&rb->spinlock, flags))
+ return NULL;
pend_pos = rb->pending_pos;
prod_pos = rb->producer_pos;
@@ -446,7 +443,7 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
*/
if (new_prod_pos - cons_pos > rb->mask ||
new_prod_pos - pend_pos > rb->mask) {
- raw_spin_unlock_irqrestore(&rb->spinlock, flags);
+ raw_res_spin_unlock_irqrestore(&rb->spinlock, flags);
return NULL;
}
@@ -458,7 +455,7 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
/* pairs with consumer's smp_load_acquire() */
smp_store_release(&rb->producer_pos, new_prod_pos);
- raw_spin_unlock_irqrestore(&rb->spinlock, flags);
+ raw_res_spin_unlock_irqrestore(&rb->spinlock, flags);
return (void *)hdr + BPF_RINGBUF_HDR_SZ;
}
diff --git a/kernel/bpf/rqspinlock.c b/kernel/bpf/rqspinlock.c
index b896c4a..338305c 100644
--- a/kernel/bpf/rqspinlock.c
+++ b/kernel/bpf/rqspinlock.c
@@ -253,7 +253,7 @@ static noinline int check_timeout(rqspinlock_t *lock, u32 mask,
})
#else
#define RES_CHECK_TIMEOUT(ts, ret, mask) \
- ({ (ret) = check_timeout(&(ts)); })
+ ({ (ret) = check_timeout((lock), (mask), &(ts)); })
#endif
/*
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 9794446..64c3393 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1583,7 +1583,7 @@ struct bpf_map *bpf_map_get(u32 ufd)
return map;
}
-EXPORT_SYMBOL(bpf_map_get);
+EXPORT_SYMBOL_NS(bpf_map_get, "BPF_INTERNAL");
struct bpf_map *bpf_map_get_with_uref(u32 ufd)
{
@@ -3364,7 +3364,7 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd)
bpf_link_inc(link);
return link;
}
-EXPORT_SYMBOL(bpf_link_get_from_fd);
+EXPORT_SYMBOL_NS(bpf_link_get_from_fd, "BPF_INTERNAL");
static void bpf_tracing_link_release(struct bpf_link *link)
{
@@ -6020,7 +6020,7 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size)
return ____bpf_sys_bpf(cmd, attr, size);
}
}
-EXPORT_SYMBOL(kern_sys_bpf);
+EXPORT_SYMBOL_NS(kern_sys_bpf, "BPF_INTERNAL");
static const struct bpf_func_proto bpf_sys_bpf_proto = {
.func = bpf_sys_bpf,
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 27f08aa..63e5b90 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -90,7 +90,7 @@
DEFINE_MUTEX(cgroup_mutex);
DEFINE_SPINLOCK(css_set_lock);
-#ifdef CONFIG_PROVE_RCU
+#if (defined CONFIG_PROVE_RCU || defined CONFIG_LOCKDEP)
EXPORT_SYMBOL_GPL(cgroup_mutex);
EXPORT_SYMBOL_GPL(css_set_lock);
#endif
@@ -2353,9 +2353,37 @@ static struct file_system_type cgroup2_fs_type = {
};
#ifdef CONFIG_CPUSETS_V1
+enum cpuset_param {
+ Opt_cpuset_v2_mode,
+};
+
+static const struct fs_parameter_spec cpuset_fs_parameters[] = {
+ fsparam_flag ("cpuset_v2_mode", Opt_cpuset_v2_mode),
+ {}
+};
+
+static int cpuset_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+ struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+ struct fs_parse_result result;
+ int opt;
+
+ opt = fs_parse(fc, cpuset_fs_parameters, param, &result);
+ if (opt < 0)
+ return opt;
+
+ switch (opt) {
+ case Opt_cpuset_v2_mode:
+ ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE;
+ return 0;
+ }
+ return -EINVAL;
+}
+
static const struct fs_context_operations cpuset_fs_context_ops = {
.get_tree = cgroup1_get_tree,
.free = cgroup_fs_context_free,
+ .parse_param = cpuset_parse_param,
};
/*
@@ -2392,6 +2420,7 @@ static int cpuset_init_fs_context(struct fs_context *fc)
static struct file_system_type cpuset_fs_type = {
.name = "cpuset",
.init_fs_context = cpuset_init_fs_context,
+ .parameters = cpuset_fs_parameters,
.fs_flags = FS_USERNS_MOUNT,
};
#endif
@@ -5923,6 +5952,12 @@ static void kill_css(struct cgroup_subsys_state *css)
if (css->flags & CSS_DYING)
return;
+ /*
+ * Call css_killed(), if defined, before setting the CSS_DYING flag
+ */
+ if (css->ss->css_killed)
+ css->ss->css_killed(css);
+
css->flags |= CSS_DYING;
/*
diff --git a/kernel/cgroup/cpuset-internal.h b/kernel/cgroup/cpuset-internal.h
index 976a8bc..383963e 100644
--- a/kernel/cgroup/cpuset-internal.h
+++ b/kernel/cgroup/cpuset-internal.h
@@ -33,6 +33,7 @@ enum prs_errcode {
PERR_CPUSEMPTY,
PERR_HKEEPING,
PERR_ACCESS,
+ PERR_REMOTE,
};
/* bits in struct cpuset flags field */
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 39c1fc6..306b604 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -61,10 +61,17 @@ static const char * const perr_strings[] = {
[PERR_CPUSEMPTY] = "cpuset.cpus and cpuset.cpus.exclusive are empty",
[PERR_HKEEPING] = "partition config conflicts with housekeeping setup",
[PERR_ACCESS] = "Enable partition not permitted",
+ [PERR_REMOTE] = "Have remote partition underneath",
};
/*
- * Exclusive CPUs distributed out to sub-partitions of top_cpuset
+ * For local partitions, update to subpartitions_cpus & isolated_cpus is done
+ * in update_parent_effective_cpumask(). For remote partitions, it is done in
+ * the remote_partition_*() and remote_cpus_update() helpers.
+ */
+/*
+ * Exclusive CPUs distributed out to local or remote sub-partitions of
+ * top_cpuset
*/
static cpumask_var_t subpartitions_cpus;
@@ -86,7 +93,6 @@ static struct list_head remote_children;
* A flag to force sched domain rebuild at the end of an operation.
* It can be set in
* - update_partition_sd_lb()
- * - remote_partition_check()
* - update_cpumasks_hier()
* - cpuset_update_flag()
* - cpuset_hotplug_update_tasks()
@@ -1089,9 +1095,14 @@ void cpuset_reset_sched_domains(void)
*
* Iterate through each task of @cs updating its cpus_allowed to the
* effective cpuset's. As this function is called with cpuset_mutex held,
- * cpuset membership stays stable. For top_cpuset, task_cpu_possible_mask()
- * is used instead of effective_cpus to make sure all offline CPUs are also
- * included as hotplug code won't update cpumasks for tasks in top_cpuset.
+ * cpuset membership stays stable.
+ *
+ * For top_cpuset, task_cpu_possible_mask() is used instead of effective_cpus
+ * to make sure all offline CPUs are also included as hotplug code won't
+ * update cpumasks for tasks in top_cpuset.
+ *
+ * As task_cpu_possible_mask() can be task dependent in arm64, we have to
+ * do cpu masking per task instead of doing it once for all.
*/
void cpuset_update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
{
@@ -1151,7 +1162,7 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
*
* Return: 0 if successful, an error code otherwise
*/
-static int update_partition_exclusive(struct cpuset *cs, int new_prs)
+static int update_partition_exclusive_flag(struct cpuset *cs, int new_prs)
{
bool exclusive = (new_prs > PRS_MEMBER);
@@ -1234,12 +1245,12 @@ static void reset_partition_data(struct cpuset *cs)
}
/*
- * partition_xcpus_newstate - Exclusive CPUs state change
+ * isolated_cpus_update - Update the isolated_cpus mask
* @old_prs: old partition_root_state
* @new_prs: new partition_root_state
* @xcpus: exclusive CPUs with state change
*/
-static void partition_xcpus_newstate(int old_prs, int new_prs, struct cpumask *xcpus)
+static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus)
{
WARN_ON_ONCE(old_prs == new_prs);
if (new_prs == PRS_ISOLATED)
@@ -1273,8 +1284,8 @@ static bool partition_xcpus_add(int new_prs, struct cpuset *parent,
isolcpus_updated = (new_prs != parent->partition_root_state);
if (isolcpus_updated)
- partition_xcpus_newstate(parent->partition_root_state, new_prs,
- xcpus);
+ isolated_cpus_update(parent->partition_root_state, new_prs,
+ xcpus);
cpumask_andnot(parent->effective_cpus, parent->effective_cpus, xcpus);
return isolcpus_updated;
@@ -1304,8 +1315,8 @@ static bool partition_xcpus_del(int old_prs, struct cpuset *parent,
isolcpus_updated = (old_prs != parent->partition_root_state);
if (isolcpus_updated)
- partition_xcpus_newstate(old_prs, parent->partition_root_state,
- xcpus);
+ isolated_cpus_update(old_prs, parent->partition_root_state,
+ xcpus);
cpumask_and(xcpus, xcpus, cpu_active_mask);
cpumask_or(parent->effective_cpus, parent->effective_cpus, xcpus);
@@ -1340,20 +1351,57 @@ EXPORT_SYMBOL_GPL(cpuset_cpu_is_isolated);
* compute_effective_exclusive_cpumask - compute effective exclusive CPUs
* @cs: cpuset
* @xcpus: effective exclusive CPUs value to be set
- * Return: true if xcpus is not empty, false otherwise.
+ * @real_cs: the real cpuset (can be NULL)
+ * Return: 0 if there is no sibling conflict, > 0 otherwise
*
- * Starting with exclusive_cpus (cpus_allowed if exclusive_cpus is not set),
- * it must be a subset of parent's effective_xcpus.
+ * If exclusive_cpus isn't explicitly set or a real_cs is provided, we have to
+ * scan the sibling cpusets and exclude their exclusive_cpus or effective_xcpus
+ * as well. The provision of real_cs means that a cpumask is being changed and
+ * the given cs is a trial one.
*/
-static bool compute_effective_exclusive_cpumask(struct cpuset *cs,
- struct cpumask *xcpus)
+static int compute_effective_exclusive_cpumask(struct cpuset *cs,
+ struct cpumask *xcpus,
+ struct cpuset *real_cs)
{
+ struct cgroup_subsys_state *css;
struct cpuset *parent = parent_cs(cs);
+ struct cpuset *sibling;
+ int retval = 0;
if (!xcpus)
xcpus = cs->effective_xcpus;
- return cpumask_and(xcpus, user_xcpus(cs), parent->effective_xcpus);
+ cpumask_and(xcpus, user_xcpus(cs), parent->effective_xcpus);
+
+ if (!real_cs) {
+ if (!cpumask_empty(cs->exclusive_cpus))
+ return 0;
+ } else {
+ cs = real_cs;
+ }
+
+ /*
+ * Exclude exclusive CPUs from siblings
+ */
+ rcu_read_lock();
+ cpuset_for_each_child(sibling, css, parent) {
+ if (sibling == cs)
+ continue;
+
+ if (!cpumask_empty(sibling->exclusive_cpus) &&
+ cpumask_intersects(xcpus, sibling->exclusive_cpus)) {
+ cpumask_andnot(xcpus, xcpus, sibling->exclusive_cpus);
+ retval++;
+ continue;
+ }
+ if (!cpumask_empty(sibling->effective_xcpus) &&
+ cpumask_intersects(xcpus, sibling->effective_xcpus)) {
+ cpumask_andnot(xcpus, xcpus, sibling->effective_xcpus);
+ retval++;
+ }
+ }
+ rcu_read_unlock();
+ return retval;
}
static inline bool is_remote_partition(struct cpuset *cs)
@@ -1395,7 +1443,7 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
* remote partition root underneath it, its exclusive_cpus must
* have overlapped with subpartitions_cpus.
*/
- compute_effective_exclusive_cpumask(cs, tmp->new_cpus);
+ compute_effective_exclusive_cpumask(cs, tmp->new_cpus, NULL);
if (cpumask_empty(tmp->new_cpus) ||
cpumask_intersects(tmp->new_cpus, subpartitions_cpus) ||
cpumask_subset(top_cpuset.effective_cpus, tmp->new_cpus))
@@ -1404,8 +1452,11 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
spin_lock_irq(&callback_lock);
isolcpus_updated = partition_xcpus_add(new_prs, NULL, tmp->new_cpus);
list_add(&cs->remote_sibling, &remote_children);
+ cpumask_copy(cs->effective_xcpus, tmp->new_cpus);
spin_unlock_irq(&callback_lock);
update_unbound_workqueue_cpumask(isolcpus_updated);
+ cpuset_force_rebuild();
+ cs->prs_err = 0;
/*
* Propagate changes in top_cpuset's effective_cpus down the hierarchy.
@@ -1428,20 +1479,24 @@ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp)
{
bool isolcpus_updated;
- compute_effective_exclusive_cpumask(cs, tmp->new_cpus);
WARN_ON_ONCE(!is_remote_partition(cs));
- WARN_ON_ONCE(!cpumask_subset(tmp->new_cpus, subpartitions_cpus));
+ WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus));
spin_lock_irq(&callback_lock);
list_del_init(&cs->remote_sibling);
isolcpus_updated = partition_xcpus_del(cs->partition_root_state,
- NULL, tmp->new_cpus);
- cs->partition_root_state = -cs->partition_root_state;
- if (!cs->prs_err)
- cs->prs_err = PERR_INVCPUS;
+ NULL, cs->effective_xcpus);
+ if (cs->prs_err)
+ cs->partition_root_state = -cs->partition_root_state;
+ else
+ cs->partition_root_state = PRS_MEMBER;
+
+ /* effective_xcpus may need to be changed */
+ compute_effective_exclusive_cpumask(cs, NULL, NULL);
reset_partition_data(cs);
spin_unlock_irq(&callback_lock);
update_unbound_workqueue_cpumask(isolcpus_updated);
+ cpuset_force_rebuild();
/*
* Propagate changes in top_cpuset's effective_cpus down the hierarchy.
@@ -1453,14 +1508,15 @@ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp)
/*
* remote_cpus_update - cpus_exclusive change of remote partition
* @cs: the cpuset to be updated
- * @newmask: the new effective_xcpus mask
+ * @xcpus: the new exclusive_cpus mask, if non-NULL
+ * @excpus: the new effective_xcpus mask
* @tmp: temporary masks
*
* top_cpuset and subpartitions_cpus will be updated or partition can be
* invalidated.
*/
-static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask,
- struct tmpmasks *tmp)
+static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus,
+ struct cpumask *excpus, struct tmpmasks *tmp)
{
bool adding, deleting;
int prs = cs->partition_root_state;
@@ -1471,29 +1527,45 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask,
WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus));
- if (cpumask_empty(newmask))
+ if (cpumask_empty(excpus)) {
+ cs->prs_err = PERR_CPUSEMPTY;
goto invalidate;
+ }
- adding = cpumask_andnot(tmp->addmask, newmask, cs->effective_xcpus);
- deleting = cpumask_andnot(tmp->delmask, cs->effective_xcpus, newmask);
+ adding = cpumask_andnot(tmp->addmask, excpus, cs->effective_xcpus);
+ deleting = cpumask_andnot(tmp->delmask, cs->effective_xcpus, excpus);
/*
* Additions of remote CPUs is only allowed if those CPUs are
* not allocated to other partitions and there are effective_cpus
* left in the top cpuset.
*/
- if (adding && (!capable(CAP_SYS_ADMIN) ||
- cpumask_intersects(tmp->addmask, subpartitions_cpus) ||
- cpumask_subset(top_cpuset.effective_cpus, tmp->addmask)))
- goto invalidate;
+ if (adding) {
+ if (!capable(CAP_SYS_ADMIN))
+ cs->prs_err = PERR_ACCESS;
+ else if (cpumask_intersects(tmp->addmask, subpartitions_cpus) ||
+ cpumask_subset(top_cpuset.effective_cpus, tmp->addmask))
+ cs->prs_err = PERR_NOCPUS;
+ if (cs->prs_err)
+ goto invalidate;
+ }
spin_lock_irq(&callback_lock);
if (adding)
isolcpus_updated += partition_xcpus_add(prs, NULL, tmp->addmask);
if (deleting)
isolcpus_updated += partition_xcpus_del(prs, NULL, tmp->delmask);
+ /*
+ * Need to update effective_xcpus and exclusive_cpus now as
+ * update_sibling_cpumasks() below may iterate back to the same cs.
+ */
+ cpumask_copy(cs->effective_xcpus, excpus);
+ if (xcpus)
+ cpumask_copy(cs->exclusive_cpus, xcpus);
spin_unlock_irq(&callback_lock);
update_unbound_workqueue_cpumask(isolcpus_updated);
+ if (adding || deleting)
+ cpuset_force_rebuild();
/*
* Propagate changes in top_cpuset's effective_cpus down the hierarchy.
@@ -1507,47 +1579,6 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask,
}
/*
- * remote_partition_check - check if a child remote partition needs update
- * @cs: the cpuset to be updated
- * @newmask: the new effective_xcpus mask
- * @delmask: temporary mask for deletion (not in tmp)
- * @tmp: temporary masks
- *
- * This should be called before the given cs has updated its cpus_allowed
- * and/or effective_xcpus.
- */
-static void remote_partition_check(struct cpuset *cs, struct cpumask *newmask,
- struct cpumask *delmask, struct tmpmasks *tmp)
-{
- struct cpuset *child, *next;
- int disable_cnt = 0;
-
- /*
- * Compute the effective exclusive CPUs that will be deleted.
- */
- if (!cpumask_andnot(delmask, cs->effective_xcpus, newmask) ||
- !cpumask_intersects(delmask, subpartitions_cpus))
- return; /* No deletion of exclusive CPUs in partitions */
-
- /*
- * Searching the remote children list to look for those that will
- * be impacted by the deletion of exclusive CPUs.
- *
- * Since a cpuset must be removed from the remote children list
- * before it can go offline and holding cpuset_mutex will prevent
- * any change in cpuset status. RCU read lock isn't needed.
- */
- lockdep_assert_held(&cpuset_mutex);
- list_for_each_entry_safe(child, next, &remote_children, remote_sibling)
- if (cpumask_intersects(child->effective_cpus, delmask)) {
- remote_partition_disable(child, tmp);
- disable_cnt++;
- }
- if (disable_cnt)
- cpuset_force_rebuild();
-}
-
-/*
* prstate_housekeeping_conflict - check for partition & housekeeping conflicts
* @prstate: partition root state to be checked
* @new_cpus: cpu mask
@@ -1601,7 +1632,7 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
* The partcmd_update command is used by update_cpumasks_hier() with newmask
* NULL and update_cpumask() with newmask set. The partcmd_invalidate is used
* by update_cpumask() with NULL newmask. In both cases, the callers won't
- * check for error and so partition_root_state and prs_error will be updated
+ * check for error and so partition_root_state and prs_err will be updated
* directly.
*/
static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
@@ -1614,11 +1645,12 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
int old_prs, new_prs;
int part_error = PERR_NONE; /* Partition error? */
int subparts_delta = 0;
- struct cpumask *xcpus; /* cs effective_xcpus */
int isolcpus_updated = 0;
+ struct cpumask *xcpus = user_xcpus(cs);
bool nocpu;
lockdep_assert_held(&cpuset_mutex);
+ WARN_ON_ONCE(is_remote_partition(cs));
/*
* new_prs will only be changed for the partcmd_update and
@@ -1626,7 +1658,6 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
*/
adding = deleting = false;
old_prs = new_prs = cs->partition_root_state;
- xcpus = user_xcpus(cs);
if (cmd == partcmd_invalidate) {
if (is_prs_invalid(old_prs))
@@ -1661,12 +1692,19 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
if ((cmd == partcmd_enable) || (cmd == partcmd_enablei)) {
/*
- * Enabling partition root is not allowed if its
- * effective_xcpus is empty or doesn't overlap with
- * parent's effective_xcpus.
+ * Need to call compute_effective_exclusive_cpumask() in case
+ * exclusive_cpus not set. Sibling conflict should only happen
+ * if exclusive_cpus isn't set.
*/
- if (cpumask_empty(xcpus) ||
- !cpumask_intersects(xcpus, parent->effective_xcpus))
+ xcpus = tmp->new_cpus;
+ if (compute_effective_exclusive_cpumask(cs, xcpus, NULL))
+ WARN_ON_ONCE(!cpumask_empty(cs->exclusive_cpus));
+
+ /*
+ * Enabling partition root is not allowed if its
+ * effective_xcpus is empty.
+ */
+ if (cpumask_empty(xcpus))
return PERR_INVCPUS;
if (prstate_housekeeping_conflict(new_prs, xcpus))
@@ -1679,19 +1717,22 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
if (nocpu)
return PERR_NOCPUS;
- cpumask_copy(tmp->delmask, xcpus);
- deleting = true;
- subparts_delta++;
+ deleting = cpumask_and(tmp->delmask, xcpus, parent->effective_xcpus);
+ if (deleting)
+ subparts_delta++;
new_prs = (cmd == partcmd_enable) ? PRS_ROOT : PRS_ISOLATED;
} else if (cmd == partcmd_disable) {
/*
- * May need to add cpus to parent's effective_cpus for
- * valid partition root.
+ * May need to add cpus back to parent's effective_cpus
+ * (and maybe removed from subpartitions_cpus/isolated_cpus)
+ * for valid partition root. xcpus may contain CPUs that
+ * shouldn't be removed from the two global cpumasks.
*/
- adding = !is_prs_invalid(old_prs) &&
- cpumask_and(tmp->addmask, xcpus, parent->effective_xcpus);
- if (adding)
+ if (is_partition_valid(cs)) {
+ cpumask_copy(tmp->addmask, cs->effective_xcpus);
+ adding = true;
subparts_delta--;
+ }
new_prs = PRS_MEMBER;
} else if (newmask) {
/*
@@ -1701,6 +1742,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
part_error = PERR_CPUSEMPTY;
goto write_error;
}
+
/* Check newmask again, whether cpus are available for parent/cs */
nocpu |= tasks_nocpu_error(parent, cs, newmask);
@@ -1829,7 +1871,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
* CPU lists in cs haven't been updated yet. So defer it to later.
*/
if ((old_prs != new_prs) && (cmd != partcmd_update)) {
- int err = update_partition_exclusive(cs, new_prs);
+ int err = update_partition_exclusive_flag(cs, new_prs);
if (err)
return err;
@@ -1867,7 +1909,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
update_unbound_workqueue_cpumask(isolcpus_updated);
if ((old_prs != new_prs) && (cmd == partcmd_update))
- update_partition_exclusive(cs, new_prs);
+ update_partition_exclusive_flag(cs, new_prs);
if (adding || deleting) {
cpuset_update_tasks_cpumask(parent, tmp->addmask);
@@ -1917,7 +1959,7 @@ static void compute_partition_effective_cpumask(struct cpuset *cs,
* 2) All the effective_cpus will be used up and cp
* has tasks
*/
- compute_effective_exclusive_cpumask(cs, new_ecpus);
+ compute_effective_exclusive_cpumask(cs, new_ecpus, NULL);
cpumask_and(new_ecpus, new_ecpus, cpu_active_mask);
rcu_read_lock();
@@ -1925,6 +1967,11 @@ static void compute_partition_effective_cpumask(struct cpuset *cs,
if (!is_partition_valid(child))
continue;
+ /*
+ * There shouldn't be a remote partition underneath another
+ * partition root.
+ */
+ WARN_ON_ONCE(is_remote_partition(child));
child->prs_err = 0;
if (!cpumask_subset(child->effective_xcpus,
cs->effective_xcpus))
@@ -1980,32 +2027,39 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
bool remote = is_remote_partition(cp);
bool update_parent = false;
+ old_prs = new_prs = cp->partition_root_state;
+
/*
- * Skip descendent remote partition that acquires CPUs
- * directly from top cpuset unless it is cs.
+ * For child remote partition root (!= cs), we need to call
+ * remote_cpus_update() if effective_xcpus will be changed.
+ * Otherwise, we can skip the whole subtree.
+ *
+ * remote_cpus_update() will reuse tmp->new_cpus only after
+ * its value is being processed.
*/
if (remote && (cp != cs)) {
- pos_css = css_rightmost_descendant(pos_css);
- continue;
+ compute_effective_exclusive_cpumask(cp, tmp->new_cpus, NULL);
+ if (cpumask_equal(cp->effective_xcpus, tmp->new_cpus)) {
+ pos_css = css_rightmost_descendant(pos_css);
+ continue;
+ }
+ rcu_read_unlock();
+ remote_cpus_update(cp, NULL, tmp->new_cpus, tmp);
+ rcu_read_lock();
+
+ /* Remote partition may be invalidated */
+ new_prs = cp->partition_root_state;
+ remote = (new_prs == old_prs);
}
- /*
- * Update effective_xcpus if exclusive_cpus set.
- * The case when exclusive_cpus isn't set is handled later.
- */
- if (!cpumask_empty(cp->exclusive_cpus) && (cp != cs)) {
- spin_lock_irq(&callback_lock);
- compute_effective_exclusive_cpumask(cp, NULL);
- spin_unlock_irq(&callback_lock);
- }
-
- old_prs = new_prs = cp->partition_root_state;
- if (remote || (is_partition_valid(parent) &&
- is_partition_valid(cp)))
+ if (remote || (is_partition_valid(parent) && is_partition_valid(cp)))
compute_partition_effective_cpumask(cp, tmp->new_cpus);
else
compute_effective_cpumask(tmp->new_cpus, cp, parent);
+ if (remote)
+ goto get_css; /* Ready to update cpuset data */
+
/*
* A partition with no effective_cpus is allowed as long as
* there is no task associated with it. Call
@@ -2025,9 +2079,6 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
if (is_in_v2_mode() && !remote && cpumask_empty(tmp->new_cpus))
cpumask_copy(tmp->new_cpus, parent->effective_cpus);
- if (remote)
- goto get_css;
-
/*
* Skip the whole subtree if
* 1) the cpumask remains the same,
@@ -2088,6 +2139,9 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
spin_lock_irq(&callback_lock);
cpumask_copy(cp->effective_cpus, tmp->new_cpus);
cp->partition_root_state = new_prs;
+ if (!cpumask_empty(cp->exclusive_cpus) && (cp != cs))
+ compute_effective_exclusive_cpumask(cp, NULL, NULL);
+
/*
* Make sure effective_xcpus is properly set for a valid
* partition root.
@@ -2174,7 +2228,14 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
parent);
if (cpumask_equal(tmp->new_cpus, sibling->effective_cpus))
continue;
+ } else if (is_remote_partition(sibling)) {
+ /*
+ * Change in a sibling cpuset won't affect a remote
+ * partition root.
+ */
+ continue;
}
+
if (!css_tryget_online(&sibling->css))
continue;
@@ -2231,8 +2292,9 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
* trialcs->effective_xcpus is used as a temporary cpumask
* for checking validity of the partition root.
*/
+ trialcs->partition_root_state = PRS_MEMBER;
if (!cpumask_empty(trialcs->exclusive_cpus) || is_partition_valid(cs))
- compute_effective_exclusive_cpumask(trialcs, NULL);
+ compute_effective_exclusive_cpumask(trialcs, NULL, cs);
}
/* Nothing to do if the cpus didn't change */
@@ -2305,19 +2367,13 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
* Call remote_cpus_update() to handle valid remote partition
*/
if (is_remote_partition(cs))
- remote_cpus_update(cs, xcpus, &tmp);
+ remote_cpus_update(cs, NULL, xcpus, &tmp);
else if (invalidate)
update_parent_effective_cpumask(cs, partcmd_invalidate,
NULL, &tmp);
else
update_parent_effective_cpumask(cs, partcmd_update,
xcpus, &tmp);
- } else if (!cpumask_empty(cs->exclusive_cpus)) {
- /*
- * Use trialcs->effective_cpus as a temp cpumask
- */
- remote_partition_check(cs, trialcs->effective_xcpus,
- trialcs->effective_cpus, &tmp);
}
spin_lock_irq(&callback_lock);
@@ -2369,8 +2425,15 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs,
if (cpumask_equal(cs->exclusive_cpus, trialcs->exclusive_cpus))
return 0;
- if (*buf)
- compute_effective_exclusive_cpumask(trialcs, NULL);
+ if (*buf) {
+ trialcs->partition_root_state = PRS_MEMBER;
+ /*
+ * Reject the change if there is exclusive CPUs conflict with
+ * the siblings.
+ */
+ if (compute_effective_exclusive_cpumask(trialcs, NULL, cs))
+ return -EINVAL;
+ }
/*
* Check all the descendants in update_cpumasks_hier() if
@@ -2401,8 +2464,8 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs,
if (invalidate)
remote_partition_disable(cs, &tmp);
else
- remote_cpus_update(cs, trialcs->effective_xcpus,
- &tmp);
+ remote_cpus_update(cs, trialcs->exclusive_cpus,
+ trialcs->effective_xcpus, &tmp);
} else if (invalidate) {
update_parent_effective_cpumask(cs, partcmd_invalidate,
NULL, &tmp);
@@ -2410,12 +2473,6 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs,
update_parent_effective_cpumask(cs, partcmd_update,
trialcs->effective_xcpus, &tmp);
}
- } else if (!cpumask_empty(trialcs->exclusive_cpus)) {
- /*
- * Use trialcs->effective_cpus as a temp cpumask
- */
- remote_partition_check(cs, trialcs->effective_xcpus,
- trialcs->effective_cpus, &tmp);
}
spin_lock_irq(&callback_lock);
cpumask_copy(cs->exclusive_cpus, trialcs->exclusive_cpus);
@@ -2782,7 +2839,7 @@ static int update_prstate(struct cpuset *cs, int new_prs)
int err = PERR_NONE, old_prs = cs->partition_root_state;
struct cpuset *parent = parent_cs(cs);
struct tmpmasks tmpmask;
- bool new_xcpus_state = false;
+ bool isolcpus_updated = false;
if (old_prs == new_prs)
return 0;
@@ -2796,18 +2853,7 @@ static int update_prstate(struct cpuset *cs, int new_prs)
if (alloc_cpumasks(NULL, &tmpmask))
return -ENOMEM;
- /*
- * Setup effective_xcpus if not properly set yet, it will be cleared
- * later if partition becomes invalid.
- */
- if ((new_prs > 0) && cpumask_empty(cs->exclusive_cpus)) {
- spin_lock_irq(&callback_lock);
- cpumask_and(cs->effective_xcpus,
- cs->cpus_allowed, parent->effective_xcpus);
- spin_unlock_irq(&callback_lock);
- }
-
- err = update_partition_exclusive(cs, new_prs);
+ err = update_partition_exclusive_flag(cs, new_prs);
if (err)
goto out;
@@ -2821,6 +2867,19 @@ static int update_prstate(struct cpuset *cs, int new_prs)
}
/*
+ * We don't support the creation of a new local partition with
+ * a remote partition underneath it. This unsupported
+ * setting can happen only if parent is the top_cpuset because
+ * a remote partition cannot be created underneath an existing
+ * local or remote partition.
+ */
+ if ((parent == &top_cpuset) &&
+ cpumask_intersects(cs->exclusive_cpus, subpartitions_cpus)) {
+ err = PERR_REMOTE;
+ goto out;
+ }
+
+ /*
* If parent is valid partition, enable local partiion.
* Otherwise, enable a remote partition.
*/
@@ -2835,8 +2894,9 @@ static int update_prstate(struct cpuset *cs, int new_prs)
} else if (old_prs && new_prs) {
/*
* A change in load balance state only, no change in cpumasks.
+ * Need to update isolated_cpus.
*/
- new_xcpus_state = true;
+ isolcpus_updated = true;
} else {
/*
* Switching back to member is always allowed even if it
@@ -2860,7 +2920,7 @@ static int update_prstate(struct cpuset *cs, int new_prs)
*/
if (err) {
new_prs = -new_prs;
- update_partition_exclusive(cs, new_prs);
+ update_partition_exclusive_flag(cs, new_prs);
}
spin_lock_irq(&callback_lock);
@@ -2868,14 +2928,18 @@ static int update_prstate(struct cpuset *cs, int new_prs)
WRITE_ONCE(cs->prs_err, err);
if (!is_partition_valid(cs))
reset_partition_data(cs);
- else if (new_xcpus_state)
- partition_xcpus_newstate(old_prs, new_prs, cs->effective_xcpus);
+ else if (isolcpus_updated)
+ isolated_cpus_update(old_prs, new_prs, cs->effective_xcpus);
spin_unlock_irq(&callback_lock);
- update_unbound_workqueue_cpumask(new_xcpus_state);
+ update_unbound_workqueue_cpumask(isolcpus_updated);
- /* Force update if switching back to member */
+ /* Force update if switching back to member & update effective_xcpus */
update_cpumasks_hier(cs, &tmpmask, !new_prs);
+ /* A newly created partition must have effective_xcpus set */
+ WARN_ON_ONCE(!old_prs && (new_prs > 0)
+ && cpumask_empty(cs->effective_xcpus));
+
/* Update sched domains and load balance flag */
update_partition_sd_lb(cs, old_prs);
@@ -3208,7 +3272,7 @@ int cpuset_common_seq_show(struct seq_file *sf, void *v)
return ret;
}
-static int sched_partition_show(struct seq_file *seq, void *v)
+static int cpuset_partition_show(struct seq_file *seq, void *v)
{
struct cpuset *cs = css_cs(seq_css(seq));
const char *err, *type = NULL;
@@ -3239,7 +3303,7 @@ static int sched_partition_show(struct seq_file *seq, void *v)
return 0;
}
-static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf,
+static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off)
{
struct cpuset *cs = css_cs(of_css(of));
@@ -3260,11 +3324,8 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf,
css_get(&cs->css);
cpus_read_lock();
mutex_lock(&cpuset_mutex);
- if (!is_cpuset_online(cs))
- goto out_unlock;
-
- retval = update_prstate(cs, val);
-out_unlock:
+ if (is_cpuset_online(cs))
+ retval = update_prstate(cs, val);
mutex_unlock(&cpuset_mutex);
cpus_read_unlock();
css_put(&cs->css);
@@ -3308,8 +3369,8 @@ static struct cftype dfl_files[] = {
{
.name = "cpus.partition",
- .seq_show = sched_partition_show,
- .write = sched_partition_write,
+ .seq_show = cpuset_partition_show,
+ .write = cpuset_partition_write,
.private = FILE_PARTITION_ROOT,
.flags = CFTYPE_NOT_ON_ROOT,
.file_offset = offsetof(struct cpuset, partition_file),
@@ -3475,9 +3536,6 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
cpus_read_lock();
mutex_lock(&cpuset_mutex);
- if (is_partition_valid(cs))
- update_prstate(cs, 0);
-
if (!cpuset_v2() && is_sched_load_balance(cs))
cpuset_update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
@@ -3488,6 +3546,22 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
cpus_read_unlock();
}
+static void cpuset_css_killed(struct cgroup_subsys_state *css)
+{
+ struct cpuset *cs = css_cs(css);
+
+ cpus_read_lock();
+ mutex_lock(&cpuset_mutex);
+
+ /* Reset valid partition back to member */
+ if (is_partition_valid(cs))
+ update_prstate(cs, PRS_MEMBER);
+
+ mutex_unlock(&cpuset_mutex);
+ cpus_read_unlock();
+
+}
+
static void cpuset_css_free(struct cgroup_subsys_state *css)
{
struct cpuset *cs = css_cs(css);
@@ -3609,6 +3683,7 @@ struct cgroup_subsys cpuset_cgrp_subsys = {
.css_alloc = cpuset_css_alloc,
.css_online = cpuset_css_online,
.css_offline = cpuset_css_offline,
+ .css_killed = cpuset_css_killed,
.css_free = cpuset_css_free,
.can_attach = cpuset_can_attach,
.cancel_attach = cpuset_cancel_attach,
@@ -3739,10 +3814,10 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
if (remote && cpumask_empty(&new_cpus) &&
partition_is_populated(cs, NULL)) {
+ cs->prs_err = PERR_HOTPLUG;
remote_partition_disable(cs, tmp);
compute_effective_cpumask(&new_cpus, cs, parent);
remote = false;
- cpuset_force_rebuild();
}
/*
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 4bb587d..b223915 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -318,10 +318,11 @@ __bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp)
might_sleep();
for_each_possible_cpu(cpu) {
- struct cgroup *pos = cgroup_rstat_updated_list(cgrp, cpu);
+ struct cgroup *pos;
/* Reacquire for each CPU to avoid disabling IRQs too long */
__cgroup_rstat_lock(cgrp, cpu);
+ pos = cgroup_rstat_updated_list(cgrp, cpu);
for (; pos; pos = pos->rstat_flush_next) {
struct cgroup_subsys_state *css;
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index 3b2bdca..77c8d94 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -336,16 +336,22 @@ static phys_addr_t dma_reserved_default_memory_size __initdata;
static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
{
- if (!rmem->priv) {
- struct dma_coherent_mem *mem;
+ struct dma_coherent_mem *mem = rmem->priv;
+ if (!mem) {
mem = dma_init_coherent_memory(rmem->base, rmem->base,
rmem->size, true);
if (IS_ERR(mem))
return PTR_ERR(mem);
rmem->priv = mem;
}
- dma_assign_coherent_memory(dev, rmem->priv);
+
+ /* Warn if the device potentially can't use the reserved memory */
+ if (mem->device_base + rmem->size - 1 >
+ min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit))
+ dev_warn(dev, "reserved memory is beyond device's set DMA address range\n");
+
+ dma_assign_coherent_memory(dev, mem);
return 0;
}
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 055da41..8df0dfa 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -64,8 +64,7 @@ struct cma *dma_contiguous_default_area;
* Users, who want to set the size of global CMA area for their system
* should use cma= kernel parameter.
*/
-static const phys_addr_t size_bytes __initconst =
- (phys_addr_t)CMA_SIZE_MBYTES * SZ_1M;
+#define size_bytes ((phys_addr_t)CMA_SIZE_MBYTES * SZ_1M)
static phys_addr_t size_cmdline __initdata = -1;
static phys_addr_t base_cmdline __initdata;
static phys_addr_t limit_cmdline __initdata;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index cda1270..051a329 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -910,15 +910,7 @@ int dma_set_coherent_mask(struct device *dev, u64 mask)
}
EXPORT_SYMBOL(dma_set_coherent_mask);
-/**
- * dma_addressing_limited - return if the device is addressing limited
- * @dev: device to check
- *
- * Return %true if the devices DMA mask is too small to address all memory in
- * the system, else %false. Lack of addressing bits is the prime reason for
- * bounce buffering, but might not be the only one.
- */
-bool dma_addressing_limited(struct device *dev)
+static bool __dma_addressing_limited(struct device *dev)
{
const struct dma_map_ops *ops = get_dma_ops(dev);
@@ -930,6 +922,23 @@ bool dma_addressing_limited(struct device *dev)
return false;
return !dma_direct_all_ram_mapped(dev);
}
+
+/**
+ * dma_addressing_limited - return if the device is addressing limited
+ * @dev: device to check
+ *
+ * Return %true if the devices DMA mask is too small to address all memory in
+ * the system, else %false. Lack of addressing bits is the prime reason for
+ * bounce buffering, but might not be the only one.
+ */
+bool dma_addressing_limited(struct device *dev)
+{
+ if (!__dma_addressing_limited(dev))
+ return false;
+
+ dev_dbg(dev, "device is DMA addressing limited\n");
+ return true;
+}
EXPORT_SYMBOL_GPL(dma_addressing_limited);
size_t dma_max_mapping_size(struct device *dev)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 128db74..95e7038 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3943,7 +3943,7 @@ static int merge_sched_in(struct perf_event *event, void *data)
perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
if (*perf_event_fasync(event))
- event->pending_kill = POLL_HUP;
+ event->pending_kill = POLL_ERR;
perf_event_wakeup(event);
} else {
@@ -5518,30 +5518,6 @@ static bool exclusive_event_installable(struct perf_event *event,
static void perf_free_addr_filters(struct perf_event *event);
-static void perf_pending_task_sync(struct perf_event *event)
-{
- struct callback_head *head = &event->pending_task;
-
- if (!event->pending_work)
- return;
- /*
- * If the task is queued to the current task's queue, we
- * obviously can't wait for it to complete. Simply cancel it.
- */
- if (task_work_cancel(current, head)) {
- event->pending_work = 0;
- local_dec(&event->ctx->nr_no_switch_fast);
- return;
- }
-
- /*
- * All accesses related to the event are within the same RCU section in
- * perf_pending_task(). The RCU grace period before the event is freed
- * will make sure all those accesses are complete by then.
- */
- rcuwait_wait_event(&event->pending_work_wait, !event->pending_work, TASK_UNINTERRUPTIBLE);
-}
-
/* vs perf_event_alloc() error */
static void __free_event(struct perf_event *event)
{
@@ -5599,7 +5575,6 @@ static void _free_event(struct perf_event *event)
{
irq_work_sync(&event->pending_irq);
irq_work_sync(&event->pending_disable_irq);
- perf_pending_task_sync(event);
unaccount_event(event);
@@ -5692,10 +5667,17 @@ static void perf_remove_from_owner(struct perf_event *event)
static void put_event(struct perf_event *event)
{
+ struct perf_event *parent;
+
if (!atomic_long_dec_and_test(&event->refcount))
return;
+ parent = event->parent;
_free_event(event);
+
+ /* Matches the refcount bump in inherit_event() */
+ if (parent)
+ put_event(parent);
}
/*
@@ -5779,11 +5761,6 @@ int perf_event_release_kernel(struct perf_event *event)
if (tmp == child) {
perf_remove_from_context(child, DETACH_GROUP);
list_move(&child->child_list, &free_list);
- /*
- * This matches the refcount bump in inherit_event();
- * this can't be the last reference.
- */
- put_event(event);
} else {
var = &ctx->refcount;
}
@@ -5809,7 +5786,8 @@ int perf_event_release_kernel(struct perf_event *event)
void *var = &child->ctx->refcount;
list_del(&child->child_list);
- free_event(child);
+ /* Last reference unless ->pending_task work is pending */
+ put_event(child);
/*
* Wake any perf_event_free_task() waiting for this event to be
@@ -5820,7 +5798,11 @@ int perf_event_release_kernel(struct perf_event *event)
}
no_ctx:
- put_event(event); /* Must be the 'last' reference */
+ /*
+ * Last reference unless ->pending_task work is pending on this event
+ * or any of its children.
+ */
+ put_event(event);
return 0;
}
EXPORT_SYMBOL_GPL(perf_event_release_kernel);
@@ -6093,7 +6075,7 @@ static __poll_t perf_poll(struct file *file, poll_table *wait)
if (unlikely(READ_ONCE(event->state) == PERF_EVENT_STATE_ERROR &&
event->attr.pinned))
- return events;
+ return EPOLLERR;
/*
* Pin the event->rb by taking event->mmap_mutex; otherwise
@@ -7236,12 +7218,6 @@ static void perf_pending_task(struct callback_head *head)
int rctx;
/*
- * All accesses to the event must belong to the same implicit RCU read-side
- * critical section as the ->pending_work reset. See comment in
- * perf_pending_task_sync().
- */
- rcu_read_lock();
- /*
* If we 'fail' here, that's OK, it means recursion is already disabled
* and we won't recurse 'further'.
*/
@@ -7251,9 +7227,8 @@ static void perf_pending_task(struct callback_head *head)
event->pending_work = 0;
perf_sigtrap(event);
local_dec(&event->ctx->nr_no_switch_fast);
- rcuwait_wake_up(&event->pending_work_wait);
}
- rcu_read_unlock();
+ put_event(event);
if (rctx >= 0)
perf_swevent_put_recursion_context(rctx);
@@ -10248,6 +10223,7 @@ static int __perf_event_overflow(struct perf_event *event,
!task_work_add(current, &event->pending_task, notify_mode)) {
event->pending_work = pending_id;
local_inc(&event->ctx->nr_no_switch_fast);
+ WARN_ON_ONCE(!atomic_long_inc_not_zero(&event->refcount));
event->pending_addr = 0;
if (valid_sample && (data->sample_flags & PERF_SAMPLE_ADDR))
@@ -12610,7 +12586,6 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
init_irq_work(&event->pending_irq, perf_pending_irq);
event->pending_disable_irq = IRQ_WORK_INIT_HARD(perf_pending_disable);
init_task_work(&event->pending_task, perf_pending_task);
- rcuwait_init(&event->pending_work_wait);
mutex_init(&event->mmap_mutex);
raw_spin_lock_init(&event->addr_filters.lock);
@@ -13747,8 +13722,7 @@ perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx)
* Kick perf_poll() for is_event_hup();
*/
perf_event_wakeup(parent_event);
- free_event(event);
- put_event(parent_event);
+ put_event(event);
return;
}
@@ -13872,13 +13846,11 @@ static void perf_free_event(struct perf_event *event,
list_del_init(&event->child_list);
mutex_unlock(&parent->child_mutex);
- put_event(parent);
-
raw_spin_lock_irq(&ctx->lock);
perf_group_detach(event);
list_del_event(event, ctx);
raw_spin_unlock_irq(&ctx->lock);
- free_event(event);
+ put_event(event);
}
/*
@@ -14016,6 +13988,9 @@ inherit_event(struct perf_event *parent_event,
if (IS_ERR(child_event))
return child_event;
+ get_ctx(child_ctx);
+ child_event->ctx = child_ctx;
+
pmu_ctx = find_get_pmu_context(child_event->pmu, child_ctx, child_event);
if (IS_ERR(pmu_ctx)) {
free_event(child_event);
@@ -14037,8 +14012,6 @@ inherit_event(struct perf_event *parent_event,
return NULL;
}
- get_ctx(child_ctx);
-
/*
* Make the child state follow the state of the parent event,
* not its attr.disabled bit. We hold the parent's mutex,
@@ -14059,7 +14032,6 @@ inherit_event(struct perf_event *parent_event,
local64_set(&hwc->period_left, sample_period);
}
- child_event->ctx = child_ctx;
child_event->overflow_handler = parent_event->overflow_handler;
child_event->overflow_handler_context
= parent_event->overflow_handler_context;
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 615b4e6d..8d783b5 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1956,6 +1956,9 @@ static void free_ret_instance(struct uprobe_task *utask,
* to-be-reused return instances for future uretprobes. If ri_timer()
* happens to be running right now, though, we fallback to safety and
* just perform RCU-delated freeing of ri.
+ * Admittedly, this is a rather simple use of seqcount, but it nicely
+ * abstracts away all the necessary memory barriers, so we use
+ * a well-supported kernel primitive here.
*/
if (raw_seqcount_try_begin(&utask->ri_seqcount, seq)) {
/* immediate reuse of ri without RCU GP is OK */
@@ -2016,12 +2019,20 @@ static void ri_timer(struct timer_list *timer)
/* RCU protects return_instance from freeing. */
guard(rcu)();
- write_seqcount_begin(&utask->ri_seqcount);
+ /*
+ * See free_ret_instance() for notes on seqcount use.
+ * We also employ raw API variants to avoid lockdep false-positive
+ * warning complaining about enabled preemption. The timer can only be
+ * invoked once for a uprobe_task. Therefore there can only be one
+ * writer. The reader does not require an even sequence count to make
+ * progress, so it is OK to remain preemptible on PREEMPT_RT.
+ */
+ raw_write_seqcount_begin(&utask->ri_seqcount);
for_each_ret_instance_rcu(ri, utask->return_instances)
hprobe_expire(&ri->hprobe, false);
- write_seqcount_end(&utask->ri_seqcount);
+ raw_write_seqcount_end(&utask->ri_seqcount);
}
static struct uprobe_task *alloc_utask(void)
diff --git a/kernel/fork.c b/kernel/fork.c
index c4b26cd..168681f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -498,10 +498,6 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
vma_numab_state_init(new);
dup_anon_vma_name(orig, new);
- /* track_pfn_copy() will later take care of copying internal state. */
- if (unlikely(new->vm_flags & VM_PFNMAP))
- untrack_pfn_clear(new);
-
return new;
}
@@ -672,6 +668,11 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
tmp = vm_area_dup(mpnt);
if (!tmp)
goto fail_nomem;
+
+ /* track_pfn_copy() will later take care of copying internal state. */
+ if (unlikely(tmp->vm_flags & VM_PFNMAP))
+ untrack_pfn_clear(tmp);
+
retval = vma_dup_policy(mpnt, tmp);
if (retval)
goto fail_nomem_policy;
diff --git a/kernel/params.c b/kernel/params.c
index 2509f21..e668fc9 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -760,38 +760,35 @@ void destroy_params(const struct kernel_param *params, unsigned num)
params[i].ops->free(params[i].arg);
}
-static struct module_kobject * __init locate_module_kobject(const char *name)
+struct module_kobject __modinit * lookup_or_create_module_kobject(const char *name)
{
struct module_kobject *mk;
struct kobject *kobj;
int err;
kobj = kset_find_obj(module_kset, name);
- if (kobj) {
- mk = to_module_kobject(kobj);
- } else {
- mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL);
- BUG_ON(!mk);
+ if (kobj)
+ return to_module_kobject(kobj);
- mk->mod = THIS_MODULE;
- mk->kobj.kset = module_kset;
- err = kobject_init_and_add(&mk->kobj, &module_ktype, NULL,
- "%s", name);
-#ifdef CONFIG_MODULES
- if (!err)
- err = sysfs_create_file(&mk->kobj, &module_uevent.attr);
-#endif
- if (err) {
- kobject_put(&mk->kobj);
- pr_crit("Adding module '%s' to sysfs failed (%d), the system may be unstable.\n",
- name, err);
- return NULL;
- }
+ mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL);
+ if (!mk)
+ return NULL;
- /* So that we hold reference in both cases. */
- kobject_get(&mk->kobj);
+ mk->mod = THIS_MODULE;
+ mk->kobj.kset = module_kset;
+ err = kobject_init_and_add(&mk->kobj, &module_ktype, NULL, "%s", name);
+ if (IS_ENABLED(CONFIG_MODULES) && !err)
+ err = sysfs_create_file(&mk->kobj, &module_uevent.attr);
+ if (err) {
+ kobject_put(&mk->kobj);
+ pr_crit("Adding module '%s' to sysfs failed (%d), the system may be unstable.\n",
+ name, err);
+ return NULL;
}
+ /* So that we hold reference in both cases. */
+ kobject_get(&mk->kobj);
+
return mk;
}
@@ -802,7 +799,7 @@ static void __init kernel_add_sysfs_param(const char *name,
struct module_kobject *mk;
int err;
- mk = locate_module_kobject(name);
+ mk = lookup_or_create_module_kobject(name);
if (!mk)
return;
@@ -873,7 +870,7 @@ static void __init version_sysfs_builtin(void)
int err;
for (vattr = __start___modver; vattr < __stop___modver; vattr++) {
- mk = locate_module_kobject(vattr->module_name);
+ mk = lookup_or_create_module_kobject(vattr->module_name);
if (mk) {
err = sysfs_create_file(&mk->kobj, &vattr->mattr.attr);
WARN_ON_ONCE(err);
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 1a19d69..816f07f 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -81,9 +81,23 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
if (!cpufreq_this_cpu_can_update(sg_policy->policy))
return false;
- if (unlikely(sg_policy->limits_changed)) {
- sg_policy->limits_changed = false;
- sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
+ if (unlikely(READ_ONCE(sg_policy->limits_changed))) {
+ WRITE_ONCE(sg_policy->limits_changed, false);
+ sg_policy->need_freq_update = true;
+
+ /*
+ * The above limits_changed update must occur before the reads
+ * of policy limits in cpufreq_driver_resolve_freq() or a policy
+ * limits update might be missed, so use a memory barrier to
+ * ensure it.
+ *
+ * This pairs with the write memory barrier in sugov_limits().
+ */
+ smp_mb();
+
+ return true;
+ } else if (sg_policy->need_freq_update) {
+ /* ignore_dl_rate_limit() wants a new frequency to be found. */
return true;
}
@@ -95,10 +109,22 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
unsigned int next_freq)
{
- if (sg_policy->need_freq_update)
+ if (sg_policy->need_freq_update) {
sg_policy->need_freq_update = false;
- else if (sg_policy->next_freq == next_freq)
+ /*
+ * The policy limits have changed, but if the return value of
+ * cpufreq_driver_resolve_freq() after applying the new limits
+ * is still equal to the previously selected frequency, the
+ * driver callback need not be invoked unless the driver
+ * specifically wants that to happen on every update of the
+ * policy limits.
+ */
+ if (sg_policy->next_freq == next_freq &&
+ !cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS))
+ return false;
+ } else if (sg_policy->next_freq == next_freq) {
return false;
+ }
sg_policy->next_freq = next_freq;
sg_policy->last_freq_update_time = time;
@@ -365,7 +391,7 @@ static inline bool sugov_hold_freq(struct sugov_cpu *sg_cpu) { return false; }
static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
{
if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_min)
- sg_cpu->sg_policy->limits_changed = true;
+ sg_cpu->sg_policy->need_freq_update = true;
}
static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
@@ -871,7 +897,16 @@ static void sugov_limits(struct cpufreq_policy *policy)
mutex_unlock(&sg_policy->work_lock);
}
- sg_policy->limits_changed = true;
+ /*
+ * The limits_changed update below must take place before the updates
+ * of policy limits in cpufreq_set_policy() or a policy limits update
+ * might be missed, so use a memory barrier to ensure it.
+ *
+ * This pairs with the memory barrier in sugov_should_update_freq().
+ */
+ smp_wmb();
+
+ WRITE_ONCE(sg_policy->limits_changed, true);
}
struct cpufreq_governor schedutil_gov = {
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 66bcd40..fdbf249 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -163,7 +163,7 @@ enum scx_ops_flags {
/*
* CPU cgroup support flags
*/
- SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16, /* cpu.weight */
+ SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16, /* DEPRECATED, will be removed on 6.18 */
SCX_OPS_ALL_FLAGS = SCX_OPS_KEEP_BUILTIN_IDLE |
SCX_OPS_ENQ_LAST |
@@ -3899,35 +3899,6 @@ bool scx_can_stop_tick(struct rq *rq)
DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem);
static bool scx_cgroup_enabled;
-static bool cgroup_warned_missing_weight;
-static bool cgroup_warned_missing_idle;
-
-static void scx_cgroup_warn_missing_weight(struct task_group *tg)
-{
- if (scx_ops_enable_state() == SCX_OPS_DISABLED ||
- cgroup_warned_missing_weight)
- return;
-
- if ((scx_ops.flags & SCX_OPS_HAS_CGROUP_WEIGHT) || !tg->css.parent)
- return;
-
- pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.weight\n",
- scx_ops.name);
- cgroup_warned_missing_weight = true;
-}
-
-static void scx_cgroup_warn_missing_idle(struct task_group *tg)
-{
- if (!scx_cgroup_enabled || cgroup_warned_missing_idle)
- return;
-
- if (!tg->idle)
- return;
-
- pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.idle\n",
- scx_ops.name);
- cgroup_warned_missing_idle = true;
-}
int scx_tg_online(struct task_group *tg)
{
@@ -3937,8 +3908,6 @@ int scx_tg_online(struct task_group *tg)
percpu_down_read(&scx_cgroup_rwsem);
- scx_cgroup_warn_missing_weight(tg);
-
if (scx_cgroup_enabled) {
if (SCX_HAS_OP(cgroup_init)) {
struct scx_cgroup_init_args args =
@@ -4076,9 +4045,7 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight)
void scx_group_set_idle(struct task_group *tg, bool idle)
{
- percpu_down_read(&scx_cgroup_rwsem);
- scx_cgroup_warn_missing_idle(tg);
- percpu_up_read(&scx_cgroup_rwsem);
+ /* TODO: Implement ops->cgroup_set_idle() */
}
static void scx_cgroup_lock(void)
@@ -4272,9 +4239,6 @@ static int scx_cgroup_init(void)
percpu_rwsem_assert_held(&scx_cgroup_rwsem);
- cgroup_warned_missing_weight = false;
- cgroup_warned_missing_idle = false;
-
/*
* scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk
* cgroups and init, all online cgroups are initialized.
@@ -4284,9 +4248,6 @@ static int scx_cgroup_init(void)
struct task_group *tg = css_tg(css);
struct scx_cgroup_init_args args = { .weight = tg->scx_weight };
- scx_cgroup_warn_missing_weight(tg);
- scx_cgroup_warn_missing_idle(tg);
-
if ((tg->scx_flags &
(SCX_TG_ONLINE | SCX_TG_INITED)) != SCX_TG_ONLINE)
continue;
@@ -4623,7 +4584,7 @@ static void scx_ops_bypass(bool bypass)
static void free_exit_info(struct scx_exit_info *ei)
{
- kfree(ei->dump);
+ kvfree(ei->dump);
kfree(ei->msg);
kfree(ei->bt);
kfree(ei);
@@ -4639,7 +4600,7 @@ static struct scx_exit_info *alloc_exit_info(size_t exit_dump_len)
ei->bt = kcalloc(SCX_EXIT_BT_LEN, sizeof(ei->bt[0]), GFP_KERNEL);
ei->msg = kzalloc(SCX_EXIT_MSG_LEN, GFP_KERNEL);
- ei->dump = kzalloc(exit_dump_len, GFP_KERNEL);
+ ei->dump = kvzalloc(exit_dump_len, GFP_KERNEL);
if (!ei->bt || !ei->msg || !ei->dump) {
free_exit_info(ei);
@@ -5252,6 +5213,9 @@ static int validate_ops(const struct sched_ext_ops *ops)
return -EINVAL;
}
+ if (ops->flags & SCX_OPS_HAS_CGROUP_WEIGHT)
+ pr_warn("SCX_OPS_HAS_CGROUP_WEIGHT is deprecated and a noop\n");
+
return 0;
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e43993a..0fb9bf9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7081,9 +7081,6 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
h_nr_idle = task_has_idle_policy(p);
if (task_sleep || task_delayed || !se->sched_delayed)
h_nr_runnable = 1;
- } else {
- cfs_rq = group_cfs_rq(se);
- slice = cfs_rq_min_slice(cfs_rq);
}
for_each_sched_entity(se) {
@@ -7093,6 +7090,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
if (p && &p->se == se)
return -1;
+ slice = cfs_rq_min_slice(cfs_rq);
break;
}
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 517ee25..30899a8 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -366,7 +366,7 @@ static const struct debug_obj_descr hrtimer_debug_descr;
static void *hrtimer_debug_hint(void *addr)
{
- return ((struct hrtimer *) addr)->function;
+ return ACCESS_PRIVATE((struct hrtimer *)addr, function);
}
/*
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index a47bcf7..9a38594 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -509,6 +509,7 @@ void tick_resume(void)
#ifdef CONFIG_SUSPEND
static DEFINE_RAW_SPINLOCK(tick_freeze_lock);
+static DEFINE_WAIT_OVERRIDE_MAP(tick_freeze_map, LD_WAIT_SLEEP);
static unsigned int tick_freeze_depth;
/**
@@ -528,9 +529,22 @@ void tick_freeze(void)
if (tick_freeze_depth == num_online_cpus()) {
trace_suspend_resume(TPS("timekeeping_freeze"),
smp_processor_id(), true);
+ /*
+ * All other CPUs have their interrupts disabled and are
+ * suspended to idle. Other tasks have been frozen so there
+ * is no scheduling happening. This means that there is no
+ * concurrency in the system at this point. Therefore it is
+ * okay to acquire a sleeping lock on PREEMPT_RT, such as a
+ * spinlock, because the lock cannot be held by other CPUs
+ * or threads and acquiring it cannot block.
+ *
+ * Inform lockdep about the situation.
+ */
+ lock_map_acquire_try(&tick_freeze_map);
system_state = SYSTEM_SUSPEND;
sched_clock_suspend();
timekeeping_suspend();
+ lock_map_release(&tick_freeze_map);
} else {
tick_suspend_local();
}
@@ -552,8 +566,16 @@ void tick_unfreeze(void)
raw_spin_lock(&tick_freeze_lock);
if (tick_freeze_depth == num_online_cpus()) {
+ /*
+ * Similar to tick_freeze(). On resumption the first CPU may
+ * acquire uncontended sleeping locks while other CPUs block on
+ * tick_freeze_lock.
+ */
+ lock_map_acquire_try(&tick_freeze_map);
timekeeping_resume();
sched_clock_resume();
+ lock_map_release(&tick_freeze_map);
+
system_state = SYSTEM_RUNNING;
trace_suspend_resume(TPS("timekeeping_freeze"),
smp_processor_id(), false);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 1e67d07..a009c91 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -164,10 +164,34 @@ static inline struct timespec64 tk_xtime(const struct timekeeper *tk)
return ts;
}
+static inline struct timespec64 tk_xtime_coarse(const struct timekeeper *tk)
+{
+ struct timespec64 ts;
+
+ ts.tv_sec = tk->xtime_sec;
+ ts.tv_nsec = tk->coarse_nsec;
+ return ts;
+}
+
+/*
+ * Update the nanoseconds part for the coarse time keepers. They can't rely
+ * on xtime_nsec because xtime_nsec could be adjusted by a small negative
+ * amount when the multiplication factor of the clock is adjusted, which
+ * could cause the coarse clocks to go slightly backwards. See
+ * timekeeping_apply_adjustment(). Thus we keep a separate copy for the coarse
+ * clockids which only is updated when the clock has been set or we have
+ * accumulated time.
+ */
+static inline void tk_update_coarse_nsecs(struct timekeeper *tk)
+{
+ tk->coarse_nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+}
+
static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts)
{
tk->xtime_sec = ts->tv_sec;
tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift;
+ tk_update_coarse_nsecs(tk);
}
static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts)
@@ -175,6 +199,7 @@ static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts)
tk->xtime_sec += ts->tv_sec;
tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift;
tk_normalize_xtime(tk);
+ tk_update_coarse_nsecs(tk);
}
static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm)
@@ -708,6 +733,7 @@ static void timekeeping_forward_now(struct timekeeper *tk)
tk_normalize_xtime(tk);
delta -= incr;
}
+ tk_update_coarse_nsecs(tk);
}
/**
@@ -804,8 +830,8 @@ EXPORT_SYMBOL_GPL(ktime_get_with_offset);
ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs)
{
struct timekeeper *tk = &tk_core.timekeeper;
- unsigned int seq;
ktime_t base, *offset = offsets[offs];
+ unsigned int seq;
u64 nsecs;
WARN_ON(timekeeping_suspended);
@@ -813,7 +839,7 @@ ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs)
do {
seq = read_seqcount_begin(&tk_core.seq);
base = ktime_add(tk->tkr_mono.base, *offset);
- nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+ nsecs = tk->coarse_nsec;
} while (read_seqcount_retry(&tk_core.seq, seq));
@@ -2161,7 +2187,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
struct timekeeper *real_tk = &tk_core.timekeeper;
unsigned int clock_set = 0;
int shift = 0, maxshift;
- u64 offset;
+ u64 offset, orig_offset;
guard(raw_spinlock_irqsave)(&tk_core.lock);
@@ -2172,7 +2198,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
tk->tkr_mono.cycle_last, tk->tkr_mono.mask,
tk->tkr_mono.clock->max_raw_delta);
-
+ orig_offset = offset;
/* Check if there's really nothing to do */
if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK)
return false;
@@ -2205,6 +2231,14 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
*/
clock_set |= accumulate_nsecs_to_secs(tk);
+ /*
+ * To avoid inconsistencies caused adjtimex TK_ADV_FREQ calls
+ * making small negative adjustments to the base xtime_nsec
+ * value, only update the coarse clocks if we accumulated time
+ */
+ if (orig_offset != offset)
+ tk_update_coarse_nsecs(tk);
+
timekeeping_update_from_shadow(&tk_core, clock_set);
return !!clock_set;
@@ -2248,7 +2282,7 @@ void ktime_get_coarse_real_ts64(struct timespec64 *ts)
do {
seq = read_seqcount_begin(&tk_core.seq);
- *ts = tk_xtime(tk);
+ *ts = tk_xtime_coarse(tk);
} while (read_seqcount_retry(&tk_core.seq, seq));
}
EXPORT_SYMBOL(ktime_get_coarse_real_ts64);
@@ -2271,7 +2305,7 @@ void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts)
do {
seq = read_seqcount_begin(&tk_core.seq);
- *ts = tk_xtime(tk);
+ *ts = tk_xtime_coarse(tk);
offset = tk_core.timekeeper.offs_real;
} while (read_seqcount_retry(&tk_core.seq, seq));
@@ -2350,12 +2384,12 @@ void ktime_get_coarse_ts64(struct timespec64 *ts)
do {
seq = read_seqcount_begin(&tk_core.seq);
- now = tk_xtime(tk);
+ now = tk_xtime_coarse(tk);
mono = tk->wall_to_monotonic;
} while (read_seqcount_retry(&tk_core.seq, seq));
set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec,
- now.tv_nsec + mono.tv_nsec);
+ now.tv_nsec + mono.tv_nsec);
}
EXPORT_SYMBOL(ktime_get_coarse_ts64);
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 01c2ab1..32ef27c 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -98,12 +98,12 @@ void update_vsyscall(struct timekeeper *tk)
/* CLOCK_REALTIME_COARSE */
vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE];
vdso_ts->sec = tk->xtime_sec;
- vdso_ts->nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+ vdso_ts->nsec = tk->coarse_nsec;
/* CLOCK_MONOTONIC_COARSE */
vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC_COARSE];
vdso_ts->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
- nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+ nsec = tk->coarse_nsec;
nsec = nsec + tk->wall_to_monotonic.tv_nsec;
vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec);
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 33082c4..95c6e34 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -89,8 +89,11 @@ static bool delete_fprobe_node(struct fprobe_hlist_node *node)
{
lockdep_assert_held(&fprobe_mutex);
- WRITE_ONCE(node->fp, NULL);
- hlist_del_rcu(&node->hlist);
+ /* Avoid double deleting */
+ if (READ_ONCE(node->fp) != NULL) {
+ WRITE_ONCE(node->fp, NULL);
+ hlist_del_rcu(&node->hlist);
+ }
return !!find_first_fprobe_node(node->addr);
}
@@ -411,6 +414,102 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num)
ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0);
}
+#ifdef CONFIG_MODULES
+
+#define FPROBE_IPS_BATCH_INIT 8
+/* instruction pointer address list */
+struct fprobe_addr_list {
+ int index;
+ int size;
+ unsigned long *addrs;
+};
+
+static int fprobe_addr_list_add(struct fprobe_addr_list *alist, unsigned long addr)
+{
+ unsigned long *addrs;
+
+ if (alist->index >= alist->size)
+ return -ENOMEM;
+
+ alist->addrs[alist->index++] = addr;
+ if (alist->index < alist->size)
+ return 0;
+
+ /* Expand the address list */
+ addrs = kcalloc(alist->size * 2, sizeof(*addrs), GFP_KERNEL);
+ if (!addrs)
+ return -ENOMEM;
+
+ memcpy(addrs, alist->addrs, alist->size * sizeof(*addrs));
+ alist->size *= 2;
+ kfree(alist->addrs);
+ alist->addrs = addrs;
+
+ return 0;
+}
+
+static void fprobe_remove_node_in_module(struct module *mod, struct hlist_head *head,
+ struct fprobe_addr_list *alist)
+{
+ struct fprobe_hlist_node *node;
+ int ret = 0;
+
+ hlist_for_each_entry_rcu(node, head, hlist) {
+ if (!within_module(node->addr, mod))
+ continue;
+ if (delete_fprobe_node(node))
+ continue;
+ /*
+ * If failed to update alist, just continue to update hlist.
+ * Therefore, at list user handler will not hit anymore.
+ */
+ if (!ret)
+ ret = fprobe_addr_list_add(alist, node->addr);
+ }
+}
+
+/* Handle module unloading to manage fprobe_ip_table. */
+static int fprobe_module_callback(struct notifier_block *nb,
+ unsigned long val, void *data)
+{
+ struct fprobe_addr_list alist = {.size = FPROBE_IPS_BATCH_INIT};
+ struct module *mod = data;
+ int i;
+
+ if (val != MODULE_STATE_GOING)
+ return NOTIFY_DONE;
+
+ alist.addrs = kcalloc(alist.size, sizeof(*alist.addrs), GFP_KERNEL);
+ /* If failed to alloc memory, we can not remove ips from hash. */
+ if (!alist.addrs)
+ return NOTIFY_DONE;
+
+ mutex_lock(&fprobe_mutex);
+ for (i = 0; i < FPROBE_IP_TABLE_SIZE; i++)
+ fprobe_remove_node_in_module(mod, &fprobe_ip_table[i], &alist);
+
+ if (alist.index < alist.size && alist.index > 0)
+ ftrace_set_filter_ips(&fprobe_graph_ops.ops,
+ alist.addrs, alist.index, 1, 0);
+ mutex_unlock(&fprobe_mutex);
+
+ kfree(alist.addrs);
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block fprobe_module_nb = {
+ .notifier_call = fprobe_module_callback,
+ .priority = 0,
+};
+
+static int __init init_fprobe_module(void)
+{
+ return register_module_notifier(&fprobe_module_nb);
+}
+early_initcall(init_fprobe_module);
+#endif
+
static int symbols_cmp(const void *a, const void *b)
{
const char **str_a = (const char **) a;
@@ -445,6 +544,7 @@ struct filter_match_data {
size_t index;
size_t size;
unsigned long *addrs;
+ struct module **mods;
};
static int filter_match_callback(void *data, const char *name, unsigned long addr)
@@ -458,30 +558,47 @@ static int filter_match_callback(void *data, const char *name, unsigned long add
if (!ftrace_location(addr))
return 0;
- if (match->addrs)
- match->addrs[match->index] = addr;
+ if (match->addrs) {
+ struct module *mod = __module_text_address(addr);
+ if (mod && !try_module_get(mod))
+ return 0;
+
+ match->mods[match->index] = mod;
+ match->addrs[match->index] = addr;
+ }
match->index++;
return match->index == match->size;
}
/*
* Make IP list from the filter/no-filter glob patterns.
- * Return the number of matched symbols, or -ENOENT.
+ * Return the number of matched symbols, or errno.
+ * If @addrs == NULL, this just counts the number of matched symbols. If @addrs
+ * is passed with an array, we need to pass the an @mods array of the same size
+ * to increment the module refcount for each symbol.
+ * This means we also need to call `module_put` for each element of @mods after
+ * using the @addrs.
*/
-static int ip_list_from_filter(const char *filter, const char *notfilter,
- unsigned long *addrs, size_t size)
+static int get_ips_from_filter(const char *filter, const char *notfilter,
+ unsigned long *addrs, struct module **mods,
+ size_t size)
{
struct filter_match_data match = { .filter = filter, .notfilter = notfilter,
- .index = 0, .size = size, .addrs = addrs};
+ .index = 0, .size = size, .addrs = addrs, .mods = mods};
int ret;
+ if (addrs && !mods)
+ return -EINVAL;
+
ret = kallsyms_on_each_symbol(filter_match_callback, &match);
if (ret < 0)
return ret;
- ret = module_kallsyms_on_each_symbol(NULL, filter_match_callback, &match);
- if (ret < 0)
- return ret;
+ if (IS_ENABLED(CONFIG_MODULES)) {
+ ret = module_kallsyms_on_each_symbol(NULL, filter_match_callback, &match);
+ if (ret < 0)
+ return ret;
+ }
return match.index ?: -ENOENT;
}
@@ -543,24 +660,35 @@ static int fprobe_init(struct fprobe *fp, unsigned long *addrs, int num)
*/
int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter)
{
- unsigned long *addrs;
- int ret;
+ unsigned long *addrs __free(kfree) = NULL;
+ struct module **mods __free(kfree) = NULL;
+ int ret, num;
if (!fp || !filter)
return -EINVAL;
- ret = ip_list_from_filter(filter, notfilter, NULL, FPROBE_IPS_MAX);
+ num = get_ips_from_filter(filter, notfilter, NULL, NULL, FPROBE_IPS_MAX);
+ if (num < 0)
+ return num;
+
+ addrs = kcalloc(num, sizeof(*addrs), GFP_KERNEL);
+ if (!addrs)
+ return -ENOMEM;
+
+ mods = kcalloc(num, sizeof(*mods), GFP_KERNEL);
+ if (!mods)
+ return -ENOMEM;
+
+ ret = get_ips_from_filter(filter, notfilter, addrs, mods, num);
if (ret < 0)
return ret;
- addrs = kcalloc(ret, sizeof(unsigned long), GFP_KERNEL);
- if (!addrs)
- return -ENOMEM;
- ret = ip_list_from_filter(filter, notfilter, addrs, ret);
- if (ret > 0)
- ret = register_fprobe_ips(fp, addrs, ret);
+ ret = register_fprobe_ips(fp, addrs, ret);
- kfree(addrs);
+ for (int i = 0; i < num; i++) {
+ if (mods[i])
+ module_put(mods[i]);
+ }
return ret;
}
EXPORT_SYMBOL_GPL(register_fprobe);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1a48aed..61130bb 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1297,6 +1297,8 @@ void ftrace_free_filter(struct ftrace_ops *ops)
return;
free_ftrace_hash(ops->func_hash->filter_hash);
free_ftrace_hash(ops->func_hash->notrace_hash);
+ ops->func_hash->filter_hash = EMPTY_HASH;
+ ops->func_hash->notrace_hash = EMPTY_HASH;
}
EXPORT_SYMBOL_GPL(ftrace_free_filter);
@@ -3256,6 +3258,31 @@ static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash,
}
/*
+ * Remove functions from @hash that are in @notrace_hash
+ */
+static void remove_hash(struct ftrace_hash *hash, struct ftrace_hash *notrace_hash)
+{
+ struct ftrace_func_entry *entry;
+ struct hlist_node *tmp;
+ int size;
+ int i;
+
+ /* If the notrace hash is empty, there's nothing to do */
+ if (ftrace_hash_empty(notrace_hash))
+ return;
+
+ size = 1 << hash->size_bits;
+ for (i = 0; i < size; i++) {
+ hlist_for_each_entry_safe(entry, tmp, &hash->buckets[i], hlist) {
+ if (!__ftrace_lookup_ip(notrace_hash, entry->ip))
+ continue;
+ remove_hash_entry(hash, entry);
+ kfree(entry);
+ }
+ }
+}
+
+/*
* Add to @hash only those that are in both @new_hash1 and @new_hash2
*
* The notrace_hash updates uses just the intersect_hash() function
@@ -3295,67 +3322,6 @@ static int intersect_hash(struct ftrace_hash **hash, struct ftrace_hash *new_has
return 0;
}
-/* Return a new hash that has a union of all @ops->filter_hash entries */
-static struct ftrace_hash *append_hashes(struct ftrace_ops *ops)
-{
- struct ftrace_hash *new_hash = NULL;
- struct ftrace_ops *subops;
- int size_bits;
- int ret;
-
- if (ops->func_hash->filter_hash)
- size_bits = ops->func_hash->filter_hash->size_bits;
- else
- size_bits = FTRACE_HASH_DEFAULT_BITS;
-
- list_for_each_entry(subops, &ops->subop_list, list) {
- ret = append_hash(&new_hash, subops->func_hash->filter_hash, size_bits);
- if (ret < 0) {
- free_ftrace_hash(new_hash);
- return NULL;
- }
- /* Nothing more to do if new_hash is empty */
- if (ftrace_hash_empty(new_hash))
- break;
- }
- /* Can't return NULL as that means this failed */
- return new_hash ? : EMPTY_HASH;
-}
-
-/* Make @ops trace evenything except what all its subops do not trace */
-static struct ftrace_hash *intersect_hashes(struct ftrace_ops *ops)
-{
- struct ftrace_hash *new_hash = NULL;
- struct ftrace_ops *subops;
- int size_bits;
- int ret;
-
- list_for_each_entry(subops, &ops->subop_list, list) {
- struct ftrace_hash *next_hash;
-
- if (!new_hash) {
- size_bits = subops->func_hash->notrace_hash->size_bits;
- new_hash = alloc_and_copy_ftrace_hash(size_bits, ops->func_hash->notrace_hash);
- if (!new_hash)
- return NULL;
- continue;
- }
- size_bits = new_hash->size_bits;
- next_hash = new_hash;
- new_hash = alloc_ftrace_hash(size_bits);
- ret = intersect_hash(&new_hash, next_hash, subops->func_hash->notrace_hash);
- free_ftrace_hash(next_hash);
- if (ret < 0) {
- free_ftrace_hash(new_hash);
- return NULL;
- }
- /* Nothing more to do if new_hash is empty */
- if (ftrace_hash_empty(new_hash))
- break;
- }
- return new_hash;
-}
-
static bool ops_equal(struct ftrace_hash *A, struct ftrace_hash *B)
{
struct ftrace_func_entry *entry;
@@ -3427,6 +3393,95 @@ static int ftrace_update_ops(struct ftrace_ops *ops, struct ftrace_hash *filter_
return 0;
}
+static int add_first_hash(struct ftrace_hash **filter_hash, struct ftrace_hash **notrace_hash,
+ struct ftrace_ops_hash *func_hash)
+{
+ /* If the filter hash is not empty, simply remove the nohash from it */
+ if (!ftrace_hash_empty(func_hash->filter_hash)) {
+ *filter_hash = copy_hash(func_hash->filter_hash);
+ if (!*filter_hash)
+ return -ENOMEM;
+ remove_hash(*filter_hash, func_hash->notrace_hash);
+ *notrace_hash = EMPTY_HASH;
+
+ } else {
+ *notrace_hash = copy_hash(func_hash->notrace_hash);
+ if (!*notrace_hash)
+ return -ENOMEM;
+ *filter_hash = EMPTY_HASH;
+ }
+ return 0;
+}
+
+static int add_next_hash(struct ftrace_hash **filter_hash, struct ftrace_hash **notrace_hash,
+ struct ftrace_ops_hash *ops_hash, struct ftrace_ops_hash *subops_hash)
+{
+ int size_bits;
+ int ret;
+
+ /* If the subops trace all functions so must the main ops */
+ if (ftrace_hash_empty(ops_hash->filter_hash) ||
+ ftrace_hash_empty(subops_hash->filter_hash)) {
+ *filter_hash = EMPTY_HASH;
+ } else {
+ /*
+ * The main ops filter hash is not empty, so its
+ * notrace_hash had better be, as the notrace hash
+ * is only used for empty main filter hashes.
+ */
+ WARN_ON_ONCE(!ftrace_hash_empty(ops_hash->notrace_hash));
+
+ size_bits = max(ops_hash->filter_hash->size_bits,
+ subops_hash->filter_hash->size_bits);
+
+ /* Copy the subops hash */
+ *filter_hash = alloc_and_copy_ftrace_hash(size_bits, subops_hash->filter_hash);
+ if (!filter_hash)
+ return -ENOMEM;
+ /* Remove any notrace functions from the copy */
+ remove_hash(*filter_hash, subops_hash->notrace_hash);
+
+ ret = append_hash(filter_hash, ops_hash->filter_hash,
+ size_bits);
+ if (ret < 0) {
+ free_ftrace_hash(*filter_hash);
+ *filter_hash = EMPTY_HASH;
+ return ret;
+ }
+ }
+
+ /*
+ * Only process notrace hashes if the main filter hash is empty
+ * (tracing all functions), otherwise the filter hash will just
+ * remove the notrace hash functions, and the notrace hash is
+ * not needed.
+ */
+ if (ftrace_hash_empty(*filter_hash)) {
+ /*
+ * Intersect the notrace functions. That is, if two
+ * subops are not tracing a set of functions, the
+ * main ops will only not trace the functions that are
+ * in both subops, but has to trace the functions that
+ * are only notrace in one of the subops, for the other
+ * subops to be able to trace them.
+ */
+ size_bits = max(ops_hash->notrace_hash->size_bits,
+ subops_hash->notrace_hash->size_bits);
+ *notrace_hash = alloc_ftrace_hash(size_bits);
+ if (!*notrace_hash)
+ return -ENOMEM;
+
+ ret = intersect_hash(notrace_hash, ops_hash->notrace_hash,
+ subops_hash->notrace_hash);
+ if (ret < 0) {
+ free_ftrace_hash(*notrace_hash);
+ *notrace_hash = EMPTY_HASH;
+ return ret;
+ }
+ }
+ return 0;
+}
+
/**
* ftrace_startup_subops - enable tracing for subops of an ops
* @ops: Manager ops (used to pick all the functions of its subops)
@@ -3439,11 +3494,10 @@ static int ftrace_update_ops(struct ftrace_ops *ops, struct ftrace_hash *filter_
*/
int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int command)
{
- struct ftrace_hash *filter_hash;
- struct ftrace_hash *notrace_hash;
+ struct ftrace_hash *filter_hash = EMPTY_HASH;
+ struct ftrace_hash *notrace_hash = EMPTY_HASH;
struct ftrace_hash *save_filter_hash;
struct ftrace_hash *save_notrace_hash;
- int size_bits;
int ret;
if (unlikely(ftrace_disabled))
@@ -3467,14 +3521,14 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int
/* For the first subops to ops just enable it normally */
if (list_empty(&ops->subop_list)) {
- /* Just use the subops hashes */
- filter_hash = copy_hash(subops->func_hash->filter_hash);
- notrace_hash = copy_hash(subops->func_hash->notrace_hash);
- if (!filter_hash || !notrace_hash) {
- free_ftrace_hash(filter_hash);
- free_ftrace_hash(notrace_hash);
- return -ENOMEM;
- }
+
+ /* The ops was empty, should have empty hashes */
+ WARN_ON_ONCE(!ftrace_hash_empty(ops->func_hash->filter_hash));
+ WARN_ON_ONCE(!ftrace_hash_empty(ops->func_hash->notrace_hash));
+
+ ret = add_first_hash(&filter_hash, ¬race_hash, subops->func_hash);
+ if (ret < 0)
+ return ret;
save_filter_hash = ops->func_hash->filter_hash;
save_notrace_hash = ops->func_hash->notrace_hash;
@@ -3500,48 +3554,16 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int
/*
* Here there's already something attached. Here are the rules:
- * o If either filter_hash is empty then the final stays empty
- * o Otherwise, the final is a superset of both hashes
- * o If either notrace_hash is empty then the final stays empty
- * o Otherwise, the final is an intersection between the hashes
+ * If the new subops and main ops filter hashes are not empty:
+ * o Make a copy of the subops filter hash
+ * o Remove all functions in the nohash from it.
+ * o Add in the main hash filter functions
+ * o Remove any of these functions from the main notrace hash
*/
- if (ftrace_hash_empty(ops->func_hash->filter_hash) ||
- ftrace_hash_empty(subops->func_hash->filter_hash)) {
- filter_hash = EMPTY_HASH;
- } else {
- size_bits = max(ops->func_hash->filter_hash->size_bits,
- subops->func_hash->filter_hash->size_bits);
- filter_hash = alloc_and_copy_ftrace_hash(size_bits, ops->func_hash->filter_hash);
- if (!filter_hash)
- return -ENOMEM;
- ret = append_hash(&filter_hash, subops->func_hash->filter_hash,
- size_bits);
- if (ret < 0) {
- free_ftrace_hash(filter_hash);
- return ret;
- }
- }
- if (ftrace_hash_empty(ops->func_hash->notrace_hash) ||
- ftrace_hash_empty(subops->func_hash->notrace_hash)) {
- notrace_hash = EMPTY_HASH;
- } else {
- size_bits = max(ops->func_hash->filter_hash->size_bits,
- subops->func_hash->filter_hash->size_bits);
- notrace_hash = alloc_ftrace_hash(size_bits);
- if (!notrace_hash) {
- free_ftrace_hash(filter_hash);
- return -ENOMEM;
- }
-
- ret = intersect_hash(¬race_hash, ops->func_hash->filter_hash,
- subops->func_hash->filter_hash);
- if (ret < 0) {
- free_ftrace_hash(filter_hash);
- free_ftrace_hash(notrace_hash);
- return ret;
- }
- }
+ ret = add_next_hash(&filter_hash, ¬race_hash, ops->func_hash, subops->func_hash);
+ if (ret < 0)
+ return ret;
list_add(&subops->list, &ops->subop_list);
@@ -3557,6 +3579,45 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int
return ret;
}
+static int rebuild_hashes(struct ftrace_hash **filter_hash, struct ftrace_hash **notrace_hash,
+ struct ftrace_ops *ops)
+{
+ struct ftrace_ops_hash temp_hash;
+ struct ftrace_ops *subops;
+ bool first = true;
+ int ret;
+
+ temp_hash.filter_hash = EMPTY_HASH;
+ temp_hash.notrace_hash = EMPTY_HASH;
+
+ list_for_each_entry(subops, &ops->subop_list, list) {
+ *filter_hash = EMPTY_HASH;
+ *notrace_hash = EMPTY_HASH;
+
+ if (first) {
+ ret = add_first_hash(filter_hash, notrace_hash, subops->func_hash);
+ if (ret < 0)
+ return ret;
+ first = false;
+ } else {
+ ret = add_next_hash(filter_hash, notrace_hash,
+ &temp_hash, subops->func_hash);
+ if (ret < 0) {
+ free_ftrace_hash(temp_hash.filter_hash);
+ free_ftrace_hash(temp_hash.notrace_hash);
+ return ret;
+ }
+ }
+
+ free_ftrace_hash(temp_hash.filter_hash);
+ free_ftrace_hash(temp_hash.notrace_hash);
+
+ temp_hash.filter_hash = *filter_hash;
+ temp_hash.notrace_hash = *notrace_hash;
+ }
+ return 0;
+}
+
/**
* ftrace_shutdown_subops - Remove a subops from a manager ops
* @ops: A manager ops to remove @subops from
@@ -3571,8 +3632,8 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int
*/
int ftrace_shutdown_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int command)
{
- struct ftrace_hash *filter_hash;
- struct ftrace_hash *notrace_hash;
+ struct ftrace_hash *filter_hash = EMPTY_HASH;
+ struct ftrace_hash *notrace_hash = EMPTY_HASH;
int ret;
if (unlikely(ftrace_disabled))
@@ -3605,14 +3666,9 @@ int ftrace_shutdown_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, in
}
/* Rebuild the hashes without subops */
- filter_hash = append_hashes(ops);
- notrace_hash = intersect_hashes(ops);
- if (!filter_hash || !notrace_hash) {
- free_ftrace_hash(filter_hash);
- free_ftrace_hash(notrace_hash);
- list_add(&subops->list, &ops->subop_list);
- return -ENOMEM;
- }
+ ret = rebuild_hashes(&filter_hash, ¬race_hash, ops);
+ if (ret < 0)
+ return ret;
ret = ftrace_update_ops(ops, filter_hash, notrace_hash);
if (ret < 0) {
@@ -3628,11 +3684,11 @@ int ftrace_shutdown_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, in
static int ftrace_hash_move_and_update_subops(struct ftrace_ops *subops,
struct ftrace_hash **orig_subhash,
- struct ftrace_hash *hash,
- int enable)
+ struct ftrace_hash *hash)
{
struct ftrace_ops *ops = subops->managed;
- struct ftrace_hash **orig_hash;
+ struct ftrace_hash *notrace_hash;
+ struct ftrace_hash *filter_hash;
struct ftrace_hash *save_hash;
struct ftrace_hash *new_hash;
int ret;
@@ -3649,24 +3705,18 @@ static int ftrace_hash_move_and_update_subops(struct ftrace_ops *subops,
return -ENOMEM;
}
- /* Create a new_hash to hold the ops new functions */
- if (enable) {
- orig_hash = &ops->func_hash->filter_hash;
- new_hash = append_hashes(ops);
- } else {
- orig_hash = &ops->func_hash->notrace_hash;
- new_hash = intersect_hashes(ops);
+ ret = rebuild_hashes(&filter_hash, ¬race_hash, ops);
+ if (!ret) {
+ ret = ftrace_update_ops(ops, filter_hash, notrace_hash);
+ free_ftrace_hash(filter_hash);
+ free_ftrace_hash(notrace_hash);
}
- /* Move the hash over to the new hash */
- ret = __ftrace_hash_move_and_update_ops(ops, orig_hash, new_hash, enable);
-
- free_ftrace_hash(new_hash);
-
if (ret) {
/* Put back the original hash */
- free_ftrace_hash_rcu(*orig_subhash);
+ new_hash = *orig_subhash;
*orig_subhash = save_hash;
+ free_ftrace_hash_rcu(new_hash);
} else {
free_ftrace_hash_rcu(save_hash);
}
@@ -4890,7 +4940,7 @@ static int ftrace_hash_move_and_update_ops(struct ftrace_ops *ops,
int enable)
{
if (ops->flags & FTRACE_OPS_FL_SUBOP)
- return ftrace_hash_move_and_update_subops(ops, orig_hash, hash, enable);
+ return ftrace_hash_move_and_update_subops(ops, orig_hash, hash);
/*
* If this ops is not enabled, it could be sharing its filters
@@ -4909,7 +4959,7 @@ static int ftrace_hash_move_and_update_ops(struct ftrace_ops *ops,
list_for_each_entry(subops, &op->subop_list, list) {
if ((subops->flags & FTRACE_OPS_FL_ENABLED) &&
subops->func_hash == ops->func_hash) {
- return ftrace_hash_move_and_update_subops(subops, orig_hash, hash, enable);
+ return ftrace_hash_move_and_update_subops(subops, orig_hash, hash);
}
}
} while_for_each_ftrace_op(op);
@@ -5914,9 +5964,10 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
/* Make a copy hash to place the new and the old entries in */
size = hash->count + direct_functions->count;
- if (size > 32)
- size = 32;
- new_hash = alloc_ftrace_hash(fls(size));
+ size = fls(size);
+ if (size > FTRACE_HASH_MAX_BITS)
+ size = FTRACE_HASH_MAX_BITS;
+ new_hash = alloc_ftrace_hash(size);
if (!new_hash)
goto out_unlock;
diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c
index 968c5c3..e407750 100644
--- a/kernel/trace/rv/rv.c
+++ b/kernel/trace/rv/rv.c
@@ -225,7 +225,12 @@ bool rv_is_nested_monitor(struct rv_monitor_def *mdef)
*/
bool rv_is_container_monitor(struct rv_monitor_def *mdef)
{
- struct rv_monitor_def *next = list_next_entry(mdef, list);
+ struct rv_monitor_def *next;
+
+ if (list_is_last(&mdef->list, &rv_monitors_list))
+ return false;
+
+ next = list_next_entry(mdef, list);
return next->parent == mdef->monitor || !mdef->monitor->enable;
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index b581e38..8ddf6b1 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9806,6 +9806,7 @@ static int instance_mkdir(const char *name)
return ret;
}
+#ifdef CONFIG_MMU
static u64 map_pages(unsigned long start, unsigned long size)
{
unsigned long vmap_start, vmap_end;
@@ -9828,6 +9829,12 @@ static u64 map_pages(unsigned long start, unsigned long size)
return (u64)vmap_start;
}
+#else
+static inline u64 map_pages(unsigned long start, unsigned long size)
+{
+ return 0;
+}
+#endif
/**
* trace_array_get_by_name - Create/Lookup a trace array, given its name.
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index ee40d4e..4ef4df6 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -80,11 +80,11 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry,
F_STRUCT(
__field_struct( struct ftrace_graph_ent, graph_ent )
__field_packed( unsigned long, graph_ent, func )
- __field_packed( unsigned long, graph_ent, depth )
+ __field_packed( unsigned int, graph_ent, depth )
__dynamic_array(unsigned long, args )
),
- F_printk("--> %ps (%lu)", (void *)__entry->func, __entry->depth)
+ F_printk("--> %ps (%u)", (void *)__entry->func, __entry->depth)
);
#ifdef CONFIG_FUNCTION_GRAPH_RETADDR
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 0993dfc..2048560 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -808,7 +808,7 @@ static __always_inline char *test_string(char *str)
kstr = ubuf->buffer;
/* For safety, do not trust the string pointer */
- if (!strncpy_from_kernel_nofault(kstr, str, USTRING_BUF_SIZE))
+ if (strncpy_from_kernel_nofault(kstr, str, USTRING_BUF_SIZE) < 0)
return NULL;
return kstr;
}
@@ -827,7 +827,7 @@ static __always_inline char *test_ustring(char *str)
/* user space address? */
ustr = (char __user *)str;
- if (!strncpy_from_user_nofault(kstr, ustr, USTRING_BUF_SIZE))
+ if (strncpy_from_user_nofault(kstr, ustr, USTRING_BUF_SIZE) < 0)
return NULL;
return kstr;
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 969f487..33cfbd4 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -370,7 +370,6 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter,
union trace_synth_field *data = &entry->fields[n_u64];
trace_seq_printf(s, print_fmt, se->fields[i]->name,
- STR_VAR_LEN_MAX,
(char *)entry + data->as_dynamic.offset,
i == se->n_fields - 1 ? "" : " ");
n_u64++;
diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index 5d7ca80..b40fa59 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -919,9 +919,15 @@ static void __find_tracepoint_module_cb(struct tracepoint *tp, struct module *mo
struct __find_tracepoint_cb_data *data = priv;
if (!data->tpoint && !strcmp(data->tp_name, tp->name)) {
- data->tpoint = tp;
- if (!data->mod)
+ /* If module is not specified, try getting module refcount. */
+ if (!data->mod && mod) {
+ /* If failed to get refcount, ignore this tracepoint. */
+ if (!try_module_get(mod))
+ return;
+
data->mod = mod;
+ }
+ data->tpoint = tp;
}
}
@@ -933,7 +939,11 @@ static void __find_tracepoint_cb(struct tracepoint *tp, void *priv)
data->tpoint = tp;
}
-/* Find a tracepoint from kernel and module. */
+/*
+ * Find a tracepoint from kernel and module. If the tracepoint is on the module,
+ * the module's refcount is incremented and returned as *@tp_mod. Thus, if it is
+ * not NULL, caller must call module_put(*tp_mod) after used the tracepoint.
+ */
static struct tracepoint *find_tracepoint(const char *tp_name,
struct module **tp_mod)
{
@@ -962,7 +972,10 @@ static void reenable_trace_fprobe(struct trace_fprobe *tf)
}
}
-/* Find a tracepoint from specified module. */
+/*
+ * Find a tracepoint from specified module. In this case, this does not get the
+ * module's refcount. The caller must ensure the module is not freed.
+ */
static struct tracepoint *find_tracepoint_in_module(struct module *mod,
const char *tp_name)
{
@@ -1169,11 +1182,6 @@ static int trace_fprobe_create_internal(int argc, const char *argv[],
if (is_tracepoint) {
ctx->flags |= TPARG_FL_TPOINT;
tpoint = find_tracepoint(symbol, &tp_mod);
- /* lock module until register this tprobe. */
- if (tp_mod && !try_module_get(tp_mod)) {
- tpoint = NULL;
- tp_mod = NULL;
- }
if (tpoint) {
ctx->funcname = kallsyms_lookup(
(unsigned long)tpoint->probestub,
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 2f077d4..0c357a8 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -880,8 +880,6 @@ static void print_graph_retval(struct trace_seq *s, struct ftrace_graph_ent_entr
if (print_retval || print_retaddr)
trace_seq_puts(s, " /*");
- else
- trace_seq_putc(s, '\n');
} else {
print_retaddr = false;
trace_seq_printf(s, "} /* %ps", func);
@@ -899,7 +897,7 @@ static void print_graph_retval(struct trace_seq *s, struct ftrace_graph_ent_entr
}
if (!entry || print_retval || print_retaddr)
- trace_seq_puts(s, " */\n");
+ trace_seq_puts(s, " */");
}
#else
@@ -975,7 +973,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
} else
trace_seq_puts(s, "();");
}
- trace_seq_printf(s, "\n");
+ trace_seq_putc(s, '\n');
print_graph_irq(iter, graph_ret->func, TRACE_GRAPH_RET,
cpu, iter->ent->pid, flags);
@@ -1313,10 +1311,11 @@ print_graph_return(struct ftrace_graph_ret_entry *retentry, struct trace_seq *s,
* that if the funcgraph-tail option is enabled.
*/
if (func_match && !(flags & TRACE_GRAPH_PRINT_TAIL))
- trace_seq_puts(s, "}\n");
+ trace_seq_puts(s, "}");
else
- trace_seq_printf(s, "} /* %ps */\n", (void *)func);
+ trace_seq_printf(s, "} /* %ps */", (void *)func);
}
+ trace_seq_putc(s, '\n');
/* Overrun */
if (flags & TRACE_GRAPH_PRINT_OVERRUN)
diff --git a/kernel/vhost_task.c b/kernel/vhost_task.c
index 2ef2e1b..2f844c2 100644
--- a/kernel/vhost_task.c
+++ b/kernel/vhost_task.c
@@ -111,7 +111,7 @@ EXPORT_SYMBOL_GPL(vhost_task_stop);
* @arg: data to be passed to fn and handled_kill
* @name: the thread's name
*
- * This returns a specialized task for use by the vhost layer or NULL on
+ * This returns a specialized task for use by the vhost layer or ERR_PTR() on
* failure. The returned task is inactive, and the caller must fire it up
* through vhost_task_start().
*/
diff --git a/lib/Kconfig b/lib/Kconfig
index 61cce06..6c1b8f1 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -139,27 +139,22 @@
source "lib/crypto/Kconfig"
config CRC_CCITT
- tristate "CRC-CCITT functions"
+ tristate
help
- This option is provided for the case where no in-kernel-tree
- modules require CRC-CCITT functions, but a module built outside
- the kernel tree does. Such modules that use library CRC-CCITT
- functions require M here.
+ The CRC-CCITT library functions. Select this if your module uses any
+ of the functions from <linux/crc-ccitt.h>.
config CRC16
- tristate "CRC16 functions"
+ tristate
help
- This option is provided for the case where no in-kernel-tree
- modules require CRC16 functions, but a module built outside
- the kernel tree does. Such modules that use library CRC16
- functions require M here.
+ The CRC16 library functions. Select this if your module uses any of
+ the functions from <linux/crc16.h>.
config CRC_T10DIF
- tristate "CRC calculation for the T10 Data Integrity Field"
+ tristate
help
- This option is only needed if a module that's not in the
- kernel tree needs to calculate CRC checks for use with the
- SCSI data integrity subsystem.
+ The CRC-T10DIF library functions. Select this if your module uses
+ any of the functions from <linux/crc-t10dif.h>.
config ARCH_HAS_CRC_T10DIF
bool
@@ -169,22 +164,17 @@
default CRC_T10DIF if ARCH_HAS_CRC_T10DIF && CRC_OPTIMIZATIONS
config CRC_ITU_T
- tristate "CRC ITU-T V.41 functions"
+ tristate
help
- This option is provided for the case where no in-kernel-tree
- modules require CRC ITU-T V.41 functions, but a module built outside
- the kernel tree does. Such modules that use library CRC ITU-T V.41
- functions require M here.
+ The CRC-ITU-T library functions. Select this if your module uses
+ any of the functions from <linux/crc-itu-t.h>.
config CRC32
- tristate "CRC32/CRC32c functions"
- default y
+ tristate
select BITREVERSE
help
- This option is provided for the case where no in-kernel-tree
- modules require CRC32/CRC32c functions, but a module built outside
- the kernel tree does. Such modules that use library CRC32/CRC32c
- functions require M here.
+ The CRC32 library functions. Select this if your module uses any of
+ the functions from <linux/crc32.h> or <linux/crc32c.h>.
config ARCH_HAS_CRC32
bool
@@ -195,6 +185,9 @@
config CRC64
tristate
+ help
+ The CRC64 library functions. Select this if your module uses any of
+ the functions from <linux/crc64.h>.
config ARCH_HAS_CRC64
bool
@@ -205,19 +198,21 @@
config CRC4
tristate
+ help
+ The CRC4 library functions. Select this if your module uses any of
+ the functions from <linux/crc4.h>.
config CRC7
tristate
-
-config LIBCRC32C
- tristate
- select CRC32
help
- This option just selects CRC32 and is provided for compatibility
- purposes until the users are updated to select CRC32 directly.
+ The CRC7 library functions. Select this if your module uses any of
+ the functions from <linux/crc7.h>.
config CRC8
tristate
+ help
+ The CRC8 library functions. Select this if your module uses any of
+ the functions from <linux/crc8.h>.
config CRC_OPTIMIZATIONS
bool "Enable optimized CRC implementations" if EXPERT
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 9fe4d8d..f9051ab 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -3290,7 +3290,7 @@
config PRIME_NUMBERS_KUNIT_TEST
tristate "Prime number generator test" if !KUNIT_ALL_TESTS
depends on KUNIT
- select PRIME_NUMBERS
+ depends on PRIME_NUMBERS
default KUNIT_ALL_TESTS
help
This option enables the KUnit test suite for the {is,next}_prime_number
diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan
index 4216b3a..f6ea0c5 100644
--- a/lib/Kconfig.ubsan
+++ b/lib/Kconfig.ubsan
@@ -118,7 +118,6 @@
config UBSAN_INTEGER_WRAP
bool "Perform checking for integer arithmetic wrap-around"
- default UBSAN
depends on !COMPILE_TEST
depends on $(cc-option,-fsanitize-undefined-ignore-overflow-pattern=all)
depends on $(cc-option,-fsanitize=signed-integer-overflow)
diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c
index 1d893e3..25ecc13 100644
--- a/lib/alloc_tag.c
+++ b/lib/alloc_tag.c
@@ -422,11 +422,20 @@ static int vm_module_tags_populate(void)
unsigned long old_shadow_end = ALIGN(phys_end, MODULE_ALIGN);
unsigned long new_shadow_end = ALIGN(new_end, MODULE_ALIGN);
unsigned long more_pages;
- unsigned long nr;
+ unsigned long nr = 0;
more_pages = ALIGN(new_end - phys_end, PAGE_SIZE) >> PAGE_SHIFT;
- nr = alloc_pages_bulk_node(GFP_KERNEL | __GFP_NOWARN,
- NUMA_NO_NODE, more_pages, next_page);
+ while (nr < more_pages) {
+ unsigned long allocated;
+
+ allocated = alloc_pages_bulk_node(GFP_KERNEL | __GFP_NOWARN,
+ NUMA_NO_NODE, more_pages - nr, next_page + nr);
+
+ if (!allocated)
+ break;
+ nr += allocated;
+ }
+
if (nr < more_pages ||
vmap_pages_range(phys_end, phys_end + (nr << PAGE_SHIFT), PAGE_KERNEL,
next_page, PAGE_SHIFT) < 0) {
diff --git a/lib/asn1_decoder.c b/lib/asn1_decoder.c
index 13da529..5738ae2 100644
--- a/lib/asn1_decoder.c
+++ b/lib/asn1_decoder.c
@@ -518,4 +518,5 @@ int asn1_ber_decoder(const struct asn1_decoder *decoder,
}
EXPORT_SYMBOL_GPL(asn1_ber_decoder);
+MODULE_DESCRIPTION("Decoder for ASN.1 BER/DER/CER encoded bytestream");
MODULE_LICENSE("GPL");
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 8c7fdb7..bc9391e 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1191,7 +1191,7 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i,
return -ENOMEM;
p = *pages;
for (int k = 0; k < n; k++) {
- struct folio *folio = page_folio(page);
+ struct folio *folio = page_folio(page + k);
p[k] = page + k;
if (!folio_test_slab(folio))
folio_get(folio);
diff --git a/lib/string.c b/lib/string.c
index eb4486e..b632c71 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -119,6 +119,7 @@ ssize_t sized_strscpy(char *dest, const char *src, size_t count)
if (count == 0 || WARN_ON_ONCE(count > INT_MAX))
return -E2BIG;
+#ifndef CONFIG_DCACHE_WORD_ACCESS
#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
/*
* If src is unaligned, don't cross a page boundary,
@@ -134,11 +135,13 @@ ssize_t sized_strscpy(char *dest, const char *src, size_t count)
if (((long) dest | (long) src) & (sizeof(long) - 1))
max = 0;
#endif
+#endif
/*
- * read_word_at_a_time() below may read uninitialized bytes after the
- * trailing zero and use them in comparisons. Disable this optimization
- * under KMSAN to prevent false positive reports.
+ * load_unaligned_zeropad() or read_word_at_a_time() below may read
+ * uninitialized bytes after the trailing zero and use them in
+ * comparisons. Disable this optimization under KMSAN to prevent
+ * false positive reports.
*/
if (IS_ENABLED(CONFIG_KMSAN))
max = 0;
@@ -146,7 +149,11 @@ ssize_t sized_strscpy(char *dest, const char *src, size_t count)
while (max >= sizeof(unsigned long)) {
unsigned long c, data;
+#ifdef CONFIG_DCACHE_WORD_ACCESS
+ c = load_unaligned_zeropad(src+res);
+#else
c = read_word_at_a_time(src+res);
+#endif
if (has_zero(c, &data, &constants)) {
data = prep_zero_mask(c, data, &constants);
data = create_zero_mask(data);
diff --git a/lib/test_ubsan.c b/lib/test_ubsan.c
index 8772e5e..a4b6f52 100644
--- a/lib/test_ubsan.c
+++ b/lib/test_ubsan.c
@@ -77,18 +77,22 @@ static void test_ubsan_shift_out_of_bounds(void)
static void test_ubsan_out_of_bounds(void)
{
- volatile int i = 4, j = 5, k = -1;
- volatile char above[4] = { }; /* Protect surrounding memory. */
- volatile int arr[4];
- volatile char below[4] = { }; /* Protect surrounding memory. */
+ int i = 4, j = 4, k = -1;
+ volatile struct {
+ char above[4]; /* Protect surrounding memory. */
+ int arr[4];
+ char below[4]; /* Protect surrounding memory. */
+ } data;
- above[0] = below[0];
+ OPTIMIZER_HIDE_VAR(i);
+ OPTIMIZER_HIDE_VAR(j);
+ OPTIMIZER_HIDE_VAR(k);
UBSAN_TEST(CONFIG_UBSAN_BOUNDS, "above");
- arr[j] = i;
+ data.arr[j] = i;
UBSAN_TEST(CONFIG_UBSAN_BOUNDS, "below");
- arr[k] = i;
+ data.arr[k] = i;
}
enum ubsan_test_enum {
diff --git a/lib/tests/slub_kunit.c b/lib/tests/slub_kunit.c
index d47c472..848b682 100644
--- a/lib/tests/slub_kunit.c
+++ b/lib/tests/slub_kunit.c
@@ -325,4 +325,5 @@ static struct kunit_suite test_suite = {
};
kunit_test_suite(test_suite);
+MODULE_DESCRIPTION("Kunit tests for slub allocator");
MODULE_LICENSE("GPL");
diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c
index 9308bcf..dfb4f23 100644
--- a/lib/ucs2_string.c
+++ b/lib/ucs2_string.c
@@ -165,4 +165,5 @@ ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength)
}
EXPORT_SYMBOL(ucs2_as_utf8);
+MODULE_DESCRIPTION("UCS2 string handling");
MODULE_LICENSE("GPL v2");
diff --git a/lib/zlib_inflate/inflate_syms.c b/lib/zlib_inflate/inflate_syms.c
index 9720114..b8996d9 100644
--- a/lib/zlib_inflate/inflate_syms.c
+++ b/lib/zlib_inflate/inflate_syms.c
@@ -18,4 +18,5 @@ EXPORT_SYMBOL(zlib_inflateEnd);
EXPORT_SYMBOL(zlib_inflateReset);
EXPORT_SYMBOL(zlib_inflateIncomp);
EXPORT_SYMBOL(zlib_inflate_blob);
+MODULE_DESCRIPTION("Data decompression using the deflation algorithm");
MODULE_LICENSE("GPL");
diff --git a/mm/cma.c b/mm/cma.c
index b06d5fe..1563293 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -35,7 +35,7 @@
struct cma cma_areas[MAX_CMA_AREAS];
unsigned int cma_area_count;
-static int __init __cma_declare_contiguous_nid(phys_addr_t base,
+static int __init __cma_declare_contiguous_nid(phys_addr_t *basep,
phys_addr_t size, phys_addr_t limit,
phys_addr_t alignment, unsigned int order_per_bit,
bool fixed, const char *name, struct cma **res_cma,
@@ -370,7 +370,7 @@ int __init cma_declare_contiguous_multi(phys_addr_t total_size,
phys_addr_t align, unsigned int order_per_bit,
const char *name, struct cma **res_cma, int nid)
{
- phys_addr_t start, end;
+ phys_addr_t start = 0, end;
phys_addr_t size, sizesum, sizeleft;
struct cma_init_memrange *mrp, *mlp, *failed;
struct cma_memrange *cmrp;
@@ -384,7 +384,7 @@ int __init cma_declare_contiguous_multi(phys_addr_t total_size,
/*
* First, try it the normal way, producing just one range.
*/
- ret = __cma_declare_contiguous_nid(0, total_size, 0, align,
+ ret = __cma_declare_contiguous_nid(&start, total_size, 0, align,
order_per_bit, false, name, res_cma, nid);
if (ret != -ENOMEM)
goto out;
@@ -580,7 +580,7 @@ int __init cma_declare_contiguous_nid(phys_addr_t base,
{
int ret;
- ret = __cma_declare_contiguous_nid(base, size, limit, alignment,
+ ret = __cma_declare_contiguous_nid(&base, size, limit, alignment,
order_per_bit, fixed, name, res_cma, nid);
if (ret != 0)
pr_err("Failed to reserve %ld MiB\n",
@@ -592,14 +592,14 @@ int __init cma_declare_contiguous_nid(phys_addr_t base,
return ret;
}
-static int __init __cma_declare_contiguous_nid(phys_addr_t base,
+static int __init __cma_declare_contiguous_nid(phys_addr_t *basep,
phys_addr_t size, phys_addr_t limit,
phys_addr_t alignment, unsigned int order_per_bit,
bool fixed, const char *name, struct cma **res_cma,
int nid)
{
phys_addr_t memblock_end = memblock_end_of_DRAM();
- phys_addr_t highmem_start;
+ phys_addr_t highmem_start, base = *basep;
int ret;
/*
@@ -722,12 +722,15 @@ static int __init __cma_declare_contiguous_nid(phys_addr_t base,
}
ret = cma_init_reserved_mem(base, size, order_per_bit, name, res_cma);
- if (ret)
+ if (ret) {
memblock_phys_free(base, size);
+ return ret;
+ }
(*res_cma)->nid = nid;
+ *basep = base;
- return ret;
+ return 0;
}
static void cma_debug_show_areas(struct cma *cma)
diff --git a/mm/compaction.c b/mm/compaction.c
index 139f00c..ca71fd3 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -981,13 +981,13 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
}
if (PageHuge(page)) {
+ const unsigned int order = compound_order(page);
/*
* skip hugetlbfs if we are not compacting for pages
* bigger than its order. THPs and other compound pages
* are handled below.
*/
if (!cc->alloc_contig) {
- const unsigned int order = compound_order(page);
if (order <= MAX_PAGE_ORDER) {
low_pfn += (1UL << order) - 1;
@@ -1011,8 +1011,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
/* Do not report -EBUSY down the chain */
if (ret == -EBUSY)
ret = 0;
- low_pfn += compound_nr(page) - 1;
- nr_scanned += compound_nr(page) - 1;
+ low_pfn += (1UL << order) - 1;
+ nr_scanned += (1UL << order) - 1;
goto isolate_fail;
}
diff --git a/mm/filemap.c b/mm/filemap.c
index b5e784f..7b90cbe 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2244,6 +2244,7 @@ unsigned filemap_get_folios_contig(struct address_space *mapping,
*start = folio->index + nr;
goto out;
}
+ xas_advance(&xas, folio_next_index(folio) - 1);
continue;
put_folio:
folio_put(folio);
diff --git a/mm/gup.c b/mm/gup.c
index 92351e2..84461d3 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2207,8 +2207,8 @@ size_t fault_in_safe_writeable(const char __user *uaddr, size_t size)
} while (start != end);
mmap_read_unlock(mm);
- if (size > (unsigned long)uaddr - start)
- return size - ((unsigned long)uaddr - start);
+ if (size > start - (unsigned long)uaddr)
+ return size - (start - (unsigned long)uaddr);
return 0;
}
EXPORT_SYMBOL(fault_in_safe_writeable);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2a47682..47d76d0 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3075,6 +3075,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmd, bool freeze, struct folio *folio)
{
+ bool pmd_migration = is_pmd_migration_entry(*pmd);
+
VM_WARN_ON_ONCE(folio && !folio_test_pmd_mappable(folio));
VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE));
VM_WARN_ON_ONCE(folio && !folio_test_locked(folio));
@@ -3085,9 +3087,12 @@ void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
* require a folio to check the PMD against. Otherwise, there
* is a risk of replacing the wrong folio.
*/
- if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) ||
- is_pmd_migration_entry(*pmd)) {
- if (folio && folio != pmd_folio(*pmd))
+ if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || pmd_migration) {
+ /*
+ * Do not apply pmd_folio() to a migration entry; and folio lock
+ * guarantees that it must be of the wrong folio anyway.
+ */
+ if (folio && (pmd_migration || folio != pmd_folio(*pmd)))
return;
__split_huge_pmd_locked(vma, pmd, address, freeze);
}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 39f92aa..7ae38bf 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2271,7 +2271,7 @@ static struct folio *alloc_surplus_hugetlb_folio(struct hstate *h,
* as surplus_pages, otherwise it might confuse
* persistent_huge_pages() momentarily.
*/
- __prep_account_new_huge_page(h, nid);
+ __prep_account_new_huge_page(h, folio_nid(folio));
/*
* We could have raced with the pool size change.
@@ -3010,7 +3010,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
struct hugepage_subpool *spool = subpool_vma(vma);
struct hstate *h = hstate_vma(vma);
struct folio *folio;
- long retval, gbl_chg;
+ long retval, gbl_chg, gbl_reserve;
map_chg_state map_chg;
int ret, idx;
struct hugetlb_cgroup *h_cg = NULL;
@@ -3163,8 +3163,16 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h),
h_cg);
out_subpool_put:
- if (map_chg)
- hugepage_subpool_put_pages(spool, 1);
+ /*
+ * put page to subpool iff the quota of subpool's rsv_hpages is used
+ * during hugepage_subpool_get_pages.
+ */
+ if (map_chg && !gbl_chg) {
+ gbl_reserve = hugepage_subpool_put_pages(spool, 1);
+ hugetlb_acct_memory(h, -gbl_reserve);
+ }
+
+
out_end_reservation:
if (map_chg != MAP_CHG_ENFORCED)
vma_end_reservation(h, vma, addr);
@@ -3825,6 +3833,7 @@ static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed,
static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
nodemask_t *nodes_allowed)
{
+ unsigned long persistent_free_count;
unsigned long min_count;
unsigned long allocated;
struct folio *folio;
@@ -3959,8 +3968,24 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
* though, we'll note that we're not allowed to exceed surplus
* and won't grow the pool anywhere else. Not until one of the
* sysctls are changed, or the surplus pages go out of use.
+ *
+ * min_count is the expected number of persistent pages, we
+ * shouldn't calculate min_count by using
+ * resv_huge_pages + persistent_huge_pages() - free_huge_pages,
+ * because there may exist free surplus huge pages, and this will
+ * lead to subtracting twice. Free surplus huge pages come from HVO
+ * failing to restore vmemmap, see comments in the callers of
+ * hugetlb_vmemmap_restore_folio(). Thus, we should calculate
+ * persistent free count first.
*/
- min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages;
+ persistent_free_count = h->free_huge_pages;
+ if (h->free_huge_pages > persistent_huge_pages(h)) {
+ if (h->free_huge_pages > h->surplus_huge_pages)
+ persistent_free_count -= h->surplus_huge_pages;
+ else
+ persistent_free_count = 0;
+ }
+ min_count = h->resv_huge_pages + persistent_huge_pages(h) - persistent_free_count;
min_count = max(count, min_count);
try_to_free_low(h, min_count, nodes_allowed);
@@ -4017,10 +4042,13 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst,
list_for_each_entry_safe(folio, next, src_list, lru) {
int i;
+ bool cma;
if (folio_test_hugetlb_vmemmap_optimized(folio))
continue;
+ cma = folio_test_hugetlb_cma(folio);
+
list_del(&folio->lru);
split_page_owner(&folio->page, huge_page_order(src), huge_page_order(dst));
@@ -4036,6 +4064,9 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst,
new_folio->mapping = NULL;
init_new_hugetlb_folio(dst, new_folio);
+ /* Copy the CMA flag so that it is freed correctly */
+ if (cma)
+ folio_set_hugetlb_cma(new_folio);
list_add(&new_folio->lru, &dst_list);
}
}
@@ -4630,7 +4661,7 @@ static void __init hugetlb_sysfs_init(void)
err = hugetlb_sysfs_add_hstate(h, hugepages_kobj,
hstate_kobjs, &hstate_attr_group);
if (err)
- pr_err("HugeTLB: Unable to add hstate %s", h->name);
+ pr_err("HugeTLB: Unable to add hstate %s\n", h->name);
}
#ifdef CONFIG_NUMA
@@ -7216,7 +7247,7 @@ bool hugetlb_reserve_pages(struct inode *inode,
struct vm_area_struct *vma,
vm_flags_t vm_flags)
{
- long chg = -1, add = -1;
+ long chg = -1, add = -1, spool_resv, gbl_resv;
struct hstate *h = hstate_inode(inode);
struct hugepage_subpool *spool = subpool_inode(inode);
struct resv_map *resv_map;
@@ -7351,8 +7382,16 @@ bool hugetlb_reserve_pages(struct inode *inode,
return true;
out_put_pages:
- /* put back original number of pages, chg */
- (void)hugepage_subpool_put_pages(spool, chg);
+ spool_resv = chg - gbl_reserve;
+ if (spool_resv) {
+ /* put sub pool's reservation back, chg - gbl_reserve */
+ gbl_resv = hugepage_subpool_put_pages(spool, spool_resv);
+ /*
+ * subpool's reserved pages can not be put back due to race,
+ * return to hstate.
+ */
+ hugetlb_acct_memory(h, -gbl_resv);
+ }
out_uncharge_cgroup:
hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h),
chg * pages_per_huge_page(h), h_cg);
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 9a99dfa..27245e8 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -238,11 +238,11 @@ static void vmemmap_remap_pte(pte_t *pte, unsigned long addr,
* struct page, the special metadata (e.g. page->flags or page->mapping)
* cannot copy to the tail struct page structs. The invalid value will be
* checked in the free_tail_page_prepare(). In order to avoid the message
- * of "corrupted mapping in tail page". We need to reset at least 3 (one
- * head struct page struct and two tail struct page structs) struct page
+ * of "corrupted mapping in tail page". We need to reset at least 4 (one
+ * head struct page struct and three tail struct page structs) struct page
* structs.
*/
-#define NR_RESET_STRUCT_PAGE 3
+#define NR_RESET_STRUCT_PAGE 4
static inline void reset_struct_pages(struct page *start)
{
diff --git a/mm/internal.h b/mm/internal.h
index 50c2f59..e9695ba 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1595,6 +1595,7 @@ unsigned long move_page_tables(struct pagetable_move_control *pmc);
#ifdef CONFIG_UNACCEPTED_MEMORY
void accept_page(struct page *page);
+void unaccepted_cleanup_work(struct work_struct *work);
#else /* CONFIG_UNACCEPTED_MEMORY */
static inline void accept_page(struct page *page)
{
diff --git a/mm/kasan/kasan_test_c.c b/mm/kasan/kasan_test_c.c
index 3ea3178..5f922dd 100644
--- a/mm/kasan/kasan_test_c.c
+++ b/mm/kasan/kasan_test_c.c
@@ -1567,6 +1567,7 @@ static void kasan_memcmp(struct kunit *test)
static void kasan_strings(struct kunit *test)
{
char *ptr;
+ char *src;
size_t size = 24;
/*
@@ -1578,6 +1579,25 @@ static void kasan_strings(struct kunit *test)
ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
+ src = kmalloc(KASAN_GRANULE_SIZE, GFP_KERNEL | __GFP_ZERO);
+ strscpy(src, "f0cacc1a0000000", KASAN_GRANULE_SIZE);
+
+ /*
+ * Make sure that strscpy() does not trigger KASAN if it overreads into
+ * poisoned memory.
+ *
+ * The expected size does not include the terminator '\0'
+ * so it is (KASAN_GRANULE_SIZE - 2) ==
+ * KASAN_GRANULE_SIZE - ("initial removed character" + "\0").
+ */
+ KUNIT_EXPECT_EQ(test, KASAN_GRANULE_SIZE - 2,
+ strscpy(ptr, src + 1, KASAN_GRANULE_SIZE));
+
+ /* strscpy should fail if the first byte is unreadable. */
+ KUNIT_EXPECT_KASAN_FAIL(test, strscpy(ptr, src + KASAN_GRANULE_SIZE,
+ KASAN_GRANULE_SIZE));
+
+ kfree(src);
kfree(ptr);
/*
@@ -2127,4 +2147,5 @@ static struct kunit_suite kasan_kunit_test_suite = {
kunit_test_suite(kasan_kunit_test_suite);
+MODULE_DESCRIPTION("KUnit tests for checking KASAN bug-detection capabilities");
MODULE_LICENSE("GPL");
diff --git a/mm/memblock.c b/mm/memblock.c
index 0a53db4d..d350941 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -2183,11 +2183,14 @@ static void __init memmap_init_reserved_pages(void)
struct memblock_region *region;
phys_addr_t start, end;
int nid;
+ unsigned long max_reserved;
/*
* set nid on all reserved pages and also treat struct
* pages for the NOMAP regions as PageReserved
*/
+repeat:
+ max_reserved = memblock.reserved.max;
for_each_mem_region(region) {
nid = memblock_get_region_node(region);
start = region->base;
@@ -2196,8 +2199,15 @@ static void __init memmap_init_reserved_pages(void)
if (memblock_is_nomap(region))
reserve_bootmem_region(start, end, nid);
- memblock_set_node(start, end, &memblock.reserved, nid);
+ memblock_set_node(start, region->size, &memblock.reserved, nid);
}
+ /*
+ * 'max' is changed means memblock.reserved has been doubled its
+ * array, which may result a new reserved region before current
+ * 'start'. Now we should repeat the procedure to set its node id.
+ */
+ if (max_reserved != memblock.reserved.max)
+ goto repeat;
/*
* initialize struct pages for reserved regions that don't have
diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c
index 8660908..4a9cf27 100644
--- a/mm/memcontrol-v1.c
+++ b/mm/memcontrol-v1.c
@@ -620,7 +620,7 @@ void memcg1_swapout(struct folio *folio, swp_entry_t entry)
mem_cgroup_id_get_many(swap_memcg, nr_entries - 1);
mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries);
- swap_cgroup_record(folio, mem_cgroup_id(memcg), entry);
+ swap_cgroup_record(folio, mem_cgroup_id(swap_memcg), entry);
folio_unqueue_deferred_split(folio);
folio->memcg_data = 0;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 421740f..c96c1f2 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1759,7 +1759,7 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
}
struct memcg_stock_pcp {
- localtry_lock_t stock_lock;
+ local_trylock_t stock_lock;
struct mem_cgroup *cached; /* this never be root cgroup */
unsigned int nr_pages;
@@ -1774,7 +1774,7 @@ struct memcg_stock_pcp {
#define FLUSHING_CACHED_CHARGE 0
};
static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock) = {
- .stock_lock = INIT_LOCALTRY_LOCK(stock_lock),
+ .stock_lock = INIT_LOCAL_TRYLOCK(stock_lock),
};
static DEFINE_MUTEX(percpu_charge_mutex);
@@ -1805,11 +1805,10 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages,
if (nr_pages > MEMCG_CHARGE_BATCH)
return ret;
- if (!localtry_trylock_irqsave(&memcg_stock.stock_lock, flags)) {
- if (!gfpflags_allow_spinning(gfp_mask))
- return ret;
- localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
- }
+ if (gfpflags_allow_spinning(gfp_mask))
+ local_lock_irqsave(&memcg_stock.stock_lock, flags);
+ else if (!local_trylock_irqsave(&memcg_stock.stock_lock, flags))
+ return ret;
stock = this_cpu_ptr(&memcg_stock);
stock_pages = READ_ONCE(stock->nr_pages);
@@ -1818,7 +1817,7 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages,
ret = true;
}
- localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+ local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
return ret;
}
@@ -1857,14 +1856,14 @@ static void drain_local_stock(struct work_struct *dummy)
* drain_stock races is that we always operate on local CPU stock
* here with IRQ disabled
*/
- localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
+ local_lock_irqsave(&memcg_stock.stock_lock, flags);
stock = this_cpu_ptr(&memcg_stock);
old = drain_obj_stock(stock);
drain_stock(stock);
clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
- localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+ local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
obj_cgroup_put(old);
}
@@ -1894,7 +1893,7 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
{
unsigned long flags;
- if (!localtry_trylock_irqsave(&memcg_stock.stock_lock, flags)) {
+ if (!local_trylock_irqsave(&memcg_stock.stock_lock, flags)) {
/*
* In case of unlikely failure to lock percpu stock_lock
* uncharge memcg directly.
@@ -1907,7 +1906,7 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
return;
}
__refill_stock(memcg, nr_pages);
- localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+ local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
}
/*
@@ -1964,9 +1963,9 @@ static int memcg_hotplug_cpu_dead(unsigned int cpu)
stock = &per_cpu(memcg_stock, cpu);
/* drain_obj_stock requires stock_lock */
- localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
+ local_lock_irqsave(&memcg_stock.stock_lock, flags);
old = drain_obj_stock(stock);
- localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+ local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
drain_stock(stock);
obj_cgroup_put(old);
@@ -2787,7 +2786,7 @@ static void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
unsigned long flags;
int *bytes;
- localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
+ local_lock_irqsave(&memcg_stock.stock_lock, flags);
stock = this_cpu_ptr(&memcg_stock);
/*
@@ -2836,7 +2835,7 @@ static void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
if (nr)
__mod_objcg_mlstate(objcg, pgdat, idx, nr);
- localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+ local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
obj_cgroup_put(old);
}
@@ -2846,7 +2845,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
unsigned long flags;
bool ret = false;
- localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
+ local_lock_irqsave(&memcg_stock.stock_lock, flags);
stock = this_cpu_ptr(&memcg_stock);
if (objcg == READ_ONCE(stock->cached_objcg) && stock->nr_bytes >= nr_bytes) {
@@ -2854,7 +2853,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
ret = true;
}
- localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+ local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
return ret;
}
@@ -2946,7 +2945,7 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
unsigned long flags;
unsigned int nr_pages = 0;
- localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
+ local_lock_irqsave(&memcg_stock.stock_lock, flags);
stock = this_cpu_ptr(&memcg_stock);
if (READ_ONCE(stock->cached_objcg) != objcg) { /* reset if necessary */
@@ -2960,7 +2959,7 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
stock->nr_bytes &= (PAGE_SIZE - 1);
}
- localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+ local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
obj_cgroup_put(old);
if (nr_pages)
diff --git a/mm/memory.c b/mm/memory.c
index 2d8c265f..4919941 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1361,7 +1361,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
struct mm_struct *dst_mm = dst_vma->vm_mm;
struct mm_struct *src_mm = src_vma->vm_mm;
struct mmu_notifier_range range;
- unsigned long next, pfn;
+ unsigned long next, pfn = 0;
bool is_cow;
int ret;
@@ -2938,11 +2938,11 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
if (fn) {
do {
if (create || !pte_none(ptep_get(pte))) {
- err = fn(pte++, addr, data);
+ err = fn(pte, addr, data);
if (err)
break;
}
- } while (addr += PAGE_SIZE, addr != end);
+ } while (pte++, addr += PAGE_SIZE, addr != end);
}
*mask |= PGTBL_PTE_MODIFIED;
@@ -3734,8 +3734,6 @@ static bool __wp_can_reuse_large_anon_folio(struct folio *folio,
return false;
VM_WARN_ON_ONCE(folio_test_ksm(folio));
- VM_WARN_ON_ONCE(folio_mapcount(folio) > folio_nr_pages(folio));
- VM_WARN_ON_ONCE(folio_entire_mapcount(folio));
if (unlikely(folio_test_swapcache(folio))) {
/*
@@ -3753,13 +3751,15 @@ static bool __wp_can_reuse_large_anon_folio(struct folio *folio,
/* Stabilize the mapcount vs. refcount and recheck. */
folio_lock_large_mapcount(folio);
- VM_WARN_ON_ONCE(folio_large_mapcount(folio) < folio_ref_count(folio));
+ VM_WARN_ON_ONCE_FOLIO(folio_large_mapcount(folio) > folio_ref_count(folio), folio);
if (folio_test_large_maybe_mapped_shared(folio))
goto unlock;
if (folio_large_mapcount(folio) != folio_ref_count(folio))
goto unlock;
+ VM_WARN_ON_ONCE_FOLIO(folio_large_mapcount(folio) > folio_nr_pages(folio), folio);
+ VM_WARN_ON_ONCE_FOLIO(folio_entire_mapcount(folio), folio);
VM_WARN_ON_ONCE(folio_mm_id(folio, 0) != vma->vm_mm->mm_id &&
folio_mm_id(folio, 1) != vma->vm_mm->mm_id);
diff --git a/mm/migrate.c b/mm/migrate.c
index f3ee6d8..676d9cf 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -845,9 +845,11 @@ static int __buffer_migrate_folio(struct address_space *mapping,
return -EAGAIN;
if (check_refs) {
- bool busy;
+ bool busy, migrating;
bool invalidated = false;
+ migrating = test_and_set_bit_lock(BH_Migrate, &head->b_state);
+ VM_WARN_ON_ONCE(migrating);
recheck_buffers:
busy = false;
spin_lock(&mapping->i_private_lock);
@@ -859,12 +861,12 @@ static int __buffer_migrate_folio(struct address_space *mapping,
}
bh = bh->b_this_page;
} while (bh != head);
+ spin_unlock(&mapping->i_private_lock);
if (busy) {
if (invalidated) {
rc = -EAGAIN;
goto unlock_buffers;
}
- spin_unlock(&mapping->i_private_lock);
invalidate_bh_lrus();
invalidated = true;
goto recheck_buffers;
@@ -883,7 +885,7 @@ static int __buffer_migrate_folio(struct address_space *mapping,
unlock_buffers:
if (check_refs)
- spin_unlock(&mapping->i_private_lock);
+ clear_bit_unlock(BH_Migrate, &head->b_state);
bh = head;
do {
unlock_buffer(bh);
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 84f14fa..9659689 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1441,6 +1441,7 @@ static void __meminit zone_init_free_lists(struct zone *zone)
#ifdef CONFIG_UNACCEPTED_MEMORY
INIT_LIST_HEAD(&zone->unaccepted_pages);
+ INIT_WORK(&zone->unaccepted_cleanup, unaccepted_cleanup_work);
#endif
}
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index c81624b..20e1d76 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -520,8 +520,8 @@ static int dirty_ratio_handler(const struct ctl_table *table, int write, void *b
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write && vm_dirty_ratio != old_ratio) {
- writeback_set_ratelimit();
vm_dirty_bytes = 0;
+ writeback_set_ratelimit();
}
return ret;
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fd6b865..00ebf3a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1400,11 +1400,12 @@ static void free_one_page(struct zone *zone, struct page *page,
struct llist_head *llhead;
unsigned long flags;
- if (!spin_trylock_irqsave(&zone->lock, flags)) {
- if (unlikely(fpi_flags & FPI_TRYLOCK)) {
+ if (unlikely(fpi_flags & FPI_TRYLOCK)) {
+ if (!spin_trylock_irqsave(&zone->lock, flags)) {
add_page_to_zone_llist(zone, page, order);
return;
}
+ } else {
spin_lock_irqsave(&zone->lock, flags);
}
@@ -2182,23 +2183,15 @@ try_to_claim_block(struct zone *zone, struct page *page,
}
/*
- * Try finding a free buddy page on the fallback list.
- *
- * This will attempt to claim a whole pageblock for the requested type
- * to ensure grouping of such requests in the future.
- *
- * If a whole block cannot be claimed, steal an individual page, regressing to
- * __rmqueue_smallest() logic to at least break up as little contiguity as
- * possible.
+ * Try to allocate from some fallback migratetype by claiming the entire block,
+ * i.e. converting it to the allocation's start migratetype.
*
* The use of signed ints for order and current_order is a deliberate
* deviation from the rest of this file, to make the for loop
* condition simpler.
- *
- * Return the stolen page, or NULL if none can be found.
*/
static __always_inline struct page *
-__rmqueue_fallback(struct zone *zone, int order, int start_migratetype,
+__rmqueue_claim(struct zone *zone, int order, int start_migratetype,
unsigned int alloc_flags)
{
struct free_area *area;
@@ -2236,14 +2229,29 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype,
page = try_to_claim_block(zone, page, current_order, order,
start_migratetype, fallback_mt,
alloc_flags);
- if (page)
- goto got_one;
+ if (page) {
+ trace_mm_page_alloc_extfrag(page, order, current_order,
+ start_migratetype, fallback_mt);
+ return page;
+ }
}
- if (alloc_flags & ALLOC_NOFRAGMENT)
- return NULL;
+ return NULL;
+}
- /* No luck claiming pageblock. Find the smallest fallback page */
+/*
+ * Try to steal a single page from some fallback migratetype. Leave the rest of
+ * the block as its current migratetype, potentially causing fragmentation.
+ */
+static __always_inline struct page *
+__rmqueue_steal(struct zone *zone, int order, int start_migratetype)
+{
+ struct free_area *area;
+ int current_order;
+ struct page *page;
+ int fallback_mt;
+ bool claim_block;
+
for (current_order = order; current_order < NR_PAGE_ORDERS; current_order++) {
area = &(zone->free_area[current_order]);
fallback_mt = find_suitable_fallback(area, current_order,
@@ -2253,25 +2261,28 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype,
page = get_page_from_free_area(area, fallback_mt);
page_del_and_expand(zone, page, order, current_order, fallback_mt);
- goto got_one;
+ trace_mm_page_alloc_extfrag(page, order, current_order,
+ start_migratetype, fallback_mt);
+ return page;
}
return NULL;
-
-got_one:
- trace_mm_page_alloc_extfrag(page, order, current_order,
- start_migratetype, fallback_mt);
-
- return page;
}
+enum rmqueue_mode {
+ RMQUEUE_NORMAL,
+ RMQUEUE_CMA,
+ RMQUEUE_CLAIM,
+ RMQUEUE_STEAL,
+};
+
/*
* Do the hard work of removing an element from the buddy allocator.
* Call me with the zone->lock already held.
*/
static __always_inline struct page *
__rmqueue(struct zone *zone, unsigned int order, int migratetype,
- unsigned int alloc_flags)
+ unsigned int alloc_flags, enum rmqueue_mode *mode)
{
struct page *page;
@@ -2290,16 +2301,48 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype,
}
}
- page = __rmqueue_smallest(zone, order, migratetype);
- if (unlikely(!page)) {
- if (alloc_flags & ALLOC_CMA)
+ /*
+ * First try the freelists of the requested migratetype, then try
+ * fallbacks modes with increasing levels of fragmentation risk.
+ *
+ * The fallback logic is expensive and rmqueue_bulk() calls in
+ * a loop with the zone->lock held, meaning the freelists are
+ * not subject to any outside changes. Remember in *mode where
+ * we found pay dirt, to save us the search on the next call.
+ */
+ switch (*mode) {
+ case RMQUEUE_NORMAL:
+ page = __rmqueue_smallest(zone, order, migratetype);
+ if (page)
+ return page;
+ fallthrough;
+ case RMQUEUE_CMA:
+ if (alloc_flags & ALLOC_CMA) {
page = __rmqueue_cma_fallback(zone, order);
-
- if (!page)
- page = __rmqueue_fallback(zone, order, migratetype,
- alloc_flags);
+ if (page) {
+ *mode = RMQUEUE_CMA;
+ return page;
+ }
+ }
+ fallthrough;
+ case RMQUEUE_CLAIM:
+ page = __rmqueue_claim(zone, order, migratetype, alloc_flags);
+ if (page) {
+ /* Replenished preferred freelist, back to normal mode. */
+ *mode = RMQUEUE_NORMAL;
+ return page;
+ }
+ fallthrough;
+ case RMQUEUE_STEAL:
+ if (!(alloc_flags & ALLOC_NOFRAGMENT)) {
+ page = __rmqueue_steal(zone, order, migratetype);
+ if (page) {
+ *mode = RMQUEUE_STEAL;
+ return page;
+ }
+ }
}
- return page;
+ return NULL;
}
/*
@@ -2311,17 +2354,19 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
unsigned long count, struct list_head *list,
int migratetype, unsigned int alloc_flags)
{
+ enum rmqueue_mode rmqm = RMQUEUE_NORMAL;
unsigned long flags;
int i;
- if (!spin_trylock_irqsave(&zone->lock, flags)) {
- if (unlikely(alloc_flags & ALLOC_TRYLOCK))
+ if (unlikely(alloc_flags & ALLOC_TRYLOCK)) {
+ if (!spin_trylock_irqsave(&zone->lock, flags))
return 0;
+ } else {
spin_lock_irqsave(&zone->lock, flags);
}
for (i = 0; i < count; ++i) {
struct page *page = __rmqueue(zone, order, migratetype,
- alloc_flags);
+ alloc_flags, &rmqm);
if (unlikely(page == NULL))
break;
@@ -2937,15 +2982,18 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone,
do {
page = NULL;
- if (!spin_trylock_irqsave(&zone->lock, flags)) {
- if (unlikely(alloc_flags & ALLOC_TRYLOCK))
+ if (unlikely(alloc_flags & ALLOC_TRYLOCK)) {
+ if (!spin_trylock_irqsave(&zone->lock, flags))
return NULL;
+ } else {
spin_lock_irqsave(&zone->lock, flags);
}
if (alloc_flags & ALLOC_HIGHATOMIC)
page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
if (!page) {
- page = __rmqueue(zone, order, migratetype, alloc_flags);
+ enum rmqueue_mode rmqm = RMQUEUE_NORMAL;
+
+ page = __rmqueue(zone, order, migratetype, alloc_flags, &rmqm);
/*
* If the allocation fails, allow OOM handling and
@@ -3422,18 +3470,6 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
return false;
}
-bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
- unsigned long mark, int highest_zoneidx)
-{
- long free_pages = zone_page_state(z, NR_FREE_PAGES);
-
- if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark)
- free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES);
-
- return __zone_watermark_ok(z, order, mark, highest_zoneidx, 0,
- free_pages);
-}
-
#ifdef CONFIG_NUMA
int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE;
@@ -4530,6 +4566,14 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
}
retry:
+ /*
+ * Deal with possible cpuset update races or zonelist updates to avoid
+ * infinite retries.
+ */
+ if (check_retry_cpuset(cpuset_mems_cookie, ac) ||
+ check_retry_zonelist(zonelist_iter_cookie))
+ goto restart;
+
/* Ensure kswapd doesn't accidentally go to sleep as long as we loop */
if (alloc_flags & ALLOC_KSWAPD)
wake_all_kswapds(order, gfp_mask, ac);
@@ -7143,6 +7187,11 @@ static DEFINE_STATIC_KEY_FALSE(zones_with_unaccepted_pages);
static bool lazy_accept = true;
+void unaccepted_cleanup_work(struct work_struct *work)
+{
+ static_branch_dec(&zones_with_unaccepted_pages);
+}
+
static int __init accept_memory_parse(char *p)
{
if (!strcmp(p, "lazy")) {
@@ -7181,8 +7230,27 @@ static void __accept_page(struct zone *zone, unsigned long *flags,
__free_pages_ok(page, MAX_PAGE_ORDER, FPI_TO_TAIL);
- if (last)
- static_branch_dec(&zones_with_unaccepted_pages);
+ if (last) {
+ /*
+ * There are two corner cases:
+ *
+ * - If allocation occurs during the CPU bring up,
+ * static_branch_dec() cannot be used directly as
+ * it causes a deadlock on cpu_hotplug_lock.
+ *
+ * Instead, use schedule_work() to prevent deadlock.
+ *
+ * - If allocation occurs before workqueues are initialized,
+ * static_branch_dec() should be called directly.
+ *
+ * Workqueues are initialized before CPU bring up, so this
+ * will not conflict with the first scenario.
+ */
+ if (system_wq)
+ schedule_work(&zone->unaccepted_cleanup);
+ else
+ unaccepted_cleanup_work(&zone->unaccepted_cleanup);
+ }
}
void accept_page(struct page *page)
diff --git a/mm/slub.c b/mm/slub.c
index b46f876..be8b09e 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1973,6 +1973,11 @@ static inline void handle_failed_objexts_alloc(unsigned long obj_exts,
#define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | \
__GFP_ACCOUNT | __GFP_NOFAIL)
+static inline void init_slab_obj_exts(struct slab *slab)
+{
+ slab->obj_exts = 0;
+}
+
int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
gfp_t gfp, bool new_slab)
{
@@ -2023,8 +2028,7 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
return 0;
}
-/* Should be called only if mem_alloc_profiling_enabled() */
-static noinline void free_slab_obj_exts(struct slab *slab)
+static inline void free_slab_obj_exts(struct slab *slab)
{
struct slabobj_ext *obj_exts;
@@ -2044,20 +2048,12 @@ static noinline void free_slab_obj_exts(struct slab *slab)
slab->obj_exts = 0;
}
-static inline bool need_slab_obj_ext(void)
-{
- if (mem_alloc_profiling_enabled())
- return true;
-
- /*
- * CONFIG_MEMCG creates vector of obj_cgroup objects conditionally
- * inside memcg_slab_post_alloc_hook. No other users for now.
- */
- return false;
-}
-
#else /* CONFIG_SLAB_OBJ_EXT */
+static inline void init_slab_obj_exts(struct slab *slab)
+{
+}
+
static int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
gfp_t gfp, bool new_slab)
{
@@ -2068,11 +2064,6 @@ static inline void free_slab_obj_exts(struct slab *slab)
{
}
-static inline bool need_slab_obj_ext(void)
-{
- return false;
-}
-
#endif /* CONFIG_SLAB_OBJ_EXT */
#ifdef CONFIG_MEM_ALLOC_PROFILING
@@ -2120,7 +2111,7 @@ __alloc_tagging_slab_alloc_hook(struct kmem_cache *s, void *object, gfp_t flags)
static inline void
alloc_tagging_slab_alloc_hook(struct kmem_cache *s, void *object, gfp_t flags)
{
- if (need_slab_obj_ext())
+ if (mem_alloc_profiling_enabled())
__alloc_tagging_slab_alloc_hook(s, object, flags);
}
@@ -2592,8 +2583,12 @@ static __always_inline void account_slab(struct slab *slab, int order,
static __always_inline void unaccount_slab(struct slab *slab, int order,
struct kmem_cache *s)
{
- if (memcg_kmem_online() || need_slab_obj_ext())
- free_slab_obj_exts(slab);
+ /*
+ * The slab object extensions should now be freed regardless of
+ * whether mem_alloc_profiling_enabled() or not because profiling
+ * might have been disabled after slab->obj_exts got allocated.
+ */
+ free_slab_obj_exts(slab);
mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
-(PAGE_SIZE << order));
@@ -2637,6 +2632,7 @@ static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
slab->objects = oo_objects(oo);
slab->inuse = 0;
slab->frozen = 0;
+ init_slab_obj_exts(slab);
account_slab(slab, oo_order(oo), s, flags);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2eff8b5..f214843 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1272,13 +1272,22 @@ int folio_alloc_swap(struct folio *folio, gfp_t gfp)
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio);
- /*
- * Should not even be attempting large allocations when huge
- * page swap is disabled. Warn and fail the allocation.
- */
- if (order && (!IS_ENABLED(CONFIG_THP_SWAP) || size > SWAPFILE_CLUSTER)) {
- VM_WARN_ON_ONCE(1);
- return -EINVAL;
+ if (order) {
+ /*
+ * Reject large allocation when THP_SWAP is disabled,
+ * the caller should split the folio and try again.
+ */
+ if (!IS_ENABLED(CONFIG_THP_SWAP))
+ return -EAGAIN;
+
+ /*
+ * Allocation size should never exceed cluster size
+ * (HPAGE_PMD_SIZE).
+ */
+ if (size > SWAPFILE_CLUSTER) {
+ VM_WARN_ON_ONCE(1);
+ return -EINVAL;
+ }
}
local_lock(&percpu_swap_cluster.lock);
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index fbf2cf6..7d5d709 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1902,6 +1902,14 @@ struct vm_area_struct *userfaultfd_clear_vma(struct vma_iterator *vmi,
unsigned long end)
{
struct vm_area_struct *ret;
+ bool give_up_on_oom = false;
+
+ /*
+ * If we are modifying only and not splitting, just give up on the merge
+ * if OOM prevents us from merging successfully.
+ */
+ if (start == vma->vm_start && end == vma->vm_end)
+ give_up_on_oom = true;
/* Reset ptes for the whole vma range if wr-protected */
if (userfaultfd_wp(vma))
@@ -1909,7 +1917,7 @@ struct vm_area_struct *userfaultfd_clear_vma(struct vma_iterator *vmi,
ret = vma_modify_flags_uffd(vmi, prev, vma, start, end,
vma->vm_flags & ~__VM_UFFD_FLAGS,
- NULL_VM_UFFD_CTX);
+ NULL_VM_UFFD_CTX, give_up_on_oom);
/*
* In the vma_merge() successful mprotect-like case 8:
@@ -1960,7 +1968,8 @@ int userfaultfd_register_range(struct userfaultfd_ctx *ctx,
new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags;
vma = vma_modify_flags_uffd(&vmi, prev, vma, start, vma_end,
new_flags,
- (struct vm_userfaultfd_ctx){ctx});
+ (struct vm_userfaultfd_ctx){ctx},
+ /* give_up_on_oom = */false);
if (IS_ERR(vma))
return PTR_ERR(vma);
diff --git a/mm/vma.c b/mm/vma.c
index 5cdc561..839d12f 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -666,6 +666,9 @@ static void vmg_adjust_set_range(struct vma_merge_struct *vmg)
/*
* Actually perform the VMA merge operation.
*
+ * IMPORTANT: We guarantee that, should vmg->give_up_on_oom is set, to not
+ * modify any VMAs or cause inconsistent state should an OOM condition arise.
+ *
* Returns 0 on success, or an error value on failure.
*/
static int commit_merge(struct vma_merge_struct *vmg)
@@ -685,6 +688,12 @@ static int commit_merge(struct vma_merge_struct *vmg)
init_multi_vma_prep(&vp, vma, vmg);
+ /*
+ * If vmg->give_up_on_oom is set, we're safe, because we don't actually
+ * manipulate any VMAs until we succeed at preallocation.
+ *
+ * Past this point, we will not return an error.
+ */
if (vma_iter_prealloc(vmg->vmi, vma))
return -ENOMEM;
@@ -915,7 +924,13 @@ static __must_check struct vm_area_struct *vma_merge_existing_range(
if (anon_dup)
unlink_anon_vmas(anon_dup);
- vmg->state = VMA_MERGE_ERROR_NOMEM;
+ /*
+ * We've cleaned up any cloned anon_vma's, no VMAs have been
+ * modified, no harm no foul if the user requests that we not
+ * report this and just give up, leaving the VMAs unmerged.
+ */
+ if (!vmg->give_up_on_oom)
+ vmg->state = VMA_MERGE_ERROR_NOMEM;
return NULL;
}
@@ -926,7 +941,15 @@ static __must_check struct vm_area_struct *vma_merge_existing_range(
abort:
vma_iter_set(vmg->vmi, start);
vma_iter_load(vmg->vmi);
- vmg->state = VMA_MERGE_ERROR_NOMEM;
+
+ /*
+ * This means we have failed to clone anon_vma's correctly, but no
+ * actual changes to VMAs have occurred, so no harm no foul - if the
+ * user doesn't want this reported and instead just wants to give up on
+ * the merge, allow it.
+ */
+ if (!vmg->give_up_on_oom)
+ vmg->state = VMA_MERGE_ERROR_NOMEM;
return NULL;
}
@@ -1068,6 +1091,10 @@ int vma_expand(struct vma_merge_struct *vmg)
/* This should already have been checked by this point. */
VM_WARN_ON_VMG(!can_merge_remove_vma(next), vmg);
vma_start_write(next);
+ /*
+ * In this case we don't report OOM, so vmg->give_up_on_mm is
+ * safe.
+ */
ret = dup_anon_vma(middle, next, &anon_dup);
if (ret)
return ret;
@@ -1090,9 +1117,15 @@ int vma_expand(struct vma_merge_struct *vmg)
return 0;
nomem:
- vmg->state = VMA_MERGE_ERROR_NOMEM;
if (anon_dup)
unlink_anon_vmas(anon_dup);
+ /*
+ * If the user requests that we just give upon OOM, we are safe to do so
+ * here, as commit merge provides this contract to us. Nothing has been
+ * changed - no harm no foul, just don't report it.
+ */
+ if (!vmg->give_up_on_oom)
+ vmg->state = VMA_MERGE_ERROR_NOMEM;
return -ENOMEM;
}
@@ -1534,6 +1567,13 @@ static struct vm_area_struct *vma_modify(struct vma_merge_struct *vmg)
if (vmg_nomem(vmg))
return ERR_PTR(-ENOMEM);
+ /*
+ * Split can fail for reasons other than OOM, so if the user requests
+ * this it's probably a mistake.
+ */
+ VM_WARN_ON(vmg->give_up_on_oom &&
+ (vma->vm_start != start || vma->vm_end != end));
+
/* Split any preceding portion of the VMA. */
if (vma->vm_start < start) {
int err = split_vma(vmg->vmi, vma, start, 1);
@@ -1602,12 +1642,15 @@ struct vm_area_struct
struct vm_area_struct *vma,
unsigned long start, unsigned long end,
unsigned long new_flags,
- struct vm_userfaultfd_ctx new_ctx)
+ struct vm_userfaultfd_ctx new_ctx,
+ bool give_up_on_oom)
{
VMG_VMA_STATE(vmg, vmi, prev, vma, start, end);
vmg.flags = new_flags;
vmg.uffd_ctx = new_ctx;
+ if (give_up_on_oom)
+ vmg.give_up_on_oom = true;
return vma_modify(&vmg);
}
diff --git a/mm/vma.h b/mm/vma.h
index 7356ca5..149926e 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -114,6 +114,12 @@ struct vma_merge_struct {
*/
bool just_expand :1;
+ /*
+ * If a merge is possible, but an OOM error occurs, give up and don't
+ * execute the merge, returning NULL.
+ */
+ bool give_up_on_oom :1;
+
/* Internal flags set during merge process: */
/*
@@ -255,7 +261,8 @@ __must_check struct vm_area_struct
struct vm_area_struct *vma,
unsigned long start, unsigned long end,
unsigned long new_flags,
- struct vm_userfaultfd_ctx new_ctx);
+ struct vm_userfaultfd_ctx new_ctx,
+ bool give_up_on_oom);
__must_check struct vm_area_struct
*vma_merge_new_range(struct vma_merge_struct *vmg);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 3ed720a..2d75116 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1940,7 +1940,7 @@ static inline void setup_vmalloc_vm(struct vm_struct *vm,
{
vm->flags = flags;
vm->addr = (void *)va->va_start;
- vm->size = va_size(va);
+ vm->size = vm->requested_size = va_size(va);
vm->caller = caller;
va->vm = vm;
}
@@ -3133,6 +3133,7 @@ struct vm_struct *__get_vm_area_node(unsigned long size,
area->flags = flags;
area->caller = caller;
+ area->requested_size = requested_size;
va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area);
if (IS_ERR(va)) {
@@ -4063,6 +4064,8 @@ EXPORT_SYMBOL(vzalloc_node_noprof);
*/
void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
{
+ struct vm_struct *vm = NULL;
+ size_t alloced_size = 0;
size_t old_size = 0;
void *n;
@@ -4072,15 +4075,17 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
}
if (p) {
- struct vm_struct *vm;
-
vm = find_vm_area(p);
if (unlikely(!vm)) {
WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p);
return NULL;
}
- old_size = get_vm_area_size(vm);
+ alloced_size = get_vm_area_size(vm);
+ old_size = vm->requested_size;
+ if (WARN(alloced_size < old_size,
+ "vrealloc() has mismatched area vs requested sizes (%p)\n", p))
+ return NULL;
}
/*
@@ -4088,14 +4093,26 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
* would be a good heuristic for when to shrink the vm_area?
*/
if (size <= old_size) {
- /* Zero out spare memory. */
- if (want_init_on_alloc(flags))
+ /* Zero out "freed" memory. */
+ if (want_init_on_free())
memset((void *)p + size, 0, old_size - size);
+ vm->requested_size = size;
kasan_poison_vmalloc(p + size, old_size - size);
- kasan_unpoison_vmalloc(p, size, KASAN_VMALLOC_PROT_NORMAL);
return (void *)p;
}
+ /*
+ * We already have the bytes available in the allocation; use them.
+ */
+ if (size <= alloced_size) {
+ kasan_unpoison_vmalloc(p + old_size, size - old_size,
+ KASAN_VMALLOC_PROT_NORMAL);
+ /* Zero out "alloced" memory. */
+ if (want_init_on_alloc(flags))
+ memset((void *)p + old_size, 0, size - old_size);
+ vm->requested_size = size;
+ }
+
/* TODO: Grow the vm_area, i.e. allocate and map additional pages. */
n = __vmalloc_noprof(size, flags);
if (!n)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b620d74..3783e45 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -6736,6 +6736,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx)
* meet watermarks.
*/
for_each_managed_zone_pgdat(zone, pgdat, i, highest_zoneidx) {
+ enum zone_stat_item item;
unsigned long free_pages;
if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)
@@ -6746,11 +6747,33 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx)
/*
* In defrag_mode, watermarks must be met in whole
* blocks to avoid polluting allocator fallbacks.
+ *
+ * However, kswapd usually cannot accomplish this on
+ * its own and needs kcompactd support. Once it's
+ * reclaimed a compaction gap, and kswapd_shrink_node
+ * has dropped order, simply ensure there are enough
+ * base pages for compaction, wake kcompactd & sleep.
*/
- if (defrag_mode)
- free_pages = zone_page_state(zone, NR_FREE_PAGES_BLOCKS);
+ if (defrag_mode && order)
+ item = NR_FREE_PAGES_BLOCKS;
else
- free_pages = zone_page_state(zone, NR_FREE_PAGES);
+ item = NR_FREE_PAGES;
+
+ /*
+ * When there is a high number of CPUs in the system,
+ * the cumulative error from the vmstat per-cpu cache
+ * can blur the line between the watermarks. In that
+ * case, be safe and get an accurate snapshot.
+ *
+ * TODO: NR_FREE_PAGES_BLOCKS moves in steps of
+ * pageblock_nr_pages, while the vmstat pcp threshold
+ * is limited to 125. On many configurations that
+ * counter won't actually be per-cpu cached. But keep
+ * things simple for now; revisit when somebody cares.
+ */
+ free_pages = zone_page_state(zone, item);
+ if (zone->percpu_drift_mark && free_pages < zone->percpu_drift_mark)
+ free_pages = zone_page_state_snapshot(zone, item);
if (__zone_watermark_ok(zone, order, mark, highest_zoneidx,
0, free_pages))
diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig
index 860a078..20b3162 100644
--- a/net/batman-adv/Kconfig
+++ b/net/batman-adv/Kconfig
@@ -9,7 +9,7 @@
config BATMAN_ADV
tristate "B.A.T.M.A.N. Advanced Meshing Protocol"
- select LIBCRC32C
+ select CRC32
help
B.A.T.M.A.N. (better approach to mobile ad-hoc networking) is
a routing protocol for multi-hop ad-hoc mesh networks. The
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index f145f96..7cd4bdce 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -725,7 +725,6 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
kref_get(&hard_iface->refcount);
- dev_hold(mesh_iface);
netdev_hold(mesh_iface, &hard_iface->meshif_dev_tracker, GFP_ATOMIC);
hard_iface->mesh_iface = mesh_iface;
bat_priv = netdev_priv(hard_iface->mesh_iface);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 95972fd..6533e28 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -2064,95 +2064,6 @@ static int create_big_sync(struct hci_dev *hdev, void *data)
return hci_le_create_big(conn, &conn->iso_qos);
}
-static void create_pa_complete(struct hci_dev *hdev, void *data, int err)
-{
- bt_dev_dbg(hdev, "");
-
- if (err)
- bt_dev_err(hdev, "Unable to create PA: %d", err);
-}
-
-static bool hci_conn_check_create_pa_sync(struct hci_conn *conn)
-{
- if (conn->type != ISO_LINK || conn->sid == HCI_SID_INVALID)
- return false;
-
- return true;
-}
-
-static int create_pa_sync(struct hci_dev *hdev, void *data)
-{
- struct hci_cp_le_pa_create_sync cp = {0};
- struct hci_conn *conn;
- int err = 0;
-
- hci_dev_lock(hdev);
-
- rcu_read_lock();
-
- /* The spec allows only one pending LE Periodic Advertising Create
- * Sync command at a time. If the command is pending now, don't do
- * anything. We check for pending connections after each PA Sync
- * Established event.
- *
- * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E
- * page 2493:
- *
- * If the Host issues this command when another HCI_LE_Periodic_
- * Advertising_Create_Sync command is pending, the Controller shall
- * return the error code Command Disallowed (0x0C).
- */
- list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) {
- if (test_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags))
- goto unlock;
- }
-
- list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) {
- if (hci_conn_check_create_pa_sync(conn)) {
- struct bt_iso_qos *qos = &conn->iso_qos;
-
- cp.options = qos->bcast.options;
- cp.sid = conn->sid;
- cp.addr_type = conn->dst_type;
- bacpy(&cp.addr, &conn->dst);
- cp.skip = cpu_to_le16(qos->bcast.skip);
- cp.sync_timeout = cpu_to_le16(qos->bcast.sync_timeout);
- cp.sync_cte_type = qos->bcast.sync_cte_type;
-
- break;
- }
- }
-
-unlock:
- rcu_read_unlock();
-
- hci_dev_unlock(hdev);
-
- if (bacmp(&cp.addr, BDADDR_ANY)) {
- hci_dev_set_flag(hdev, HCI_PA_SYNC);
- set_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags);
-
- err = __hci_cmd_sync_status(hdev, HCI_OP_LE_PA_CREATE_SYNC,
- sizeof(cp), &cp, HCI_CMD_TIMEOUT);
- if (!err)
- err = hci_update_passive_scan_sync(hdev);
-
- if (err) {
- hci_dev_clear_flag(hdev, HCI_PA_SYNC);
- clear_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags);
- }
- }
-
- return err;
-}
-
-int hci_pa_create_sync_pending(struct hci_dev *hdev)
-{
- /* Queue start pa_create_sync and scan */
- return hci_cmd_sync_queue(hdev, create_pa_sync,
- NULL, create_pa_complete);
-}
-
struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst,
__u8 dst_type, __u8 sid,
struct bt_iso_qos *qos)
@@ -2167,97 +2078,18 @@ struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst,
conn->dst_type = dst_type;
conn->sid = sid;
conn->state = BT_LISTEN;
+ conn->conn_timeout = msecs_to_jiffies(qos->bcast.sync_timeout * 10);
hci_conn_hold(conn);
- hci_pa_create_sync_pending(hdev);
+ hci_connect_pa_sync(hdev, conn);
return conn;
}
-static bool hci_conn_check_create_big_sync(struct hci_conn *conn)
-{
- if (!conn->num_bis)
- return false;
-
- return true;
-}
-
-static void big_create_sync_complete(struct hci_dev *hdev, void *data, int err)
-{
- bt_dev_dbg(hdev, "");
-
- if (err)
- bt_dev_err(hdev, "Unable to create BIG sync: %d", err);
-}
-
-static int big_create_sync(struct hci_dev *hdev, void *data)
-{
- DEFINE_FLEX(struct hci_cp_le_big_create_sync, pdu, bis, num_bis, 0x11);
- struct hci_conn *conn;
-
- rcu_read_lock();
-
- pdu->num_bis = 0;
-
- /* The spec allows only one pending LE BIG Create Sync command at
- * a time. If the command is pending now, don't do anything. We
- * check for pending connections after each BIG Sync Established
- * event.
- *
- * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E
- * page 2586:
- *
- * If the Host sends this command when the Controller is in the
- * process of synchronizing to any BIG, i.e. the HCI_LE_BIG_Sync_
- * Established event has not been generated, the Controller shall
- * return the error code Command Disallowed (0x0C).
- */
- list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) {
- if (test_bit(HCI_CONN_CREATE_BIG_SYNC, &conn->flags))
- goto unlock;
- }
-
- list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) {
- if (hci_conn_check_create_big_sync(conn)) {
- struct bt_iso_qos *qos = &conn->iso_qos;
-
- set_bit(HCI_CONN_CREATE_BIG_SYNC, &conn->flags);
-
- pdu->handle = qos->bcast.big;
- pdu->sync_handle = cpu_to_le16(conn->sync_handle);
- pdu->encryption = qos->bcast.encryption;
- memcpy(pdu->bcode, qos->bcast.bcode,
- sizeof(pdu->bcode));
- pdu->mse = qos->bcast.mse;
- pdu->timeout = cpu_to_le16(qos->bcast.timeout);
- pdu->num_bis = conn->num_bis;
- memcpy(pdu->bis, conn->bis, conn->num_bis);
-
- break;
- }
- }
-
-unlock:
- rcu_read_unlock();
-
- if (!pdu->num_bis)
- return 0;
-
- return hci_send_cmd(hdev, HCI_OP_LE_BIG_CREATE_SYNC,
- struct_size(pdu, bis, pdu->num_bis), pdu);
-}
-
-int hci_le_big_create_sync_pending(struct hci_dev *hdev)
-{
- /* Queue big_create_sync */
- return hci_cmd_sync_queue_once(hdev, big_create_sync,
- NULL, big_create_sync_complete);
-}
-
-int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon,
- struct bt_iso_qos *qos,
- __u16 sync_handle, __u8 num_bis, __u8 bis[])
+int hci_conn_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon,
+ struct bt_iso_qos *qos, __u16 sync_handle,
+ __u8 num_bis, __u8 bis[])
{
int err;
@@ -2274,9 +2106,10 @@ int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon,
hcon->num_bis = num_bis;
memcpy(hcon->bis, bis, num_bis);
+ hcon->conn_timeout = msecs_to_jiffies(qos->bcast.timeout * 10);
}
- return hci_le_big_create_sync_pending(hdev);
+ return hci_connect_big_sync(hdev, hcon);
}
static void create_big_complete(struct hci_dev *hdev, void *data, int err)
@@ -3072,6 +2905,7 @@ void hci_setup_tx_timestamp(struct sk_buff *skb, size_t key_offset,
const struct sockcm_cookie *sockc)
{
struct sock *sk = skb ? skb->sk : NULL;
+ int key;
/* This shall be called on a single skb of those generated by user
* sendmsg(), and only when the sendmsg() does not return error to
@@ -3087,13 +2921,16 @@ void hci_setup_tx_timestamp(struct sk_buff *skb, size_t key_offset,
sock_tx_timestamp(sk, sockc, &skb_shinfo(skb)->tx_flags);
+ if (sk->sk_type == SOCK_STREAM)
+ key = atomic_add_return(key_offset, &sk->sk_tskey);
+
if (sockc->tsflags & SOF_TIMESTAMPING_OPT_ID &&
sockc->tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) {
if (sockc->tsflags & SOCKCM_FLAG_TS_OPT_ID) {
skb_shinfo(skb)->tskey = sockc->ts_opt_id;
} else {
- int key = atomic_add_return(key_offset, &sk->sk_tskey);
-
+ if (sk->sk_type != SOCK_STREAM)
+ key = atomic_inc_return(&sk->sk_tskey);
skb_shinfo(skb)->tskey = key - 1;
}
}
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 1d8616f..6d60611 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -6160,11 +6160,12 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
* event or send an immediate device found event if the data
* should not be stored for later.
*/
- if (!ext_adv && !has_pending_adv_report(hdev)) {
+ if (!has_pending_adv_report(hdev)) {
/* If the report will trigger a SCAN_REQ store it for
* later merging.
*/
- if (type == LE_ADV_IND || type == LE_ADV_SCAN_IND) {
+ if (!ext_adv && (type == LE_ADV_IND ||
+ type == LE_ADV_SCAN_IND)) {
store_pending_adv_report(hdev, bdaddr, bdaddr_type,
rssi, flags, data, len);
return;
@@ -6377,8 +6378,7 @@ static void hci_le_pa_sync_estabilished_evt(struct hci_dev *hdev, void *data,
hci_dev_clear_flag(hdev, HCI_PA_SYNC);
- conn = hci_conn_hash_lookup_sid(hdev, ev->sid, &ev->bdaddr,
- ev->bdaddr_type);
+ conn = hci_conn_hash_lookup_create_pa_sync(hdev);
if (!conn) {
bt_dev_err(hdev,
"Unable to find connection for dst %pMR sid 0x%2.2x",
@@ -6417,9 +6417,6 @@ static void hci_le_pa_sync_estabilished_evt(struct hci_dev *hdev, void *data,
}
unlock:
- /* Handle any other pending PA sync command */
- hci_pa_create_sync_pending(hdev);
-
hci_dev_unlock(hdev);
}
@@ -6931,7 +6928,7 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data,
bt_dev_dbg(hdev, "status 0x%2.2x", ev->status);
- if (!hci_le_ev_skb_pull(hdev, skb, HCI_EVT_LE_BIG_SYNC_ESTABILISHED,
+ if (!hci_le_ev_skb_pull(hdev, skb, HCI_EVT_LE_BIG_SYNC_ESTABLISHED,
flex_array_size(ev, bis, ev->num_bis)))
return;
@@ -7002,9 +6999,6 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data,
}
unlock:
- /* Handle any other pending BIG sync command */
- hci_le_big_create_sync_pending(hdev);
-
hci_dev_unlock(hdev);
}
@@ -7126,8 +7120,8 @@ static const struct hci_le_ev {
hci_le_create_big_complete_evt,
sizeof(struct hci_evt_le_create_big_complete),
HCI_MAX_EVENT_SIZE),
- /* [0x1d = HCI_EV_LE_BIG_SYNC_ESTABILISHED] */
- HCI_LE_EV_VL(HCI_EVT_LE_BIG_SYNC_ESTABILISHED,
+ /* [0x1d = HCI_EV_LE_BIG_SYNC_ESTABLISHED] */
+ HCI_LE_EV_VL(HCI_EVT_LE_BIG_SYNC_ESTABLISHED,
hci_le_big_sync_established_evt,
sizeof(struct hci_evt_le_big_sync_estabilished),
HCI_MAX_EVENT_SIZE),
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 609b035..e56b1cb 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -2693,16 +2693,16 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev)
/* Force address filtering if PA Sync is in progress */
if (hci_dev_test_flag(hdev, HCI_PA_SYNC)) {
- struct hci_cp_le_pa_create_sync *sent;
+ struct hci_conn *conn;
- sent = hci_sent_cmd_data(hdev, HCI_OP_LE_PA_CREATE_SYNC);
- if (sent) {
+ conn = hci_conn_hash_lookup_create_pa_sync(hdev);
+ if (conn) {
struct conn_params pa;
memset(&pa, 0, sizeof(pa));
- bacpy(&pa.addr, &sent->addr);
- pa.addr_type = sent->addr_type;
+ bacpy(&pa.addr, &conn->dst);
+ pa.addr_type = conn->dst_type;
/* Clear first since there could be addresses left
* behind.
@@ -6895,3 +6895,143 @@ int hci_le_conn_update_sync(struct hci_dev *hdev, struct hci_conn *conn,
return __hci_cmd_sync_status(hdev, HCI_OP_LE_CONN_UPDATE,
sizeof(cp), &cp, HCI_CMD_TIMEOUT);
}
+
+static void create_pa_complete(struct hci_dev *hdev, void *data, int err)
+{
+ bt_dev_dbg(hdev, "err %d", err);
+
+ if (!err)
+ return;
+
+ hci_dev_clear_flag(hdev, HCI_PA_SYNC);
+
+ if (err == -ECANCELED)
+ return;
+
+ hci_dev_lock(hdev);
+
+ hci_update_passive_scan_sync(hdev);
+
+ hci_dev_unlock(hdev);
+}
+
+static int hci_le_pa_create_sync(struct hci_dev *hdev, void *data)
+{
+ struct hci_cp_le_pa_create_sync cp;
+ struct hci_conn *conn = data;
+ struct bt_iso_qos *qos = &conn->iso_qos;
+ int err;
+
+ if (!hci_conn_valid(hdev, conn))
+ return -ECANCELED;
+
+ if (hci_dev_test_and_set_flag(hdev, HCI_PA_SYNC))
+ return -EBUSY;
+
+ /* Mark HCI_CONN_CREATE_PA_SYNC so hci_update_passive_scan_sync can
+ * program the address in the allow list so PA advertisements can be
+ * received.
+ */
+ set_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags);
+
+ hci_update_passive_scan_sync(hdev);
+
+ memset(&cp, 0, sizeof(cp));
+ cp.options = qos->bcast.options;
+ cp.sid = conn->sid;
+ cp.addr_type = conn->dst_type;
+ bacpy(&cp.addr, &conn->dst);
+ cp.skip = cpu_to_le16(qos->bcast.skip);
+ cp.sync_timeout = cpu_to_le16(qos->bcast.sync_timeout);
+ cp.sync_cte_type = qos->bcast.sync_cte_type;
+
+ /* The spec allows only one pending LE Periodic Advertising Create
+ * Sync command at a time so we forcefully wait for PA Sync Established
+ * event since cmd_work can only schedule one command at a time.
+ *
+ * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E
+ * page 2493:
+ *
+ * If the Host issues this command when another HCI_LE_Periodic_
+ * Advertising_Create_Sync command is pending, the Controller shall
+ * return the error code Command Disallowed (0x0C).
+ */
+ err = __hci_cmd_sync_status_sk(hdev, HCI_OP_LE_PA_CREATE_SYNC,
+ sizeof(cp), &cp,
+ HCI_EV_LE_PA_SYNC_ESTABLISHED,
+ conn->conn_timeout, NULL);
+ if (err == -ETIMEDOUT)
+ __hci_cmd_sync_status(hdev, HCI_OP_LE_PA_CREATE_SYNC_CANCEL,
+ 0, NULL, HCI_CMD_TIMEOUT);
+
+ return err;
+}
+
+int hci_connect_pa_sync(struct hci_dev *hdev, struct hci_conn *conn)
+{
+ return hci_cmd_sync_queue_once(hdev, hci_le_pa_create_sync, conn,
+ create_pa_complete);
+}
+
+static void create_big_complete(struct hci_dev *hdev, void *data, int err)
+{
+ struct hci_conn *conn = data;
+
+ bt_dev_dbg(hdev, "err %d", err);
+
+ if (err == -ECANCELED)
+ return;
+
+ if (hci_conn_valid(hdev, conn))
+ clear_bit(HCI_CONN_CREATE_BIG_SYNC, &conn->flags);
+}
+
+static int hci_le_big_create_sync(struct hci_dev *hdev, void *data)
+{
+ DEFINE_FLEX(struct hci_cp_le_big_create_sync, cp, bis, num_bis, 0x11);
+ struct hci_conn *conn = data;
+ struct bt_iso_qos *qos = &conn->iso_qos;
+ int err;
+
+ if (!hci_conn_valid(hdev, conn))
+ return -ECANCELED;
+
+ set_bit(HCI_CONN_CREATE_BIG_SYNC, &conn->flags);
+
+ memset(cp, 0, sizeof(*cp));
+ cp->handle = qos->bcast.big;
+ cp->sync_handle = cpu_to_le16(conn->sync_handle);
+ cp->encryption = qos->bcast.encryption;
+ memcpy(cp->bcode, qos->bcast.bcode, sizeof(cp->bcode));
+ cp->mse = qos->bcast.mse;
+ cp->timeout = cpu_to_le16(qos->bcast.timeout);
+ cp->num_bis = conn->num_bis;
+ memcpy(cp->bis, conn->bis, conn->num_bis);
+
+ /* The spec allows only one pending LE BIG Create Sync command at
+ * a time, so we forcefully wait for BIG Sync Established event since
+ * cmd_work can only schedule one command at a time.
+ *
+ * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E
+ * page 2586:
+ *
+ * If the Host sends this command when the Controller is in the
+ * process of synchronizing to any BIG, i.e. the HCI_LE_BIG_Sync_
+ * Established event has not been generated, the Controller shall
+ * return the error code Command Disallowed (0x0C).
+ */
+ err = __hci_cmd_sync_status_sk(hdev, HCI_OP_LE_BIG_CREATE_SYNC,
+ struct_size(cp, bis, cp->num_bis), cp,
+ HCI_EVT_LE_BIG_SYNC_ESTABLISHED,
+ conn->conn_timeout, NULL);
+ if (err == -ETIMEDOUT)
+ hci_le_big_terminate_sync(hdev, cp->handle);
+
+ return err;
+}
+
+int hci_connect_big_sync(struct hci_dev *hdev, struct hci_conn *conn)
+{
+ return hci_cmd_sync_queue_once(hdev, hci_le_big_create_sync, conn,
+ create_big_complete);
+}
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 3501a99..2819cda 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -1462,14 +1462,13 @@ static void iso_conn_big_sync(struct sock *sk)
lock_sock(sk);
if (!test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) {
- err = hci_le_big_create_sync(hdev, iso_pi(sk)->conn->hcon,
- &iso_pi(sk)->qos,
- iso_pi(sk)->sync_handle,
- iso_pi(sk)->bc_num_bis,
- iso_pi(sk)->bc_bis);
+ err = hci_conn_big_create_sync(hdev, iso_pi(sk)->conn->hcon,
+ &iso_pi(sk)->qos,
+ iso_pi(sk)->sync_handle,
+ iso_pi(sk)->bc_num_bis,
+ iso_pi(sk)->bc_bis);
if (err)
- bt_dev_err(hdev, "hci_le_big_create_sync: %d",
- err);
+ bt_dev_err(hdev, "hci_big_create_sync: %d", err);
}
release_sock(sk);
@@ -1922,7 +1921,7 @@ static void iso_conn_ready(struct iso_conn *conn)
hcon);
} else if (test_bit(HCI_CONN_BIG_SYNC_FAILED, &hcon->flags)) {
ev = hci_recv_event_data(hcon->hdev,
- HCI_EVT_LE_BIG_SYNC_ESTABILISHED);
+ HCI_EVT_LE_BIG_SYNC_ESTABLISHED);
/* Get reference to PA sync parent socket, if it exists */
parent = iso_get_sock(&hcon->src, &hcon->dst,
@@ -2113,12 +2112,11 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags)
if (!test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags) &&
!test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) {
- err = hci_le_big_create_sync(hdev,
- hcon,
- &iso_pi(sk)->qos,
- iso_pi(sk)->sync_handle,
- iso_pi(sk)->bc_num_bis,
- iso_pi(sk)->bc_bis);
+ err = hci_conn_big_create_sync(hdev, hcon,
+ &iso_pi(sk)->qos,
+ iso_pi(sk)->sync_handle,
+ iso_pi(sk)->bc_num_bis,
+ iso_pi(sk)->bc_bis);
if (err) {
bt_dev_err(hdev, "hci_le_big_create_sync: %d",
err);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index c7b66b2..7347275 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -3991,7 +3991,8 @@ static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd,
/* Check if the ACL is secure enough (if not SDP) */
if (psm != cpu_to_le16(L2CAP_PSM_SDP) &&
- !hci_conn_check_link_mode(conn->hcon)) {
+ (!hci_conn_check_link_mode(conn->hcon) ||
+ !l2cap_check_enc_key_size(conn->hcon))) {
conn->disc_reason = HCI_ERROR_AUTH_FAILURE;
result = L2CAP_CR_SEC_BLOCK;
goto response;
@@ -7414,6 +7415,9 @@ static int l2cap_recv_frag(struct l2cap_conn *conn, struct sk_buff *skb,
return -ENOMEM;
/* Init rx_len */
conn->rx_len = len;
+
+ skb_set_delivery_time(conn->rx_skb, skb->tstamp,
+ skb->tstamp_type);
}
/* Copy as much as the rx_skb can hold */
@@ -7538,8 +7542,24 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags)
if (skb->len > len) {
BT_ERR("Frame is too long (len %u, expected len %d)",
skb->len, len);
+ /* PTS test cases L2CAP/COS/CED/BI-14-C and BI-15-C
+ * (Multiple Signaling Command in one PDU, Data
+ * Truncated, BR/EDR) send a C-frame to the IUT with
+ * PDU Length set to 8 and Channel ID set to the
+ * correct signaling channel for the logical link.
+ * The Information payload contains one L2CAP_ECHO_REQ
+ * packet with Data Length set to 0 with 0 octets of
+ * echo data and one invalid command packet due to
+ * data truncated in PDU but present in HCI packet.
+ *
+ * Shorter the socket buffer to the PDU length to
+ * allow to process valid commands from the PDU before
+ * setting the socket unreliable.
+ */
+ skb->len = len;
+ l2cap_recv_frame(conn, skb);
l2cap_conn_unreliable(conn, ECOMM);
- goto drop;
+ goto unlock;
}
/* Append fragment into frame (with header) */
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index d9a69ec..939a3aa 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -715,8 +715,8 @@ static int br_vlan_add_existing(struct net_bridge *br,
u16 flags, bool *changed,
struct netlink_ext_ack *extack)
{
- bool would_change = __vlan_flags_would_change(vlan, flags);
bool becomes_brentry = false;
+ bool would_change = false;
int err;
if (!br_vlan_is_brentry(vlan)) {
@@ -725,6 +725,8 @@ static int br_vlan_add_existing(struct net_bridge *br,
return -EINVAL;
becomes_brentry = true;
+ } else {
+ would_change = __vlan_flags_would_change(vlan, flags);
}
/* Master VLANs that aren't brentries weren't notified before,
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 17226b2..6fefe7a 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -655,6 +655,7 @@ static int j1939_sk_release(struct socket *sock)
sock->sk = NULL;
release_sock(sk);
+ sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
sock_put(sk);
return 0;
diff --git a/net/ceph/Kconfig b/net/ceph/Kconfig
index c5c4eef..0aa21fc 100644
--- a/net/ceph/Kconfig
+++ b/net/ceph/Kconfig
@@ -2,7 +2,7 @@
config CEPH_LIB
tristate "Ceph core library"
depends on INET
- select LIBCRC32C
+ select CRC32
select CRYPTO_AES
select CRYPTO_CBC
select CRYPTO_GCM
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index b24afec..6664ea7 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -220,16 +220,6 @@ void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *osd_req,
}
EXPORT_SYMBOL(osd_req_op_extent_osd_data_pages);
-void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *osd_req,
- unsigned int which, struct ceph_pagelist *pagelist)
-{
- struct ceph_osd_data *osd_data;
-
- osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
- ceph_osd_data_pagelist_init(osd_data, pagelist);
-}
-EXPORT_SYMBOL(osd_req_op_extent_osd_data_pagelist);
-
#ifdef CONFIG_BLOCK
void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req,
unsigned int which,
@@ -297,19 +287,6 @@ static void osd_req_op_cls_request_info_pagelist(
ceph_osd_data_pagelist_init(osd_data, pagelist);
}
-void osd_req_op_cls_request_data_pagelist(
- struct ceph_osd_request *osd_req,
- unsigned int which, struct ceph_pagelist *pagelist)
-{
- struct ceph_osd_data *osd_data;
-
- osd_data = osd_req_op_data(osd_req, which, cls, request_data);
- ceph_osd_data_pagelist_init(osd_data, pagelist);
- osd_req->r_ops[which].cls.indata_len += pagelist->length;
- osd_req->r_ops[which].indata_len += pagelist->length;
-}
-EXPORT_SYMBOL(osd_req_op_cls_request_data_pagelist);
-
void osd_req_op_cls_request_data_pages(struct ceph_osd_request *osd_req,
unsigned int which, struct page **pages, u64 length,
u32 alignment, bool pages_from_pool, bool own_pages)
diff --git a/net/core/dev.c b/net/core/dev.c
index 0608605..1be7cb7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1518,16 +1518,10 @@ void netdev_features_change(struct net_device *dev)
}
EXPORT_SYMBOL(netdev_features_change);
-/**
- * netdev_state_change - device changes state
- * @dev: device to cause notification
- *
- * Called to indicate a device has changed state. This function calls
- * the notifier chains for netdev_chain and sends a NEWLINK message
- * to the routing socket.
- */
-void netdev_state_change(struct net_device *dev)
+void netif_state_change(struct net_device *dev)
{
+ netdev_ops_assert_locked_or_invisible(dev);
+
if (dev->flags & IFF_UP) {
struct netdev_notifier_change_info change_info = {
.info.dev = dev,
@@ -1538,7 +1532,6 @@ void netdev_state_change(struct net_device *dev)
rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL, 0, NULL);
}
}
-EXPORT_SYMBOL(netdev_state_change);
/**
* __netdev_notify_peers - notify network peers about existence of @dev,
@@ -11941,15 +11934,24 @@ void unregister_netdevice_many_notify(struct list_head *head,
BUG_ON(dev->reg_state != NETREG_REGISTERED);
}
- /* If device is running, close it first. */
+ /* If device is running, close it first. Start with ops locked... */
list_for_each_entry(dev, head, unreg_list) {
- list_add_tail(&dev->close_list, &close_head);
- netdev_lock_ops(dev);
+ if (netdev_need_ops_lock(dev)) {
+ list_add_tail(&dev->close_list, &close_head);
+ netdev_lock(dev);
+ }
+ }
+ dev_close_many(&close_head, true);
+ /* ... now unlock them and go over the rest. */
+ list_for_each_entry(dev, head, unreg_list) {
+ if (netdev_need_ops_lock(dev))
+ netdev_unlock(dev);
+ else
+ list_add_tail(&dev->close_list, &close_head);
}
dev_close_many(&close_head, true);
list_for_each_entry(dev, head, unreg_list) {
- netdev_unlock_ops(dev);
/* And unlink it from device chain. */
unlist_netdevice(dev);
netdev_lock(dev);
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index 90bafb0..90898cd 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -327,3 +327,19 @@ int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf)
return ret;
}
EXPORT_SYMBOL_GPL(dev_xdp_propagate);
+
+/**
+ * netdev_state_change() - device changes state
+ * @dev: device to cause notification
+ *
+ * Called to indicate a device has changed state. This function calls
+ * the notifier chains for netdev_chain and sends a NEWLINK message
+ * to the routing socket.
+ */
+void netdev_state_change(struct net_device *dev)
+{
+ netdev_lock_ops(dev);
+ netif_state_change(dev);
+ netdev_unlock_ops(dev);
+}
+EXPORT_SYMBOL(netdev_state_change);
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 4bc64d9..7af30208 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -257,6 +257,24 @@ static int nla_put_port_range(struct sk_buff *skb, int attrtype,
return nla_put(skb, attrtype, sizeof(*range), range);
}
+static bool fib_rule_iif_match(const struct fib_rule *rule, int iifindex,
+ const struct flowi *fl)
+{
+ u8 iif_is_l3_master = READ_ONCE(rule->iif_is_l3_master);
+
+ return iif_is_l3_master ? l3mdev_fib_rule_iif_match(fl, iifindex) :
+ fl->flowi_iif == iifindex;
+}
+
+static bool fib_rule_oif_match(const struct fib_rule *rule, int oifindex,
+ const struct flowi *fl)
+{
+ u8 oif_is_l3_master = READ_ONCE(rule->oif_is_l3_master);
+
+ return oif_is_l3_master ? l3mdev_fib_rule_oif_match(fl, oifindex) :
+ fl->flowi_oif == oifindex;
+}
+
static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
struct flowi *fl, int flags,
struct fib_lookup_arg *arg)
@@ -264,11 +282,11 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
int iifindex, oifindex, ret = 0;
iifindex = READ_ONCE(rule->iifindex);
- if (iifindex && (iifindex != fl->flowi_iif))
+ if (iifindex && !fib_rule_iif_match(rule, iifindex, fl))
goto out;
oifindex = READ_ONCE(rule->oifindex);
- if (oifindex && (oifindex != fl->flowi_oif))
+ if (oifindex && !fib_rule_oif_match(rule, oifindex, fl))
goto out;
if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask)
@@ -736,16 +754,20 @@ static int fib_nl2rule_rtnl(struct fib_rule *nlrule,
struct net_device *dev;
dev = __dev_get_by_name(nlrule->fr_net, nlrule->iifname);
- if (dev)
+ if (dev) {
nlrule->iifindex = dev->ifindex;
+ nlrule->iif_is_l3_master = netif_is_l3_master(dev);
+ }
}
if (tb[FRA_OIFNAME]) {
struct net_device *dev;
dev = __dev_get_by_name(nlrule->fr_net, nlrule->oifname);
- if (dev)
+ if (dev) {
nlrule->oifindex = dev->ifindex;
+ nlrule->oif_is_l3_master = netif_is_l3_master(dev);
+ }
}
return 0;
@@ -1336,11 +1358,17 @@ static void attach_rules(struct list_head *rules, struct net_device *dev)
list_for_each_entry(rule, rules, list) {
if (rule->iifindex == -1 &&
- strcmp(dev->name, rule->iifname) == 0)
+ strcmp(dev->name, rule->iifname) == 0) {
WRITE_ONCE(rule->iifindex, dev->ifindex);
+ WRITE_ONCE(rule->iif_is_l3_master,
+ netif_is_l3_master(dev));
+ }
if (rule->oifindex == -1 &&
- strcmp(dev->name, rule->oifname) == 0)
+ strcmp(dev->name, rule->oifname) == 0) {
WRITE_ONCE(rule->oifindex, dev->ifindex);
+ WRITE_ONCE(rule->oif_is_l3_master,
+ netif_is_l3_master(dev));
+ }
}
}
@@ -1349,10 +1377,14 @@ static void detach_rules(struct list_head *rules, struct net_device *dev)
struct fib_rule *rule;
list_for_each_entry(rule, rules, list) {
- if (rule->iifindex == dev->ifindex)
+ if (rule->iifindex == dev->ifindex) {
WRITE_ONCE(rule->iifindex, -1);
- if (rule->oifindex == dev->ifindex)
+ WRITE_ONCE(rule->iif_is_l3_master, false);
+ }
+ if (rule->oifindex == dev->ifindex) {
WRITE_ONCE(rule->oifindex, -1);
+ WRITE_ONCE(rule->oif_is_l3_master, false);
+ }
}
}
diff --git a/net/core/filter.c b/net/core/filter.c
index bc68287..79cab4d 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -218,24 +218,36 @@ BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x)
return 0;
}
+static int bpf_skb_load_helper_convert_offset(const struct sk_buff *skb, int offset)
+{
+ if (likely(offset >= 0))
+ return offset;
+
+ if (offset >= SKF_NET_OFF)
+ return offset - SKF_NET_OFF + skb_network_offset(skb);
+
+ if (offset >= SKF_LL_OFF && skb_mac_header_was_set(skb))
+ return offset - SKF_LL_OFF + skb_mac_offset(skb);
+
+ return INT_MIN;
+}
+
BPF_CALL_4(bpf_skb_load_helper_8, const struct sk_buff *, skb, const void *,
data, int, headlen, int, offset)
{
- u8 tmp, *ptr;
+ u8 tmp;
const int len = sizeof(tmp);
- if (offset >= 0) {
- if (headlen - offset >= len)
- return *(u8 *)(data + offset);
- if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
- return tmp;
- } else {
- ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
- if (likely(ptr))
- return *(u8 *)ptr;
- }
+ offset = bpf_skb_load_helper_convert_offset(skb, offset);
+ if (offset == INT_MIN)
+ return -EFAULT;
- return -EFAULT;
+ if (headlen - offset >= len)
+ return *(u8 *)(data + offset);
+ if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
+ return tmp;
+ else
+ return -EFAULT;
}
BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb,
@@ -248,21 +260,19 @@ BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb,
BPF_CALL_4(bpf_skb_load_helper_16, const struct sk_buff *, skb, const void *,
data, int, headlen, int, offset)
{
- __be16 tmp, *ptr;
+ __be16 tmp;
const int len = sizeof(tmp);
- if (offset >= 0) {
- if (headlen - offset >= len)
- return get_unaligned_be16(data + offset);
- if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
- return be16_to_cpu(tmp);
- } else {
- ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
- if (likely(ptr))
- return get_unaligned_be16(ptr);
- }
+ offset = bpf_skb_load_helper_convert_offset(skb, offset);
+ if (offset == INT_MIN)
+ return -EFAULT;
- return -EFAULT;
+ if (headlen - offset >= len)
+ return get_unaligned_be16(data + offset);
+ if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
+ return be16_to_cpu(tmp);
+ else
+ return -EFAULT;
}
BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb,
@@ -275,21 +285,19 @@ BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb,
BPF_CALL_4(bpf_skb_load_helper_32, const struct sk_buff *, skb, const void *,
data, int, headlen, int, offset)
{
- __be32 tmp, *ptr;
+ __be32 tmp;
const int len = sizeof(tmp);
- if (likely(offset >= 0)) {
- if (headlen - offset >= len)
- return get_unaligned_be32(data + offset);
- if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
- return be32_to_cpu(tmp);
- } else {
- ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
- if (likely(ptr))
- return get_unaligned_be32(ptr);
- }
+ offset = bpf_skb_load_helper_convert_offset(skb, offset);
+ if (offset == INT_MIN)
+ return -EFAULT;
- return -EFAULT;
+ if (headlen - offset >= len)
+ return get_unaligned_be32(data + offset);
+ if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
+ return be32_to_cpu(tmp);
+ else
+ return -EFAULT;
}
BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb,
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index cb04ef2..864f3bb 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -183,7 +183,7 @@ static void linkwatch_do_dev(struct net_device *dev)
else
dev_deactivate(dev);
- netdev_state_change(dev);
+ netif_state_change(dev);
}
/* Note: our callers are responsible for calling netdev_tracker_free().
* This is the reason we use __dev_put() instead of dev_put().
@@ -240,7 +240,9 @@ static void __linkwatch_run_queue(int urgent_only)
*/
netdev_tracker_free(dev, &dev->linkwatch_dev_tracker);
spin_unlock_irq(&lweventlist_lock);
+ netdev_lock_ops(dev);
linkwatch_do_dev(dev);
+ netdev_unlock_ops(dev);
do_dev--;
spin_lock_irq(&lweventlist_lock);
}
@@ -253,25 +255,41 @@ static void __linkwatch_run_queue(int urgent_only)
spin_unlock_irq(&lweventlist_lock);
}
-void linkwatch_sync_dev(struct net_device *dev)
+static bool linkwatch_clean_dev(struct net_device *dev)
{
unsigned long flags;
- int clean = 0;
+ bool clean = false;
spin_lock_irqsave(&lweventlist_lock, flags);
if (!list_empty(&dev->link_watch_list)) {
list_del_init(&dev->link_watch_list);
- clean = 1;
+ clean = true;
/* We must release netdev tracker under
* the spinlock protection.
*/
netdev_tracker_free(dev, &dev->linkwatch_dev_tracker);
}
spin_unlock_irqrestore(&lweventlist_lock, flags);
- if (clean)
+
+ return clean;
+}
+
+void __linkwatch_sync_dev(struct net_device *dev)
+{
+ netdev_ops_assert_locked(dev);
+
+ if (linkwatch_clean_dev(dev))
linkwatch_do_dev(dev);
}
+void linkwatch_sync_dev(struct net_device *dev)
+{
+ if (linkwatch_clean_dev(dev)) {
+ netdev_lock_ops(dev);
+ linkwatch_do_dev(dev);
+ netdev_unlock_ops(dev);
+ }
+}
/* Must be called with the rtnl semaphore held */
void linkwatch_run_queue(void)
diff --git a/net/core/lock_debug.c b/net/core/lock_debug.c
index b7f22dc..941e26c 100644
--- a/net/core/lock_debug.c
+++ b/net/core/lock_debug.c
@@ -20,11 +20,11 @@ int netdev_debug_event(struct notifier_block *nb, unsigned long event,
switch (cmd) {
case NETDEV_REGISTER:
case NETDEV_UP:
+ case NETDEV_CHANGE:
netdev_ops_assert_locked(dev);
fallthrough;
case NETDEV_DOWN:
case NETDEV_REBOOT:
- case NETDEV_CHANGE:
case NETDEV_UNREGISTER:
case NETDEV_CHANGEMTU:
case NETDEV_CHANGEADDR:
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index e39a459..60f27cb4 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -333,6 +333,8 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
struct dst_entry *dst;
int ret;
+ local_bh_disable();
+
if (dev_xmit_recursion()) {
net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
__func__);
@@ -348,8 +350,10 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
lwtstate = dst->lwtstate;
if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
- lwtstate->type > LWTUNNEL_ENCAP_MAX)
- return 0;
+ lwtstate->type > LWTUNNEL_ENCAP_MAX) {
+ ret = 0;
+ goto out;
+ }
ret = -EOPNOTSUPP;
rcu_read_lock();
@@ -364,11 +368,13 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
if (ret == -EOPNOTSUPP)
goto drop;
- return ret;
+ goto out;
drop:
kfree_skb(skb);
+out:
+ local_bh_enable();
return ret;
}
EXPORT_SYMBOL_GPL(lwtunnel_output);
@@ -380,6 +386,8 @@ int lwtunnel_xmit(struct sk_buff *skb)
struct dst_entry *dst;
int ret;
+ local_bh_disable();
+
if (dev_xmit_recursion()) {
net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
__func__);
@@ -396,8 +404,10 @@ int lwtunnel_xmit(struct sk_buff *skb)
lwtstate = dst->lwtstate;
if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
- lwtstate->type > LWTUNNEL_ENCAP_MAX)
- return 0;
+ lwtstate->type > LWTUNNEL_ENCAP_MAX) {
+ ret = 0;
+ goto out;
+ }
ret = -EOPNOTSUPP;
rcu_read_lock();
@@ -412,11 +422,13 @@ int lwtunnel_xmit(struct sk_buff *skb)
if (ret == -EOPNOTSUPP)
goto drop;
- return ret;
+ goto out;
drop:
kfree_skb(skb);
+out:
+ local_bh_enable();
return ret;
}
EXPORT_SYMBOL_GPL(lwtunnel_xmit);
@@ -428,6 +440,8 @@ int lwtunnel_input(struct sk_buff *skb)
struct dst_entry *dst;
int ret;
+ DEBUG_NET_WARN_ON_ONCE(!in_softirq());
+
if (dev_xmit_recursion()) {
net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
__func__);
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 5d7af50..230743b 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -861,14 +861,17 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
mutex_lock(&priv->lock);
+ err = 0;
netdev = netdev_get_by_index_lock(genl_info_net(info), ifindex);
- if (!netdev || !netif_device_present(netdev)) {
+ if (!netdev) {
err = -ENODEV;
goto err_unlock_sock;
}
-
- if (!netdev_need_ops_lock(netdev)) {
+ if (!netif_device_present(netdev))
+ err = -ENODEV;
+ else if (!netdev_need_ops_lock(netdev))
err = -EOPNOTSUPP;
+ if (err) {
NL_SET_BAD_ATTR(info->extack,
info->attrs[NETDEV_A_DEV_IFINDEX]);
goto err_unlock;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index c238528..c5a7f41 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1043,7 +1043,7 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
}
EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo);
-void netdev_set_operstate(struct net_device *dev, int newstate)
+void netif_set_operstate(struct net_device *dev, int newstate)
{
unsigned int old = READ_ONCE(dev->operstate);
@@ -1052,9 +1052,9 @@ void netdev_set_operstate(struct net_device *dev, int newstate)
return;
} while (!try_cmpxchg(&dev->operstate, &old, newstate));
- netdev_state_change(dev);
+ netif_state_change(dev);
}
-EXPORT_SYMBOL(netdev_set_operstate);
+EXPORT_SYMBOL(netif_set_operstate);
static void set_operstate(struct net_device *dev, unsigned char transition)
{
@@ -1080,7 +1080,7 @@ static void set_operstate(struct net_device *dev, unsigned char transition)
break;
}
- netdev_set_operstate(dev, operstate);
+ netif_set_operstate(dev, operstate);
}
static unsigned int rtnl_dev_get_flags(const struct net_device *dev)
@@ -3027,7 +3027,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
err = validate_linkmsg(dev, tb, extack);
if (err < 0)
- goto errout;
+ return err;
if (tb[IFLA_IFNAME])
nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
@@ -3396,7 +3396,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
errout:
if (status & DO_SETLINK_MODIFIED) {
if ((status & DO_SETLINK_NOTIFY) == DO_SETLINK_NOTIFY)
- netdev_state_change(dev);
+ netif_state_change(dev);
if (err < 0)
net_warn_ratelimited("A link change request failed with some changes committed already. Interface %s may have been left with an inconsistent configuration, please check.\n",
diff --git a/net/core/selftests.c b/net/core/selftests.c
index e99ae98..35f807e 100644
--- a/net/core/selftests.c
+++ b/net/core/selftests.c
@@ -100,10 +100,10 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev,
ehdr->h_proto = htons(ETH_P_IP);
if (attr->tcp) {
+ memset(thdr, 0, sizeof(*thdr));
thdr->source = htons(attr->sport);
thdr->dest = htons(attr->dport);
thdr->doff = sizeof(struct tcphdr) / 4;
- thdr->check = 0;
} else {
uhdr->source = htons(attr->sport);
uhdr->dest = htons(attr->dport);
@@ -144,10 +144,18 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev,
attr->id = net_test_next_id;
shdr->id = net_test_next_id++;
- if (attr->size)
- skb_put(skb, attr->size);
- if (attr->max_size && attr->max_size > skb->len)
- skb_put(skb, attr->max_size - skb->len);
+ if (attr->size) {
+ void *payload = skb_put(skb, attr->size);
+
+ memset(payload, 0, attr->size);
+ }
+
+ if (attr->max_size && attr->max_size > skb->len) {
+ size_t pad_len = attr->max_size - skb->len;
+ void *pad = skb_put(skb, pad_len);
+
+ memset(pad, 0, pad_len);
+ }
skb->csum = 0;
skb->ip_summed = CHECKSUM_PARTIAL;
diff --git a/net/core/sock.c b/net/core/sock.c
index f67a3c5b..e54449c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2130,6 +2130,8 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
*/
static inline void sock_lock_init(struct sock *sk)
{
+ sk_owner_clear(sk);
+
if (sk->sk_kern_sock)
sock_lock_init_class_and_name(
sk,
@@ -2226,6 +2228,9 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
cgroup_sk_free(&sk->sk_cgrp_data);
mem_cgroup_sk_free(sk);
security_sk_free(sk);
+
+ sk_owner_put(sk);
+
if (slab != NULL)
kmem_cache_free(slab, sk);
else
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index e827775..436a7e1 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -862,6 +862,16 @@ static void dsa_tree_teardown_lags(struct dsa_switch_tree *dst)
kfree(dst->lags);
}
+static void dsa_tree_teardown_routing_table(struct dsa_switch_tree *dst)
+{
+ struct dsa_link *dl, *next;
+
+ list_for_each_entry_safe(dl, next, &dst->rtable, list) {
+ list_del(&dl->list);
+ kfree(dl);
+ }
+}
+
static int dsa_tree_setup(struct dsa_switch_tree *dst)
{
bool complete;
@@ -879,7 +889,7 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst)
err = dsa_tree_setup_cpu_ports(dst);
if (err)
- return err;
+ goto teardown_rtable;
err = dsa_tree_setup_switches(dst);
if (err)
@@ -911,14 +921,14 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst)
dsa_tree_teardown_switches(dst);
teardown_cpu_ports:
dsa_tree_teardown_cpu_ports(dst);
+teardown_rtable:
+ dsa_tree_teardown_routing_table(dst);
return err;
}
static void dsa_tree_teardown(struct dsa_switch_tree *dst)
{
- struct dsa_link *dl, *next;
-
if (!dst->setup)
return;
@@ -932,10 +942,7 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst)
dsa_tree_teardown_cpu_ports(dst);
- list_for_each_entry_safe(dl, next, &dst->rtable, list) {
- list_del(&dl->list);
- kfree(dl);
- }
+ dsa_tree_teardown_routing_table(dst);
pr_info("DSA: tree %d torn down\n", dst->index);
@@ -1478,12 +1485,44 @@ static int dsa_switch_parse(struct dsa_switch *ds, struct dsa_chip_data *cd)
static void dsa_switch_release_ports(struct dsa_switch *ds)
{
+ struct dsa_mac_addr *a, *tmp;
struct dsa_port *dp, *next;
+ struct dsa_vlan *v, *n;
dsa_switch_for_each_port_safe(dp, next, ds) {
- WARN_ON(!list_empty(&dp->fdbs));
- WARN_ON(!list_empty(&dp->mdbs));
- WARN_ON(!list_empty(&dp->vlans));
+ /* These are either entries that upper layers lost track of
+ * (probably due to bugs), or installed through interfaces
+ * where one does not necessarily have to remove them, like
+ * ndo_dflt_fdb_add().
+ */
+ list_for_each_entry_safe(a, tmp, &dp->fdbs, list) {
+ dev_info(ds->dev,
+ "Cleaning up unicast address %pM vid %u from port %d\n",
+ a->addr, a->vid, dp->index);
+ list_del(&a->list);
+ kfree(a);
+ }
+
+ list_for_each_entry_safe(a, tmp, &dp->mdbs, list) {
+ dev_info(ds->dev,
+ "Cleaning up multicast address %pM vid %u from port %d\n",
+ a->addr, a->vid, dp->index);
+ list_del(&a->list);
+ kfree(a);
+ }
+
+ /* These are entries that upper layers have lost track of,
+ * probably due to bugs, but also due to dsa_port_do_vlan_del()
+ * having failed and the VLAN entry still lingering on.
+ */
+ list_for_each_entry_safe(v, n, &dp->vlans, list) {
+ dev_info(ds->dev,
+ "Cleaning up vid %u from port %d\n",
+ v->vid, dp->index);
+ list_del(&v->list);
+ kfree(v);
+ }
+
list_del(&dp->list);
kfree(dp);
}
diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c
index 3ee53e2..53e03fd 100644
--- a/net/dsa/tag_8021q.c
+++ b/net/dsa/tag_8021q.c
@@ -197,7 +197,7 @@ static int dsa_port_do_tag_8021q_vlan_del(struct dsa_port *dp, u16 vid)
err = ds->ops->tag_8021q_vlan_del(ds, port, vid);
if (err) {
- refcount_inc(&v->refcount);
+ refcount_set(&v->refcount, 1);
return err;
}
diff --git a/net/ethtool/cmis.h b/net/ethtool/cmis.h
index 1e79041..4a9a946 100644
--- a/net/ethtool/cmis.h
+++ b/net/ethtool/cmis.h
@@ -101,7 +101,6 @@ struct ethtool_cmis_cdb_rpl {
};
u32 ethtool_cmis_get_max_lpl_size(u8 num_of_byte_octs);
-u32 ethtool_cmis_get_max_epl_size(u8 num_of_byte_octs);
void ethtool_cmis_cdb_compose_args(struct ethtool_cmis_cdb_cmd_args *args,
enum ethtool_cmis_cdb_cmd_id cmd, u8 *lpl,
diff --git a/net/ethtool/cmis_cdb.c b/net/ethtool/cmis_cdb.c
index d159dc1..3057576 100644
--- a/net/ethtool/cmis_cdb.c
+++ b/net/ethtool/cmis_cdb.c
@@ -16,15 +16,6 @@ u32 ethtool_cmis_get_max_lpl_size(u8 num_of_byte_octs)
return 8 * (1 + min_t(u8, num_of_byte_octs, 15));
}
-/* For accessing the EPL field on page 9Fh, the allowable length extension is
- * min(i, 255) byte octets where i specifies the allowable additional number of
- * byte octets in a READ or a WRITE.
- */
-u32 ethtool_cmis_get_max_epl_size(u8 num_of_byte_octs)
-{
- return 8 * (1 + min_t(u8, num_of_byte_octs, 255));
-}
-
void ethtool_cmis_cdb_compose_args(struct ethtool_cmis_cdb_cmd_args *args,
enum ethtool_cmis_cdb_cmd_id cmd, u8 *lpl,
u8 lpl_len, u8 *epl, u16 epl_len,
@@ -33,19 +24,16 @@ void ethtool_cmis_cdb_compose_args(struct ethtool_cmis_cdb_cmd_args *args,
{
args->req.id = cpu_to_be16(cmd);
args->req.lpl_len = lpl_len;
- if (lpl) {
+ if (lpl)
memcpy(args->req.payload, lpl, args->req.lpl_len);
- args->read_write_len_ext =
- ethtool_cmis_get_max_lpl_size(read_write_len_ext);
- }
if (epl) {
args->req.epl_len = cpu_to_be16(epl_len);
args->req.epl = epl;
- args->read_write_len_ext =
- ethtool_cmis_get_max_epl_size(read_write_len_ext);
}
args->max_duration = max_duration;
+ args->read_write_len_ext =
+ ethtool_cmis_get_max_lpl_size(read_write_len_ext);
args->msleep_pre_rpl = msleep_pre_rpl;
args->rpl_exp_len = rpl_exp_len;
args->flags = flags;
@@ -363,7 +351,7 @@ ethtool_cmis_module_poll(struct net_device *dev,
struct netlink_ext_ack extack = {};
int err;
- ethtool_cmis_page_init(&page_data, 0, offset, sizeof(rpl));
+ ethtool_cmis_page_init(&page_data, 0, offset, sizeof(*rpl));
page_data.data = (u8 *)rpl;
err = ops->get_module_eeprom_by_page(dev, &page_data, &extack);
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 0cb6da1..49bea6b4 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -830,6 +830,7 @@ void ethtool_ringparam_get_cfg(struct net_device *dev,
/* Driver gives us current state, we want to return current config */
kparam->tcp_data_split = dev->cfg->hds_config;
+ kparam->hds_thresh = dev->cfg->hds_thresh;
}
static void ethtool_init_tsinfo(struct kernel_ethtool_ts_info *info)
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 2216394..8262cc1 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -60,7 +60,7 @@ static struct devlink *netdev_to_devlink_get(struct net_device *dev)
u32 ethtool_op_get_link(struct net_device *dev)
{
/* Synchronize carrier state with link watch, see also rtnl_getlink() */
- linkwatch_sync_dev(dev);
+ __linkwatch_sync_dev(dev);
return netif_carrier_ok(dev) ? 1 : 0;
}
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index a163d40..977beea 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -500,7 +500,7 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info)
netdev_unlock_ops(req_info->dev);
rtnl_unlock();
if (ret < 0)
- goto err_cleanup;
+ goto err_dev;
ret = ops->reply_size(req_info, reply_data);
if (ret < 0)
goto err_cleanup;
@@ -560,7 +560,7 @@ static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev,
netdev_unlock_ops(dev);
rtnl_unlock();
if (ret < 0)
- goto out;
+ goto out_cancel;
ret = ethnl_fill_reply_header(skb, dev, ctx->ops->hdr_attr);
if (ret < 0)
goto out;
@@ -569,6 +569,7 @@ static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev,
out:
if (ctx->ops->cleanup_data)
ctx->ops->cleanup_data(ctx->reply_data);
+out_cancel:
ctx->reply_data->dev = NULL;
if (ret < 0)
genlmsg_cancel(skb, ehdr);
@@ -793,7 +794,7 @@ static void ethnl_default_notify(struct net_device *dev, unsigned int cmd,
ethnl_init_reply_data(reply_data, ops, dev);
ret = ops->prepare_data(req_info, reply_data, &info);
if (ret < 0)
- goto err_cleanup;
+ goto err_rep;
ret = ops->reply_size(req_info, reply_data);
if (ret < 0)
goto err_cleanup;
@@ -828,6 +829,7 @@ static void ethnl_default_notify(struct net_device *dev, unsigned int cmd,
err_cleanup:
if (ops->cleanup_data)
ops->cleanup_data(reply_data);
+err_rep:
kfree(reply_data);
kfree(req_info);
return;
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 439cfb7a..1b1b700 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -33,14 +33,14 @@ static void hsr_set_operstate(struct hsr_port *master, bool has_carrier)
struct net_device *dev = master->dev;
if (!is_admin_up(dev)) {
- netdev_set_operstate(dev, IF_OPER_DOWN);
+ netif_set_operstate(dev, IF_OPER_DOWN);
return;
}
if (has_carrier)
- netdev_set_operstate(dev, IF_OPER_UP);
+ netif_set_operstate(dev, IF_OPER_UP);
else
- netdev_set_operstate(dev, IF_OPER_LOWERLAYERDOWN);
+ netif_set_operstate(dev, IF_OPER_LOWERLAYERDOWN);
}
static bool hsr_check_carrier(struct hsr_port *master)
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 0e40768..f14a41e 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -120,47 +120,16 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
}
#ifdef CONFIG_INET_ESPINTCP
-struct esp_tcp_sk {
- struct sock *sk;
- struct rcu_head rcu;
-};
-
-static void esp_free_tcp_sk(struct rcu_head *head)
-{
- struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu);
-
- sock_put(esk->sk);
- kfree(esk);
-}
-
static struct sock *esp_find_tcp_sk(struct xfrm_state *x)
{
struct xfrm_encap_tmpl *encap = x->encap;
struct net *net = xs_net(x);
- struct esp_tcp_sk *esk;
__be16 sport, dport;
- struct sock *nsk;
struct sock *sk;
- sk = rcu_dereference(x->encap_sk);
- if (sk && sk->sk_state == TCP_ESTABLISHED)
- return sk;
-
spin_lock_bh(&x->lock);
sport = encap->encap_sport;
dport = encap->encap_dport;
- nsk = rcu_dereference_protected(x->encap_sk,
- lockdep_is_held(&x->lock));
- if (sk && sk == nsk) {
- esk = kmalloc(sizeof(*esk), GFP_ATOMIC);
- if (!esk) {
- spin_unlock_bh(&x->lock);
- return ERR_PTR(-ENOMEM);
- }
- RCU_INIT_POINTER(x->encap_sk, NULL);
- esk->sk = sk;
- call_rcu(&esk->rcu, esp_free_tcp_sk);
- }
spin_unlock_bh(&x->lock);
sk = inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, x->id.daddr.a4,
@@ -173,20 +142,6 @@ static struct sock *esp_find_tcp_sk(struct xfrm_state *x)
return ERR_PTR(-EINVAL);
}
- spin_lock_bh(&x->lock);
- nsk = rcu_dereference_protected(x->encap_sk,
- lockdep_is_held(&x->lock));
- if (encap->encap_sport != sport ||
- encap->encap_dport != dport) {
- sock_put(sk);
- sk = nsk ?: ERR_PTR(-EREMCHG);
- } else if (sk == nsk) {
- sock_put(sk);
- } else {
- rcu_assign_pointer(x->encap_sk, sk);
- }
- spin_unlock_bh(&x->lock);
-
return sk;
}
@@ -199,8 +154,10 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
sk = esp_find_tcp_sk(x);
err = PTR_ERR_OR_ZERO(sk);
- if (err)
+ if (err) {
+ kfree_skb(skb);
goto out;
+ }
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
@@ -209,6 +166,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
err = espintcp_push_skb(sk, skb);
bh_unlock_sock(sk);
+ sock_put(sk);
+
out:
rcu_read_unlock();
return err;
@@ -392,6 +351,8 @@ static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x,
if (IS_ERR(sk))
return ERR_CAST(sk);
+ sock_put(sk);
+
*lenp = htons(len);
esph = (struct ip_esp_hdr *)(lenp + 1);
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 934f777..d293087 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -439,7 +439,7 @@ static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb,
iif, sdif);
NAPI_GRO_CB(skb)->is_flist = !sk;
if (sk)
- sock_put(sk);
+ sock_gen_put(sk);
}
INDIRECT_CALLABLE_SCOPE
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 2c07255..9a8142c 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -247,6 +247,62 @@ static struct sk_buff *__udpv4_gso_segment_list_csum(struct sk_buff *segs)
return segs;
}
+static void __udpv6_gso_segment_csum(struct sk_buff *seg,
+ struct in6_addr *oldip,
+ const struct in6_addr *newip,
+ __be16 *oldport, __be16 newport)
+{
+ struct udphdr *uh = udp_hdr(seg);
+
+ if (ipv6_addr_equal(oldip, newip) && *oldport == newport)
+ return;
+
+ if (uh->check) {
+ inet_proto_csum_replace16(&uh->check, seg, oldip->s6_addr32,
+ newip->s6_addr32, true);
+
+ inet_proto_csum_replace2(&uh->check, seg, *oldport, newport,
+ false);
+ if (!uh->check)
+ uh->check = CSUM_MANGLED_0;
+ }
+
+ *oldip = *newip;
+ *oldport = newport;
+}
+
+static struct sk_buff *__udpv6_gso_segment_list_csum(struct sk_buff *segs)
+{
+ const struct ipv6hdr *iph;
+ const struct udphdr *uh;
+ struct ipv6hdr *iph2;
+ struct sk_buff *seg;
+ struct udphdr *uh2;
+
+ seg = segs;
+ uh = udp_hdr(seg);
+ iph = ipv6_hdr(seg);
+ uh2 = udp_hdr(seg->next);
+ iph2 = ipv6_hdr(seg->next);
+
+ if (!(*(const u32 *)&uh->source ^ *(const u32 *)&uh2->source) &&
+ ipv6_addr_equal(&iph->saddr, &iph2->saddr) &&
+ ipv6_addr_equal(&iph->daddr, &iph2->daddr))
+ return segs;
+
+ while ((seg = seg->next)) {
+ uh2 = udp_hdr(seg);
+ iph2 = ipv6_hdr(seg);
+
+ __udpv6_gso_segment_csum(seg, &iph2->saddr, &iph->saddr,
+ &uh2->source, uh->source);
+ __udpv6_gso_segment_csum(seg, &iph2->daddr, &iph->daddr,
+ &uh2->dest, uh->dest);
+ }
+
+ return segs;
+}
+
static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb,
netdev_features_t features,
bool is_ipv6)
@@ -259,7 +315,10 @@ static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb,
udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss);
- return is_ipv6 ? skb : __udpv4_gso_segment_list_csum(skb);
+ if (is_ipv6)
+ return __udpv6_gso_segment_list_csum(skb);
+ else
+ return __udpv4_gso_segment_list_csum(skb);
}
struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index b5b0632..0d31a8c 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -182,11 +182,15 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
int offset = skb_gro_offset(skb);
const struct net_offload *ops;
struct sk_buff *pp = NULL;
- int ret;
+ int len, dlen;
+ __u8 *udpdata;
+ __be32 *udpdata32;
- offset = offset - sizeof(struct udphdr);
-
- if (!pskb_pull(skb, offset))
+ len = skb->len - offset;
+ dlen = offset + min(len, 8);
+ udpdata = skb_gro_header(skb, dlen, offset);
+ udpdata32 = (__be32 *)udpdata;
+ if (unlikely(!udpdata))
return NULL;
rcu_read_lock();
@@ -194,11 +198,10 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
if (!ops || !ops->callbacks.gro_receive)
goto out;
- ret = __xfrm4_udp_encap_rcv(sk, skb, false);
- if (ret)
+ /* check if it is a keepalive or IKE packet */
+ if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0)
goto out;
- skb_push(skb, offset);
NAPI_GRO_CB(skb)->proto = IPPROTO_UDP;
pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
@@ -208,7 +211,6 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
out:
rcu_read_unlock();
- skb_push(skb, offset);
NAPI_GRO_CB(skb)->same_flow = 0;
NAPI_GRO_CB(skb)->flush = 1;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 2cffb8f..9ba83f0 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3154,12 +3154,13 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg)
rtnl_net_lock(net);
dev = __dev_get_by_index(net, ireq.ifr6_ifindex);
- netdev_lock_ops(dev);
- if (dev)
+ if (dev) {
+ netdev_lock_ops(dev);
err = inet6_addr_add(net, dev, &cfg, 0, 0, NULL);
- else
+ netdev_unlock_ops(dev);
+ } else {
err = -ENODEV;
- netdev_unlock_ops(dev);
+ }
rtnl_net_unlock(net);
return err;
}
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 9e73944..72adfc1 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -137,47 +137,16 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
}
#ifdef CONFIG_INET6_ESPINTCP
-struct esp_tcp_sk {
- struct sock *sk;
- struct rcu_head rcu;
-};
-
-static void esp_free_tcp_sk(struct rcu_head *head)
-{
- struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu);
-
- sock_put(esk->sk);
- kfree(esk);
-}
-
static struct sock *esp6_find_tcp_sk(struct xfrm_state *x)
{
struct xfrm_encap_tmpl *encap = x->encap;
struct net *net = xs_net(x);
- struct esp_tcp_sk *esk;
__be16 sport, dport;
- struct sock *nsk;
struct sock *sk;
- sk = rcu_dereference(x->encap_sk);
- if (sk && sk->sk_state == TCP_ESTABLISHED)
- return sk;
-
spin_lock_bh(&x->lock);
sport = encap->encap_sport;
dport = encap->encap_dport;
- nsk = rcu_dereference_protected(x->encap_sk,
- lockdep_is_held(&x->lock));
- if (sk && sk == nsk) {
- esk = kmalloc(sizeof(*esk), GFP_ATOMIC);
- if (!esk) {
- spin_unlock_bh(&x->lock);
- return ERR_PTR(-ENOMEM);
- }
- RCU_INIT_POINTER(x->encap_sk, NULL);
- esk->sk = sk;
- call_rcu(&esk->rcu, esp_free_tcp_sk);
- }
spin_unlock_bh(&x->lock);
sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, &x->id.daddr.in6,
@@ -190,20 +159,6 @@ static struct sock *esp6_find_tcp_sk(struct xfrm_state *x)
return ERR_PTR(-EINVAL);
}
- spin_lock_bh(&x->lock);
- nsk = rcu_dereference_protected(x->encap_sk,
- lockdep_is_held(&x->lock));
- if (encap->encap_sport != sport ||
- encap->encap_dport != dport) {
- sock_put(sk);
- sk = nsk ?: ERR_PTR(-EREMCHG);
- } else if (sk == nsk) {
- sock_put(sk);
- } else {
- rcu_assign_pointer(x->encap_sk, sk);
- }
- spin_unlock_bh(&x->lock);
-
return sk;
}
@@ -216,8 +171,10 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
sk = esp6_find_tcp_sk(x);
err = PTR_ERR_OR_ZERO(sk);
- if (err)
+ if (err) {
+ kfree_skb(skb);
goto out;
+ }
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
@@ -226,6 +183,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
err = espintcp_push_skb(sk, skb);
bh_unlock_sock(sk);
+ sock_put(sk);
+
out:
rcu_read_unlock();
return err;
@@ -422,6 +381,8 @@ static struct ip_esp_hdr *esp6_output_tcp_encap(struct xfrm_state *x,
if (IS_ERR(sk))
return ERR_CAST(sk);
+ sock_put(sk);
+
*lenp = htons(len);
esph = (struct ip_esp_hdr *)(lenp + 1);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ab12b81..96f1621 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -470,10 +470,10 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
goto out;
hash = fl6->mp_hash;
- if (hash <= atomic_read(&first->fib6_nh->fib_nh_upper_bound) &&
- rt6_score_route(first->fib6_nh, first->fib6_flags, oif,
- strict) >= 0) {
- match = first;
+ if (hash <= atomic_read(&first->fib6_nh->fib_nh_upper_bound)) {
+ if (rt6_score_route(first->fib6_nh, first->fib6_flags, oif,
+ strict) >= 0)
+ match = first;
goto out;
}
@@ -1771,6 +1771,7 @@ static int rt6_insert_exception(struct rt6_info *nrt,
if (!err) {
spin_lock_bh(&f6i->fib6_table->tb6_lock);
fib6_update_sernum(net, f6i);
+ fib6_add_gc_list(f6i);
spin_unlock_bh(&f6i->fib6_table->tb6_lock);
fib6_force_start_gc(net);
}
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index d9b11fe..a8a04f4 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -42,7 +42,7 @@ static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb,
iif, sdif);
NAPI_GRO_CB(skb)->is_flist = !sk;
if (sk)
- sock_put(sk);
+ sock_gen_put(sk);
#endif /* IS_ENABLED(CONFIG_IPV6) */
}
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 4abc5e9..841c81a 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -179,14 +179,18 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
int offset = skb_gro_offset(skb);
const struct net_offload *ops;
struct sk_buff *pp = NULL;
- int ret;
+ int len, dlen;
+ __u8 *udpdata;
+ __be32 *udpdata32;
if (skb->protocol == htons(ETH_P_IP))
return xfrm4_gro_udp_encap_rcv(sk, head, skb);
- offset = offset - sizeof(struct udphdr);
-
- if (!pskb_pull(skb, offset))
+ len = skb->len - offset;
+ dlen = offset + min(len, 8);
+ udpdata = skb_gro_header(skb, dlen, offset);
+ udpdata32 = (__be32 *)udpdata;
+ if (unlikely(!udpdata))
return NULL;
rcu_read_lock();
@@ -194,11 +198,10 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
if (!ops || !ops->callbacks.gro_receive)
goto out;
- ret = __xfrm6_udp_encap_rcv(sk, skb, false);
- if (ret)
+ /* check if it is a keepalive or IKE packet */
+ if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0)
goto out;
- skb_push(skb, offset);
NAPI_GRO_CB(skb)->proto = IPPROTO_UDP;
pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
@@ -208,7 +211,6 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
out:
rcu_read_unlock();
- skb_push(skb, offset);
NAPI_GRO_CB(skb)->same_flow = 0;
NAPI_GRO_CB(skb)->flush = 1;
diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c
index ca10916..5432a5f 100644
--- a/net/l3mdev/l3mdev.c
+++ b/net/l3mdev/l3mdev.c
@@ -277,8 +277,10 @@ void l3mdev_update_flow(struct net *net, struct flowi *fl)
if (fl->flowi_oif) {
dev = dev_get_by_index_rcu(net, fl->flowi_oif);
if (dev) {
- if (!fl->flowi_l3mdev)
+ if (!fl->flowi_l3mdev) {
fl->flowi_l3mdev = l3mdev_master_ifindex_rcu(dev);
+ fl->flowi_flags |= FLOWI_FLAG_L3MDEV_OIF;
+ }
/* oif set to L3mdev directs lookup to its table;
* reset to avoid oif match in fib_lookup
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index f0f4a25..969b3e2 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -659,6 +659,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
ieee80211_txq_remove_vlan(local, sdata);
+ if (sdata->vif.txq)
+ ieee80211_txq_purge(sdata->local, to_txq_info(sdata->vif.txq));
+
sdata->bss = NULL;
if (local->open_count == 0)
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index b17b3cc..a362254b 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -1085,7 +1085,13 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
ieee80211_report_used_skb(local, skb, false, status->ack_hwtstamp);
- if (status->free_list)
+ /*
+ * This is a bit racy but we can avoid a lot of work
+ * with this test...
+ */
+ if (local->tx_mntrs)
+ ieee80211_tx_monitor(local, skb, retry_count, status);
+ else if (status->free_list)
list_add_tail(&skb->list, status->free_list);
else
dev_kfree_skb(skb);
diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c
index dd89561..9b12ca9 100644
--- a/net/mctp/af_mctp.c
+++ b/net/mctp/af_mctp.c
@@ -630,6 +630,9 @@ static int mctp_sk_hash(struct sock *sk)
{
struct net *net = sock_net(sk);
+ /* Bind lookup runs under RCU, remain live during that. */
+ sock_set_flag(sk, SOCK_RCU_FREE);
+
mutex_lock(&net->mctp.bind_lock);
sk_add_node_rcu(sk, &net->mctp.binds);
mutex_unlock(&net->mctp.bind_lock);
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 2cb62f0..a715dcb 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -337,7 +337,11 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)
release_sock(sk);
- sock_kfree_s(sk, match, sizeof(*match));
+ kfree_rcu_mightsleep(match);
+ /* Adjust sk_omem_alloc like sock_kfree_s() does, to match
+ * with allocation of this memory by sock_kmemdup()
+ */
+ atomic_sub(sizeof(*match), &sk->sk_omem_alloc);
err = 0;
out:
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 409bd41..24c2de1 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -899,13 +899,17 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
goto dispose_child;
}
- if (!subflow_hmac_valid(req, &mp_opt) ||
- !mptcp_can_accept_new_subflow(subflow_req->msk)) {
+ if (!subflow_hmac_valid(req, &mp_opt)) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
goto dispose_child;
}
+ if (!mptcp_can_accept_new_subflow(owner)) {
+ subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
+ goto dispose_child;
+ }
+
/* move the msk reference ownership to the subflow */
subflow_req->msk = NULL;
ctx->conn = (struct sock *)owner;
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index df2dc21..047ba81 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -212,7 +212,7 @@
bool 'SCTP protocol connection tracking support'
depends on NETFILTER_ADVANCED
default y
- select LIBCRC32C
+ select CRC32
help
With this option enabled, the layer 3 independent connection
tracking code will be able to do state tracking on SCTP connections.
@@ -475,7 +475,7 @@
config NF_TABLES
select NETFILTER_NETLINK
- select LIBCRC32C
+ select CRC32
tristate "Netfilter nf_tables support"
help
nftables is the new packet classification framework that intends to
diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index 2a3017b..8c5b1fe 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -105,7 +105,7 @@
config IP_VS_PROTO_SCTP
bool "SCTP load balancing support"
- select LIBCRC32C
+ select CRC32
help
This option enables support for load balancing SCTP transport
protocol. Say Y if unsure.
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 9d83615..9441ac3 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -383,8 +383,8 @@ static void flow_offload_del(struct nf_flowtable *flow_table,
void flow_offload_teardown(struct flow_offload *flow)
{
clear_bit(IPS_OFFLOAD_BIT, &flow->ct->status);
- set_bit(NF_FLOW_TEARDOWN, &flow->flags);
- flow_offload_fixup_ct(flow);
+ if (!test_and_set_bit(NF_FLOW_TEARDOWN, &flow->flags))
+ flow_offload_fixup_ct(flow);
}
EXPORT_SYMBOL_GPL(flow_offload_teardown);
@@ -558,10 +558,12 @@ static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table,
if (nf_flow_has_expired(flow) ||
nf_ct_is_dying(flow->ct) ||
- nf_flow_custom_gc(flow_table, flow))
+ nf_flow_custom_gc(flow_table, flow)) {
flow_offload_teardown(flow);
- else if (!teardown)
+ teardown = true;
+ } else if (!teardown) {
nf_flow_table_extend_ct_timeout(flow->ct);
+ }
if (teardown) {
if (test_bit(NF_FLOW_HW, &flow->flags)) {
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index b8d3c32..c15db28 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -994,8 +994,9 @@ static int nft_pipapo_avx2_lookup_8b_16(unsigned long *map, unsigned long *fill,
NFT_PIPAPO_AVX2_BUCKET_LOAD8(5, lt, 8, pkt[8], bsize);
NFT_PIPAPO_AVX2_AND(6, 2, 3);
+ NFT_PIPAPO_AVX2_AND(3, 4, 7);
NFT_PIPAPO_AVX2_BUCKET_LOAD8(7, lt, 9, pkt[9], bsize);
- NFT_PIPAPO_AVX2_AND(0, 4, 5);
+ NFT_PIPAPO_AVX2_AND(0, 3, 5);
NFT_PIPAPO_AVX2_BUCKET_LOAD8(1, lt, 10, pkt[10], bsize);
NFT_PIPAPO_AVX2_AND(2, 6, 7);
NFT_PIPAPO_AVX2_BUCKET_LOAD8(3, lt, 11, pkt[11], bsize);
diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig
index 2535f3f..5481bd56 100644
--- a/net/openvswitch/Kconfig
+++ b/net/openvswitch/Kconfig
@@ -11,7 +11,7 @@
(!NF_NAT || NF_NAT) && \
(!NETFILTER_CONNCOUNT || NETFILTER_CONNCOUNT)))
depends on PSAMPLE || !PSAMPLE
- select LIBCRC32C
+ select CRC32
select MPLS
select NET_MPLS_GSO
select DST_CACHE
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 95e0dd1..518be23 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2876,7 +2876,8 @@ static int validate_set(const struct nlattr *a,
size_t key_len;
/* There can be only one key in a action */
- if (nla_total_size(nla_len(ovs_key)) != nla_len(a))
+ if (!nla_ok(ovs_key, nla_len(a)) ||
+ nla_total_size(nla_len(ovs_key)) != nla_len(a))
return -EINVAL;
key_len = nla_len(ovs_key);
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 8180d0c..a800127 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -784,7 +784,7 @@
config NET_ACT_CSUM
tristate "Checksum Updating"
depends on NET_CLS_ACT && INET
- select LIBCRC32C
+ select CRC32
help
Say Y here to update some common checksum after some direct
packet alterations.
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 4f648af..ecec0a1 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2057,6 +2057,7 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb,
struct tcmsg *tcm;
struct nlmsghdr *nlh;
unsigned char *b = skb_tail_pointer(skb);
+ int ret = -EMSGSIZE;
nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
if (!nlh)
@@ -2101,11 +2102,45 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb,
return skb->len;
+cls_op_not_supp:
+ ret = -EOPNOTSUPP;
out_nlmsg_trim:
nla_put_failure:
-cls_op_not_supp:
nlmsg_trim(skb, b);
- return -1;
+ return ret;
+}
+
+static struct sk_buff *tfilter_notify_prep(struct net *net,
+ struct sk_buff *oskb,
+ struct nlmsghdr *n,
+ struct tcf_proto *tp,
+ struct tcf_block *block,
+ struct Qdisc *q, u32 parent,
+ void *fh, int event,
+ u32 portid, bool rtnl_held,
+ struct netlink_ext_ack *extack)
+{
+ unsigned int size = oskb ? max(NLMSG_GOODSIZE, oskb->len) : NLMSG_GOODSIZE;
+ struct sk_buff *skb;
+ int ret;
+
+retry:
+ skb = alloc_skb(size, GFP_KERNEL);
+ if (!skb)
+ return ERR_PTR(-ENOBUFS);
+
+ ret = tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
+ n->nlmsg_seq, n->nlmsg_flags, event, false,
+ rtnl_held, extack);
+ if (ret <= 0) {
+ kfree_skb(skb);
+ if (ret == -EMSGSIZE) {
+ size += NLMSG_GOODSIZE;
+ goto retry;
+ }
+ return ERR_PTR(-EINVAL);
+ }
+ return skb;
}
static int tfilter_notify(struct net *net, struct sk_buff *oskb,
@@ -2121,16 +2156,10 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb,
if (!unicast && !rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC))
return 0;
- skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
- if (!skb)
- return -ENOBUFS;
-
- if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
- n->nlmsg_seq, n->nlmsg_flags, event,
- false, rtnl_held, extack) <= 0) {
- kfree_skb(skb);
- return -EINVAL;
- }
+ skb = tfilter_notify_prep(net, oskb, n, tp, block, q, parent, fh, event,
+ portid, rtnl_held, extack);
+ if (IS_ERR(skb))
+ return PTR_ERR(skb);
if (unicast)
err = rtnl_unicast(skb, net, portid);
@@ -2153,16 +2182,11 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC))
return tp->ops->delete(tp, fh, last, rtnl_held, extack);
- skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
- if (!skb)
- return -ENOBUFS;
-
- if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
- n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER,
- false, rtnl_held, extack) <= 0) {
+ skb = tfilter_notify_prep(net, oskb, n, tp, block, q, parent, fh,
+ RTM_DELTFILTER, portid, rtnl_held, extack);
+ if (IS_ERR(skb)) {
NL_SET_ERR_MSG(extack, "Failed to build del event notification");
- kfree_skb(skb);
- return -EINVAL;
+ return PTR_ERR(skb);
}
err = tp->ops->delete(tp, fh, last, rtnl_held, extack);
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 81189d0..12dd711 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -65,10 +65,7 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
&q->stats, qdisc_pkt_len, codel_get_enqueue_time,
drop_func, dequeue_func);
- /* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
- * or HTB crashes. Defer it for next round.
- */
- if (q->stats.drop_count && sch->q.qlen) {
+ if (q->stats.drop_count) {
qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len);
q->stats.drop_count = 0;
q->stats.drop_len = 0;
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index c69b999..9b6d79b 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -35,6 +35,11 @@ struct drr_sched {
struct Qdisc_class_hash clhash;
};
+static bool cl_is_active(struct drr_class *cl)
+{
+ return !list_empty(&cl->alist);
+}
+
static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid)
{
struct drr_sched *q = qdisc_priv(sch);
@@ -105,6 +110,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
return -ENOBUFS;
gnet_stats_basic_sync_init(&cl->bstats);
+ INIT_LIST_HEAD(&cl->alist);
cl->common.classid = classid;
cl->quantum = quantum;
cl->qdisc = qdisc_create_dflt(sch->dev_queue,
@@ -229,7 +235,7 @@ static void drr_qlen_notify(struct Qdisc *csh, unsigned long arg)
{
struct drr_class *cl = (struct drr_class *)arg;
- list_del(&cl->alist);
+ list_del_init(&cl->alist);
}
static int drr_dump_class(struct Qdisc *sch, unsigned long arg,
@@ -336,7 +342,6 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl;
int err = 0;
- bool first;
cl = drr_classify(skb, sch, &err);
if (cl == NULL) {
@@ -346,7 +351,6 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
return err;
}
- first = !cl->qdisc->q.qlen;
err = qdisc_enqueue(skb, cl->qdisc, to_free);
if (unlikely(err != NET_XMIT_SUCCESS)) {
if (net_xmit_drop_count(err)) {
@@ -356,7 +360,7 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
return err;
}
- if (first) {
+ if (!cl_is_active(cl)) {
list_add_tail(&cl->alist, &q->active);
cl->deficit = cl->quantum;
}
@@ -390,7 +394,7 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch)
if (unlikely(skb == NULL))
goto out;
if (cl->qdisc->q.qlen == 0)
- list_del(&cl->alist);
+ list_del_init(&cl->alist);
bstats_update(&cl->bstats, skb);
qdisc_bstats_update(sch, skb);
@@ -431,7 +435,7 @@ static void drr_reset_qdisc(struct Qdisc *sch)
for (i = 0; i < q->clhash.hashsize; i++) {
hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) {
if (cl->qdisc->q.qlen)
- list_del(&cl->alist);
+ list_del_init(&cl->alist);
qdisc_reset(cl->qdisc);
}
}
diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index 516038a..2c069f0 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -74,6 +74,11 @@ static const struct nla_policy ets_class_policy[TCA_ETS_MAX + 1] = {
[TCA_ETS_QUANTA_BAND] = { .type = NLA_U32 },
};
+static bool cl_is_active(struct ets_class *cl)
+{
+ return !list_empty(&cl->alist);
+}
+
static int ets_quantum_parse(struct Qdisc *sch, const struct nlattr *attr,
unsigned int *quantum,
struct netlink_ext_ack *extack)
@@ -293,7 +298,7 @@ static void ets_class_qlen_notify(struct Qdisc *sch, unsigned long arg)
* to remove them.
*/
if (!ets_class_is_strict(q, cl) && sch->q.qlen)
- list_del(&cl->alist);
+ list_del_init(&cl->alist);
}
static int ets_class_dump(struct Qdisc *sch, unsigned long arg,
@@ -416,7 +421,6 @@ static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct ets_sched *q = qdisc_priv(sch);
struct ets_class *cl;
int err = 0;
- bool first;
cl = ets_classify(skb, sch, &err);
if (!cl) {
@@ -426,7 +430,6 @@ static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
return err;
}
- first = !cl->qdisc->q.qlen;
err = qdisc_enqueue(skb, cl->qdisc, to_free);
if (unlikely(err != NET_XMIT_SUCCESS)) {
if (net_xmit_drop_count(err)) {
@@ -436,7 +439,7 @@ static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
return err;
}
- if (first && !ets_class_is_strict(q, cl)) {
+ if (!cl_is_active(cl) && !ets_class_is_strict(q, cl)) {
list_add_tail(&cl->alist, &q->active);
cl->deficit = cl->quantum;
}
@@ -488,7 +491,7 @@ static struct sk_buff *ets_qdisc_dequeue(struct Qdisc *sch)
if (unlikely(!skb))
goto out;
if (cl->qdisc->q.qlen == 0)
- list_del(&cl->alist);
+ list_del_init(&cl->alist);
return ets_qdisc_dequeue_skb(sch, skb);
}
@@ -657,7 +660,7 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt,
}
for (i = q->nbands; i < oldbands; i++) {
if (i >= q->nstrict && q->classes[i].qdisc->q.qlen)
- list_del(&q->classes[i].alist);
+ list_del_init(&q->classes[i].alist);
qdisc_tree_flush_backlog(q->classes[i].qdisc);
}
WRITE_ONCE(q->nstrict, nstrict);
@@ -713,7 +716,7 @@ static void ets_qdisc_reset(struct Qdisc *sch)
for (band = q->nstrict; band < q->nbands; band++) {
if (q->classes[band].qdisc->q.qlen)
- list_del(&q->classes[band].alist);
+ list_del_init(&q->classes[band].alist);
}
for (band = 0; band < q->nbands; band++)
qdisc_reset(q->classes[band].qdisc);
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 799f539..6c9029f 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -315,10 +315,8 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
}
qdisc_bstats_update(sch, skb);
flow->deficit -= qdisc_pkt_len(skb);
- /* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
- * or HTB crashes. Defer it for next round.
- */
- if (q->cstats.drop_count && sch->q.qlen) {
+
+ if (q->cstats.drop_count) {
qdisc_tree_reduce_backlog(sch, q->cstats.drop_count,
q->cstats.drop_len);
q->cstats.drop_count = 0;
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index c287bf8..cb8c525 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -203,7 +203,10 @@ eltree_insert(struct hfsc_class *cl)
static inline void
eltree_remove(struct hfsc_class *cl)
{
- rb_erase(&cl->el_node, &cl->sched->eligible);
+ if (!RB_EMPTY_NODE(&cl->el_node)) {
+ rb_erase(&cl->el_node, &cl->sched->eligible);
+ RB_CLEAR_NODE(&cl->el_node);
+ }
}
static inline void
@@ -958,6 +961,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
if (cl != NULL) {
int old_flags;
+ int len = 0;
if (parentid) {
if (cl->cl_parent &&
@@ -988,9 +992,13 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
if (usc != NULL)
hfsc_change_usc(cl, usc, cur_time);
+ if (cl->qdisc->q.qlen != 0)
+ len = qdisc_peek_len(cl->qdisc);
+ /* Check queue length again since some qdisc implementations
+ * (e.g., netem/codel) might empty the queue during the peek
+ * operation.
+ */
if (cl->qdisc->q.qlen != 0) {
- int len = qdisc_peek_len(cl->qdisc);
-
if (cl->cl_flags & HFSC_RSC) {
if (old_flags & HFSC_RSC)
update_ed(cl, len);
@@ -1220,7 +1228,8 @@ hfsc_qlen_notify(struct Qdisc *sch, unsigned long arg)
/* vttree is now handled in update_vf() so that update_vf(cl, 0, 0)
* needs to be called explicitly to remove a class from vttree.
*/
- update_vf(cl, 0, 0);
+ if (cl->cl_nactive)
+ update_vf(cl, 0, 0);
if (cl->cl_flags & HFSC_RSC)
eltree_remove(cl);
}
@@ -1560,7 +1569,7 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
return err;
}
- if (first) {
+ if (first && !cl->cl_nactive) {
if (cl->cl_flags & HFSC_RSC)
init_ed(cl, len);
if (cl->cl_flags & HFSC_FSC)
@@ -1632,10 +1641,16 @@ hfsc_dequeue(struct Qdisc *sch)
if (cl->qdisc->q.qlen != 0) {
/* update ed */
next_len = qdisc_peek_len(cl->qdisc);
- if (realtime)
- update_ed(cl, next_len);
- else
- update_d(cl, next_len);
+ /* Check queue length again since some qdisc implementations
+ * (e.g., netem/codel) might empty the queue during the peek
+ * operation.
+ */
+ if (cl->qdisc->q.qlen != 0) {
+ if (realtime)
+ update_ed(cl, next_len);
+ else
+ update_d(cl, next_len);
+ }
} else {
/* the class becomes passive */
eltree_remove(cl);
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index c31bc54..4b9a639 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1485,6 +1485,8 @@ static void htb_qlen_notify(struct Qdisc *sch, unsigned long arg)
{
struct htb_class *cl = (struct htb_class *)arg;
+ if (!cl->prio_activity)
+ return;
htb_deactivate(qdisc_priv(sch), cl);
}
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 2cfbc97..bf1282c 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -202,6 +202,11 @@ struct qfq_sched {
*/
enum update_reason {enqueue, requeue};
+static bool cl_is_active(struct qfq_class *cl)
+{
+ return !list_empty(&cl->alist);
+}
+
static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid)
{
struct qfq_sched *q = qdisc_priv(sch);
@@ -347,7 +352,7 @@ static void qfq_deactivate_class(struct qfq_sched *q, struct qfq_class *cl)
struct qfq_aggregate *agg = cl->agg;
- list_del(&cl->alist); /* remove from RR queue of the aggregate */
+ list_del_init(&cl->alist); /* remove from RR queue of the aggregate */
if (list_empty(&agg->active)) /* agg is now inactive */
qfq_deactivate_agg(q, agg);
}
@@ -474,6 +479,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
gnet_stats_basic_sync_init(&cl->bstats);
cl->common.classid = classid;
cl->deficit = lmax;
+ INIT_LIST_HEAD(&cl->alist);
cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
classid, NULL);
@@ -982,7 +988,7 @@ static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg,
cl->deficit -= (int) len;
if (cl->qdisc->q.qlen == 0) /* no more packets, remove from list */
- list_del(&cl->alist);
+ list_del_init(&cl->alist);
else if (cl->deficit < qdisc_pkt_len(cl->qdisc->ops->peek(cl->qdisc))) {
cl->deficit += agg->lmax;
list_move_tail(&cl->alist, &agg->active);
@@ -1214,7 +1220,6 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct qfq_class *cl;
struct qfq_aggregate *agg;
int err = 0;
- bool first;
cl = qfq_classify(skb, sch, &err);
if (cl == NULL) {
@@ -1236,7 +1241,6 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
}
gso_segs = skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1;
- first = !cl->qdisc->q.qlen;
err = qdisc_enqueue(skb, cl->qdisc, to_free);
if (unlikely(err != NET_XMIT_SUCCESS)) {
pr_debug("qfq_enqueue: enqueue failed %d\n", err);
@@ -1252,8 +1256,8 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
++sch->q.qlen;
agg = cl->agg;
- /* if the queue was not empty, then done here */
- if (!first) {
+ /* if the class is active, then done here */
+ if (cl_is_active(cl)) {
if (unlikely(skb == cl->qdisc->ops->peek(cl->qdisc)) &&
list_first_entry(&agg->active, struct qfq_class, alist)
== cl && cl->deficit < len)
@@ -1415,6 +1419,8 @@ static void qfq_qlen_notify(struct Qdisc *sch, unsigned long arg)
struct qfq_sched *q = qdisc_priv(sch);
struct qfq_class *cl = (struct qfq_class *)arg;
+ if (list_empty(&cl->alist))
+ return;
qfq_deactivate_class(q, cl);
}
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 9ed197e..b912ad9 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -631,6 +631,15 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt,
struct red_parms *p = NULL;
struct sk_buff *to_free = NULL;
struct sk_buff *tail = NULL;
+ unsigned int maxflows;
+ unsigned int quantum;
+ unsigned int divisor;
+ int perturb_period;
+ u8 headdrop;
+ u8 maxdepth;
+ int limit;
+ u8 flags;
+
if (opt->nla_len < nla_attr_size(sizeof(*ctl)))
return -EINVAL;
@@ -652,39 +661,64 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt,
if (!p)
return -ENOMEM;
}
- if (ctl->limit == 1) {
- NL_SET_ERR_MSG_MOD(extack, "invalid limit");
- return -EINVAL;
- }
+
sch_tree_lock(sch);
+
+ limit = q->limit;
+ divisor = q->divisor;
+ headdrop = q->headdrop;
+ maxdepth = q->maxdepth;
+ maxflows = q->maxflows;
+ perturb_period = q->perturb_period;
+ quantum = q->quantum;
+ flags = q->flags;
+
+ /* update and validate configuration */
if (ctl->quantum)
- q->quantum = ctl->quantum;
- WRITE_ONCE(q->perturb_period, ctl->perturb_period * HZ);
+ quantum = ctl->quantum;
+ perturb_period = ctl->perturb_period * HZ;
if (ctl->flows)
- q->maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS);
+ maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS);
if (ctl->divisor) {
- q->divisor = ctl->divisor;
- q->maxflows = min_t(u32, q->maxflows, q->divisor);
+ divisor = ctl->divisor;
+ maxflows = min_t(u32, maxflows, divisor);
}
if (ctl_v1) {
if (ctl_v1->depth)
- q->maxdepth = min_t(u32, ctl_v1->depth, SFQ_MAX_DEPTH);
+ maxdepth = min_t(u32, ctl_v1->depth, SFQ_MAX_DEPTH);
if (p) {
- swap(q->red_parms, p);
- red_set_parms(q->red_parms,
+ red_set_parms(p,
ctl_v1->qth_min, ctl_v1->qth_max,
ctl_v1->Wlog,
ctl_v1->Plog, ctl_v1->Scell_log,
NULL,
ctl_v1->max_P);
}
- q->flags = ctl_v1->flags;
- q->headdrop = ctl_v1->headdrop;
+ flags = ctl_v1->flags;
+ headdrop = ctl_v1->headdrop;
}
if (ctl->limit) {
- q->limit = min_t(u32, ctl->limit, q->maxdepth * q->maxflows);
- q->maxflows = min_t(u32, q->maxflows, q->limit);
+ limit = min_t(u32, ctl->limit, maxdepth * maxflows);
+ maxflows = min_t(u32, maxflows, limit);
}
+ if (limit == 1) {
+ sch_tree_unlock(sch);
+ kfree(p);
+ NL_SET_ERR_MSG_MOD(extack, "invalid limit");
+ return -EINVAL;
+ }
+
+ /* commit configuration */
+ q->limit = limit;
+ q->divisor = divisor;
+ q->headdrop = headdrop;
+ q->maxdepth = maxdepth;
+ q->maxflows = maxflows;
+ WRITE_ONCE(q->perturb_period, perturb_period);
+ q->quantum = quantum;
+ q->flags = flags;
+ if (p)
+ swap(q->red_parms, p);
qlen = sch->q.qlen;
while (sch->q.qlen > q->limit) {
diff --git a/net/sctp/Kconfig b/net/sctp/Kconfig
index 5da599f..d18a72d 100644
--- a/net/sctp/Kconfig
+++ b/net/sctp/Kconfig
@@ -7,10 +7,10 @@
tristate "The SCTP Protocol"
depends on INET
depends on IPV6 || IPV6=n
+ select CRC32
select CRYPTO
select CRYPTO_HMAC
select CRYPTO_SHA1
- select LIBCRC32C
select NET_UDP_TUNNEL
help
Stream Control Transmission Protocol
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 36ee34f..53725ee 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -72,8 +72,9 @@
/* Forward declarations for internal helper functions. */
static bool sctp_writeable(const struct sock *sk);
static void sctp_wfree(struct sk_buff *skb);
-static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
- size_t msg_len);
+static int sctp_wait_for_sndbuf(struct sctp_association *asoc,
+ struct sctp_transport *transport,
+ long *timeo_p, size_t msg_len);
static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p);
static int sctp_wait_for_connect(struct sctp_association *, long *timeo_p);
static int sctp_wait_for_accept(struct sock *sk, long timeo);
@@ -1828,7 +1829,7 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc,
if (sctp_wspace(asoc) <= 0 || !sk_wmem_schedule(sk, msg_len)) {
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
- err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len);
+ err = sctp_wait_for_sndbuf(asoc, transport, &timeo, msg_len);
if (err)
goto err;
if (unlikely(sinfo->sinfo_stream >= asoc->stream.outcnt)) {
@@ -9214,8 +9215,9 @@ void sctp_sock_rfree(struct sk_buff *skb)
/* Helper function to wait for space in the sndbuf. */
-static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
- size_t msg_len)
+static int sctp_wait_for_sndbuf(struct sctp_association *asoc,
+ struct sctp_transport *transport,
+ long *timeo_p, size_t msg_len)
{
struct sock *sk = asoc->base.sk;
long current_timeo = *timeo_p;
@@ -9225,7 +9227,9 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
pr_debug("%s: asoc:%p, timeo:%ld, msg_len:%zu\n", __func__, asoc,
*timeo_p, msg_len);
- /* Increment the association's refcnt. */
+ /* Increment the transport and association's refcnt. */
+ if (transport)
+ sctp_transport_hold(transport);
sctp_association_hold(asoc);
/* Wait on the association specific sndbuf space. */
@@ -9234,7 +9238,7 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
TASK_INTERRUPTIBLE);
if (asoc->base.dead)
goto do_dead;
- if (!*timeo_p)
+ if ((!*timeo_p) || (transport && transport->dead))
goto do_nonblock;
if (sk->sk_err || asoc->state >= SCTP_STATE_SHUTDOWN_PENDING)
goto do_error;
@@ -9259,7 +9263,9 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
out:
finish_wait(&asoc->wait, &wait);
- /* Release the association's refcnt. */
+ /* Release the transport and association's refcnt. */
+ if (transport)
+ sctp_transport_put(transport);
sctp_association_put(asoc);
return err;
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 59675f6..6946c14 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -117,6 +117,8 @@ struct sctp_transport *sctp_transport_new(struct net *net,
*/
void sctp_transport_free(struct sctp_transport *transport)
{
+ transport->dead = 1;
+
/* Try to delete the heartbeat timer. */
if (timer_delete(&transport->hb_timer))
sctp_transport_put(transport);
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 3e6cb35..3760131 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -362,6 +362,9 @@ static void smc_destruct(struct sock *sk)
return;
}
+static struct lock_class_key smc_key;
+static struct lock_class_key smc_slock_key;
+
void smc_sk_init(struct net *net, struct sock *sk, int protocol)
{
struct smc_sock *smc = smc_sk(sk);
@@ -375,6 +378,8 @@ void smc_sk_init(struct net *net, struct sock *sk, int protocol)
INIT_WORK(&smc->connect_work, smc_connect_work);
INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
INIT_LIST_HEAD(&smc->accept_q);
+ sock_lock_init_class_and_name(sk, "slock-AF_SMC", &smc_slock_key,
+ "sk_lock-AF_SMC", &smc_key);
spin_lock_init(&smc->accept_q_lock);
spin_lock_init(&smc->conn.send_lock);
sk->sk_prot->hash(sk);
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 004cdb59..7ce5e28 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1536,13 +1536,9 @@ static ssize_t write_flush(struct file *file, const char __user *buf,
* or by one second if it has already reached the current time.
* Newly added cache entries will always have ->last_refresh greater
* that ->flush_time, so they don't get flushed prematurely.
- *
- * If someone frequently calls the flush interface, we should
- * immediately clean the corresponding cache_detail instead of
- * continuously accumulating nextcheck.
*/
- if (cd->flush_time >= now && cd->flush_time < (now + 5))
+ if (cd->flush_time >= now)
now = cd->flush_time + 1;
cd->flush_time = now;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 50c2e08..18be6ff 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1046,6 +1046,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
if (unlikely(l->backlog[imp].len >= l->backlog[imp].limit)) {
if (imp == TIPC_SYSTEM_IMPORTANCE) {
pr_warn("%s<%s>, link overflow", link_rst_msg, l->name);
+ __skb_queue_purge(list);
return -ENOBUFS;
}
rc = link_schedule_user(l, hdr);
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
index e2f1962..b45c5b9 100644
--- a/net/tipc/monitor.c
+++ b/net/tipc/monitor.c
@@ -716,7 +716,8 @@ void tipc_mon_reinit_self(struct net *net)
if (!mon)
continue;
write_lock_bh(&mon->lock);
- mon->self->addr = tipc_own_addr(net);
+ if (mon->self)
+ mon->self->addr = tipc_own_addr(net);
write_unlock_bh(&mon->lock);
}
}
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index cb86b0b..a3ccb313 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -852,6 +852,11 @@ static int tls_setsockopt(struct sock *sk, int level, int optname,
return do_tls_setsockopt(sk, optname, optval, optlen);
}
+static int tls_disconnect(struct sock *sk, int flags)
+{
+ return -EOPNOTSUPP;
+}
+
struct tls_context *tls_ctx_create(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
@@ -947,6 +952,7 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG],
prot[TLS_BASE][TLS_BASE] = *base;
prot[TLS_BASE][TLS_BASE].setsockopt = tls_setsockopt;
prot[TLS_BASE][TLS_BASE].getsockopt = tls_getsockopt;
+ prot[TLS_BASE][TLS_BASE].disconnect = tls_disconnect;
prot[TLS_BASE][TLS_BASE].close = tls_sk_proto_close;
prot[TLS_SW][TLS_BASE] = prot[TLS_BASE][TLS_BASE];
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 5696af4..4abc81f 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -338,13 +338,14 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
u32 len = xdp_get_buff_len(xdp);
int err;
- spin_lock_bh(&xs->rx_lock);
err = xsk_rcv_check(xs, xdp, len);
if (!err) {
+ spin_lock_bh(&xs->pool->rx_lock);
err = __xsk_rcv(xs, xdp, len);
xsk_flush(xs);
+ spin_unlock_bh(&xs->pool->rx_lock);
}
- spin_unlock_bh(&xs->rx_lock);
+
return err;
}
@@ -1734,7 +1735,6 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
xs = xdp_sk(sk);
xs->state = XSK_READY;
mutex_init(&xs->mutex);
- spin_lock_init(&xs->rx_lock);
INIT_LIST_HEAD(&xs->map_list);
spin_lock_init(&xs->map_list_lock);
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 25a76c5..c5181a9 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -89,6 +89,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
pool->addrs = umem->addrs;
pool->tx_metadata_len = umem->tx_metadata_len;
pool->tx_sw_csum = umem->flags & XDP_UMEM_TX_SW_CSUM;
+ spin_lock_init(&pool->rx_lock);
INIT_LIST_HEAD(&pool->free_list);
INIT_LIST_HEAD(&pool->xskb_list);
INIT_LIST_HEAD(&pool->xsk_tx_list);
diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
index fe82e2d..fc7a603 100644
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -171,8 +171,10 @@ int espintcp_queue_out(struct sock *sk, struct sk_buff *skb)
struct espintcp_ctx *ctx = espintcp_getctx(sk);
if (skb_queue_len(&ctx->out_queue) >=
- READ_ONCE(net_hotdata.max_backlog))
+ READ_ONCE(net_hotdata.max_backlog)) {
+ kfree_skb(skb);
return -ENOBUFS;
+ }
__skb_queue_tail(&ctx->out_queue, skb);
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 341d79e..2f57dab 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -838,9 +838,6 @@ int __xfrm_state_delete(struct xfrm_state *x)
xfrm_nat_keepalive_state_updated(x);
spin_unlock(&net->xfrm.xfrm_state_lock);
- if (x->encap_sk)
- sock_put(rcu_dereference_raw(x->encap_sk));
-
xfrm_dev_state_delete(x);
/* All xfrm_state objects are created by xfrm_state_alloc.
diff --git a/rust/Makefile b/rust/Makefile
index fa0eea8..3aca903 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -368,7 +368,7 @@
$(obj)/bindings/bindings_helpers_generated.rs: $(src)/helpers/helpers.c FORCE
$(call if_changed_dep,bindgen)
-rust_exports = $(NM) -p --defined-only $(1) | awk '$$2~/(T|R|D|B)/ && $$3!~/__cfi/ && $$3!~/__odr_asan/ { printf $(2),$$3 }'
+rust_exports = $(NM) -p --defined-only $(1) | awk '$$2~/(T|R|D|B)/ && $$3!~/__(pfx|cfi|odr_asan)/ { printf $(2),$$3 }'
quiet_cmd_exports = EXPORTS $@
cmd_exports = \
diff --git a/rust/helpers/dma.c b/rust/helpers/dma.c
new file mode 100644
index 0000000..df8b8a7
--- /dev/null
+++ b/rust/helpers/dma.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/dma-mapping.h>
+
+void *rust_helper_dma_alloc_attrs(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flag,
+ unsigned long attrs)
+{
+ return dma_alloc_attrs(dev, size, dma_handle, flag, attrs);
+}
+
+void rust_helper_dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
+ dma_addr_t dma_handle, unsigned long attrs)
+{
+ dma_free_attrs(dev, size, cpu_addr, dma_handle, attrs);
+}
diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c
index e1c21eb..1e7c84df 100644
--- a/rust/helpers/helpers.c
+++ b/rust/helpers/helpers.c
@@ -14,6 +14,7 @@
#include "cpumask.c"
#include "cred.c"
#include "device.c"
+#include "dma.c"
#include "err.c"
#include "fs.c"
#include "io.c"
diff --git a/rust/helpers/io.c b/rust/helpers/io.c
index 4c2401c..15ea187 100644
--- a/rust/helpers/io.c
+++ b/rust/helpers/io.c
@@ -7,94 +7,94 @@ void __iomem *rust_helper_ioremap(phys_addr_t offset, size_t size)
return ioremap(offset, size);
}
-void rust_helper_iounmap(volatile void __iomem *addr)
+void rust_helper_iounmap(void __iomem *addr)
{
iounmap(addr);
}
-u8 rust_helper_readb(const volatile void __iomem *addr)
+u8 rust_helper_readb(const void __iomem *addr)
{
return readb(addr);
}
-u16 rust_helper_readw(const volatile void __iomem *addr)
+u16 rust_helper_readw(const void __iomem *addr)
{
return readw(addr);
}
-u32 rust_helper_readl(const volatile void __iomem *addr)
+u32 rust_helper_readl(const void __iomem *addr)
{
return readl(addr);
}
#ifdef CONFIG_64BIT
-u64 rust_helper_readq(const volatile void __iomem *addr)
+u64 rust_helper_readq(const void __iomem *addr)
{
return readq(addr);
}
#endif
-void rust_helper_writeb(u8 value, volatile void __iomem *addr)
+void rust_helper_writeb(u8 value, void __iomem *addr)
{
writeb(value, addr);
}
-void rust_helper_writew(u16 value, volatile void __iomem *addr)
+void rust_helper_writew(u16 value, void __iomem *addr)
{
writew(value, addr);
}
-void rust_helper_writel(u32 value, volatile void __iomem *addr)
+void rust_helper_writel(u32 value, void __iomem *addr)
{
writel(value, addr);
}
#ifdef CONFIG_64BIT
-void rust_helper_writeq(u64 value, volatile void __iomem *addr)
+void rust_helper_writeq(u64 value, void __iomem *addr)
{
writeq(value, addr);
}
#endif
-u8 rust_helper_readb_relaxed(const volatile void __iomem *addr)
+u8 rust_helper_readb_relaxed(const void __iomem *addr)
{
return readb_relaxed(addr);
}
-u16 rust_helper_readw_relaxed(const volatile void __iomem *addr)
+u16 rust_helper_readw_relaxed(const void __iomem *addr)
{
return readw_relaxed(addr);
}
-u32 rust_helper_readl_relaxed(const volatile void __iomem *addr)
+u32 rust_helper_readl_relaxed(const void __iomem *addr)
{
return readl_relaxed(addr);
}
#ifdef CONFIG_64BIT
-u64 rust_helper_readq_relaxed(const volatile void __iomem *addr)
+u64 rust_helper_readq_relaxed(const void __iomem *addr)
{
return readq_relaxed(addr);
}
#endif
-void rust_helper_writeb_relaxed(u8 value, volatile void __iomem *addr)
+void rust_helper_writeb_relaxed(u8 value, void __iomem *addr)
{
writeb_relaxed(value, addr);
}
-void rust_helper_writew_relaxed(u16 value, volatile void __iomem *addr)
+void rust_helper_writew_relaxed(u16 value, void __iomem *addr)
{
writew_relaxed(value, addr);
}
-void rust_helper_writel_relaxed(u32 value, volatile void __iomem *addr)
+void rust_helper_writel_relaxed(u32 value, void __iomem *addr)
{
writel_relaxed(value, addr);
}
#ifdef CONFIG_64BIT
-void rust_helper_writeq_relaxed(u64 value, volatile void __iomem *addr)
+void rust_helper_writeq_relaxed(u64 value, void __iomem *addr)
{
writeq_relaxed(value, addr);
}
diff --git a/rust/kernel/firmware.rs b/rust/kernel/firmware.rs
index f04b058..2494c96e 100644
--- a/rust/kernel/firmware.rs
+++ b/rust/kernel/firmware.rs
@@ -4,7 +4,7 @@
//!
//! C header: [`include/linux/firmware.h`](srctree/include/linux/firmware.h)
-use crate::{bindings, device::Device, error::Error, error::Result, str::CStr};
+use crate::{bindings, device::Device, error::Error, error::Result, ffi, str::CStr};
use core::ptr::NonNull;
/// # Invariants
@@ -12,7 +12,11 @@
/// One of the following: `bindings::request_firmware`, `bindings::firmware_request_nowarn`,
/// `bindings::firmware_request_platform`, `bindings::request_firmware_direct`.
struct FwFunc(
- unsafe extern "C" fn(*mut *const bindings::firmware, *const u8, *mut bindings::device) -> i32,
+ unsafe extern "C" fn(
+ *mut *const bindings::firmware,
+ *const ffi::c_char,
+ *mut bindings::device,
+ ) -> i32,
);
impl FwFunc {
diff --git a/rust/pin-init/examples/pthread_mutex.rs b/rust/pin-init/examples/pthread_mutex.rs
index 9164298..5ac22f1 100644
--- a/rust/pin-init/examples/pthread_mutex.rs
+++ b/rust/pin-init/examples/pthread_mutex.rs
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: Apache-2.0 OR MIT
-// inspired by https://github.com/nbdd0121/pin-init/blob/trunk/examples/pthread_mutex.rs
+// inspired by <https://github.com/nbdd0121/pin-init/blob/trunk/examples/pthread_mutex.rs>
#![allow(clippy::undocumented_unsafe_blocks)]
#![cfg_attr(feature = "alloc", feature(allocator_api))]
#[cfg(not(windows))]
diff --git a/rust/pin-init/src/alloc.rs b/rust/pin-init/src/alloc.rs
index e16baa3..5017f57 100644
--- a/rust/pin-init/src/alloc.rs
+++ b/rust/pin-init/src/alloc.rs
@@ -17,11 +17,9 @@
pub extern crate alloc;
-// SAFETY: All zeros is equivalent to `None` (option layout optimization guarantee).
-//
-// In this case we are allowed to use `T: ?Sized`, since all zeros is the `None` variant and there
-// is no problem with a VTABLE pointer being null.
-unsafe impl<T: ?Sized> ZeroableOption for Box<T> {}
+// SAFETY: All zeros is equivalent to `None` (option layout optimization guarantee:
+// <https://doc.rust-lang.org/stable/std/option/index.html#representation>).
+unsafe impl<T> ZeroableOption for Box<T> {}
/// Smart pointer that can initialize memory in-place.
pub trait InPlaceInit<T>: Sized {
diff --git a/rust/pin-init/src/lib.rs b/rust/pin-init/src/lib.rs
index 05c4451..0806c68 100644
--- a/rust/pin-init/src/lib.rs
+++ b/rust/pin-init/src/lib.rs
@@ -1447,7 +1447,7 @@ macro_rules! impl_zeroable {
{<T: ?Sized + Zeroable>} UnsafeCell<T>,
// SAFETY: All zeros is equivalent to `None` (option layout optimization guarantee:
- // https://doc.rust-lang.org/stable/std/option/index.html#representation).
+ // <https://doc.rust-lang.org/stable/std/option/index.html#representation>).
Option<NonZeroU8>, Option<NonZeroU16>, Option<NonZeroU32>, Option<NonZeroU64>,
Option<NonZeroU128>, Option<NonZeroUsize>,
Option<NonZeroI8>, Option<NonZeroI16>, Option<NonZeroI32>, Option<NonZeroI64>,
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 5b63263..95a4fa1 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -376,7 +376,7 @@
@echo " CLANG-bpf " $@
$(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(BPF_EXTRA_CFLAGS) \
-I$(obj) -I$(srctree)/tools/testing/selftests/bpf/ \
- -I$(LIBBPF_INCLUDE) \
+ -I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES) \
-D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \
-D__TARGET_ARCH_$(SRCARCH) -Wno-compare-distinct-pointer-types \
-Wno-gnu-variable-sized-type-not-at-end \
diff --git a/samples/livepatch/livepatch-callbacks-busymod.c b/samples/livepatch/livepatch-callbacks-busymod.c
index 6910559..fadc2a8 100644
--- a/samples/livepatch/livepatch-callbacks-busymod.c
+++ b/samples/livepatch/livepatch-callbacks-busymod.c
@@ -56,4 +56,5 @@ static void livepatch_callbacks_mod_exit(void)
module_init(livepatch_callbacks_mod_init);
module_exit(livepatch_callbacks_mod_exit);
+MODULE_DESCRIPTION("Live patching demo for (un)patching callbacks, support module");
MODULE_LICENSE("GPL");
diff --git a/samples/livepatch/livepatch-callbacks-demo.c b/samples/livepatch/livepatch-callbacks-demo.c
index 11c3f43..9e69d9c 100644
--- a/samples/livepatch/livepatch-callbacks-demo.c
+++ b/samples/livepatch/livepatch-callbacks-demo.c
@@ -192,5 +192,6 @@ static void livepatch_callbacks_demo_exit(void)
module_init(livepatch_callbacks_demo_init);
module_exit(livepatch_callbacks_demo_exit);
+MODULE_DESCRIPTION("Live patching demo for (un)patching callbacks");
MODULE_LICENSE("GPL");
MODULE_INFO(livepatch, "Y");
diff --git a/samples/livepatch/livepatch-callbacks-mod.c b/samples/livepatch/livepatch-callbacks-mod.c
index 2a074f42..d1851b4 100644
--- a/samples/livepatch/livepatch-callbacks-mod.c
+++ b/samples/livepatch/livepatch-callbacks-mod.c
@@ -38,4 +38,5 @@ static void livepatch_callbacks_mod_exit(void)
module_init(livepatch_callbacks_mod_init);
module_exit(livepatch_callbacks_mod_exit);
+MODULE_DESCRIPTION("Live patching demo for (un)patching callbacks, support module");
MODULE_LICENSE("GPL");
diff --git a/samples/livepatch/livepatch-sample.c b/samples/livepatch/livepatch-sample.c
index cd76d7e..5263a2f 100644
--- a/samples/livepatch/livepatch-sample.c
+++ b/samples/livepatch/livepatch-sample.c
@@ -66,5 +66,6 @@ static void livepatch_exit(void)
module_init(livepatch_init);
module_exit(livepatch_exit);
+MODULE_DESCRIPTION("Kernel Live Patching Sample Module");
MODULE_LICENSE("GPL");
MODULE_INFO(livepatch, "Y");
diff --git a/samples/livepatch/livepatch-shadow-fix1.c b/samples/livepatch/livepatch-shadow-fix1.c
index f3f1538..cbf68ca 100644
--- a/samples/livepatch/livepatch-shadow-fix1.c
+++ b/samples/livepatch/livepatch-shadow-fix1.c
@@ -168,5 +168,6 @@ static void livepatch_shadow_fix1_exit(void)
module_init(livepatch_shadow_fix1_init);
module_exit(livepatch_shadow_fix1_exit);
+MODULE_DESCRIPTION("Live patching demo for shadow variables");
MODULE_LICENSE("GPL");
MODULE_INFO(livepatch, "Y");
diff --git a/samples/livepatch/livepatch-shadow-fix2.c b/samples/livepatch/livepatch-shadow-fix2.c
index 361046a..b99122c 100644
--- a/samples/livepatch/livepatch-shadow-fix2.c
+++ b/samples/livepatch/livepatch-shadow-fix2.c
@@ -128,5 +128,6 @@ static void livepatch_shadow_fix2_exit(void)
module_init(livepatch_shadow_fix2_init);
module_exit(livepatch_shadow_fix2_exit);
+MODULE_DESCRIPTION("Live patching demo for shadow variables");
MODULE_LICENSE("GPL");
MODULE_INFO(livepatch, "Y");
diff --git a/scripts/Makefile.compiler b/scripts/Makefile.compiler
index 8956587..f4fcc1e 100644
--- a/scripts/Makefile.compiler
+++ b/scripts/Makefile.compiler
@@ -79,8 +79,8 @@
# Usage: MY_RUSTFLAGS += $(call __rustc-option,$(RUSTC),$(MY_RUSTFLAGS),-Cinstrument-coverage,-Zinstrument-coverage)
# TODO: remove RUSTC_BOOTSTRAP=1 when we raise the minimum GNU Make version to 4.4
__rustc-option = $(call try-run,\
- echo '#![allow(missing_docs)]#![feature(no_core)]#![no_core]' | RUSTC_BOOTSTRAP=1\
- $(1) --sysroot=/dev/null $(filter-out --sysroot=/dev/null,$(2)) $(3)\
+ echo '$(pound)![allow(missing_docs)]$(pound)![feature(no_core)]$(pound)![no_core]' | RUSTC_BOOTSTRAP=1\
+ $(1) --sysroot=/dev/null $(filter-out --sysroot=/dev/null --target=%,$(2)) $(3)\
--crate-type=rlib --out-dir=$(TMPOUT) --emit=obj=- - >/dev/null,$(3),$(4))
# rustc-option
diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
index d758975..d88acdf4 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -8,6 +8,7 @@
# Default set of warnings, always enabled
KBUILD_CFLAGS += -Wall
+KBUILD_CFLAGS += -Wextra
KBUILD_CFLAGS += -Wundef
KBUILD_CFLAGS += -Werror=implicit-function-declaration
KBUILD_CFLAGS += -Werror=implicit-int
@@ -15,7 +16,7 @@
KBUILD_CFLAGS += -Werror=strict-prototypes
KBUILD_CFLAGS += -Wno-format-security
KBUILD_CFLAGS += -Wno-trigraphs
-KBUILD_CFLAGS += $(call cc-disable-warning,frame-address,)
+KBUILD_CFLAGS += $(call cc-disable-warning, frame-address)
KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
KBUILD_CFLAGS += -Wmissing-declarations
KBUILD_CFLAGS += -Wmissing-prototypes
@@ -56,6 +57,13 @@
# globally built with -Wcast-function-type.
KBUILD_CFLAGS += $(call cc-option, -Wcast-function-type)
+# Currently, disable -Wstringop-overflow for GCC 11, globally.
+KBUILD_CFLAGS-$(CONFIG_CC_NO_STRINGOP_OVERFLOW) += $(call cc-disable-warning, stringop-overflow)
+KBUILD_CFLAGS-$(CONFIG_CC_STRINGOP_OVERFLOW) += $(call cc-option, -Wstringop-overflow)
+
+# Currently, disable -Wunterminated-string-initialization as broken
+KBUILD_CFLAGS += $(call cc-disable-warning, unterminated-string-initialization)
+
# The allocators already balk at large sizes, so silence the compiler
# warnings for bounds checks involving those possible values. While
# -Wno-alloc-size-larger-than would normally be used here, earlier versions
@@ -82,7 +90,6 @@
# Warn if there is an enum types mismatch
KBUILD_CFLAGS += $(call cc-option,-Wenum-conversion)
-KBUILD_CFLAGS += -Wextra
KBUILD_CFLAGS += -Wunused
#
diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py
index cd41bc9..fe663dd 100755
--- a/scripts/generate_rust_analyzer.py
+++ b/scripts/generate_rust_analyzer.py
@@ -112,6 +112,12 @@
cfg=["kernel"],
)
+ append_crate(
+ "ffi",
+ srctree / "rust" / "ffi.rs",
+ ["core", "compiler_builtins"],
+ )
+
def append_crate_with_generated(
display_name,
deps,
@@ -131,9 +137,9 @@
"exclude_dirs": [],
}
- append_crate_with_generated("bindings", ["core"])
- append_crate_with_generated("uapi", ["core"])
- append_crate_with_generated("kernel", ["core", "macros", "build_error", "pin_init", "bindings", "uapi"])
+ append_crate_with_generated("bindings", ["core", "ffi"])
+ append_crate_with_generated("uapi", ["core", "ffi"])
+ append_crate_with_generated("kernel", ["core", "macros", "build_error", "pin_init", "ffi", "bindings", "uapi"])
def is_root_crate(build_file, target):
try:
diff --git a/scripts/genksyms/keywords.c b/scripts/genksyms/keywords.c
index b85e097..ee1499d 100644
--- a/scripts/genksyms/keywords.c
+++ b/scripts/genksyms/keywords.c
@@ -17,6 +17,8 @@ static struct resword {
{ "__signed__", SIGNED_KEYW },
{ "__typeof", TYPEOF_KEYW },
{ "__typeof__", TYPEOF_KEYW },
+ { "__typeof_unqual", TYPEOF_KEYW },
+ { "__typeof_unqual__", TYPEOF_KEYW },
{ "__volatile", VOLATILE_KEYW },
{ "__volatile__", VOLATILE_KEYW },
{ "__builtin_va_list", VA_LIST_KEYW },
@@ -40,6 +42,10 @@ static struct resword {
// KAO. },
// { "attribute", ATTRIBUTE_KEYW },
+ // X86 named address space qualifiers
+ { "__seg_gs", X86_SEG_KEYW },
+ { "__seg_fs", X86_SEG_KEYW },
+
{ "auto", AUTO_KEYW },
{ "char", CHAR_KEYW },
{ "const", CONST_KEYW },
@@ -57,6 +63,7 @@ static struct resword {
{ "struct", STRUCT_KEYW },
{ "typedef", TYPEDEF_KEYW },
{ "typeof", TYPEOF_KEYW },
+ { "typeof_unqual", TYPEOF_KEYW },
{ "union", UNION_KEYW },
{ "unsigned", UNSIGNED_KEYW },
{ "void", VOID_KEYW },
diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y
index ee600a8..efdcf07 100644
--- a/scripts/genksyms/parse.y
+++ b/scripts/genksyms/parse.y
@@ -91,6 +91,8 @@
%token TYPEOF_KEYW
%token VA_LIST_KEYW
+%token X86_SEG_KEYW
+
%token EXPORT_SYMBOL_KEYW
%token ASM_PHRASE
@@ -292,7 +294,8 @@
;
type_qualifier:
- CONST_KEYW | VOLATILE_KEYW
+ X86_SEG_KEYW
+ | CONST_KEYW | VOLATILE_KEYW
| RESTRICT_KEYW
{ /* restrict has no effect in prototypes so ignore it */
remove_node($1);
diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening
index c17366c..3fe9d7b 100644
--- a/security/Kconfig.hardening
+++ b/security/Kconfig.hardening
@@ -344,7 +344,7 @@
choice
prompt "Randomize layout of sensitive kernel structures"
- default RANDSTRUCT_FULL if COMPILE_TEST && (GCC_PLUGINS || CC_HAS_RANDSTRUCT)
+ default RANDSTRUCT_FULL if COMPILE_TEST && CC_HAS_RANDSTRUCT
default RANDSTRUCT_NONE
help
If you enable this, the layouts of structures that are entirely
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index f3e7ac5..f99ab1a 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -245,7 +245,9 @@ static int process_measurement(struct file *file, const struct cred *cred,
&allowed_algos);
violation_check = ((func == FILE_CHECK || func == MMAP_CHECK ||
func == MMAP_CHECK_REQPROT) &&
- (ima_policy_flag & IMA_MEASURE));
+ (ima_policy_flag & IMA_MEASURE) &&
+ ((action & IMA_MEASURE) ||
+ (file->f_mode & FMODE_WRITE)));
if (!action && !violation_check)
return 0;
diff --git a/security/landlock/domain.c b/security/landlock/domain.c
index bae2e99..a647b68 100644
--- a/security/landlock/domain.c
+++ b/security/landlock/domain.c
@@ -16,6 +16,7 @@
#include <linux/path.h>
#include <linux/pid.h>
#include <linux/sched.h>
+#include <linux/signal.h>
#include <linux/uidgid.h>
#include "access.h"
@@ -99,8 +100,7 @@ static struct landlock_details *get_current_details(void)
return ERR_PTR(-ENOMEM);
memcpy(details->exe_path, path_str, path_size);
- WARN_ON_ONCE(current_cred() != current_real_cred());
- details->pid = get_pid(task_pid(current));
+ details->pid = get_pid(task_tgid(current));
details->uid = from_kuid(&init_user_ns, current_uid());
get_task_comm(details->comm, current);
return details;
diff --git a/security/landlock/domain.h b/security/landlock/domain.h
index ed0d348..7fb70b2 100644
--- a/security/landlock/domain.h
+++ b/security/landlock/domain.h
@@ -130,7 +130,7 @@ int landlock_init_hierarchy_log(struct landlock_hierarchy *const hierarchy);
static inline void
landlock_free_hierarchy_details(struct landlock_hierarchy *const hierarchy)
{
- if (WARN_ON_ONCE(!hierarchy || !hierarchy->details))
+ if (!hierarchy || !hierarchy->details)
return;
put_pid(hierarchy->details->pid);
diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c
index 54a9f29..b9561e34 100644
--- a/security/landlock/syscalls.c
+++ b/security/landlock/syscalls.c
@@ -169,20 +169,16 @@ const int landlock_abi_version = 7;
* the new ruleset.
* @size: Size of the pointed &struct landlock_ruleset_attr (needed for
* backward and forward compatibility).
- * @flags: Supported value:
+ * @flags: Supported values:
+ *
* - %LANDLOCK_CREATE_RULESET_VERSION
* - %LANDLOCK_CREATE_RULESET_ERRATA
*
* This system call enables to create a new Landlock ruleset, and returns the
* related file descriptor on success.
*
- * If @flags is %LANDLOCK_CREATE_RULESET_VERSION and @attr is NULL and @size is
- * 0, then the returned value is the highest supported Landlock ABI version
- * (starting at 1).
- *
- * If @flags is %LANDLOCK_CREATE_RULESET_ERRATA and @attr is NULL and @size is
- * 0, then the returned value is a bitmask of fixed issues for the current
- * Landlock ABI version.
+ * If %LANDLOCK_CREATE_RULESET_VERSION or %LANDLOCK_CREATE_RULESET_ERRATA is
+ * set, then @attr must be NULL and @size must be 0.
*
* Possible returned errors are:
*
@@ -191,6 +187,9 @@ const int landlock_abi_version = 7;
* - %E2BIG: @attr or @size inconsistencies;
* - %EFAULT: @attr or @size inconsistencies;
* - %ENOMSG: empty &landlock_ruleset_attr.handled_access_fs.
+ *
+ * .. kernel-doc:: include/uapi/linux/landlock.h
+ * :identifiers: landlock_create_ruleset_flags
*/
SYSCALL_DEFINE3(landlock_create_ruleset,
const struct landlock_ruleset_attr __user *const, attr,
@@ -452,18 +451,15 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd,
* @ruleset_fd: File descriptor tied to the ruleset to merge with the target.
* @flags: Supported values:
*
- * - %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF
- * - %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON
- * - %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF
+ * - %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF
+ * - %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON
+ * - %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF
*
* This system call enables to enforce a Landlock ruleset on the current
* thread. Enforcing a ruleset requires that the task has %CAP_SYS_ADMIN in its
* namespace or is running with no_new_privs. This avoids scenarios where
* unprivileged tasks can affect the behavior of privileged children.
*
- * It is allowed to only pass the %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF
- * flag with a @ruleset_fd value of -1.
- *
* Possible returned errors are:
*
* - %EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time;
@@ -475,6 +471,9 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd,
* %CAP_SYS_ADMIN in its namespace.
* - %E2BIG: The maximum number of stacked rulesets is reached for the current
* thread.
+ *
+ * .. kernel-doc:: include/uapi/linux/landlock.h
+ * :identifiers: landlock_restrict_self_flags
*/
SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32,
flags)
diff --git a/sound/isa/azt2320.c b/sound/isa/azt2320.c
index b937c91..588b9f0 100644
--- a/sound/isa/azt2320.c
+++ b/sound/isa/azt2320.c
@@ -189,8 +189,8 @@ static int snd_card_azt2320_probe(int dev,
if (error < 0)
return error;
- strcpy(card->driver, "AZT2320");
- strcpy(card->shortname, "Aztech AZT2320");
+ strscpy(card->driver, "AZT2320");
+ strscpy(card->shortname, "Aztech AZT2320");
sprintf(card->longname, "%s, WSS at 0x%lx, irq %i, dma %i&%i",
card->shortname, chip->port, irq[dev], dma1[dev], dma2[dev]);
diff --git a/sound/pci/hda/Kconfig b/sound/pci/hda/Kconfig
index fb955a2..9c42727 100644
--- a/sound/pci/hda/Kconfig
+++ b/sound/pci/hda/Kconfig
@@ -96,9 +96,7 @@
config SND_HDA_CIRRUS_SCODEC_KUNIT_TEST
tristate "KUnit test for Cirrus side-codec library" if !KUNIT_ALL_TESTS
- select SND_HDA_CIRRUS_SCODEC
- select GPIOLIB
- depends on KUNIT
+ depends on SND_HDA_CIRRUS_SCODEC && GPIOLIB && KUNIT
default KUNIT_ALL_TESTS
help
This builds KUnit tests for the cirrus side-codec library.
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 79004bc..8a2b09e 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -441,6 +441,10 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
alc_update_coef_idx(codec, 0x67, 0xf000, 0x3000);
fallthrough;
case 0x10ec0215:
+ case 0x10ec0236:
+ case 0x10ec0245:
+ case 0x10ec0256:
+ case 0x10ec0257:
case 0x10ec0285:
case 0x10ec0289:
alc_update_coef_idx(codec, 0x36, 1<<13, 0);
@@ -448,12 +452,8 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
case 0x10ec0230:
case 0x10ec0233:
case 0x10ec0235:
- case 0x10ec0236:
- case 0x10ec0245:
case 0x10ec0255:
- case 0x10ec0256:
case 0x19e58326:
- case 0x10ec0257:
case 0x10ec0282:
case 0x10ec0283:
case 0x10ec0286:
@@ -6742,6 +6742,25 @@ static void alc274_fixup_bind_dacs(struct hda_codec *codec,
codec->power_save_node = 0;
}
+/* avoid DAC 0x06 for speaker switch 0x17; it has no volume control */
+static void alc274_fixup_hp_aio_bind_dacs(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ static const hda_nid_t conn[] = { 0x02, 0x03 }; /* exclude 0x06 */
+ /* The speaker is routed to the Node 0x06 by a mistake, thus the
+ * speaker's volume can't be adjusted since the node doesn't have
+ * Amp-out capability. Assure the speaker and lineout pin to be
+ * coupled with DAC NID 0x02.
+ */
+ static const hda_nid_t preferred_pairs[] = {
+ 0x16, 0x02, 0x17, 0x02, 0x21, 0x03, 0
+ };
+ struct alc_spec *spec = codec->spec;
+
+ snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn);
+ spec->gen.preferred_dacs = preferred_pairs;
+}
+
/* avoid DAC 0x06 for bass speaker 0x17; it has no volume control */
static void alc289_fixup_asus_ga401(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
@@ -6963,6 +6982,41 @@ static void alc285_fixup_hp_spectre_x360_eb1(struct hda_codec *codec,
}
}
+/* GPIO1 = amplifier on/off */
+static void alc285_fixup_hp_spectre_x360_df1(struct hda_codec *codec,
+ const struct hda_fixup *fix,
+ int action)
+{
+ struct alc_spec *spec = codec->spec;
+ static const hda_nid_t conn[] = { 0x02 };
+ static const struct hda_pintbl pincfgs[] = {
+ { 0x14, 0x90170110 }, /* front/high speakers */
+ { 0x17, 0x90170130 }, /* back/bass speakers */
+ { }
+ };
+
+ // enable mute led
+ alc285_fixup_hp_mute_led_coefbit(codec, fix, action);
+
+ switch (action) {
+ case HDA_FIXUP_ACT_PRE_PROBE:
+ /* needed for amp of back speakers */
+ spec->gpio_mask |= 0x01;
+ spec->gpio_dir |= 0x01;
+ snd_hda_apply_pincfgs(codec, pincfgs);
+ /* share DAC to have unified volume control */
+ snd_hda_override_conn_list(codec, 0x14, ARRAY_SIZE(conn), conn);
+ snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn);
+ break;
+ case HDA_FIXUP_ACT_INIT:
+ /* need to toggle GPIO to enable the amp of back speakers */
+ alc_update_gpio_data(codec, 0x01, true);
+ msleep(100);
+ alc_update_gpio_data(codec, 0x01, false);
+ break;
+ }
+}
+
static void alc285_fixup_hp_spectre_x360(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
@@ -7761,6 +7815,7 @@ enum {
ALC280_FIXUP_HP_9480M,
ALC245_FIXUP_HP_X360_AMP,
ALC285_FIXUP_HP_SPECTRE_X360_EB1,
+ ALC285_FIXUP_HP_SPECTRE_X360_DF1,
ALC285_FIXUP_HP_ENVY_X360,
ALC288_FIXUP_DELL_HEADSET_MODE,
ALC288_FIXUP_DELL1_MIC_NO_PRESENCE,
@@ -7969,6 +8024,8 @@ enum {
ALC233_FIXUP_MEDION_MTL_SPK,
ALC294_FIXUP_BASS_SPEAKER_15,
ALC283_FIXUP_DELL_HP_RESUME,
+ ALC294_FIXUP_ASUS_CS35L41_SPI_2,
+ ALC274_FIXUP_HP_AIO_BIND_DACS,
};
/* A special fixup for Lenovo C940 and Yoga Duet 7;
@@ -9836,6 +9893,10 @@ static const struct hda_fixup alc269_fixups[] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc285_fixup_hp_spectre_x360_eb1
},
+ [ALC285_FIXUP_HP_SPECTRE_X360_DF1] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc285_fixup_hp_spectre_x360_df1
+ },
[ALC285_FIXUP_HP_ENVY_X360] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc285_fixup_hp_envy_x360,
@@ -10333,6 +10394,16 @@ static const struct hda_fixup alc269_fixups[] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc283_fixup_dell_hp_resume,
},
+ [ALC294_FIXUP_ASUS_CS35L41_SPI_2] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = cs35l41_fixup_spi_two,
+ .chained = true,
+ .chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC,
+ },
+ [ALC274_FIXUP_HP_AIO_BIND_DACS] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc274_fixup_hp_aio_bind_dacs,
+ },
};
static const struct hda_quirk alc269_fixup_tbl[] = {
@@ -10557,6 +10628,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x86c1, "HP Laptop 15-da3001TU", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
SND_PCI_QUIRK(0x103c, 0x86c7, "HP Envy AiO 32", ALC274_FIXUP_HP_ENVY_GPIO),
SND_PCI_QUIRK(0x103c, 0x86e7, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1),
+ SND_PCI_QUIRK(0x103c, 0x863e, "HP Spectre x360 15-df1xxx", ALC285_FIXUP_HP_SPECTRE_X360_DF1),
SND_PCI_QUIRK(0x103c, 0x86e8, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1),
SND_PCI_QUIRK(0x103c, 0x86f9, "HP Spectre x360 13-aw0xxx", ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED),
SND_PCI_QUIRK(0x103c, 0x8716, "HP Elite Dragonfly G2 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT),
@@ -10761,12 +10833,13 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8caf, "HP Elite mt645 G8 Mobile Thin Client", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
SND_PCI_QUIRK(0x103c, 0x8cbd, "HP Pavilion Aero Laptop 13-bg0xxx", ALC245_FIXUP_HP_X360_MUTE_LEDS),
- SND_PCI_QUIRK(0x103c, 0x8cdd, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2),
- SND_PCI_QUIRK(0x103c, 0x8cde, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x103c, 0x8cdd, "HP Spectre", ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX),
+ SND_PCI_QUIRK(0x103c, 0x8cde, "HP OmniBook Ultra Flip Laptop 14t", ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX),
SND_PCI_QUIRK(0x103c, 0x8cdf, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8ce0, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8d01, "HP ZBook Power 14 G12", ALC285_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8d18, "HP EliteStudio 8 AIO", ALC274_FIXUP_HP_AIO_BIND_DACS),
SND_PCI_QUIRK(0x103c, 0x8d84, "HP EliteBook X G1i", ALC285_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8d85, "HP EliteBook 14 G12", ALC285_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8d86, "HP Elite X360 14 G12", ALC285_FIXUP_HP_GPIO_LED),
@@ -10786,11 +10859,15 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x8da1, "HP 16 Clipper OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x103c, 0x8da7, "HP 14 Enstrom OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x103c, 0x8da8, "HP 16 Piston OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x103c, 0x8dd4, "HP EliteStudio 8 AIO", ALC274_FIXUP_HP_AIO_BIND_DACS),
SND_PCI_QUIRK(0x103c, 0x8de8, "HP Gemtree", ALC245_FIXUP_TAS2781_SPI_2),
SND_PCI_QUIRK(0x103c, 0x8de9, "HP Gemtree", ALC245_FIXUP_TAS2781_SPI_2),
SND_PCI_QUIRK(0x103c, 0x8dec, "HP EliteBook 640 G12", ALC236_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8ded, "HP EliteBook 640 G12", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8dee, "HP EliteBook 660 G12", ALC236_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8def, "HP EliteBook 660 G12", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8df0, "HP EliteBook 630 G12", ALC236_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8df1, "HP EliteBook 630 G12", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8dfc, "HP EliteBook 645 G12", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8dfe, "HP EliteBook 665 G12", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8e11, "HP Trekker", ALC287_FIXUP_CS35L41_I2C_2),
@@ -10835,11 +10912,11 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x12a0, "ASUS X441UV", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x12a3, "Asus N7691ZM", ALC269_FIXUP_ASUS_N7601ZM),
SND_PCI_QUIRK(0x1043, 0x12af, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2),
- SND_PCI_QUIRK(0x1043, 0x12b4, "ASUS B3405CCA / P3405CCA", ALC245_FIXUP_CS35L41_SPI_2),
- SND_PCI_QUIRK(0x1043, 0x12e0, "ASUS X541SA", ALC256_FIXUP_ASUS_MIC),
- SND_PCI_QUIRK(0x1043, 0x12f0, "ASUS X541UV", ALC256_FIXUP_ASUS_MIC),
+ SND_PCI_QUIRK(0x1043, 0x12b4, "ASUS B3405CCA / P3405CCA", ALC294_FIXUP_ASUS_CS35L41_SPI_2),
+ SND_PCI_QUIRK(0x1043, 0x12e0, "ASUS X541SA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1043, 0x12f0, "ASUS X541UV", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE),
- SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC),
+ SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK),
SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650PY/PZ/PV/PU/PYV/PZV/PIV/PVV", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
SND_PCI_QUIRK(0x1043, 0x1460, "Asus VivoBook 15", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
@@ -10893,7 +10970,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS),
SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JU/JV/JI", ALC285_FIXUP_ASUS_HEADSET_MIC),
SND_PCI_QUIRK(0x1043, 0x1caf, "ASUS G634JY/JZ/JI/JG", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
- SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC),
+ SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x1ccf, "ASUS G814JU/JV/JI", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1cdf, "ASUS G814JY/JZ/JG", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1cef, "ASUS G834JY/JZ/JI/JG", ALC285_FIXUP_ASUS_HEADSET_MIC),
@@ -10925,14 +11002,14 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x1fb3, "ASUS ROG Flow Z13 GZ302EA", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x1043, 0x3011, "ASUS B5605CVA", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
- SND_PCI_QUIRK(0x1043, 0x3061, "ASUS B3405CCA", ALC245_FIXUP_CS35L41_SPI_2),
- SND_PCI_QUIRK(0x1043, 0x3071, "ASUS B5405CCA", ALC245_FIXUP_CS35L41_SPI_2),
- SND_PCI_QUIRK(0x1043, 0x30c1, "ASUS B3605CCA / P3605CCA", ALC245_FIXUP_CS35L41_SPI_2),
- SND_PCI_QUIRK(0x1043, 0x30d1, "ASUS B5405CCA", ALC245_FIXUP_CS35L41_SPI_2),
- SND_PCI_QUIRK(0x1043, 0x30e1, "ASUS B5605CCA", ALC245_FIXUP_CS35L41_SPI_2),
+ SND_PCI_QUIRK(0x1043, 0x3061, "ASUS B3405CCA", ALC294_FIXUP_ASUS_CS35L41_SPI_2),
+ SND_PCI_QUIRK(0x1043, 0x3071, "ASUS B5405CCA", ALC294_FIXUP_ASUS_CS35L41_SPI_2),
+ SND_PCI_QUIRK(0x1043, 0x30c1, "ASUS B3605CCA / P3605CCA", ALC294_FIXUP_ASUS_CS35L41_SPI_2),
+ SND_PCI_QUIRK(0x1043, 0x30d1, "ASUS B5405CCA", ALC294_FIXUP_ASUS_CS35L41_SPI_2),
+ SND_PCI_QUIRK(0x1043, 0x30e1, "ASUS B5605CCA", ALC294_FIXUP_ASUS_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x31d0, "ASUS Zen AIO 27 Z272SD_A272SD", ALC274_FIXUP_ASUS_ZEN_AIO_27),
- SND_PCI_QUIRK(0x1043, 0x31e1, "ASUS B5605CCA", ALC245_FIXUP_CS35L41_SPI_2),
- SND_PCI_QUIRK(0x1043, 0x31f1, "ASUS B3605CCA", ALC245_FIXUP_CS35L41_SPI_2),
+ SND_PCI_QUIRK(0x1043, 0x31e1, "ASUS B5605CCA", ALC294_FIXUP_ASUS_CS35L41_SPI_2),
+ SND_PCI_QUIRK(0x1043, 0x31f1, "ASUS B3605CCA", ALC294_FIXUP_ASUS_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
SND_PCI_QUIRK(0x1043, 0x3a30, "ASUS G814JVR/JIR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
@@ -11487,6 +11564,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
{.id = ALC295_FIXUP_HP_OMEN, .name = "alc295-hp-omen"},
{.id = ALC285_FIXUP_HP_SPECTRE_X360, .name = "alc285-hp-spectre-x360"},
{.id = ALC285_FIXUP_HP_SPECTRE_X360_EB1, .name = "alc285-hp-spectre-x360-eb1"},
+ {.id = ALC285_FIXUP_HP_SPECTRE_X360_DF1, .name = "alc285-hp-spectre-x360-df1"},
{.id = ALC285_FIXUP_HP_ENVY_X360, .name = "alc285-hp-envy-x360"},
{.id = ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP, .name = "alc287-ideapad-bass-spk-amp"},
{.id = ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN, .name = "alc287-yoga9-bass-spk-pin"},
diff --git a/sound/pci/hda/tas2781_hda_spi.c b/sound/pci/hda/tas2781_hda_spi.c
index 399f2e4..25175ff 100644
--- a/sound/pci/hda/tas2781_hda_spi.c
+++ b/sound/pci/hda/tas2781_hda_spi.c
@@ -1003,8 +1003,7 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context)
*/
out:
- if (fmw)
- release_firmware(fmw);
+ release_firmware(fmw);
pm_runtime_mark_last_busy(tas_hda->priv->dev);
pm_runtime_put_autosuspend(tas_hda->priv->dev);
}
diff --git a/sound/soc/amd/acp/acp-i2s.c b/sound/soc/amd/acp/acp-i2s.c
index a38409d..70fa54d 100644
--- a/sound/soc/amd/acp/acp-i2s.c
+++ b/sound/soc/amd/acp/acp-i2s.c
@@ -97,7 +97,7 @@ static int acp_i2s_set_tdm_slot(struct snd_soc_dai *dai, u32 tx_mask, u32 rx_mas
struct acp_stream *stream;
int slot_len, no_of_slots;
- chip = dev_get_platdata(dev);
+ chip = dev_get_drvdata(dev->parent);
switch (slot_width) {
case SLOT_WIDTH_8:
slot_len = 8;
diff --git a/sound/soc/amd/acp/acp-legacy-common.c b/sound/soc/amd/acp/acp-legacy-common.c
index b4d6848..ba8db08 100644
--- a/sound/soc/amd/acp/acp-legacy-common.c
+++ b/sound/soc/amd/acp/acp-legacy-common.c
@@ -450,7 +450,7 @@ int acp_machine_select(struct acp_chip_info *chip)
struct snd_soc_acpi_mach *mach;
int size, platform;
- if (chip->flag == FLAG_AMD_LEGACY_ONLY_DMIC) {
+ if (chip->flag == FLAG_AMD_LEGACY_ONLY_DMIC && chip->is_pdm_dev) {
platform = chip->acp_rev;
chip->mach_dev = platform_device_register_data(chip->dev, "acp-pdm-mach",
PLATFORM_DEVID_NONE, &platform,
diff --git a/sound/soc/amd/acp/acp-rembrandt.c b/sound/soc/amd/acp/acp-rembrandt.c
index 746b6ed..cccdd10 100644
--- a/sound/soc/amd/acp/acp-rembrandt.c
+++ b/sound/soc/amd/acp/acp-rembrandt.c
@@ -199,7 +199,7 @@ static void rembrandt_audio_remove(struct platform_device *pdev)
static int rmb_pcm_resume(struct device *dev)
{
- struct acp_chip_info *chip = dev_get_platdata(dev);
+ struct acp_chip_info *chip = dev_get_drvdata(dev->parent);
struct acp_stream *stream;
struct snd_pcm_substream *substream;
snd_pcm_uframes_t buf_in_frames;
diff --git a/sound/soc/amd/acp/acp-renoir.c b/sound/soc/amd/acp/acp-renoir.c
index ebf0106..04f6d70b 100644
--- a/sound/soc/amd/acp/acp-renoir.c
+++ b/sound/soc/amd/acp/acp-renoir.c
@@ -146,7 +146,7 @@ static void renoir_audio_remove(struct platform_device *pdev)
static int rn_pcm_resume(struct device *dev)
{
- struct acp_chip_info *chip = dev_get_platdata(dev);
+ struct acp_chip_info *chip = dev_get_drvdata(dev->parent);
struct acp_stream *stream;
struct snd_pcm_substream *substream;
snd_pcm_uframes_t buf_in_frames;
diff --git a/sound/soc/amd/acp/acp63.c b/sound/soc/amd/acp/acp63.c
index 52d895e..1f15c96 100644
--- a/sound/soc/amd/acp/acp63.c
+++ b/sound/soc/amd/acp/acp63.c
@@ -250,7 +250,7 @@ static void acp63_audio_remove(struct platform_device *pdev)
static int acp63_pcm_resume(struct device *dev)
{
- struct acp_chip_info *chip = dev_get_platdata(dev);
+ struct acp_chip_info *chip = dev_get_drvdata(dev->parent);
struct acp_stream *stream;
struct snd_pcm_substream *substream;
snd_pcm_uframes_t buf_in_frames;
diff --git a/sound/soc/amd/acp/acp70.c b/sound/soc/amd/acp/acp70.c
index 6d5f5ad..217b717 100644
--- a/sound/soc/amd/acp/acp70.c
+++ b/sound/soc/amd/acp/acp70.c
@@ -182,7 +182,7 @@ static void acp_acp70_audio_remove(struct platform_device *pdev)
static int acp70_pcm_resume(struct device *dev)
{
- struct acp_chip_info *chip = dev_get_platdata(dev);
+ struct acp_chip_info *chip = dev_get_drvdata(dev->parent);
struct acp_stream *stream;
struct snd_pcm_substream *substream;
snd_pcm_uframes_t buf_in_frames;
diff --git a/sound/soc/amd/ps/pci-ps.c b/sound/soc/amd/ps/pci-ps.c
index 8e57f31..7936b31 100644
--- a/sound/soc/amd/ps/pci-ps.c
+++ b/sound/soc/amd/ps/pci-ps.c
@@ -193,6 +193,7 @@ static irqreturn_t acp63_irq_handler(int irq, void *dev_id)
struct amd_sdw_manager *amd_manager;
u32 ext_intr_stat, ext_intr_stat1;
u16 irq_flag = 0;
+ u16 wake_irq_flag = 0;
u16 sdw_dma_irq_flag = 0;
adata = dev_id;
@@ -231,7 +232,7 @@ static irqreturn_t acp63_irq_handler(int irq, void *dev_id)
}
if (adata->acp_rev >= ACP70_PCI_REV)
- irq_flag = check_and_handle_acp70_sdw_wake_irq(adata);
+ wake_irq_flag = check_and_handle_acp70_sdw_wake_irq(adata);
if (ext_intr_stat & BIT(PDM_DMA_STAT)) {
ps_pdm_data = dev_get_drvdata(&adata->pdm_dev->dev);
@@ -245,7 +246,7 @@ static irqreturn_t acp63_irq_handler(int irq, void *dev_id)
if (sdw_dma_irq_flag)
return IRQ_WAKE_THREAD;
- if (irq_flag)
+ if (irq_flag | wake_irq_flag)
return IRQ_HANDLED;
else
return IRQ_NONE;
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 40bb7a1..20f99cb 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -776,10 +776,9 @@
tristate
config SND_SOC_CS_AMP_LIB_TEST
- tristate "KUnit test for Cirrus Logic cs-amp-lib"
- depends on KUNIT
+ tristate "KUnit test for Cirrus Logic cs-amp-lib" if !KUNIT_ALL_TESTS
+ depends on SND_SOC_CS_AMP_LIB && KUNIT
default KUNIT_ALL_TESTS
- select SND_SOC_CS_AMP_LIB
help
This builds KUnit tests for the Cirrus Logic common
amplifier library.
diff --git a/sound/soc/codecs/aw88081.c b/sound/soc/codecs/aw88081.c
index ad16ab6..3dd8428f 100644
--- a/sound/soc/codecs/aw88081.c
+++ b/sound/soc/codecs/aw88081.c
@@ -1295,9 +1295,19 @@ static int aw88081_i2c_probe(struct i2c_client *i2c)
aw88081_dai, ARRAY_SIZE(aw88081_dai));
}
+#if defined(CONFIG_OF)
+static const struct of_device_id aw88081_of_match[] = {
+ { .compatible = "awinic,aw88081" },
+ { .compatible = "awinic,aw88083" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, aw88081_of_match);
+#endif
+
static struct i2c_driver aw88081_i2c_driver = {
.driver = {
.name = AW88081_I2C_NAME,
+ .of_match_table = of_match_ptr(aw88081_of_match),
},
.probe = aw88081_i2c_probe,
.id_table = aw88081_i2c_id,
diff --git a/sound/soc/codecs/cs42l43-jack.c b/sound/soc/codecs/cs42l43-jack.c
index ac19a57..6165ac1 100644
--- a/sound/soc/codecs/cs42l43-jack.c
+++ b/sound/soc/codecs/cs42l43-jack.c
@@ -654,6 +654,10 @@ static int cs42l43_run_type_detect(struct cs42l43_codec *priv)
reinit_completion(&priv->type_detect);
+ regmap_update_bits(cs42l43->regmap, CS42L43_STEREO_MIC_CLAMP_CTRL,
+ CS42L43_SMIC_HPAMP_CLAMP_DIS_FRC_VAL_MASK,
+ CS42L43_SMIC_HPAMP_CLAMP_DIS_FRC_VAL_MASK);
+
cs42l43_start_hs_bias(priv, true);
regmap_update_bits(cs42l43->regmap, CS42L43_HS2,
CS42L43_HSDET_MODE_MASK, 0x3 << CS42L43_HSDET_MODE_SHIFT);
@@ -665,6 +669,9 @@ static int cs42l43_run_type_detect(struct cs42l43_codec *priv)
CS42L43_HSDET_MODE_MASK, 0x2 << CS42L43_HSDET_MODE_SHIFT);
cs42l43_stop_hs_bias(priv);
+ regmap_update_bits(cs42l43->regmap, CS42L43_STEREO_MIC_CLAMP_CTRL,
+ CS42L43_SMIC_HPAMP_CLAMP_DIS_FRC_VAL_MASK, 0);
+
if (!time_left)
return -ETIMEDOUT;
@@ -702,6 +709,9 @@ static void cs42l43_clear_jack(struct cs42l43_codec *priv)
CS42L43_PGA_WIDESWING_MODE_EN_MASK, 0);
regmap_update_bits(cs42l43->regmap, CS42L43_STEREO_MIC_CTRL,
CS42L43_JACK_STEREO_CONFIG_MASK, 0);
+ regmap_update_bits(cs42l43->regmap, CS42L43_STEREO_MIC_CLAMP_CTRL,
+ CS42L43_SMIC_HPAMP_CLAMP_DIS_FRC_MASK,
+ CS42L43_SMIC_HPAMP_CLAMP_DIS_FRC_MASK);
regmap_update_bits(cs42l43->regmap, CS42L43_HS2,
CS42L43_HSDET_MODE_MASK | CS42L43_HSDET_MANUAL_MODE_MASK,
0x2 << CS42L43_HSDET_MODE_SHIFT);
diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c
index 17019b1..bc01ff6 100644
--- a/sound/soc/codecs/hdmi-codec.c
+++ b/sound/soc/codecs/hdmi-codec.c
@@ -842,12 +842,28 @@ static void print_eld_info(struct snd_info_entry *entry,
static int hdmi_dai_proc_new(struct hdmi_codec_priv *hcp,
struct snd_soc_dai *dai)
{
+ struct snd_soc_component *component = dai->component;
+ struct snd_soc_card *card = component->card;
+ struct snd_soc_dai *d;
+ struct snd_soc_pcm_runtime *rtd;
struct snd_info_entry *entry;
char name[32];
- int err;
+ int err, i, id = 0;
- snprintf(name, sizeof(name), "eld#%d", dai->id);
- err = snd_card_proc_new(dai->component->card->snd_card, name, &entry);
+ /*
+ * To avoid duplicate proc entry, find its rtd and use rtd->id
+ * instead of dai->id
+ */
+ for_each_card_rtds(card, rtd) {
+ for_each_rtd_dais(rtd, i, d)
+ if (d == dai) {
+ id = rtd->id;
+ goto found;
+ }
+ }
+found:
+ snprintf(name, sizeof(name), "eld#%d", id);
+ err = snd_card_proc_new(card->snd_card, name, &entry);
if (err < 0)
return err;
diff --git a/sound/soc/codecs/lpass-wsa-macro.c b/sound/soc/codecs/lpass-wsa-macro.c
index b261fa3..c1fb71c 100644
--- a/sound/soc/codecs/lpass-wsa-macro.c
+++ b/sound/soc/codecs/lpass-wsa-macro.c
@@ -63,6 +63,10 @@
#define CDC_WSA_TX_SPKR_PROT_CLK_DISABLE 0
#define CDC_WSA_TX_SPKR_PROT_PCM_RATE_MASK GENMASK(3, 0)
#define CDC_WSA_TX_SPKR_PROT_PCM_RATE_8K 0
+#define CDC_WSA_TX_SPKR_PROT_PCM_RATE_16K 1
+#define CDC_WSA_TX_SPKR_PROT_PCM_RATE_24K 2
+#define CDC_WSA_TX_SPKR_PROT_PCM_RATE_32K 3
+#define CDC_WSA_TX_SPKR_PROT_PCM_RATE_48K 4
#define CDC_WSA_TX0_SPKR_PROT_PATH_CFG0 (0x0248)
#define CDC_WSA_TX1_SPKR_PROT_PATH_CTL (0x0264)
#define CDC_WSA_TX1_SPKR_PROT_PATH_CFG0 (0x0268)
@@ -407,6 +411,7 @@ struct wsa_macro {
int ear_spkr_gain;
int spkr_gain_offset;
int spkr_mode;
+ u32 pcm_rate_vi;
int is_softclip_on[WSA_MACRO_SOFTCLIP_MAX];
int softclip_clk_users[WSA_MACRO_SOFTCLIP_MAX];
struct regmap *regmap;
@@ -1280,6 +1285,7 @@ static int wsa_macro_hw_params(struct snd_pcm_substream *substream,
struct snd_soc_dai *dai)
{
struct snd_soc_component *component = dai->component;
+ struct wsa_macro *wsa = snd_soc_component_get_drvdata(component);
int ret;
switch (substream->stream) {
@@ -1292,6 +1298,11 @@ static int wsa_macro_hw_params(struct snd_pcm_substream *substream,
return ret;
}
break;
+ case SNDRV_PCM_STREAM_CAPTURE:
+ if (dai->id == WSA_MACRO_AIF_VI)
+ wsa->pcm_rate_vi = params_rate(params);
+
+ break;
default:
break;
}
@@ -1448,6 +1459,67 @@ static void wsa_macro_mclk_enable(struct wsa_macro *wsa, bool mclk_enable)
}
}
+static void wsa_macro_enable_disable_vi_sense(struct snd_soc_component *component, bool enable,
+ u32 tx_reg0, u32 tx_reg1, u32 val)
+{
+ if (enable) {
+ /* Enable V&I sensing */
+ snd_soc_component_update_bits(component, tx_reg0,
+ CDC_WSA_TX_SPKR_PROT_RESET_MASK,
+ CDC_WSA_TX_SPKR_PROT_RESET);
+ snd_soc_component_update_bits(component, tx_reg1,
+ CDC_WSA_TX_SPKR_PROT_RESET_MASK,
+ CDC_WSA_TX_SPKR_PROT_RESET);
+ snd_soc_component_update_bits(component, tx_reg0,
+ CDC_WSA_TX_SPKR_PROT_PCM_RATE_MASK,
+ val);
+ snd_soc_component_update_bits(component, tx_reg1,
+ CDC_WSA_TX_SPKR_PROT_PCM_RATE_MASK,
+ val);
+ snd_soc_component_update_bits(component, tx_reg0,
+ CDC_WSA_TX_SPKR_PROT_CLK_EN_MASK,
+ CDC_WSA_TX_SPKR_PROT_CLK_ENABLE);
+ snd_soc_component_update_bits(component, tx_reg1,
+ CDC_WSA_TX_SPKR_PROT_CLK_EN_MASK,
+ CDC_WSA_TX_SPKR_PROT_CLK_ENABLE);
+ snd_soc_component_update_bits(component, tx_reg0,
+ CDC_WSA_TX_SPKR_PROT_RESET_MASK,
+ CDC_WSA_TX_SPKR_PROT_NO_RESET);
+ snd_soc_component_update_bits(component, tx_reg1,
+ CDC_WSA_TX_SPKR_PROT_RESET_MASK,
+ CDC_WSA_TX_SPKR_PROT_NO_RESET);
+ } else {
+ snd_soc_component_update_bits(component, tx_reg0,
+ CDC_WSA_TX_SPKR_PROT_RESET_MASK,
+ CDC_WSA_TX_SPKR_PROT_RESET);
+ snd_soc_component_update_bits(component, tx_reg1,
+ CDC_WSA_TX_SPKR_PROT_RESET_MASK,
+ CDC_WSA_TX_SPKR_PROT_RESET);
+ snd_soc_component_update_bits(component, tx_reg0,
+ CDC_WSA_TX_SPKR_PROT_CLK_EN_MASK,
+ CDC_WSA_TX_SPKR_PROT_CLK_DISABLE);
+ snd_soc_component_update_bits(component, tx_reg1,
+ CDC_WSA_TX_SPKR_PROT_CLK_EN_MASK,
+ CDC_WSA_TX_SPKR_PROT_CLK_DISABLE);
+ }
+}
+
+static void wsa_macro_enable_disable_vi_feedback(struct snd_soc_component *component,
+ bool enable, u32 rate)
+{
+ struct wsa_macro *wsa = snd_soc_component_get_drvdata(component);
+
+ if (test_bit(WSA_MACRO_TX0, &wsa->active_ch_mask[WSA_MACRO_AIF_VI]))
+ wsa_macro_enable_disable_vi_sense(component, enable,
+ CDC_WSA_TX0_SPKR_PROT_PATH_CTL,
+ CDC_WSA_TX1_SPKR_PROT_PATH_CTL, rate);
+
+ if (test_bit(WSA_MACRO_TX1, &wsa->active_ch_mask[WSA_MACRO_AIF_VI]))
+ wsa_macro_enable_disable_vi_sense(component, enable,
+ CDC_WSA_TX2_SPKR_PROT_PATH_CTL,
+ CDC_WSA_TX3_SPKR_PROT_PATH_CTL, rate);
+}
+
static int wsa_macro_mclk_event(struct snd_soc_dapm_widget *w,
struct snd_kcontrol *kcontrol, int event)
{
@@ -1464,58 +1536,37 @@ static int wsa_macro_enable_vi_feedback(struct snd_soc_dapm_widget *w,
{
struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
struct wsa_macro *wsa = snd_soc_component_get_drvdata(component);
- u32 tx_reg0, tx_reg1;
+ u32 rate_val;
- if (test_bit(WSA_MACRO_TX0, &wsa->active_ch_mask[WSA_MACRO_AIF_VI])) {
- tx_reg0 = CDC_WSA_TX0_SPKR_PROT_PATH_CTL;
- tx_reg1 = CDC_WSA_TX1_SPKR_PROT_PATH_CTL;
- } else if (test_bit(WSA_MACRO_TX1, &wsa->active_ch_mask[WSA_MACRO_AIF_VI])) {
- tx_reg0 = CDC_WSA_TX2_SPKR_PROT_PATH_CTL;
- tx_reg1 = CDC_WSA_TX3_SPKR_PROT_PATH_CTL;
+ switch (wsa->pcm_rate_vi) {
+ case 8000:
+ rate_val = CDC_WSA_TX_SPKR_PROT_PCM_RATE_8K;
+ break;
+ case 16000:
+ rate_val = CDC_WSA_TX_SPKR_PROT_PCM_RATE_16K;
+ break;
+ case 24000:
+ rate_val = CDC_WSA_TX_SPKR_PROT_PCM_RATE_24K;
+ break;
+ case 32000:
+ rate_val = CDC_WSA_TX_SPKR_PROT_PCM_RATE_32K;
+ break;
+ case 48000:
+ rate_val = CDC_WSA_TX_SPKR_PROT_PCM_RATE_48K;
+ break;
+ default:
+ rate_val = CDC_WSA_TX_SPKR_PROT_PCM_RATE_8K;
+ break;
}
switch (event) {
case SND_SOC_DAPM_POST_PMU:
- /* Enable V&I sensing */
- snd_soc_component_update_bits(component, tx_reg0,
- CDC_WSA_TX_SPKR_PROT_RESET_MASK,
- CDC_WSA_TX_SPKR_PROT_RESET);
- snd_soc_component_update_bits(component, tx_reg1,
- CDC_WSA_TX_SPKR_PROT_RESET_MASK,
- CDC_WSA_TX_SPKR_PROT_RESET);
- snd_soc_component_update_bits(component, tx_reg0,
- CDC_WSA_TX_SPKR_PROT_PCM_RATE_MASK,
- CDC_WSA_TX_SPKR_PROT_PCM_RATE_8K);
- snd_soc_component_update_bits(component, tx_reg1,
- CDC_WSA_TX_SPKR_PROT_PCM_RATE_MASK,
- CDC_WSA_TX_SPKR_PROT_PCM_RATE_8K);
- snd_soc_component_update_bits(component, tx_reg0,
- CDC_WSA_TX_SPKR_PROT_CLK_EN_MASK,
- CDC_WSA_TX_SPKR_PROT_CLK_ENABLE);
- snd_soc_component_update_bits(component, tx_reg1,
- CDC_WSA_TX_SPKR_PROT_CLK_EN_MASK,
- CDC_WSA_TX_SPKR_PROT_CLK_ENABLE);
- snd_soc_component_update_bits(component, tx_reg0,
- CDC_WSA_TX_SPKR_PROT_RESET_MASK,
- CDC_WSA_TX_SPKR_PROT_NO_RESET);
- snd_soc_component_update_bits(component, tx_reg1,
- CDC_WSA_TX_SPKR_PROT_RESET_MASK,
- CDC_WSA_TX_SPKR_PROT_NO_RESET);
+ /* Enable V&I sensing */
+ wsa_macro_enable_disable_vi_feedback(component, true, rate_val);
break;
case SND_SOC_DAPM_POST_PMD:
/* Disable V&I sensing */
- snd_soc_component_update_bits(component, tx_reg0,
- CDC_WSA_TX_SPKR_PROT_RESET_MASK,
- CDC_WSA_TX_SPKR_PROT_RESET);
- snd_soc_component_update_bits(component, tx_reg1,
- CDC_WSA_TX_SPKR_PROT_RESET_MASK,
- CDC_WSA_TX_SPKR_PROT_RESET);
- snd_soc_component_update_bits(component, tx_reg0,
- CDC_WSA_TX_SPKR_PROT_CLK_EN_MASK,
- CDC_WSA_TX_SPKR_PROT_CLK_DISABLE);
- snd_soc_component_update_bits(component, tx_reg1,
- CDC_WSA_TX_SPKR_PROT_CLK_EN_MASK,
- CDC_WSA_TX_SPKR_PROT_CLK_DISABLE);
+ wsa_macro_enable_disable_vi_feedback(component, false, rate_val);
break;
}
diff --git a/sound/soc/dwc/dwc-i2s.c b/sound/soc/dwc/dwc-i2s.c
index 4c4171b..28001e9 100644
--- a/sound/soc/dwc/dwc-i2s.c
+++ b/sound/soc/dwc/dwc-i2s.c
@@ -199,12 +199,10 @@ static void i2s_start(struct dw_i2s_dev *dev,
else
i2s_write_reg(dev->i2s_base, IRER, 1);
- /* I2S needs to enable IRQ to make a handshake with DMAC on the JH7110 SoC */
- if (dev->use_pio || dev->is_jh7110)
- i2s_enable_irqs(dev, substream->stream, config->chan_nr);
- else
+ if (!(dev->use_pio || dev->is_jh7110))
i2s_enable_dma(dev, substream->stream);
+ i2s_enable_irqs(dev, substream->stream, config->chan_nr);
i2s_write_reg(dev->i2s_base, CER, 1);
}
@@ -218,11 +216,12 @@ static void i2s_stop(struct dw_i2s_dev *dev,
else
i2s_write_reg(dev->i2s_base, IRER, 0);
- if (dev->use_pio || dev->is_jh7110)
- i2s_disable_irqs(dev, substream->stream, 8);
- else
+ if (!(dev->use_pio || dev->is_jh7110))
i2s_disable_dma(dev, substream->stream);
+ i2s_disable_irqs(dev, substream->stream, 8);
+
+
if (!dev->active) {
i2s_write_reg(dev->i2s_base, CER, 0);
i2s_write_reg(dev->i2s_base, IER, 0);
diff --git a/sound/soc/fsl/fsl_asrc_dma.c b/sound/soc/fsl/fsl_asrc_dma.c
index f501f47..1bba483 100644
--- a/sound/soc/fsl/fsl_asrc_dma.c
+++ b/sound/soc/fsl/fsl_asrc_dma.c
@@ -156,11 +156,24 @@ static int fsl_asrc_dma_hw_params(struct snd_soc_component *component,
for_each_dpcm_be(rtd, stream, dpcm) {
struct snd_soc_pcm_runtime *be = dpcm->be;
struct snd_pcm_substream *substream_be;
- struct snd_soc_dai *dai = snd_soc_rtd_to_cpu(be, 0);
+ struct snd_soc_dai *dai_cpu = snd_soc_rtd_to_cpu(be, 0);
+ struct snd_soc_dai *dai_codec = snd_soc_rtd_to_codec(be, 0);
+ struct snd_soc_dai *dai;
if (dpcm->fe != rtd)
continue;
+ /*
+ * With audio graph card, original cpu dai is changed to codec
+ * device in backend, so if cpu dai is dummy device in backend,
+ * get the codec dai device, which is the real hardware device
+ * connected.
+ */
+ if (!snd_soc_dai_is_dummy(dai_cpu))
+ dai = dai_cpu;
+ else
+ dai = dai_codec;
+
substream_be = snd_soc_dpcm_get_substream(be, stream);
dma_params_be = snd_soc_dai_get_dma_data(dai, substream_be);
dev_be = dai->dev;
diff --git a/sound/soc/fsl/fsl_qmc_audio.c b/sound/soc/fsl/fsl_qmc_audio.c
index b297929..5614a8b 100644
--- a/sound/soc/fsl/fsl_qmc_audio.c
+++ b/sound/soc/fsl/fsl_qmc_audio.c
@@ -250,6 +250,9 @@ static int qmc_audio_pcm_trigger(struct snd_soc_component *component,
switch (cmd) {
case SNDRV_PCM_TRIGGER_START:
bitmap_zero(prtd->chans_pending, 64);
+ prtd->buffer_ended = 0;
+ prtd->ch_dma_addr_current = prtd->ch_dma_addr_start;
+
if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
for (i = 0; i < prtd->channels; i++)
prtd->qmc_dai->chans[i].prtd_tx = prtd;
diff --git a/sound/soc/fsl/imx-card.c b/sound/soc/fsl/imx-card.c
index 3686d46..45e000f 100644
--- a/sound/soc/fsl/imx-card.c
+++ b/sound/soc/fsl/imx-card.c
@@ -544,7 +544,7 @@ static int imx_card_parse_of(struct imx_card_data *data)
if (!card->dai_link)
return -ENOMEM;
- data->link_data = devm_kcalloc(dev, num_links, sizeof(*link), GFP_KERNEL);
+ data->link_data = devm_kcalloc(dev, num_links, sizeof(*link_data), GFP_KERNEL);
if (!data->link_data)
return -ENOMEM;
diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c
index a1ccc30..3ae2a21 100644
--- a/sound/soc/generic/simple-card-utils.c
+++ b/sound/soc/generic/simple-card-utils.c
@@ -1174,9 +1174,9 @@ void graph_util_parse_link_direction(struct device_node *np,
bool is_playback_only = of_property_read_bool(np, "playback-only");
bool is_capture_only = of_property_read_bool(np, "capture-only");
- if (is_playback_only)
+ if (playback_only)
*playback_only = is_playback_only;
- if (is_capture_only)
+ if (capture_only)
*capture_only = is_capture_only;
}
EXPORT_SYMBOL_GPL(graph_util_parse_link_direction);
diff --git a/sound/soc/intel/avs/path.c b/sound/soc/intel/avs/path.c
index ef0c1d1..cafb8c6 100644
--- a/sound/soc/intel/avs/path.c
+++ b/sound/soc/intel/avs/path.c
@@ -115,6 +115,78 @@ avs_path_find_variant(struct avs_dev *adev,
return NULL;
}
+static struct acpi_nhlt_config *
+avs_nhlt_config_or_default(struct avs_dev *adev, struct avs_tplg_module *t);
+
+int avs_path_set_constraint(struct avs_dev *adev, struct avs_tplg_path_template *template,
+ struct snd_pcm_hw_constraint_list *rate_list,
+ struct snd_pcm_hw_constraint_list *channels_list,
+ struct snd_pcm_hw_constraint_list *sample_bits_list)
+{
+ struct avs_tplg_path *path_template;
+ unsigned int *rlist, *clist, *slist;
+ size_t i;
+
+ i = 0;
+ list_for_each_entry(path_template, &template->path_list, node)
+ i++;
+
+ rlist = kcalloc(i, sizeof(rlist), GFP_KERNEL);
+ clist = kcalloc(i, sizeof(clist), GFP_KERNEL);
+ slist = kcalloc(i, sizeof(slist), GFP_KERNEL);
+
+ i = 0;
+ list_for_each_entry(path_template, &template->path_list, node) {
+ struct avs_tplg_pipeline *pipeline_template;
+
+ list_for_each_entry(pipeline_template, &path_template->ppl_list, node) {
+ struct avs_tplg_module *module_template;
+
+ list_for_each_entry(module_template, &pipeline_template->mod_list, node) {
+ const guid_t *type = &module_template->cfg_ext->type;
+ struct acpi_nhlt_config *blob;
+
+ if (!guid_equal(type, &AVS_COPIER_MOD_UUID) &&
+ !guid_equal(type, &AVS_WOVHOSTM_MOD_UUID))
+ continue;
+
+ switch (module_template->cfg_ext->copier.dma_type) {
+ case AVS_DMA_DMIC_LINK_INPUT:
+ case AVS_DMA_I2S_LINK_OUTPUT:
+ case AVS_DMA_I2S_LINK_INPUT:
+ break;
+ default:
+ continue;
+ }
+
+ blob = avs_nhlt_config_or_default(adev, module_template);
+ if (IS_ERR(blob))
+ continue;
+
+ rlist[i] = path_template->fe_fmt->sampling_freq;
+ clist[i] = path_template->fe_fmt->num_channels;
+ slist[i] = path_template->fe_fmt->bit_depth;
+ i++;
+ }
+ }
+ }
+
+ if (i) {
+ rate_list->count = i;
+ rate_list->list = rlist;
+ channels_list->count = i;
+ channels_list->list = clist;
+ sample_bits_list->count = i;
+ sample_bits_list->list = slist;
+ } else {
+ kfree(rlist);
+ kfree(clist);
+ kfree(slist);
+ }
+
+ return i;
+}
+
static void avs_init_node_id(union avs_connector_node_id *node_id,
struct avs_tplg_modcfg_ext *te, u32 dma_id)
{
diff --git a/sound/soc/intel/avs/path.h b/sound/soc/intel/avs/path.h
index 7ed7e94..c65ed84 100644
--- a/sound/soc/intel/avs/path.h
+++ b/sound/soc/intel/avs/path.h
@@ -69,6 +69,11 @@ int avs_path_reset(struct avs_path *path);
int avs_path_pause(struct avs_path *path);
int avs_path_run(struct avs_path *path, int trigger);
+int avs_path_set_constraint(struct avs_dev *adev, struct avs_tplg_path_template *template,
+ struct snd_pcm_hw_constraint_list *rate_list,
+ struct snd_pcm_hw_constraint_list *channels_list,
+ struct snd_pcm_hw_constraint_list *sample_bits_list);
+
int avs_peakvol_set_volume(struct avs_dev *adev, struct avs_path_module *mod,
struct soc_mixer_control *mc, long *input);
int avs_peakvol_set_mute(struct avs_dev *adev, struct avs_path_module *mod,
diff --git a/sound/soc/intel/avs/pcm.c b/sound/soc/intel/avs/pcm.c
index dac4633..d83ef50 100644
--- a/sound/soc/intel/avs/pcm.c
+++ b/sound/soc/intel/avs/pcm.c
@@ -31,6 +31,10 @@ struct avs_dma_data {
struct hdac_ext_stream *host_stream;
};
+ struct snd_pcm_hw_constraint_list rate_list;
+ struct snd_pcm_hw_constraint_list channels_list;
+ struct snd_pcm_hw_constraint_list sample_bits_list;
+
struct work_struct period_elapsed_work;
struct snd_pcm_substream *substream;
};
@@ -74,6 +78,45 @@ void avs_period_elapsed(struct snd_pcm_substream *substream)
schedule_work(&data->period_elapsed_work);
}
+static int hw_rule_param_size(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule);
+static int avs_hw_constraints_init(struct snd_pcm_substream *substream, struct snd_soc_dai *dai)
+{
+ struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream);
+ struct snd_pcm_runtime *runtime = substream->runtime;
+ struct snd_pcm_hw_constraint_list *r, *c, *s;
+ struct avs_tplg_path_template *template;
+ struct avs_dma_data *data;
+ int ret;
+
+ ret = snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS);
+ if (ret < 0)
+ return ret;
+
+ data = snd_soc_dai_get_dma_data(dai, substream);
+ r = &(data->rate_list);
+ c = &(data->channels_list);
+ s = &(data->sample_bits_list);
+
+ template = avs_dai_find_path_template(dai, !rtd->dai_link->no_pcm, substream->stream);
+ ret = avs_path_set_constraint(data->adev, template, r, c, s);
+ if (ret <= 0)
+ return ret;
+
+ ret = snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_RATE, r);
+ if (ret < 0)
+ return ret;
+
+ ret = snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS, c);
+ if (ret < 0)
+ return ret;
+
+ ret = snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_SAMPLE_BITS, s);
+ if (ret < 0)
+ return ret;
+
+ return 0;
+}
+
static int avs_dai_startup(struct snd_pcm_substream *substream, struct snd_soc_dai *dai)
{
struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream);
@@ -101,7 +144,7 @@ static int avs_dai_startup(struct snd_pcm_substream *substream, struct snd_soc_d
if (rtd->dai_link->ignore_suspend)
adev->num_lp_paths++;
- return 0;
+ return avs_hw_constraints_init(substream, dai);
}
static void avs_dai_shutdown(struct snd_pcm_substream *substream, struct snd_soc_dai *dai)
@@ -114,6 +157,10 @@ static void avs_dai_shutdown(struct snd_pcm_substream *substream, struct snd_soc
if (rtd->dai_link->ignore_suspend)
data->adev->num_lp_paths--;
+ kfree(data->rate_list.list);
+ kfree(data->channels_list.list);
+ kfree(data->sample_bits_list.list);
+
snd_soc_dai_set_dma_data(dai, substream, NULL);
kfree(data);
}
@@ -927,7 +974,8 @@ static int avs_component_probe(struct snd_soc_component *component)
else
mach->tplg_filename = devm_kasprintf(adev->dev, GFP_KERNEL,
"hda-generic-tplg.bin");
-
+ if (!mach->tplg_filename)
+ return -ENOMEM;
filename = kasprintf(GFP_KERNEL, "%s/%s", component->driver->topology_name_prefix,
mach->tplg_filename);
if (!filename)
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 6446cda..0f3b8f4 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -576,6 +576,19 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
BYT_RT5640_SSP0_AIF2 |
BYT_RT5640_MCLK_EN),
},
+ { /* Acer Aspire SW3-013 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Aspire SW3-013"),
+ },
+ .driver_data = (void *)(BYT_RT5640_DMIC1_MAP |
+ BYT_RT5640_JD_SRC_JD2_IN4N |
+ BYT_RT5640_OVCD_TH_2000UA |
+ BYT_RT5640_OVCD_SF_0P75 |
+ BYT_RT5640_DIFF_MIC |
+ BYT_RT5640_SSP0_AIF1 |
+ BYT_RT5640_MCLK_EN),
+ },
{
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c
index 90dafa8..095d08b 100644
--- a/sound/soc/intel/boards/sof_sdw.c
+++ b/sound/soc/intel/boards/sof_sdw.c
@@ -764,6 +764,7 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = {
static const struct snd_pci_quirk sof_sdw_ssid_quirk_table[] = {
SND_PCI_QUIRK(0x1043, 0x1e13, "ASUS Zenbook S14", SOC_SDW_CODEC_MIC),
+ SND_PCI_QUIRK(0x1043, 0x1f43, "ASUS Zenbook S16", SOC_SDW_CODEC_MIC),
{}
};
diff --git a/sound/soc/intel/catpt/dsp.c b/sound/soc/intel/catpt/dsp.c
index 5993819..008a20a 100644
--- a/sound/soc/intel/catpt/dsp.c
+++ b/sound/soc/intel/catpt/dsp.c
@@ -156,7 +156,7 @@ static void catpt_dsp_set_srampge(struct catpt_dev *cdev, struct resource *sram,
{
unsigned long old;
u32 off = sram->start;
- u32 b = __ffs(mask);
+ unsigned long b = __ffs(mask);
old = catpt_readl_pci(cdev, VDRTCTL0) & mask;
dev_dbg(cdev->dev, "SRAMPGE [0x%08lx] 0x%08lx -> 0x%08lx",
diff --git a/sound/soc/intel/common/soc-acpi-intel-ptl-match.c b/sound/soc/intel/common/soc-acpi-intel-ptl-match.c
index 6603d8de..c599eb43 100644
--- a/sound/soc/intel/common/soc-acpi-intel-ptl-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-ptl-match.c
@@ -431,7 +431,8 @@ static const struct snd_soc_acpi_link_adr ptl_cs42l43_l3[] = {
.mask = BIT(3),
.num_adr = ARRAY_SIZE(cs42l43_3_adr),
.adr_d = cs42l43_3_adr,
- }
+ },
+ {}
};
static const struct snd_soc_acpi_link_adr ptl_rt722_only[] = {
diff --git a/sound/soc/qcom/lpass.h b/sound/soc/qcom/lpass.h
index 27a2bf9..de3ec6f 100644
--- a/sound/soc/qcom/lpass.h
+++ b/sound/soc/qcom/lpass.h
@@ -13,10 +13,11 @@
#include <linux/platform_device.h>
#include <linux/regmap.h>
#include <dt-bindings/sound/qcom,lpass.h>
+#include <dt-bindings/sound/qcom,q6afe.h>
#include "lpass-hdmi.h"
#define LPASS_AHBIX_CLOCK_FREQUENCY 131072000
-#define LPASS_MAX_PORTS (LPASS_CDC_DMA_VA_TX8 + 1)
+#define LPASS_MAX_PORTS (DISPLAY_PORT_RX_7 + 1)
#define LPASS_MAX_MI2S_PORTS (8)
#define LPASS_MAX_DMA_CHANNELS (8)
#define LPASS_MAX_HDMI_DMA_CHANNELS (4)
diff --git a/sound/soc/renesas/rz-ssi.c b/sound/soc/renesas/rz-ssi.c
index 3a0af4c..0f7458a 100644
--- a/sound/soc/renesas/rz-ssi.c
+++ b/sound/soc/renesas/rz-ssi.c
@@ -1244,7 +1244,7 @@ static int rz_ssi_runtime_resume(struct device *dev)
static const struct dev_pm_ops rz_ssi_pm_ops = {
RUNTIME_PM_OPS(rz_ssi_runtime_suspend, rz_ssi_runtime_resume, NULL)
- SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
+ NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
};
static struct platform_driver rz_ssi_driver = {
diff --git a/sound/soc/sdw_utils/soc_sdw_bridge_cs35l56.c b/sound/soc/sdw_utils/soc_sdw_bridge_cs35l56.c
index 246e5c2..c7e55f4 100644
--- a/sound/soc/sdw_utils/soc_sdw_bridge_cs35l56.c
+++ b/sound/soc/sdw_utils/soc_sdw_bridge_cs35l56.c
@@ -60,6 +60,10 @@ static int asoc_sdw_bridge_cs35l56_asp_init(struct snd_soc_pcm_runtime *rtd)
/* 4 x 16-bit sample slots and FSYNC=48000, BCLK=3.072 MHz */
for_each_rtd_codec_dais(rtd, i, codec_dai) {
+ ret = asoc_sdw_cs35l56_volume_limit(card, codec_dai->component->name_prefix);
+ if (ret)
+ return ret;
+
ret = snd_soc_dai_set_tdm_slot(codec_dai, tx_mask, rx_mask, 4, 16);
if (ret < 0)
return ret;
diff --git a/sound/soc/sdw_utils/soc_sdw_cs42l43.c b/sound/soc/sdw_utils/soc_sdw_cs42l43.c
index 668c9d2..b415d45 100644
--- a/sound/soc/sdw_utils/soc_sdw_cs42l43.c
+++ b/sound/soc/sdw_utils/soc_sdw_cs42l43.c
@@ -20,6 +20,8 @@
#include <sound/soc-dapm.h>
#include <sound/soc_sdw_utils.h>
+#define CS42L43_SPK_VOLUME_0DB 128 /* 0dB Max */
+
static const struct snd_soc_dapm_route cs42l43_hs_map[] = {
{ "Headphone", NULL, "cs42l43 AMP3_OUT" },
{ "Headphone", NULL, "cs42l43 AMP4_OUT" },
@@ -117,6 +119,14 @@ int asoc_sdw_cs42l43_spk_rtd_init(struct snd_soc_pcm_runtime *rtd, struct snd_so
return -ENOMEM;
}
+ ret = snd_soc_limit_volume(card, "cs42l43 Speaker Digital Volume",
+ CS42L43_SPK_VOLUME_0DB);
+ if (ret)
+ dev_err(card->dev, "cs42l43 speaker volume limit failed: %d\n", ret);
+ else
+ dev_info(card->dev, "Setting CS42L43 Speaker volume limit to %d\n",
+ CS42L43_SPK_VOLUME_0DB);
+
ret = snd_soc_dapm_add_routes(&card->dapm, cs42l43_spk_map,
ARRAY_SIZE(cs42l43_spk_map));
if (ret)
diff --git a/sound/soc/sdw_utils/soc_sdw_cs_amp.c b/sound/soc/sdw_utils/soc_sdw_cs_amp.c
index 4b6181cf..35b550b 100644
--- a/sound/soc/sdw_utils/soc_sdw_cs_amp.c
+++ b/sound/soc/sdw_utils/soc_sdw_cs_amp.c
@@ -16,6 +16,25 @@
#define CODEC_NAME_SIZE 8
#define CS_AMP_CHANNELS_PER_AMP 4
+#define CS35L56_SPK_VOLUME_0DB 400 /* 0dB Max */
+
+int asoc_sdw_cs35l56_volume_limit(struct snd_soc_card *card, const char *name_prefix)
+{
+ char *volume_ctl_name;
+ int ret;
+
+ volume_ctl_name = kasprintf(GFP_KERNEL, "%s Speaker Volume", name_prefix);
+ if (!volume_ctl_name)
+ return -ENOMEM;
+
+ ret = snd_soc_limit_volume(card, volume_ctl_name, CS35L56_SPK_VOLUME_0DB);
+ if (ret)
+ dev_err(card->dev, "%s limit set failed: %d\n", volume_ctl_name, ret);
+
+ kfree(volume_ctl_name);
+ return ret;
+}
+EXPORT_SYMBOL_NS(asoc_sdw_cs35l56_volume_limit, "SND_SOC_SDW_UTILS");
int asoc_sdw_cs_spk_rtd_init(struct snd_soc_pcm_runtime *rtd, struct snd_soc_dai *dai)
{
@@ -40,6 +59,11 @@ int asoc_sdw_cs_spk_rtd_init(struct snd_soc_pcm_runtime *rtd, struct snd_soc_dai
snprintf(widget_name, sizeof(widget_name), "%s SPK",
codec_dai->component->name_prefix);
+
+ ret = asoc_sdw_cs35l56_volume_limit(card, codec_dai->component->name_prefix);
+ if (ret)
+ return ret;
+
ret = snd_soc_dapm_add_routes(&card->dapm, &route, 1);
if (ret)
return ret;
diff --git a/sound/soc/sdw_utils/soc_sdw_rt_dmic.c b/sound/soc/sdw_utils/soc_sdw_rt_dmic.c
index 46d917a..97be110 100644
--- a/sound/soc/sdw_utils/soc_sdw_rt_dmic.c
+++ b/sound/soc/sdw_utils/soc_sdw_rt_dmic.c
@@ -29,6 +29,8 @@ int asoc_sdw_rt_dmic_rtd_init(struct snd_soc_pcm_runtime *rtd, struct snd_soc_da
mic_name = devm_kasprintf(card->dev, GFP_KERNEL, "rt715-sdca");
else
mic_name = devm_kasprintf(card->dev, GFP_KERNEL, "%s", component->name_prefix);
+ if (!mic_name)
+ return -ENOMEM;
card->components = devm_kasprintf(card->dev, GFP_KERNEL,
"%s mic:%s", card->components,
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 4308a6c..4383519 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1584,10 +1584,13 @@ int dpcm_add_paths(struct snd_soc_pcm_runtime *fe, int stream,
/*
* Filter for systems with 'component_chaining' enabled.
* This helps to avoid unnecessary re-configuration of an
- * already active BE on such systems.
+ * already active BE on such systems and ensures the BE DAI
+ * widget is powered ON after hw_params() BE DAI callback.
*/
if (fe->card->component_chaining &&
(be->dpcm[stream].state != SND_SOC_DPCM_STATE_NEW) &&
+ (be->dpcm[stream].state != SND_SOC_DPCM_STATE_OPEN) &&
+ (be->dpcm[stream].state != SND_SOC_DPCM_STATE_HW_PARAMS) &&
(be->dpcm[stream].state != SND_SOC_DPCM_STATE_CLOSE))
continue;
diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c
index e8c1abf..bf5299b 100644
--- a/sound/soc/stm/stm32_sai_sub.c
+++ b/sound/soc/stm/stm32_sai_sub.c
@@ -409,11 +409,11 @@ static int stm32_sai_set_parent_rate(struct stm32_sai_sub_data *sai,
unsigned int rate)
{
struct platform_device *pdev = sai->pdev;
- unsigned int sai_ck_rate, sai_ck_max_rate, sai_curr_rate, sai_new_rate;
+ unsigned int sai_ck_rate, sai_ck_max_rate, sai_ck_min_rate, sai_curr_rate, sai_new_rate;
int div, ret;
/*
- * Set maximum expected kernel clock frequency
+ * Set minimum and maximum expected kernel clock frequency
* - mclk on or spdif:
* f_sai_ck = MCKDIV * mclk-fs * fs
* Here typical 256 ratio is assumed for mclk-fs
@@ -423,13 +423,16 @@ static int stm32_sai_set_parent_rate(struct stm32_sai_sub_data *sai,
* Set constraint MCKDIV * FRL <= 256, to ensure MCKDIV is in available range
* f_sai_ck = sai_ck_max_rate * pow_of_two(FRL) / 256
*/
+ sai_ck_min_rate = rate * 256;
if (!(rate % SAI_RATE_11K))
sai_ck_max_rate = SAI_MAX_SAMPLE_RATE_11K * 256;
else
sai_ck_max_rate = SAI_MAX_SAMPLE_RATE_8K * 256;
- if (!sai->sai_mclk && !STM_SAI_PROTOCOL_IS_SPDIF(sai))
+ if (!sai->sai_mclk && !STM_SAI_PROTOCOL_IS_SPDIF(sai)) {
+ sai_ck_min_rate = rate * sai->fs_length;
sai_ck_max_rate /= DIV_ROUND_CLOSEST(256, roundup_pow_of_two(sai->fs_length));
+ }
/*
* Request exclusivity, as the clock is shared by SAI sub-blocks and by
@@ -444,7 +447,10 @@ static int stm32_sai_set_parent_rate(struct stm32_sai_sub_data *sai,
* return immediately.
*/
sai_curr_rate = clk_get_rate(sai->sai_ck);
- if (stm32_sai_rate_accurate(sai_ck_max_rate, sai_curr_rate))
+ dev_dbg(&pdev->dev, "kernel clock rate: min [%u], max [%u], current [%u]",
+ sai_ck_min_rate, sai_ck_max_rate, sai_curr_rate);
+ if (stm32_sai_rate_accurate(sai_ck_max_rate, sai_curr_rate) &&
+ sai_curr_rate >= sai_ck_min_rate)
return 0;
/*
@@ -472,7 +478,7 @@ static int stm32_sai_set_parent_rate(struct stm32_sai_sub_data *sai,
/* Try a lower frequency */
div++;
sai_ck_rate = sai_ck_max_rate / div;
- } while (sai_ck_rate > rate);
+ } while (sai_ck_rate >= sai_ck_min_rate);
/* No accurate rate found */
dev_err(&pdev->dev, "Failed to find an accurate rate");
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index a29f28e..f36ec98 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -926,6 +926,8 @@ static int endpoint_set_interface(struct snd_usb_audio *chip,
{
int altset = set ? ep->altsetting : 0;
int err;
+ int retries = 0;
+ const int max_retries = 5;
if (ep->iface_ref->altset == altset)
return 0;
@@ -935,8 +937,13 @@ static int endpoint_set_interface(struct snd_usb_audio *chip,
usb_audio_dbg(chip, "Setting usb interface %d:%d for EP 0x%x\n",
ep->iface, altset, ep->ep_num);
+retry:
err = usb_set_interface(chip->dev, ep->iface, altset);
if (err < 0) {
+ if (err == -EPROTO && ++retries <= max_retries) {
+ msleep(5 * (1 << (retries - 1)));
+ goto retry;
+ }
usb_audio_err_ratelimited(
chip, "%d:%d: usb_set_interface failed (%d)\n",
ep->iface, altset, err);
diff --git a/sound/usb/format.c b/sound/usb/format.c
index 9d32b21..0ba4641 100644
--- a/sound/usb/format.c
+++ b/sound/usb/format.c
@@ -260,7 +260,8 @@ static int parse_audio_format_rates_v1(struct snd_usb_audio *chip, struct audiof
}
/* Jabra Evolve 65 headset */
- if (chip->usb_id == USB_ID(0x0b0e, 0x030b)) {
+ if (chip->usb_id == USB_ID(0x0b0e, 0x030b) ||
+ chip->usb_id == USB_ID(0x0b0e, 0x030c)) {
/* only 48kHz for playback while keeping 16kHz for capture */
if (fp->nr_rates != 1)
return set_fixed_rate(fp, 48000, SNDRV_PCM_RATE_48000);
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index dcdd7e9..cfed000 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -1885,10 +1885,18 @@ static void snd_usbmidi_init_substream(struct snd_usb_midi *umidi,
}
port_info = find_port_info(umidi, number);
- name_format = port_info ? port_info->name :
- (jack_name != default_jack_name ? "%s %s" : "%s %s %d");
- snprintf(substream->name, sizeof(substream->name),
- name_format, umidi->card->shortname, jack_name, number + 1);
+ if (port_info || jack_name == default_jack_name ||
+ strncmp(umidi->card->shortname, jack_name, strlen(umidi->card->shortname)) != 0) {
+ name_format = port_info ? port_info->name :
+ (jack_name != default_jack_name ? "%s %s" : "%s %s %d");
+ snprintf(substream->name, sizeof(substream->name),
+ name_format, umidi->card->shortname, jack_name, number + 1);
+ } else {
+ /* The manufacturer included the iProduct name in the jack
+ * name, do not use both
+ */
+ strscpy(substream->name, jack_name);
+ }
*rsubstream = substream;
}
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 6d44f8c..af9d9ac 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -43,9 +43,6 @@
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
#define KVM_DIRTY_LOG_PAGE_OFFSET 64
-#define KVM_REG_SIZE(id) \
- (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
-
struct kvm_regs {
struct user_pt_regs regs; /* sp = sp_el0 */
@@ -108,6 +105,7 @@ struct kvm_regs {
#define KVM_ARM_VCPU_PTRAUTH_ADDRESS 5 /* VCPU uses address authentication */
#define KVM_ARM_VCPU_PTRAUTH_GENERIC 6 /* VCPU uses generic authentication */
#define KVM_ARM_VCPU_HAS_EL2 7 /* Support nested virtualization */
+#define KVM_ARM_VCPU_HAS_EL2_E2H0 8 /* Limit NV support to E2H RES0 */
struct kvm_vcpu_init {
__u32 target;
@@ -418,6 +416,7 @@ enum {
#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7
#define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8
+#define KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ 9
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
(0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
index 9306726..df36f23 100644
--- a/tools/arch/arm64/include/uapi/asm/unistd.h
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -1,24 +1,2 @@
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#define __ARCH_WANT_RENAMEAT
-#define __ARCH_WANT_NEW_STAT
-#define __ARCH_WANT_SET_GET_RLIMIT
-#define __ARCH_WANT_TIME32_SYSCALLS
-#define __ARCH_WANT_MEMFD_SECRET
-
-#include <asm-generic/unistd.h>
+#include <asm/unistd_64.h>
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 9e3fa79..6c2c152 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -75,8 +75,8 @@
#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */
#define X86_FEATURE_K8 ( 3*32+ 4) /* Opteron, Athlon64 */
#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* CPU based on Zen5 microarchitecture */
-#define X86_FEATURE_P3 ( 3*32+ 6) /* P3 */
-#define X86_FEATURE_P4 ( 3*32+ 7) /* P4 */
+/* Free ( 3*32+ 6) */
+/* Free ( 3*32+ 7) */
#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* "constant_tsc" TSC ticks at a constant rate */
#define X86_FEATURE_UP ( 3*32+ 9) /* "up" SMP kernel running on UP */
#define X86_FEATURE_ART ( 3*32+10) /* "art" Always running timer (ART) */
@@ -329,6 +329,7 @@
#define X86_FEATURE_CLZERO (13*32+ 0) /* "clzero" CLZERO instruction */
#define X86_FEATURE_IRPERF (13*32+ 1) /* "irperf" Instructions Retired Count */
#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* "xsaveerptr" Always save/restore FP error pointers */
+#define X86_FEATURE_INVLPGB (13*32+ 3) /* INVLPGB and TLBSYNC instructions supported */
#define X86_FEATURE_RDPRU (13*32+ 4) /* "rdpru" Read processor register at user level */
#define X86_FEATURE_WBNOINVD (13*32+ 9) /* "wbnoinvd" WBNOINVD instruction */
#define X86_FEATURE_AMD_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */
@@ -377,6 +378,7 @@
#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* "v_spec_ctrl" Virtual SPEC_CTRL */
#define X86_FEATURE_VNMI (15*32+25) /* "vnmi" Virtual NMI */
#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* SVME addr check */
+#define X86_FEATURE_IDLE_HLT (15*32+30) /* IDLE HLT intercept */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* "avx512vbmi" AVX512 Vector Bit Manipulation instructions*/
@@ -434,15 +436,18 @@
#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* Speculative Store Bypass Disable */
/* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */
-#define X86_FEATURE_SME (19*32+ 0) /* "sme" AMD Secure Memory Encryption */
-#define X86_FEATURE_SEV (19*32+ 1) /* "sev" AMD Secure Encrypted Virtualization */
+#define X86_FEATURE_SME (19*32+ 0) /* "sme" Secure Memory Encryption */
+#define X86_FEATURE_SEV (19*32+ 1) /* "sev" Secure Encrypted Virtualization */
#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* VM Page Flush MSR is supported */
-#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" AMD Secure Encrypted Virtualization - Encrypted State */
-#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" AMD Secure Encrypted Virtualization - Secure Nested Paging */
+#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" Secure Encrypted Virtualization - Encrypted State */
+#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" Secure Encrypted Virtualization - Secure Nested Paging */
#define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* Virtual TSC_AUX */
-#define X86_FEATURE_SME_COHERENT (19*32+10) /* AMD hardware-enforced cache coherency */
-#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" AMD SEV-ES full debug state swap support */
+#define X86_FEATURE_SME_COHERENT (19*32+10) /* hardware-enforced cache coherency */
+#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" SEV-ES full debug state swap support */
+#define X86_FEATURE_RMPREAD (19*32+21) /* RMPREAD instruction */
+#define X86_FEATURE_SEGMENTED_RMP (19*32+23) /* Segmented RMP support */
#define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */
+#define X86_FEATURE_HV_INUSE_WR_ALLOWED (19*32+30) /* Allow Write to in-use hypervisor-owned pages */
/* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */
@@ -455,6 +460,11 @@
#define X86_FEATURE_SBPB (20*32+27) /* Selective Branch Prediction Barrier */
#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */
#define X86_FEATURE_SRSO_NO (20*32+29) /* CPU is not affected by SRSO */
+#define X86_FEATURE_SRSO_USER_KERNEL_NO (20*32+30) /* CPU is not affected by SRSO across user/kernel boundaries */
+#define X86_FEATURE_SRSO_BP_SPEC_REDUCE (20*32+31) /*
+ * BP_CFG[BpSpecReduce] can be used to mitigate SRSO for VMs.
+ * (SRSO_MSR_FIX in the official doc).
+ */
/*
* Extended auxiliary flags: Linux defined - for features scattered in various
@@ -470,6 +480,7 @@
#define X86_FEATURE_AMD_FAST_CPPC (21*32 + 5) /* Fast CPPC */
#define X86_FEATURE_AMD_HETEROGENEOUS_CORES (21*32 + 6) /* Heterogeneous Core Topology */
#define X86_FEATURE_AMD_WORKLOAD_CLASS (21*32 + 7) /* Workload Classification */
+#define X86_FEATURE_PREFER_YMM (21*32 + 8) /* Avoid ZMM registers due to downclocking */
/*
* BUG word(s)
@@ -521,4 +532,5 @@
#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */
#define X86_BUG_BHI X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */
#define X86_BUG_IBPB_NO_RET X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */
+#define X86_BUG_SPECTRE_V2_USER X86_BUG(1*32 + 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index dc1c105..e6134ef2 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -397,7 +397,8 @@
#define MSR_IA32_PASID_VALID BIT_ULL(31)
/* DEBUGCTLMSR bits (others vary by model): */
-#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */
+#define DEBUGCTLMSR_LBR_BIT 0 /* last branch recording */
+#define DEBUGCTLMSR_LBR (1UL << DEBUGCTLMSR_LBR_BIT)
#define DEBUGCTLMSR_BTF_SHIFT 1
#define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */
#define DEBUGCTLMSR_BUS_LOCK_DETECT (1UL << 2)
@@ -610,6 +611,7 @@
#define MSR_AMD_PERF_CTL 0xc0010062
#define MSR_AMD_PERF_STATUS 0xc0010063
#define MSR_AMD_PSTATE_DEF_BASE 0xc0010064
+#define MSR_AMD64_GUEST_TSC_FREQ 0xc0010134
#define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140
#define MSR_AMD64_OSVW_STATUS 0xc0010141
#define MSR_AMD_PPIN_CTL 0xc00102f0
@@ -646,6 +648,7 @@
#define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */
#define MSR_AMD64_SVM_AVIC_DOORBELL 0xc001011b
#define MSR_AMD64_VM_PAGE_FLUSH 0xc001011e
+#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f
#define MSR_AMD64_SEV_ES_GHCB 0xc0010130
#define MSR_AMD64_SEV 0xc0010131
#define MSR_AMD64_SEV_ENABLED_BIT 0
@@ -684,11 +687,12 @@
#define MSR_AMD64_SNP_SMT_PROT BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT)
#define MSR_AMD64_SNP_RESV_BIT 18
#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT)
-
-#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f
-
#define MSR_AMD64_RMP_BASE 0xc0010132
#define MSR_AMD64_RMP_END 0xc0010133
+#define MSR_AMD64_RMP_CFG 0xc0010136
+#define MSR_AMD64_SEG_RMP_ENABLED_BIT 0
+#define MSR_AMD64_SEG_RMP_ENABLED BIT_ULL(MSR_AMD64_SEG_RMP_ENABLED_BIT)
+#define MSR_AMD64_RMP_SEGMENT_SHIFT(x) (((x) & GENMASK_ULL(13, 8)) >> 8)
#define MSR_SVSM_CAA 0xc001f000
@@ -699,15 +703,17 @@
#define MSR_AMD_CPPC_REQ 0xc00102b3
#define MSR_AMD_CPPC_STATUS 0xc00102b4
-#define AMD_CPPC_LOWEST_PERF(x) (((x) >> 0) & 0xff)
-#define AMD_CPPC_LOWNONLIN_PERF(x) (((x) >> 8) & 0xff)
-#define AMD_CPPC_NOMINAL_PERF(x) (((x) >> 16) & 0xff)
-#define AMD_CPPC_HIGHEST_PERF(x) (((x) >> 24) & 0xff)
+/* Masks for use with MSR_AMD_CPPC_CAP1 */
+#define AMD_CPPC_LOWEST_PERF_MASK GENMASK(7, 0)
+#define AMD_CPPC_LOWNONLIN_PERF_MASK GENMASK(15, 8)
+#define AMD_CPPC_NOMINAL_PERF_MASK GENMASK(23, 16)
+#define AMD_CPPC_HIGHEST_PERF_MASK GENMASK(31, 24)
-#define AMD_CPPC_MAX_PERF(x) (((x) & 0xff) << 0)
-#define AMD_CPPC_MIN_PERF(x) (((x) & 0xff) << 8)
-#define AMD_CPPC_DES_PERF(x) (((x) & 0xff) << 16)
-#define AMD_CPPC_ENERGY_PERF_PREF(x) (((x) & 0xff) << 24)
+/* Masks for use with MSR_AMD_CPPC_REQ */
+#define AMD_CPPC_MAX_PERF_MASK GENMASK(7, 0)
+#define AMD_CPPC_MIN_PERF_MASK GENMASK(15, 8)
+#define AMD_CPPC_DES_PERF_MASK GENMASK(23, 16)
+#define AMD_CPPC_EPP_PERF_MASK GENMASK(31, 24)
/* AMD Performance Counter Global Status and Control MSRs */
#define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS 0xc0000300
@@ -719,6 +725,7 @@
/* Zen4 */
#define MSR_ZEN4_BP_CFG 0xc001102e
+#define MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT 4
#define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5
/* Fam 19h MSRs */
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 88585c1..460306b 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -559,6 +559,9 @@ struct kvm_x86_mce {
#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7)
#define KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA (1 << 8)
+#define KVM_XEN_MSR_MIN_INDEX 0x40000000u
+#define KVM_XEN_MSR_MAX_INDEX 0x4fffffffu
+
struct kvm_xen_hvm_config {
__u32 flags;
__u32 msr;
@@ -925,5 +928,6 @@ struct kvm_hyperv_eventfd {
#define KVM_X86_SEV_VM 2
#define KVM_X86_SEV_ES_VM 3
#define KVM_X86_SNP_VM 4
+#define KVM_X86_TDX_VM 5
#endif /* _ASM_X86_KVM_H */
diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h
index 1814b41..ec13212 100644
--- a/tools/arch/x86/include/uapi/asm/svm.h
+++ b/tools/arch/x86/include/uapi/asm/svm.h
@@ -95,6 +95,7 @@
#define SVM_EXIT_CR14_WRITE_TRAP 0x09e
#define SVM_EXIT_CR15_WRITE_TRAP 0x09f
#define SVM_EXIT_INVPCID 0x0a2
+#define SVM_EXIT_IDLE_HLT 0x0a6
#define SVM_EXIT_NPF 0x400
#define SVM_EXIT_AVIC_INCOMPLETE_IPI 0x401
#define SVM_EXIT_AVIC_UNACCELERATED_ACCESS 0x402
@@ -224,6 +225,7 @@
{ SVM_EXIT_CR4_WRITE_TRAP, "write_cr4_trap" }, \
{ SVM_EXIT_CR8_WRITE_TRAP, "write_cr8_trap" }, \
{ SVM_EXIT_INVPCID, "invpcid" }, \
+ { SVM_EXIT_IDLE_HLT, "idle-halt" }, \
{ SVM_EXIT_NPF, "npf" }, \
{ SVM_EXIT_AVIC_INCOMPLETE_IPI, "avic_incomplete_ipi" }, \
{ SVM_EXIT_AVIC_UNACCELERATED_ACCESS, "avic_unaccelerated_access" }, \
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index 0199d56..d66b710 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -3,6 +3,7 @@
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
@@ -28,7 +29,7 @@
* only for the return value that is the same as the source input,
* which the compiler could/should do much better anyway.
*/
-SYM_FUNC_START(__memset)
+SYM_TYPED_FUNC_START(__memset)
ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS
movq %rdi,%r9
diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt
index caedb3e..f5dd84e 100644
--- a/tools/arch/x86/lib/x86-opcode-map.txt
+++ b/tools/arch/x86/lib/x86-opcode-map.txt
@@ -996,8 +996,8 @@
83: Grp1 Ev,Ib (1A),(es)
# CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL,
# CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ
-84: CTESTSCC (ev)
-85: CTESTSCC (es) | CTESTSCC (66),(es)
+84: CTESTSCC Eb,Gb (ev)
+85: CTESTSCC Ev,Gv (es) | CTESTSCC Ev,Gv (66),(es)
88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es)
8f: POP2 Bq,Rq (000),(11B),(ev)
a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es)
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index 04ba035..b9ce3aa 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -24,6 +24,7 @@
#include <sys/poll.h>
#include <sys/utsname.h>
+#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
@@ -677,6 +678,88 @@ static void kvp_process_ipconfig_file(char *cmd,
pclose(file);
}
+static bool kvp_verify_ip_address(const void *address_string)
+{
+ char verify_buf[sizeof(struct in6_addr)];
+
+ if (inet_pton(AF_INET, address_string, verify_buf) == 1)
+ return true;
+ if (inet_pton(AF_INET6, address_string, verify_buf) == 1)
+ return true;
+ return false;
+}
+
+static void kvp_extract_routes(const char *line, void **output, size_t *remaining)
+{
+ static const char needle[] = "via ";
+ const char *match, *haystack = line;
+
+ while ((match = strstr(haystack, needle))) {
+ const char *address, *next_char;
+
+ /* Address starts after needle. */
+ address = match + strlen(needle);
+
+ /* The char following address is a space or end of line. */
+ next_char = strpbrk(address, " \t\\");
+ if (!next_char)
+ next_char = address + strlen(address) + 1;
+
+ /* Enough room for address and semicolon. */
+ if (*remaining >= (next_char - address) + 1) {
+ memcpy(*output, address, next_char - address);
+ /* Terminate string for verification. */
+ memcpy(*output + (next_char - address), "", 1);
+ if (kvp_verify_ip_address(*output)) {
+ /* Advance output buffer. */
+ *output += next_char - address;
+ *remaining -= next_char - address;
+
+ /* Each address needs a trailing semicolon. */
+ memcpy(*output, ";", 1);
+ *output += 1;
+ *remaining -= 1;
+ }
+ }
+ haystack = next_char;
+ }
+}
+
+static void kvp_get_gateway(void *buffer, size_t buffer_len)
+{
+ static const char needle[] = "default ";
+ FILE *f;
+ void *output = buffer;
+ char *line = NULL;
+ size_t alloc_size = 0, remaining = buffer_len - 1;
+ ssize_t num_chars;
+
+ /* Show route information in a single line, for each address family */
+ f = popen("ip --oneline -4 route show;ip --oneline -6 route show", "r");
+ if (!f) {
+ /* Convert buffer into C-String. */
+ memcpy(output, "", 1);
+ return;
+ }
+ while ((num_chars = getline(&line, &alloc_size, f)) > 0) {
+ /* Skip short lines. */
+ if (num_chars <= strlen(needle))
+ continue;
+ /* Skip lines without default route. */
+ if (memcmp(line, needle, strlen(needle)))
+ continue;
+ /* Remove trailing newline to simplify further parsing. */
+ if (line[num_chars - 1] == '\n')
+ line[num_chars - 1] = '\0';
+ /* Search routes after match. */
+ kvp_extract_routes(line + strlen(needle), &output, &remaining);
+ }
+ /* Convert buffer into C-String. */
+ memcpy(output, "", 1);
+ free(line);
+ pclose(f);
+}
+
static void kvp_get_ipconfig_info(char *if_name,
struct hv_kvp_ipaddr_value *buffer)
{
@@ -685,30 +768,7 @@ static void kvp_get_ipconfig_info(char *if_name,
char *p;
FILE *file;
- /*
- * Get the address of default gateway (ipv4).
- */
- sprintf(cmd, "%s %s", "ip route show dev", if_name);
- strcat(cmd, " | awk '/default/ {print $3 }'");
-
- /*
- * Execute the command to gather gateway info.
- */
- kvp_process_ipconfig_file(cmd, (char *)buffer->gate_way,
- (MAX_GATEWAY_SIZE * 2), INET_ADDRSTRLEN, 0);
-
- /*
- * Get the address of default gateway (ipv6).
- */
- sprintf(cmd, "%s %s", "ip -f inet6 route show dev", if_name);
- strcat(cmd, " | awk '/default/ {print $3 }'");
-
- /*
- * Execute the command to gather gateway info (ipv6).
- */
- kvp_process_ipconfig_file(cmd, (char *)buffer->gate_way,
- (MAX_GATEWAY_SIZE * 2), INET6_ADDRSTRLEN, 1);
-
+ kvp_get_gateway(buffer->gate_way, sizeof(buffer->gate_way));
/*
* Gather the DNS state.
diff --git a/tools/include/linux/cfi_types.h b/tools/include/linux/cfi_types.h
new file mode 100644
index 0000000..6b87136
--- /dev/null
+++ b/tools/include/linux/cfi_types.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Clang Control Flow Integrity (CFI) type definitions.
+ */
+#ifndef _LINUX_CFI_TYPES_H
+#define _LINUX_CFI_TYPES_H
+
+#ifdef __ASSEMBLY__
+#include <linux/linkage.h>
+
+#ifdef CONFIG_CFI_CLANG
+/*
+ * Use the __kcfi_typeid_<function> type identifier symbol to
+ * annotate indirectly called assembly functions. The compiler emits
+ * these symbols for all address-taken function declarations in C
+ * code.
+ */
+#ifndef __CFI_TYPE
+#define __CFI_TYPE(name) \
+ .4byte __kcfi_typeid_##name
+#endif
+
+#define SYM_TYPED_ENTRY(name, linkage, align...) \
+ linkage(name) ASM_NL \
+ align ASM_NL \
+ __CFI_TYPE(name) ASM_NL \
+ name:
+
+#define SYM_TYPED_START(name, linkage, align...) \
+ SYM_TYPED_ENTRY(name, linkage, align)
+
+#else /* CONFIG_CFI_CLANG */
+
+#define SYM_TYPED_START(name, linkage, align...) \
+ SYM_START(name, linkage, align)
+
+#endif /* CONFIG_CFI_CLANG */
+
+#ifndef SYM_TYPED_FUNC_START
+#define SYM_TYPED_FUNC_START(name) \
+ SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* _LINUX_CFI_TYPES_H */
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index 1ea2c4c..ef1c27f 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -85,6 +85,7 @@
/* compatibility flags */
#define MAP_FILE 0
+#define PKEY_UNRESTRICTED 0x0
#define PKEY_DISABLE_ACCESS 0x1
#define PKEY_DISABLE_WRITE 0x2
#define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 88dc393..2892a45 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -849,9 +849,11 @@ __SYSCALL(__NR_getxattrat, sys_getxattrat)
__SYSCALL(__NR_listxattrat, sys_listxattrat)
#define __NR_removexattrat 466
__SYSCALL(__NR_removexattrat, sys_removexattrat)
+#define __NR_open_tree_attr 467
+__SYSCALL(__NR_open_tree_attr, sys_open_tree_attr)
#undef __NR_syscalls
-#define __NR_syscalls 467
+#define __NR_syscalls 468
/*
* 32 bit systems traditionally used different
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index 5d32d53..ced0fc3 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -79,6 +79,8 @@ enum {
#define IPPROTO_MPLS IPPROTO_MPLS
IPPROTO_ETHERNET = 143, /* Ethernet-within-IPv6 Encapsulation */
#define IPPROTO_ETHERNET IPPROTO_ETHERNET
+ IPPROTO_AGGFRAG = 144, /* AGGFRAG in ESP (RFC 9347) */
+#define IPPROTO_AGGFRAG IPPROTO_AGGFRAG
IPPROTO_RAW = 255, /* Raw IP packets */
#define IPPROTO_RAW IPPROTO_RAW
IPPROTO_SMC = 256, /* Shared Memory Communications */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 502ea63..b6ae8ad 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -617,10 +617,6 @@ struct kvm_ioeventfd {
#define KVM_X86_DISABLE_EXITS_HLT (1 << 1)
#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2)
#define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3)
-#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \
- KVM_X86_DISABLE_EXITS_HLT | \
- KVM_X86_DISABLE_EXITS_PAUSE | \
- KVM_X86_DISABLE_EXITS_CSTATE)
/* for KVM_ENABLE_CAP */
struct kvm_enable_cap {
@@ -933,6 +929,7 @@ struct kvm_enable_cap {
#define KVM_CAP_PRE_FAULT_MEMORY 236
#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237
#define KVM_CAP_X86_GUEST_MODE 238
+#define KVM_CAP_ARM_WRITABLE_IMP_ID_REGS 239
struct kvm_irq_routing_irqchip {
__u32 irqchip;
@@ -1070,6 +1067,10 @@ struct kvm_dirty_tlb {
#define KVM_REG_SIZE_SHIFT 52
#define KVM_REG_SIZE_MASK 0x00f0000000000000ULL
+
+#define KVM_REG_SIZE(id) \
+ (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
+
#define KVM_REG_SIZE_U8 0x0000000000000000ULL
#define KVM_REG_SIZE_U16 0x0010000000000000ULL
#define KVM_REG_SIZE_U32 0x0020000000000000ULL
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 0524d54..5fc753c 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -385,6 +385,8 @@ enum perf_event_read_format {
*
* @sample_max_stack: Max number of frame pointers in a callchain,
* should be < /proc/sys/kernel/perf_event_max_stack
+ * Max number of entries of branch stack
+ * should be < hardware limit
*/
struct perf_event_attr {
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index 887a252..f78ee36 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -98,43 +98,93 @@ struct statx_timestamp {
*/
struct statx {
/* 0x00 */
- __u32 stx_mask; /* What results were written [uncond] */
- __u32 stx_blksize; /* Preferred general I/O size [uncond] */
- __u64 stx_attributes; /* Flags conveying information about the file [uncond] */
+ /* What results were written [uncond] */
+ __u32 stx_mask;
+
+ /* Preferred general I/O size [uncond] */
+ __u32 stx_blksize;
+
+ /* Flags conveying information about the file [uncond] */
+ __u64 stx_attributes;
+
/* 0x10 */
- __u32 stx_nlink; /* Number of hard links */
- __u32 stx_uid; /* User ID of owner */
- __u32 stx_gid; /* Group ID of owner */
- __u16 stx_mode; /* File mode */
+ /* Number of hard links */
+ __u32 stx_nlink;
+
+ /* User ID of owner */
+ __u32 stx_uid;
+
+ /* Group ID of owner */
+ __u32 stx_gid;
+
+ /* File mode */
+ __u16 stx_mode;
__u16 __spare0[1];
+
/* 0x20 */
- __u64 stx_ino; /* Inode number */
- __u64 stx_size; /* File size */
- __u64 stx_blocks; /* Number of 512-byte blocks allocated */
- __u64 stx_attributes_mask; /* Mask to show what's supported in stx_attributes */
+ /* Inode number */
+ __u64 stx_ino;
+
+ /* File size */
+ __u64 stx_size;
+
+ /* Number of 512-byte blocks allocated */
+ __u64 stx_blocks;
+
+ /* Mask to show what's supported in stx_attributes */
+ __u64 stx_attributes_mask;
+
/* 0x40 */
- struct statx_timestamp stx_atime; /* Last access time */
- struct statx_timestamp stx_btime; /* File creation time */
- struct statx_timestamp stx_ctime; /* Last attribute change time */
- struct statx_timestamp stx_mtime; /* Last data modification time */
+ /* Last access time */
+ struct statx_timestamp stx_atime;
+
+ /* File creation time */
+ struct statx_timestamp stx_btime;
+
+ /* Last attribute change time */
+ struct statx_timestamp stx_ctime;
+
+ /* Last data modification time */
+ struct statx_timestamp stx_mtime;
+
/* 0x80 */
- __u32 stx_rdev_major; /* Device ID of special file [if bdev/cdev] */
+ /* Device ID of special file [if bdev/cdev] */
+ __u32 stx_rdev_major;
__u32 stx_rdev_minor;
- __u32 stx_dev_major; /* ID of device containing file [uncond] */
+
+ /* ID of device containing file [uncond] */
+ __u32 stx_dev_major;
__u32 stx_dev_minor;
+
/* 0x90 */
__u64 stx_mnt_id;
- __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */
- __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */
+
+ /* Memory buffer alignment for direct I/O */
+ __u32 stx_dio_mem_align;
+
+ /* File offset alignment for direct I/O */
+ __u32 stx_dio_offset_align;
+
/* 0xa0 */
- __u64 stx_subvol; /* Subvolume identifier */
- __u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */
- __u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */
+ /* Subvolume identifier */
+ __u64 stx_subvol;
+
+ /* Min atomic write unit in bytes */
+ __u32 stx_atomic_write_unit_min;
+
+ /* Max atomic write unit in bytes */
+ __u32 stx_atomic_write_unit_max;
+
/* 0xb0 */
- __u32 stx_atomic_write_segments_max; /* Max atomic write segment count */
- __u32 __spare1[1];
+ /* Max atomic write segment count */
+ __u32 stx_atomic_write_segments_max;
+
+ /* File offset alignment for direct I/O reads */
+ __u32 stx_dio_read_offset_align;
+
/* 0xb8 */
__u64 __spare3[9]; /* Spare space for future expansion */
+
/* 0x100 */
};
@@ -164,6 +214,7 @@ struct statx {
#define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */
#define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */
#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */
+#define STATX_DIO_READ_ALIGN 0x00020000U /* Want/got dio read alignment info */
#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
diff --git a/tools/lib/perf/Makefile b/tools/lib/perf/Makefile
index ffcfd77..7fbb50b 100644
--- a/tools/lib/perf/Makefile
+++ b/tools/lib/perf/Makefile
@@ -42,6 +42,7 @@
TEST_ARGS := $(if $(V),-v)
INCLUDES = \
+-I$(OUTPUT)arch/$(SRCARCH)/include/generated/uapi \
-I$(srctree)/tools/lib/perf/include \
-I$(srctree)/tools/lib/ \
-I$(srctree)/tools/include \
@@ -99,7 +100,16 @@
$(call QUIET_CLEAN, libapi)
$(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null
-$(LIBPERF_IN): FORCE
+uapi-asm := $(OUTPUT)arch/$(SRCARCH)/include/generated/uapi/asm
+ifeq ($(SRCARCH),arm64)
+ syscall-y := $(uapi-asm)/unistd_64.h
+endif
+uapi-asm-generic:
+ $(if $(syscall-y),\
+ $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.asm-headers obj=$(uapi-asm) \
+ generic=include/uapi/asm-generic $(syscall-y),)
+
+$(LIBPERF_IN): uapi-asm-generic FORCE
$(Q)$(MAKE) $(build)=libperf
$(LIBPERF_A): $(LIBPERF_IN)
@@ -120,7 +130,7 @@
clean: $(LIBAPI)-clean
$(call QUIET_CLEAN, libperf) $(RM) $(LIBPERF_A) \
*.o *~ *.a *.so *.so.$(VERSION) *.so.$(LIBPERF_VERSION) .*.d .*.cmd tests/*.o LIBPERF-CFLAGS $(LIBPERF_PC) \
- $(TESTS_STATIC) $(TESTS_SHARED)
+ $(TESTS_STATIC) $(TESTS_SHARED) $(syscall-y)
TESTS_IN = tests-in.o
diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py
index a1427c5..30c0a34 100755
--- a/tools/net/ynl/pyynl/ynl_gen_c.py
+++ b/tools/net/ynl/pyynl/ynl_gen_c.py
@@ -162,9 +162,15 @@
def free_needs_iter(self):
return False
- def free(self, ri, var, ref):
+ def _free_lines(self, ri, var, ref):
if self.is_multi_val() or self.presence_type() == 'len':
- ri.cw.p(f'free({var}->{ref}{self.c_name});')
+ return [f'free({var}->{ref}{self.c_name});']
+ return []
+
+ def free(self, ri, var, ref):
+ lines = self._free_lines(ri, var, ref)
+ for line in lines:
+ ri.cw.p(line)
def arg_member(self, ri):
member = self._complex_member_type(ri)
@@ -263,6 +269,10 @@
var = "req"
member = f"{var}->{'.'.join(ref)}"
+ local_vars = []
+ if self.free_needs_iter():
+ local_vars += ['unsigned int i;']
+
code = []
presence = ''
for i in range(0, len(ref)):
@@ -272,6 +282,10 @@
if i == len(ref) - 1 and self.presence_type() != 'bit':
continue
code.append(presence + ' = 1;')
+ ref_path = '.'.join(ref[:-1])
+ if ref_path:
+ ref_path += '.'
+ code += self._free_lines(ri, var, ref_path)
code += self._setter_lines(ri, member, presence)
func_name = f"{op_prefix(ri, direction, deref=deref)}_set_{'_'.join(ref)}"
@@ -279,7 +293,8 @@
alloc = bool([x for x in code if 'alloc(' in x])
if free and not alloc:
func_name = '__' + func_name
- ri.cw.write_func('static inline void', func_name, body=code,
+ ri.cw.write_func('static inline void', func_name, local_vars=local_vars,
+ body=code,
args=[f'{type_name(ri, direction, deref=deref)} *{var}'] + self.arg_member(ri))
@@ -482,8 +497,7 @@
['unsigned int len;']
def _setter_lines(self, ri, member, presence):
- return [f"free({member});",
- f"{presence}_len = strlen({self.c_name});",
+ return [f"{presence}_len = strlen({self.c_name});",
f"{member} = malloc({presence}_len + 1);",
f'memcpy({member}, {self.c_name}, {presence}_len);',
f'{member}[{presence}_len] = 0;']
@@ -536,8 +550,7 @@
['unsigned int len;']
def _setter_lines(self, ri, member, presence):
- return [f"free({member});",
- f"{presence}_len = len;",
+ return [f"{presence}_len = len;",
f"{member} = malloc({presence}_len);",
f'memcpy({member}, {self.c_name}, {presence}_len);']
@@ -574,12 +587,14 @@
def _complex_member_type(self, ri):
return self.nested_struct_type
- def free(self, ri, var, ref):
+ def _free_lines(self, ri, var, ref):
+ lines = []
at = '&'
if self.is_recursive_for_op(ri):
at = ''
- ri.cw.p(f'if ({var}->{ref}{self.c_name})')
- ri.cw.p(f'{self.nested_render_name}_free({at}{var}->{ref}{self.c_name});')
+ lines += [f'if ({var}->{ref}{self.c_name})']
+ lines += [f'{self.nested_render_name}_free({at}{var}->{ref}{self.c_name});']
+ return lines
def _attr_typol(self):
return f'.type = YNL_PT_NEST, .nest = &{self.nested_render_name}_nest, '
@@ -632,15 +647,19 @@
def free_needs_iter(self):
return 'type' not in self.attr or self.attr['type'] == 'nest'
- def free(self, ri, var, ref):
+ def _free_lines(self, ri, var, ref):
+ lines = []
if self.attr['type'] in scalars:
- ri.cw.p(f"free({var}->{ref}{self.c_name});")
+ lines += [f"free({var}->{ref}{self.c_name});"]
elif 'type' not in self.attr or self.attr['type'] == 'nest':
- ri.cw.p(f"for (i = 0; i < {var}->{ref}n_{self.c_name}; i++)")
- ri.cw.p(f'{self.nested_render_name}_free(&{var}->{ref}{self.c_name}[i]);')
- ri.cw.p(f"free({var}->{ref}{self.c_name});")
+ lines += [
+ f"for (i = 0; i < {var}->{ref}n_{self.c_name}; i++)",
+ f'{self.nested_render_name}_free(&{var}->{ref}{self.c_name}[i]);',
+ f"free({var}->{ref}{self.c_name});",
+ ]
else:
raise Exception(f"Free of MultiAttr sub-type {self.attr['type']} not supported yet")
+ return lines
def _attr_policy(self, policy):
return self.base_type._attr_policy(policy)
@@ -654,10 +673,10 @@
def attr_put(self, ri, var):
if self.attr['type'] in scalars:
put_type = self.type
- ri.cw.p(f"for (unsigned int i = 0; i < {var}->n_{self.c_name}; i++)")
+ ri.cw.p(f"for (i = 0; i < {var}->n_{self.c_name}; i++)")
ri.cw.p(f"ynl_attr_put_{put_type}(nlh, {self.enum_name}, {var}->{self.c_name}[i]);")
elif 'type' not in self.attr or self.attr['type'] == 'nest':
- ri.cw.p(f"for (unsigned int i = 0; i < {var}->n_{self.c_name}; i++)")
+ ri.cw.p(f"for (i = 0; i < {var}->n_{self.c_name}; i++)")
self._attr_put_line(ri, var, f"{self.nested_render_name}_put(nlh, " +
f"{self.enum_name}, &{var}->{self.c_name}[i])")
else:
@@ -666,8 +685,7 @@
def _setter_lines(self, ri, member, presence):
# For multi-attr we have a count, not presence, hack up the presence
presence = presence[:-(len('_present.') + len(self.c_name))] + "n_" + self.c_name
- return [f"free({member});",
- f"{member} = {self.c_name};",
+ return [f"{member} = {self.c_name};",
f"{presence} = n_{self.c_name};"]
@@ -696,8 +714,11 @@
def _attr_get(self, ri, var):
local_vars = ['const struct nlattr *attr2;']
get_lines = [f'attr_{self.c_name} = attr;',
- 'ynl_attr_for_each_nested(attr2, attr)',
- f'\t{var}->n_{self.c_name}++;']
+ 'ynl_attr_for_each_nested(attr2, attr) {',
+ '\tif (ynl_attr_validate(yarg, attr2))',
+ '\t\treturn YNL_PARSE_CB_ERROR;',
+ f'\t{var}->n_{self.c_name}++;',
+ '}']
return get_lines, None, local_vars
@@ -755,6 +776,7 @@
self.request = False
self.reply = False
self.recursive = False
+ self.in_multi_val = False # used by a MultiAttr or and legacy arrays
self.attr_list = []
self.attrs = dict()
@@ -1122,6 +1144,10 @@
if attr in rs_members['reply']:
self.pure_nested_structs[nested].reply = True
+ if spec.is_multi_val():
+ child = self.pure_nested_structs.get(nested)
+ child.in_multi_val = True
+
self._sort_pure_types()
# Propagate the request / reply / recursive
@@ -1136,6 +1162,8 @@
struct.child_nests.update(child.child_nests)
child.request |= struct.request
child.reply |= struct.reply
+ if spec.is_multi_val():
+ child.in_multi_val = True
if attr_set in struct.child_nests:
struct.recursive = True
@@ -1399,9 +1427,9 @@
def write_func(self, qual_ret, name, body, args=None, local_vars=None):
self.write_func_prot(qual_ret=qual_ret, name=name, args=args)
+ self.block_start()
self.write_func_lvar(local_vars=local_vars)
- self.block_start()
for line in body:
self.p(line)
self.block_end()
@@ -1644,11 +1672,23 @@
def put_req_nested(ri, struct):
+ local_vars = []
+ init_lines = []
+
+ local_vars.append('struct nlattr *nest;')
+ init_lines.append("nest = ynl_attr_nest_start(nlh, attr_type);")
+
+ for _, arg in struct.member_list():
+ if arg.presence_type() == 'count':
+ local_vars.append('unsigned int i;')
+ break
+
put_req_nested_prototype(ri, struct, suffix='')
ri.cw.block_start()
- ri.cw.write_func_lvar('struct nlattr *nest;')
+ ri.cw.write_func_lvar(local_vars)
- ri.cw.p("nest = ynl_attr_nest_start(nlh, attr_type);")
+ for line in init_lines:
+ ri.cw.p(line)
for _, arg in struct.member_list():
arg.attr_put(ri, "obj")
@@ -1850,6 +1890,11 @@
local_vars += ['size_t hdr_len;',
'void *hdr;']
+ for _, attr in ri.struct["request"].member_list():
+ if attr.presence_type() == 'count':
+ local_vars += ['unsigned int i;']
+ break
+
print_prototype(ri, direction, terminate=False)
ri.cw.block_start()
ri.cw.write_func_lvar(local_vars)
@@ -2941,6 +2986,9 @@
for attr_set, struct in parsed.pure_nested_structs.items():
ri = RenderInfo(cw, parsed, args.mode, "", "", attr_set)
print_type_full(ri, struct)
+ if struct.request and struct.in_multi_val:
+ free_rsp_nested_prototype(ri)
+ cw.nl()
for op_name, op in parsed.ops.items():
cw.p(f"/* ============== {op.enum_name} ============== */")
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 33d861c..3ce7b54 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -522,7 +522,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
case INAT_PFX_REPNE:
if (modrm == 0xca)
/* eretu/erets */
- insn->type = INSN_CONTEXT_SWITCH;
+ insn->type = INSN_SYSRET;
break;
default:
if (modrm == 0xca)
@@ -535,11 +535,15 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
insn->type = INSN_JUMP_CONDITIONAL;
- } else if (op2 == 0x05 || op2 == 0x07 || op2 == 0x34 ||
- op2 == 0x35) {
+ } else if (op2 == 0x05 || op2 == 0x34) {
- /* sysenter, sysret */
- insn->type = INSN_CONTEXT_SWITCH;
+ /* syscall, sysenter */
+ insn->type = INSN_SYSCALL;
+
+ } else if (op2 == 0x07 || op2 == 0x35) {
+
+ /* sysret, sysexit */
+ insn->type = INSN_SYSRET;
} else if (op2 == 0x0b || op2 == 0xb9) {
@@ -676,7 +680,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
case 0xca: /* retf */
case 0xcb: /* retf */
- insn->type = INSN_CONTEXT_SWITCH;
+ insn->type = INSN_SYSRET;
break;
case 0xe0: /* loopne */
@@ -721,7 +725,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
} else if (modrm_reg == 5) {
/* jmpf */
- insn->type = INSN_CONTEXT_SWITCH;
+ insn->type = INSN_SYSRET;
} else if (modrm_reg == 6) {
diff --git a/tools/objtool/arch/x86/special.c b/tools/objtool/arch/x86/special.c
index 403e587..06ca4a2 100644
--- a/tools/objtool/arch/x86/special.c
+++ b/tools/objtool/arch/x86/special.c
@@ -126,7 +126,7 @@ struct reloc *arch_find_switch_table(struct objtool_file *file,
* indicates a rare GCC quirk/bug which can leave dead
* code behind.
*/
- if (reloc_type(text_reloc) == R_X86_64_PC32) {
+ if (!file->ignore_unreachables && reloc_type(text_reloc) == R_X86_64_PC32) {
WARN_INSN(insn, "ignoring unreachables due to jump table quirk");
file->ignore_unreachables = true;
}
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 4a1f6c3..3a41106 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -225,6 +225,7 @@ static bool is_rust_noreturn(const struct symbol *func)
str_ends_with(func->name, "_4core9panicking14panic_nounwind") ||
str_ends_with(func->name, "_4core9panicking18panic_bounds_check") ||
str_ends_with(func->name, "_4core9panicking19assert_failed_inner") ||
+ str_ends_with(func->name, "_4core9panicking30panic_null_pointer_dereference") ||
str_ends_with(func->name, "_4core9panicking36panic_misaligned_pointer_dereference") ||
strstr(func->name, "_4core9panicking13assert_failed") ||
strstr(func->name, "_4core9panicking11panic_const24panic_const_") ||
@@ -3505,6 +3506,34 @@ static struct instruction *next_insn_to_validate(struct objtool_file *file,
return next_insn_same_sec(file, alt_group->orig_group->last_insn);
}
+static bool skip_alt_group(struct instruction *insn)
+{
+ struct instruction *alt_insn = insn->alts ? insn->alts->insn : NULL;
+
+ /* ANNOTATE_IGNORE_ALTERNATIVE */
+ if (insn->alt_group && insn->alt_group->ignore)
+ return true;
+
+ /*
+ * For NOP patched with CLAC/STAC, only follow the latter to avoid
+ * impossible code paths combining patched CLAC with unpatched STAC
+ * or vice versa.
+ *
+ * ANNOTATE_IGNORE_ALTERNATIVE could have been used here, but Linus
+ * requested not to do that to avoid hurting .s file readability
+ * around CLAC/STAC alternative sites.
+ */
+
+ if (!alt_insn)
+ return false;
+
+ /* Don't override ASM_{CLAC,STAC}_UNSAFE */
+ if (alt_insn->alt_group && alt_insn->alt_group->ignore)
+ return false;
+
+ return alt_insn->type == INSN_CLAC || alt_insn->type == INSN_STAC;
+}
+
/*
* Follow the branch starting at the given instruction, and recursively follow
* any other branches (jumps). Meanwhile, track the frame pointer state at
@@ -3625,7 +3654,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
}
}
- if (insn->alt_group && insn->alt_group->ignore)
+ if (skip_alt_group(insn))
return 0;
if (handle_insn_ops(insn, next_insn, &state))
@@ -3684,14 +3713,20 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
break;
- case INSN_CONTEXT_SWITCH:
- if (func) {
- if (!next_insn || !next_insn->hint) {
- WARN_INSN(insn, "unsupported instruction in callable function");
- return 1;
- }
- break;
+ case INSN_SYSCALL:
+ if (func && (!next_insn || !next_insn->hint)) {
+ WARN_INSN(insn, "unsupported instruction in callable function");
+ return 1;
}
+
+ break;
+
+ case INSN_SYSRET:
+ if (func && (!next_insn || !next_insn->hint)) {
+ WARN_INSN(insn, "unsupported instruction in callable function");
+ return 1;
+ }
+
return 0;
case INSN_STAC:
@@ -3886,6 +3921,12 @@ static int validate_unret(struct objtool_file *file, struct instruction *insn)
WARN_INSN(insn, "RET before UNTRAIN");
return 1;
+ case INSN_SYSCALL:
+ break;
+
+ case INSN_SYSRET:
+ return 0;
+
case INSN_NOP:
if (insn->retpoline_safe)
return 0;
@@ -3895,6 +3936,9 @@ static int validate_unret(struct objtool_file *file, struct instruction *insn)
break;
}
+ if (insn->dead_end)
+ return 0;
+
if (!next) {
WARN_INSN(insn, "teh end!");
return 1;
diff --git a/tools/objtool/include/objtool/arch.h b/tools/objtool/include/objtool/arch.h
index 089a1ac..01ef6f4 100644
--- a/tools/objtool/include/objtool/arch.h
+++ b/tools/objtool/include/objtool/arch.h
@@ -19,7 +19,8 @@ enum insn_type {
INSN_CALL,
INSN_CALL_DYNAMIC,
INSN_RETURN,
- INSN_CONTEXT_SWITCH,
+ INSN_SYSCALL,
+ INSN_SYSRET,
INSN_BUG,
INSN_NOP,
INSN_STAC,
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index eea95c6..b7769a2 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -29,6 +29,7 @@
$(call detected_var,SRCARCH)
CFLAGS += -I$(OUTPUT)arch/$(SRCARCH)/include/generated
+CFLAGS += -I$(OUTPUT)libperf/arch/$(SRCARCH)/include/generated/uapi
# Additional ARCH settings for ppc
ifeq ($(SRCARCH),powerpc)
diff --git a/tools/perf/arch/arm/entry/syscalls/syscall.tbl b/tools/perf/arch/arm/entry/syscalls/syscall.tbl
index 49eeb2a..27c1d5e 100644
--- a/tools/perf/arch/arm/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/arm/entry/syscalls/syscall.tbl
@@ -481,3 +481,4 @@
464 common getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat
+467 common open_tree_attr sys_open_tree_attr
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index c844cd5..1e8c44c 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -381,3 +381,4 @@
464 n64 getxattrat sys_getxattrat
465 n64 listxattrat sys_listxattrat
466 n64 removexattrat sys_removexattrat
+467 n64 open_tree_attr sys_open_tree_attr
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index d8b4ab7..9a084bd 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -557,3 +557,4 @@
464 common getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat
+467 common open_tree_attr sys_open_tree_attr
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index e9115b4..a4569b9 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -469,3 +469,4 @@
464 common getxattrat sys_getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat sys_removexattrat
+467 common open_tree_attr sys_open_tree_attr sys_open_tree_attr
diff --git a/tools/perf/arch/sh/entry/syscalls/syscall.tbl b/tools/perf/arch/sh/entry/syscalls/syscall.tbl
index c8cad33..52a7652 100644
--- a/tools/perf/arch/sh/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/sh/entry/syscalls/syscall.tbl
@@ -470,3 +470,4 @@
464 common getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat
+467 common open_tree_attr sys_open_tree_attr
diff --git a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
index 727f99d..83e45eb 100644
--- a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
@@ -512,3 +512,4 @@
464 common getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat
+467 common open_tree_attr sys_open_tree_attr
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
index 4d0fb2f..ac007ea 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
@@ -396,7 +396,7 @@
381 i386 pkey_alloc sys_pkey_alloc
382 i386 pkey_free sys_pkey_free
383 i386 statx sys_statx
-384 i386 arch_prctl sys_arch_prctl compat_sys_arch_prctl
+384 i386 arch_prctl sys_arch_prctl
385 i386 io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents
386 i386 rseq sys_rseq
393 i386 semget sys_semget
@@ -472,3 +472,4 @@
464 i386 getxattrat sys_getxattrat
465 i386 listxattrat sys_listxattrat
466 i386 removexattrat sys_removexattrat
+467 i386 open_tree_attr sys_open_tree_attr
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 5eb708b..cfb5ca4 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -390,6 +390,7 @@
464 common getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat
+467 common open_tree_attr sys_open_tree_attr
#
# Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
index 37effc1..f657a77 100644
--- a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
@@ -437,3 +437,4 @@
464 common getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat
+467 common open_tree_attr sys_open_tree_attr
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index a4499e5..857f664 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -20,6 +20,7 @@
"include/uapi/linux/stat.h"
"include/linux/bits.h"
"include/vdso/bits.h"
+ "include/linux/cfi_types.h"
"include/linux/const.h"
"include/vdso/const.h"
"include/vdso/unaligned.h"
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index d18cc47..c3322eb 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -392,6 +392,8 @@ struct ucred {
extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr);
extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data);
+extern int put_cmsg_notrunc(struct msghdr *msg, int level, int type, int len,
+ void *data);
struct timespec64;
struct __kernel_timespec;
diff --git a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
index 6e6907e..a15ac2f 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
@@ -155,4 +155,8 @@
#define AT_HANDLE_MNT_ID_UNIQUE 0x001 /* Return the u64 unique mount ID. */
#define AT_HANDLE_CONNECTABLE 0x002 /* Request a connectable file handle */
+/* Flags for execveat2(2). */
+#define AT_EXECVE_CHECK 0x10000 /* Only perform a check if execution
+ would be allowed. */
+
#endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h
index 7539717..e762e1a 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fs.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h
@@ -40,6 +40,15 @@
#define BLOCK_SIZE_BITS 10
#define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)
+/* flags for integrity meta */
+#define IO_INTEGRITY_CHK_GUARD (1U << 0) /* enforce guard check */
+#define IO_INTEGRITY_CHK_REFTAG (1U << 1) /* enforce ref check */
+#define IO_INTEGRITY_CHK_APPTAG (1U << 2) /* enforce app check */
+
+#define IO_INTEGRITY_VALID_FLAGS (IO_INTEGRITY_CHK_GUARD | \
+ IO_INTEGRITY_CHK_REFTAG | \
+ IO_INTEGRITY_CHK_APPTAG)
+
#define SEEK_SET 0 /* seek relative to beginning of file */
#define SEEK_CUR 1 /* seek relative to current file position */
#define SEEK_END 2 /* seek relative to end of file */
@@ -203,10 +212,8 @@ struct fsxattr {
#define BLKROTATIONAL _IO(0x12,126)
#define BLKZEROOUT _IO(0x12,127)
#define BLKGETDISKSEQ _IOR(0x12,128,__u64)
-/*
- * A jump here: 130-136 are reserved for zoned block devices
- * (see uapi/linux/blkzoned.h)
- */
+/* 130-136 are used by zoned block device ioctls (uapi/linux/blkzoned.h) */
+/* 137-141 are used by blk-crypto ioctls (uapi/linux/blk-crypto.h) */
#define BMAP_IOCTL 1 /* obsolete - kept for compatibility */
#define FIBMAP _IO(0x00,1) /* bmap access */
@@ -332,9 +339,13 @@ typedef int __bitwise __kernel_rwf_t;
/* Atomic Write */
#define RWF_ATOMIC ((__force __kernel_rwf_t)0x00000040)
+/* buffered IO that drops the cache after reading or writing data */
+#define RWF_DONTCACHE ((__force __kernel_rwf_t)0x00000080)
+
/* mask of flags supported by the kernel */
#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
- RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC)
+ RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC |\
+ RWF_DONTCACHE)
#define PROCFS_IOCTL_MAGIC 'f'
diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h
index c070088..7fa67c2 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/mount.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h
@@ -179,7 +179,12 @@ struct statmount {
__u32 opt_array; /* [str] Array of nul terminated fs options */
__u32 opt_sec_num; /* Number of security options */
__u32 opt_sec_array; /* [str] Array of nul terminated security options */
- __u64 __spare2[46];
+ __u64 supported_mask; /* Mask flags that this kernel supports */
+ __u32 mnt_uidmap_num; /* Number of uid mappings */
+ __u32 mnt_uidmap; /* [str] Array of uid mappings (as seen from callers namespace) */
+ __u32 mnt_gidmap_num; /* Number of gid mappings */
+ __u32 mnt_gidmap; /* [str] Array of gid mappings (as seen from callers namespace) */
+ __u64 __spare2[43];
char str[]; /* Variable size part containing strings */
};
@@ -217,6 +222,9 @@ struct mnt_id_req {
#define STATMOUNT_SB_SOURCE 0x00000200U /* Want/got sb_source */
#define STATMOUNT_OPT_ARRAY 0x00000400U /* Want/got opt_... */
#define STATMOUNT_OPT_SEC_ARRAY 0x00000800U /* Want/got opt_sec... */
+#define STATMOUNT_SUPPORTED_MASK 0x00001000U /* Want/got supported mask flags */
+#define STATMOUNT_MNT_UIDMAP 0x00002000U /* Want/got uidmap... */
+#define STATMOUNT_MNT_GIDMAP 0x00004000U /* Want/got gidmap... */
/*
* Special @mnt_id values that can be passed to listmount
diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
index 5c60806..15c18ef 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
@@ -353,4 +353,15 @@ struct prctl_mm_map {
*/
#define PR_LOCK_SHADOW_STACK_STATUS 76
+/*
+ * Controls the mode of timer_create() for CRIU restore operations.
+ * Enabling this allows CRIU to restore timers with explicit IDs.
+ *
+ * Don't use for normal operations as the result might be undefined.
+ */
+#define PR_TIMER_CREATE_RESTORE_IDS 77
+# define PR_TIMER_CREATE_RESTORE_IDS_OFF 0
+# define PR_TIMER_CREATE_RESTORE_IDS_ON 1
+# define PR_TIMER_CREATE_RESTORE_IDS_GET 2
+
#endif /* _LINUX_PRCTL_H */
diff --git a/tools/perf/trace/beauty/include/uapi/linux/stat.h b/tools/perf/trace/beauty/include/uapi/linux/stat.h
index 887a252..f78ee36 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/stat.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/stat.h
@@ -98,43 +98,93 @@ struct statx_timestamp {
*/
struct statx {
/* 0x00 */
- __u32 stx_mask; /* What results were written [uncond] */
- __u32 stx_blksize; /* Preferred general I/O size [uncond] */
- __u64 stx_attributes; /* Flags conveying information about the file [uncond] */
+ /* What results were written [uncond] */
+ __u32 stx_mask;
+
+ /* Preferred general I/O size [uncond] */
+ __u32 stx_blksize;
+
+ /* Flags conveying information about the file [uncond] */
+ __u64 stx_attributes;
+
/* 0x10 */
- __u32 stx_nlink; /* Number of hard links */
- __u32 stx_uid; /* User ID of owner */
- __u32 stx_gid; /* Group ID of owner */
- __u16 stx_mode; /* File mode */
+ /* Number of hard links */
+ __u32 stx_nlink;
+
+ /* User ID of owner */
+ __u32 stx_uid;
+
+ /* Group ID of owner */
+ __u32 stx_gid;
+
+ /* File mode */
+ __u16 stx_mode;
__u16 __spare0[1];
+
/* 0x20 */
- __u64 stx_ino; /* Inode number */
- __u64 stx_size; /* File size */
- __u64 stx_blocks; /* Number of 512-byte blocks allocated */
- __u64 stx_attributes_mask; /* Mask to show what's supported in stx_attributes */
+ /* Inode number */
+ __u64 stx_ino;
+
+ /* File size */
+ __u64 stx_size;
+
+ /* Number of 512-byte blocks allocated */
+ __u64 stx_blocks;
+
+ /* Mask to show what's supported in stx_attributes */
+ __u64 stx_attributes_mask;
+
/* 0x40 */
- struct statx_timestamp stx_atime; /* Last access time */
- struct statx_timestamp stx_btime; /* File creation time */
- struct statx_timestamp stx_ctime; /* Last attribute change time */
- struct statx_timestamp stx_mtime; /* Last data modification time */
+ /* Last access time */
+ struct statx_timestamp stx_atime;
+
+ /* File creation time */
+ struct statx_timestamp stx_btime;
+
+ /* Last attribute change time */
+ struct statx_timestamp stx_ctime;
+
+ /* Last data modification time */
+ struct statx_timestamp stx_mtime;
+
/* 0x80 */
- __u32 stx_rdev_major; /* Device ID of special file [if bdev/cdev] */
+ /* Device ID of special file [if bdev/cdev] */
+ __u32 stx_rdev_major;
__u32 stx_rdev_minor;
- __u32 stx_dev_major; /* ID of device containing file [uncond] */
+
+ /* ID of device containing file [uncond] */
+ __u32 stx_dev_major;
__u32 stx_dev_minor;
+
/* 0x90 */
__u64 stx_mnt_id;
- __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */
- __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */
+
+ /* Memory buffer alignment for direct I/O */
+ __u32 stx_dio_mem_align;
+
+ /* File offset alignment for direct I/O */
+ __u32 stx_dio_offset_align;
+
/* 0xa0 */
- __u64 stx_subvol; /* Subvolume identifier */
- __u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */
- __u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */
+ /* Subvolume identifier */
+ __u64 stx_subvol;
+
+ /* Min atomic write unit in bytes */
+ __u32 stx_atomic_write_unit_min;
+
+ /* Max atomic write unit in bytes */
+ __u32 stx_atomic_write_unit_max;
+
/* 0xb0 */
- __u32 stx_atomic_write_segments_max; /* Max atomic write segment count */
- __u32 __spare1[1];
+ /* Max atomic write segment count */
+ __u32 stx_atomic_write_segments_max;
+
+ /* File offset alignment for direct I/O reads */
+ __u32 stx_dio_read_offset_align;
+
/* 0xb8 */
__u64 __spare3[9]; /* Spare space for future expansion */
+
/* 0x100 */
};
@@ -164,6 +214,7 @@ struct statx {
#define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */
#define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */
#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */
+#define STATX_DIO_READ_ALIGN 0x00020000U /* Want/got dio read alignment info */
#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
diff --git a/tools/perf/trace/beauty/include/uapi/sound/asound.h b/tools/perf/trace/beauty/include/uapi/sound/asound.h
index 4cd5132..5a049ee 100644
--- a/tools/perf/trace/beauty/include/uapi/sound/asound.h
+++ b/tools/perf/trace/beauty/include/uapi/sound/asound.h
@@ -716,7 +716,7 @@ enum {
* Raw MIDI section - /dev/snd/midi??
*/
-#define SNDRV_RAWMIDI_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 4)
+#define SNDRV_RAWMIDI_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 5)
enum {
SNDRV_RAWMIDI_STREAM_OUTPUT = 0,
@@ -728,6 +728,9 @@ enum {
#define SNDRV_RAWMIDI_INFO_INPUT 0x00000002
#define SNDRV_RAWMIDI_INFO_DUPLEX 0x00000004
#define SNDRV_RAWMIDI_INFO_UMP 0x00000008
+#define SNDRV_RAWMIDI_INFO_STREAM_INACTIVE 0x00000010
+
+#define SNDRV_RAWMIDI_DEVICE_UNKNOWN 0
struct snd_rawmidi_info {
unsigned int device; /* RO/WR (control): device number */
@@ -740,7 +743,8 @@ struct snd_rawmidi_info {
unsigned char subname[32]; /* name of active or selected subdevice */
unsigned int subdevices_count;
unsigned int subdevices_avail;
- unsigned char reserved[64]; /* reserved for future use */
+ int tied_device; /* R: tied rawmidi device (UMP/legacy) */
+ unsigned char reserved[60]; /* reserved for future use */
};
#define SNDRV_RAWMIDI_MODE_FRAMING_MASK (7<<0)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1974395..3c030da 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2566,25 +2566,6 @@ static bool evsel__detect_missing_features(struct evsel *evsel, struct perf_cpu
return false;
}
-static bool evsel__handle_error_quirks(struct evsel *evsel, int error)
-{
- /*
- * AMD core PMU tries to forward events with precise_ip to IBS PMU
- * implicitly. But IBS PMU has more restrictions so it can fail with
- * supported event attributes. Let's forward it back to the core PMU
- * by clearing precise_ip only if it's from precise_max (:P).
- */
- if ((error == -EINVAL || error == -ENOENT) && x86__is_amd_cpu() &&
- evsel->core.attr.precise_ip && evsel->precise_max) {
- evsel->core.attr.precise_ip = 0;
- pr_debug2_peo("removing precise_ip on AMD\n");
- display_attr(&evsel->core.attr);
- return true;
- }
-
- return false;
-}
-
static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
struct perf_thread_map *threads,
int start_cpu_map_idx, int end_cpu_map_idx)
@@ -2730,9 +2711,6 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
if (evsel__precise_ip_fallback(evsel))
goto retry_open;
- if (evsel__handle_error_quirks(evsel, err))
- goto retry_open;
-
out_close:
if (err)
threads->err_thread = thread;
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 9fb2c13..0b037e7 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -371,7 +371,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
* has to be pointed by symsrc_filename
*/
if (ofs == 0) {
- if (dso__data_get_fd(dso, machine, &fd) {
+ if (dso__data_get_fd(dso, machine, &fd)) {
ofs = elf_section_offset(fd, ".debug_frame");
dso__data_put_fd(dso);
}
diff --git a/tools/sched_ext/scx_flatcg.bpf.c b/tools/sched_ext/scx_flatcg.bpf.c
index 2c720e3..fdc7170 100644
--- a/tools/sched_ext/scx_flatcg.bpf.c
+++ b/tools/sched_ext/scx_flatcg.bpf.c
@@ -950,5 +950,5 @@ SCX_OPS_DEFINE(flatcg_ops,
.cgroup_move = (void *)fcg_cgroup_move,
.init = (void *)fcg_init,
.exit = (void *)fcg_exit,
- .flags = SCX_OPS_HAS_CGROUP_WEIGHT | SCX_OPS_ENQ_EXITING,
+ .flags = SCX_OPS_ENQ_EXITING,
.name = "flatcg");
diff --git a/tools/scripts/syscall.tbl b/tools/scripts/syscall.tbl
index ebbdb3c..580b4e24 100644
--- a/tools/scripts/syscall.tbl
+++ b/tools/scripts/syscall.tbl
@@ -407,3 +407,4 @@
464 common getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat
+467 common open_tree_attr sys_open_tree_attr
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index f2957a3..bf9caa9 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -1780,7 +1780,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
if (rc)
return rc;
- rc = devm_cxl_setup_fwctl(cxlmd);
+ rc = devm_cxl_setup_fwctl(&pdev->dev, cxlmd);
if (rc)
dev_dbg(dev, "No CXL FWCTL setup\n");
diff --git a/tools/testing/kunit/configs/all_tests.config b/tools/testing/kunit/configs/all_tests.config
index cdd9782..422e186 100644
--- a/tools/testing/kunit/configs/all_tests.config
+++ b/tools/testing/kunit/configs/all_tests.config
@@ -20,6 +20,7 @@
CONFIG_PCI=y
CONFIG_USB4=y
+CONFIG_I2C=y
CONFIG_NET=y
CONFIG_MCTP=y
@@ -43,6 +44,8 @@
CONFIG_AUDIT=y
+CONFIG_PRIME_NUMBERS=y
+
CONFIG_SECURITY=y
CONFIG_SECURITY_APPARMOR=y
CONFIG_SECURITY_LANDLOCK=y
@@ -51,3 +54,4 @@
CONFIG_SND=y
CONFIG_SND_SOC=y
CONFIG_SND_SOC_TOPOLOGY_BUILD=y
+CONFIG_SND_SOC_CS35L56_I2C=y
diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py
index da53a70..c176487 100644
--- a/tools/testing/kunit/kunit_parser.py
+++ b/tools/testing/kunit/kunit_parser.py
@@ -809,6 +809,10 @@
test.log.extend(parse_diagnostic(lines))
if test.name != "" and not peek_test_name_match(lines, test):
test.add_error(printer, 'missing subtest result line!')
+ elif not lines:
+ print_log(test.log, printer)
+ test.status = TestStatus.NO_TESTS
+ test.add_error(printer, 'No more test results!')
else:
parse_test_result(lines, test, expected_num, printer)
diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py
index 5ff4f6f..bbba921 100755
--- a/tools/testing/kunit/kunit_tool_test.py
+++ b/tools/testing/kunit/kunit_tool_test.py
@@ -371,8 +371,8 @@
"""
result = kunit_parser.parse_run_tests(output.splitlines(), stdout)
# Missing test results after test plan should alert a suspected test crash.
- self.assertEqual(kunit_parser.TestStatus.TEST_CRASHED, result.status)
- self.assertEqual(result.counts, kunit_parser.TestCounts(passed=1, crashed=1, errors=1))
+ self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status)
+ self.assertEqual(result.counts, kunit_parser.TestCounts(passed=1, errors=2))
def line_stream_from_strs(strs: Iterable[str]) -> kunit_parser.LineStream:
return kunit_parser.LineStream(enumerate(strs, start=1))
diff --git a/tools/testing/kunit/qemu_configs/sh.py b/tools/testing/kunit/qemu_configs/sh.py
index 78a474a..f00cb89 100644
--- a/tools/testing/kunit/qemu_configs/sh.py
+++ b/tools/testing/kunit/qemu_configs/sh.py
@@ -7,7 +7,9 @@
CONFIG_MEMORY_START=0x0c000000
CONFIG_SH_RTS7751R2D=y
CONFIG_RTS7751R2D_PLUS=y
-CONFIG_SERIAL_SH_SCI=y''',
+CONFIG_SERIAL_SH_SCI=y
+CONFIG_CMDLINE_EXTEND=y
+''',
qemu_arch='sh4',
kernel_path='arch/sh/boot/zImage',
kernel_command_line='console=ttySC1',
diff --git a/tools/testing/memblock/internal.h b/tools/testing/memblock/internal.h
index 1cf82ac..0ab4b53 100644
--- a/tools/testing/memblock/internal.h
+++ b/tools/testing/memblock/internal.h
@@ -24,4 +24,10 @@ static inline void accept_memory(phys_addr_t start, unsigned long size)
{
}
+static inline unsigned long free_reserved_area(void *start, void *end,
+ int poison, const char *s)
+{
+ return 0;
+}
+
#endif
diff --git a/tools/testing/memblock/linux/mutex.h b/tools/testing/memblock/linux/mutex.h
new file mode 100644
index 0000000..ae3f497
--- /dev/null
+++ b/tools/testing/memblock/linux/mutex.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _MUTEX_H
+#define _MUTEX_H
+
+#define DEFINE_MUTEX(name) int name
+
+static inline void dummy_mutex_guard(int *name)
+{
+}
+
+#define guard(mutex) \
+ dummy_##mutex##_guard
+
+#endif /* _MUTEX_H */
\ No newline at end of file
diff --git a/tools/testing/memblock/tests/basic_api.c b/tools/testing/memblock/tests/basic_api.c
index 6750308..01e836f 100644
--- a/tools/testing/memblock/tests/basic_api.c
+++ b/tools/testing/memblock/tests/basic_api.c
@@ -2434,6 +2434,107 @@ static int memblock_overlaps_region_checks(void)
return 0;
}
+#ifdef CONFIG_NUMA
+static int memblock_set_node_check(void)
+{
+ unsigned long i, max_reserved;
+ struct memblock_region *rgn;
+ void *orig_region;
+
+ PREFIX_PUSH();
+
+ reset_memblock_regions();
+ memblock_allow_resize();
+
+ dummy_physical_memory_init();
+ memblock_add(dummy_physical_memory_base(), MEM_SIZE);
+ orig_region = memblock.reserved.regions;
+
+ /* Equally Split range to node 0 and 1*/
+ memblock_set_node(memblock_start_of_DRAM(),
+ memblock_phys_mem_size() / 2, &memblock.memory, 0);
+ memblock_set_node(memblock_start_of_DRAM() + memblock_phys_mem_size() / 2,
+ memblock_phys_mem_size() / 2, &memblock.memory, 1);
+
+ ASSERT_EQ(memblock.memory.cnt, 2);
+ rgn = &memblock.memory.regions[0];
+ ASSERT_EQ(rgn->base, memblock_start_of_DRAM());
+ ASSERT_EQ(rgn->size, memblock_phys_mem_size() / 2);
+ ASSERT_EQ(memblock_get_region_node(rgn), 0);
+ rgn = &memblock.memory.regions[1];
+ ASSERT_EQ(rgn->base, memblock_start_of_DRAM() + memblock_phys_mem_size() / 2);
+ ASSERT_EQ(rgn->size, memblock_phys_mem_size() / 2);
+ ASSERT_EQ(memblock_get_region_node(rgn), 1);
+
+ /* Reserve 126 regions with the last one across node boundary */
+ for (i = 0; i < 125; i++)
+ memblock_reserve(memblock_start_of_DRAM() + SZ_16 * i, SZ_8);
+
+ memblock_reserve(memblock_start_of_DRAM() + memblock_phys_mem_size() / 2 - SZ_8,
+ SZ_16);
+
+ /*
+ * Commit 61167ad5fecd ("mm: pass nid to reserve_bootmem_region()")
+ * do following process to set nid to each memblock.reserved region.
+ * But it may miss some region if memblock_set_node() double the
+ * array.
+ *
+ * By checking 'max', we make sure all region nid is set properly.
+ */
+repeat:
+ max_reserved = memblock.reserved.max;
+ for_each_mem_region(rgn) {
+ int nid = memblock_get_region_node(rgn);
+
+ memblock_set_node(rgn->base, rgn->size, &memblock.reserved, nid);
+ }
+ if (max_reserved != memblock.reserved.max)
+ goto repeat;
+
+ /* Confirm each region has valid node set */
+ for_each_reserved_mem_region(rgn) {
+ ASSERT_TRUE(numa_valid_node(memblock_get_region_node(rgn)));
+ if (rgn == (memblock.reserved.regions + memblock.reserved.cnt - 1))
+ ASSERT_EQ(1, memblock_get_region_node(rgn));
+ else
+ ASSERT_EQ(0, memblock_get_region_node(rgn));
+ }
+
+ dummy_physical_memory_cleanup();
+
+ /*
+ * The current reserved.regions is occupying a range of memory that
+ * allocated from dummy_physical_memory_init(). After free the memory,
+ * we must not use it. So restore the origin memory region to make sure
+ * the tests can run as normal and not affected by the double array.
+ */
+ memblock.reserved.regions = orig_region;
+ memblock.reserved.cnt = INIT_MEMBLOCK_RESERVED_REGIONS;
+
+ test_pass_pop();
+
+ return 0;
+}
+
+static int memblock_set_node_checks(void)
+{
+ prefix_reset();
+ prefix_push("memblock_set_node");
+ test_print("Running memblock_set_node tests...\n");
+
+ memblock_set_node_check();
+
+ prefix_pop();
+
+ return 0;
+}
+#else
+static int memblock_set_node_checks(void)
+{
+ return 0;
+}
+#endif
+
int memblock_basic_checks(void)
{
memblock_initialization_check();
@@ -2444,6 +2545,7 @@ int memblock_basic_checks(void)
memblock_bottom_up_checks();
memblock_trim_memory_checks();
memblock_overlaps_region_checks();
+ memblock_set_node_checks();
return 0;
}
diff --git a/tools/testing/selftests/.gitignore b/tools/testing/selftests/.gitignore
index cb24124..674aaa02 100644
--- a/tools/testing/selftests/.gitignore
+++ b/tools/testing/selftests/.gitignore
@@ -4,7 +4,6 @@
gpioinclude/
gpiolsgpio
kselftest_install/
-tpm2/SpaceTest.log
# Python bytecode and cache
__pycache__/
diff --git a/tools/testing/selftests/bpf/config.x86_64 b/tools/testing/selftests/bpf/config.x86_64
index 5680bef..5e713ef 100644
--- a/tools/testing/selftests/bpf/config.x86_64
+++ b/tools/testing/selftests/bpf/config.x86_64
@@ -39,7 +39,6 @@
CONFIG_CPU_FREQ_STAT=y
CONFIG_CPU_IDLE_GOV_LADDER=y
CONFIG_CPUSETS=y
-CONFIG_CRC_T10DIF=y
CONFIG_CRYPTO_BLAKE2B=y
CONFIG_CRYPTO_SEQIV=y
CONFIG_CRYPTO_XXHASH=y
diff --git a/tools/testing/selftests/bpf/prog_tests/for_each.c b/tools/testing/selftests/bpf/prog_tests/for_each.c
index 09f6487..5fea320 100644
--- a/tools/testing/selftests/bpf/prog_tests/for_each.c
+++ b/tools/testing/selftests/bpf/prog_tests/for_each.c
@@ -6,6 +6,7 @@
#include "for_each_array_map_elem.skel.h"
#include "for_each_map_elem_write_key.skel.h"
#include "for_each_multi_maps.skel.h"
+#include "for_each_hash_modify.skel.h"
static unsigned int duration;
@@ -203,6 +204,40 @@ static void test_multi_maps(void)
for_each_multi_maps__destroy(skel);
}
+static void test_hash_modify(void)
+{
+ struct for_each_hash_modify *skel;
+ int max_entries, i, err;
+ __u64 key, val;
+
+ LIBBPF_OPTS(bpf_test_run_opts, topts,
+ .data_in = &pkt_v4,
+ .data_size_in = sizeof(pkt_v4),
+ .repeat = 1
+ );
+
+ skel = for_each_hash_modify__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "for_each_hash_modify__open_and_load"))
+ return;
+
+ max_entries = bpf_map__max_entries(skel->maps.hashmap);
+ for (i = 0; i < max_entries; i++) {
+ key = i;
+ val = i;
+ err = bpf_map__update_elem(skel->maps.hashmap, &key, sizeof(key),
+ &val, sizeof(val), BPF_ANY);
+ if (!ASSERT_OK(err, "map_update"))
+ goto out;
+ }
+
+ err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_pkt_access), &topts);
+ ASSERT_OK(err, "bpf_prog_test_run_opts");
+ ASSERT_OK(topts.retval, "retval");
+
+out:
+ for_each_hash_modify__destroy(skel);
+}
+
void test_for_each(void)
{
if (test__start_subtest("hash_map"))
@@ -213,4 +248,6 @@ void test_for_each(void)
test_write_map_key();
if (test__start_subtest("multi_maps"))
test_multi_maps();
+ if (test__start_subtest("hash_modify"))
+ test_hash_modify();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c b/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c
index 115287b..0703e98 100644
--- a/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c
@@ -25,8 +25,11 @@ static void *spin_lock_thread(void *arg)
while (!READ_ONCE(skip)) {
err = bpf_prog_test_run_opts(prog_fd, &topts);
- ASSERT_OK(err, "test_run");
- ASSERT_OK(topts.retval, "test_run retval");
+ if (err || topts.retval) {
+ ASSERT_OK(err, "test_run");
+ ASSERT_OK(topts.retval, "test_run retval");
+ break;
+ }
}
pthread_exit(arg);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
index 2d07963..0a99fd4 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
@@ -68,7 +68,6 @@ static void test_sockmap_ktls_disconnect_after_delete(int family, int map)
goto close_cli;
err = disconnect(cli);
- ASSERT_OK(err, "disconnect");
close_cli:
close(cli);
diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index 13a2e22..863df7c 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -221,7 +221,7 @@
#define CAN_USE_GOTOL
#endif
-#if _clang_major__ >= 18
+#if __clang_major__ >= 18
#define CAN_USE_BPF_ST
#endif
diff --git a/tools/testing/selftests/bpf/progs/for_each_hash_modify.c b/tools/testing/selftests/bpf/progs/for_each_hash_modify.c
new file mode 100644
index 0000000..8230716
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/for_each_hash_modify.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Intel Corporation */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 128);
+ __type(key, __u64);
+ __type(value, __u64);
+} hashmap SEC(".maps");
+
+static int cb(struct bpf_map *map, __u64 *key, __u64 *val, void *arg)
+{
+ bpf_map_delete_elem(map, key);
+ bpf_map_update_elem(map, key, val, 0);
+ return 0;
+}
+
+SEC("tc")
+int test_pkt_access(struct __sk_buff *skb)
+{
+ (void)skb;
+
+ bpf_for_each_map_elem(&hashmap, cb, NULL, 0);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/res_spin_lock.c b/tools/testing/selftests/bpf/progs/res_spin_lock.c
index b33385d..22c4fb8 100644
--- a/tools/testing/selftests/bpf/progs/res_spin_lock.c
+++ b/tools/testing/selftests/bpf/progs/res_spin_lock.c
@@ -38,13 +38,14 @@ int res_spin_lock_test(struct __sk_buff *ctx)
r = bpf_res_spin_lock(&elem1->lock);
if (r)
return r;
- if (!bpf_res_spin_lock(&elem2->lock)) {
+ r = bpf_res_spin_lock(&elem2->lock);
+ if (!r) {
bpf_res_spin_unlock(&elem2->lock);
bpf_res_spin_unlock(&elem1->lock);
return -1;
}
bpf_res_spin_unlock(&elem1->lock);
- return 0;
+ return r != -EDEADLK;
}
SEC("tc")
@@ -124,12 +125,15 @@ int res_spin_lock_test_held_lock_max(struct __sk_buff *ctx)
/* Trigger AA, after exhausting entries in the held lock table. This
* time, only the timeout can save us, as AA detection won't succeed.
*/
- if (!bpf_res_spin_lock(locks[34])) {
+ ret = bpf_res_spin_lock(locks[34]);
+ if (!ret) {
bpf_res_spin_unlock(locks[34]);
ret = 1;
goto end;
}
+ ret = ret != -ETIMEDOUT ? 2 : 0;
+
end:
for (i = i - 1; i >= 0; i--)
bpf_res_spin_unlock(locks[i]);
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index 400a696..a17256d 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -88,22 +88,32 @@
# If isolated CPUs have been reserved at boot time (as shown in
# cpuset.cpus.isolated), these isolated CPUs should be outside of CPUs 0-8
# that will be used by this script for testing purpose. If not, some of
-# the tests may fail incorrectly. These pre-isolated CPUs should stay in
-# an isolated state throughout the testing process for now.
+# the tests may fail incorrectly. Wait a bit and retry again just in case
+# these isolated CPUs are leftover from previous run and have just been
+# cleaned up earlier in this script.
+#
+# These pre-isolated CPUs should stay in an isolated state throughout the
+# testing process for now.
#
BOOT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated)
+[[ -n "$BOOT_ISOLCPUS" ]] && {
+ sleep 0.5
+ BOOT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated)
+}
if [[ -n "$BOOT_ISOLCPUS" ]]
then
[[ $(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//") -le 8 ]] &&
skip_test "Pre-isolated CPUs ($BOOT_ISOLCPUS) overlap CPUs to be tested"
echo "Pre-isolated CPUs: $BOOT_ISOLCPUS"
fi
+
cleanup()
{
online_cpus
cd $CGROUP2
- rmdir A1/A2/A3 A1/A2 A1 B1 > /dev/null 2>&1
- rmdir test > /dev/null 2>&1
+ rmdir A1/A2/A3 A1/A2 A1 B1 test/A1 test/B1 test > /dev/null 2>&1
+ rmdir rtest/p1/c11 rtest/p1/c12 rtest/p2/c21 \
+ rtest/p2/c22 rtest/p1 rtest/p2 rtest > /dev/null 2>&1
[[ -n "$SCHED_DEBUG" ]] &&
echo "$SCHED_DEBUG" > /sys/kernel/debug/sched/verbose
}
@@ -173,14 +183,22 @@
#
# Cgroup test hierarchy
#
-# root -- A1 -- A2 -- A3
-# +- B1
+# root
+# |
+# +------+------+
+# | |
+# A1 B1
+# |
+# A2
+# |
+# A3
#
# P<v> = set cpus.partition (0:member, 1:root, 2:isolated)
# C<l> = add cpu-list to cpuset.cpus
# X<l> = add cpu-list to cpuset.cpus.exclusive
# S<p> = use prefix in subtree_control
# T = put a task into cgroup
+# CX<l> = add cpu-list to both cpuset.cpus and cpuset.cpus.exclusive
# O<c>=<v> = Write <v> to CPU online file of <c>
#
# ECPUs - effective CPUs of cpusets
@@ -207,130 +225,129 @@
" C0-1:P1 . . C2-3 S+:C4-5 . . . 0 A1:4-5"
" C0-1 . . C2-3:P1 . . . C2 0 "
" C0-1 . . C2-3:P1 . . . C4-5 0 B1:4-5"
- "C0-3:P1:S+ C2-3:P1 . . . . . . 0 A1:0-1,A2:2-3"
- "C0-3:P1:S+ C2-3:P1 . . C1-3 . . . 0 A1:1,A2:2-3"
- "C2-3:P1:S+ C3:P1 . . C3 . . . 0 A1:,A2:3 A1:P1,A2:P1"
- "C2-3:P1:S+ C3:P1 . . C3 P0 . . 0 A1:3,A2:3 A1:P1,A2:P0"
- "C2-3:P1:S+ C2:P1 . . C2-4 . . . 0 A1:3-4,A2:2"
- "C2-3:P1:S+ C3:P1 . . C3 . . C0-2 0 A1:,B1:0-2 A1:P1,A2:P1"
- "$SETUP_A123_PARTITIONS . C2-3 . . . 0 A1:,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
+ "C0-3:P1:S+ C2-3:P1 . . . . . . 0 A1:0-1|A2:2-3|XA2:2-3"
+ "C0-3:P1:S+ C2-3:P1 . . C1-3 . . . 0 A1:1|A2:2-3|XA2:2-3"
+ "C2-3:P1:S+ C3:P1 . . C3 . . . 0 A1:|A2:3|XA2:3 A1:P1|A2:P1"
+ "C2-3:P1:S+ C3:P1 . . C3 P0 . . 0 A1:3|A2:3 A1:P1|A2:P0"
+ "C2-3:P1:S+ C2:P1 . . C2-4 . . . 0 A1:3-4|A2:2"
+ "C2-3:P1:S+ C3:P1 . . C3 . . C0-2 0 A1:|B1:0-2 A1:P1|A2:P1"
+ "$SETUP_A123_PARTITIONS . C2-3 . . . 0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
# CPU offlining cases:
- " C0-1 . . C2-3 S+ C4-5 . O2=0 0 A1:0-1,B1:3"
- "C0-3:P1:S+ C2-3:P1 . . O2=0 . . . 0 A1:0-1,A2:3"
- "C0-3:P1:S+ C2-3:P1 . . O2=0 O2=1 . . 0 A1:0-1,A2:2-3"
- "C0-3:P1:S+ C2-3:P1 . . O1=0 . . . 0 A1:0,A2:2-3"
- "C0-3:P1:S+ C2-3:P1 . . O1=0 O1=1 . . 0 A1:0-1,A2:2-3"
- "C2-3:P1:S+ C3:P1 . . O3=0 O3=1 . . 0 A1:2,A2:3 A1:P1,A2:P1"
- "C2-3:P1:S+ C3:P2 . . O3=0 O3=1 . . 0 A1:2,A2:3 A1:P1,A2:P2"
- "C2-3:P1:S+ C3:P1 . . O2=0 O2=1 . . 0 A1:2,A2:3 A1:P1,A2:P1"
- "C2-3:P1:S+ C3:P2 . . O2=0 O2=1 . . 0 A1:2,A2:3 A1:P1,A2:P2"
- "C2-3:P1:S+ C3:P1 . . O2=0 . . . 0 A1:,A2:3 A1:P1,A2:P1"
- "C2-3:P1:S+ C3:P1 . . O3=0 . . . 0 A1:2,A2: A1:P1,A2:P1"
- "C2-3:P1:S+ C3:P1 . . T:O2=0 . . . 0 A1:3,A2:3 A1:P1,A2:P-1"
- "C2-3:P1:S+ C3:P1 . . . T:O3=0 . . 0 A1:2,A2:2 A1:P1,A2:P-1"
- "$SETUP_A123_PARTITIONS . O1=0 . . . 0 A1:,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
- "$SETUP_A123_PARTITIONS . O2=0 . . . 0 A1:1,A2:,A3:3 A1:P1,A2:P1,A3:P1"
- "$SETUP_A123_PARTITIONS . O3=0 . . . 0 A1:1,A2:2,A3: A1:P1,A2:P1,A3:P1"
- "$SETUP_A123_PARTITIONS . T:O1=0 . . . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1"
- "$SETUP_A123_PARTITIONS . . T:O2=0 . . 0 A1:1,A2:3,A3:3 A1:P1,A2:P1,A3:P-1"
- "$SETUP_A123_PARTITIONS . . . T:O3=0 . 0 A1:1,A2:2,A3:2 A1:P1,A2:P1,A3:P-1"
- "$SETUP_A123_PARTITIONS . T:O1=0 O1=1 . . 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
- "$SETUP_A123_PARTITIONS . . T:O2=0 O2=1 . 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
- "$SETUP_A123_PARTITIONS . . . T:O3=0 O3=1 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
- "$SETUP_A123_PARTITIONS . T:O1=0 O2=0 O1=1 . 0 A1:1,A2:,A3:3 A1:P1,A2:P1,A3:P1"
- "$SETUP_A123_PARTITIONS . T:O1=0 O2=0 O2=1 . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1"
+ " C0-1 . . C2-3 S+ C4-5 . O2=0 0 A1:0-1|B1:3"
+ "C0-3:P1:S+ C2-3:P1 . . O2=0 . . . 0 A1:0-1|A2:3"
+ "C0-3:P1:S+ C2-3:P1 . . O2=0 O2=1 . . 0 A1:0-1|A2:2-3"
+ "C0-3:P1:S+ C2-3:P1 . . O1=0 . . . 0 A1:0|A2:2-3"
+ "C0-3:P1:S+ C2-3:P1 . . O1=0 O1=1 . . 0 A1:0-1|A2:2-3"
+ "C2-3:P1:S+ C3:P1 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P1"
+ "C2-3:P1:S+ C3:P2 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P2"
+ "C2-3:P1:S+ C3:P1 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P1"
+ "C2-3:P1:S+ C3:P2 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P2"
+ "C2-3:P1:S+ C3:P1 . . O2=0 . . . 0 A1:|A2:3 A1:P1|A2:P1"
+ "C2-3:P1:S+ C3:P1 . . O3=0 . . . 0 A1:2|A2: A1:P1|A2:P1"
+ "C2-3:P1:S+ C3:P1 . . T:O2=0 . . . 0 A1:3|A2:3 A1:P1|A2:P-1"
+ "C2-3:P1:S+ C3:P1 . . . T:O3=0 . . 0 A1:2|A2:2 A1:P1|A2:P-1"
+ "$SETUP_A123_PARTITIONS . O1=0 . . . 0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
+ "$SETUP_A123_PARTITIONS . O2=0 . . . 0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1"
+ "$SETUP_A123_PARTITIONS . O3=0 . . . 0 A1:1|A2:2|A3: A1:P1|A2:P1|A3:P1"
+ "$SETUP_A123_PARTITIONS . T:O1=0 . . . 0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1"
+ "$SETUP_A123_PARTITIONS . . T:O2=0 . . 0 A1:1|A2:3|A3:3 A1:P1|A2:P1|A3:P-1"
+ "$SETUP_A123_PARTITIONS . . . T:O3=0 . 0 A1:1|A2:2|A3:2 A1:P1|A2:P1|A3:P-1"
+ "$SETUP_A123_PARTITIONS . T:O1=0 O1=1 . . 0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
+ "$SETUP_A123_PARTITIONS . . T:O2=0 O2=1 . 0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
+ "$SETUP_A123_PARTITIONS . . . T:O3=0 O3=1 0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
+ "$SETUP_A123_PARTITIONS . T:O1=0 O2=0 O1=1 . 0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1"
+ "$SETUP_A123_PARTITIONS . T:O1=0 O2=0 O2=1 . 0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1"
# old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
# ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
#
# Remote partition and cpuset.cpus.exclusive tests
#
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 . . . 0 A1:0-3,A2:1-3,A3:2-3,XA1:2-3"
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3:P2 . . 0 A1:0-1,A2:2-3,A3:2-3 A1:P0,A2:P2 2-3"
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 X3:P2 . . 0 A1:0-2,A2:3,A3:3 A1:P0,A2:P2 3"
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2 . 0 A1:0-1,A2:1,A3:2-3 A1:P0,A3:P2 2-3"
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:C3 . 0 A1:0-1,A2:1,A3:2-3 A1:P0,A3:P2 2-3"
- " C0-3:S+ C1-3:S+ C2-3 C2-3 . . . P2 0 A1:0-3,A2:1-3,A3:2-3,B1:2-3 A1:P0,A3:P0,B1:P-2"
+ " C0-3:S+ C1-3:S+ C2-3 . X2-3 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3"
+ " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3:P2 . . 0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3"
+ " C0-3:S+ C1-3:S+ C2-3 . X2-3 X3:P2 . . 0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3"
+ " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+ " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:C3 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+ " C0-3:S+ C1-3:S+ C2-3 C2-3 . . . P2 0 A1:0-3|A2:1-3|A3:2-3|B1:2-3 A1:P0|A3:P0|B1:P-2"
" C0-3:S+ C1-3:S+ C2-3 C4-5 . . . P2 0 B1:4-5 B1:P2 4-5"
- " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2 0 A3:2-3,B1:4 A3:P2,B1:P2 2-4"
- " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2:C1-3 P2 0 A3:2-3,B1:4 A3:P2,B1:P2 2-4"
- " C0-3:S+ C1-3:S+ C2-3 C4 X1-3 X1-3:P2 P2 . 0 A2:1,A3:2-3 A2:P2,A3:P2 1-3"
- " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2:C4-5 0 A3:2-3,B1:4-5 A3:P2,B1:P2 2-5"
- " C4:X0-3:S+ X1-3:S+ X2-3 . . P2 . . 0 A1:4,A2:1-3,A3:1-3 A2:P2 1-3"
- " C4:X0-3:S+ X1-3:S+ X2-3 . . . P2 . 0 A1:4,A2:4,A3:2-3 A3:P2 2-3"
+ " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
+ " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2:C1-3 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
+ " C0-3:S+ C1-3:S+ C2-3 C4 X1-3 X1-3:P2 P2 . 0 A2:1|A3:2-3 A2:P2|A3:P2 1-3"
+ " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5"
+ " C4:X0-3:S+ X1-3:S+ X2-3 . . P2 . . 0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3"
+ " C4:X0-3:S+ X1-3:S+ X2-3 . . . P2 . 0 A1:4|A2:4|A3:2-3 A3:P2 2-3"
# Nested remote/local partition tests
- " C0-3:S+ C1-3:S+ C2-3 C4-5 X2-3 X2-3:P1 P2 P1 0 A1:0-1,A2:,A3:2-3,B1:4-5 \
- A1:P0,A2:P1,A3:P2,B1:P1 2-3"
- " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1,A2:,A3:2-3,B1:4 \
- A1:P0,A2:P1,A3:P2,B1:P1 2-4,2-3"
- " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 . P1 0 A1:0-1,A2:2-3,A3:2-3,B1:4 \
- A1:P0,A2:P1,A3:P0,B1:P1"
- " C0-3:S+ C1-3:S+ C3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1,A2:2,A3:3,B1:4 \
- A1:P0,A2:P1,A3:P2,B1:P1 2-4,3"
- " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X4:P1 . 0 A1:0-1,A2:2-3,A3:4 \
- A1:P0,A2:P2,A3:P1 2-4,2-3"
- " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X3-4:P1 . 0 A1:0-1,A2:2,A3:3-4 \
- A1:P0,A2:P2,A3:P1 2"
+ " C0-3:S+ C1-3:S+ C2-3 C4-5 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4-5 \
+ A1:P0|A2:P1|A3:P2|B1:P1 2-3"
+ " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4 \
+ A1:P0|A2:P1|A3:P2|B1:P1 2-4|2-3"
+ " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 . P1 0 A1:0-1|A2:2-3|A3:2-3|B1:4 \
+ A1:P0|A2:P1|A3:P0|B1:P1"
+ " C0-3:S+ C1-3:S+ C3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:2|A3:3|B1:4 \
+ A1:P0|A2:P1|A3:P2|B1:P1 2-4|3"
+ " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X4:P1 . 0 A1:0-1|A2:2-3|A3:4 \
+ A1:P0|A2:P2|A3:P1 2-4|2-3"
+ " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X3-4:P1 . 0 A1:0-1|A2:2|A3:3-4 \
+ A1:P0|A2:P2|A3:P1 2"
" C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \
- . . X5 . . 0 A1:0-4,A2:1-4,A3:2-4 \
- A1:P0,A2:P-2,A3:P-1"
+ . . X5 . . 0 A1:0-4|A2:1-4|A3:2-4 \
+ A1:P0|A2:P-2|A3:P-1 ."
" C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \
- . . . X1 . 0 A1:0-1,A2:2-4,A3:2-4 \
- A1:P0,A2:P2,A3:P-1 2-4"
+ . . . X1 . 0 A1:0-1|A2:2-4|A3:2-4 \
+ A1:P0|A2:P2|A3:P-1 2-4"
# Remote partition offline tests
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:O2=0 . 0 A1:0-1,A2:1,A3:3 A1:P0,A3:P2 2-3"
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1,A2:1,A3:2-3 A1:P0,A3:P2 2-3"
- " C0-3:S+ C1-3:S+ C3 . X2-3 X2-3 P2:O3=0 . 0 A1:0-2,A2:1-2,A3: A1:P0,A3:P2 3"
- " C0-3:S+ C1-3:S+ C3 . X2-3 X2-3 T:P2:O3=0 . 0 A1:0-2,A2:1-2,A3:1-2 A1:P0,A3:P-2 3,"
+ " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:O2=0 . 0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3"
+ " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+ " C0-3:S+ C1-3:S+ C3 . X2-3 X2-3 P2:O3=0 . 0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3"
+ " C0-3:S+ C1-3:S+ C3 . X2-3 X2-3 T:P2:O3=0 . 0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|"
# An invalidated remote partition cannot self-recover from hotplug
- " C0-3:S+ C1-3:S+ C2 . X2-3 X2-3 T:P2:O2=0 O2=1 0 A1:0-3,A2:1-3,A3:2 A1:P0,A3:P-2"
+ " C0-3:S+ C1-3:S+ C2 . X2-3 X2-3 T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ."
# cpus.exclusive.effective clearing test
- " C0-3:S+ C1-3:S+ C2 . X2-3:X . . . 0 A1:0-3,A2:1-3,A3:2,XA1:"
+ " C0-3:S+ C1-3:S+ C2 . X2-3:X . . . 0 A1:0-3|A2:1-3|A3:2|XA1:"
# Invalid to valid remote partition transition test
- " C0-3:S+ C1-3 . . . X3:P2 . . 0 A1:0-3,A2:1-3,XA2: A2:P-2"
+ " C0-3:S+ C1-3 . . . X3:P2 . . 0 A1:0-3|A2:1-3|XA2: A2:P-2 ."
" C0-3:S+ C1-3:X3:P2
- . . X2-3 P2 . . 0 A1:0-2,A2:3,XA2:3 A2:P2 3"
+ . . X2-3 P2 . . 0 A1:0-2|A2:3|XA2:3 A2:P2 3"
# Invalid to valid local partition direct transition tests
- " C1-3:S+:P2 X4:P2 . . . . . . 0 A1:1-3,XA1:1-3,A2:1-3:XA2: A1:P2,A2:P-2 1-3"
- " C1-3:S+:P2 X4:P2 . . . X3:P2 . . 0 A1:1-2,XA1:1-3,A2:3:XA2:3 A1:P2,A2:P2 1-3"
- " C0-3:P2 . . C4-6 C0-4 . . . 0 A1:0-4,B1:4-6 A1:P-2,B1:P0"
- " C0-3:P2 . . C4-6 C0-4:C0-3 . . . 0 A1:0-3,B1:4-6 A1:P2,B1:P0 0-3"
- " C0-3:P2 . . C3-5:C4-5 . . . . 0 A1:0-3,B1:4-5 A1:P2,B1:P0 0-3"
+ " C1-3:S+:P2 X4:P2 . . . . . . 0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3"
+ " C1-3:S+:P2 X4:P2 . . . X3:P2 . . 0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3"
+ " C0-3:P2 . . C4-6 C0-4 . . . 0 A1:0-4|B1:4-6 A1:P-2|B1:P0"
+ " C0-3:P2 . . C4-6 C0-4:C0-3 . . . 0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3"
# Local partition invalidation tests
" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
- . . . . . 0 A1:1,A2:2,A3:3 A1:P2,A2:P2,A3:P2 1-3"
+ . . . . . 0 A1:1|A2:2|A3:3 A1:P2|A2:P2|A3:P2 1-3"
" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
- . . X4 . . 0 A1:1-3,A2:1-3,A3:2-3,XA2:,XA3: A1:P2,A2:P-2,A3:P-2 1-3"
+ . . X4 . . 0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3"
" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
- . . C4:X . . 0 A1:1-3,A2:1-3,A3:2-3,XA2:,XA3: A1:P2,A2:P-2,A3:P-2 1-3"
+ . . C4:X . . 0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3"
# Local partition CPU change tests
- " C0-5:S+:P2 C4-5:S+:P1 . . . C3-5 . . 0 A1:0-2,A2:3-5 A1:P2,A2:P1 0-2"
- " C0-5:S+:P2 C4-5:S+:P1 . . C1-5 . . . 0 A1:1-3,A2:4-5 A1:P2,A2:P1 1-3"
+ " C0-5:S+:P2 C4-5:S+:P1 . . . C3-5 . . 0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2"
+ " C0-5:S+:P2 C4-5:S+:P1 . . C1-5 . . . 0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3"
# cpus_allowed/exclusive_cpus update tests
" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
- . X:C4 . P2 . 0 A1:4,A2:4,XA2:,XA3:,A3:4 \
- A1:P0,A3:P-2"
+ . X:C4 . P2 . 0 A1:4|A2:4|XA2:|XA3:|A3:4 \
+ A1:P0|A3:P-2 ."
" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
- . X1 . P2 . 0 A1:0-3,A2:1-3,XA1:1,XA2:,XA3:,A3:2-3 \
- A1:P0,A3:P-2"
+ . X1 . P2 . 0 A1:0-3|A2:1-3|XA1:1|XA2:|XA3:|A3:2-3 \
+ A1:P0|A3:P-2 ."
" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
- . . X3 P2 . 0 A1:0-2,A2:1-2,XA2:3,XA3:3,A3:3 \
- A1:P0,A3:P2 3"
+ . . X3 P2 . 0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3 \
+ A1:P0|A3:P2 3"
" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
- . . X3 . . 0 A1:0-3,A2:1-3,XA2:3,XA3:3,A3:2-3 \
- A1:P0,A3:P-2"
+ . . X3 . . 0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3|XA3:3 \
+ A1:P0|A3:P2 3"
" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
- . X4 . . . 0 A1:0-3,A2:1-3,A3:2-3,XA1:4,XA2:,XA3 \
- A1:P0,A3:P-2"
+ . X4 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:4|XA2:|XA3 \
+ A1:P0|A3:P-2"
# old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
# ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
@@ -339,68 +356,127 @@
#
# Adding CPUs to partition root that are not in parent's
# cpuset.cpus is allowed, but those extra CPUs are ignored.
- "C2-3:P1:S+ C3:P1 . . . C2-4 . . 0 A1:,A2:2-3 A1:P1,A2:P1"
+ "C2-3:P1:S+ C3:P1 . . . C2-4 . . 0 A1:|A2:2-3 A1:P1|A2:P1"
# Taking away all CPUs from parent or itself if there are tasks
# will make the partition invalid.
- "C2-3:P1:S+ C3:P1 . . T C2-3 . . 0 A1:2-3,A2:2-3 A1:P1,A2:P-1"
- " C3:P1:S+ C3 . . T P1 . . 0 A1:3,A2:3 A1:P1,A2:P-1"
- "$SETUP_A123_PARTITIONS . T:C2-3 . . . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1"
- "$SETUP_A123_PARTITIONS . T:C2-3:C1-3 . . . 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
+ "C2-3:P1:S+ C3:P1 . . T C2-3 . . 0 A1:2-3|A2:2-3 A1:P1|A2:P-1"
+ " C3:P1:S+ C3 . . T P1 . . 0 A1:3|A2:3 A1:P1|A2:P-1"
+ "$SETUP_A123_PARTITIONS . T:C2-3 . . . 0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1"
+ "$SETUP_A123_PARTITIONS . T:C2-3:C1-3 . . . 0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
# Changing a partition root to member makes child partitions invalid
- "C2-3:P1:S+ C3:P1 . . P0 . . . 0 A1:2-3,A2:3 A1:P0,A2:P-1"
- "$SETUP_A123_PARTITIONS . C2-3 P0 . . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P0,A3:P-1"
+ "C2-3:P1:S+ C3:P1 . . P0 . . . 0 A1:2-3|A2:3 A1:P0|A2:P-1"
+ "$SETUP_A123_PARTITIONS . C2-3 P0 . . 0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P0|A3:P-1"
# cpuset.cpus can contains cpus not in parent's cpuset.cpus as long
# as they overlap.
- "C2-3:P1:S+ . . . . C3-4:P1 . . 0 A1:2,A2:3 A1:P1,A2:P1"
+ "C2-3:P1:S+ . . . . C3-4:P1 . . 0 A1:2|A2:3 A1:P1|A2:P1"
# Deletion of CPUs distributed to child cgroup is allowed.
- "C0-1:P1:S+ C1 . C2-3 C4-5 . . . 0 A1:4-5,A2:4-5"
+ "C0-1:P1:S+ C1 . C2-3 C4-5 . . . 0 A1:4-5|A2:4-5"
# To become a valid partition root, cpuset.cpus must overlap parent's
# cpuset.cpus.
- " C0-1:P1 . . C2-3 S+ C4-5:P1 . . 0 A1:0-1,A2:0-1 A1:P1,A2:P-1"
+ " C0-1:P1 . . C2-3 S+ C4-5:P1 . . 0 A1:0-1|A2:0-1 A1:P1|A2:P-1"
# Enabling partition with child cpusets is allowed
- " C0-1:S+ C1 . C2-3 P1 . . . 0 A1:0-1,A2:1 A1:P1"
+ " C0-1:S+ C1 . C2-3 P1 . . . 0 A1:0-1|A2:1 A1:P1"
- # A partition root with non-partition root parent is invalid, but it
+ # A partition root with non-partition root parent is invalid| but it
# can be made valid if its parent becomes a partition root too.
- " C0-1:S+ C1 . C2-3 . P2 . . 0 A1:0-1,A2:1 A1:P0,A2:P-2"
- " C0-1:S+ C1:P2 . C2-3 P1 . . . 0 A1:0,A2:1 A1:P1,A2:P2"
+ " C0-1:S+ C1 . C2-3 . P2 . . 0 A1:0-1|A2:1 A1:P0|A2:P-2"
+ " C0-1:S+ C1:P2 . C2-3 P1 . . . 0 A1:0|A2:1 A1:P1|A2:P2 0-1|1"
# A non-exclusive cpuset.cpus change will invalidate partition and its siblings
- " C0-1:P1 . . C2-3 C0-2 . . . 0 A1:0-2,B1:2-3 A1:P-1,B1:P0"
- " C0-1:P1 . . P1:C2-3 C0-2 . . . 0 A1:0-2,B1:2-3 A1:P-1,B1:P-1"
- " C0-1 . . P1:C2-3 C0-2 . . . 0 A1:0-2,B1:2-3 A1:P0,B1:P-1"
+ " C0-1:P1 . . C2-3 C0-2 . . . 0 A1:0-2|B1:2-3 A1:P-1|B1:P0"
+ " C0-1:P1 . . P1:C2-3 C0-2 . . . 0 A1:0-2|B1:2-3 A1:P-1|B1:P-1"
+ " C0-1 . . P1:C2-3 C0-2 . . . 0 A1:0-2|B1:2-3 A1:P0|B1:P-1"
# cpuset.cpus can overlap with sibling cpuset.cpus.exclusive but not subsumed by it
- " C0-3 . . C4-5 X5 . . . 0 A1:0-3,B1:4-5"
+ " C0-3 . . C4-5 X5 . . . 0 A1:0-3|B1:4-5"
# Child partition root that try to take all CPUs from parent partition
# with tasks will remain invalid.
- " C1-4:P1:S+ P1 . . . . . . 0 A1:1-4,A2:1-4 A1:P1,A2:P-1"
- " C1-4:P1:S+ P1 . . . C1-4 . . 0 A1,A2:1-4 A1:P1,A2:P1"
- " C1-4:P1:S+ P1 . . T C1-4 . . 0 A1:1-4,A2:1-4 A1:P1,A2:P-1"
+ " C1-4:P1:S+ P1 . . . . . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
+ " C1-4:P1:S+ P1 . . . C1-4 . . 0 A1|A2:1-4 A1:P1|A2:P1"
+ " C1-4:P1:S+ P1 . . T C1-4 . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
# Clearing of cpuset.cpus with a preset cpuset.cpus.exclusive shouldn't
# affect cpuset.cpus.exclusive.effective.
- " C1-4:X3:S+ C1:X3 . . . C . . 0 A2:1-4,XA2:3"
+ " C1-4:X3:S+ C1:X3 . . . C . . 0 A2:1-4|XA2:3"
+
+ # cpuset.cpus can contain CPUs that overlap a sibling cpuset with cpus.exclusive
+ # but creating a local partition out of it is not allowed. Similarly and change
+ # in cpuset.cpus of a local partition that overlaps sibling exclusive CPUs will
+ # invalidate it.
+ " CX1-4:S+ CX2-4:P2 . C5-6 . . . P1 0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \
+ A1:P0|A2:P2:B1:P1 2-4"
+ " CX1-4:S+ CX2-4:P2 . C3-6 . . . P1 0 A1:1|A2:2-4|B1:5-6 \
+ A1:P0|A2:P2:B1:P-1 2-4"
+ " CX1-4:S+ CX2-4:P2 . C5-6 . . . P1:C3-6 0 A1:1|A2:2-4|B1:5-6 \
+ A1:P0|A2:P2:B1:P-1 2-4"
# old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
# ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
# Failure cases:
# A task cannot be added to a partition with no cpu
- "C2-3:P1:S+ C3:P1 . . O2=0:T . . . 1 A1:,A2:3 A1:P1,A2:P1"
+ "C2-3:P1:S+ C3:P1 . . O2=0:T . . . 1 A1:|A2:3 A1:P1|A2:P1"
# Changes to cpuset.cpus.exclusive that violate exclusivity rule is rejected
- " C0-3 . . C4-5 X0-3 . . X3-5 1 A1:0-3,B1:4-5"
+ " C0-3 . . C4-5 X0-3 . . X3-5 1 A1:0-3|B1:4-5"
# cpuset.cpus cannot be a subset of sibling cpuset.cpus.exclusive
- " C0-3 . . C4-5 X3-5 . . . 1 A1:0-3,B1:4-5"
+ " C0-3 . . C4-5 X3-5 . . . 1 A1:0-3|B1:4-5"
+)
+
+#
+# Cpuset controller remote partition test matrix.
+#
+# Cgroup test hierarchy
+#
+# root
+# |
+# rtest (cpuset.cpus.exclusive=1-7)
+# |
+# +------+------+
+# | |
+# p1 p2
+# +--+--+ +--+--+
+# | | | |
+# c11 c12 c21 c22
+#
+# REMOTE_TEST_MATRIX uses the same notational convention as TEST_MATRIX.
+# Only CPUs 1-7 should be used.
+#
+REMOTE_TEST_MATRIX=(
+ # old-p1 old-p2 old-c11 old-c12 old-c21 old-c22
+ # new-p1 new-p2 new-c11 new-c12 new-c21 new-c22 ECPUs Pstate ISOLCPUS
+ # ------ ------ ------- ------- ------- ------- ----- ------ --------
+ " X1-3:S+ X4-6:S+ X1-2 X3 X4-5 X6 \
+ . . P2 P2 P2 P2 c11:1-2|c12:3|c21:4-5|c22:6 \
+ c11:P2|c12:P2|c21:P2|c22:P2 1-6"
+ " CX1-4:S+ . X1-2:P2 C3 . . \
+ . . . C3-4 . . p1:3-4|c11:1-2|c12:3-4 \
+ p1:P0|c11:P2|c12:P0 1-2"
+ " CX1-4:S+ . X1-2:P2 . . . \
+ X2-4 . . . . . p1:1,3-4|c11:2 \
+ p1:P0|c11:P2 2"
+ " CX1-5:S+ . X1-2:P2 X3-5:P1 . . \
+ X2-4 . . . . . p1:1,5|c11:2|c12:3-4 \
+ p1:P0|c11:P2|c12:P1 2"
+ " CX1-4:S+ . X1-2:P2 X3-4:P1 . . \
+ . . X2 . . . p1:1|c11:2|c12:3-4 \
+ p1:P0|c11:P2|c12:P1 2"
+ # p1 as member, will get its effective CPUs from its parent rtest
+ " CX1-4:S+ . X1-2:P2 X3-4:P1 . . \
+ . . X1 CX2-4 . . p1:5-7|c11:1|c12:2-4 \
+ p1:P0|c11:P2|c12:P1 1"
+ " CX1-4:S+ X5-6:P1:S+ . . . . \
+ . . X1-2:P2 X4-5:P1 . X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \
+ p1:P0|p2:P1|c11:P2|c12:P1|c22:P2 \
+ 1-2,4-6|1-2,5-6"
)
#
@@ -453,25 +529,26 @@
PFILE=$CGRP/cpuset.cpus.partition
CFILE=$CGRP/cpuset.cpus
XFILE=$CGRP/cpuset.cpus.exclusive
- S=$(expr substr $CMD 1 1)
- if [[ $S = S ]]
- then
- PREFIX=${CMD#?}
+ case $CMD in
+ S*) PREFIX=${CMD#?}
COMM="echo ${PREFIX}${CTRL} > $SFILE"
eval $COMM $REDIRECT
- elif [[ $S = X ]]
- then
+ ;;
+ X*)
CPUS=${CMD#?}
COMM="echo $CPUS > $XFILE"
eval $COMM $REDIRECT
- elif [[ $S = C ]]
- then
- CPUS=${CMD#?}
+ ;;
+ CX*)
+ CPUS=${CMD#??}
+ COMM="echo $CPUS > $CFILE; echo $CPUS > $XFILE"
+ eval $COMM $REDIRECT
+ ;;
+ C*) CPUS=${CMD#?}
COMM="echo $CPUS > $CFILE"
eval $COMM $REDIRECT
- elif [[ $S = P ]]
- then
- VAL=${CMD#?}
+ ;;
+ P*) VAL=${CMD#?}
case $VAL in
0) VAL=member
;;
@@ -486,15 +563,17 @@
esac
COMM="echo $VAL > $PFILE"
eval $COMM $REDIRECT
- elif [[ $S = O ]]
- then
- VAL=${CMD#?}
+ ;;
+ O*) VAL=${CMD#?}
write_cpu_online $VAL
- elif [[ $S = T ]]
- then
- COMM="echo 0 > $TFILE"
+ ;;
+ T*) COMM="echo 0 > $TFILE"
eval $COMM $REDIRECT
- fi
+ ;;
+ *) echo "Unknown command: $CMD"
+ exit 1
+ ;;
+ esac
RET=$?
[[ $RET -ne 0 ]] && {
[[ -n "$SHOWERR" ]] && {
@@ -532,21 +611,18 @@
}
#
-# Return 1 if the list of effective cpus isn't the same as the initial list.
+# Remove all the test cgroup directories
#
reset_cgroup_states()
{
echo 0 > $CGROUP2/cgroup.procs
online_cpus
- rmdir A1/A2/A3 A1/A2 A1 B1 > /dev/null 2>&1
- pause 0.02
- set_ctrl_state . R-
- pause 0.01
+ rmdir $RESET_LIST > /dev/null 2>&1
}
dump_states()
{
- for DIR in . A1 A1/A2 A1/A2/A3 B1
+ for DIR in $CGROUP_LIST
do
CPUS=$DIR/cpuset.cpus
ECPUS=$DIR/cpuset.cpus.effective
@@ -566,17 +642,33 @@
}
#
+# Set the actual cgroup directory into $CGRP_DIR
+# $1 - cgroup name
+#
+set_cgroup_dir()
+{
+ CGRP_DIR=$1
+ [[ $CGRP_DIR = A2 ]] && CGRP_DIR=A1/A2
+ [[ $CGRP_DIR = A3 ]] && CGRP_DIR=A1/A2/A3
+ [[ $CGRP_DIR = c11 ]] && CGRP_DIR=p1/c11
+ [[ $CGRP_DIR = c12 ]] && CGRP_DIR=p1/c12
+ [[ $CGRP_DIR = c21 ]] && CGRP_DIR=p2/c21
+ [[ $CGRP_DIR = c22 ]] && CGRP_DIR=p2/c22
+}
+
+#
# Check effective cpus
-# $1 - check string, format: <cgroup>:<cpu-list>[,<cgroup>:<cpu-list>]*
+# $1 - check string, format: <cgroup>:<cpu-list>[|<cgroup>:<cpu-list>]*
#
check_effective_cpus()
{
CHK_STR=$1
- for CHK in $(echo $CHK_STR | sed -e "s/,/ /g")
+ for CHK in $(echo $CHK_STR | sed -e "s/|/ /g")
do
set -- $(echo $CHK | sed -e "s/:/ /g")
CGRP=$1
- CPUS=$2
+ EXPECTED_CPUS=$2
+ ACTUAL_CPUS=
if [[ $CGRP = X* ]]
then
CGRP=${CGRP#X}
@@ -584,41 +676,39 @@
else
FILE=cpuset.cpus.effective
fi
- [[ $CGRP = A2 ]] && CGRP=A1/A2
- [[ $CGRP = A3 ]] && CGRP=A1/A2/A3
- [[ -e $CGRP/$FILE ]] || return 1
- [[ $CPUS = $(cat $CGRP/$FILE) ]] || return 1
+ set_cgroup_dir $CGRP
+ [[ -e $CGRP_DIR/$FILE ]] || return 1
+ ACTUAL_CPUS=$(cat $CGRP_DIR/$FILE)
+ [[ $EXPECTED_CPUS = $ACTUAL_CPUS ]] || return 1
done
}
#
# Check cgroup states
-# $1 - check string, format: <cgroup>:<state>[,<cgroup>:<state>]*
+# $1 - check string, format: <cgroup>:<state>[|<cgroup>:<state>]*
#
check_cgroup_states()
{
CHK_STR=$1
- for CHK in $(echo $CHK_STR | sed -e "s/,/ /g")
+ for CHK in $(echo $CHK_STR | sed -e "s/|/ /g")
do
set -- $(echo $CHK | sed -e "s/:/ /g")
CGRP=$1
- CGRP_DIR=$CGRP
- STATE=$2
+ EXPECTED_STATE=$2
FILE=
- EVAL=$(expr substr $STATE 2 2)
- [[ $CGRP = A2 ]] && CGRP_DIR=A1/A2
- [[ $CGRP = A3 ]] && CGRP_DIR=A1/A2/A3
+ EVAL=$(expr substr $EXPECTED_STATE 2 2)
- case $STATE in
+ set_cgroup_dir $CGRP
+ case $EXPECTED_STATE in
P*) FILE=$CGRP_DIR/cpuset.cpus.partition
;;
- *) echo "Unknown state: $STATE!"
+ *) echo "Unknown state: $EXPECTED_STATE!"
exit 1
;;
esac
- VAL=$(cat $FILE)
+ ACTUAL_STATE=$(cat $FILE)
- case "$VAL" in
+ case "$ACTUAL_STATE" in
member) VAL=0
;;
root) VAL=1
@@ -642,7 +732,7 @@
[[ $VAL -eq 1 && $VERBOSE -gt 0 ]] && {
DOMS=$(cat $CGRP_DIR/cpuset.cpus.effective)
[[ -n "$DOMS" ]] &&
- echo " [$CGRP] sched-domain: $DOMS" > $CONSOLE
+ echo " [$CGRP_DIR] sched-domain: $DOMS" > $CONSOLE
}
done
return 0
@@ -665,22 +755,22 @@
#
check_isolcpus()
{
- EXPECT_VAL=$1
- ISOLCPUS=
+ EXPECTED_ISOLCPUS=$1
+ ISCPUS=${CGROUP2}/cpuset.cpus.isolated
+ ISOLCPUS=$(cat $ISCPUS)
LASTISOLCPU=
SCHED_DOMAINS=/sys/kernel/debug/sched/domains
- ISCPUS=${CGROUP2}/cpuset.cpus.isolated
- if [[ $EXPECT_VAL = . ]]
+ if [[ $EXPECTED_ISOLCPUS = . ]]
then
- EXPECT_VAL=
- EXPECT_VAL2=
- elif [[ $(expr $EXPECT_VAL : ".*,.*") > 0 ]]
+ EXPECTED_ISOLCPUS=
+ EXPECTED_SDOMAIN=
+ elif [[ $(expr $EXPECTED_ISOLCPUS : ".*|.*") > 0 ]]
then
- set -- $(echo $EXPECT_VAL | sed -e "s/,/ /g")
- EXPECT_VAL=$1
- EXPECT_VAL2=$2
+ set -- $(echo $EXPECTED_ISOLCPUS | sed -e "s/|/ /g")
+ EXPECTED_ISOLCPUS=$2
+ EXPECTED_SDOMAIN=$1
else
- EXPECT_VAL2=$EXPECT_VAL
+ EXPECTED_SDOMAIN=$EXPECTED_ISOLCPUS
fi
#
@@ -689,20 +779,21 @@
# to make appending those CPUs easier.
#
[[ -n "$BOOT_ISOLCPUS" ]] && {
- EXPECT_VAL=${EXPECT_VAL:+${EXPECT_VAL},}${BOOT_ISOLCPUS}
- EXPECT_VAL2=${EXPECT_VAL2:+${EXPECT_VAL2},}${BOOT_ISOLCPUS}
+ EXPECTED_ISOLCPUS=${EXPECTED_ISOLCPUS:+${EXPECTED_ISOLCPUS},}${BOOT_ISOLCPUS}
+ EXPECTED_SDOMAIN=${EXPECTED_SDOMAIN:+${EXPECTED_SDOMAIN},}${BOOT_ISOLCPUS}
}
#
# Check cpuset.cpus.isolated cpumask
#
- [[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && {
+ [[ "$EXPECTED_ISOLCPUS" != "$ISOLCPUS" ]] && {
# Take a 50ms pause and try again
pause 0.05
ISOLCPUS=$(cat $ISCPUS)
}
- [[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && return 1
+ [[ "$EXPECTED_ISOLCPUS" != "$ISOLCPUS" ]] && return 1
ISOLCPUS=
+ EXPECTED_ISOLCPUS=$EXPECTED_SDOMAIN
#
# Use the sched domain in debugfs to check isolated CPUs, if available
@@ -736,7 +827,7 @@
done
[[ "$ISOLCPUS" = *- ]] && ISOLCPUS=${ISOLCPUS}$LASTISOLCPU
- [[ "$EXPECT_VAL" = "$ISOLCPUS" ]]
+ [[ "$EXPECTED_SDOMAIN" = "$ISOLCPUS" ]]
}
test_fail()
@@ -774,6 +865,63 @@
}
#
+# Check state transition test result
+# $1 - Test number
+# $2 - Expected effective CPU values
+# $3 - Expected partition states
+# $4 - Expected isolated CPUs
+#
+check_test_results()
+{
+ _NR=$1
+ _ECPUS="$2"
+ _PSTATES="$3"
+ _ISOLCPUS="$4"
+
+ [[ -n "$_ECPUS" && "$_ECPUS" != . ]] && {
+ check_effective_cpus $_ECPUS
+ [[ $? -ne 0 ]] && test_fail $_NR "effective CPU" \
+ "Cgroup $CGRP: expected $EXPECTED_CPUS, got $ACTUAL_CPUS"
+ }
+
+ [[ -n "$_PSTATES" && "$_PSTATES" != . ]] && {
+ check_cgroup_states $_PSTATES
+ [[ $? -ne 0 ]] && test_fail $_NR states \
+ "Cgroup $CGRP: expected $EXPECTED_STATE, got $ACTUAL_STATE"
+ }
+
+ # Compare the expected isolated CPUs with the actual ones,
+ # if available
+ [[ -n "$_ISOLCPUS" ]] && {
+ check_isolcpus $_ISOLCPUS
+ [[ $? -ne 0 ]] && {
+ [[ -n "$BOOT_ISOLCPUS" ]] && _ISOLCPUS=${_ISOLCPUS},${BOOT_ISOLCPUS}
+ test_fail $_NR "isolated CPU" \
+ "Expect $_ISOLCPUS, get $ISOLCPUS instead"
+ }
+ }
+ reset_cgroup_states
+ #
+ # Check to see if effective cpu list changes
+ #
+ _NEWLIST=$(cat $CGROUP2/cpuset.cpus.effective)
+ RETRY=0
+ while [[ $_NEWLIST != $CPULIST && $RETRY -lt 8 ]]
+ do
+ # Wait a bit longer & recheck a few times
+ pause 0.02
+ ((RETRY++))
+ _NEWLIST=$(cat $CGROUP2/cpuset.cpus.effective)
+ done
+ [[ $_NEWLIST != $CPULIST ]] && {
+ echo "Effective cpus changed to $_NEWLIST after test $_NR!"
+ exit 1
+ }
+ null_isolcpus_check
+ [[ $VERBOSE -gt 0 ]] && echo "Test $I done."
+}
+
+#
# Run cpuset state transition test
# $1 - test matrix name
#
@@ -785,6 +933,8 @@
{
TEST=$1
CONTROLLER=cpuset
+ CGROUP_LIST=". A1 A1/A2 A1/A2/A3 B1"
+ RESET_LIST="A1/A2/A3 A1/A2 A1 B1"
I=0
eval CNT="\${#$TEST[@]}"
@@ -812,10 +962,11 @@
STATES=${11}
ICPUS=${12}
- set_ctrl_state_noerr B1 $OLD_B1
set_ctrl_state_noerr A1 $OLD_A1
set_ctrl_state_noerr A1/A2 $OLD_A2
set_ctrl_state_noerr A1/A2/A3 $OLD_A3
+ set_ctrl_state_noerr B1 $OLD_B1
+
RETVAL=0
set_ctrl_state A1 $NEW_A1; ((RETVAL += $?))
set_ctrl_state A1/A2 $NEW_A2; ((RETVAL += $?))
@@ -824,51 +975,83 @@
[[ $RETVAL -ne $RESULT ]] && test_fail $I result
- [[ -n "$ECPUS" && "$ECPUS" != . ]] && {
- check_effective_cpus $ECPUS
- [[ $? -ne 0 ]] && test_fail $I "effective CPU"
- }
-
- [[ -n "$STATES" && "$STATES" != . ]] && {
- check_cgroup_states $STATES
- [[ $? -ne 0 ]] && test_fail $I states
- }
-
- # Compare the expected isolated CPUs with the actual ones,
- # if available
- [[ -n "$ICPUS" ]] && {
- check_isolcpus $ICPUS
- [[ $? -ne 0 ]] && {
- [[ -n "$BOOT_ISOLCPUS" ]] && ICPUS=${ICPUS},${BOOT_ISOLCPUS}
- test_fail $I "isolated CPU" \
- "Expect $ICPUS, get $ISOLCPUS instead"
- }
- }
- reset_cgroup_states
- #
- # Check to see if effective cpu list changes
- #
- NEWLIST=$(cat cpuset.cpus.effective)
- RETRY=0
- while [[ $NEWLIST != $CPULIST && $RETRY -lt 8 ]]
- do
- # Wait a bit longer & recheck a few times
- pause 0.02
- ((RETRY++))
- NEWLIST=$(cat cpuset.cpus.effective)
- done
- [[ $NEWLIST != $CPULIST ]] && {
- echo "Effective cpus changed to $NEWLIST after test $I!"
- exit 1
- }
- null_isolcpus_check
- [[ $VERBOSE -gt 0 ]] && echo "Test $I done."
+ check_test_results $I "$ECPUS" "$STATES" "$ICPUS"
((I++))
done
echo "All $I tests of $TEST PASSED."
}
#
+# Run cpuset remote partition state transition test
+# $1 - test matrix name
+#
+run_remote_state_test()
+{
+ TEST=$1
+ CONTROLLER=cpuset
+ [[ -d rtest ]] || mkdir rtest
+ cd rtest
+ echo +cpuset > cgroup.subtree_control
+ echo "1-7" > cpuset.cpus
+ echo "1-7" > cpuset.cpus.exclusive
+ CGROUP_LIST=".. . p1 p2 p1/c11 p1/c12 p2/c21 p2/c22"
+ RESET_LIST="p1/c11 p1/c12 p2/c21 p2/c22 p1 p2"
+ I=0
+ eval CNT="\${#$TEST[@]}"
+
+ reset_cgroup_states
+ console_msg "Running remote partition state transition test ..."
+
+ while [[ $I -lt $CNT ]]
+ do
+ echo "Running test $I ..." > $CONSOLE
+ [[ $VERBOSE -gt 1 ]] && {
+ echo ""
+ eval echo \${$TEST[$I]}
+ }
+ eval set -- "\${$TEST[$I]}"
+ OLD_p1=$1
+ OLD_p2=$2
+ OLD_c11=$3
+ OLD_c12=$4
+ OLD_c21=$5
+ OLD_c22=$6
+ NEW_p1=$7
+ NEW_p2=$8
+ NEW_c11=$9
+ NEW_c12=${10}
+ NEW_c21=${11}
+ NEW_c22=${12}
+ ECPUS=${13}
+ STATES=${14}
+ ICPUS=${15}
+
+ set_ctrl_state_noerr p1 $OLD_p1
+ set_ctrl_state_noerr p2 $OLD_p2
+ set_ctrl_state_noerr p1/c11 $OLD_c11
+ set_ctrl_state_noerr p1/c12 $OLD_c12
+ set_ctrl_state_noerr p2/c21 $OLD_c21
+ set_ctrl_state_noerr p2/c22 $OLD_c22
+
+ RETVAL=0
+ set_ctrl_state p1 $NEW_p1 ; ((RETVAL += $?))
+ set_ctrl_state p2 $NEW_p2 ; ((RETVAL += $?))
+ set_ctrl_state p1/c11 $NEW_c11; ((RETVAL += $?))
+ set_ctrl_state p1/c12 $NEW_c12; ((RETVAL += $?))
+ set_ctrl_state p2/c21 $NEW_c21; ((RETVAL += $?))
+ set_ctrl_state p2/c22 $NEW_c22; ((RETVAL += $?))
+
+ [[ $RETVAL -ne 0 ]] && test_fail $I result
+
+ check_test_results $I "$ECPUS" "$STATES" "$ICPUS"
+ ((I++))
+ done
+ cd ..
+ rmdir rtest
+ echo "All $I tests of $TEST PASSED."
+}
+
+#
# Testing the new "isolated" partition root type
#
test_isolated()
@@ -932,6 +1115,7 @@
echo $$ > $CGROUP2/cgroup.procs
[[ -d A1 ]] && rmdir A1
null_isolcpus_check
+ pause 0.05
}
#
@@ -997,10 +1181,13 @@
else
echo "Inotify test PASSED"
fi
+ echo member > cpuset.cpus.partition
+ echo "" > cpuset.cpus
}
trap cleanup 0 2 3 6
run_state_test TEST_MATRIX
+run_remote_state_test REMOTE_TEST_MATRIX
test_isolated
test_inotify
echo "All tests PASSED."
diff --git a/tools/testing/selftests/drivers/net/dsa/tc_taprio.sh b/tools/testing/selftests/drivers/net/dsa/tc_taprio.sh
new file mode 120000
index 0000000..d16a65e
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/dsa/tc_taprio.sh
@@ -0,0 +1 @@
+run_net_forwarding_test.sh
\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/hds.py b/tools/testing/selftests/drivers/net/hds.py
index 8b7f6ac..7c90a04 100755
--- a/tools/testing/selftests/drivers/net/hds.py
+++ b/tools/testing/selftests/drivers/net/hds.py
@@ -6,7 +6,7 @@
from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_raises, KsftSkipEx
from lib.py import CmdExitFailure, EthtoolFamily, NlError
from lib.py import NetDrvEnv
-from lib.py import defer, ethtool, ip
+from lib.py import defer, ethtool, ip, random
def _get_hds_mode(cfg, netnl) -> str:
@@ -109,6 +109,36 @@
ksft_eq(0, rings['hds-thresh'])
+def set_hds_thresh_random(cfg, netnl) -> None:
+ try:
+ rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+ except NlError as e:
+ raise KsftSkipEx('ring-get not supported by device')
+ if 'hds-thresh' not in rings:
+ raise KsftSkipEx('hds-thresh not supported by device')
+ if 'hds-thresh-max' not in rings:
+ raise KsftSkipEx('hds-thresh-max not defined by device')
+
+ if rings['hds-thresh-max'] < 2:
+ raise KsftSkipEx('hds-thresh-max is too small')
+ elif rings['hds-thresh-max'] == 2:
+ hds_thresh = 1
+ else:
+ while True:
+ hds_thresh = random.randint(1, rings['hds-thresh-max'] - 1)
+ if hds_thresh != rings['hds-thresh']:
+ break
+
+ try:
+ netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': hds_thresh})
+ except NlError as e:
+ if e.error == errno.EINVAL:
+ raise KsftSkipEx("hds-thresh-set not supported by the device")
+ elif e.error == errno.EOPNOTSUPP:
+ raise KsftSkipEx("ring-set not supported by the device")
+ rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+ ksft_eq(hds_thresh, rings['hds-thresh'])
+
def set_hds_thresh_max(cfg, netnl) -> None:
try:
rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
@@ -243,6 +273,7 @@
get_hds_thresh,
set_hds_disable,
set_hds_enable,
+ set_hds_thresh_random,
set_hds_thresh_zero,
set_hds_thresh_max,
set_hds_thresh_gt,
diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py
index 9f271ab..6a0378e 100755
--- a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py
+++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py
@@ -35,6 +35,7 @@
rx_ring = _get_rx_ring_entries(cfg)
try:
+ ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote)
ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote)
ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote)
flow_rule_id = _set_flow_rule(cfg, combined_chans - 1)
@@ -48,6 +49,7 @@
ethtool(f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote)
ethtool(f"-X {cfg.ifname} default", host=cfg.remote)
ethtool(f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote)
+ ethtool(f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote)
def test_zcrx_oneshot(cfg) -> None:
@@ -59,6 +61,7 @@
rx_ring = _get_rx_ring_entries(cfg)
try:
+ ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote)
ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote)
ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote)
flow_rule_id = _set_flow_rule(cfg, combined_chans - 1)
@@ -72,6 +75,7 @@
ethtool(f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote)
ethtool(f"-X {cfg.ifname} default", host=cfg.remote)
ethtool(f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote)
+ ethtool(f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote)
def main() -> None:
diff --git a/tools/testing/selftests/drivers/net/ocelot/psfp.sh b/tools/testing/selftests/drivers/net/ocelot/psfp.sh
index bed748d..8972f42 100755
--- a/tools/testing/selftests/drivers/net/ocelot/psfp.sh
+++ b/tools/testing/selftests/drivers/net/ocelot/psfp.sh
@@ -266,18 +266,14 @@
"${base_time}" \
"${CYCLE_TIME_NS}" \
"${SHIFT_TIME_NS}" \
+ "${GATE_DURATION_NS}" \
"${NUM_PKTS}" \
"${STREAM_VID}" \
"${STREAM_PRIO}" \
"" \
"${isochron_dat}"
- # Count all received packets by looking at the non-zero RX timestamps
- received=$(isochron report \
- --input-file "${isochron_dat}" \
- --printf-format "%u\n" --printf-args "R" | \
- grep -w -v '0' | wc -l)
-
+ received=$(isochron_report_num_received "${isochron_dat}")
if [ "${received}" = "${expected}" ]; then
RET=0
else
diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
index 4a2d5c4..59a71f2 100644
--- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
+++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
@@ -48,8 +48,16 @@ static uint64_t get_mnt_id(struct __test_metadata *const _metadata,
static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX";
+static const int mark_cmds[] = {
+ FAN_MARK_ADD,
+ FAN_MARK_REMOVE,
+ FAN_MARK_FLUSH
+};
+
+#define NUM_FAN_FDS ARRAY_SIZE(mark_cmds)
+
FIXTURE(fanotify) {
- int fan_fd;
+ int fan_fd[NUM_FAN_FDS];
char buf[256];
unsigned int rem;
void *next;
@@ -61,7 +69,7 @@ FIXTURE(fanotify) {
FIXTURE_SETUP(fanotify)
{
- int ret;
+ int i, ret;
ASSERT_EQ(unshare(CLONE_NEWNS), 0);
@@ -89,20 +97,34 @@ FIXTURE_SETUP(fanotify)
self->root_id = get_mnt_id(_metadata, "/");
ASSERT_NE(self->root_id, 0);
- self->fan_fd = fanotify_init(FAN_REPORT_MNT, 0);
- ASSERT_GE(self->fan_fd, 0);
-
- ret = fanotify_mark(self->fan_fd, FAN_MARK_ADD | FAN_MARK_MNTNS,
- FAN_MNT_ATTACH | FAN_MNT_DETACH, self->ns_fd, NULL);
- ASSERT_EQ(ret, 0);
+ for (i = 0; i < NUM_FAN_FDS; i++) {
+ self->fan_fd[i] = fanotify_init(FAN_REPORT_MNT | FAN_NONBLOCK,
+ 0);
+ ASSERT_GE(self->fan_fd[i], 0);
+ ret = fanotify_mark(self->fan_fd[i], FAN_MARK_ADD |
+ FAN_MARK_MNTNS,
+ FAN_MNT_ATTACH | FAN_MNT_DETACH,
+ self->ns_fd, NULL);
+ ASSERT_EQ(ret, 0);
+ // On fd[0] we do an extra ADD that changes nothing.
+ // On fd[1]/fd[2] we REMOVE/FLUSH which removes the mark.
+ ret = fanotify_mark(self->fan_fd[i], mark_cmds[i] |
+ FAN_MARK_MNTNS,
+ FAN_MNT_ATTACH | FAN_MNT_DETACH,
+ self->ns_fd, NULL);
+ ASSERT_EQ(ret, 0);
+ }
self->rem = 0;
}
FIXTURE_TEARDOWN(fanotify)
{
+ int i;
+
ASSERT_EQ(self->rem, 0);
- close(self->fan_fd);
+ for (i = 0; i < NUM_FAN_FDS; i++)
+ close(self->fan_fd[i]);
ASSERT_EQ(fchdir(self->orig_root), 0);
@@ -123,8 +145,21 @@ static uint64_t expect_notify(struct __test_metadata *const _metadata,
unsigned int thislen;
if (!self->rem) {
- ssize_t len = read(self->fan_fd, self->buf, sizeof(self->buf));
- ASSERT_GT(len, 0);
+ ssize_t len;
+ int i;
+
+ for (i = NUM_FAN_FDS - 1; i >= 0; i--) {
+ len = read(self->fan_fd[i], self->buf,
+ sizeof(self->buf));
+ if (i > 0) {
+ // Groups 1,2 should get EAGAIN
+ ASSERT_EQ(len, -1);
+ ASSERT_EQ(errno, EAGAIN);
+ } else {
+ // Group 0 should get events
+ ASSERT_GT(len, 0);
+ }
+ }
self->rem = len;
self->next = (void *) self->buf;
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc b/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc
index 6b94b67..f656bcc 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc
@@ -7,11 +7,32 @@
MAX_ARGS=128
EXCEED_ARGS=$((MAX_ARGS + 1))
+# bash and dash evaluate variables differently.
+# dash will evaluate '\\' every time it is read whereas bash does not.
+#
+# TEST_STRING="$TEST_STRING \\$i"
+# echo $TEST_STRING
+#
+# With i=123
+# On bash, that will print "\123"
+# but on dash, that will print the escape sequence of \123 as the \ will
+# be interpreted again in the echo.
+#
+# Set a variable "bs" to save a double backslash, then echo that
+# to "ts" to see if $ts changed or not. If it changed, it's dash,
+# if not, it's bash, and then bs can equal a single backslash.
+bs='\\'
+ts=`echo $bs`
+if [ "$ts" = '\\' ]; then
+ # this is bash
+ bs='\'
+fi
+
check_max_args() { # event_header
TEST_STRING=$1
# Acceptable
for i in `seq 1 $MAX_ARGS`; do
- TEST_STRING="$TEST_STRING \\$i"
+ TEST_STRING="$TEST_STRING $bs$i"
done
echo "$TEST_STRING" >> dynamic_events
echo > dynamic_events
diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc
index 118247b..c62165f 100644
--- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc
+++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc
@@ -80,6 +80,26 @@
exit_fail
fi
+# Check strings too
+if [ -f events/syscalls/sys_enter_openat/filter ]; then
+ DIRNAME=`basename $TMPDIR`
+ echo "filename.ustring ~ \"*$DIRNAME*\"" > events/syscalls/sys_enter_openat/filter
+ echo 1 > events/syscalls/sys_enter_openat/enable
+ echo 1 > tracing_on
+ ls /bin/sh
+ nocnt=`grep openat trace | wc -l`
+ ls $TMPDIR
+ echo 0 > tracing_on
+ hitcnt=`grep openat trace | wc -l`;
+ echo 0 > events/syscalls/sys_enter_openat/enable
+ if [ $nocnt -gt 0 ]; then
+ exit_fail
+ fi
+ if [ $hitcnt -eq 0 ]; then
+ exit_fail
+ fi
+fi
+
reset_events_filter
exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-multi-filter.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-multi-filter.tc
new file mode 100644
index 0000000..b6d6a31
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-multi-filter.tc
@@ -0,0 +1,177 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: ftrace - function graph filters
+# requires: set_ftrace_filter function_graph:tracer
+
+# Make sure that function graph filtering works
+
+INSTANCE1="instances/test1_$$"
+INSTANCE2="instances/test2_$$"
+
+WD=`pwd`
+
+do_reset() {
+ cd $WD
+ if [ -d $INSTANCE1 ]; then
+ echo nop > $INSTANCE1/current_tracer
+ rmdir $INSTANCE1
+ fi
+ if [ -d $INSTANCE2 ]; then
+ echo nop > $INSTANCE2/current_tracer
+ rmdir $INSTANCE2
+ fi
+}
+
+mkdir $INSTANCE1
+if ! grep -q function_graph $INSTANCE1/available_tracers; then
+ echo "function_graph not allowed with instances"
+ rmdir $INSTANCE1
+ exit_unsupported
+fi
+
+mkdir $INSTANCE2
+
+fail() { # msg
+ do_reset
+ echo $1
+ exit_fail
+}
+
+disable_tracing
+clear_trace
+
+function_count() {
+ search=$1
+ vsearch=$2
+
+ if [ -z "$search" ]; then
+ cat enabled_functions | wc -l
+ elif [ -z "$vsearch" ]; then
+ grep $search enabled_functions | wc -l
+ else
+ grep $search enabled_functions | grep $vsearch| wc -l
+ fi
+}
+
+set_fgraph() {
+ instance=$1
+ filter="$2"
+ notrace="$3"
+
+ echo "$filter" > $instance/set_ftrace_filter
+ echo "$notrace" > $instance/set_ftrace_notrace
+ echo function_graph > $instance/current_tracer
+}
+
+check_functions() {
+ orig_cnt=$1
+ test=$2
+
+ cnt=`function_count $test`
+ if [ $cnt -gt $orig_cnt ]; then
+ fail
+ fi
+}
+
+check_cnt() {
+ orig_cnt=$1
+ search=$2
+ vsearch=$3
+
+ cnt=`function_count $search $vsearch`
+ if [ $cnt -gt $orig_cnt ]; then
+ fail
+ fi
+}
+
+reset_graph() {
+ instance=$1
+ echo nop > $instance/current_tracer
+}
+
+# get any functions that were enabled before the test
+total_cnt=`function_count`
+sched_cnt=`function_count sched`
+lock_cnt=`function_count lock`
+time_cnt=`function_count time`
+clock_cnt=`function_count clock`
+locks_clock_cnt=`function_count locks clock`
+clock_locks_cnt=`function_count clock locks`
+
+# Trace functions with "sched" but not "time"
+set_fgraph $INSTANCE1 '*sched*' '*time*'
+
+# Make sure "time" isn't listed
+check_functions $time_cnt 'time'
+instance1_cnt=`function_count`
+
+# Trace functions with "lock" but not "clock"
+set_fgraph $INSTANCE2 '*lock*' '*clock*'
+instance1_2_cnt=`function_count`
+
+# Turn off the first instance
+reset_graph $INSTANCE1
+
+# The second instance doesn't trace "clock" functions
+check_functions $clock_cnt 'clock'
+instance2_cnt=`function_count`
+
+# Start from a clean slate
+reset_graph $INSTANCE2
+check_functions $total_cnt
+
+# Trace functions with "lock" but not "clock"
+set_fgraph $INSTANCE2 '*lock*' '*clock*'
+
+# This should match the last time instance 2 was by itself
+cnt=`function_count`
+if [ $instance2_cnt -ne $cnt ]; then
+ fail
+fi
+
+# And it should not be tracing "clock" functions
+check_functions $clock_cnt 'clock'
+
+# Trace functions with "sched" but not "time"
+set_fgraph $INSTANCE1 '*sched*' '*time*'
+
+# This should match the last time both instances were enabled
+cnt=`function_count`
+if [ $instance1_2_cnt -ne $cnt ]; then
+ fail
+fi
+
+# Turn off the second instance
+reset_graph $INSTANCE2
+
+# This should match the last time instance 1 was by itself
+cnt=`function_count`
+if [ $instance1_cnt -ne $cnt ]; then
+ fail
+fi
+
+# And it should not be tracing "time" functions
+check_functions $time_cnt 'time'
+
+# Start from a clean slate
+reset_graph $INSTANCE1
+check_functions $total_cnt
+
+# Enable all functions but those that have "locks"
+set_fgraph $INSTANCE1 '' '*locks*'
+
+# Enable all functions but those that have "clock"
+set_fgraph $INSTANCE2 '' '*clock*'
+
+# If a function has "locks" it should not have "clock"
+check_cnt $locks_clock_cnt locks clock
+
+# If a function has "clock" it should not have "locks"
+check_cnt $clock_locks_cnt clock locks
+
+reset_graph $INSTANCE1
+reset_graph $INSTANCE2
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c
index 7d7a6a0..2d8230d 100644
--- a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c
+++ b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c
@@ -98,7 +98,7 @@ int main(int argc, char *argv[])
info("Calling futex_waitv on f1: %u @ %p with val=%u\n", f1, &f1, f1+1);
res = futex_waitv(&waitv, 1, 0, &to, CLOCK_MONOTONIC);
if (!res || errno != EWOULDBLOCK) {
- ksft_test_result_pass("futex_waitv returned: %d %s\n",
+ ksft_test_result_fail("futex_waitv returned: %d %s\n",
res ? errno : res,
res ? strerror(errno) : "");
ret = RET_FAIL;
diff --git a/tools/testing/selftests/hid/config.common b/tools/testing/selftests/hid/config.common
index 45b5570..b1f4085 100644
--- a/tools/testing/selftests/hid/config.common
+++ b/tools/testing/selftests/hid/config.common
@@ -39,7 +39,6 @@
CONFIG_CPU_FREQ_STAT=y
CONFIG_CPU_IDLE_GOV_LADDER=y
CONFIG_CPUSETS=y
-CONFIG_CRC_T10DIF=y
CONFIG_CRYPTO_BLAKE2B=y
CONFIG_CRYPTO_DEV_VIRTIO=y
CONFIG_CRYPTO_SEQIV=y
diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index f773f8f..f62b0a5 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -50,8 +50,18 @@
# Non-compiled test targets
TEST_PROGS_x86 += x86/nx_huge_pages_test.sh
+# Compiled test targets valid on all architectures with libkvm support
+TEST_GEN_PROGS_COMMON = demand_paging_test
+TEST_GEN_PROGS_COMMON += dirty_log_test
+TEST_GEN_PROGS_COMMON += guest_print_test
+TEST_GEN_PROGS_COMMON += kvm_binary_stats_test
+TEST_GEN_PROGS_COMMON += kvm_create_max_vcpus
+TEST_GEN_PROGS_COMMON += kvm_page_table_test
+TEST_GEN_PROGS_COMMON += set_memory_region_test
+
# Compiled test targets
-TEST_GEN_PROGS_x86 = x86/cpuid_test
+TEST_GEN_PROGS_x86 = $(TEST_GEN_PROGS_COMMON)
+TEST_GEN_PROGS_x86 += x86/cpuid_test
TEST_GEN_PROGS_x86 += x86/cr4_cpuid_sync_test
TEST_GEN_PROGS_x86 += x86/dirty_log_page_splitting_test
TEST_GEN_PROGS_x86 += x86/feature_msrs_test
@@ -119,27 +129,21 @@
TEST_GEN_PROGS_x86 += x86/recalc_apic_map_test
TEST_GEN_PROGS_x86 += access_tracking_perf_test
TEST_GEN_PROGS_x86 += coalesced_io_test
-TEST_GEN_PROGS_x86 += demand_paging_test
-TEST_GEN_PROGS_x86 += dirty_log_test
TEST_GEN_PROGS_x86 += dirty_log_perf_test
TEST_GEN_PROGS_x86 += guest_memfd_test
-TEST_GEN_PROGS_x86 += guest_print_test
TEST_GEN_PROGS_x86 += hardware_disable_test
-TEST_GEN_PROGS_x86 += kvm_create_max_vcpus
-TEST_GEN_PROGS_x86 += kvm_page_table_test
TEST_GEN_PROGS_x86 += memslot_modification_stress_test
TEST_GEN_PROGS_x86 += memslot_perf_test
TEST_GEN_PROGS_x86 += mmu_stress_test
TEST_GEN_PROGS_x86 += rseq_test
-TEST_GEN_PROGS_x86 += set_memory_region_test
TEST_GEN_PROGS_x86 += steal_time
-TEST_GEN_PROGS_x86 += kvm_binary_stats_test
TEST_GEN_PROGS_x86 += system_counter_offset_test
TEST_GEN_PROGS_x86 += pre_fault_memory_test
# Compiled outputs used by test targets
TEST_GEN_PROGS_EXTENDED_x86 += x86/nx_huge_pages_test
+TEST_GEN_PROGS_arm64 = $(TEST_GEN_PROGS_COMMON)
TEST_GEN_PROGS_arm64 += arm64/aarch32_id_regs
TEST_GEN_PROGS_arm64 += arm64/arch_timer_edge_cases
TEST_GEN_PROGS_arm64 += arm64/debug-exceptions
@@ -158,22 +162,16 @@
TEST_GEN_PROGS_arm64 += access_tracking_perf_test
TEST_GEN_PROGS_arm64 += arch_timer
TEST_GEN_PROGS_arm64 += coalesced_io_test
-TEST_GEN_PROGS_arm64 += demand_paging_test
-TEST_GEN_PROGS_arm64 += dirty_log_test
TEST_GEN_PROGS_arm64 += dirty_log_perf_test
-TEST_GEN_PROGS_arm64 += guest_print_test
TEST_GEN_PROGS_arm64 += get-reg-list
-TEST_GEN_PROGS_arm64 += kvm_create_max_vcpus
-TEST_GEN_PROGS_arm64 += kvm_page_table_test
TEST_GEN_PROGS_arm64 += memslot_modification_stress_test
TEST_GEN_PROGS_arm64 += memslot_perf_test
TEST_GEN_PROGS_arm64 += mmu_stress_test
TEST_GEN_PROGS_arm64 += rseq_test
-TEST_GEN_PROGS_arm64 += set_memory_region_test
TEST_GEN_PROGS_arm64 += steal_time
-TEST_GEN_PROGS_arm64 += kvm_binary_stats_test
-TEST_GEN_PROGS_s390 = s390/memop
+TEST_GEN_PROGS_s390 = $(TEST_GEN_PROGS_COMMON)
+TEST_GEN_PROGS_s390 += s390/memop
TEST_GEN_PROGS_s390 += s390/resets
TEST_GEN_PROGS_s390 += s390/sync_regs_test
TEST_GEN_PROGS_s390 += s390/tprot
@@ -182,27 +180,14 @@
TEST_GEN_PROGS_s390 += s390/cpumodel_subfuncs_test
TEST_GEN_PROGS_s390 += s390/shared_zeropage_test
TEST_GEN_PROGS_s390 += s390/ucontrol_test
-TEST_GEN_PROGS_s390 += demand_paging_test
-TEST_GEN_PROGS_s390 += dirty_log_test
-TEST_GEN_PROGS_s390 += guest_print_test
-TEST_GEN_PROGS_s390 += kvm_create_max_vcpus
-TEST_GEN_PROGS_s390 += kvm_page_table_test
TEST_GEN_PROGS_s390 += rseq_test
-TEST_GEN_PROGS_s390 += set_memory_region_test
-TEST_GEN_PROGS_s390 += kvm_binary_stats_test
+TEST_GEN_PROGS_riscv = $(TEST_GEN_PROGS_COMMON)
TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test
TEST_GEN_PROGS_riscv += riscv/ebreak_test
TEST_GEN_PROGS_riscv += arch_timer
TEST_GEN_PROGS_riscv += coalesced_io_test
-TEST_GEN_PROGS_riscv += demand_paging_test
-TEST_GEN_PROGS_riscv += dirty_log_test
TEST_GEN_PROGS_riscv += get-reg-list
-TEST_GEN_PROGS_riscv += guest_print_test
-TEST_GEN_PROGS_riscv += kvm_binary_stats_test
-TEST_GEN_PROGS_riscv += kvm_create_max_vcpus
-TEST_GEN_PROGS_riscv += kvm_page_table_test
-TEST_GEN_PROGS_riscv += set_memory_region_test
TEST_GEN_PROGS_riscv += steal_time
SPLIT_TESTS += arch_timer
diff --git a/tools/testing/selftests/kvm/arm64/page_fault_test.c b/tools/testing/selftests/kvm/arm64/page_fault_test.c
index ec33a8f..dc6559d 100644
--- a/tools/testing/selftests/kvm/arm64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/arm64/page_fault_test.c
@@ -199,7 +199,7 @@ static bool guest_set_ha(void)
if (hadbs == 0)
return false;
- tcr = read_sysreg(tcr_el1) | TCR_EL1_HA;
+ tcr = read_sysreg(tcr_el1) | TCR_HA;
write_sysreg(tcr, tcr_el1);
isb();
diff --git a/tools/testing/selftests/kvm/include/arm64/processor.h b/tools/testing/selftests/kvm/include/arm64/processor.h
index 1e8d0d5..b0fc0f9 100644
--- a/tools/testing/selftests/kvm/include/arm64/processor.h
+++ b/tools/testing/selftests/kvm/include/arm64/processor.h
@@ -62,6 +62,67 @@
MAIR_ATTRIDX(MAIR_ATTR_NORMAL, MT_NORMAL) | \
MAIR_ATTRIDX(MAIR_ATTR_NORMAL_WT, MT_NORMAL_WT))
+/* TCR_EL1 specific flags */
+#define TCR_T0SZ_OFFSET 0
+#define TCR_T0SZ(x) ((UL(64) - (x)) << TCR_T0SZ_OFFSET)
+
+#define TCR_IRGN0_SHIFT 8
+#define TCR_IRGN0_MASK (UL(3) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_NC (UL(0) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_WBWA (UL(1) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_WT (UL(2) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_WBnWA (UL(3) << TCR_IRGN0_SHIFT)
+
+#define TCR_ORGN0_SHIFT 10
+#define TCR_ORGN0_MASK (UL(3) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_NC (UL(0) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_WBWA (UL(1) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_WT (UL(2) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_WBnWA (UL(3) << TCR_ORGN0_SHIFT)
+
+#define TCR_SH0_SHIFT 12
+#define TCR_SH0_MASK (UL(3) << TCR_SH0_SHIFT)
+#define TCR_SH0_INNER (UL(3) << TCR_SH0_SHIFT)
+
+#define TCR_TG0_SHIFT 14
+#define TCR_TG0_MASK (UL(3) << TCR_TG0_SHIFT)
+#define TCR_TG0_4K (UL(0) << TCR_TG0_SHIFT)
+#define TCR_TG0_64K (UL(1) << TCR_TG0_SHIFT)
+#define TCR_TG0_16K (UL(2) << TCR_TG0_SHIFT)
+
+#define TCR_IPS_SHIFT 32
+#define TCR_IPS_MASK (UL(7) << TCR_IPS_SHIFT)
+#define TCR_IPS_52_BITS (UL(6) << TCR_IPS_SHIFT)
+#define TCR_IPS_48_BITS (UL(5) << TCR_IPS_SHIFT)
+#define TCR_IPS_40_BITS (UL(2) << TCR_IPS_SHIFT)
+#define TCR_IPS_36_BITS (UL(1) << TCR_IPS_SHIFT)
+
+#define TCR_HA (UL(1) << 39)
+#define TCR_DS (UL(1) << 59)
+
+/*
+ * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
+ */
+#define PTE_ATTRINDX(t) ((t) << 2)
+#define PTE_ATTRINDX_MASK GENMASK(4, 2)
+#define PTE_ATTRINDX_SHIFT 2
+
+#define PTE_VALID BIT(0)
+#define PGD_TYPE_TABLE BIT(1)
+#define PUD_TYPE_TABLE BIT(1)
+#define PMD_TYPE_TABLE BIT(1)
+#define PTE_TYPE_PAGE BIT(1)
+
+#define PTE_SHARED (UL(3) << 8) /* SH[1:0], inner shareable */
+#define PTE_AF BIT(10)
+
+#define PTE_ADDR_MASK(page_shift) GENMASK(47, (page_shift))
+#define PTE_ADDR_51_48 GENMASK(15, 12)
+#define PTE_ADDR_51_48_SHIFT 12
+#define PTE_ADDR_MASK_LPA2(page_shift) GENMASK(49, (page_shift))
+#define PTE_ADDR_51_50_LPA2 GENMASK(9, 8)
+#define PTE_ADDR_51_50_LPA2_SHIFT 8
+
void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init);
struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
struct kvm_vcpu_init *init, void *guest_code);
@@ -102,12 +163,6 @@ enum {
(v) == VECTOR_SYNC_LOWER_64 || \
(v) == VECTOR_SYNC_LOWER_32)
-/* Access flag */
-#define PTE_AF (1ULL << 10)
-
-/* Access flag update enable/disable */
-#define TCR_EL1_HA (1ULL << 39)
-
void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k,
uint32_t *ipa16k, uint32_t *ipa64k);
diff --git a/tools/testing/selftests/kvm/lib/arm64/processor.c b/tools/testing/selftests/kvm/lib/arm64/processor.c
index 7ba3aa3..9d69904 100644
--- a/tools/testing/selftests/kvm/lib/arm64/processor.c
+++ b/tools/testing/selftests/kvm/lib/arm64/processor.c
@@ -72,13 +72,13 @@ static uint64_t addr_pte(struct kvm_vm *vm, uint64_t pa, uint64_t attrs)
uint64_t pte;
if (use_lpa2_pte_format(vm)) {
- pte = pa & GENMASK(49, vm->page_shift);
- pte |= FIELD_GET(GENMASK(51, 50), pa) << 8;
- attrs &= ~GENMASK(9, 8);
+ pte = pa & PTE_ADDR_MASK_LPA2(vm->page_shift);
+ pte |= FIELD_GET(GENMASK(51, 50), pa) << PTE_ADDR_51_50_LPA2_SHIFT;
+ attrs &= ~PTE_ADDR_51_50_LPA2;
} else {
- pte = pa & GENMASK(47, vm->page_shift);
+ pte = pa & PTE_ADDR_MASK(vm->page_shift);
if (vm->page_shift == 16)
- pte |= FIELD_GET(GENMASK(51, 48), pa) << 12;
+ pte |= FIELD_GET(GENMASK(51, 48), pa) << PTE_ADDR_51_48_SHIFT;
}
pte |= attrs;
@@ -90,12 +90,12 @@ static uint64_t pte_addr(struct kvm_vm *vm, uint64_t pte)
uint64_t pa;
if (use_lpa2_pte_format(vm)) {
- pa = pte & GENMASK(49, vm->page_shift);
- pa |= FIELD_GET(GENMASK(9, 8), pte) << 50;
+ pa = pte & PTE_ADDR_MASK_LPA2(vm->page_shift);
+ pa |= FIELD_GET(PTE_ADDR_51_50_LPA2, pte) << 50;
} else {
- pa = pte & GENMASK(47, vm->page_shift);
+ pa = pte & PTE_ADDR_MASK(vm->page_shift);
if (vm->page_shift == 16)
- pa |= FIELD_GET(GENMASK(15, 12), pte) << 48;
+ pa |= FIELD_GET(PTE_ADDR_51_48, pte) << 48;
}
return pa;
@@ -128,7 +128,8 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm)
static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
uint64_t flags)
{
- uint8_t attr_idx = flags & 7;
+ uint8_t attr_idx = flags & (PTE_ATTRINDX_MASK >> PTE_ATTRINDX_SHIFT);
+ uint64_t pg_attr;
uint64_t *ptep;
TEST_ASSERT((vaddr % vm->page_size) == 0,
@@ -147,18 +148,21 @@ static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, vaddr) * 8;
if (!*ptep)
- *ptep = addr_pte(vm, vm_alloc_page_table(vm), 3);
+ *ptep = addr_pte(vm, vm_alloc_page_table(vm),
+ PGD_TYPE_TABLE | PTE_VALID);
switch (vm->pgtable_levels) {
case 4:
ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, vaddr) * 8;
if (!*ptep)
- *ptep = addr_pte(vm, vm_alloc_page_table(vm), 3);
+ *ptep = addr_pte(vm, vm_alloc_page_table(vm),
+ PUD_TYPE_TABLE | PTE_VALID);
/* fall through */
case 3:
ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, vaddr) * 8;
if (!*ptep)
- *ptep = addr_pte(vm, vm_alloc_page_table(vm), 3);
+ *ptep = addr_pte(vm, vm_alloc_page_table(vm),
+ PMD_TYPE_TABLE | PTE_VALID);
/* fall through */
case 2:
ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, vaddr) * 8;
@@ -167,7 +171,11 @@ static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
TEST_FAIL("Page table levels must be 2, 3, or 4");
}
- *ptep = addr_pte(vm, paddr, (attr_idx << 2) | (1 << 10) | 3); /* AF */
+ pg_attr = PTE_AF | PTE_ATTRINDX(attr_idx) | PTE_TYPE_PAGE | PTE_VALID;
+ if (!use_lpa2_pte_format(vm))
+ pg_attr |= PTE_SHARED;
+
+ *ptep = addr_pte(vm, paddr, pg_attr);
}
void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
@@ -293,20 +301,20 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
case VM_MODE_P48V48_64K:
case VM_MODE_P40V48_64K:
case VM_MODE_P36V48_64K:
- tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
+ tcr_el1 |= TCR_TG0_64K;
break;
case VM_MODE_P52V48_16K:
case VM_MODE_P48V48_16K:
case VM_MODE_P40V48_16K:
case VM_MODE_P36V48_16K:
case VM_MODE_P36V47_16K:
- tcr_el1 |= 2ul << 14; /* TG0 = 16KB */
+ tcr_el1 |= TCR_TG0_16K;
break;
case VM_MODE_P52V48_4K:
case VM_MODE_P48V48_4K:
case VM_MODE_P40V48_4K:
case VM_MODE_P36V48_4K:
- tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
+ tcr_el1 |= TCR_TG0_4K;
break;
default:
TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
@@ -319,35 +327,35 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
case VM_MODE_P52V48_4K:
case VM_MODE_P52V48_16K:
case VM_MODE_P52V48_64K:
- tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
+ tcr_el1 |= TCR_IPS_52_BITS;
ttbr0_el1 |= FIELD_GET(GENMASK(51, 48), vm->pgd) << 2;
break;
case VM_MODE_P48V48_4K:
case VM_MODE_P48V48_16K:
case VM_MODE_P48V48_64K:
- tcr_el1 |= 5ul << 32; /* IPS = 48 bits */
+ tcr_el1 |= TCR_IPS_48_BITS;
break;
case VM_MODE_P40V48_4K:
case VM_MODE_P40V48_16K:
case VM_MODE_P40V48_64K:
- tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
+ tcr_el1 |= TCR_IPS_40_BITS;
break;
case VM_MODE_P36V48_4K:
case VM_MODE_P36V48_16K:
case VM_MODE_P36V48_64K:
case VM_MODE_P36V47_16K:
- tcr_el1 |= 1ul << 32; /* IPS = 36 bits */
+ tcr_el1 |= TCR_IPS_36_BITS;
break;
default:
TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
}
- sctlr_el1 |= (1 << 0) | (1 << 2) | (1 << 12) /* M | C | I */;
- /* TCR_EL1 |= IRGN0:WBWA | ORGN0:WBWA | SH0:Inner-Shareable */;
- tcr_el1 |= (1 << 8) | (1 << 10) | (3 << 12);
- tcr_el1 |= (64 - vm->va_bits) /* T0SZ */;
+ sctlr_el1 |= SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_I;
+
+ tcr_el1 |= TCR_IRGN0_WBWA | TCR_ORGN0_WBWA | TCR_SH0_INNER;
+ tcr_el1 |= TCR_T0SZ(vm->va_bits);
if (use_lpa2_pte_format(vm))
- tcr_el1 |= (1ul << 59) /* DS */;
+ tcr_el1 |= TCR_DS;
vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), sctlr_el1);
vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), tcr_el1);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 279ad89..815bc45 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -2019,9 +2019,8 @@ static struct exit_reason {
KVM_EXIT_STRING(RISCV_SBI),
KVM_EXIT_STRING(RISCV_CSR),
KVM_EXIT_STRING(NOTIFY),
-#ifdef KVM_EXIT_MEMORY_NOT_PRESENT
- KVM_EXIT_STRING(MEMORY_NOT_PRESENT),
-#endif
+ KVM_EXIT_STRING(LOONGARCH_IOCSR),
+ KVM_EXIT_STRING(MEMORY_FAULT),
};
/*
diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c
index e589867..1375fca 100644
--- a/tools/testing/selftests/kvm/rseq_test.c
+++ b/tools/testing/selftests/kvm/rseq_test.c
@@ -196,25 +196,27 @@ static void calc_min_max_cpu(void)
static void help(const char *name)
{
puts("");
- printf("usage: %s [-h] [-u]\n", name);
+ printf("usage: %s [-h] [-u] [-l latency]\n", name);
printf(" -u: Don't sanity check the number of successful KVM_RUNs\n");
+ printf(" -l: Set /dev/cpu_dma_latency to suppress deep sleep states\n");
puts("");
exit(0);
}
int main(int argc, char *argv[])
{
+ int r, i, snapshot, opt, fd = -1, latency = -1;
bool skip_sanity_check = false;
- int r, i, snapshot;
struct kvm_vm *vm;
struct kvm_vcpu *vcpu;
u32 cpu, rseq_cpu;
- int opt;
- while ((opt = getopt(argc, argv, "hu")) != -1) {
+ while ((opt = getopt(argc, argv, "hl:u")) != -1) {
switch (opt) {
case 'u':
skip_sanity_check = true;
+ case 'l':
+ latency = atoi_paranoid(optarg);
break;
case 'h':
default:
@@ -243,6 +245,20 @@ int main(int argc, char *argv[])
pthread_create(&migration_thread, NULL, migration_worker,
(void *)(unsigned long)syscall(SYS_gettid));
+ if (latency >= 0) {
+ /*
+ * Writes to cpu_dma_latency persist only while the file is
+ * open, i.e. it allows userspace to provide guaranteed latency
+ * while running a workload. Keep the file open until the test
+ * completes, otherwise writing cpu_dma_latency is meaningless.
+ */
+ fd = open("/dev/cpu_dma_latency", O_RDWR);
+ TEST_ASSERT(fd >= 0, __KVM_SYSCALL_ERROR("open() /dev/cpu_dma_latency", fd));
+
+ r = write(fd, &latency, 4);
+ TEST_ASSERT(r >= 1, "Error setting /dev/cpu_dma_latency");
+ }
+
for (i = 0; !done; i++) {
vcpu_run(vcpu);
TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC,
@@ -278,6 +294,9 @@ int main(int argc, char *argv[])
"rseq CPU = %d, sched CPU = %d", rseq_cpu, cpu);
}
+ if (fd > 0)
+ close(fd);
+
/*
* Sanity check that the test was able to enter the guest a reasonable
* number of times, e.g. didn't get stalled too often/long waiting for
@@ -293,8 +312,8 @@ int main(int argc, char *argv[])
TEST_ASSERT(skip_sanity_check || i > (NR_TASK_MIGRATIONS / 2),
"Only performed %d KVM_RUNs, task stalled too much?\n\n"
" Try disabling deep sleep states to reduce CPU wakeup latency,\n"
- " e.g. via cpuidle.off=1 or setting /dev/cpu_dma_latency to '0',\n"
- " or run with -u to disable this sanity check.", i);
+ " e.g. via cpuidle.off=1 or via -l <latency>, or run with -u to\n"
+ " disable this sanity check.", i);
pthread_join(migration_thread, NULL);
diff --git a/tools/testing/selftests/kvm/x86/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c
index 2b550ef..390ae2d 100644
--- a/tools/testing/selftests/kvm/x86/monitor_mwait_test.c
+++ b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c
@@ -7,6 +7,7 @@
#include "kvm_util.h"
#include "processor.h"
+#include "kselftest.h"
#define CPUID_MWAIT (1u << 3)
@@ -14,6 +15,8 @@ enum monitor_mwait_testcases {
MWAIT_QUIRK_DISABLED = BIT(0),
MISC_ENABLES_QUIRK_DISABLED = BIT(1),
MWAIT_DISABLED = BIT(2),
+ CPUID_DISABLED = BIT(3),
+ TEST_MAX = CPUID_DISABLED * 2 - 1,
};
/*
@@ -35,11 +38,19 @@ do { \
testcase, vector); \
} while (0)
-static void guest_monitor_wait(int testcase)
+static void guest_monitor_wait(void *arg)
{
+ int testcase = (int) (long) arg;
u8 vector;
- GUEST_SYNC(testcase);
+ u64 val = rdmsr(MSR_IA32_MISC_ENABLE) & ~MSR_IA32_MISC_ENABLE_MWAIT;
+ if (!(testcase & MWAIT_DISABLED))
+ val |= MSR_IA32_MISC_ENABLE_MWAIT;
+ wrmsr(MSR_IA32_MISC_ENABLE, val);
+
+ __GUEST_ASSERT(this_cpu_has(X86_FEATURE_MWAIT) == !(testcase & MWAIT_DISABLED),
+ "Expected CPUID.MWAIT %s\n",
+ (testcase & MWAIT_DISABLED) ? "cleared" : "set");
/*
* Arbitrarily MONITOR this function, SVM performs fault checks before
@@ -50,19 +61,6 @@ static void guest_monitor_wait(int testcase)
vector = kvm_asm_safe("mwait", "a"(guest_monitor_wait), "c"(0), "d"(0));
GUEST_ASSERT_MONITOR_MWAIT("MWAIT", testcase, vector);
-}
-
-static void guest_code(void)
-{
- guest_monitor_wait(MWAIT_DISABLED);
-
- guest_monitor_wait(MWAIT_QUIRK_DISABLED | MWAIT_DISABLED);
-
- guest_monitor_wait(MISC_ENABLES_QUIRK_DISABLED | MWAIT_DISABLED);
- guest_monitor_wait(MISC_ENABLES_QUIRK_DISABLED);
-
- guest_monitor_wait(MISC_ENABLES_QUIRK_DISABLED | MWAIT_QUIRK_DISABLED | MWAIT_DISABLED);
- guest_monitor_wait(MISC_ENABLES_QUIRK_DISABLED | MWAIT_QUIRK_DISABLED);
GUEST_DONE();
}
@@ -74,56 +72,64 @@ int main(int argc, char *argv[])
struct kvm_vm *vm;
struct ucall uc;
int testcase;
+ char test[80];
- TEST_REQUIRE(this_cpu_has(X86_FEATURE_MWAIT));
TEST_REQUIRE(kvm_has_cap(KVM_CAP_DISABLE_QUIRKS2));
- vm = vm_create_with_one_vcpu(&vcpu, guest_code);
- vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_MWAIT);
+ ksft_print_header();
+ ksft_set_plan(12);
+ for (testcase = 0; testcase <= TEST_MAX; testcase++) {
+ vm = vm_create_with_one_vcpu(&vcpu, guest_monitor_wait);
+ vcpu_args_set(vcpu, 1, (void *)(long)testcase);
- while (1) {
+ disabled_quirks = 0;
+ if (testcase & MWAIT_QUIRK_DISABLED) {
+ disabled_quirks |= KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS;
+ strcpy(test, "MWAIT can fault");
+ } else {
+ strcpy(test, "MWAIT never faults");
+ }
+ if (testcase & MISC_ENABLES_QUIRK_DISABLED) {
+ disabled_quirks |= KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT;
+ strcat(test, ", MISC_ENABLE updates CPUID");
+ } else {
+ strcat(test, ", no CPUID updates");
+ }
+
+ vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, disabled_quirks);
+
+ if (!(testcase & MISC_ENABLES_QUIRK_DISABLED) &&
+ (!!(testcase & CPUID_DISABLED) ^ !!(testcase & MWAIT_DISABLED)))
+ continue;
+
+ if (testcase & CPUID_DISABLED) {
+ strcat(test, ", CPUID clear");
+ vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_MWAIT);
+ } else {
+ strcat(test, ", CPUID set");
+ vcpu_set_cpuid_feature(vcpu, X86_FEATURE_MWAIT);
+ }
+
+ if (testcase & MWAIT_DISABLED)
+ strcat(test, ", MWAIT disabled");
+
vcpu_run(vcpu);
TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
switch (get_ucall(vcpu, &uc)) {
- case UCALL_SYNC:
- testcase = uc.args[1];
- break;
case UCALL_ABORT:
- REPORT_GUEST_ASSERT(uc);
- goto done;
+ /* Detected in vcpu_run */
+ break;
case UCALL_DONE:
- goto done;
+ ksft_test_result_pass("%s\n", test);
+ break;
default:
TEST_FAIL("Unknown ucall %lu", uc.cmd);
- goto done;
+ break;
}
-
- disabled_quirks = 0;
- if (testcase & MWAIT_QUIRK_DISABLED)
- disabled_quirks |= KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS;
- if (testcase & MISC_ENABLES_QUIRK_DISABLED)
- disabled_quirks |= KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT;
- vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, disabled_quirks);
-
- /*
- * If the MISC_ENABLES quirk (KVM neglects to update CPUID to
- * enable/disable MWAIT) is disabled, toggle the ENABLE_MWAIT
- * bit in MISC_ENABLES accordingly. If the quirk is enabled,
- * the only valid configuration is MWAIT disabled, as CPUID
- * can't be manually changed after running the vCPU.
- */
- if (!(testcase & MISC_ENABLES_QUIRK_DISABLED)) {
- TEST_ASSERT(testcase & MWAIT_DISABLED,
- "Can't toggle CPUID features after running vCPU");
- continue;
- }
-
- vcpu_set_msr(vcpu, MSR_IA32_MISC_ENABLE,
- (testcase & MWAIT_DISABLED) ? 0 : MSR_IA32_MISC_ENABLE_MWAIT);
+ kvm_vm_free(vm);
}
+ ksft_finished();
-done:
- kvm_vm_free(vm);
return 0;
}
diff --git a/tools/testing/selftests/landlock/audit.h b/tools/testing/selftests/landlock/audit.h
index b905408..18a6014 100644
--- a/tools/testing/selftests/landlock/audit.h
+++ b/tools/testing/selftests/landlock/audit.h
@@ -300,15 +300,22 @@ static int audit_match_record(int audit_fd, const __u16 type,
return err;
}
-static int __maybe_unused matches_log_domain_allocated(int audit_fd,
+static int __maybe_unused matches_log_domain_allocated(int audit_fd, pid_t pid,
__u64 *domain_id)
{
- return audit_match_record(
- audit_fd, AUDIT_LANDLOCK_DOMAIN,
- REGEX_LANDLOCK_PREFIX
- " status=allocated mode=enforcing pid=[0-9]\\+ uid=[0-9]\\+"
- " exe=\"[^\"]\\+\" comm=\".*_test\"$",
- domain_id);
+ static const char log_template[] = REGEX_LANDLOCK_PREFIX
+ " status=allocated mode=enforcing pid=%d uid=[0-9]\\+"
+ " exe=\"[^\"]\\+\" comm=\".*_test\"$";
+ char log_match[sizeof(log_template) + 10];
+ int log_match_len;
+
+ log_match_len =
+ snprintf(log_match, sizeof(log_match), log_template, pid);
+ if (log_match_len > sizeof(log_match))
+ return -E2BIG;
+
+ return audit_match_record(audit_fd, AUDIT_LANDLOCK_DOMAIN, log_match,
+ domain_id);
}
static int __maybe_unused matches_log_domain_deallocated(
diff --git a/tools/testing/selftests/landlock/audit_test.c b/tools/testing/selftests/landlock/audit_test.c
index a064307..cfc571a 100644
--- a/tools/testing/selftests/landlock/audit_test.c
+++ b/tools/testing/selftests/landlock/audit_test.c
@@ -9,6 +9,7 @@
#include <errno.h>
#include <limits.h>
#include <linux/landlock.h>
+#include <pthread.h>
#include <stdlib.h>
#include <sys/mount.h>
#include <sys/prctl.h>
@@ -40,7 +41,6 @@ FIXTURE(audit)
{
struct audit_filter audit_filter;
int audit_fd;
- __u64(*domain_stack)[16];
};
FIXTURE_SETUP(audit)
@@ -60,18 +60,10 @@ FIXTURE_SETUP(audit)
TH_LOG("Failed to initialize audit: %s", error_msg);
}
clear_cap(_metadata, CAP_AUDIT_CONTROL);
-
- self->domain_stack = mmap(NULL, sizeof(*self->domain_stack),
- PROT_READ | PROT_WRITE,
- MAP_SHARED | MAP_ANONYMOUS, -1, 0);
- ASSERT_NE(MAP_FAILED, self->domain_stack);
- memset(self->domain_stack, 0, sizeof(*self->domain_stack));
}
FIXTURE_TEARDOWN(audit)
{
- EXPECT_EQ(0, munmap(self->domain_stack, sizeof(*self->domain_stack)));
-
set_cap(_metadata, CAP_AUDIT_CONTROL);
EXPECT_EQ(0, audit_cleanup(self->audit_fd, &self->audit_filter));
clear_cap(_metadata, CAP_AUDIT_CONTROL);
@@ -83,9 +75,15 @@ TEST_F(audit, layers)
.scoped = LANDLOCK_SCOPE_SIGNAL,
};
int status, ruleset_fd, i;
+ __u64(*domain_stack)[16];
__u64 prev_dom = 3;
pid_t child;
+ domain_stack = mmap(NULL, sizeof(*domain_stack), PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+ ASSERT_NE(MAP_FAILED, domain_stack);
+ memset(domain_stack, 0, sizeof(*domain_stack));
+
ruleset_fd =
landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
ASSERT_LE(0, ruleset_fd);
@@ -94,7 +92,7 @@ TEST_F(audit, layers)
child = fork();
ASSERT_LE(0, child);
if (child == 0) {
- for (i = 0; i < ARRAY_SIZE(*self->domain_stack); i++) {
+ for (i = 0; i < ARRAY_SIZE(*domain_stack); i++) {
__u64 denial_dom = 1;
__u64 allocated_dom = 2;
@@ -107,7 +105,8 @@ TEST_F(audit, layers)
matches_log_signal(_metadata, self->audit_fd,
getppid(), &denial_dom));
EXPECT_EQ(0, matches_log_domain_allocated(
- self->audit_fd, &allocated_dom));
+ self->audit_fd, getpid(),
+ &allocated_dom));
EXPECT_NE(denial_dom, 1);
EXPECT_NE(denial_dom, 0);
EXPECT_EQ(denial_dom, allocated_dom);
@@ -115,7 +114,7 @@ TEST_F(audit, layers)
/* Checks that the new domain is younger than the previous one. */
EXPECT_GT(allocated_dom, prev_dom);
prev_dom = allocated_dom;
- (*self->domain_stack)[i] = allocated_dom;
+ (*domain_stack)[i] = allocated_dom;
}
/* Checks that we reached the maximum number of layers. */
@@ -142,23 +141,143 @@ TEST_F(audit, layers)
/* Purges log from deallocated domains. */
EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
&audit_tv_dom_drop, sizeof(audit_tv_dom_drop)));
- for (i = ARRAY_SIZE(*self->domain_stack) - 1; i >= 0; i--) {
+ for (i = ARRAY_SIZE(*domain_stack) - 1; i >= 0; i--) {
__u64 deallocated_dom = 2;
EXPECT_EQ(0, matches_log_domain_deallocated(self->audit_fd, 1,
&deallocated_dom));
- EXPECT_EQ((*self->domain_stack)[i], deallocated_dom)
+ EXPECT_EQ((*domain_stack)[i], deallocated_dom)
{
TH_LOG("Failed to match domain %llx (#%d)",
- (*self->domain_stack)[i], i);
+ (*domain_stack)[i], i);
}
}
+ EXPECT_EQ(0, munmap(domain_stack, sizeof(*domain_stack)));
EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
&audit_tv_default, sizeof(audit_tv_default)));
-
EXPECT_EQ(0, close(ruleset_fd));
}
+struct thread_data {
+ pid_t parent_pid;
+ int ruleset_fd, pipe_child, pipe_parent;
+};
+
+static void *thread_audit_test(void *arg)
+{
+ const struct thread_data *data = (struct thread_data *)arg;
+ uintptr_t err = 0;
+ char buffer;
+
+ /* TGID and TID are different for a second thread. */
+ if (getpid() == gettid()) {
+ err = 1;
+ goto out;
+ }
+
+ if (landlock_restrict_self(data->ruleset_fd, 0)) {
+ err = 2;
+ goto out;
+ }
+
+ if (close(data->ruleset_fd)) {
+ err = 3;
+ goto out;
+ }
+
+ /* Creates a denial to get the domain ID. */
+ if (kill(data->parent_pid, 0) != -1) {
+ err = 4;
+ goto out;
+ }
+
+ if (EPERM != errno) {
+ err = 5;
+ goto out;
+ }
+
+ /* Signals the parent to read denial logs. */
+ if (write(data->pipe_child, ".", 1) != 1) {
+ err = 6;
+ goto out;
+ }
+
+ /* Waits for the parent to update audit filters. */
+ if (read(data->pipe_parent, &buffer, 1) != 1) {
+ err = 7;
+ goto out;
+ }
+
+out:
+ close(data->pipe_child);
+ close(data->pipe_parent);
+ return (void *)err;
+}
+
+/* Checks that the PID tied to a domain is not a TID but the TGID. */
+TEST_F(audit, thread)
+{
+ const struct landlock_ruleset_attr ruleset_attr = {
+ .scoped = LANDLOCK_SCOPE_SIGNAL,
+ };
+ __u64 denial_dom = 1;
+ __u64 allocated_dom = 2;
+ __u64 deallocated_dom = 3;
+ pthread_t thread;
+ int pipe_child[2], pipe_parent[2];
+ char buffer;
+ struct thread_data child_data;
+
+ child_data.parent_pid = getppid();
+ ASSERT_EQ(0, pipe2(pipe_child, O_CLOEXEC));
+ child_data.pipe_child = pipe_child[1];
+ ASSERT_EQ(0, pipe2(pipe_parent, O_CLOEXEC));
+ child_data.pipe_parent = pipe_parent[0];
+ child_data.ruleset_fd =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+ ASSERT_LE(0, child_data.ruleset_fd);
+
+ /* TGID and TID are the same for the initial thread . */
+ EXPECT_EQ(getpid(), gettid());
+ EXPECT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+ ASSERT_EQ(0, pthread_create(&thread, NULL, thread_audit_test,
+ &child_data));
+
+ /* Waits for the child to generate a denial. */
+ ASSERT_EQ(1, read(pipe_child[0], &buffer, 1));
+ EXPECT_EQ(0, close(pipe_child[0]));
+
+ /* Matches the signal log to get the domain ID. */
+ EXPECT_EQ(0, matches_log_signal(_metadata, self->audit_fd,
+ child_data.parent_pid, &denial_dom));
+ EXPECT_NE(denial_dom, 1);
+ EXPECT_NE(denial_dom, 0);
+
+ EXPECT_EQ(0, matches_log_domain_allocated(self->audit_fd, getpid(),
+ &allocated_dom));
+ EXPECT_EQ(denial_dom, allocated_dom);
+
+ /* Updates filter rules to match the drop record. */
+ set_cap(_metadata, CAP_AUDIT_CONTROL);
+ EXPECT_EQ(0, audit_filter_drop(self->audit_fd, AUDIT_ADD_RULE));
+ EXPECT_EQ(0, audit_filter_exe(self->audit_fd, &self->audit_filter,
+ AUDIT_DEL_RULE));
+ clear_cap(_metadata, CAP_AUDIT_CONTROL);
+
+ /* Signals the thread to exit, which will generate a domain deallocation. */
+ ASSERT_EQ(1, write(pipe_parent[1], ".", 1));
+ EXPECT_EQ(0, close(pipe_parent[1]));
+ ASSERT_EQ(0, pthread_join(thread, NULL));
+
+ EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
+ &audit_tv_dom_drop, sizeof(audit_tv_dom_drop)));
+ EXPECT_EQ(0, matches_log_domain_deallocated(self->audit_fd, 1,
+ &deallocated_dom));
+ EXPECT_EQ(denial_dom, deallocated_dom);
+ EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
+ &audit_tv_default, sizeof(audit_tv_default)));
+}
+
FIXTURE(audit_flags)
{
struct audit_filter audit_filter;
@@ -273,7 +392,8 @@ TEST_F(audit_flags, signal)
/* Checks domain information records. */
EXPECT_EQ(0, matches_log_domain_allocated(
- self->audit_fd, &allocated_dom));
+ self->audit_fd, getpid(),
+ &allocated_dom));
EXPECT_NE(*self->domain_id, 1);
EXPECT_NE(*self->domain_id, 0);
EXPECT_EQ(*self->domain_id, allocated_dom);
diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c
index f819011..7372938 100644
--- a/tools/testing/selftests/landlock/fs_test.c
+++ b/tools/testing/selftests/landlock/fs_test.c
@@ -5964,7 +5964,8 @@ TEST_F(audit_layout1, refer_handled)
EXPECT_EQ(EXDEV, errno);
EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.refer",
dir_s1d1));
- EXPECT_EQ(0, matches_log_domain_allocated(self->audit_fd, NULL));
+ EXPECT_EQ(0,
+ matches_log_domain_allocated(self->audit_fd, getpid(), NULL));
EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.refer",
dir_s1d3));
diff --git a/tools/testing/selftests/lib/config b/tools/testing/selftests/lib/config
index 81a1f64..377b369 100644
--- a/tools/testing/selftests/lib/config
+++ b/tools/testing/selftests/lib/config
@@ -1,2 +1,3 @@
CONFIG_TEST_BITMAP=m
+CONFIG_PRIME_NUMBERS=m
CONFIG_TEST_BITOPS=m
diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c
index e949a43..17ed3e9 100644
--- a/tools/testing/selftests/mincore/mincore_selftest.c
+++ b/tools/testing/selftests/mincore/mincore_selftest.c
@@ -261,9 +261,6 @@ TEST(check_file_mmap)
TH_LOG("No read-ahead pages found in memory");
}
- EXPECT_LT(i, vec_size) {
- TH_LOG("Read-ahead pages reached the end of the file");
- }
/*
* End of the readahead window. The rest of the pages shouldn't
* be in memory.
@@ -286,8 +283,7 @@ TEST(check_file_mmap)
/*
* Test mincore() behavior on a page backed by a tmpfs file. This test
- * performs the same steps as the previous one. However, we don't expect
- * any readahead in this case.
+ * performs the same steps as the previous one.
*/
TEST(check_tmpfs_mmap)
{
@@ -298,7 +294,6 @@ TEST(check_tmpfs_mmap)
int page_size;
int fd;
int i;
- int ra_pages = 0;
page_size = sysconf(_SC_PAGESIZE);
vec_size = FILE_SIZE / page_size;
@@ -341,8 +336,7 @@ TEST(check_tmpfs_mmap)
}
/*
- * Touch a page in the middle of the mapping. We expect only
- * that page to be fetched into memory.
+ * Touch a page in the middle of the mapping.
*/
addr[FILE_SIZE / 2] = 1;
retval = mincore(addr, FILE_SIZE, vec);
@@ -351,15 +345,6 @@ TEST(check_tmpfs_mmap)
TH_LOG("Page not found in memory after use");
}
- i = FILE_SIZE / 2 / page_size + 1;
- while (i < vec_size && vec[i]) {
- ra_pages++;
- i++;
- }
- ASSERT_EQ(ra_pages, 0) {
- TH_LOG("Read-ahead pages found in memory");
- }
-
munmap(addr, FILE_SIZE);
close(fd);
free(vec);
diff --git a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
index 67df7b4..e1fe16b 100755
--- a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
+++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
@@ -29,7 +29,7 @@
if [[ $cgroup2 ]]; then
cgroup_path=$(mount -t cgroup2 | head -1 | awk '{print $3}')
if [[ -z "$cgroup_path" ]]; then
- cgroup_path=/dev/cgroup/memory
+ cgroup_path=$(mktemp -d)
mount -t cgroup2 none $cgroup_path
do_umount=1
fi
@@ -37,7 +37,7 @@
else
cgroup_path=$(mount -t cgroup | grep ",hugetlb" | awk '{print $3}')
if [[ -z "$cgroup_path" ]]; then
- cgroup_path=/dev/cgroup/memory
+ cgroup_path=$(mktemp -d)
mount -t cgroup memory,hugetlb $cgroup_path
do_umount=1
fi
diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c
index 2c3a0eb..9bc4591 100644
--- a/tools/testing/selftests/mm/compaction_test.c
+++ b/tools/testing/selftests/mm/compaction_test.c
@@ -90,6 +90,8 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size,
int compaction_index = 0;
char nr_hugepages[20] = {0};
char init_nr_hugepages[24] = {0};
+ char target_nr_hugepages[24] = {0};
+ int slen;
snprintf(init_nr_hugepages, sizeof(init_nr_hugepages),
"%lu", initial_nr_hugepages);
@@ -106,11 +108,18 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size,
goto out;
}
- /* Request a large number of huge pages. The Kernel will allocate
- as much as it can */
- if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) {
- ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n",
- strerror(errno));
+ /*
+ * Request huge pages for about half of the free memory. The Kernel
+ * will allocate as much as it can, and we expect it will get at least 1/3
+ */
+ nr_hugepages_ul = mem_free / hugepage_size / 2;
+ snprintf(target_nr_hugepages, sizeof(target_nr_hugepages),
+ "%lu", nr_hugepages_ul);
+
+ slen = strlen(target_nr_hugepages);
+ if (write(fd, target_nr_hugepages, slen) != slen) {
+ ksft_print_msg("Failed to write %lu to /proc/sys/vm/nr_hugepages: %s\n",
+ nr_hugepages_ul, strerror(errno));
goto close_fd;
}
diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c
index f0cb14e..b6cfe0a 100644
--- a/tools/testing/selftests/mm/cow.c
+++ b/tools/testing/selftests/mm/cow.c
@@ -293,7 +293,7 @@ static void do_test_vmsplice_in_parent(char *mem, size_t size,
.iov_base = mem,
.iov_len = size,
};
- ssize_t cur, total, transferred;
+ ssize_t cur, total, transferred = 0;
struct comm_pipes comm_pipes;
char *old, *new;
int ret, fds[2];
diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c
index b3d0e27..eba43ea 100644
--- a/tools/testing/selftests/mm/guard-regions.c
+++ b/tools/testing/selftests/mm/guard-regions.c
@@ -271,12 +271,16 @@ FIXTURE_SETUP(guard_regions)
self->page_size = (unsigned long)sysconf(_SC_PAGESIZE);
setup_sighandler();
- if (variant->backing == ANON_BACKED)
+ switch (variant->backing) {
+ case ANON_BACKED:
return;
-
- self->fd = open_file(
- variant->backing == SHMEM_BACKED ? "/tmp/" : "",
- self->path);
+ case LOCAL_FILE_BACKED:
+ self->fd = open_file("", self->path);
+ break;
+ case SHMEM_BACKED:
+ self->fd = memfd_create(self->path, 0);
+ break;
+ }
/* We truncate file to at least 100 pages, tests can modify as needed. */
ASSERT_EQ(ftruncate(self->fd, 100 * self->page_size), 0);
@@ -1696,7 +1700,7 @@ TEST_F(guard_regions, readonly_file)
char *ptr;
int i;
- if (variant->backing == ANON_BACKED)
+ if (variant->backing != LOCAL_FILE_BACKED)
SKIP(return, "Read-only test specific to file-backed");
/* Map shared so we can populate with pattern, populate it, unmap. */
diff --git a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh
index 11f9bbe..0b0d4ba 100755
--- a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh
+++ b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh
@@ -23,7 +23,7 @@
if [[ $cgroup2 ]]; then
CGROUP_ROOT=$(mount -t cgroup2 | head -1 | awk '{print $3}')
if [[ -z "$CGROUP_ROOT" ]]; then
- CGROUP_ROOT=/dev/cgroup/memory
+ CGROUP_ROOT=$(mktemp -d)
mount -t cgroup2 none $CGROUP_ROOT
do_umount=1
fi
diff --git a/tools/testing/selftests/mm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h
index 1bad310..17bf2d1 100644
--- a/tools/testing/selftests/mm/pkey-powerpc.h
+++ b/tools/testing/selftests/mm/pkey-powerpc.h
@@ -3,6 +3,8 @@
#ifndef _PKEYS_POWERPC_H
#define _PKEYS_POWERPC_H
+#include <sys/stat.h>
+
#ifndef SYS_pkey_alloc
# define SYS_pkey_alloc 384
# define SYS_pkey_free 385
@@ -102,8 +104,18 @@ static inline void expect_fault_on_read_execonly_key(void *p1, int pkey)
return;
}
+#define REPEAT_8(s) s s s s s s s s
+#define REPEAT_64(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) \
+ REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s)
+#define REPEAT_512(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) \
+ REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s)
+#define REPEAT_4096(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) \
+ REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s)
+#define REPEAT_16384(s) REPEAT_4096(s) REPEAT_4096(s) \
+ REPEAT_4096(s) REPEAT_4096(s)
+
/* 4-byte instructions * 16384 = 64K page */
-#define __page_o_noops() asm(".rept 16384 ; nop; .endr")
+#define __page_o_noops() asm(REPEAT_16384("nop\n"))
static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey)
{
diff --git a/tools/testing/selftests/mm/pkey_util.c b/tools/testing/selftests/mm/pkey_util.c
index ca4ad0d..255b332 100644
--- a/tools/testing/selftests/mm/pkey_util.c
+++ b/tools/testing/selftests/mm/pkey_util.c
@@ -1,4 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
+#define __SANE_USERSPACE_TYPES__
#include <sys/syscall.h>
#include <unistd.h>
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 679542f..532bb73 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -39,6 +39,7 @@
sk_bind_sendto_listen
sk_connect_zero_addr
sk_so_peek_off
+skf_net_off
socket
so_incoming_cpu
so_netns_cookie
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 6d718b4..124078b 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -106,6 +106,8 @@
TEST_PROGS += busy_poll_test.sh
TEST_GEN_PROGS += proc_net_pktgen
TEST_PROGS += lwt_dst_cache_ref_loop.sh
+TEST_PROGS += skf_net_off.sh
+TEST_GEN_FILES += skf_net_off
# YNL files, must be before "include ..lib.mk"
YNL_GEN_FILES := busy_poller netlink-dumps
diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index b866bab..c7cea55 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -359,6 +359,23 @@
"$getnomatch" "iif flowlabel masked redirect to table" \
"iif flowlabel masked no redirect to table"
fi
+
+ $IP link show dev $DEV | grep -q vrf0
+ if [ $? -eq 0 ]; then
+ match="oif vrf0"
+ getmatch="oif $DEV"
+ getnomatch="oif lo"
+ fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "VRF oif redirect to table" \
+ "VRF oif no redirect to table"
+
+ match="from $SRC_IP6 iif vrf0"
+ getmatch="from $SRC_IP6 iif $DEV"
+ getnomatch="from $SRC_IP6 iif lo"
+ fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "VRF iif redirect to table" \
+ "VRF iif no redirect to table"
+ fi
}
fib_rule6_vrf_test()
@@ -635,6 +652,23 @@
"$getnomatch" "iif dscp masked redirect to table" \
"iif dscp masked no redirect to table"
fi
+
+ $IP link show dev $DEV | grep -q vrf0
+ if [ $? -eq 0 ]; then
+ match="oif vrf0"
+ getmatch="oif $DEV"
+ getnomatch="oif lo"
+ fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "VRF oif redirect to table" \
+ "VRF oif no redirect to table"
+
+ match="from $SRC_IP iif vrf0"
+ getmatch="from $SRC_IP iif $DEV"
+ getnomatch="from $SRC_IP iif lo"
+ fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "VRF iif redirect to table" \
+ "VRF iif no redirect to table"
+ fi
}
fib_rule4_vrf_test()
diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
index 90f8a24..e59fba3 100755
--- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
@@ -1,7 +1,7 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn other_tpid"
+ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn other_tpid 8021p drop_untagged"
NUM_NETIFS=4
CHECK_TC="yes"
source lib.sh
@@ -194,6 +194,100 @@
tc qdisc del dev $h2 clsact
}
+8021p_do()
+{
+ local should_fail=$1; shift
+ local mac=de:ad:be:ef:13:37
+
+ tc filter add dev $h2 ingress protocol all pref 1 handle 101 \
+ flower dst_mac $mac action drop
+
+ $MZ -q $h1 -c 1 -b $mac -a own "81:00 00:00 08:00 aa-aa-aa-aa-aa-aa-aa-aa-aa"
+ sleep 1
+
+ tc -j -s filter show dev $h2 ingress \
+ | jq -e ".[] | select(.options.handle == 101) \
+ | select(.options.actions[0].stats.packets == 1)" &> /dev/null
+ check_err_fail $should_fail $? "802.1p-tagged reception"
+
+ tc filter del dev $h2 ingress pref 1
+}
+
+8021p()
+{
+ RET=0
+
+ tc qdisc add dev $h2 clsact
+ ip link set $h2 promisc on
+
+ # Test that with the default_pvid, 1, packets tagged with VID 0 are
+ # accepted.
+ 8021p_do 0
+
+ # Test that packets tagged with VID 0 are still accepted after changing
+ # the default_pvid.
+ ip link set br0 type bridge vlan_default_pvid 10
+ 8021p_do 0
+
+ log_test "Reception of 802.1p-tagged traffic"
+
+ ip link set $h2 promisc off
+ tc qdisc del dev $h2 clsact
+}
+
+send_untagged_and_8021p()
+{
+ ping_do $h1 192.0.2.2
+ check_fail $?
+
+ 8021p_do 1
+}
+
+drop_untagged()
+{
+ RET=0
+
+ tc qdisc add dev $h2 clsact
+ ip link set $h2 promisc on
+
+ # Test that with no PVID, untagged and 802.1p-tagged traffic is
+ # dropped.
+ ip link set br0 type bridge vlan_default_pvid 1
+
+ # First we reconfigure the default_pvid, 1, as a non-PVID VLAN.
+ bridge vlan add dev $swp1 vid 1 untagged
+ send_untagged_and_8021p
+ bridge vlan add dev $swp1 vid 1 pvid untagged
+
+ # Next we try to delete VID 1 altogether
+ bridge vlan del dev $swp1 vid 1
+ send_untagged_and_8021p
+ bridge vlan add dev $swp1 vid 1 pvid untagged
+
+ # Set up the bridge without a default_pvid, then check that the 8021q
+ # module, when the bridge port goes down and then up again, does not
+ # accidentally re-enable untagged packet reception.
+ ip link set br0 type bridge vlan_default_pvid 0
+ ip link set $swp1 down
+ ip link set $swp1 up
+ setup_wait
+ send_untagged_and_8021p
+
+ # Remove swp1 as a bridge port and let it rejoin the bridge while it
+ # has no default_pvid.
+ ip link set $swp1 nomaster
+ ip link set $swp1 master br0
+ send_untagged_and_8021p
+
+ # Restore settings
+ ip link set br0 type bridge vlan_default_pvid 1
+
+ log_test "Dropping of untagged and 802.1p-tagged traffic with no PVID"
+
+ ip link set $h2 promisc off
+ tc qdisc del dev $h2 clsact
+}
+
trap cleanup EXIT
setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/tc_taprio.sh b/tools/testing/selftests/net/forwarding/tc_taprio.sh
new file mode 100755
index 0000000..8992aea
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/tc_taprio.sh
@@ -0,0 +1,421 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS=" \
+ test_clock_jump_backward \
+ test_taprio_after_ptp \
+ test_max_sdu \
+ test_clock_jump_backward_forward \
+"
+NUM_NETIFS=4
+source tc_common.sh
+source lib.sh
+source tsn_lib.sh
+
+require_command python3
+
+# The test assumes the usual topology from the README, where h1 is connected to
+# swp1, h2 to swp2, and swp1 and swp2 are together in a bridge.
+# Additional assumption: h1 and h2 use the same PHC, and so do swp1 and swp2.
+# By synchronizing h1 to swp1 via PTP, h2 is also implicitly synchronized to
+# swp1 (and both to CLOCK_REALTIME).
+h1=${NETIFS[p1]}
+swp1=${NETIFS[p2]}
+swp2=${NETIFS[p3]}
+h2=${NETIFS[p4]}
+
+UDS_ADDRESS_H1="/var/run/ptp4l_h1"
+UDS_ADDRESS_SWP1="/var/run/ptp4l_swp1"
+
+H1_IPV4="192.0.2.1"
+H2_IPV4="192.0.2.2"
+H1_IPV6="2001:db8:1::1"
+H2_IPV6="2001:db8:1::2"
+
+# Tunables
+NUM_PKTS=100
+STREAM_VID=10
+STREAM_PRIO_1=6
+STREAM_PRIO_2=5
+STREAM_PRIO_3=4
+# PTP uses TC 0
+ALL_GATES=$((1 << 0 | 1 << STREAM_PRIO_1 | 1 << STREAM_PRIO_2))
+# Use a conservative cycle of 10 ms to allow the test to still pass when the
+# kernel has some extra overhead like lockdep etc
+CYCLE_TIME_NS=10000000
+# Create two Gate Control List entries, one OPEN and one CLOSE, of equal
+# durations
+GATE_DURATION_NS=$((CYCLE_TIME_NS / 2))
+# Give 2/3 of the cycle time to user space and 1/3 to the kernel
+FUDGE_FACTOR=$((CYCLE_TIME_NS / 3))
+# Shift the isochron base time by half the gate time, so that packets are
+# always received by swp1 close to the middle of the time slot, to minimize
+# inaccuracies due to network sync
+SHIFT_TIME_NS=$((GATE_DURATION_NS / 2))
+
+path_delay=
+
+h1_create()
+{
+ simple_if_init $h1 $H1_IPV4/24 $H1_IPV6/64
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 $H1_IPV4/24 $H1_IPV6/64
+}
+
+h2_create()
+{
+ simple_if_init $h2 $H2_IPV4/24 $H2_IPV6/64
+}
+
+h2_destroy()
+{
+ simple_if_fini $h2 $H2_IPV4/24 $H2_IPV6/64
+}
+
+switch_create()
+{
+ local h2_mac_addr=$(mac_get $h2)
+
+ ip link set $swp1 up
+ ip link set $swp2 up
+
+ ip link add br0 type bridge vlan_filtering 1
+ ip link set $swp1 master br0
+ ip link set $swp2 master br0
+ ip link set br0 up
+
+ bridge vlan add dev $swp2 vid $STREAM_VID
+ bridge vlan add dev $swp1 vid $STREAM_VID
+ bridge fdb add dev $swp2 \
+ $h2_mac_addr vlan $STREAM_VID static master
+}
+
+switch_destroy()
+{
+ ip link del br0
+}
+
+ptp_setup()
+{
+ # Set up swp1 as a master PHC for h1, synchronized to the local
+ # CLOCK_REALTIME.
+ phc2sys_start $UDS_ADDRESS_SWP1
+ ptp4l_start $h1 true $UDS_ADDRESS_H1
+ ptp4l_start $swp1 false $UDS_ADDRESS_SWP1
+}
+
+ptp_cleanup()
+{
+ ptp4l_stop $swp1
+ ptp4l_stop $h1
+ phc2sys_stop
+}
+
+txtime_setup()
+{
+ local if_name=$1
+
+ tc qdisc add dev $if_name clsact
+ # Classify PTP on TC 7 and isochron on TC 6
+ tc filter add dev $if_name egress protocol 0x88f7 \
+ flower action skbedit priority 7
+ tc filter add dev $if_name egress protocol 802.1Q \
+ flower vlan_ethtype 0xdead action skbedit priority 6
+ tc qdisc add dev $if_name handle 100: parent root mqprio num_tc 8 \
+ queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 \
+ map 0 1 2 3 4 5 6 7 \
+ hw 1
+ # Set up TC 5, 6, 7 for SO_TXTIME. tc-mqprio queues count from 1.
+ tc qdisc replace dev $if_name parent 100:$((STREAM_PRIO_1 + 1)) etf \
+ clockid CLOCK_TAI offload delta $FUDGE_FACTOR
+ tc qdisc replace dev $if_name parent 100:$((STREAM_PRIO_2 + 1)) etf \
+ clockid CLOCK_TAI offload delta $FUDGE_FACTOR
+ tc qdisc replace dev $if_name parent 100:$((STREAM_PRIO_3 + 1)) etf \
+ clockid CLOCK_TAI offload delta $FUDGE_FACTOR
+}
+
+txtime_cleanup()
+{
+ local if_name=$1
+
+ tc qdisc del dev $if_name clsact
+ tc qdisc del dev $if_name root
+}
+
+taprio_replace()
+{
+ local if_name="$1"; shift
+ local extra_args="$1"; shift
+
+ # STREAM_PRIO_1 always has an open gate.
+ # STREAM_PRIO_2 has a gate open for GATE_DURATION_NS (half the cycle time)
+ # STREAM_PRIO_3 always has a closed gate.
+ tc qdisc replace dev $if_name root stab overhead 24 taprio num_tc 8 \
+ queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 \
+ map 0 1 2 3 4 5 6 7 \
+ sched-entry S $(printf "%x" $ALL_GATES) $GATE_DURATION_NS \
+ sched-entry S $(printf "%x" $((ALL_GATES & ~(1 << STREAM_PRIO_2)))) $GATE_DURATION_NS \
+ base-time 0 flags 0x2 $extra_args
+ taprio_wait_for_admin $if_name
+}
+
+taprio_cleanup()
+{
+ local if_name=$1
+
+ tc qdisc del dev $if_name root
+}
+
+probe_path_delay()
+{
+ local isochron_dat="$(mktemp)"
+ local received
+
+ log_info "Probing path delay"
+
+ isochron_do "$h1" "$h2" "$UDS_ADDRESS_H1" "" 0 \
+ "$CYCLE_TIME_NS" "" "" "$NUM_PKTS" \
+ "$STREAM_VID" "$STREAM_PRIO_1" "" "$isochron_dat"
+
+ received=$(isochron_report_num_received "$isochron_dat")
+ if [ "$received" != "$NUM_PKTS" ]; then
+ echo "Cannot establish basic data path between $h1 and $h2"
+ exit $ksft_fail
+ fi
+
+ printf "pdelay = {}\n" > isochron_data.py
+ isochron report --input-file "$isochron_dat" \
+ --printf-format "pdelay[%u] = %d - %d\n" \
+ --printf-args "qRT" \
+ >> isochron_data.py
+ cat <<-'EOF' > isochron_postprocess.py
+ #!/usr/bin/env python3
+
+ from isochron_data import pdelay
+ import numpy as np
+
+ w = np.array(list(pdelay.values()))
+ print("{}".format(np.max(w)))
+ EOF
+ path_delay=$(python3 ./isochron_postprocess.py)
+
+ log_info "Path delay from $h1 to $h2 estimated at $path_delay ns"
+
+ if [ "$path_delay" -gt "$GATE_DURATION_NS" ]; then
+ echo "Path delay larger than gate duration, aborting"
+ exit $ksft_fail
+ fi
+
+ rm -f ./isochron_data.py 2> /dev/null
+ rm -f ./isochron_postprocess.py 2> /dev/null
+ rm -f "$isochron_dat" 2> /dev/null
+}
+
+setup_prepare()
+{
+ vrf_prepare
+
+ h1_create
+ h2_create
+ switch_create
+
+ txtime_setup $h1
+
+ # Temporarily set up PTP just to probe the end-to-end path delay.
+ ptp_setup
+ probe_path_delay
+ ptp_cleanup
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ isochron_recv_stop
+ txtime_cleanup $h1
+
+ switch_destroy
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+run_test()
+{
+ local base_time=$1; shift
+ local stream_prio=$1; shift
+ local expected_delay=$1; shift
+ local should_fail=$1; shift
+ local test_name=$1; shift
+ local isochron_dat="$(mktemp)"
+ local received
+ local median_delay
+
+ RET=0
+
+ # Set the shift time equal to the cycle time, which effectively
+ # cancels the default advance time. Packets won't be sent early in
+ # software, which ensures that they won't prematurely enter through
+ # the open gate in __test_out_of_band(). Also, the gate is open for
+ # long enough that this won't cause a problem in __test_in_band().
+ isochron_do "$h1" "$h2" "$UDS_ADDRESS_H1" "" "$base_time" \
+ "$CYCLE_TIME_NS" "$SHIFT_TIME_NS" "$GATE_DURATION_NS" \
+ "$NUM_PKTS" "$STREAM_VID" "$stream_prio" "" "$isochron_dat"
+
+ received=$(isochron_report_num_received "$isochron_dat")
+ [ "$received" = "$NUM_PKTS" ]
+ check_err_fail $should_fail $? "Reception of $NUM_PKTS packets"
+
+ if [ $should_fail = 0 ] && [ "$received" = "$NUM_PKTS" ]; then
+ printf "pdelay = {}\n" > isochron_data.py
+ isochron report --input-file "$isochron_dat" \
+ --printf-format "pdelay[%u] = %d - %d\n" \
+ --printf-args "qRT" \
+ >> isochron_data.py
+ cat <<-'EOF' > isochron_postprocess.py
+ #!/usr/bin/env python3
+
+ from isochron_data import pdelay
+ import numpy as np
+
+ w = np.array(list(pdelay.values()))
+ print("{}".format(int(np.median(w))))
+ EOF
+ median_delay=$(python3 ./isochron_postprocess.py)
+
+ # If the condition below is true, packets were delayed by a closed gate
+ [ "$median_delay" -gt $((path_delay + expected_delay)) ]
+ check_fail $? "Median delay $median_delay is greater than expected delay $expected_delay plus path delay $path_delay"
+
+ # If the condition below is true, packets were sent expecting them to
+ # hit a closed gate in the switch, but were not delayed
+ [ "$expected_delay" -gt 0 ] && [ "$median_delay" -lt "$expected_delay" ]
+ check_fail $? "Median delay $median_delay is less than expected delay $expected_delay"
+ fi
+
+ log_test "$test_name"
+
+ rm -f ./isochron_data.py 2> /dev/null
+ rm -f ./isochron_postprocess.py 2> /dev/null
+ rm -f "$isochron_dat" 2> /dev/null
+}
+
+__test_always_open()
+{
+ run_test 0.000000000 $STREAM_PRIO_1 0 0 "Gate always open"
+}
+
+__test_always_closed()
+{
+ run_test 0.000000000 $STREAM_PRIO_3 0 1 "Gate always closed"
+}
+
+__test_in_band()
+{
+ # Send packets in-band with the OPEN gate entry
+ run_test 0.000000000 $STREAM_PRIO_2 0 0 "In band with gate"
+}
+
+__test_out_of_band()
+{
+ # Send packets in-band with the CLOSE gate entry
+ run_test 0.005000000 $STREAM_PRIO_2 \
+ $((GATE_DURATION_NS - SHIFT_TIME_NS)) 0 \
+ "Out of band with gate"
+}
+
+run_subtests()
+{
+ __test_always_open
+ __test_always_closed
+ __test_in_band
+ __test_out_of_band
+}
+
+test_taprio_after_ptp()
+{
+ log_info "Setting up taprio after PTP"
+ ptp_setup
+ taprio_replace $swp2
+ run_subtests
+ taprio_cleanup $swp2
+ ptp_cleanup
+}
+
+__test_under_max_sdu()
+{
+ # Limit max-sdu for STREAM_PRIO_1
+ taprio_replace "$swp2" "max-sdu 0 0 0 0 0 0 100 0"
+ run_test 0.000000000 $STREAM_PRIO_1 0 0 "Under maximum SDU"
+}
+
+__test_over_max_sdu()
+{
+ # Limit max-sdu for STREAM_PRIO_1
+ taprio_replace "$swp2" "max-sdu 0 0 0 0 0 0 20 0"
+ run_test 0.000000000 $STREAM_PRIO_1 0 1 "Over maximum SDU"
+}
+
+test_max_sdu()
+{
+ ptp_setup
+ __test_under_max_sdu
+ __test_over_max_sdu
+ taprio_cleanup $swp2
+ ptp_cleanup
+}
+
+# Perform a clock jump in the past without synchronization running, so that the
+# time base remains where it was set by phc_ctl.
+test_clock_jump_backward()
+{
+ # This is a more complex schedule specifically crafted in a way that
+ # has been problematic on NXP LS1028A. Not much to test with it other
+ # than the fact that it passes traffic.
+ tc qdisc replace dev $swp2 root stab overhead 24 taprio num_tc 8 \
+ queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 map 0 1 2 3 4 5 6 7 \
+ base-time 0 sched-entry S 20 300000 sched-entry S 10 200000 \
+ sched-entry S 20 300000 sched-entry S 48 200000 \
+ sched-entry S 20 300000 sched-entry S 83 200000 \
+ sched-entry S 40 300000 sched-entry S 00 200000 flags 2
+
+ log_info "Forcing a backward clock jump"
+ phc_ctl $swp1 set 0
+
+ ping_test $h1 192.0.2.2
+ taprio_cleanup $swp2
+}
+
+# Test that taprio tolerates clock jumps.
+# Since ptp4l and phc2sys are running, it is expected for the time to
+# eventually recover (through yet another clock jump). Isochron waits
+# until that is the case.
+test_clock_jump_backward_forward()
+{
+ log_info "Forcing a backward and a forward clock jump"
+ taprio_replace $swp2
+ phc_ctl $swp1 set 0
+ ptp_setup
+ ping_test $h1 192.0.2.2
+ run_subtests
+ ptp_cleanup
+ taprio_cleanup $swp2
+}
+
+tc_offload_check
+if [[ $? -ne 0 ]]; then
+ log_test_skip "Could not test offloaded functionality"
+ exit $EXIT_STATUS
+fi
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/tsn_lib.sh b/tools/testing/selftests/net/forwarding/tsn_lib.sh
index b91bcd8..08c044f 100644
--- a/tools/testing/selftests/net/forwarding/tsn_lib.sh
+++ b/tools/testing/selftests/net/forwarding/tsn_lib.sh
@@ -2,6 +2,8 @@
# SPDX-License-Identifier: GPL-2.0
# Copyright 2021-2022 NXP
+tc_testing_scripts_dir=$(dirname $0)/../../tc-testing/scripts
+
REQUIRE_ISOCHRON=${REQUIRE_ISOCHRON:=yes}
REQUIRE_LINUXPTP=${REQUIRE_LINUXPTP:=yes}
@@ -18,6 +20,7 @@
if [[ "$REQUIRE_LINUXPTP" = "yes" ]]; then
require_command phc2sys
require_command ptp4l
+ require_command phc_ctl
fi
phc2sys_start()
@@ -182,6 +185,7 @@
local base_time=$1; shift
local cycle_time=$1; shift
local shift_time=$1; shift
+ local window_size=$1; shift
local num_pkts=$1; shift
local vid=$1; shift
local priority=$1; shift
@@ -212,6 +216,10 @@
extra_args="${extra_args} --shift-time=${shift_time}"
fi
+ if ! [ -z "${window_size}" ]; then
+ extra_args="${extra_args} --window-size=${window_size}"
+ fi
+
if [ "${use_l2}" = "true" ]; then
extra_args="${extra_args} --l2 --etype=0xdead ${vid}"
receiver_extra_args="--l2 --etype=0xdead"
@@ -247,3 +255,21 @@
cpufreq_restore ${ISOCHRON_CPU}
}
+
+isochron_report_num_received()
+{
+ local isochron_dat=$1; shift
+
+ # Count all received packets by looking at the non-zero RX timestamps
+ isochron report \
+ --input-file "${isochron_dat}" \
+ --printf-format "%u\n" --printf-args "R" | \
+ grep -w -v '0' | wc -l
+}
+
+taprio_wait_for_admin()
+{
+ local if_name="$1"; shift
+
+ "$tc_testing_scripts_dir/taprio_wait_for_admin.sh" "$(which tc)" "$if_name"
+}
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 4f55477..e7a7534 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -206,9 +206,8 @@
local token
local msg
- ss_token="$(ss -inmHMN $ns | grep 'token:' |\
- head -n 1 |\
- sed 's/.*token:\([0-9a-f]*\).*/\1/')"
+ ss_token="$(ss -inmHMN $ns |
+ mptcp_lib_get_info_value "token" "token")"
token="$(ip netns exec $ns ./mptcp_diag -t $ss_token |\
awk -F':[ \t]+' '/^token/ {print $2}')"
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 13a3b68..befa66f 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -1441,6 +1441,15 @@
fi
fi
+ count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinSynAckHMacFailure")
+ if [ -z "$count" ]; then
+ rc=${KSFT_SKIP}
+ elif [ "$count" != "0" ]; then
+ rc=${KSFT_FAIL}
+ print_check "synack HMAC"
+ fail_test "got $count JOIN[s] synack HMAC failure expected 0"
+ fi
+
count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinAckRx")
if [ -z "$count" ]; then
rc=${KSFT_SKIP}
@@ -1450,6 +1459,15 @@
fail_test "got $count JOIN[s] ack rx expected $ack_nr"
fi
+ count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinAckHMacFailure")
+ if [ -z "$count" ]; then
+ rc=${KSFT_SKIP}
+ elif [ "$count" != "0" ]; then
+ rc=${KSFT_FAIL}
+ print_check "ack HMAC"
+ fail_test "got $count JOIN[s] ack HMAC failure expected 0"
+ fi
+
print_results "join Rx" ${rc}
join_syn_tx="${join_syn_tx:-${syn_nr}}" \
diff --git a/tools/testing/selftests/net/netfilter/nft_concat_range.sh b/tools/testing/selftests/net/netfilter/nft_concat_range.sh
index 47088b0..1f5979c 100755
--- a/tools/testing/selftests/net/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/net/netfilter/nft_concat_range.sh
@@ -27,7 +27,7 @@
net6_port_net6_port net_port_mac_proto_net"
# Reported bugs, also described by TYPE_ variables below
-BUGS="flush_remove_add reload net_port_proto_match"
+BUGS="flush_remove_add reload net_port_proto_match avx2_mismatch"
# List of possible paths to pktgen script from kernel tree for performance tests
PKTGEN_SCRIPT_PATHS="
@@ -387,6 +387,25 @@
perf_duration 0
"
+
+TYPE_avx2_mismatch="
+display avx2 false match
+type_spec inet_proto . ipv6_addr
+chain_spec meta l4proto . ip6 daddr
+dst proto addr6
+src
+start 1
+count 1
+src_delta 1
+tools ping
+proto icmp6
+
+race_repeat 0
+
+perf_duration 0
+"
+
+
# Set template for all tests, types and rules are filled in depending on test
set_template='
flush ruleset
@@ -1629,6 +1648,24 @@
nft flush ruleset
}
+test_bug_avx2_mismatch()
+{
+ setup veth send_"${proto}" set || return ${ksft_skip}
+
+ local a1="fe80:dead:01ff:0a02:0b03:6007:8009:a001"
+ local a2="fe80:dead:01fe:0a02:0b03:6007:8009:a001"
+
+ nft "add element inet filter test { icmpv6 . $a1 }"
+
+ dst_addr6="$a2"
+ send_icmp6
+
+ if [ "$(count_packets)" -gt "0" ]; then
+ err "False match for $a2"
+ return 1
+ fi
+}
+
test_reported_issues() {
eval test_bug_"${subtest}"
}
diff --git a/tools/testing/selftests/net/skf_net_off.c b/tools/testing/selftests/net/skf_net_off.c
new file mode 100644
index 0000000..1fdf61d
--- /dev/null
+++ b/tools/testing/selftests/net/skf_net_off.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Open a tun device.
+ *
+ * [modifications: use IFF_NAPI_FRAGS, add sk filter]
+ *
+ * Expects the device to have been configured previously, e.g.:
+ * sudo ip tuntap add name tap1 mode tap
+ * sudo ip link set tap1 up
+ * sudo ip link set dev tap1 addr 02:00:00:00:00:01
+ * sudo ip -6 addr add fdab::1 peer fdab::2 dev tap1 nodad
+ *
+ * And to avoid premature pskb_may_pull:
+ *
+ * sudo ethtool -K tap1 gro off
+ * sudo bash -c 'echo 0 > /proc/sys/net/ipv4/ip_early_demux'
+ */
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <fcntl.h>
+#include <getopt.h>
+#include <linux/filter.h>
+#include <linux/if.h>
+#include <linux/if_packet.h>
+#include <linux/if_tun.h>
+#include <linux/ipv6.h>
+#include <netinet/if_ether.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/poll.h>
+#include <sys/types.h>
+#include <sys/uio.h>
+#include <unistd.h>
+
+static bool cfg_do_filter;
+static bool cfg_do_frags;
+static int cfg_dst_port = 8000;
+static char *cfg_ifname;
+
+static int tun_open(const char *tun_name)
+{
+ struct ifreq ifr = {0};
+ int fd, ret;
+
+ fd = open("/dev/net/tun", O_RDWR);
+ if (fd == -1)
+ error(1, errno, "open /dev/net/tun");
+
+ ifr.ifr_flags = IFF_TAP;
+ if (cfg_do_frags)
+ ifr.ifr_flags |= IFF_NAPI | IFF_NAPI_FRAGS;
+
+ strncpy(ifr.ifr_name, tun_name, IFNAMSIZ - 1);
+
+ ret = ioctl(fd, TUNSETIFF, &ifr);
+ if (ret)
+ error(1, ret, "ioctl TUNSETIFF");
+
+ return fd;
+}
+
+static void sk_set_filter(int fd)
+{
+ const int offset_proto = offsetof(struct ip6_hdr, ip6_nxt);
+ const int offset_dport = sizeof(struct ip6_hdr) + offsetof(struct udphdr, dest);
+
+ /* Filter UDP packets with destination port cfg_dst_port */
+ struct sock_filter filter_code[] = {
+ BPF_STMT(BPF_LD + BPF_B + BPF_ABS, SKF_AD_OFF + SKF_AD_PKTTYPE),
+ BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, PACKET_HOST, 0, 4),
+ BPF_STMT(BPF_LD + BPF_B + BPF_ABS, SKF_NET_OFF + offset_proto),
+ BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, IPPROTO_UDP, 0, 2),
+ BPF_STMT(BPF_LD + BPF_H + BPF_ABS, SKF_NET_OFF + offset_dport),
+ BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, cfg_dst_port, 1, 0),
+ BPF_STMT(BPF_RET + BPF_K, 0),
+ BPF_STMT(BPF_RET + BPF_K, 0xFFFF),
+ };
+
+ struct sock_fprog filter = {
+ sizeof(filter_code) / sizeof(filter_code[0]),
+ filter_code,
+ };
+
+ if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &filter, sizeof(filter)))
+ error(1, errno, "setsockopt attach filter");
+}
+
+static int raw_open(void)
+{
+ int fd;
+
+ fd = socket(PF_INET6, SOCK_RAW, IPPROTO_UDP);
+ if (fd == -1)
+ error(1, errno, "socket raw (udp)");
+
+ if (cfg_do_filter)
+ sk_set_filter(fd);
+
+ return fd;
+}
+
+static void tun_write(int fd)
+{
+ const char eth_src[] = { 0x02, 0x00, 0x00, 0x00, 0x00, 0x02 };
+ const char eth_dst[] = { 0x02, 0x00, 0x00, 0x00, 0x00, 0x01 };
+ struct tun_pi pi = {0};
+ struct ipv6hdr ip6h = {0};
+ struct udphdr uh = {0};
+ struct ethhdr eth = {0};
+ uint32_t payload;
+ struct iovec iov[5];
+ int ret;
+
+ pi.proto = htons(ETH_P_IPV6);
+
+ memcpy(eth.h_source, eth_src, sizeof(eth_src));
+ memcpy(eth.h_dest, eth_dst, sizeof(eth_dst));
+ eth.h_proto = htons(ETH_P_IPV6);
+
+ ip6h.version = 6;
+ ip6h.payload_len = htons(sizeof(uh) + sizeof(uint32_t));
+ ip6h.nexthdr = IPPROTO_UDP;
+ ip6h.hop_limit = 8;
+ if (inet_pton(AF_INET6, "fdab::2", &ip6h.saddr) != 1)
+ error(1, errno, "inet_pton src");
+ if (inet_pton(AF_INET6, "fdab::1", &ip6h.daddr) != 1)
+ error(1, errno, "inet_pton src");
+
+ uh.source = htons(8000);
+ uh.dest = htons(cfg_dst_port);
+ uh.len = ip6h.payload_len;
+ uh.check = 0;
+
+ payload = htonl(0xABABABAB); /* Covered in IPv6 length */
+
+ iov[0].iov_base = π
+ iov[0].iov_len = sizeof(pi);
+ iov[1].iov_base = ð
+ iov[1].iov_len = sizeof(eth);
+ iov[2].iov_base = &ip6h;
+ iov[2].iov_len = sizeof(ip6h);
+ iov[3].iov_base = &uh;
+ iov[3].iov_len = sizeof(uh);
+ iov[4].iov_base = &payload;
+ iov[4].iov_len = sizeof(payload);
+
+ ret = writev(fd, iov, sizeof(iov) / sizeof(iov[0]));
+ if (ret <= 0)
+ error(1, errno, "writev");
+}
+
+static void raw_read(int fd)
+{
+ struct timeval tv = { .tv_usec = 100 * 1000 };
+ struct msghdr msg = {0};
+ struct iovec iov[2];
+ struct udphdr uh;
+ uint32_t payload[2];
+ int ret;
+
+ if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
+ error(1, errno, "setsockopt rcvtimeo udp");
+
+ iov[0].iov_base = &uh;
+ iov[0].iov_len = sizeof(uh);
+
+ iov[1].iov_base = payload;
+ iov[1].iov_len = sizeof(payload);
+
+ msg.msg_iov = iov;
+ msg.msg_iovlen = sizeof(iov) / sizeof(iov[0]);
+
+ ret = recvmsg(fd, &msg, 0);
+ if (ret <= 0)
+ error(1, errno, "read raw");
+ if (ret != sizeof(uh) + sizeof(payload[0]))
+ error(1, errno, "read raw: len=%d\n", ret);
+
+ fprintf(stderr, "raw recv: 0x%x\n", payload[0]);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int c;
+
+ while ((c = getopt(argc, argv, "fFi:")) != -1) {
+ switch (c) {
+ case 'f':
+ cfg_do_filter = true;
+ printf("bpf filter enabled\n");
+ break;
+ case 'F':
+ cfg_do_frags = true;
+ printf("napi frags mode enabled\n");
+ break;
+ case 'i':
+ cfg_ifname = optarg;
+ break;
+ default:
+ error(1, 0, "unknown option %c", optopt);
+ break;
+ }
+ }
+
+ if (!cfg_ifname)
+ error(1, 0, "must specify tap interface name (-i)");
+}
+
+int main(int argc, char **argv)
+{
+ int fdt, fdr;
+
+ parse_opts(argc, argv);
+
+ fdr = raw_open();
+ fdt = tun_open(cfg_ifname);
+
+ tun_write(fdt);
+ raw_read(fdr);
+
+ if (close(fdt))
+ error(1, errno, "close tun");
+ if (close(fdr))
+ error(1, errno, "close udp");
+
+ fprintf(stderr, "OK\n");
+ return 0;
+}
+
diff --git a/tools/testing/selftests/net/skf_net_off.sh b/tools/testing/selftests/net/skf_net_off.sh
new file mode 100755
index 0000000..5da5066
--- /dev/null
+++ b/tools/testing/selftests/net/skf_net_off.sh
@@ -0,0 +1,30 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+readonly NS="ns-$(mktemp -u XXXXXX)"
+
+cleanup() {
+ ip netns del $NS
+}
+
+ip netns add $NS
+trap cleanup EXIT
+
+ip -netns $NS link set lo up
+ip -netns $NS tuntap add name tap1 mode tap
+ip -netns $NS link set tap1 up
+ip -netns $NS link set dev tap1 addr 02:00:00:00:00:01
+ip -netns $NS -6 addr add fdab::1 peer fdab::2 dev tap1 nodad
+ip netns exec $NS ethtool -K tap1 gro off
+
+# disable early demux, else udp_v6_early_demux pulls udp header into linear
+ip netns exec $NS sysctl -w net.ipv4.ip_early_demux=0
+
+echo "no filter"
+ip netns exec $NS ./skf_net_off -i tap1
+
+echo "filter, linear skb (-f)"
+ip netns exec $NS ./skf_net_off -i tap1 -f
+
+echo "filter, fragmented skb (-f) (-F)"
+ip netns exec $NS ./skf_net_off -i tap1 -f -F
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 9a85f93..5ded3b3 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -1753,6 +1753,42 @@ TEST_F(tls_basic, rekey_tx)
EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
}
+TEST_F(tls_basic, disconnect)
+{
+ char const *test_str = "test_message";
+ int send_len = strlen(test_str) + 1;
+ struct tls_crypto_info_keys key;
+ struct sockaddr_in addr;
+ char buf[20];
+ int ret;
+
+ if (self->notls)
+ return;
+
+ tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128,
+ &key, 0);
+
+ ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &key, key.len);
+ ASSERT_EQ(ret, 0);
+
+ /* Pre-queue the data so that setsockopt parses it but doesn't
+ * dequeue it from the TCP socket. recvmsg would dequeue.
+ */
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+
+ ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &key, key.len);
+ ASSERT_EQ(ret, 0);
+
+ addr.sin_family = AF_UNSPEC;
+ addr.sin_addr.s_addr = htonl(INADDR_ANY);
+ addr.sin_port = 0;
+ ret = connect(self->cfd, &addr, sizeof(addr));
+ EXPECT_EQ(ret, -1);
+ EXPECT_EQ(errno, EOPNOTSUPP);
+
+ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+}
+
TEST_F(tls, rekey)
{
char const *test_str_1 = "test_message_before_rekey";
diff --git a/tools/testing/selftests/pcie_bwctrl/Makefile b/tools/testing/selftests/pcie_bwctrl/Makefile
index 48ec048..277f92f 100644
--- a/tools/testing/selftests/pcie_bwctrl/Makefile
+++ b/tools/testing/selftests/pcie_bwctrl/Makefile
@@ -1,2 +1,3 @@
-TEST_PROGS = set_pcie_cooling_state.sh set_pcie_speed.sh
+TEST_PROGS = set_pcie_cooling_state.sh
+TEST_FILES = set_pcie_speed.sh
include ../lib.mk
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json b/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json
index 1ba96c4..d9fc62a 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json
@@ -412,5 +412,27 @@
"teardown": [
"$TC qdisc del dev $DUMMY ingress"
]
+ },
+ {
+ "id": "33f4",
+ "name": "Check echo of big filter command",
+ "category": [
+ "infra",
+ "u32"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DUMMY parent root handle 10: fq_codel"
+ ],
+ "cmdUnderTest": "bash -c '$TC -echo filter add dev $DUMMY parent 10: u32 match u32 0 0 $(for i in $(seq 32); do echo action pedit munge ip dport set 22; done) | grep \"added filter\"'",
+ "verifyCmd": "",
+ "expExitCode": "0",
+ "matchCount": "0",
+ "matchPattern": "",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY parent root fq_codel"
+ ]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index 25454fd..0843f6d 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -158,5 +158,385 @@
"$TC qdisc del dev $DUMMY handle 1: root",
"$IP addr del 10.10.10.10/24 dev $DUMMY || true"
]
+ },
+ {
+ "id": "a4bb",
+ "name": "Test FQ_CODEL with HTB parent - force packet drop with empty queue",
+ "category": [
+ "qdisc",
+ "fq_codel",
+ "htb"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1: root htb default 10",
+ "$TC class add dev $DUMMY parent 1: classid 1:10 htb rate 1kbit",
+ "$TC qdisc add dev $DUMMY parent 1:10 handle 10: fq_codel memory_limit 1 flows 1 target 0.1ms interval 1ms",
+ "$TC filter add dev $DUMMY parent 1: protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:10",
+ "ping -c 5 -f -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "sleep 0.1"
+ ],
+ "cmdUnderTest": "$TC -s qdisc show dev $DUMMY",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DUMMY | grep -A 5 'qdisc fq_codel'",
+ "matchPattern": "dropped [1-9][0-9]*",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1: root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "a4be",
+ "name": "Test FQ_CODEL with QFQ parent - force packet drop with empty queue",
+ "category": [
+ "qdisc",
+ "fq_codel",
+ "qfq"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1: root qfq",
+ "$TC class add dev $DUMMY parent 1: classid 1:10 qfq weight 1 maxpkt 1000",
+ "$TC qdisc add dev $DUMMY parent 1:10 handle 10: fq_codel memory_limit 1 flows 1 target 0.1ms interval 1ms",
+ "$TC filter add dev $DUMMY parent 1: protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:10",
+ "ping -c 10 -s 1000 -f -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "sleep 0.1"
+ ],
+ "cmdUnderTest": "$TC -s qdisc show dev $DUMMY",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DUMMY | grep -A 5 'qdisc fq_codel'",
+ "matchPattern": "dropped [1-9][0-9]*",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1: root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "a4bf",
+ "name": "Test FQ_CODEL with HFSC parent - force packet drop with empty queue",
+ "category": [
+ "qdisc",
+ "fq_codel",
+ "hfsc"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1: root hfsc default 10",
+ "$TC class add dev $DUMMY parent 1: classid 1:10 hfsc sc rate 1kbit ul rate 1kbit",
+ "$TC qdisc add dev $DUMMY parent 1:10 handle 10: fq_codel memory_limit 1 flows 1 target 0.1ms interval 1ms",
+ "$TC filter add dev $DUMMY parent 1: protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:10",
+ "ping -c 5 -f -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "sleep 0.1"
+ ],
+ "cmdUnderTest": "$TC -s qdisc show dev $DUMMY",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DUMMY | grep -A 5 'qdisc fq_codel'",
+ "matchPattern": "dropped [1-9][0-9]*",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1: root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "a4c0",
+ "name": "Test FQ_CODEL with DRR parent - force packet drop with empty queue",
+ "category": [
+ "qdisc",
+ "fq_codel",
+ "drr"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1: root drr",
+ "$TC class add dev $DUMMY parent 1: classid 1:10 drr quantum 1500",
+ "$TC qdisc add dev $DUMMY parent 1:10 handle 10: fq_codel memory_limit 1 flows 1 target 0.1ms interval 1ms",
+ "$TC filter add dev $DUMMY parent 1: protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:10",
+ "ping -c 5 -f -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "sleep 0.1"
+ ],
+ "cmdUnderTest": "$TC -s qdisc show dev $DUMMY",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DUMMY | grep -A 5 'qdisc fq_codel'",
+ "matchPattern": "dropped [1-9][0-9]*",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1: root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "a4c1",
+ "name": "Test FQ_CODEL with ETS parent - force packet drop with empty queue",
+ "category": [
+ "qdisc",
+ "fq_codel",
+ "ets"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 strict 1",
+ "$TC class change dev $DUMMY parent 1: classid 1:1 ets",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 10: fq_codel memory_limit 1 flows 1 target 0.1ms interval 1ms",
+ "$TC filter add dev $DUMMY parent 1: protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1",
+ "ping -c 5 -f -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "sleep 0.1"
+ ],
+ "cmdUnderTest": "$TC -s qdisc show dev $DUMMY",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DUMMY | grep -A 5 'qdisc fq_codel'",
+ "matchPattern": "dropped [1-9][0-9]*",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1: root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "a4c3",
+ "name": "Test HFSC with netem/blackhole - queue emptying during peek operation",
+ "category": [
+ "qdisc",
+ "hfsc",
+ "netem",
+ "blackhole"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root drr",
+ "$TC class add dev $DUMMY parent 1:0 classid 1:1 drr",
+ "$TC class add dev $DUMMY parent 1:0 classid 1:2 drr",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 plug limit 1024",
+ "$TC qdisc add dev $DUMMY parent 1:2 handle 3:0 hfsc default 1",
+ "$TC class add dev $DUMMY parent 3:0 classid 3:1 hfsc rt m1 5Mbit d 10ms m2 10Mbit",
+ "$TC qdisc add dev $DUMMY parent 3:1 handle 4:0 netem delay 1ms",
+ "$TC qdisc add dev $DUMMY parent 4:1 handle 5:0 blackhole",
+ "ping -c 3 -W 0.01 -i 0.001 -s 1 10.10.10.10 -I $DUMMY > /dev/null 2>&1 || true",
+ "$TC class change dev $DUMMY parent 3:0 classid 3:1 hfsc sc m1 5Mbit d 10ms m2 10Mbit",
+ "$TC class del dev $DUMMY parent 3:0 classid 3:1",
+ "$TC class add dev $DUMMY parent 3:0 classid 3:1 hfsc rt m1 5Mbit d 10ms m2 10Mbit",
+ "ping -c 3 -W 0.01 -i 0.001 -s 1 10.10.10.10 -I $DUMMY > /dev/null 2>&1 || true"
+ ],
+ "cmdUnderTest": "$TC class change dev $DUMMY parent 3:0 classid 3:1 hfsc sc m1 5Mbit d 10ms m2 10Mbit",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+ "matchPattern": "qdisc hfsc 3:.*parent 1:2.*default 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "90ec",
+ "name": "Test DRR's enqueue reentrant behaviour with netem",
+ "category": [
+ "qdisc",
+ "drr"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root drr",
+ "$TC class replace dev $DUMMY parent 1:0 classid 1:1 drr",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%",
+ "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1"
+ ],
+ "cmdUnderTest": "ping -c 1 -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -j -s qdisc ls dev $DUMMY handle 1:0",
+ "matchJSON": [
+ {
+ "kind": "drr",
+ "handle": "1:",
+ "bytes": 196,
+ "packets": 2
+ }
+ ],
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "1f1f",
+ "name": "Test ETS's enqueue reentrant behaviour with netem",
+ "category": [
+ "qdisc",
+ "ets"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root ets bands 2",
+ "$TC class replace dev $DUMMY parent 1:0 classid 1:1 ets quantum 1500",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%",
+ "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1"
+ ],
+ "cmdUnderTest": "ping -c 1 -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -j -s class show dev $DUMMY",
+ "matchJSON": [
+ {
+ "class": "ets",
+ "handle": "1:1",
+ "stats": {
+ "bytes": 196,
+ "packets": 2
+ }
+ }
+ ],
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "5e6d",
+ "name": "Test QFQ's enqueue reentrant behaviour with netem",
+ "category": [
+ "qdisc",
+ "qfq"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root qfq",
+ "$TC class replace dev $DUMMY parent 1:0 classid 1:1 qfq weight 100 maxpkt 1500",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%",
+ "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1"
+ ],
+ "cmdUnderTest": "ping -c 1 -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -j -s qdisc ls dev $DUMMY handle 1:0",
+ "matchJSON": [
+ {
+ "kind": "qfq",
+ "handle": "1:",
+ "bytes": 196,
+ "packets": 2
+ }
+ ],
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "bf1d",
+ "name": "Test HFSC's enqueue reentrant behaviour with netem",
+ "category": [
+ "qdisc",
+ "hfsc"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root hfsc",
+ "$TC class add dev $DUMMY parent 1:0 classid 1:1 hfsc ls m2 10Mbit",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%",
+ "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip dst 10.10.10.1/32 flowid 1:1",
+ "$TC class add dev $DUMMY parent 1:0 classid 1:2 hfsc ls m2 10Mbit",
+ "$TC qdisc add dev $DUMMY parent 1:2 handle 3:0 netem duplicate 100%",
+ "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 2 u32 match ip dst 10.10.10.2/32 flowid 1:2",
+ "ping -c 1 10.10.10.1 -I$DUMMY > /dev/null || true",
+ "$TC filter del dev $DUMMY parent 1:0 protocol ip prio 1",
+ "$TC class del dev $DUMMY classid 1:1"
+ ],
+ "cmdUnderTest": "ping -c 1 10.10.10.2 -I$DUMMY > /dev/null || true",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -j -s qdisc ls dev $DUMMY handle 1:0",
+ "matchJSON": [
+ {
+ "kind": "hfsc",
+ "handle": "1:",
+ "bytes": 392,
+ "packets": 4
+ }
+ ],
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "7c3b",
+ "name": "Test nested DRR's enqueue reentrant behaviour with netem",
+ "category": [
+ "qdisc",
+ "drr"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root drr",
+ "$TC class add dev $DUMMY parent 1:0 classid 1:1 drr",
+ "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1",
+ "$TC qdisc add dev $DUMMY handle 2:0 parent 1:1 drr",
+ "$TC class add dev $DUMMY classid 2:1 parent 2:0 drr",
+ "$TC filter add dev $DUMMY parent 2:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 2:1",
+ "$TC qdisc add dev $DUMMY parent 2:1 handle 3:0 netem duplicate 100%"
+ ],
+ "cmdUnderTest": "ping -c 1 -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -j -s qdisc ls dev $DUMMY handle 1:0",
+ "matchJSON": [
+ {
+ "kind": "drr",
+ "handle": "1:",
+ "bytes": 196,
+ "packets": 2
+ }
+ ],
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json
index 50e8d72..28c6ce6 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json
@@ -228,5 +228,41 @@
"matchCount": "0",
"teardown": [
]
+ },
+ {
+ "id": "7f8f",
+ "name": "Check that a derived limit of 1 is rejected (limit 2 depth 1 flows 1)",
+ "category": [
+ "qdisc",
+ "sfq"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [],
+ "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfq limit 2 depth 1 flows 1",
+ "expExitCode": "2",
+ "verifyCmd": "$TC qdisc show dev $DUMMY",
+ "matchPattern": "sfq",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "5168",
+ "name": "Check that a derived limit of 1 is rejected (limit 2 depth 1 divisor 1)",
+ "category": [
+ "qdisc",
+ "sfq"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [],
+ "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfq limit 2 depth 1 divisor 1",
+ "expExitCode": "2",
+ "verifyCmd": "$TC qdisc show dev $DUMMY",
+ "matchPattern": "sfq",
+ "matchCount": "0",
+ "teardown": []
}
]
diff --git a/tools/testing/selftests/tpm2/.gitignore b/tools/testing/selftests/tpm2/.gitignore
new file mode 100644
index 0000000..6d6165c5
--- /dev/null
+++ b/tools/testing/selftests/tpm2/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+AsyncTest.log
+SpaceTest.log
diff --git a/tools/testing/selftests/tpm2/test_smoke.sh b/tools/testing/selftests/tpm2/test_smoke.sh
index 168f4b1..3a60e6c 100755
--- a/tools/testing/selftests/tpm2/test_smoke.sh
+++ b/tools/testing/selftests/tpm2/test_smoke.sh
@@ -6,6 +6,6 @@
[ -e /dev/tpm0 ] || exit $ksft_skip
read tpm_version < /sys/class/tpm/tpm0/tpm_version_major
-[ "$tpm_version" == 2 ] || exit $ksft_skip
+[ "$tpm_version" = 2 ] || exit $ksft_skip
python3 -m unittest -v tpm2_tests.SmokeTest 2>&1
diff --git a/tools/testing/selftests/ublk/Makefile b/tools/testing/selftests/ublk/Makefile
index c7781ef..ec4624a 100644
--- a/tools/testing/selftests/ublk/Makefile
+++ b/tools/testing/selftests/ublk/Makefile
@@ -6,6 +6,9 @@
TEST_PROGS := test_generic_01.sh
TEST_PROGS += test_generic_02.sh
TEST_PROGS += test_generic_03.sh
+TEST_PROGS += test_generic_04.sh
+TEST_PROGS += test_generic_05.sh
+TEST_PROGS += test_generic_06.sh
TEST_PROGS += test_null_01.sh
TEST_PROGS += test_null_02.sh
@@ -21,12 +24,16 @@
TEST_PROGS += test_stress_01.sh
TEST_PROGS += test_stress_02.sh
+TEST_PROGS += test_stress_03.sh
+TEST_PROGS += test_stress_04.sh
+TEST_PROGS += test_stress_05.sh
TEST_GEN_PROGS_EXTENDED = kublk
include ../lib.mk
-$(TEST_GEN_PROGS_EXTENDED): kublk.c null.c file_backed.c common.c stripe.c
+$(TEST_GEN_PROGS_EXTENDED): kublk.c null.c file_backed.c common.c stripe.c \
+ fault_inject.c
check:
shellcheck -x -f gcc *.sh
diff --git a/tools/testing/selftests/ublk/fault_inject.c b/tools/testing/selftests/ublk/fault_inject.c
new file mode 100644
index 0000000..94a8e72
--- /dev/null
+++ b/tools/testing/selftests/ublk/fault_inject.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Fault injection ublk target. Hack this up however you like for
+ * testing specific behaviors of ublk_drv. Currently is a null target
+ * with a configurable delay before completing each I/O. This delay can
+ * be used to test ublk_drv's handling of I/O outstanding to the ublk
+ * server when it dies.
+ */
+
+#include "kublk.h"
+
+static int ublk_fault_inject_tgt_init(const struct dev_ctx *ctx,
+ struct ublk_dev *dev)
+{
+ const struct ublksrv_ctrl_dev_info *info = &dev->dev_info;
+ unsigned long dev_size = 250UL << 30;
+
+ dev->tgt.dev_size = dev_size;
+ dev->tgt.params = (struct ublk_params) {
+ .types = UBLK_PARAM_TYPE_BASIC,
+ .basic = {
+ .logical_bs_shift = 9,
+ .physical_bs_shift = 12,
+ .io_opt_shift = 12,
+ .io_min_shift = 9,
+ .max_sectors = info->max_io_buf_bytes >> 9,
+ .dev_sectors = dev_size >> 9,
+ },
+ };
+
+ dev->private_data = (void *)(unsigned long)(ctx->fault_inject.delay_us * 1000);
+ return 0;
+}
+
+static int ublk_fault_inject_queue_io(struct ublk_queue *q, int tag)
+{
+ const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag);
+ struct io_uring_sqe *sqe;
+ struct __kernel_timespec ts = {
+ .tv_nsec = (long long)q->dev->private_data,
+ };
+
+ ublk_queue_alloc_sqes(q, &sqe, 1);
+ io_uring_prep_timeout(sqe, &ts, 1, 0);
+ sqe->user_data = build_user_data(tag, ublksrv_get_op(iod), 0, 1);
+
+ ublk_queued_tgt_io(q, tag, 1);
+
+ return 0;
+}
+
+static void ublk_fault_inject_tgt_io_done(struct ublk_queue *q, int tag,
+ const struct io_uring_cqe *cqe)
+{
+ const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag);
+
+ if (cqe->res != -ETIME)
+ ublk_err("%s: unexpected cqe res %d\n", __func__, cqe->res);
+
+ if (ublk_completed_tgt_io(q, tag))
+ ublk_complete_io(q, tag, iod->nr_sectors << 9);
+ else
+ ublk_err("%s: io not complete after 1 cqe\n", __func__);
+}
+
+static void ublk_fault_inject_cmd_line(struct dev_ctx *ctx, int argc, char *argv[])
+{
+ static const struct option longopts[] = {
+ { "delay_us", 1, NULL, 0 },
+ { 0, 0, 0, 0 }
+ };
+ int option_idx, opt;
+
+ ctx->fault_inject.delay_us = 0;
+ while ((opt = getopt_long(argc, argv, "",
+ longopts, &option_idx)) != -1) {
+ switch (opt) {
+ case 0:
+ if (!strcmp(longopts[option_idx].name, "delay_us"))
+ ctx->fault_inject.delay_us = strtoll(optarg, NULL, 10);
+ }
+ }
+}
+
+static void ublk_fault_inject_usage(const struct ublk_tgt_ops *ops)
+{
+ printf("\tfault_inject: [--delay_us us (default 0)]\n");
+}
+
+const struct ublk_tgt_ops fault_inject_tgt_ops = {
+ .name = "fault_inject",
+ .init_tgt = ublk_fault_inject_tgt_init,
+ .queue_io = ublk_fault_inject_queue_io,
+ .tgt_io_done = ublk_fault_inject_tgt_io_done,
+ .parse_cmd_line = ublk_fault_inject_cmd_line,
+ .usage = ublk_fault_inject_usage,
+};
diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c
index 91c282b..e57a148 100644
--- a/tools/testing/selftests/ublk/kublk.c
+++ b/tools/testing/selftests/ublk/kublk.c
@@ -5,22 +5,24 @@
#include "kublk.h"
+#define MAX_NR_TGT_ARG 64
+
unsigned int ublk_dbg_mask = UBLK_LOG;
static const struct ublk_tgt_ops *tgt_ops_list[] = {
&null_tgt_ops,
&loop_tgt_ops,
&stripe_tgt_ops,
+ &fault_inject_tgt_ops,
};
static const struct ublk_tgt_ops *ublk_find_tgt(const char *name)
{
- const struct ublk_tgt_ops *ops;
int i;
if (name == NULL)
return NULL;
- for (i = 0; sizeof(tgt_ops_list) / sizeof(ops); i++)
+ for (i = 0; i < ARRAY_SIZE(tgt_ops_list); i++)
if (strcmp(tgt_ops_list[i]->name, name) == 0)
return tgt_ops_list[i];
return NULL;
@@ -118,6 +120,27 @@ static int ublk_ctrl_start_dev(struct ublk_dev *dev,
return __ublk_ctrl_cmd(dev, &data);
}
+static int ublk_ctrl_start_user_recovery(struct ublk_dev *dev)
+{
+ struct ublk_ctrl_cmd_data data = {
+ .cmd_op = UBLK_U_CMD_START_USER_RECOVERY,
+ };
+
+ return __ublk_ctrl_cmd(dev, &data);
+}
+
+static int ublk_ctrl_end_user_recovery(struct ublk_dev *dev, int daemon_pid)
+{
+ struct ublk_ctrl_cmd_data data = {
+ .cmd_op = UBLK_U_CMD_END_USER_RECOVERY,
+ .flags = CTRL_CMD_HAS_DATA,
+ };
+
+ dev->dev_info.ublksrv_pid = data.data[0] = daemon_pid;
+
+ return __ublk_ctrl_cmd(dev, &data);
+}
+
static int ublk_ctrl_add_dev(struct ublk_dev *dev)
{
struct ublk_ctrl_cmd_data data = {
@@ -207,10 +230,73 @@ static const char *ublk_dev_state_desc(struct ublk_dev *dev)
};
}
+static void ublk_print_cpu_set(const cpu_set_t *set, char *buf, unsigned len)
+{
+ unsigned done = 0;
+ int i;
+
+ for (i = 0; i < CPU_SETSIZE; i++) {
+ if (CPU_ISSET(i, set))
+ done += snprintf(&buf[done], len - done, "%d ", i);
+ }
+}
+
+static void ublk_adjust_affinity(cpu_set_t *set)
+{
+ int j, updated = 0;
+
+ /*
+ * Just keep the 1st CPU now.
+ *
+ * In future, auto affinity selection can be tried.
+ */
+ for (j = 0; j < CPU_SETSIZE; j++) {
+ if (CPU_ISSET(j, set)) {
+ if (!updated) {
+ updated = 1;
+ continue;
+ }
+ CPU_CLR(j, set);
+ }
+ }
+}
+
+/* Caller must free the allocated buffer */
+static int ublk_ctrl_get_affinity(struct ublk_dev *ctrl_dev, cpu_set_t **ptr_buf)
+{
+ struct ublk_ctrl_cmd_data data = {
+ .cmd_op = UBLK_U_CMD_GET_QUEUE_AFFINITY,
+ .flags = CTRL_CMD_HAS_DATA | CTRL_CMD_HAS_BUF,
+ };
+ cpu_set_t *buf;
+ int i, ret;
+
+ buf = malloc(sizeof(cpu_set_t) * ctrl_dev->dev_info.nr_hw_queues);
+ if (!buf)
+ return -ENOMEM;
+
+ for (i = 0; i < ctrl_dev->dev_info.nr_hw_queues; i++) {
+ data.data[0] = i;
+ data.len = sizeof(cpu_set_t);
+ data.addr = (__u64)&buf[i];
+
+ ret = __ublk_ctrl_cmd(ctrl_dev, &data);
+ if (ret < 0) {
+ free(buf);
+ return ret;
+ }
+ ublk_adjust_affinity(&buf[i]);
+ }
+
+ *ptr_buf = buf;
+ return 0;
+}
+
static void ublk_ctrl_dump(struct ublk_dev *dev)
{
struct ublksrv_ctrl_dev_info *info = &dev->dev_info;
struct ublk_params p;
+ cpu_set_t *affinity;
int ret;
ret = ublk_ctrl_get_params(dev, &p);
@@ -219,12 +305,31 @@ static void ublk_ctrl_dump(struct ublk_dev *dev)
return;
}
+ ret = ublk_ctrl_get_affinity(dev, &affinity);
+ if (ret < 0) {
+ ublk_err("failed to get affinity %m\n");
+ return;
+ }
+
ublk_log("dev id %d: nr_hw_queues %d queue_depth %d block size %d dev_capacity %lld\n",
info->dev_id, info->nr_hw_queues, info->queue_depth,
1 << p.basic.logical_bs_shift, p.basic.dev_sectors);
ublk_log("\tmax rq size %d daemon pid %d flags 0x%llx state %s\n",
info->max_io_buf_bytes, info->ublksrv_pid, info->flags,
ublk_dev_state_desc(dev));
+
+ if (affinity) {
+ char buf[512];
+ int i;
+
+ for (i = 0; i < info->nr_hw_queues; i++) {
+ ublk_print_cpu_set(&affinity[i], buf, sizeof(buf));
+ printf("\tqueue %u: tid %d affinity(%s)\n",
+ i, dev->q[i].tid, buf);
+ }
+ free(affinity);
+ }
+
fflush(stdout);
}
@@ -347,7 +452,9 @@ static int ublk_queue_init(struct ublk_queue *q)
}
ret = ublk_setup_ring(&q->ring, ring_depth, cq_depth,
- IORING_SETUP_COOP_TASKRUN);
+ IORING_SETUP_COOP_TASKRUN |
+ IORING_SETUP_SINGLE_ISSUER |
+ IORING_SETUP_DEFER_TASKRUN);
if (ret < 0) {
ublk_err("ublk dev %d queue %d setup io_uring failed %d\n",
q->dev->dev_info.dev_id, q->q_id, ret);
@@ -602,9 +709,24 @@ static int ublk_process_io(struct ublk_queue *q)
return reapped;
}
+static void ublk_queue_set_sched_affinity(const struct ublk_queue *q,
+ cpu_set_t *cpuset)
+{
+ if (sched_setaffinity(0, sizeof(*cpuset), cpuset) < 0)
+ ublk_err("ublk dev %u queue %u set affinity failed",
+ q->dev->dev_info.dev_id, q->q_id);
+}
+
+struct ublk_queue_info {
+ struct ublk_queue *q;
+ sem_t *queue_sem;
+ cpu_set_t *affinity;
+};
+
static void *ublk_io_handler_fn(void *data)
{
- struct ublk_queue *q = data;
+ struct ublk_queue_info *info = data;
+ struct ublk_queue *q = info->q;
int dev_id = q->dev->dev_info.dev_id;
int ret;
@@ -614,6 +736,10 @@ static void *ublk_io_handler_fn(void *data)
dev_id, q->q_id);
return NULL;
}
+ /* IO perf is sensitive with queue pthread affinity on NUMA machine*/
+ ublk_queue_set_sched_affinity(q, info->affinity);
+ sem_post(info->queue_sem);
+
ublk_dbg(UBLK_DBG_QUEUE, "tid %d: ublk dev %d queue %d started\n",
q->tid, dev_id, q->q_id);
@@ -639,7 +765,7 @@ static void ublk_set_parameters(struct ublk_dev *dev)
dev->dev_info.dev_id, ret);
}
-static int ublk_send_dev_event(const struct dev_ctx *ctx, int dev_id)
+static int ublk_send_dev_event(const struct dev_ctx *ctx, struct ublk_dev *dev, int dev_id)
{
uint64_t id;
int evtfd = ctx->_evtfd;
@@ -652,36 +778,68 @@ static int ublk_send_dev_event(const struct dev_ctx *ctx, int dev_id)
else
id = ERROR_EVTFD_DEVID;
+ if (dev && ctx->shadow_dev)
+ memcpy(&ctx->shadow_dev->q, &dev->q, sizeof(dev->q));
+
if (write(evtfd, &id, sizeof(id)) != sizeof(id))
return -EINVAL;
+ close(evtfd);
+ shmdt(ctx->shadow_dev);
+
return 0;
}
static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
{
- int ret, i;
- void *thread_ret;
const struct ublksrv_ctrl_dev_info *dinfo = &dev->dev_info;
+ struct ublk_queue_info *qinfo;
+ cpu_set_t *affinity_buf;
+ void *thread_ret;
+ sem_t queue_sem;
+ int ret, i;
ublk_dbg(UBLK_DBG_DEV, "%s enter\n", __func__);
+ qinfo = (struct ublk_queue_info *)calloc(sizeof(struct ublk_queue_info),
+ dinfo->nr_hw_queues);
+ if (!qinfo)
+ return -ENOMEM;
+
+ sem_init(&queue_sem, 0, 0);
ret = ublk_dev_prep(ctx, dev);
if (ret)
return ret;
+ ret = ublk_ctrl_get_affinity(dev, &affinity_buf);
+ if (ret)
+ return ret;
+
for (i = 0; i < dinfo->nr_hw_queues; i++) {
dev->q[i].dev = dev;
dev->q[i].q_id = i;
+
+ qinfo[i].q = &dev->q[i];
+ qinfo[i].queue_sem = &queue_sem;
+ qinfo[i].affinity = &affinity_buf[i];
pthread_create(&dev->q[i].thread, NULL,
ublk_io_handler_fn,
- &dev->q[i]);
+ &qinfo[i]);
}
+ for (i = 0; i < dinfo->nr_hw_queues; i++)
+ sem_wait(&queue_sem);
+ free(qinfo);
+ free(affinity_buf);
+
/* everything is fine now, start us */
- ublk_set_parameters(dev);
- ret = ublk_ctrl_start_dev(dev, getpid());
+ if (ctx->recovery)
+ ret = ublk_ctrl_end_user_recovery(dev, getpid());
+ else {
+ ublk_set_parameters(dev);
+ ret = ublk_ctrl_start_dev(dev, getpid());
+ }
if (ret < 0) {
ublk_err("%s: ublk_ctrl_start_dev failed: %d\n", __func__, ret);
goto fail;
@@ -691,7 +849,7 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
if (ctx->fg)
ublk_ctrl_dump(dev);
else
- ublk_send_dev_event(ctx, dev->dev_info.dev_id);
+ ublk_send_dev_event(ctx, dev, dev->dev_info.dev_id);
/* wait until we are terminated */
for (i = 0; i < dinfo->nr_hw_queues; i++)
@@ -856,7 +1014,10 @@ static int __cmd_dev_add(const struct dev_ctx *ctx)
}
}
- ret = ublk_ctrl_add_dev(dev);
+ if (ctx->recovery)
+ ret = ublk_ctrl_start_user_recovery(dev);
+ else
+ ret = ublk_ctrl_add_dev(dev);
if (ret < 0) {
ublk_err("%s: can't add dev id %d, type %s ret %d\n",
__func__, dev_id, tgt_type, ret);
@@ -870,7 +1031,7 @@ static int __cmd_dev_add(const struct dev_ctx *ctx)
fail:
if (ret < 0)
- ublk_send_dev_event(ctx, -1);
+ ublk_send_dev_event(ctx, dev, -1);
ublk_ctrl_deinit(dev);
return ret;
}
@@ -884,30 +1045,58 @@ static int cmd_dev_add(struct dev_ctx *ctx)
if (ctx->fg)
goto run;
+ ctx->_shmid = shmget(IPC_PRIVATE, sizeof(struct ublk_dev), IPC_CREAT | 0666);
+ if (ctx->_shmid < 0) {
+ ublk_err("%s: failed to shmget %s\n", __func__, strerror(errno));
+ exit(-1);
+ }
+ ctx->shadow_dev = (struct ublk_dev *)shmat(ctx->_shmid, NULL, 0);
+ if (ctx->shadow_dev == (struct ublk_dev *)-1) {
+ ublk_err("%s: failed to shmat %s\n", __func__, strerror(errno));
+ exit(-1);
+ }
ctx->_evtfd = eventfd(0, 0);
if (ctx->_evtfd < 0) {
ublk_err("%s: failed to create eventfd %s\n", __func__, strerror(errno));
exit(-1);
}
- setsid();
res = fork();
if (res == 0) {
+ int res2;
+
+ setsid();
+ res2 = fork();
+ if (res2 == 0) {
+ /* prepare for detaching */
+ close(STDIN_FILENO);
+ close(STDOUT_FILENO);
+ close(STDERR_FILENO);
run:
- res = __cmd_dev_add(ctx);
- return res;
+ res = __cmd_dev_add(ctx);
+ return res;
+ } else {
+ /* detached from the foreground task */
+ exit(EXIT_SUCCESS);
+ }
} else if (res > 0) {
uint64_t id;
+ int exit_code = EXIT_FAILURE;
res = read(ctx->_evtfd, &id, sizeof(id));
close(ctx->_evtfd);
if (res == sizeof(id) && id != ERROR_EVTFD_DEVID) {
ctx->dev_id = id - 1;
- return __cmd_dev_list(ctx);
+ if (__cmd_dev_list(ctx) >= 0)
+ exit_code = EXIT_SUCCESS;
}
- exit(EXIT_FAILURE);
+ shmdt(ctx->shadow_dev);
+ shmctl(ctx->_shmid, IPC_RMID, NULL);
+ /* wait for child and detach from it */
+ wait(NULL);
+ exit(exit_code);
} else {
- return res;
+ exit(EXIT_FAILURE);
}
}
@@ -969,6 +1158,9 @@ static int __cmd_dev_list(struct dev_ctx *ctx)
ublk_err("%s: can't get dev info from %d: %d\n",
__func__, ctx->dev_id, ret);
} else {
+ if (ctx->shadow_dev)
+ memcpy(&dev->q, ctx->shadow_dev->q, sizeof(dev->q));
+
ublk_ctrl_dump(dev);
}
@@ -1039,14 +1231,47 @@ static int cmd_dev_get_features(void)
return ret;
}
+static void __cmd_create_help(char *exe, bool recovery)
+{
+ int i;
+
+ printf("%s %s -t [null|loop|stripe|fault_inject] [-q nr_queues] [-d depth] [-n dev_id]\n",
+ exe, recovery ? "recover" : "add");
+ printf("\t[--foreground] [--quiet] [-z] [--debug_mask mask] [-r 0|1 ] [-g 0|1]\n");
+ printf("\t[-e 0|1 ] [-i 0|1]\n");
+ printf("\t[target options] [backfile1] [backfile2] ...\n");
+ printf("\tdefault: nr_queues=2(max 32), depth=128(max 1024), dev_id=-1(auto allocation)\n");
+
+ for (i = 0; i < sizeof(tgt_ops_list) / sizeof(tgt_ops_list[0]); i++) {
+ const struct ublk_tgt_ops *ops = tgt_ops_list[i];
+
+ if (ops->usage)
+ ops->usage(ops);
+ }
+}
+
+static void cmd_add_help(char *exe)
+{
+ __cmd_create_help(exe, false);
+ printf("\n");
+}
+
+static void cmd_recover_help(char *exe)
+{
+ __cmd_create_help(exe, true);
+ printf("\tPlease provide exact command line for creating this device with real dev_id\n");
+ printf("\n");
+}
+
static int cmd_dev_help(char *exe)
{
- printf("%s add -t [null|loop] [-q nr_queues] [-d depth] [-n dev_id] [backfile1] [backfile2] ...\n", exe);
- printf("\t default: nr_queues=2(max 4), depth=128(max 128), dev_id=-1(auto allocation)\n");
+ cmd_add_help(exe);
+ cmd_recover_help(exe);
+
printf("%s del [-n dev_id] -a \n", exe);
- printf("\t -a delete all devices -n delete specified device\n");
+ printf("\t -a delete all devices -n delete specified device\n\n");
printf("%s list [-n dev_id] -a \n", exe);
- printf("\t -a list all devices, -n list specified device, default -a \n");
+ printf("\t -a list all devices, -n list specified device, default -a \n\n");
printf("%s features\n", exe);
return 0;
}
@@ -1063,9 +1288,13 @@ int main(int argc, char *argv[])
{ "quiet", 0, NULL, 0 },
{ "zero_copy", 0, NULL, 'z' },
{ "foreground", 0, NULL, 0 },
- { "chunk_size", 1, NULL, 0 },
+ { "recovery", 1, NULL, 'r' },
+ { "recovery_fail_io", 1, NULL, 'e'},
+ { "recovery_reissue", 1, NULL, 'i'},
+ { "get_data", 1, NULL, 'g'},
{ 0, 0, 0, 0 }
};
+ const struct ublk_tgt_ops *ops = NULL;
int option_idx, opt;
const char *cmd = argv[1];
struct dev_ctx ctx = {
@@ -1073,15 +1302,18 @@ int main(int argc, char *argv[])
.nr_hw_queues = 2,
.dev_id = -1,
.tgt_type = "unknown",
- .chunk_size = 65536, /* def chunk size is 64K */
};
int ret = -EINVAL, i;
+ int tgt_argc = 1;
+ char *tgt_argv[MAX_NR_TGT_ARG] = { NULL };
+ int value;
if (argc == 1)
return ret;
+ opterr = 0;
optind = 2;
- while ((opt = getopt_long(argc, argv, "t:n:d:q:az",
+ while ((opt = getopt_long(argc, argv, "t:n:d:q:r:e:i:az",
longopts, &option_idx)) != -1) {
switch (opt) {
case 'a':
@@ -1103,6 +1335,26 @@ int main(int argc, char *argv[])
case 'z':
ctx.flags |= UBLK_F_SUPPORT_ZERO_COPY | UBLK_F_USER_COPY;
break;
+ case 'r':
+ value = strtol(optarg, NULL, 10);
+ if (value)
+ ctx.flags |= UBLK_F_USER_RECOVERY;
+ break;
+ case 'e':
+ value = strtol(optarg, NULL, 10);
+ if (value)
+ ctx.flags |= UBLK_F_USER_RECOVERY | UBLK_F_USER_RECOVERY_FAIL_IO;
+ break;
+ case 'i':
+ value = strtol(optarg, NULL, 10);
+ if (value)
+ ctx.flags |= UBLK_F_USER_RECOVERY | UBLK_F_USER_RECOVERY_REISSUE;
+ break;
+ case 'g':
+ value = strtol(optarg, NULL, 10);
+ if (value)
+ ctx.flags |= UBLK_F_NEED_GET_DATA;
+ break;
case 0:
if (!strcmp(longopts[option_idx].name, "debug_mask"))
ublk_dbg_mask = strtol(optarg, NULL, 16);
@@ -1110,8 +1362,26 @@ int main(int argc, char *argv[])
ublk_dbg_mask = 0;
if (!strcmp(longopts[option_idx].name, "foreground"))
ctx.fg = 1;
- if (!strcmp(longopts[option_idx].name, "chunk_size"))
- ctx.chunk_size = strtol(optarg, NULL, 10);
+ break;
+ case '?':
+ /*
+ * target requires every option must have argument
+ */
+ if (argv[optind][0] == '-' || argv[optind - 1][0] != '-') {
+ fprintf(stderr, "every target option requires argument: %s %s\n",
+ argv[optind - 1], argv[optind]);
+ exit(EXIT_FAILURE);
+ }
+
+ if (tgt_argc < (MAX_NR_TGT_ARG - 1) / 2) {
+ tgt_argv[tgt_argc++] = argv[optind - 1];
+ tgt_argv[tgt_argc++] = argv[optind];
+ } else {
+ fprintf(stderr, "too many target options\n");
+ exit(EXIT_FAILURE);
+ }
+ optind += 1;
+ break;
}
}
@@ -1120,9 +1390,25 @@ int main(int argc, char *argv[])
ctx.files[ctx.nr_files++] = argv[i++];
}
+ ops = ublk_find_tgt(ctx.tgt_type);
+ if (ops && ops->parse_cmd_line) {
+ optind = 0;
+
+ tgt_argv[0] = ctx.tgt_type;
+ ops->parse_cmd_line(&ctx, tgt_argc, tgt_argv);
+ }
+
if (!strcmp(cmd, "add"))
ret = cmd_dev_add(&ctx);
- else if (!strcmp(cmd, "del"))
+ else if (!strcmp(cmd, "recover")) {
+ if (ctx.dev_id < 0) {
+ fprintf(stderr, "device id isn't provided for recovering\n");
+ ret = -EINVAL;
+ } else {
+ ctx.recovery = 1;
+ ret = cmd_dev_add(&ctx);
+ }
+ } else if (!strcmp(cmd, "del"))
ret = cmd_dev_del(&ctx);
else if (!strcmp(cmd, "list")) {
ctx.all = 1;
diff --git a/tools/testing/selftests/ublk/kublk.h b/tools/testing/selftests/ublk/kublk.h
index 760ff8f..918db5c 100644
--- a/tools/testing/selftests/ublk/kublk.h
+++ b/tools/testing/selftests/ublk/kublk.h
@@ -20,9 +20,15 @@
#include <sys/wait.h>
#include <sys/eventfd.h>
#include <sys/uio.h>
+#include <sys/ipc.h>
+#include <sys/shm.h>
+#include <linux/io_uring.h>
#include <liburing.h>
-#include <linux/ublk_cmd.h>
+#include <semaphore.h>
+
+/* allow ublk_dep.h to override ublk_cmd.h */
#include "ublk_dep.h"
+#include <linux/ublk_cmd.h>
#define __maybe_unused __attribute__((unused))
#define MAX_BACK_FILES 4
@@ -30,6 +36,8 @@
#define min(a, b) ((a) < (b) ? (a) : (b))
#endif
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof(x[0]))
+
/****************** part 1: libublk ********************/
#define CTRL_DEV "/dev/ublk-control"
@@ -42,8 +50,8 @@
#define UBLKSRV_IO_IDLE_SECS 20
#define UBLK_IO_MAX_BYTES (1 << 20)
-#define UBLK_MAX_QUEUES 4
-#define UBLK_QUEUE_DEPTH 128
+#define UBLK_MAX_QUEUES 32
+#define UBLK_QUEUE_DEPTH 1024
#define UBLK_DBG_DEV (1U << 0)
#define UBLK_DBG_QUEUE (1U << 1)
@@ -55,6 +63,16 @@
struct ublk_dev;
struct ublk_queue;
+struct stripe_ctx {
+ /* stripe */
+ unsigned int chunk_size;
+};
+
+struct fault_inject_ctx {
+ /* fault_inject */
+ unsigned long delay_us;
+};
+
struct dev_ctx {
char tgt_type[16];
unsigned long flags;
@@ -66,11 +84,18 @@ struct dev_ctx {
unsigned int logging:1;
unsigned int all:1;
unsigned int fg:1;
-
- /* stripe */
- unsigned int chunk_size;
+ unsigned int recovery:1;
int _evtfd;
+ int _shmid;
+
+ /* built from shmem, only for ublk_dump_dev() */
+ struct ublk_dev *shadow_dev;
+
+ union {
+ struct stripe_ctx stripe;
+ struct fault_inject_ctx fault_inject;
+ };
};
struct ublk_ctrl_cmd_data {
@@ -107,6 +132,14 @@ struct ublk_tgt_ops {
int (*queue_io)(struct ublk_queue *, int tag);
void (*tgt_io_done)(struct ublk_queue *,
int tag, const struct io_uring_cqe *);
+
+ /*
+ * Target specific command line handling
+ *
+ * each option requires argument for target command line
+ */
+ void (*parse_cmd_line)(struct dev_ctx *ctx, int argc, char *argv[]);
+ void (*usage)(const struct ublk_tgt_ops *ops);
};
struct ublk_tgt {
@@ -357,6 +390,7 @@ static inline int ublk_queue_use_zc(const struct ublk_queue *q)
extern const struct ublk_tgt_ops null_tgt_ops;
extern const struct ublk_tgt_ops loop_tgt_ops;
extern const struct ublk_tgt_ops stripe_tgt_ops;
+extern const struct ublk_tgt_ops fault_inject_tgt_ops;
void backing_file_tgt_deinit(struct ublk_dev *dev);
int backing_file_tgt_init(struct ublk_dev *dev);
diff --git a/tools/testing/selftests/ublk/stripe.c b/tools/testing/selftests/ublk/stripe.c
index 179731c..5dbd639 100644
--- a/tools/testing/selftests/ublk/stripe.c
+++ b/tools/testing/selftests/ublk/stripe.c
@@ -281,7 +281,7 @@ static int ublk_stripe_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev)
.max_sectors = dev->dev_info.max_io_buf_bytes >> 9,
},
};
- unsigned chunk_size = ctx->chunk_size;
+ unsigned chunk_size = ctx->stripe.chunk_size;
struct stripe_conf *conf;
unsigned chunk_shift;
loff_t bytes = 0;
@@ -344,10 +344,36 @@ static void ublk_stripe_tgt_deinit(struct ublk_dev *dev)
backing_file_tgt_deinit(dev);
}
+static void ublk_stripe_cmd_line(struct dev_ctx *ctx, int argc, char *argv[])
+{
+ static const struct option longopts[] = {
+ { "chunk_size", 1, NULL, 0 },
+ { 0, 0, 0, 0 }
+ };
+ int option_idx, opt;
+
+ ctx->stripe.chunk_size = 65536;
+ while ((opt = getopt_long(argc, argv, "",
+ longopts, &option_idx)) != -1) {
+ switch (opt) {
+ case 0:
+ if (!strcmp(longopts[option_idx].name, "chunk_size"))
+ ctx->stripe.chunk_size = strtol(optarg, NULL, 10);
+ }
+ }
+}
+
+static void ublk_stripe_usage(const struct ublk_tgt_ops *ops)
+{
+ printf("\tstripe: [--chunk_size chunk_size (default 65536)]\n");
+}
+
const struct ublk_tgt_ops stripe_tgt_ops = {
.name = "stripe",
.init_tgt = ublk_stripe_tgt_init,
.deinit_tgt = ublk_stripe_tgt_deinit,
.queue_io = ublk_stripe_queue_io,
.tgt_io_done = ublk_stripe_io_done,
+ .parse_cmd_line = ublk_stripe_cmd_line,
+ .usage = ublk_stripe_usage,
};
diff --git a/tools/testing/selftests/ublk/test_common.sh b/tools/testing/selftests/ublk/test_common.sh
index a88b359..a81210ca 100755
--- a/tools/testing/selftests/ublk/test_common.sh
+++ b/tools/testing/selftests/ublk/test_common.sh
@@ -17,8 +17,8 @@
local minor
dev=/dev/ublkb"${dev_id}"
- major=$(stat -c '%Hr' "$dev")
- minor=$(stat -c '%Lr' "$dev")
+ major="0x"$(stat -c '%t' "$dev")
+ minor="0x"$(stat -c '%T' "$dev")
echo $(( (major & 0xfff) << 20 | (minor & 0xfffff) ))
}
@@ -30,18 +30,26 @@
}
_create_backfile() {
- local my_size=$1
- local my_file
+ local index=$1
+ local new_size=$2
+ local old_file
+ local new_file
- my_file=$(mktemp ublk_file_"${my_size}"_XXXXX)
- truncate -s "${my_size}" "${my_file}"
- echo "$my_file"
+ old_file="${UBLK_BACKFILES[$index]}"
+ [ -f "$old_file" ] && rm -f "$old_file"
+
+ new_file=$(mktemp ublk_file_"${new_size}"_XXXXX)
+ truncate -s "${new_size}" "${new_file}"
+ UBLK_BACKFILES["$index"]="$new_file"
}
-_remove_backfile() {
- local file=$1
+_remove_files() {
+ local file
- [ -f "$file" ] && rm -f "$file"
+ for file in "${UBLK_BACKFILES[@]}"; do
+ [ -f "$file" ] && rm -f "$file"
+ done
+ [ -f "$UBLK_TMP" ] && rm -f "$UBLK_TMP"
}
_create_tmp_dir() {
@@ -106,6 +114,7 @@
local type=$1
shift 1
modprobe ublk_drv > /dev/null 2>&1
+ UBLK_TMP=$(mktemp ublk_test_XXXXX)
[ "$UBLK_TEST_QUIET" -eq 0 ] && echo "ublk $type: $*"
}
@@ -129,7 +138,10 @@
echo "$1 : [FAIL]"
fi
fi
- [ "$2" -ne 0 ] && exit "$2"
+ if [ "$2" -ne 0 ]; then
+ _remove_files
+ exit "$2"
+ fi
return 0
}
@@ -138,16 +150,16 @@
{
local tid=$1
local code=$2
- shift 2
+
if [ "${code}" -ne 0 ]; then
- _remove_test_files "$@"
_show_result "${tid}" "${code}"
fi
}
_cleanup_test() {
"${UBLK_PROG}" del -a
- rm -f "$UBLK_TMP"
+
+ _remove_files
}
_have_feature()
@@ -158,9 +170,11 @@
return 1
}
-_add_ublk_dev() {
- local kublk_temp;
+_create_ublk_dev() {
local dev_id;
+ local cmd=$1
+
+ shift 1
if [ ! -c /dev/ublk-control ]; then
return ${UBLK_SKIP_CODE}
@@ -171,17 +185,34 @@
fi
fi
- kublk_temp=$(mktemp /tmp/kublk-XXXXXX)
- if ! "${UBLK_PROG}" add "$@" > "${kublk_temp}" 2>&1; then
+ if ! dev_id=$("${UBLK_PROG}" "$cmd" "$@" | grep "dev id" | awk -F '[ :]' '{print $3}'); then
echo "fail to add ublk dev $*"
- rm -f "${kublk_temp}"
return 255
fi
-
- dev_id=$(grep "dev id" "${kublk_temp}" | awk -F '[ :]' '{print $3}')
udevadm settle
- rm -f "${kublk_temp}"
- echo "${dev_id}"
+
+ if [[ "$dev_id" =~ ^[0-9]+$ ]]; then
+ echo "${dev_id}"
+ else
+ return 255
+ fi
+}
+
+_add_ublk_dev() {
+ _create_ublk_dev "add" "$@"
+}
+
+_recover_ublk_dev() {
+ local dev_id
+ local state
+
+ dev_id=$(_create_ublk_dev "recover" "$@")
+ for ((j=0;j<20;j++)); do
+ state=$(_get_ublk_dev_state "${dev_id}")
+ [ "$state" == "LIVE" ] && break
+ sleep 1
+ done
+ echo "$state"
}
# kill the ublk daemon and return ublk device state
@@ -220,7 +251,7 @@
local kill_server=$3
fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio \
- --rw=readwrite --iodepth=64 --size="${size}" --numjobs=4 \
+ --rw=readwrite --iodepth=256 --size="${size}" --numjobs=4 \
--runtime=20 --time_based > /dev/null 2>&1 &
sleep 2
if [ "${kill_server}" = "yes" ]; then
@@ -238,15 +269,80 @@
wait
}
+run_io_and_remove()
+{
+ local size=$1
+ local dev_id
+ shift 1
+
+ dev_id=$(_add_ublk_dev "$@")
+ _check_add_dev "$TID" $?
+
+ [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs. remove device(ublk add $*)"
+ if ! __run_io_and_remove "$dev_id" "${size}" "no"; then
+ echo "/dev/ublkc$dev_id isn't removed"
+ exit 255
+ fi
+}
+
+run_io_and_kill_daemon()
+{
+ local size=$1
+ local dev_id
+ shift 1
+
+ dev_id=$(_add_ublk_dev "$@")
+ _check_add_dev "$TID" $?
+
+ [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs kill ublk server(ublk add $*)"
+ if ! __run_io_and_remove "$dev_id" "${size}" "yes"; then
+ echo "/dev/ublkc$dev_id isn't removed res ${res}"
+ exit 255
+ fi
+}
+
+run_io_and_recover()
+{
+ local state
+ local dev_id
+
+ dev_id=$(_add_ublk_dev "$@")
+ _check_add_dev "$TID" $?
+
+ fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio \
+ --rw=readwrite --iodepth=256 --size="${size}" --numjobs=4 \
+ --runtime=20 --time_based > /dev/null 2>&1 &
+ sleep 4
+
+ state=$(__ublk_kill_daemon "${dev_id}" "QUIESCED")
+ if [ "$state" != "QUIESCED" ]; then
+ echo "device isn't quiesced($state) after killing daemon"
+ return 255
+ fi
+
+ state=$(_recover_ublk_dev -n "$dev_id" "$@")
+ if [ "$state" != "LIVE" ]; then
+ echo "faile to recover to LIVE($state)"
+ return 255
+ fi
+
+ if ! __remove_ublk_dev_return "${dev_id}"; then
+ echo "delete dev ${dev_id} failed"
+ return 255
+ fi
+ wait
+}
+
+
_ublk_test_top_dir()
{
cd "$(dirname "$0")" && pwd
}
-UBLK_TMP=$(mktemp ublk_test_XXXXX)
UBLK_PROG=$(_ublk_test_top_dir)/kublk
UBLK_TEST_QUIET=1
UBLK_TEST_SHOW_RESULT=1
+UBLK_BACKFILES=()
export UBLK_PROG
export UBLK_TEST_QUIET
export UBLK_TEST_SHOW_RESULT
diff --git a/tools/testing/selftests/ublk/test_generic_04.sh b/tools/testing/selftests/ublk/test_generic_04.sh
new file mode 100755
index 0000000..8a3bc08
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_04.sh
@@ -0,0 +1,40 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_04"
+ERR_CODE=0
+
+ublk_run_recover_test()
+{
+ run_io_and_recover "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
+ fi
+}
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "recover" "basic recover function verification"
+
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
+
+ublk_run_recover_test -t null -q 2 -r 1 &
+ublk_run_recover_test -t loop -q 2 -r 1 "${UBLK_BACKFILES[0]}" &
+ublk_run_recover_test -t stripe -q 2 -r 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+ublk_run_recover_test -t null -q 2 -r 1 -i 1 &
+ublk_run_recover_test -t loop -q 2 -r 1 -i 1 "${UBLK_BACKFILES[0]}" &
+ublk_run_recover_test -t stripe -q 2 -r 1 -i 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+_cleanup_test "recover"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_generic_05.sh b/tools/testing/selftests/ublk/test_generic_05.sh
new file mode 100755
index 0000000..3bb00a3
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_05.sh
@@ -0,0 +1,44 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_05"
+ERR_CODE=0
+
+ublk_run_recover_test()
+{
+ run_io_and_recover "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
+ fi
+}
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+if ! _have_feature "ZERO_COPY"; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "recover" "basic recover function verification (zero copy)"
+
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
+
+ublk_run_recover_test -t null -q 2 -r 1 -z &
+ublk_run_recover_test -t loop -q 2 -r 1 -z "${UBLK_BACKFILES[0]}" &
+ublk_run_recover_test -t stripe -q 2 -r 1 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+ublk_run_recover_test -t null -q 2 -r 1 -z -i 1 &
+ublk_run_recover_test -t loop -q 2 -r 1 -z -i 1 "${UBLK_BACKFILES[0]}" &
+ublk_run_recover_test -t stripe -q 2 -r 1 -z -i 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+_cleanup_test "recover"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_generic_06.sh b/tools/testing/selftests/ublk/test_generic_06.sh
new file mode 100755
index 0000000..b67230c
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_06.sh
@@ -0,0 +1,41 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_06"
+ERR_CODE=0
+
+_prep_test "fault_inject" "fast cleanup when all I/Os of one hctx are in server"
+
+# configure ublk server to sleep 2s before completing each I/O
+dev_id=$(_add_ublk_dev -t fault_inject -q 2 -d 1 --delay_us 2000000)
+_check_add_dev $TID $?
+
+STARTTIME=${SECONDS}
+
+dd if=/dev/urandom of=/dev/ublkb${dev_id} oflag=direct bs=4k count=1 status=none > /dev/null 2>&1 &
+dd_pid=$!
+
+__ublk_kill_daemon ${dev_id} "DEAD"
+
+wait $dd_pid
+dd_exitcode=$?
+
+ENDTIME=${SECONDS}
+ELAPSED=$(($ENDTIME - $STARTTIME))
+
+# assert that dd sees an error and exits quickly after ublk server is
+# killed. previously this relied on seeing an I/O timeout and so would
+# take ~30s
+if [ $dd_exitcode -eq 0 ]; then
+ echo "dd unexpectedly exited successfully!"
+ ERR_CODE=255
+fi
+if [ $ELAPSED -ge 5 ]; then
+ echo "dd took $ELAPSED seconds to exit (>= 5s tolerance)!"
+ ERR_CODE=255
+fi
+
+_cleanup_test "fault_inject"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_01.sh b/tools/testing/selftests/ublk/test_loop_01.sh
index 1ef8b60..833fa0d 100755
--- a/tools/testing/selftests/ublk/test_loop_01.sh
+++ b/tools/testing/selftests/ublk/test_loop_01.sh
@@ -12,10 +12,10 @@
_prep_test "loop" "write and verify test"
-backfile_0=$(_create_backfile 256M)
+_create_backfile 0 256M
-dev_id=$(_add_ublk_dev -t loop "$backfile_0")
-_check_add_dev $TID $? "${backfile_0}"
+dev_id=$(_add_ublk_dev -t loop "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
# run fio over the ublk disk
_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M
@@ -23,6 +23,4 @@
_cleanup_test "loop"
-_remove_backfile "$backfile_0"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_02.sh b/tools/testing/selftests/ublk/test_loop_02.sh
index 03863d8..874568b 100755
--- a/tools/testing/selftests/ublk/test_loop_02.sh
+++ b/tools/testing/selftests/ublk/test_loop_02.sh
@@ -8,15 +8,13 @@
_prep_test "loop" "mkfs & mount & umount"
-backfile_0=$(_create_backfile 256M)
-dev_id=$(_add_ublk_dev -t loop "$backfile_0")
-_check_add_dev $TID $? "$backfile_0"
+_create_backfile 0 256M
+dev_id=$(_add_ublk_dev -t loop "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
_mkfs_mount_test /dev/ublkb"${dev_id}"
ERR_CODE=$?
_cleanup_test "loop"
-_remove_backfile "$backfile_0"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_03.sh b/tools/testing/selftests/ublk/test_loop_03.sh
index e9ca744..c30f797 100755
--- a/tools/testing/selftests/ublk/test_loop_03.sh
+++ b/tools/testing/selftests/ublk/test_loop_03.sh
@@ -12,9 +12,9 @@
_prep_test "loop" "write and verify over zero copy"
-backfile_0=$(_create_backfile 256M)
-dev_id=$(_add_ublk_dev -t loop -z "$backfile_0")
-_check_add_dev $TID $? "$backfile_0"
+_create_backfile 0 256M
+dev_id=$(_add_ublk_dev -t loop -z "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
# run fio over the ublk disk
_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M
@@ -22,6 +22,4 @@
_cleanup_test "loop"
-_remove_backfile "$backfile_0"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_04.sh b/tools/testing/selftests/ublk/test_loop_04.sh
index 1435422..b01d75b 100755
--- a/tools/testing/selftests/ublk/test_loop_04.sh
+++ b/tools/testing/selftests/ublk/test_loop_04.sh
@@ -8,15 +8,14 @@
_prep_test "loop" "mkfs & mount & umount with zero copy"
-backfile_0=$(_create_backfile 256M)
-dev_id=$(_add_ublk_dev -t loop -z "$backfile_0")
-_check_add_dev $TID $? "$backfile_0"
+_create_backfile 0 256M
+
+dev_id=$(_add_ublk_dev -t loop -z "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
_mkfs_mount_test /dev/ublkb"${dev_id}"
ERR_CODE=$?
_cleanup_test "loop"
-_remove_backfile "$backfile_0"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_05.sh b/tools/testing/selftests/ublk/test_loop_05.sh
index 2e6e2e6..de21415 100755
--- a/tools/testing/selftests/ublk/test_loop_05.sh
+++ b/tools/testing/selftests/ublk/test_loop_05.sh
@@ -12,10 +12,10 @@
_prep_test "loop" "write and verify test"
-backfile_0=$(_create_backfile 256M)
+_create_backfile 0 256M
-dev_id=$(_add_ublk_dev -q 2 -t loop "$backfile_0")
-_check_add_dev $TID $? "${backfile_0}"
+dev_id=$(_add_ublk_dev -q 2 -t loop "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
# run fio over the ublk disk
_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M
@@ -23,6 +23,4 @@
_cleanup_test "loop"
-_remove_backfile "$backfile_0"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_01.sh b/tools/testing/selftests/ublk/test_stress_01.sh
index a8be245..7d3150f 100755
--- a/tools/testing/selftests/ublk/test_stress_01.sh
+++ b/tools/testing/selftests/ublk/test_stress_01.sh
@@ -4,44 +4,31 @@
. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
TID="stress_01"
ERR_CODE=0
-DEV_ID=-1
ublk_io_and_remove()
{
- local size=$1
- shift 1
- local backfile=""
- if echo "$@" | grep -q "loop"; then
- backfile=${*: -1}
- fi
- DEV_ID=$(_add_ublk_dev "$@")
- _check_add_dev $TID $? "${backfile}"
-
- [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs. remove device(ublk add $*)"
- if ! __run_io_and_remove "${DEV_ID}" "${size}" "no"; then
- echo "/dev/ublkc${DEV_ID} isn't removed"
- _remove_backfile "${backfile}"
- exit 255
+ run_io_and_remove "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
fi
}
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
_prep_test "stress" "run IO and remove device"
-ublk_io_and_remove 8G -t null -q 4
-ERR_CODE=$?
-if [ ${ERR_CODE} -ne 0 ]; then
- _show_result $TID $ERR_CODE
-fi
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
-BACK_FILE=$(_create_backfile 256M)
-ublk_io_and_remove 256M -t loop -q 4 "${BACK_FILE}"
-ERR_CODE=$?
-if [ ${ERR_CODE} -ne 0 ]; then
- _show_result $TID $ERR_CODE
-fi
+ublk_io_and_remove 8G -t null -q 4 &
+ublk_io_and_remove 256M -t loop -q 4 "${UBLK_BACKFILES[0]}" &
+ublk_io_and_remove 256M -t stripe -q 4 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
-ublk_io_and_remove 256M -t loop -q 4 -z "${BACK_FILE}"
-ERR_CODE=$?
_cleanup_test "stress"
-_remove_backfile "${BACK_FILE}"
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_02.sh b/tools/testing/selftests/ublk/test_stress_02.sh
index 2159e4c..1a90651 100755
--- a/tools/testing/selftests/ublk/test_stress_02.sh
+++ b/tools/testing/selftests/ublk/test_stress_02.sh
@@ -4,44 +4,31 @@
. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
TID="stress_02"
ERR_CODE=0
-DEV_ID=-1
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
ublk_io_and_kill_daemon()
{
- local size=$1
- shift 1
- local backfile=""
- if echo "$@" | grep -q "loop"; then
- backfile=${*: -1}
- fi
- DEV_ID=$(_add_ublk_dev "$@")
- _check_add_dev $TID $? "${backfile}"
-
- [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs kill ublk server(ublk add $*)"
- if ! __run_io_and_remove "${DEV_ID}" "${size}" "yes"; then
- echo "/dev/ublkc${DEV_ID} isn't removed res ${res}"
- _remove_backfile "${backfile}"
- exit 255
+ run_io_and_kill_daemon "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
fi
}
_prep_test "stress" "run IO and kill ublk server"
-ublk_io_and_kill_daemon 8G -t null -q 4
-ERR_CODE=$?
-if [ ${ERR_CODE} -ne 0 ]; then
- _show_result $TID $ERR_CODE
-fi
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
-BACK_FILE=$(_create_backfile 256M)
-ublk_io_and_kill_daemon 256M -t loop -q 4 "${BACK_FILE}"
-ERR_CODE=$?
-if [ ${ERR_CODE} -ne 0 ]; then
- _show_result $TID $ERR_CODE
-fi
+ublk_io_and_kill_daemon 8G -t null -q 4 &
+ublk_io_and_kill_daemon 256M -t loop -q 4 "${UBLK_BACKFILES[0]}" &
+ublk_io_and_kill_daemon 256M -t stripe -q 4 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
-ublk_io_and_kill_daemon 256M -t loop -q 4 -z "${BACK_FILE}"
-ERR_CODE=$?
_cleanup_test "stress"
-_remove_backfile "${BACK_FILE}"
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_03.sh b/tools/testing/selftests/ublk/test_stress_03.sh
new file mode 100755
index 0000000..e0854f7
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stress_03.sh
@@ -0,0 +1,38 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+TID="stress_03"
+ERR_CODE=0
+
+ublk_io_and_remove()
+{
+ run_io_and_remove "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
+ fi
+}
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+if ! _have_feature "ZERO_COPY"; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "stress" "run IO and remove device(zero copy)"
+
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
+
+ublk_io_and_remove 8G -t null -q 4 -z &
+ublk_io_and_remove 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" &
+ublk_io_and_remove 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+_cleanup_test "stress"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_04.sh b/tools/testing/selftests/ublk/test_stress_04.sh
new file mode 100755
index 0000000..1798a98
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stress_04.sh
@@ -0,0 +1,37 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+TID="stress_04"
+ERR_CODE=0
+
+ublk_io_and_kill_daemon()
+{
+ run_io_and_kill_daemon "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
+ fi
+}
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+if ! _have_feature "ZERO_COPY"; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "stress" "run IO and kill ublk server(zero copy)"
+
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
+
+ublk_io_and_kill_daemon 8G -t null -q 4 -z &
+ublk_io_and_kill_daemon 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" &
+ublk_io_and_kill_daemon 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+_cleanup_test "stress"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_05.sh b/tools/testing/selftests/ublk/test_stress_05.sh
new file mode 100755
index 0000000..a7071b1
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stress_05.sh
@@ -0,0 +1,64 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+TID="stress_05"
+ERR_CODE=0
+
+run_io_and_remove()
+{
+ local size=$1
+ local dev_id
+ local dev_pid
+ shift 1
+
+ dev_id=$(_add_ublk_dev "$@")
+ _check_add_dev $TID $?
+
+ [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs. remove device(ublk add $*)"
+
+ fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio \
+ --rw=readwrite --iodepth=128 --size="${size}" --numjobs=4 \
+ --runtime=40 --time_based > /dev/null 2>&1 &
+ sleep 4
+
+ dev_pid=$(_get_ublk_daemon_pid "$dev_id")
+ kill -9 "$dev_pid"
+
+ if ! __remove_ublk_dev_return "${dev_id}"; then
+ echo "delete dev ${dev_id} failed"
+ return 255
+ fi
+}
+
+ublk_io_and_remove()
+{
+ run_io_and_remove "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
+ fi
+}
+
+_prep_test "stress" "run IO and remove device with recovery enabled"
+
+_create_backfile 0 256M
+_create_backfile 1 256M
+
+for reissue in $(seq 0 1); do
+ ublk_io_and_remove 8G -t null -q 4 -g 1 -r 1 -i "$reissue" &
+ ublk_io_and_remove 256M -t loop -q 4 -g 1 -r 1 -i "$reissue" "${UBLK_BACKFILES[0]}" &
+ wait
+done
+
+if _have_feature "ZERO_COPY"; then
+ for reissue in $(seq 0 1); do
+ ublk_io_and_remove 8G -t null -q 4 -g 1 -z -r 1 -i "$reissue" &
+ ublk_io_and_remove 256M -t loop -q 4 -g 1 -z -r 1 -i "$reissue" "${UBLK_BACKFILES[1]}" &
+ wait
+ done
+fi
+
+_cleanup_test "stress"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stripe_01.sh b/tools/testing/selftests/ublk/test_stripe_01.sh
index 7e387ef..4e4f0fd 100755
--- a/tools/testing/selftests/ublk/test_stripe_01.sh
+++ b/tools/testing/selftests/ublk/test_stripe_01.sh
@@ -12,19 +12,15 @@
_prep_test "stripe" "write and verify test"
-backfile_0=$(_create_backfile 256M)
-backfile_1=$(_create_backfile 256M)
+_create_backfile 0 256M
+_create_backfile 1 256M
-dev_id=$(_add_ublk_dev -t stripe "$backfile_0" "$backfile_1")
-_check_add_dev $TID $? "${backfile_0}"
+dev_id=$(_add_ublk_dev -t stripe "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}")
+_check_add_dev $TID $?
# run fio over the ublk disk
_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=512M
ERR_CODE=$?
_cleanup_test "stripe"
-
-_remove_backfile "$backfile_0"
-_remove_backfile "$backfile_1"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stripe_02.sh b/tools/testing/selftests/ublk/test_stripe_02.sh
index e8a45fa..5820ab2 100755
--- a/tools/testing/selftests/ublk/test_stripe_02.sh
+++ b/tools/testing/selftests/ublk/test_stripe_02.sh
@@ -8,17 +8,14 @@
_prep_test "stripe" "mkfs & mount & umount"
-backfile_0=$(_create_backfile 256M)
-backfile_1=$(_create_backfile 256M)
-dev_id=$(_add_ublk_dev -t stripe "$backfile_0" "$backfile_1")
-_check_add_dev $TID $? "$backfile_0" "$backfile_1"
+_create_backfile 0 256M
+_create_backfile 1 256M
+
+dev_id=$(_add_ublk_dev -t stripe "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}")
+_check_add_dev $TID $?
_mkfs_mount_test /dev/ublkb"${dev_id}"
ERR_CODE=$?
_cleanup_test "stripe"
-
-_remove_backfile "$backfile_0"
-_remove_backfile "$backfile_1"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stripe_03.sh b/tools/testing/selftests/ublk/test_stripe_03.sh
index c1b34af..20b977e 100755
--- a/tools/testing/selftests/ublk/test_stripe_03.sh
+++ b/tools/testing/selftests/ublk/test_stripe_03.sh
@@ -12,19 +12,15 @@
_prep_test "stripe" "write and verify test"
-backfile_0=$(_create_backfile 256M)
-backfile_1=$(_create_backfile 256M)
+_create_backfile 0 256M
+_create_backfile 1 256M
-dev_id=$(_add_ublk_dev -q 2 -t stripe "$backfile_0" "$backfile_1")
-_check_add_dev $TID $? "${backfile_0}"
+dev_id=$(_add_ublk_dev -q 2 -t stripe "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}")
+_check_add_dev $TID $?
# run fio over the ublk disk
_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=512M
ERR_CODE=$?
_cleanup_test "stripe"
-
-_remove_backfile "$backfile_0"
-_remove_backfile "$backfile_1"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stripe_04.sh b/tools/testing/selftests/ublk/test_stripe_04.sh
new file mode 100755
index 0000000..1b51ed2
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stripe_04.sh
@@ -0,0 +1,21 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="stripe_04"
+ERR_CODE=0
+
+_prep_test "stripe" "mkfs & mount & umount on zero copy"
+
+_create_backfile 0 256M
+_create_backfile 1 256M
+
+dev_id=$(_add_ublk_dev -t stripe -z -q 2 "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}")
+_check_add_dev $TID $?
+
+_mkfs_mount_test /dev/ublkb"${dev_id}"
+ERR_CODE=$?
+
+_cleanup_test "stripe"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/shared/linux.c b/tools/testing/shared/linux.c
index 66dbb36..0f97fb0 100644
--- a/tools/testing/shared/linux.c
+++ b/tools/testing/shared/linux.c
@@ -150,7 +150,7 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
void kmem_cache_free_bulk(struct kmem_cache *cachep, size_t size, void **list)
{
if (kmalloc_verbose)
- pr_debug("Bulk free %p[0-%lu]\n", list, size - 1);
+ pr_debug("Bulk free %p[0-%zu]\n", list, size - 1);
pthread_mutex_lock(&cachep->lock);
for (int i = 0; i < size; i++)
@@ -168,7 +168,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
size_t i;
if (kmalloc_verbose)
- pr_debug("Bulk alloc %lu\n", size);
+ pr_debug("Bulk alloc %zu\n", size);
pthread_mutex_lock(&cachep->lock);
if (cachep->nr_objs >= size) {
diff --git a/tools/testing/shared/linux/cleanup.h b/tools/testing/shared/linux/cleanup.h
new file mode 100644
index 0000000..ea30814
--- /dev/null
+++ b/tools/testing/shared/linux/cleanup.h
@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include "../../../../include/linux/cleanup.h"
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 746e1f4..727b542 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -75,7 +75,7 @@
depends on KVM && COMPAT && !(S390 || ARM64 || RISCV)
config HAVE_KVM_IRQ_BYPASS
- bool
+ tristate
select IRQ_BYPASS_MANAGER
config HAVE_KVM_VCPU_ASYNC_IOCTL
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 249ba5b..11e5d1e 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -149,7 +149,7 @@ irqfd_shutdown(struct work_struct *work)
/*
* It is now safe to release the object's resources
*/
-#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
+#if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS)
irq_bypass_unregister_consumer(&irqfd->consumer);
#endif
eventfd_ctx_put(irqfd->eventfd);
@@ -274,7 +274,7 @@ static void irqfd_update(struct kvm *kvm, struct kvm_kernel_irqfd *irqfd)
write_seqcount_end(&irqfd->irq_entry_sc);
}
-#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
+#if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS)
void __attribute__((weak)) kvm_arch_irq_bypass_stop(
struct irq_bypass_consumer *cons)
{
@@ -424,7 +424,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
if (events & EPOLLIN)
schedule_work(&irqfd->inject);
-#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
+#if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS)
if (kvm_arch_has_irq_bypass()) {
irqfd->consumer.token = (void *)irqfd->eventfd;
irqfd->consumer.add_producer = kvm_arch_irq_bypass_add_producer;
@@ -609,14 +609,14 @@ void kvm_irq_routing_update(struct kvm *kvm)
spin_lock_irq(&kvm->irqfds.lock);
list_for_each_entry(irqfd, &kvm->irqfds.items, list) {
-#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
+#if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS)
/* Under irqfds.lock, so can read irq_entry safely */
struct kvm_kernel_irq_routing_entry old = irqfd->irq_entry;
#endif
irqfd_update(kvm, irqfd);
-#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
+#if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS)
if (irqfd->producer &&
kvm_arch_irqfd_route_changed(&old, &irqfd->irq_entry)) {
int ret = kvm_arch_update_irqfd_routing(
