Merge tag 'vfs-6.12-rc6.fixes' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs
Pull filesystem fixes from Christian Brauner:
"VFS:
- Fix copy_page_from_iter_atomic() if KMAP_LOCAL_FORCE_MAP=y is set
- Add a get_tree_bdev_flags() helper that allows to modify e.g.,
whether errors are logged into the filesystem context during
superblock creation. This is used by erofs to fix a userspace
regression where an error is currently logged when its used on a
regular file which is an new allowed mode in erofs.
netfs:
- Fix the sysfs debug path in the documentation.
- Fix iov_iter_get_pages*() for folio queues by skipping the page
extracation if we're at the end of a folio.
afs:
- Fix moving subdirectories to different parent directory.
autofs:
- Fix handling of AUTOFS_DEV_IOCTL_TIMEOUT_CMD ioctl in
validate_dev_ioctl(). The actual ioctl number, not the ioctl
command needs to be checked for autofs"
* tag 'vfs-6.12-rc6.fixes' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs:
iov_iter: fix copy_page_from_iter_atomic() if KMAP_LOCAL_FORCE_MAP
autofs: fix thinko in validate_dev_ioctl()
iov_iter: Fix iov_iter_get_pages*() for folio_queue
afs: Fix missing subdir edit when renamed between parent dirs
doc: correcting the debug path for cachefiles
erofs: use get_tree_bdev_flags() to avoid misleading messages
fs/super.c: introduce get_tree_bdev_flags()
diff --git a/.mailmap b/.mailmap
index 442da86..9a94c51 100644
--- a/.mailmap
+++ b/.mailmap
@@ -306,6 +306,11 @@
Jens Axboe <axboe@kernel.dk> <axboe@meta.com>
Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
Jernej Skrabec <jernej.skrabec@gmail.com> <jernej.skrabec@siol.net>
+Jesper Dangaard Brouer <hawk@kernel.org> <brouer@redhat.com>
+Jesper Dangaard Brouer <hawk@kernel.org> <hawk@comx.dk>
+Jesper Dangaard Brouer <hawk@kernel.org> <jbrouer@redhat.com>
+Jesper Dangaard Brouer <hawk@kernel.org> <jdb@comx.dk>
+Jesper Dangaard Brouer <hawk@kernel.org> <netoptimizer@brouer.com>
Jessica Zhang <quic_jesszhan@quicinc.com> <jesszhan@codeaurora.org>
Jilai Wang <quic_jilaiw@quicinc.com> <jilaiw@codeaurora.org>
Jiri Kosina <jikos@kernel.org> <jikos@jikos.cz>
diff --git a/Documentation/admin-guide/pm/cpufreq.rst b/Documentation/admin-guide/pm/cpufreq.rst
index fe1be4ad..a21369e 100644
--- a/Documentation/admin-guide/pm/cpufreq.rst
+++ b/Documentation/admin-guide/pm/cpufreq.rst
@@ -425,8 +425,8 @@
``rate_limit_us``
Minimum time (in microseconds) that has to pass between two consecutive
- runs of governor computations (default: 1000 times the scaling driver's
- transition latency).
+ runs of governor computations (default: 1.5 times the scaling driver's
+ transition latency or the maximum 2ms).
The purpose of this tunable is to reduce the scheduler context overhead
of the governor which might be excessive without it.
@@ -474,17 +474,17 @@
This is how often the governor's worker routine should run, in
microseconds.
- Typically, it is set to values of the order of 10000 (10 ms). Its
- default value is equal to the value of ``cpuinfo_transition_latency``
- for each policy this governor is attached to (but since the unit here
- is greater by 1000, this means that the time represented by
- ``sampling_rate`` is 1000 times greater than the transition latency by
- default).
+ Typically, it is set to values of the order of 2000 (2 ms). Its
+ default value is to add a 50% breathing room
+ to ``cpuinfo_transition_latency`` on each policy this governor is
+ attached to. The minimum is typically the length of two scheduler
+ ticks.
If this tunable is per-policy, the following shell command sets the time
- represented by it to be 750 times as high as the transition latency::
+ represented by it to be 1.5 times as high as the transition latency
+ (the default)::
- # echo `$(($(cat cpuinfo_transition_latency) * 750 / 1000)) > ondemand/sampling_rate
+ # echo `$(($(cat cpuinfo_transition_latency) * 3 / 2)) > ondemand/sampling_rate
``up_threshold``
If the estimated CPU load is above this value (in percent), the governor
diff --git a/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml b/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml
index ab3206f..beef193 100644
--- a/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml
+++ b/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml
@@ -102,21 +102,21 @@
default: 2
interrupts:
- oneOf:
- - minItems: 1
- items:
- - description: TX interrupt
- - description: RX interrupt
- - items:
- - description: common/combined interrupt
+ minItems: 1
+ maxItems: 2
interrupt-names:
oneOf:
- - minItems: 1
+ - description: TX interrupt
+ const: tx
+ - description: RX interrupt
+ const: rx
+ - description: TX and RX interrupts
items:
- const: tx
- const: rx
- - const: common
+ - description: Common/combined interrupt
+ const: common
fck_parent:
$ref: /schemas/types.yaml#/definitions/string
diff --git a/Documentation/devicetree/bindings/sound/rockchip,rk3308-codec.yaml b/Documentation/devicetree/bindings/sound/rockchip,rk3308-codec.yaml
index ecf3d7d..2cf229a 100644
--- a/Documentation/devicetree/bindings/sound/rockchip,rk3308-codec.yaml
+++ b/Documentation/devicetree/bindings/sound/rockchip,rk3308-codec.yaml
@@ -48,6 +48,10 @@
- const: mclk_rx
- const: hclk
+ port:
+ $ref: audio-graph-port.yaml#
+ unevaluatedProperties: false
+
resets:
maxItems: 1
diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst
index f0d2cb2..73f0bfd 100644
--- a/Documentation/filesystems/netfs_library.rst
+++ b/Documentation/filesystems/netfs_library.rst
@@ -592,4 +592,3 @@
.. kernel-doc:: include/linux/netfs.h
.. kernel-doc:: fs/netfs/buffered_read.c
-.. kernel-doc:: fs/netfs/io.c
diff --git a/Documentation/networking/packet_mmap.rst b/Documentation/networking/packet_mmap.rst
index dca15d1..0237078 100644
--- a/Documentation/networking/packet_mmap.rst
+++ b/Documentation/networking/packet_mmap.rst
@@ -16,7 +16,7 @@
Howto can be found at:
- https://sites.google.com/site/packetmmap/
+ https://web.archive.org/web/20220404160947/https://sites.google.com/site/packetmmap/
Please send your comments to
- Ulisses Alonso Camaró <uaca@i.hate.spam.alumni.uv.es>
@@ -166,7 +166,8 @@
/* bind socket to eth0 */
bind(this->socket, (struct sockaddr *)&my_addr, sizeof(struct sockaddr_ll));
- A complete tutorial is available at: https://sites.google.com/site/packetmmap/
+ A complete tutorial is available at:
+ https://web.archive.org/web/20220404160947/https://sites.google.com/site/packetmmap/
By default, the user should put data at::
diff --git a/Documentation/userspace-api/mseal.rst b/Documentation/userspace-api/mseal.rst
index 4132eec..41102f7 100644
--- a/Documentation/userspace-api/mseal.rst
+++ b/Documentation/userspace-api/mseal.rst
@@ -23,177 +23,166 @@
A similar feature already exists in the XNU kernel with the
VM_FLAGS_PERMANENT flag [1] and on OpenBSD with the mimmutable syscall [2].
-User API
-========
-mseal()
------------
-The mseal() syscall has the following signature:
+SYSCALL
+=======
+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:
+ - The start address must be in an allocated VMA.
+ - The start address must be page aligned.
+ - The end address (**addr** + **len**) must be in an allocated VMA.
+ - no gap (unallocated memory) between start and end address.
-**addr/len**: virtual memory address range.
+ The ``len`` will be paged aligned implicitly by the kernel.
-The address range set by ``addr``/``len`` must meet:
- - The start address must be in an allocated VMA.
- - The start address must be page aligned.
- - The end address (``addr`` + ``len``) must be in an allocated VMA.
- - no gap (unallocated memory) between start and end address.
+ **flags**: reserved for future use.
-The ``len`` will be paged aligned implicitly by the kernel.
+ **Return values**:
+ - **0**: Success.
+ - **-EINVAL**:
+ * Invalid input ``flags``.
+ * The start address (``addr``) is not page aligned.
+ * Address range (``addr`` + ``len``) overflow.
+ - **-ENOMEM**:
+ * The start address (``addr``) is not allocated.
+ * The end address (``addr`` + ``len``) is not allocated.
+ * A gap (unallocated memory) between start and end address.
+ - **-EPERM**:
+ * sealing is supported only on 64-bit CPUs, 32-bit is not supported.
-**flags**: reserved for future use.
+ **Note about error return**:
+ - For above error cases, users can expect the given memory range is
+ unmodified, i.e. no partial update.
+ - There might be other internal errors/cases not listed here, e.g.
+ error during merging/splitting VMAs, or the process reaching the maximum
+ number of supported VMAs. In those cases, partial updates to the given
+ memory range could happen. However, those cases should be rare.
-**return values**:
+ **Architecture support**:
+ mseal only works on 64-bit CPUs, not 32-bit CPUs.
-- ``0``: Success.
+ **Idempotent**:
+ users can call mseal multiple times. mseal on an already sealed memory
+ is a no-action (not error).
-- ``-EINVAL``:
- - Invalid input ``flags``.
- - The start address (``addr``) is not page aligned.
- - Address range (``addr`` + ``len``) overflow.
+ **no munseal**
+ Once mapping is sealed, it can't be unsealed. The kernel should never
+ have munseal, this is consistent with other sealing feature, e.g.
+ F_SEAL_SEAL for file.
-- ``-ENOMEM``:
- - The start address (``addr``) is not allocated.
- - The end address (``addr`` + ``len``) is not allocated.
- - A gap (unallocated memory) between start and end address.
+Blocked mm syscall for sealed mapping
+-------------------------------------
+ It might be important to note: **once the mapping is sealed, it will
+ stay in the process's memory until the process terminates**.
-- ``-EPERM``:
- - sealing is supported only on 64-bit CPUs, 32-bit is not supported.
+ Example::
-- For above error cases, users can expect the given memory range is
- unmodified, i.e. no partial update.
+ *ptr = mmap(0, 4096, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+ rc = mseal(ptr, 4096, 0);
+ /* munmap will fail */
+ rc = munmap(ptr, 4096);
+ assert(rc < 0);
-- There might be other internal errors/cases not listed here, e.g.
- error during merging/splitting VMAs, or the process reaching the max
- number of supported VMAs. In those cases, partial updates to the given
- memory range could happen. However, those cases should be rare.
+ Blocked mm syscall:
+ - munmap
+ - mmap
+ - mremap
+ - mprotect and pkey_mprotect
+ - some destructive madvise behaviors: MADV_DONTNEED, MADV_FREE,
+ MADV_DONTNEED_LOCKED, MADV_FREE, MADV_DONTFORK, MADV_WIPEONFORK
-**Blocked operations after sealing**:
- Unmapping, moving to another location, and shrinking the size,
- via munmap() and mremap(), can leave an empty space, therefore
- can be replaced with a VMA with a new set of attributes.
+ The first set of syscalls to block is munmap, mremap, mmap. They can
+ either leave an empty space in the address space, therefore allowing
+ replacement with a new mapping with new set of attributes, or can
+ overwrite the existing mapping with another mapping.
- Moving or expanding a different VMA into the current location,
- via mremap().
+ mprotect and pkey_mprotect are blocked because they changes the
+ protection bits (RWX) of the mapping.
- Modifying a VMA via mmap(MAP_FIXED).
+ Certain destructive madvise behaviors, specifically MADV_DONTNEED,
+ MADV_FREE, MADV_DONTNEED_LOCKED, and MADV_WIPEONFORK, can introduce
+ risks when applied to anonymous memory by threads lacking write
+ permissions. Consequently, these operations are prohibited under such
+ conditions. The aforementioned behaviors have the potential to modify
+ region contents by discarding pages, effectively performing a memset(0)
+ operation on the anonymous memory.
- Size expansion, via mremap(), does not appear to pose any
- specific risks to sealed VMAs. It is included anyway because
- the use case is unclear. In any case, users can rely on
- merging to expand a sealed VMA.
+ Kernel will return -EPERM for blocked syscalls.
- mprotect() and pkey_mprotect().
+ When blocked syscall return -EPERM due to sealing, the memory regions may
+ or may not be changed, depends on the syscall being blocked:
- Some destructive madvice() behaviors (e.g. MADV_DONTNEED)
- for anonymous memory, when users don't have write permission to the
- memory. Those behaviors can alter region contents by discarding pages,
- effectively a memset(0) for anonymous memory.
+ - munmap: munmap is atomic. If one of VMAs in the given range is
+ sealed, none of VMAs are updated.
+ - mprotect, pkey_mprotect, madvise: partial update might happen, e.g.
+ when mprotect over multiple VMAs, mprotect might update the beginning
+ VMAs before reaching the sealed VMA and return -EPERM.
+ - mmap and mremap: undefined behavior.
- Kernel will return -EPERM for blocked operations.
-
- For blocked operations, one can expect the given address is unmodified,
- i.e. no partial update. Note, this is different from existing mm
- system call behaviors, where partial updates are made till an error is
- found and returned to userspace. To give an example:
-
- Assume following code sequence:
-
- - ptr = mmap(null, 8192, PROT_NONE);
- - munmap(ptr + 4096, 4096);
- - ret1 = mprotect(ptr, 8192, PROT_READ);
- - mseal(ptr, 4096);
- - ret2 = mprotect(ptr, 8192, PROT_NONE);
-
- ret1 will be -ENOMEM, the page from ptr is updated to PROT_READ.
-
- ret2 will be -EPERM, the page remains to be PROT_READ.
-
-**Note**:
-
-- mseal() only works on 64-bit CPUs, not 32-bit CPU.
-
-- users can call mseal() multiple times, mseal() on an already sealed memory
- is a no-action (not error).
-
-- munseal() is not supported.
-
-Use cases:
-==========
+Use cases
+=========
- glibc:
The dynamic linker, during loading ELF executables, can apply sealing to
- non-writable memory segments.
+ mapping segments.
-- Chrome browser: protect some security sensitive data-structures.
+- Chrome browser: protect some security sensitive data structures.
-Notes on which memory to seal:
-==============================
-
-It might be important to note that sealing changes the lifetime of a mapping,
-i.e. the sealed mapping won’t be unmapped till the process terminates or the
-exec system call is invoked. Applications can apply sealing to any virtual
-memory region from userspace, but it is crucial to thoroughly analyze the
-mapping's lifetime prior to apply the sealing.
+When not to use mseal
+=====================
+Applications can apply sealing to any virtual memory region from userspace,
+but it is *crucial to thoroughly analyze the mapping's lifetime* prior to
+apply the sealing. This is because the sealed mapping *won’t be unmapped*
+until the process terminates or the exec system call is invoked.
For example:
+ - aio/shm
+ aio/shm can call mmap and munmap on behalf of userspace, e.g.
+ ksys_shmdt() in shm.c. The lifetimes of those mapping are not tied to
+ the lifetime of the process. If those memories are sealed from userspace,
+ then munmap will fail, causing leaks in VMA address space during the
+ lifetime of the process.
-- aio/shm
+ - ptr allocated by malloc (heap)
+ Don't use mseal on the memory ptr return from malloc().
+ malloc() is implemented by allocator, e.g. by glibc. Heap manager might
+ allocate a ptr from brk or mapping created by mmap.
+ If an app calls mseal on a ptr returned from malloc(), this can affect
+ the heap manager's ability to manage the mappings; the outcome is
+ non-deterministic.
- aio/shm can call mmap()/munmap() on behalf of userspace, e.g. ksys_shmdt() in
- shm.c. The lifetime of those mapping are not tied to the lifetime of the
- process. If those memories are sealed from userspace, then munmap() will fail,
- causing leaks in VMA address space during the lifetime of the process.
+ Example::
-- Brk (heap)
+ ptr = malloc(size);
+ /* don't call mseal on ptr return from malloc. */
+ mseal(ptr, size);
+ /* free will success, allocator can't shrink heap lower than ptr */
+ free(ptr);
- Currently, userspace applications can seal parts of the heap by calling
- malloc() and mseal().
- let's assume following calls from user space:
+mseal doesn't block
+===================
+In a nutshell, mseal blocks certain mm syscall from modifying some of VMA's
+attributes, such as protection bits (RWX). Sealed mappings doesn't mean the
+memory is immutable.
- - ptr = malloc(size);
- - mprotect(ptr, size, RO);
- - mseal(ptr, size);
- - free(ptr);
-
- Technically, before mseal() is added, the user can change the protection of
- the heap by calling mprotect(RO). As long as the user changes the protection
- back to RW before free(), the memory range can be reused.
-
- Adding mseal() into the picture, however, the heap is then sealed partially,
- the user can still free it, but the memory remains to be RO. If the address
- is re-used by the heap manager for another malloc, the process might crash
- soon after. Therefore, it is important not to apply sealing to any memory
- that might get recycled.
-
- Furthermore, even if the application never calls the free() for the ptr,
- the heap manager may invoke the brk system call to shrink the size of the
- heap. In the kernel, the brk-shrink will call munmap(). Consequently,
- depending on the location of the ptr, the outcome of brk-shrink is
- nondeterministic.
-
-
-Additional notes:
-=================
As Jann Horn pointed out in [3], there are still a few ways to write
-to RO memory, which is, in a way, by design. Those cases are not covered
-by mseal(). If applications want to block such cases, sandbox tools (such as
-seccomp, LSM, etc) might be considered.
+to RO memory, which is, in a way, by design. And those could be blocked
+by different security measures.
Those cases are:
-- Write to read-only memory through /proc/self/mem interface.
-- Write to read-only memory through ptrace (such as PTRACE_POKETEXT).
-- userfaultfd.
+ - Write to read-only memory through /proc/self/mem interface (FOLL_FORCE).
+ - Write to read-only memory through ptrace (such as PTRACE_POKETEXT).
+ - userfaultfd.
The idea that inspired this patch comes from Stephen Röttger’s work in V8
CFI [4]. Chrome browser in ChromeOS will be the first user of this API.
-Reference:
-==========
-[1] https://github.com/apple-oss-distributions/xnu/blob/1031c584a5e37aff177559b9f69dbd3c8c3fd30a/osfmk/mach/vm_statistics.h#L274
-
-[2] https://man.openbsd.org/mimmutable.2
-
-[3] https://lore.kernel.org/lkml/CAG48ez3ShUYey+ZAFsU2i1RpQn0a5eOs2hzQ426FkcgnfUGLvA@mail.gmail.com
-
-[4] https://docs.google.com/document/d/1O2jwK4dxI3nRcOJuPYkonhTkNQfbmwdvxQMyXgeaRHo/edit#heading=h.bvaojj9fu6hc
+Reference
+=========
+- [1] https://github.com/apple-oss-distributions/xnu/blob/1031c584a5e37aff177559b9f69dbd3c8c3fd30a/osfmk/mach/vm_statistics.h#L274
+- [2] https://man.openbsd.org/mimmutable.2
+- [3] https://lore.kernel.org/lkml/CAG48ez3ShUYey+ZAFsU2i1RpQn0a5eOs2hzQ426FkcgnfUGLvA@mail.gmail.com
+- [4] https://docs.google.com/document/d/1O2jwK4dxI3nRcOJuPYkonhTkNQfbmwdvxQMyXgeaRHo/edit#heading=h.bvaojj9fu6hc
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index e324719..edc070c 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -8098,13 +8098,15 @@
KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is
disabled.
-KVM_X86_QUIRK_SLOT_ZAP_ALL By default, KVM invalidates all SPTEs in
- fast way for memslot deletion when VM type
- is KVM_X86_DEFAULT_VM.
- When this quirk is disabled or when VM type
- is other than KVM_X86_DEFAULT_VM, KVM zaps
- only leaf SPTEs that are within the range of
- the memslot being deleted.
+KVM_X86_QUIRK_SLOT_ZAP_ALL By default, for KVM_X86_DEFAULT_VM VMs, KVM
+ invalidates all SPTEs in all memslots and
+ address spaces when a memslot is deleted or
+ moved. When this quirk is disabled (or the
+ VM type isn't KVM_X86_DEFAULT_VM), KVM only
+ ensures the backing memory of the deleted
+ or moved memslot isn't reachable, i.e KVM
+ _may_ invalidate only SPTEs related to the
+ memslot.
=================================== ============================================
7.32 KVM_CAP_MAX_VCPU_ID
diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst
index 20a9a37..1bedd56 100644
--- a/Documentation/virt/kvm/locking.rst
+++ b/Documentation/virt/kvm/locking.rst
@@ -136,7 +136,7 @@
to gfn. For indirect sp, we disabled fast page fault for simplicity.
A solution for indirect sp could be to pin the gfn, for example via
-kvm_vcpu_gfn_to_pfn_atomic, before the cmpxchg. After the pinning:
+gfn_to_pfn_memslot_atomic, before the cmpxchg. After the pinning:
- We have held the refcount of pfn; that means the pfn can not be freed and
be reused for another gfn.
diff --git a/MAINTAINERS b/MAINTAINERS
index e9659a5..a274079 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9723,6 +9723,7 @@
F: include/linux/gpio.h
F: include/linux/gpio/
F: include/linux/of_gpio.h
+K: (devm_)?gpio_(request|free|direction|get|set)
GPIO UAPI
M: Bartosz Golaszewski <brgl@bgdev.pl>
@@ -14986,6 +14987,7 @@
MICROCHIP AUDIO ASOC DRIVERS
M: Claudiu Beznea <claudiu.beznea@tuxon.dev>
+M: Andrei Simion <andrei.simion@microchip.com>
L: linux-sound@vger.kernel.org
S: Supported
F: Documentation/devicetree/bindings/sound/atmel*
@@ -15094,6 +15096,7 @@
MICROCHIP MCP16502 PMIC DRIVER
M: Claudiu Beznea <claudiu.beznea@tuxon.dev>
+M: Andrei Simion <andrei.simion@microchip.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Supported
F: Documentation/devicetree/bindings/regulator/microchip,mcp16502.yaml
@@ -15224,6 +15227,7 @@
MICROCHIP SSC DRIVER
M: Claudiu Beznea <claudiu.beznea@tuxon.dev>
+M: Andrei Simion <andrei.simion@microchip.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Supported
F: Documentation/devicetree/bindings/misc/atmel-ssc.txt
@@ -16042,6 +16046,7 @@
M: Eric Dumazet <edumazet@google.com>
M: Jakub Kicinski <kuba@kernel.org>
M: Paolo Abeni <pabeni@redhat.com>
+R: Simon Horman <horms@kernel.org>
L: netdev@vger.kernel.org
S: Maintained
P: Documentation/process/maintainer-netdev.rst
@@ -16084,6 +16089,7 @@
F: lib/net_utils.c
F: lib/random32.c
F: net/
+F: samples/pktgen/
F: tools/net/
F: tools/testing/selftests/net/
X: Documentation/networking/mac80211-injection.rst
@@ -23143,7 +23149,7 @@
F: drivers/iio/adc/ti-lmp92064.c
TI PCM3060 ASoC CODEC DRIVER
-M: Kirill Marinushkin <kmarinushkin@birdec.com>
+M: Kirill Marinushkin <k.marinushkin@gmail.com>
L: linux-sound@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/sound/pcm3060.txt
diff --git a/Makefile b/Makefile
index a9a7d9ff..5e04e4a 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 12
SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
NAME = Baby Opossum Posse
# *DOCUMENTATION*
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index b36a3b6..67afac65 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -178,6 +178,7 @@ struct kvm_nvhe_init_params {
unsigned long hcr_el2;
unsigned long vttbr;
unsigned long vtcr;
+ unsigned long tmp;
};
/*
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 94cff50..bf64fed 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -51,6 +51,7 @@
#define KVM_REQ_RELOAD_PMU KVM_ARCH_REQ(5)
#define KVM_REQ_SUSPEND KVM_ARCH_REQ(6)
#define KVM_REQ_RESYNC_PMU_EL0 KVM_ARCH_REQ(7)
+#define KVM_REQ_NESTED_S2_UNMAP KVM_ARCH_REQ(8)
#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
KVM_DIRTY_LOG_INITIALLY_SET)
@@ -212,6 +213,12 @@ struct kvm_s2_mmu {
bool nested_stage2_enabled;
/*
+ * true when this MMU needs to be unmapped before being used for a new
+ * purpose.
+ */
+ bool pending_unmap;
+
+ /*
* 0: Nobody is currently using this, check vttbr for validity
* >0: Somebody is actively using this.
*/
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index cd4087f..66d93e3 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -166,7 +166,8 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr);
void __init free_hyp_pgds(void);
-void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size);
+void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
+ u64 size, bool may_block);
void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index e8bc6d6..233e655 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -78,6 +78,8 @@ extern void kvm_s2_mmu_iterate_by_vmid(struct kvm *kvm, u16 vmid,
extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu);
extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu);
+extern void check_nested_vcpu_requests(struct kvm_vcpu *vcpu);
+
struct kvm_s2_trans {
phys_addr_t output;
unsigned long block_size;
@@ -124,7 +126,7 @@ extern int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu,
struct kvm_s2_trans *trans);
extern int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2);
extern void kvm_nested_s2_wp(struct kvm *kvm);
-extern void kvm_nested_s2_unmap(struct kvm *kvm);
+extern void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block);
extern void kvm_nested_s2_flush(struct kvm *kvm);
unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val);
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 27de1dd..b21dd24 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -146,6 +146,7 @@ int main(void)
DEFINE(NVHE_INIT_HCR_EL2, offsetof(struct kvm_nvhe_init_params, hcr_el2));
DEFINE(NVHE_INIT_VTTBR, offsetof(struct kvm_nvhe_init_params, vttbr));
DEFINE(NVHE_INIT_VTCR, offsetof(struct kvm_nvhe_init_params, vtcr));
+ DEFINE(NVHE_INIT_TMP, offsetof(struct kvm_nvhe_init_params, tmp));
#endif
#ifdef CONFIG_CPU_PM
DEFINE(CPU_CTX_SP, offsetof(struct cpu_suspend_ctx, sp));
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index a0d01c4..48cafb6 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -997,6 +997,9 @@ static int kvm_vcpu_suspend(struct kvm_vcpu *vcpu)
static int check_vcpu_requests(struct kvm_vcpu *vcpu)
{
if (kvm_request_pending(vcpu)) {
+ if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu))
+ return -EIO;
+
if (kvm_check_request(KVM_REQ_SLEEP, vcpu))
kvm_vcpu_sleep(vcpu);
@@ -1031,6 +1034,8 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu)
if (kvm_dirty_ring_check_request(vcpu))
return 0;
+
+ check_nested_vcpu_requests(vcpu);
}
return 1;
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 401af18..fc18662 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -24,28 +24,25 @@
.align 11
SYM_CODE_START(__kvm_hyp_init)
- ventry __invalid // Synchronous EL2t
- ventry __invalid // IRQ EL2t
- ventry __invalid // FIQ EL2t
- ventry __invalid // Error EL2t
+ ventry . // Synchronous EL2t
+ ventry . // IRQ EL2t
+ ventry . // FIQ EL2t
+ ventry . // Error EL2t
- ventry __invalid // Synchronous EL2h
- ventry __invalid // IRQ EL2h
- ventry __invalid // FIQ EL2h
- ventry __invalid // Error EL2h
+ ventry . // Synchronous EL2h
+ ventry . // IRQ EL2h
+ ventry . // FIQ EL2h
+ ventry . // Error EL2h
ventry __do_hyp_init // Synchronous 64-bit EL1
- ventry __invalid // IRQ 64-bit EL1
- ventry __invalid // FIQ 64-bit EL1
- ventry __invalid // Error 64-bit EL1
+ ventry . // IRQ 64-bit EL1
+ ventry . // FIQ 64-bit EL1
+ ventry . // Error 64-bit EL1
- ventry __invalid // Synchronous 32-bit EL1
- ventry __invalid // IRQ 32-bit EL1
- ventry __invalid // FIQ 32-bit EL1
- ventry __invalid // Error 32-bit EL1
-
-__invalid:
- b .
+ ventry . // Synchronous 32-bit EL1
+ ventry . // IRQ 32-bit EL1
+ ventry . // FIQ 32-bit EL1
+ ventry . // Error 32-bit EL1
/*
* Only uses x0..x3 so as to not clobber callee-saved SMCCC registers.
@@ -76,6 +73,13 @@
eret
SYM_CODE_END(__kvm_hyp_init)
+SYM_CODE_START_LOCAL(__kvm_init_el2_state)
+ /* Initialize EL2 CPU state to sane values. */
+ init_el2_state // Clobbers x0..x2
+ finalise_el2_state
+ ret
+SYM_CODE_END(__kvm_init_el2_state)
+
/*
* Initialize the hypervisor in EL2.
*
@@ -102,9 +106,12 @@
// TPIDR_EL2 is used to preserve x0 across the macro maze...
isb
msr tpidr_el2, x0
- init_el2_state
- finalise_el2_state
+ str lr, [x0, #NVHE_INIT_TMP]
+
+ bl __kvm_init_el2_state
+
mrs x0, tpidr_el2
+ ldr lr, [x0, #NVHE_INIT_TMP]
1:
ldr x1, [x0, #NVHE_INIT_TPIDR_EL2]
@@ -199,9 +206,8 @@
2: msr SPsel, #1 // We want to use SP_EL{1,2}
- /* Initialize EL2 CPU state to sane values. */
- init_el2_state // Clobbers x0..x2
- finalise_el2_state
+ bl __kvm_init_el2_state
+
__init_el2_nvhe_prepare_eret
/* Enable MMU, set vectors and stack. */
diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c
index 5763d97..ee6573b 100644
--- a/arch/arm64/kvm/hypercalls.c
+++ b/arch/arm64/kvm/hypercalls.c
@@ -317,7 +317,7 @@ int kvm_smccc_call_handler(struct kvm_vcpu *vcpu)
* to the guest, and hide SSBS so that the
* guest stays protected.
*/
- if (cpus_have_final_cap(ARM64_SSBS))
+ if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SSBS, IMP))
break;
fallthrough;
case SPECTRE_UNAFFECTED:
@@ -428,7 +428,7 @@ int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
* Convert the workaround level into an easy-to-compare number, where higher
* values mean better protection.
*/
-static int get_kernel_wa_level(u64 regid)
+static int get_kernel_wa_level(struct kvm_vcpu *vcpu, u64 regid)
{
switch (regid) {
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
@@ -449,7 +449,7 @@ static int get_kernel_wa_level(u64 regid)
* don't have any FW mitigation if SSBS is there at
* all times.
*/
- if (cpus_have_final_cap(ARM64_SSBS))
+ if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SSBS, IMP))
return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
fallthrough;
case SPECTRE_UNAFFECTED:
@@ -486,7 +486,7 @@ int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
- val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
+ val = get_kernel_wa_level(vcpu, reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
break;
case KVM_REG_ARM_STD_BMAP:
val = READ_ONCE(smccc_feat->std_bmap);
@@ -588,7 +588,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
if (val & ~KVM_REG_FEATURE_LEVEL_MASK)
return -EINVAL;
- if (get_kernel_wa_level(reg->id) < val)
+ if (get_kernel_wa_level(vcpu, reg->id) < val)
return -EINVAL;
return 0;
@@ -624,7 +624,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
* We can deal with NOT_AVAIL on NOT_REQUIRED, but not the
* other way around.
*/
- if (get_kernel_wa_level(reg->id) < wa_level)
+ if (get_kernel_wa_level(vcpu, reg->id) < wa_level)
return -EINVAL;
return 0;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index a509b63..0f7658a 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -328,9 +328,10 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
may_block));
}
-void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
+void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
+ u64 size, bool may_block)
{
- __unmap_stage2_range(mmu, start, size, true);
+ __unmap_stage2_range(mmu, start, size, may_block);
}
void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
@@ -1015,7 +1016,7 @@ static void stage2_unmap_memslot(struct kvm *kvm,
if (!(vma->vm_flags & VM_PFNMAP)) {
gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
- kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
+ kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start, true);
}
hva = vm_end;
} while (hva < reg_end);
@@ -1042,7 +1043,7 @@ void stage2_unmap_vm(struct kvm *kvm)
kvm_for_each_memslot(memslot, bkt, slots)
stage2_unmap_memslot(kvm, memslot);
- kvm_nested_s2_unmap(kvm);
+ kvm_nested_s2_unmap(kvm, true);
write_unlock(&kvm->mmu_lock);
mmap_read_unlock(current->mm);
@@ -1912,7 +1913,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
(range->end - range->start) << PAGE_SHIFT,
range->may_block);
- kvm_nested_s2_unmap(kvm);
+ kvm_nested_s2_unmap(kvm, range->may_block);
return false;
}
@@ -2179,8 +2180,8 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
phys_addr_t size = slot->npages << PAGE_SHIFT;
write_lock(&kvm->mmu_lock);
- kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size);
- kvm_nested_s2_unmap(kvm);
+ kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size, true);
+ kvm_nested_s2_unmap(kvm, true);
write_unlock(&kvm->mmu_lock);
}
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index f9e30dd..c4b17d9 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -632,9 +632,9 @@ static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
/* Set the scene for the next search */
kvm->arch.nested_mmus_next = (i + 1) % kvm->arch.nested_mmus_size;
- /* Clear the old state */
+ /* Make sure we don't forget to do the laundry */
if (kvm_s2_mmu_valid(s2_mmu))
- kvm_stage2_unmap_range(s2_mmu, 0, kvm_phys_size(s2_mmu));
+ s2_mmu->pending_unmap = true;
/*
* The virtual VMID (modulo CnP) will be used as a key when matching
@@ -650,6 +650,16 @@ static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
out:
atomic_inc(&s2_mmu->refcnt);
+
+ /*
+ * Set the vCPU request to perform an unmap, even if the pending unmap
+ * originates from another vCPU. This guarantees that the MMU has been
+ * completely unmapped before any vCPU actually uses it, and allows
+ * multiple vCPUs to lend a hand with completing the unmap.
+ */
+ if (s2_mmu->pending_unmap)
+ kvm_make_request(KVM_REQ_NESTED_S2_UNMAP, vcpu);
+
return s2_mmu;
}
@@ -663,6 +673,13 @@ void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu)
void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu)
{
+ /*
+ * The vCPU kept its reference on the MMU after the last put, keep
+ * rolling with it.
+ */
+ if (vcpu->arch.hw_mmu)
+ return;
+
if (is_hyp_ctxt(vcpu)) {
vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
} else {
@@ -674,10 +691,18 @@ void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu)
void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu)
{
- if (kvm_is_nested_s2_mmu(vcpu->kvm, vcpu->arch.hw_mmu)) {
+ /*
+ * Keep a reference on the associated stage-2 MMU if the vCPU is
+ * scheduling out and not in WFI emulation, suggesting it is likely to
+ * reuse the MMU sometime soon.
+ */
+ if (vcpu->scheduled_out && !vcpu_get_flag(vcpu, IN_WFI))
+ return;
+
+ if (kvm_is_nested_s2_mmu(vcpu->kvm, vcpu->arch.hw_mmu))
atomic_dec(&vcpu->arch.hw_mmu->refcnt);
- vcpu->arch.hw_mmu = NULL;
- }
+
+ vcpu->arch.hw_mmu = NULL;
}
/*
@@ -730,7 +755,7 @@ void kvm_nested_s2_wp(struct kvm *kvm)
}
}
-void kvm_nested_s2_unmap(struct kvm *kvm)
+void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block)
{
int i;
@@ -740,7 +765,7 @@ void kvm_nested_s2_unmap(struct kvm *kvm)
struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
if (kvm_s2_mmu_valid(mmu))
- kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu));
+ kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), may_block);
}
}
@@ -1184,3 +1209,17 @@ int kvm_init_nv_sysregs(struct kvm *kvm)
return 0;
}
+
+void check_nested_vcpu_requests(struct kvm_vcpu *vcpu)
+{
+ if (kvm_check_request(KVM_REQ_NESTED_S2_UNMAP, vcpu)) {
+ struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu;
+
+ write_lock(&vcpu->kvm->mmu_lock);
+ if (mmu->pending_unmap) {
+ kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), true);
+ mmu->pending_unmap = false;
+ }
+ write_unlock(&vcpu->kvm->mmu_lock);
+ }
+}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index dad88e3..ff8c4e1 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1527,6 +1527,14 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE);
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_SME);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_RNDR_trap);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_NMI);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_GCS);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_THE);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTEX);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_DF2);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_PFAR);
break;
case SYS_ID_AA64PFR2_EL1:
/* We only expose FPMR */
@@ -1550,7 +1558,8 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
val &= ~ID_AA64MMFR2_EL1_CCIDX_MASK;
break;
case SYS_ID_AA64MMFR3_EL1:
- val &= ID_AA64MMFR3_EL1_TCRX | ID_AA64MMFR3_EL1_S1POE;
+ val &= ID_AA64MMFR3_EL1_TCRX | ID_AA64MMFR3_EL1_S1POE |
+ ID_AA64MMFR3_EL1_S1PIE;
break;
case SYS_ID_MMFR4_EL1:
val &= ~ARM64_FEATURE_MASK(ID_MMFR4_EL1_CCIDX);
@@ -1985,7 +1994,7 @@ static u64 reset_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
* one cache line.
*/
if (kvm_has_mte(vcpu->kvm))
- clidr |= 2 << CLIDR_TTYPE_SHIFT(loc);
+ clidr |= 2ULL << CLIDR_TTYPE_SHIFT(loc);
__vcpu_sys_reg(vcpu, r->reg) = clidr;
@@ -2376,7 +2385,19 @@ static const struct sys_reg_desc sys_reg_descs[] = {
ID_AA64PFR0_EL1_RAS |
ID_AA64PFR0_EL1_AdvSIMD |
ID_AA64PFR0_EL1_FP), },
- ID_SANITISED(ID_AA64PFR1_EL1),
+ ID_WRITABLE(ID_AA64PFR1_EL1, ~(ID_AA64PFR1_EL1_PFAR |
+ ID_AA64PFR1_EL1_DF2 |
+ ID_AA64PFR1_EL1_MTEX |
+ ID_AA64PFR1_EL1_THE |
+ ID_AA64PFR1_EL1_GCS |
+ ID_AA64PFR1_EL1_MTE_frac |
+ ID_AA64PFR1_EL1_NMI |
+ ID_AA64PFR1_EL1_RNDR_trap |
+ ID_AA64PFR1_EL1_SME |
+ ID_AA64PFR1_EL1_RES0 |
+ ID_AA64PFR1_EL1_MPAM_frac |
+ ID_AA64PFR1_EL1_RAS_frac |
+ ID_AA64PFR1_EL1_MTE)),
ID_WRITABLE(ID_AA64PFR2_EL1, ID_AA64PFR2_EL1_FPMR),
ID_UNALLOCATED(4,3),
ID_WRITABLE(ID_AA64ZFR0_EL1, ~ID_AA64ZFR0_EL1_RES0),
@@ -2390,7 +2411,21 @@ static const struct sys_reg_desc sys_reg_descs[] = {
.get_user = get_id_reg,
.set_user = set_id_aa64dfr0_el1,
.reset = read_sanitised_id_aa64dfr0_el1,
- .val = ID_AA64DFR0_EL1_PMUVer_MASK |
+ /*
+ * Prior to FEAT_Debugv8.9, the architecture defines context-aware
+ * breakpoints (CTX_CMPs) as the highest numbered breakpoints (BRPs).
+ * KVM does not trap + emulate the breakpoint registers, and as such
+ * cannot support a layout that misaligns with the underlying hardware.
+ * While it may be possible to describe a subset that aligns with
+ * hardware, just prevent changes to BRPs and CTX_CMPs altogether for
+ * simplicity.
+ *
+ * See DDI0487K.a, section D2.8.3 Breakpoint types and linking
+ * of breakpoints for more details.
+ */
+ .val = ID_AA64DFR0_EL1_DoubleLock_MASK |
+ ID_AA64DFR0_EL1_WRPs_MASK |
+ ID_AA64DFR0_EL1_PMUVer_MASK |
ID_AA64DFR0_EL1_DebugVer_MASK, },
ID_SANITISED(ID_AA64DFR1_EL1),
ID_UNALLOCATED(5,2),
@@ -2433,6 +2468,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
ID_AA64MMFR2_EL1_NV |
ID_AA64MMFR2_EL1_CCIDX)),
ID_WRITABLE(ID_AA64MMFR3_EL1, (ID_AA64MMFR3_EL1_TCRX |
+ ID_AA64MMFR3_EL1_S1PIE |
ID_AA64MMFR3_EL1_S1POE)),
ID_SANITISED(ID_AA64MMFR4_EL1),
ID_UNALLOCATED(7,5),
@@ -2903,7 +2939,7 @@ static bool handle_alle1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
* Drop all shadow S2s, resulting in S1/S2 TLBIs for each of the
* corresponding VMIDs.
*/
- kvm_nested_s2_unmap(vcpu->kvm);
+ kvm_nested_s2_unmap(vcpu->kvm, true);
write_unlock(&vcpu->kvm->mmu_lock);
@@ -2955,7 +2991,30 @@ union tlbi_info {
static void s2_mmu_unmap_range(struct kvm_s2_mmu *mmu,
const union tlbi_info *info)
{
- kvm_stage2_unmap_range(mmu, info->range.start, info->range.size);
+ /*
+ * The unmap operation is allowed to drop the MMU lock and block, which
+ * means that @mmu could be used for a different context than the one
+ * currently being invalidated.
+ *
+ * This behavior is still safe, as:
+ *
+ * 1) The vCPU(s) that recycled the MMU are responsible for invalidating
+ * the entire MMU before reusing it, which still honors the intent
+ * of a TLBI.
+ *
+ * 2) Until the guest TLBI instruction is 'retired' (i.e. increment PC
+ * and ERET to the guest), other vCPUs are allowed to use stale
+ * translations.
+ *
+ * 3) Accidentally unmapping an unrelated MMU context is nonfatal, and
+ * at worst may cause more aborts for shadow stage-2 fills.
+ *
+ * Dropping the MMU lock also implies that shadow stage-2 fills could
+ * happen behind the back of the TLBI. This is still safe, though, as
+ * the L1 needs to put its stage-2 in a consistent state before doing
+ * the TLBI.
+ */
+ kvm_stage2_unmap_range(mmu, info->range.start, info->range.size, true);
}
static bool handle_vmalls12e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
@@ -3050,7 +3109,11 @@ static void s2_mmu_unmap_ipa(struct kvm_s2_mmu *mmu,
max_size = compute_tlb_inval_range(mmu, info->ipa.addr);
base_addr &= ~(max_size - 1);
- kvm_stage2_unmap_range(mmu, base_addr, max_size);
+ /*
+ * See comment in s2_mmu_unmap_range() for why this is allowed to
+ * reschedule.
+ */
+ kvm_stage2_unmap_range(mmu, base_addr, max_size, true);
}
static bool handle_ipas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index e7c53e8..48c9525 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -417,8 +417,28 @@ static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
kfree(vgic_cpu->private_irqs);
vgic_cpu->private_irqs = NULL;
- if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
+ if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
+ /*
+ * If this vCPU is being destroyed because of a failed creation
+ * then unregister the redistributor to avoid leaving behind a
+ * dangling pointer to the vCPU struct.
+ *
+ * vCPUs that have been successfully created (i.e. added to
+ * kvm->vcpu_array) get unregistered in kvm_vgic_destroy(), as
+ * this function gets called while holding kvm->arch.config_lock
+ * in the VM teardown path and would otherwise introduce a lock
+ * inversion w.r.t. kvm->srcu.
+ *
+ * vCPUs that failed creation are torn down outside of the
+ * kvm->arch.config_lock and do not get unregistered in
+ * kvm_vgic_destroy(), meaning it is both safe and necessary to
+ * do so here.
+ */
+ if (kvm_get_vcpu_by_id(vcpu->kvm, vcpu->vcpu_id) != vcpu)
+ vgic_unregister_redist_iodev(vcpu);
+
vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
+ }
}
void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
@@ -524,22 +544,31 @@ int kvm_vgic_map_resources(struct kvm *kvm)
if (ret)
goto out;
- dist->ready = true;
dist_base = dist->vgic_dist_base;
mutex_unlock(&kvm->arch.config_lock);
ret = vgic_register_dist_iodev(kvm, dist_base, type);
- if (ret)
+ if (ret) {
kvm_err("Unable to register VGIC dist MMIO regions\n");
+ goto out_slots;
+ }
+ /*
+ * kvm_io_bus_register_dev() guarantees all readers see the new MMIO
+ * registration before returning through synchronize_srcu(), which also
+ * implies a full memory barrier. As such, marking the distributor as
+ * 'ready' here is guaranteed to be ordered after all vCPUs having seen
+ * a completely configured distributor.
+ */
+ dist->ready = true;
goto out_slots;
out:
mutex_unlock(&kvm->arch.config_lock);
out_slots:
- mutex_unlock(&kvm->slots_lock);
-
if (ret)
- kvm_vgic_destroy(kvm);
+ kvm_vm_dead(kvm);
+
+ mutex_unlock(&kvm->slots_lock);
return ret;
}
diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c
index 1d26bb5..5f4f57a 100644
--- a/arch/arm64/kvm/vgic/vgic-kvm-device.c
+++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c
@@ -236,7 +236,12 @@ static int vgic_set_common_attr(struct kvm_device *dev,
mutex_lock(&dev->kvm->arch.config_lock);
- if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_spis)
+ /*
+ * Either userspace has already configured NR_IRQS or
+ * the vgic has already been initialized and vgic_init()
+ * supplied a default amount of SPIs.
+ */
+ if (dev->kvm->arch.vgic.nr_spis)
ret = -EBUSY;
else
dev->kvm->arch.vgic.nr_spis =
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 8bbd0b2..5db82bf 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -2220,7 +2220,11 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
emit(A64_STR64I(A64_R(20), A64_SP, regs_off + 8), ctx);
if (flags & BPF_TRAMP_F_CALL_ORIG) {
- emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
+ /* for the first pass, assume the worst case */
+ if (!ctx->image)
+ ctx->idx += 4;
+ else
+ emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
emit_call((const u64)__bpf_tramp_enter, ctx);
}
@@ -2264,7 +2268,11 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
if (flags & BPF_TRAMP_F_CALL_ORIG) {
im->ip_epilogue = ctx->ro_image + ctx->idx;
- emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
+ /* for the first pass, assume the worst case */
+ if (!ctx->image)
+ ctx->idx += 4;
+ else
+ emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
emit_call((const u64)__bpf_tramp_exit, ctx);
}
diff --git a/arch/loongarch/include/asm/bootinfo.h b/arch/loongarch/include/asm/bootinfo.h
index 6d5846d..7657e01 100644
--- a/arch/loongarch/include/asm/bootinfo.h
+++ b/arch/loongarch/include/asm/bootinfo.h
@@ -26,6 +26,10 @@ struct loongson_board_info {
#define NR_WORDS DIV_ROUND_UP(NR_CPUS, BITS_PER_LONG)
+/*
+ * The "core" of cores_per_node and cores_per_package stands for a
+ * logical core, which means in a SMT system it stands for a thread.
+ */
struct loongson_system_configuration {
int nr_cpus;
int nr_nodes;
diff --git a/arch/loongarch/include/asm/kasan.h b/arch/loongarch/include/asm/kasan.h
index cd6084f..c6bce5f 100644
--- a/arch/loongarch/include/asm/kasan.h
+++ b/arch/loongarch/include/asm/kasan.h
@@ -16,7 +16,7 @@
#define XRANGE_SHIFT (48)
/* Valid address length */
-#define XRANGE_SHADOW_SHIFT (PGDIR_SHIFT + PAGE_SHIFT - 3)
+#define XRANGE_SHADOW_SHIFT min(cpu_vabits, VA_BITS)
/* Used for taking out the valid address */
#define XRANGE_SHADOW_MASK GENMASK_ULL(XRANGE_SHADOW_SHIFT - 1, 0)
/* One segment whole address space size */
diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h
index 2654241..64ad277 100644
--- a/arch/loongarch/include/asm/loongarch.h
+++ b/arch/loongarch/include/asm/loongarch.h
@@ -250,7 +250,7 @@
#define CSR_ESTAT_IS_WIDTH 15
#define CSR_ESTAT_IS (_ULCAST_(0x7fff) << CSR_ESTAT_IS_SHIFT)
-#define LOONGARCH_CSR_ERA 0x6 /* ERA */
+#define LOONGARCH_CSR_ERA 0x6 /* Exception return address */
#define LOONGARCH_CSR_BADV 0x7 /* Bad virtual address */
diff --git a/arch/loongarch/include/asm/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h
index 4e2d6b7..a7b9c9e 100644
--- a/arch/loongarch/include/asm/pgalloc.h
+++ b/arch/loongarch/include/asm/pgalloc.h
@@ -10,6 +10,7 @@
#define __HAVE_ARCH_PMD_ALLOC_ONE
#define __HAVE_ARCH_PUD_ALLOC_ONE
+#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
#include <asm-generic/pgalloc.h>
static inline void pmd_populate_kernel(struct mm_struct *mm,
@@ -44,6 +45,16 @@ extern void pagetable_init(void);
extern pgd_t *pgd_alloc(struct mm_struct *mm);
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
+{
+ pte_t *pte = __pte_alloc_one_kernel(mm);
+
+ if (pte)
+ kernel_pte_init(pte);
+
+ return pte;
+}
+
#define __pte_free_tlb(tlb, pte, address) \
do { \
pagetable_pte_dtor(page_ptdesc(pte)); \
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index 9965f52..20714b7 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -269,6 +269,7 @@ extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pm
extern void pgd_init(void *addr);
extern void pud_init(void *addr);
extern void pmd_init(void *addr);
+extern void kernel_pte_init(void *addr);
/*
* Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that
@@ -325,39 +326,17 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
{
WRITE_ONCE(*ptep, pteval);
- if (pte_val(pteval) & _PAGE_GLOBAL) {
- pte_t *buddy = ptep_buddy(ptep);
- /*
- * Make sure the buddy is global too (if it's !none,
- * it better already be global)
- */
- if (pte_none(ptep_get(buddy))) {
#ifdef CONFIG_SMP
- /*
- * For SMP, multiple CPUs can race, so we need
- * to do this atomically.
- */
- __asm__ __volatile__(
- __AMOR "$zero, %[global], %[buddy] \n"
- : [buddy] "+ZB" (buddy->pte)
- : [global] "r" (_PAGE_GLOBAL)
- : "memory");
-
- DBAR(0b11000); /* o_wrw = 0b11000 */
-#else /* !CONFIG_SMP */
- WRITE_ONCE(*buddy, __pte(pte_val(ptep_get(buddy)) | _PAGE_GLOBAL));
-#endif /* CONFIG_SMP */
- }
- }
+ if (pte_val(pteval) & _PAGE_GLOBAL)
+ DBAR(0b11000); /* o_wrw = 0b11000 */
+#endif
}
static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
{
- /* Preserve global status for the pair */
- if (pte_val(ptep_get(ptep_buddy(ptep))) & _PAGE_GLOBAL)
- set_pte(ptep, __pte(_PAGE_GLOBAL));
- else
- set_pte(ptep, __pte(0));
+ pte_t pte = ptep_get(ptep);
+ pte_val(pte) &= _PAGE_GLOBAL;
+ set_pte(ptep, pte);
}
#define PGD_T_LOG2 (__builtin_ffs(sizeof(pgd_t)) - 1)
diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c
index f2ff8b5..6e58f65 100644
--- a/arch/loongarch/kernel/process.c
+++ b/arch/loongarch/kernel/process.c
@@ -293,13 +293,15 @@ unsigned long stack_top(void)
{
unsigned long top = TASK_SIZE & PAGE_MASK;
- /* Space for the VDSO & data page */
- top -= PAGE_ALIGN(current->thread.vdso->size);
- top -= VVAR_SIZE;
+ if (current->thread.vdso) {
+ /* Space for the VDSO & data page */
+ top -= PAGE_ALIGN(current->thread.vdso->size);
+ top -= VVAR_SIZE;
- /* Space to randomize the VDSO base */
- if (current->flags & PF_RANDOMIZE)
- top -= VDSO_RANDOMIZE_SIZE;
+ /* Space to randomize the VDSO base */
+ if (current->flags & PF_RANDOMIZE)
+ top -= VDSO_RANDOMIZE_SIZE;
+ }
return top;
}
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index 00e3072..cbd3c09 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -55,6 +55,7 @@
#define SMBIOS_FREQHIGH_OFFSET 0x17
#define SMBIOS_FREQLOW_MASK 0xFF
#define SMBIOS_CORE_PACKAGE_OFFSET 0x23
+#define SMBIOS_THREAD_PACKAGE_OFFSET 0x25
#define LOONGSON_EFI_ENABLE (1 << 3)
unsigned long fw_arg0, fw_arg1, fw_arg2;
@@ -125,7 +126,7 @@ static void __init parse_cpu_table(const struct dmi_header *dm)
cpu_clock_freq = freq_temp * 1000000;
loongson_sysconf.cpuname = (void *)dmi_string_parse(dm, dmi_data[16]);
- loongson_sysconf.cores_per_package = *(dmi_data + SMBIOS_CORE_PACKAGE_OFFSET);
+ loongson_sysconf.cores_per_package = *(dmi_data + SMBIOS_THREAD_PACKAGE_OFFSET);
pr_info("CpuClock = %llu\n", cpu_clock_freq);
}
diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c
index f9f4eb0..c57b413 100644
--- a/arch/loongarch/kernel/traps.c
+++ b/arch/loongarch/kernel/traps.c
@@ -555,6 +555,9 @@ asmlinkage void noinstr do_ale(struct pt_regs *regs)
#else
unsigned int *pc;
+ if (regs->csr_prmd & CSR_PRMD_PIE)
+ local_irq_enable();
+
perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, regs->csr_badvaddr);
/*
@@ -579,6 +582,8 @@ 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)
+ local_irq_disable();
#endif
irqentry_exit(regs, state);
}
diff --git a/arch/loongarch/kernel/vdso.c b/arch/loongarch/kernel/vdso.c
index f6fcc52..2c0d852 100644
--- a/arch/loongarch/kernel/vdso.c
+++ b/arch/loongarch/kernel/vdso.c
@@ -34,7 +34,6 @@ static union {
struct loongarch_vdso_data vdata;
} loongarch_vdso_data __page_aligned_data;
-static struct page *vdso_pages[] = { NULL };
struct vdso_data *vdso_data = generic_vdso_data.data;
struct vdso_pcpu_data *vdso_pdata = loongarch_vdso_data.vdata.pdata;
struct vdso_rng_data *vdso_rng_data = &loongarch_vdso_data.vdata.rng_data;
@@ -85,10 +84,8 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
struct loongarch_vdso_info vdso_info = {
.vdso = vdso_start,
- .size = PAGE_SIZE,
.code_mapping = {
.name = "[vdso]",
- .pages = vdso_pages,
.mremap = vdso_mremap,
},
.data_mapping = {
@@ -103,11 +100,14 @@ static int __init init_vdso(void)
unsigned long i, cpu, pfn;
BUG_ON(!PAGE_ALIGNED(vdso_info.vdso));
- BUG_ON(!PAGE_ALIGNED(vdso_info.size));
for_each_possible_cpu(cpu)
vdso_pdata[cpu].node = cpu_to_node(cpu);
+ vdso_info.size = PAGE_ALIGN(vdso_end - vdso_start);
+ vdso_info.code_mapping.pages =
+ kcalloc(vdso_info.size / PAGE_SIZE, sizeof(struct page *), GFP_KERNEL);
+
pfn = __phys_to_pfn(__pa_symbol(vdso_info.vdso));
for (i = 0; i < vdso_info.size / PAGE_SIZE; i++)
vdso_info.code_mapping.pages[i] = pfn_to_page(pfn + i);
diff --git a/arch/loongarch/kvm/timer.c b/arch/loongarch/kvm/timer.c
index 74a4b5c..32dc213 100644
--- a/arch/loongarch/kvm/timer.c
+++ b/arch/loongarch/kvm/timer.c
@@ -161,10 +161,11 @@ static void _kvm_save_timer(struct kvm_vcpu *vcpu)
if (kvm_vcpu_is_blocking(vcpu)) {
/*
- * HRTIMER_MODE_PINNED is suggested since vcpu may run in
- * the same physical cpu in next time
+ * HRTIMER_MODE_PINNED_HARD is suggested since vcpu may run in
+ * the same physical cpu in next time, and the timer should run
+ * in hardirq context even in the PREEMPT_RT case.
*/
- hrtimer_start(&vcpu->arch.swtimer, expire, HRTIMER_MODE_ABS_PINNED);
+ hrtimer_start(&vcpu->arch.swtimer, expire, HRTIMER_MODE_ABS_PINNED_HARD);
}
}
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 0697b10..174734a 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -1457,7 +1457,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
vcpu->arch.vpid = 0;
vcpu->arch.flush_gpa = INVALID_GPA;
- hrtimer_init(&vcpu->arch.swtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+ hrtimer_init(&vcpu->arch.swtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
vcpu->arch.swtimer.function = kvm_swtimer_wakeup;
vcpu->arch.handle_exit = kvm_handle_exit;
diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c
index 8a87a48..188b52bb 100644
--- a/arch/loongarch/mm/init.c
+++ b/arch/loongarch/mm/init.c
@@ -201,7 +201,9 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
if (!pte)
panic("%s: Failed to allocate memory\n", __func__);
+
pmd_populate_kernel(&init_mm, pmd, pte);
+ kernel_pte_init(pte);
}
return pte_offset_kernel(pmd, addr);
diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c
index eb6a29b..3fa69b2 100644
--- a/arch/loongarch/mm/pgtable.c
+++ b/arch/loongarch/mm/pgtable.c
@@ -116,6 +116,26 @@ void pud_init(void *addr)
EXPORT_SYMBOL_GPL(pud_init);
#endif
+void kernel_pte_init(void *addr)
+{
+ unsigned long *p, *end;
+
+ p = (unsigned long *)addr;
+ end = p + PTRS_PER_PTE;
+
+ do {
+ p[0] = _PAGE_GLOBAL;
+ p[1] = _PAGE_GLOBAL;
+ p[2] = _PAGE_GLOBAL;
+ p[3] = _PAGE_GLOBAL;
+ p[4] = _PAGE_GLOBAL;
+ p += 8;
+ p[-3] = _PAGE_GLOBAL;
+ p[-2] = _PAGE_GLOBAL;
+ p[-1] = _PAGE_GLOBAL;
+ } while (p != end);
+}
+
pmd_t mk_pmd(struct page *page, pgprot_t prot)
{
pmd_t pmd;
diff --git a/arch/mips/kernel/cmpxchg.c b/arch/mips/kernel/cmpxchg.c
index e974a49..c371def 100644
--- a/arch/mips/kernel/cmpxchg.c
+++ b/arch/mips/kernel/cmpxchg.c
@@ -102,3 +102,4 @@ unsigned long __cmpxchg_small(volatile void *ptr, unsigned long old,
return old;
}
}
+EXPORT_SYMBOL(__cmpxchg_small);
diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c
index 0a1e859..a8085cd 100644
--- a/arch/riscv/kvm/aia_imsic.c
+++ b/arch/riscv/kvm/aia_imsic.c
@@ -55,7 +55,7 @@ struct imsic {
/* IMSIC SW-file */
struct imsic_mrif *swfile;
phys_addr_t swfile_pa;
- spinlock_t swfile_extirq_lock;
+ raw_spinlock_t swfile_extirq_lock;
};
#define imsic_vs_csr_read(__c) \
@@ -622,7 +622,7 @@ static void imsic_swfile_extirq_update(struct kvm_vcpu *vcpu)
* interruptions between reading topei and updating pending status.
*/
- spin_lock_irqsave(&imsic->swfile_extirq_lock, flags);
+ raw_spin_lock_irqsave(&imsic->swfile_extirq_lock, flags);
if (imsic_mrif_atomic_read(mrif, &mrif->eidelivery) &&
imsic_mrif_topei(mrif, imsic->nr_eix, imsic->nr_msis))
@@ -630,7 +630,7 @@ static void imsic_swfile_extirq_update(struct kvm_vcpu *vcpu)
else
kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_EXT);
- spin_unlock_irqrestore(&imsic->swfile_extirq_lock, flags);
+ raw_spin_unlock_irqrestore(&imsic->swfile_extirq_lock, flags);
}
static void imsic_swfile_read(struct kvm_vcpu *vcpu, bool clear,
@@ -1051,7 +1051,7 @@ int kvm_riscv_vcpu_aia_imsic_init(struct kvm_vcpu *vcpu)
}
imsic->swfile = page_to_virt(swfile_page);
imsic->swfile_pa = page_to_phys(swfile_page);
- spin_lock_init(&imsic->swfile_extirq_lock);
+ raw_spin_lock_init(&imsic->swfile_extirq_lock);
/* Setup IO device */
kvm_iodevice_init(&imsic->iodev, &imsic_iodoev_ops);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2852fcd..16354df 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2257,6 +2257,7 @@
config ADDRESS_MASKING
bool "Linear Address Masking support"
depends on X86_64
+ depends on COMPILE_TEST || !CPU_MITIGATIONS # wait for LASS
help
Linear Address Masking (LAM) modifies the checking that is applied
to 64-bit linear addresses, allowing software to use of the
diff --git a/arch/x86/include/asm/runtime-const.h b/arch/x86/include/asm/runtime-const.h
index 24e3a53..6652ebd 100644
--- a/arch/x86/include/asm/runtime-const.h
+++ b/arch/x86/include/asm/runtime-const.h
@@ -6,7 +6,7 @@
typeof(sym) __ret; \
asm_inline("mov %1,%0\n1:\n" \
".pushsection runtime_ptr_" #sym ",\"a\"\n\t" \
- ".long 1b - %c2 - .\n\t" \
+ ".long 1b - %c2 - .\n" \
".popsection" \
:"=r" (__ret) \
:"i" ((unsigned long)0x0123456789abcdefull), \
@@ -20,7 +20,7 @@
typeof(0u+(val)) __ret = (val); \
asm_inline("shrl $12,%k0\n1:\n" \
".pushsection runtime_shift_" #sym ",\"a\"\n\t" \
- ".long 1b - 1 - .\n\t" \
+ ".long 1b - 1 - .\n" \
".popsection" \
:"+r" (__ret)); \
__ret; })
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index afce8ee..b0a8872 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -12,6 +12,13 @@
#include <asm/cpufeatures.h>
#include <asm/page.h>
#include <asm/percpu.h>
+#include <asm/runtime-const.h>
+
+/*
+ * Virtual variable: there's no actual backing store for this,
+ * it can purely be used as 'runtime_const_ptr(USER_PTR_MAX)'
+ */
+extern unsigned long USER_PTR_MAX;
#ifdef CONFIG_ADDRESS_MASKING
/*
@@ -46,19 +53,24 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm,
#endif
-/*
- * The virtual address space space is logically divided into a kernel
- * half and a user half. When cast to a signed type, user pointers
- * are positive and kernel pointers are negative.
- */
-#define valid_user_address(x) ((__force long)(x) >= 0)
+#define valid_user_address(x) \
+ ((__force unsigned long)(x) <= runtime_const_ptr(USER_PTR_MAX))
/*
* Masking the user address is an alternative to a conditional
* user_access_begin that can avoid the fencing. This only works
* for dense accesses starting at the address.
*/
-#define mask_user_address(x) ((typeof(x))((long)(x)|((long)(x)>>63)))
+static inline void __user *mask_user_address(const void __user *ptr)
+{
+ unsigned long mask;
+ asm("cmp %1,%0\n\t"
+ "sbb %0,%0"
+ :"=r" (mask)
+ :"r" (ptr),
+ "0" (runtime_const_ptr(USER_PTR_MAX)));
+ return (__force void __user *)(mask | (__force unsigned long)ptr);
+}
#define masked_user_access_begin(x) ({ \
__auto_type __masked_ptr = (x); \
__masked_ptr = mask_user_address(__masked_ptr); \
@@ -69,23 +81,16 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm,
* arbitrary values in those bits rather then masking them off.
*
* Enforce two rules:
- * 1. 'ptr' must be in the user half of the address space
+ * 1. 'ptr' must be in the user part of the address space
* 2. 'ptr+size' must not overflow into kernel addresses
*
- * Note that addresses around the sign change are not valid addresses,
- * and will GP-fault even with LAM enabled if the sign bit is set (see
- * "CR3.LAM_SUP" that can narrow the canonicality check if we ever
- * enable it, but not remove it entirely).
- *
- * So the "overflow into kernel addresses" does not imply some sudden
- * exact boundary at the sign bit, and we can allow a lot of slop on the
- * size check.
+ * Note that we always have at least one guard page between the
+ * max user address and the non-canonical gap, allowing us to
+ * ignore small sizes entirely.
*
* In fact, we could probably remove the size check entirely, since
* any kernel accesses will be in increasing address order starting
- * at 'ptr', and even if the end might be in kernel space, we'll
- * hit the GP faults for non-canonical accesses before we ever get
- * there.
+ * at 'ptr'.
*
* That's a separate optimization, for now just handle the small
* constant case.
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f1040cb..a5f221ea5 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -69,6 +69,7 @@
#include <asm/sev.h>
#include <asm/tdx.h>
#include <asm/posted_intr.h>
+#include <asm/runtime-const.h>
#include "cpu.h"
@@ -2389,6 +2390,15 @@ void __init arch_cpu_finalize_init(void)
alternative_instructions();
if (IS_ENABLED(CONFIG_X86_64)) {
+ unsigned long USER_PTR_MAX = TASK_SIZE_MAX-1;
+
+ /*
+ * Enable this when LAM is gated on LASS support
+ if (cpu_feature_enabled(X86_FEATURE_LAM))
+ USER_PTR_MAX = (1ul << 63) - PAGE_SIZE - 1;
+ */
+ runtime_const_init(ptr, USER_PTR_MAX);
+
/*
* Make sure the first 2MB area is not mapped by huge pages
* There are typically fixed size MTRRs in there and overlapping
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index f63b051..31a7371 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -584,7 +584,7 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_
native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->new_rev, dummy);
}
-static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
+static enum ucode_state _load_microcode_amd(u8 family, const u8 *data, size_t size);
static int __init save_microcode_in_initrd(void)
{
@@ -605,7 +605,7 @@ static int __init save_microcode_in_initrd(void)
if (!desc.mc)
return -EINVAL;
- ret = load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size);
+ ret = _load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size);
if (ret > UCODE_UPDATED)
return -EINVAL;
@@ -613,16 +613,19 @@ static int __init save_microcode_in_initrd(void)
}
early_initcall(save_microcode_in_initrd);
-static inline bool patch_cpus_equivalent(struct ucode_patch *p, struct ucode_patch *n)
+static inline bool patch_cpus_equivalent(struct ucode_patch *p,
+ struct ucode_patch *n,
+ bool ignore_stepping)
{
/* Zen and newer hardcode the f/m/s in the patch ID */
if (x86_family(bsp_cpuid_1_eax) >= 0x17) {
union cpuid_1_eax p_cid = ucode_rev_to_cpuid(p->patch_id);
union cpuid_1_eax n_cid = ucode_rev_to_cpuid(n->patch_id);
- /* Zap stepping */
- p_cid.stepping = 0;
- n_cid.stepping = 0;
+ if (ignore_stepping) {
+ p_cid.stepping = 0;
+ n_cid.stepping = 0;
+ }
return p_cid.full == n_cid.full;
} else {
@@ -644,13 +647,13 @@ static struct ucode_patch *cache_find_patch(struct ucode_cpu_info *uci, u16 equi
WARN_ON_ONCE(!n.patch_id);
list_for_each_entry(p, µcode_cache, plist)
- if (patch_cpus_equivalent(p, &n))
+ if (patch_cpus_equivalent(p, &n, false))
return p;
return NULL;
}
-static inline bool patch_newer(struct ucode_patch *p, struct ucode_patch *n)
+static inline int patch_newer(struct ucode_patch *p, struct ucode_patch *n)
{
/* Zen and newer hardcode the f/m/s in the patch ID */
if (x86_family(bsp_cpuid_1_eax) >= 0x17) {
@@ -659,6 +662,9 @@ static inline bool patch_newer(struct ucode_patch *p, struct ucode_patch *n)
zp.ucode_rev = p->patch_id;
zn.ucode_rev = n->patch_id;
+ if (zn.stepping != zp.stepping)
+ return -1;
+
return zn.rev > zp.rev;
} else {
return n->patch_id > p->patch_id;
@@ -668,10 +674,14 @@ static inline bool patch_newer(struct ucode_patch *p, struct ucode_patch *n)
static void update_cache(struct ucode_patch *new_patch)
{
struct ucode_patch *p;
+ int ret;
list_for_each_entry(p, µcode_cache, plist) {
- if (patch_cpus_equivalent(p, new_patch)) {
- if (!patch_newer(p, new_patch)) {
+ if (patch_cpus_equivalent(p, new_patch, true)) {
+ ret = patch_newer(p, new_patch);
+ if (ret < 0)
+ continue;
+ else if (!ret) {
/* we already have the latest patch */
kfree(new_patch->data);
kfree(new_patch);
@@ -944,6 +954,20 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
return UCODE_OK;
}
+static enum ucode_state _load_microcode_amd(u8 family, const u8 *data, size_t size)
+{
+ enum ucode_state ret;
+
+ /* free old equiv table */
+ free_equiv_cpu_table();
+
+ ret = __load_microcode_amd(family, data, size);
+ if (ret != UCODE_OK)
+ cleanup();
+
+ return ret;
+}
+
static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size)
{
struct cpuinfo_x86 *c;
@@ -951,14 +975,9 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz
struct ucode_patch *p;
enum ucode_state ret;
- /* free old equiv table */
- free_equiv_cpu_table();
-
- ret = __load_microcode_amd(family, data, size);
- if (ret != UCODE_OK) {
- cleanup();
+ ret = _load_microcode_amd(family, data, size);
+ if (ret != UCODE_OK)
return ret;
- }
for_each_node(nid) {
cpu = cpumask_first(cpumask_of_node(nid));
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 263f8ae..21e9e48 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -37,6 +37,7 @@
#include <asm/apic.h>
#include <asm/apicdef.h>
#include <asm/hypervisor.h>
+#include <asm/mtrr.h>
#include <asm/tlb.h>
#include <asm/cpuidle_haltpoll.h>
#include <asm/ptrace.h>
@@ -980,6 +981,9 @@ static void __init kvm_init_platform(void)
}
kvmclock_init();
x86_platform.apic_post_init = kvm_apic_init;
+
+ /* Set WB as the default cache mode for SEV-SNP and TDX */
+ mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK);
}
#if defined(CONFIG_AMD_MEM_ENCRYPT)
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index d05392d..2dbadf3 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -261,12 +261,6 @@ static noinstr bool handle_bug(struct pt_regs *regs)
int ud_type;
u32 imm;
- /*
- * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug()
- * is a rare case that uses @regs without passing them to
- * irqentry_enter().
- */
- kmsan_unpoison_entry_regs(regs);
ud_type = decode_bug(regs->ip, &imm);
if (ud_type == BUG_NONE)
return handled;
@@ -276,6 +270,12 @@ static noinstr bool handle_bug(struct pt_regs *regs)
*/
instrumentation_begin();
/*
+ * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug()
+ * is a rare case that uses @regs without passing them to
+ * irqentry_enter().
+ */
+ kmsan_unpoison_entry_regs(regs);
+ /*
* Since we're emulating a CALL with exceptions, restore the interrupt
* state to what it was at the exception site.
*/
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 6726be8..b8c5741 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -358,6 +358,7 @@
#endif
RUNTIME_CONST_VARIABLES
+ RUNTIME_CONST(ptr, USER_PTR_MAX)
. = ALIGN(PAGE_SIZE);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index a9a23e0..8e853a5 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1556,6 +1556,17 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
{
bool flush = false;
+ /*
+ * To prevent races with vCPUs faulting in a gfn using stale data,
+ * zapping a gfn range must be protected by mmu_invalidate_in_progress
+ * (and mmu_invalidate_seq). The only exception is memslot deletion;
+ * in that case, SRCU synchronization ensures that SPTEs are zapped
+ * after all vCPUs have unlocked SRCU, guaranteeing that vCPUs see the
+ * invalid slot.
+ */
+ lockdep_assert_once(kvm->mmu_invalidate_in_progress ||
+ lockdep_is_held(&kvm->slots_lock));
+
if (kvm_memslots_have_rmaps(kvm))
flush = __kvm_rmap_zap_gfn_range(kvm, range->slot,
range->start, range->end,
@@ -1884,14 +1895,10 @@ static bool sp_has_gptes(struct kvm_mmu_page *sp)
if (is_obsolete_sp((_kvm), (_sp))) { \
} else
-#define for_each_gfn_valid_sp(_kvm, _sp, _gfn) \
+#define for_each_gfn_valid_sp_with_gptes(_kvm, _sp, _gfn) \
for_each_valid_sp(_kvm, _sp, \
&(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)]) \
- if ((_sp)->gfn != (_gfn)) {} else
-
-#define for_each_gfn_valid_sp_with_gptes(_kvm, _sp, _gfn) \
- for_each_gfn_valid_sp(_kvm, _sp, _gfn) \
- if (!sp_has_gptes(_sp)) {} else
+ if ((_sp)->gfn != (_gfn) || !sp_has_gptes(_sp)) {} else
static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
@@ -7063,15 +7070,15 @@ static void kvm_mmu_zap_memslot_pages_and_flush(struct kvm *kvm,
/*
* Since accounting information is stored in struct kvm_arch_memory_slot,
- * shadow pages deletion (e.g. unaccount_shadowed()) requires that all
- * gfns with a shadow page have a corresponding memslot. Do so before
- * the memslot goes away.
+ * all MMU pages that are shadowing guest PTEs must be zapped before the
+ * memslot is deleted, as freeing such pages after the memslot is freed
+ * will result in use-after-free, e.g. in unaccount_shadowed().
*/
for (i = 0; i < slot->npages; i++) {
struct kvm_mmu_page *sp;
gfn_t gfn = slot->base_gfn + i;
- for_each_gfn_valid_sp(kvm, sp, gfn)
+ for_each_gfn_valid_sp_with_gptes(kvm, sp, gfn)
kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) {
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index d5314cb..cf84103 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -63,8 +63,12 @@ static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index)
u64 pdpte;
int ret;
+ /*
+ * Note, nCR3 is "assumed" to be 32-byte aligned, i.e. the CPU ignores
+ * nCR3[4:0] when loading PDPTEs from memory.
+ */
ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte,
- offset_in_page(cr3) + index * 8, 8);
+ (cr3 & GENMASK(11, 5)) + index * 8, 8);
if (ret)
return 0;
return pdpte;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 1a44383..81ed596 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -4888,9 +4888,6 @@ void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
vmx->hv_deadline_tsc = -1;
kvm_set_cr8(vcpu, 0);
- vmx_segment_cache_clear(vmx);
- kvm_register_mark_available(vcpu, VCPU_EXREG_SEGMENTS);
-
seg_setup(VCPU_SREG_CS);
vmcs_write16(GUEST_CS_SELECTOR, 0xf000);
vmcs_writel(GUEST_CS_BASE, 0xffff0000ul);
@@ -4917,6 +4914,9 @@ void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
vmcs_writel(GUEST_IDTR_BASE, 0);
vmcs_write32(GUEST_IDTR_LIMIT, 0xffff);
+ vmx_segment_cache_clear(vmx);
+ kvm_register_mark_available(vcpu, VCPU_EXREG_SEGMENTS);
+
vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE);
vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0);
vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, 0);
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index d066aec..4357ec2 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -39,8 +39,13 @@
.macro check_range size:req
.if IS_ENABLED(CONFIG_X86_64)
- mov %rax, %rdx
- sar $63, %rdx
+ movq $0x0123456789abcdef,%rdx
+ 1:
+ .pushsection runtime_ptr_USER_PTR_MAX,"a"
+ .long 1b - 8 - .
+ .popsection
+ cmp %rax, %rdx
+ sbb %rdx, %rdx
or %rdx, %rax
.else
cmp $TASK_SIZE_MAX-\size+1, %eax
diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
index 0ce1776..9a6a943 100644
--- a/arch/x86/virt/svm/sev.c
+++ b/arch/x86/virt/svm/sev.c
@@ -173,6 +173,8 @@ static void __init __snp_fixup_e820_tables(u64 pa)
e820__range_update(pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
e820__range_update_table(e820_table_kexec, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
e820__range_update_table(e820_table_firmware, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
+ if (!memblock_is_region_reserved(pa, PMD_SIZE))
+ memblock_reserve(pa, PMD_SIZE);
}
}
diff --git a/block/blk-map.c b/block/blk-map.c
index 0e1167b..6ef2ec1 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -600,9 +600,7 @@ static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter)
if (nsegs >= nr_segs || bytes > UINT_MAX - bv->bv_len)
goto put_bio;
if (bytes + bv->bv_len > nr_iter)
- goto put_bio;
- if (bv->bv_offset + bv->bv_len > PAGE_SIZE)
- goto put_bio;
+ break;
nsegs++;
bytes += bv->bv_len;
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 5147020..7773e6b 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -130,6 +130,17 @@ static const struct dmi_system_id dmi_lid_quirks[] = {
},
.driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN,
},
+ {
+ /*
+ * Samsung galaxybook2 ,initial _LID device notification returns
+ * lid closed.
+ */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "750XED"),
+ },
+ .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN,
+ },
{}
};
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index b73b3aa..c3fc2c0 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -1916,9 +1916,15 @@ unsigned int cppc_perf_to_khz(struct cppc_perf_caps *caps, unsigned int perf)
u64 mul, div;
if (caps->lowest_freq && caps->nominal_freq) {
- mul = caps->nominal_freq - caps->lowest_freq;
+ /* Avoid special case when nominal_freq is equal to lowest_freq */
+ if (caps->lowest_freq == caps->nominal_freq) {
+ mul = caps->nominal_freq;
+ div = caps->nominal_perf;
+ } else {
+ mul = caps->nominal_freq - caps->lowest_freq;
+ div = caps->nominal_perf - caps->lowest_perf;
+ }
mul *= KHZ_PER_MHZ;
- div = caps->nominal_perf - caps->lowest_perf;
offset = caps->nominal_freq * KHZ_PER_MHZ -
div64_u64(caps->nominal_perf * mul, div);
} else {
@@ -1939,11 +1945,17 @@ unsigned int cppc_khz_to_perf(struct cppc_perf_caps *caps, unsigned int freq)
{
s64 retval, offset = 0;
static u64 max_khz;
- u64 mul, div;
+ u64 mul, div;
if (caps->lowest_freq && caps->nominal_freq) {
- mul = caps->nominal_perf - caps->lowest_perf;
- div = caps->nominal_freq - caps->lowest_freq;
+ /* Avoid special case when nominal_freq is equal to lowest_freq */
+ if (caps->lowest_freq == caps->nominal_freq) {
+ mul = caps->nominal_perf;
+ div = caps->nominal_freq;
+ } else {
+ mul = caps->nominal_perf - caps->lowest_perf;
+ div = caps->nominal_freq - caps->lowest_freq;
+ }
/*
* We don't need to convert to kHz for computing offset and can
* directly use nominal_freq and lowest_freq as the div64_u64
diff --git a/drivers/acpi/prmt.c b/drivers/acpi/prmt.c
index 1cfaa59..747f83f 100644
--- a/drivers/acpi/prmt.c
+++ b/drivers/acpi/prmt.c
@@ -52,7 +52,7 @@ struct prm_context_buffer {
static LIST_HEAD(prm_module_list);
struct prm_handler_info {
- guid_t guid;
+ efi_guid_t guid;
efi_status_t (__efiapi *handler_addr)(u64, void *);
u64 static_data_buffer_addr;
u64 acpi_param_buffer_addr;
@@ -72,17 +72,21 @@ struct prm_module_info {
struct prm_handler_info handlers[] __counted_by(handler_count);
};
-static u64 efi_pa_va_lookup(u64 pa)
+static u64 efi_pa_va_lookup(efi_guid_t *guid, u64 pa)
{
efi_memory_desc_t *md;
u64 pa_offset = pa & ~PAGE_MASK;
u64 page = pa & PAGE_MASK;
for_each_efi_memory_desc(md) {
- if (md->phys_addr < pa && pa < md->phys_addr + PAGE_SIZE * md->num_pages)
+ if ((md->attribute & EFI_MEMORY_RUNTIME) &&
+ (md->phys_addr < pa && pa < md->phys_addr + PAGE_SIZE * md->num_pages)) {
return pa_offset + md->virt_addr + page - md->phys_addr;
+ }
}
+ pr_warn("Failed to find VA for GUID: %pUL, PA: 0x%llx", guid, pa);
+
return 0;
}
@@ -148,9 +152,15 @@ acpi_parse_prmt(union acpi_subtable_headers *header, const unsigned long end)
th = &tm->handlers[cur_handler];
guid_copy(&th->guid, (guid_t *)handler_info->handler_guid);
- th->handler_addr = (void *)efi_pa_va_lookup(handler_info->handler_address);
- th->static_data_buffer_addr = efi_pa_va_lookup(handler_info->static_data_buffer_address);
- th->acpi_param_buffer_addr = efi_pa_va_lookup(handler_info->acpi_param_buffer_address);
+ th->handler_addr =
+ (void *)efi_pa_va_lookup(&th->guid, handler_info->handler_address);
+
+ th->static_data_buffer_addr =
+ efi_pa_va_lookup(&th->guid, handler_info->static_data_buffer_address);
+
+ th->acpi_param_buffer_addr =
+ efi_pa_va_lookup(&th->guid, handler_info->acpi_param_buffer_address);
+
} while (++cur_handler < tm->handler_count && (handler_info = get_next_handler(handler_info)));
return 0;
@@ -277,6 +287,13 @@ static acpi_status acpi_platformrt_space_handler(u32 function,
if (!handler || !module)
goto invalid_guid;
+ if (!handler->handler_addr ||
+ !handler->static_data_buffer_addr ||
+ !handler->acpi_param_buffer_addr) {
+ buffer->prm_status = PRM_HANDLER_ERROR;
+ return AE_OK;
+ }
+
ACPI_COPY_NAMESEG(context.signature, "PRMC");
context.revision = 0x0;
context.reserved = 0x0;
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 129bceb..7fe842d 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -503,6 +503,13 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = {
DMI_MATCH(DMI_BOARD_NAME, "17U70P"),
},
},
+ {
+ /* LG Electronics 16T90SP */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"),
+ DMI_MATCH(DMI_BOARD_NAME, "16T90SP"),
+ },
+ },
{ }
};
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index fa41ea5..3b303d4 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -651,6 +651,7 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap,
/* the scmd has an associated qc */
if (!(qc->flags & ATA_QCFLAG_EH)) {
/* which hasn't failed yet, timeout */
+ set_host_byte(scmd, DID_TIME_OUT);
qc->err_mask |= AC_ERR_TIMEOUT;
qc->flags |= ATA_QCFLAG_EH;
nr_timedout++;
diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c
index 8545460..1ff99a7 100644
--- a/drivers/char/tpm/tpm-chip.c
+++ b/drivers/char/tpm/tpm-chip.c
@@ -674,6 +674,16 @@ EXPORT_SYMBOL_GPL(tpm_chip_register);
*/
void tpm_chip_unregister(struct tpm_chip *chip)
{
+#ifdef CONFIG_TCG_TPM2_HMAC
+ int rc;
+
+ rc = tpm_try_get_ops(chip);
+ if (!rc) {
+ tpm2_end_auth_session(chip);
+ tpm_put_ops(chip);
+ }
+#endif
+
tpm_del_legacy_sysfs(chip);
if (tpm_is_hwrng_enabled(chip))
hwrng_unregister(&chip->hwrng);
diff --git a/drivers/char/tpm/tpm-dev-common.c b/drivers/char/tpm/tpm-dev-common.c
index c3fbbf4..48ff874 100644
--- a/drivers/char/tpm/tpm-dev-common.c
+++ b/drivers/char/tpm/tpm-dev-common.c
@@ -27,6 +27,9 @@ static ssize_t tpm_dev_transmit(struct tpm_chip *chip, struct tpm_space *space,
struct tpm_header *header = (void *)buf;
ssize_t ret, len;
+ if (chip->flags & TPM_CHIP_FLAG_TPM2)
+ tpm2_end_auth_session(chip);
+
ret = tpm2_prepare_space(chip, space, buf, bufsiz);
/* If the command is not implemented by the TPM, synthesize a
* response with a TPM2_RC_COMMAND_CODE return for user-space.
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index 5da134f..8134f00 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -379,10 +379,12 @@ int tpm_pm_suspend(struct device *dev)
rc = tpm_try_get_ops(chip);
if (!rc) {
- if (chip->flags & TPM_CHIP_FLAG_TPM2)
+ if (chip->flags & TPM_CHIP_FLAG_TPM2) {
+ tpm2_end_auth_session(chip);
tpm2_shutdown(chip, TPM2_SU_STATE);
- else
+ } else {
rc = tpm1_pm_suspend(chip, tpm_suspend_pcr);
+ }
tpm_put_ops(chip);
}
diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c
index 511c670..0739830 100644
--- a/drivers/char/tpm/tpm2-sessions.c
+++ b/drivers/char/tpm/tpm2-sessions.c
@@ -333,6 +333,9 @@ void tpm_buf_append_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf,
}
#ifdef CONFIG_TCG_TPM2_HMAC
+ /* The first write to /dev/tpm{rm0} will flush the session. */
+ attributes |= TPM2_SA_CONTINUE_SESSION;
+
/*
* The Architecture Guide requires us to strip trailing zeros
* before computing the HMAC
@@ -484,7 +487,8 @@ static void tpm2_KDFe(u8 z[EC_PT_SZ], const char *str, u8 *pt_u, u8 *pt_v,
sha256_final(&sctx, out);
}
-static void tpm_buf_append_salt(struct tpm_buf *buf, struct tpm_chip *chip)
+static void tpm_buf_append_salt(struct tpm_buf *buf, struct tpm_chip *chip,
+ struct tpm2_auth *auth)
{
struct crypto_kpp *kpp;
struct kpp_request *req;
@@ -543,7 +547,7 @@ static void tpm_buf_append_salt(struct tpm_buf *buf, struct tpm_chip *chip)
sg_set_buf(&s[0], chip->null_ec_key_x, EC_PT_SZ);
sg_set_buf(&s[1], chip->null_ec_key_y, EC_PT_SZ);
kpp_request_set_input(req, s, EC_PT_SZ*2);
- sg_init_one(d, chip->auth->salt, EC_PT_SZ);
+ sg_init_one(d, auth->salt, EC_PT_SZ);
kpp_request_set_output(req, d, EC_PT_SZ);
crypto_kpp_compute_shared_secret(req);
kpp_request_free(req);
@@ -554,8 +558,7 @@ static void tpm_buf_append_salt(struct tpm_buf *buf, struct tpm_chip *chip)
* This works because KDFe fully consumes the secret before it
* writes the salt
*/
- tpm2_KDFe(chip->auth->salt, "SECRET", x, chip->null_ec_key_x,
- chip->auth->salt);
+ tpm2_KDFe(auth->salt, "SECRET", x, chip->null_ec_key_x, auth->salt);
out:
crypto_free_kpp(kpp);
@@ -853,7 +856,9 @@ int tpm_buf_check_hmac_response(struct tpm_chip *chip, struct tpm_buf *buf,
if (rc)
/* manually close the session if it wasn't consumed */
tpm2_flush_context(chip, auth->handle);
- memzero_explicit(auth, sizeof(*auth));
+
+ kfree_sensitive(auth);
+ chip->auth = NULL;
} else {
/* reset for next use */
auth->session = TPM_HEADER_SIZE;
@@ -881,7 +886,8 @@ void tpm2_end_auth_session(struct tpm_chip *chip)
return;
tpm2_flush_context(chip, auth->handle);
- memzero_explicit(auth, sizeof(*auth));
+ kfree_sensitive(auth);
+ chip->auth = NULL;
}
EXPORT_SYMBOL(tpm2_end_auth_session);
@@ -915,33 +921,37 @@ static int tpm2_parse_start_auth_session(struct tpm2_auth *auth,
static int tpm2_load_null(struct tpm_chip *chip, u32 *null_key)
{
- int rc;
unsigned int offset = 0; /* dummy offset for null seed context */
u8 name[SHA256_DIGEST_SIZE + 2];
+ u32 tmp_null_key;
+ int rc;
rc = tpm2_load_context(chip, chip->null_key_context, &offset,
- null_key);
- if (rc != -EINVAL)
- return rc;
+ &tmp_null_key);
+ if (rc != -EINVAL) {
+ if (!rc)
+ *null_key = tmp_null_key;
+ goto err;
+ }
- /* an integrity failure may mean the TPM has been reset */
- dev_err(&chip->dev, "NULL key integrity failure!\n");
- /* check the null name against what we know */
- tpm2_create_primary(chip, TPM2_RH_NULL, NULL, name);
- if (memcmp(name, chip->null_key_name, sizeof(name)) == 0)
- /* name unchanged, assume transient integrity failure */
- return rc;
- /*
- * Fatal TPM failure: the NULL seed has actually changed, so
- * the TPM must have been illegally reset. All in-kernel TPM
- * operations will fail because the NULL primary can't be
- * loaded to salt the sessions, but disable the TPM anyway so
- * userspace programmes can't be compromised by it.
- */
- dev_err(&chip->dev, "NULL name has changed, disabling TPM due to interference\n");
+ /* Try to re-create null key, given the integrity failure: */
+ rc = tpm2_create_primary(chip, TPM2_RH_NULL, &tmp_null_key, name);
+ if (rc)
+ goto err;
+
+ /* Return null key if the name has not been changed: */
+ if (!memcmp(name, chip->null_key_name, sizeof(name))) {
+ *null_key = tmp_null_key;
+ return 0;
+ }
+
+ /* Deduce from the name change TPM interference: */
+ dev_err(&chip->dev, "null key integrity check failed\n");
+ tpm2_flush_context(chip, tmp_null_key);
chip->flags |= TPM_CHIP_FLAG_DISABLE;
- return rc;
+err:
+ return rc ? -ENODEV : 0;
}
/**
@@ -958,16 +968,20 @@ static int tpm2_load_null(struct tpm_chip *chip, u32 *null_key)
*/
int tpm2_start_auth_session(struct tpm_chip *chip)
{
+ struct tpm2_auth *auth;
struct tpm_buf buf;
- struct tpm2_auth *auth = chip->auth;
- int rc;
u32 null_key;
+ int rc;
- if (!auth) {
- dev_warn_once(&chip->dev, "auth session is not active\n");
+ if (chip->auth) {
+ dev_warn_once(&chip->dev, "auth session is active\n");
return 0;
}
+ auth = kzalloc(sizeof(*auth), GFP_KERNEL);
+ if (!auth)
+ return -ENOMEM;
+
rc = tpm2_load_null(chip, &null_key);
if (rc)
goto out;
@@ -988,7 +1002,7 @@ int tpm2_start_auth_session(struct tpm_chip *chip)
tpm_buf_append(&buf, auth->our_nonce, sizeof(auth->our_nonce));
/* append encrypted salt and squirrel away unencrypted in auth */
- tpm_buf_append_salt(&buf, chip);
+ tpm_buf_append_salt(&buf, chip, auth);
/* session type (HMAC, audit or policy) */
tpm_buf_append_u8(&buf, TPM2_SE_HMAC);
@@ -1010,10 +1024,13 @@ int tpm2_start_auth_session(struct tpm_chip *chip)
tpm_buf_destroy(&buf);
- if (rc)
- goto out;
+ if (rc == TPM2_RC_SUCCESS) {
+ chip->auth = auth;
+ return 0;
+ }
- out:
+out:
+ kfree_sensitive(auth);
return rc;
}
EXPORT_SYMBOL(tpm2_start_auth_session);
@@ -1347,18 +1364,21 @@ static int tpm2_create_null_primary(struct tpm_chip *chip)
*
* Derive and context save the null primary and allocate memory in the
* struct tpm_chip for the authorizations.
+ *
+ * Return:
+ * * 0 - OK
+ * * -errno - A system error
+ * * TPM_RC - A TPM error
*/
int tpm2_sessions_init(struct tpm_chip *chip)
{
int rc;
rc = tpm2_create_null_primary(chip);
- if (rc)
- dev_err(&chip->dev, "TPM: security failed (NULL seed derivation): %d\n", rc);
-
- chip->auth = kmalloc(sizeof(*chip->auth), GFP_KERNEL);
- if (!chip->auth)
- return -ENOMEM;
+ if (rc) {
+ dev_err(&chip->dev, "null key creation failed with %d\n", rc);
+ return rc;
+ }
return rc;
}
diff --git a/drivers/firewire/core-topology.c b/drivers/firewire/core-topology.c
index 6adadb1..892b94c 100644
--- a/drivers/firewire/core-topology.c
+++ b/drivers/firewire/core-topology.c
@@ -204,7 +204,7 @@ static struct fw_node *build_tree(struct fw_card *card, const u32 *sid, int self
// the node->ports array where the parent node should be. Later,
// when we handle the parent node, we fix up the reference.
++parent_count;
- node->color = i;
+ node->color = port_index;
break;
case PHY_PACKET_SELF_ID_PORT_STATUS_CHILD:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index f85ace0..1f5a296 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -147,6 +147,7 @@ static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif,
struct acpi_buffer *params)
{
acpi_status status;
+ union acpi_object *obj;
union acpi_object atif_arg_elements[2];
struct acpi_object_list atif_arg;
struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
@@ -169,16 +170,24 @@ static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif,
status = acpi_evaluate_object(atif->handle, NULL, &atif_arg,
&buffer);
+ obj = (union acpi_object *)buffer.pointer;
- /* Fail only if calling the method fails and ATIF is supported */
+ /* Fail if calling the method fails and ATIF is supported */
if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
DRM_DEBUG_DRIVER("failed to evaluate ATIF got %s\n",
acpi_format_exception(status));
- kfree(buffer.pointer);
+ kfree(obj);
return NULL;
}
- return buffer.pointer;
+ if (obj->type != ACPI_TYPE_BUFFER) {
+ DRM_DEBUG_DRIVER("bad object returned from ATIF: %d\n",
+ obj->type);
+ kfree(obj);
+ return NULL;
+ }
+
+ return obj;
}
/**
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
index a876349..9288f37 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
@@ -51,6 +51,12 @@ MODULE_FIRMWARE("amdgpu/sdma_7_0_1.bin");
#define SDMA0_HYP_DEC_REG_END 0x589a
#define SDMA1_HYP_DEC_REG_OFFSET 0x20
+/*define for compression field for sdma7*/
+#define SDMA_PKT_CONSTANT_FILL_HEADER_compress_offset 0
+#define SDMA_PKT_CONSTANT_FILL_HEADER_compress_mask 0x00000001
+#define SDMA_PKT_CONSTANT_FILL_HEADER_compress_shift 16
+#define SDMA_PKT_CONSTANT_FILL_HEADER_COMPRESS(x) (((x) & SDMA_PKT_CONSTANT_FILL_HEADER_compress_mask) << SDMA_PKT_CONSTANT_FILL_HEADER_compress_shift)
+
static const struct amdgpu_hwip_reg_entry sdma_reg_list_7_0[] = {
SOC15_REG_ENTRY_STR(GC, 0, regSDMA0_STATUS_REG),
SOC15_REG_ENTRY_STR(GC, 0, regSDMA0_STATUS1_REG),
@@ -1724,7 +1730,8 @@ static void sdma_v7_0_emit_fill_buffer(struct amdgpu_ib *ib,
uint64_t dst_offset,
uint32_t byte_count)
{
- ib->ptr[ib->length_dw++] = SDMA_PKT_COPY_LINEAR_HEADER_OP(SDMA_OP_CONST_FILL);
+ ib->ptr[ib->length_dw++] = SDMA_PKT_CONSTANT_FILL_HEADER_OP(SDMA_OP_CONST_FILL) |
+ SDMA_PKT_CONSTANT_FILL_HEADER_COMPRESS(1);
ib->ptr[ib->length_dw++] = lower_32_bits(dst_offset);
ib->ptr[ib->length_dw++] = upper_32_bits(dst_offset);
ib->ptr[ib->length_dw++] = src_data;
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 6b5e2206..13421a5 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -8374,7 +8374,8 @@ static void manage_dm_interrupts(struct amdgpu_device *adev,
if (amdgpu_ip_version(adev, DCE_HWIP, 0) <
IP_VERSION(3, 5, 0) ||
acrtc_state->stream->link->psr_settings.psr_version <
- DC_PSR_VERSION_UNSUPPORTED) {
+ DC_PSR_VERSION_UNSUPPORTED ||
+ !(adev->flags & AMD_IS_APU)) {
timing = &acrtc_state->stream->timing;
/* at least 2 frames */
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 069e019..eea317d 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
@@ -44,6 +44,7 @@
#include "dm_helpers.h"
#include "ddc_service_types.h"
+#include "clk_mgr.h"
static u32 edid_extract_panel_id(struct edid *edid)
{
@@ -1121,6 +1122,8 @@ bool dm_helpers_dp_handle_test_pattern_request(
struct pipe_ctx *pipe_ctx = NULL;
struct amdgpu_dm_connector *aconnector = link->priv;
struct drm_device *dev = aconnector->base.dev;
+ struct dc_state *dc_state = ctx->dc->current_state;
+ struct clk_mgr *clk_mgr = ctx->dc->clk_mgr;
int i;
for (i = 0; i < MAX_PIPES; i++) {
@@ -1221,6 +1224,16 @@ bool dm_helpers_dp_handle_test_pattern_request(
pipe_ctx->stream->test_pattern.type = test_pattern;
pipe_ctx->stream->test_pattern.color_space = test_pattern_color_space;
+ /* Temp W/A for compliance test failure */
+ dc_state->bw_ctx.bw.dcn.clk.p_state_change_support = false;
+ dc_state->bw_ctx.bw.dcn.clk.dramclk_khz = clk_mgr->dc_mode_softmax_enabled ?
+ clk_mgr->bw_params->dc_mode_softmax_memclk : clk_mgr->bw_params->max_memclk_mhz;
+ dc_state->bw_ctx.bw.dcn.clk.idle_dramclk_khz = dc_state->bw_ctx.bw.dcn.clk.dramclk_khz;
+ ctx->dc->clk_mgr->funcs->update_clocks(
+ ctx->dc->clk_mgr,
+ dc_state,
+ false);
+
dc_link_dp_set_test_pattern(
(struct dc_link *) link,
test_pattern,
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
index 3cd52e7..95838c7 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
@@ -841,6 +841,8 @@ bool is_psr_su_specific_panel(struct dc_link *link)
isPSRSUSupported = false;
else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x03)
isPSRSUSupported = false;
+ else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x01)
+ isPSRSUSupported = false;
else if (dpcd_caps->psr_info.force_psrsu_cap == 0x1)
isPSRSUSupported = true;
}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 9ad9cf7..80e60ea2 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1234,6 +1234,14 @@ static void smu_init_xgmi_plpd_mode(struct smu_context *smu)
}
}
+static bool smu_is_workload_profile_available(struct smu_context *smu,
+ u32 profile)
+{
+ if (profile >= PP_SMC_POWER_PROFILE_COUNT)
+ return false;
+ return smu->workload_map && smu->workload_map[profile].valid_mapping;
+}
+
static int smu_sw_init(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1265,7 +1273,8 @@ static int smu_sw_init(void *handle)
smu->workload_prority[PP_SMC_POWER_PROFILE_COMPUTE] = 5;
smu->workload_prority[PP_SMC_POWER_PROFILE_CUSTOM] = 6;
- if (smu->is_apu)
+ if (smu->is_apu ||
+ !smu_is_workload_profile_available(smu, PP_SMC_POWER_PROFILE_FULLSCREEN3D))
smu->workload_mask = 1 << smu->workload_prority[PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT];
else
smu->workload_mask = 1 << smu->workload_prority[PP_SMC_POWER_PROFILE_FULLSCREEN3D];
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0.h
index ee457a6..c2fd0a4 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0.h
@@ -25,7 +25,7 @@
#define SMU14_DRIVER_IF_V14_0_H
//Increment this version if SkuTable_t or BoardTable_t change
-#define PPTABLE_VERSION 0x18
+#define PPTABLE_VERSION 0x1B
#define NUM_GFXCLK_DPM_LEVELS 16
#define NUM_SOCCLK_DPM_LEVELS 8
@@ -145,7 +145,7 @@ typedef enum {
} FEATURE_BTC_e;
// Debug Overrides Bitmask
-#define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_VCN_FCLK 0x00000001
+#define DEBUG_OVERRIDE_NOT_USE 0x00000001
#define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_DCN_FCLK 0x00000002
#define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_MP0_FCLK 0x00000004
#define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_VCN_DCFCLK 0x00000008
@@ -161,6 +161,7 @@ typedef enum {
#define DEBUG_OVERRIDE_ENABLE_SOC_VF_BRINGUP_MODE 0x00002000
#define DEBUG_OVERRIDE_ENABLE_PER_WGP_RESIENCY 0x00004000
#define DEBUG_OVERRIDE_DISABLE_MEMORY_VOLTAGE_SCALING 0x00008000
+#define DEBUG_OVERRIDE_DFLL_BTC_FCW_LOG 0x00010000
// VR Mapping Bit Defines
#define VR_MAPPING_VR_SELECT_MASK 0x01
@@ -391,6 +392,21 @@ typedef struct {
EccInfo_t EccInfo[24];
} EccInfoTable_t;
+#define EPCS_HIGH_POWER 600
+#define EPCS_NORMAL_POWER 450
+#define EPCS_LOW_POWER 300
+#define EPCS_SHORTED_POWER 150
+#define EPCS_NO_BOOTUP 0
+
+typedef enum{
+ EPCS_SHORTED_LIMIT,
+ EPCS_LOW_POWER_LIMIT,
+ EPCS_NORMAL_POWER_LIMIT,
+ EPCS_HIGH_POWER_LIMIT,
+ EPCS_NOT_CONFIGURED,
+ EPCS_STATUS_COUNT,
+} EPCS_STATUS_e;
+
//D3HOT sequences
typedef enum {
BACO_SEQUENCE,
@@ -662,7 +678,7 @@ typedef enum {
} PP_GRTAVFS_FW_SEP_FUSE_e;
#define PP_NUM_RTAVFS_PWL_ZONES 5
-
+#define PP_NUM_PSM_DIDT_PWL_ZONES 3
// VBIOS or PPLIB configures telemetry slope and offset. Only slope expected to be set for SVI3
// Slope Q1.7, Offset Q1.2
@@ -746,10 +762,10 @@ typedef struct {
uint16_t Padding;
//Frequency changes
- int16_t GfxclkFmin; // MHz
- int16_t GfxclkFmax; // MHz
- uint16_t UclkFmin; // MHz
- uint16_t UclkFmax; // MHz
+ int16_t GfxclkFoffset;
+ uint16_t Padding1;
+ uint16_t UclkFmin;
+ uint16_t UclkFmax;
uint16_t FclkFmin;
uint16_t FclkFmax;
@@ -770,19 +786,23 @@ typedef struct {
uint8_t MaxOpTemp;
uint8_t AdvancedOdModeEnabled;
- uint8_t Padding1[3];
+ uint8_t Padding2[3];
uint16_t GfxVoltageFullCtrlMode;
uint16_t SocVoltageFullCtrlMode;
uint16_t GfxclkFullCtrlMode;
uint16_t UclkFullCtrlMode;
uint16_t FclkFullCtrlMode;
- uint16_t Padding2;
+ uint16_t Padding3;
int16_t GfxEdc;
int16_t GfxPccLimitControl;
- uint32_t Spare[10];
+ uint16_t GfxclkFmaxVmax;
+ uint8_t GfxclkFmaxVmaxTemperature;
+ uint8_t Padding4[1];
+
+ uint32_t Spare[9];
uint32_t MmHubPadding[8]; // SMU internal use. Adding here instead of external as a workaround
} OverDriveTable_t;
@@ -802,8 +822,8 @@ typedef struct {
uint16_t VddSocVmax;
//gfxclk
- int16_t GfxclkFmin; // MHz
- int16_t GfxclkFmax; // MHz
+ int16_t GfxclkFoffset;
+ uint16_t Padding;
//uclk
uint16_t UclkFmin; // MHz
uint16_t UclkFmax; // MHz
@@ -828,7 +848,7 @@ typedef struct {
uint8_t FanZeroRpmEnable;
//temperature
uint8_t MaxOpTemp;
- uint8_t Padding[2];
+ uint8_t Padding1[2];
//Full Ctrl
uint16_t GfxVoltageFullCtrlMode;
@@ -839,7 +859,7 @@ typedef struct {
//EDC
int16_t GfxEdc;
int16_t GfxPccLimitControl;
- int16_t Padding1;
+ int16_t Padding2;
uint32_t Spare[5];
} OverDriveLimits_t;
@@ -987,8 +1007,9 @@ typedef struct {
uint16_t BaseClockDc;
uint16_t GameClockDc;
uint16_t BoostClockDc;
-
- uint32_t Reserved[4];
+ uint16_t MaxReportedClock;
+ uint16_t Padding;
+ uint32_t Reserved[3];
} DriverReportedClocks_t;
typedef struct {
@@ -1132,7 +1153,7 @@ typedef struct {
uint32_t DcModeMaxFreq [PPCLK_COUNT ]; // In MHz
uint16_t GfxclkAibFmax;
- uint16_t GfxclkFreqCap;
+ uint16_t GfxDpmPadding;
//GFX Idle Power Settings
uint16_t GfxclkFgfxoffEntry; // Entry in RLC stage (PLL), in Mhz
@@ -1172,8 +1193,7 @@ typedef struct {
uint32_t DvoFmaxLowScaler; //Unitless float
// GFX DCS
- uint16_t DcsGfxOffVoltage; //Voltage in mV(Q2) applied to VDDGFX when entering DCS GFXOFF phase
- uint16_t PaddingDcs;
+ uint32_t PaddingDcs;
uint16_t DcsMinGfxOffTime; //Minimum amount of time PMFW shuts GFX OFF as part of GFX DCS phase
uint16_t DcsMaxGfxOffTime; //Maximum amount of time PMFW can shut GFX OFF as part of GFX DCS phase at a stretch.
@@ -1205,8 +1225,7 @@ typedef struct {
uint16_t DalDcModeMaxUclkFreq;
uint8_t PaddingsMem[2];
//FCLK Section
- uint16_t FclkDpmDisallowPstateFreq; //Frequency which FW will target when indicated that display config cannot support P-state. Set to 0 use FW calculated value
- uint16_t PaddingFclk;
+ uint32_t PaddingFclk;
// Link DPM Settings
uint8_t PcieGenSpeed[NUM_LINK_LEVELS]; ///< 0:PciE-gen1 1:PciE-gen2 2:PciE-gen3 3:PciE-gen4 4:PciE-gen5
@@ -1215,12 +1234,19 @@ typedef struct {
// SECTION: VDD_GFX AVFS
uint8_t OverrideGfxAvfsFuses;
- uint8_t GfxAvfsPadding[3];
+ uint8_t GfxAvfsPadding[1];
+ uint16_t DroopGBStDev;
uint32_t SocHwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT]; //new added for Soc domain
uint32_t GfxL2HwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT]; //see fusedoc for encoding
//uint32_t GfxSeHwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT];
- uint32_t spare_HwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT];
+
+ uint16_t PsmDidt_Vcross[PP_NUM_PSM_DIDT_PWL_ZONES-1];
+ uint32_t PsmDidt_StaticDroop_A[PP_NUM_PSM_DIDT_PWL_ZONES];
+ uint32_t PsmDidt_StaticDroop_B[PP_NUM_PSM_DIDT_PWL_ZONES];
+ uint32_t PsmDidt_DynDroop_A[PP_NUM_PSM_DIDT_PWL_ZONES];
+ uint32_t PsmDidt_DynDroop_B[PP_NUM_PSM_DIDT_PWL_ZONES];
+ uint32_t spare_HwRtAvfsFuses[19];
uint32_t SocCommonRtAvfs[PP_GRTAVFS_FW_COMMON_FUSE_COUNT];
uint32_t GfxCommonRtAvfs[PP_GRTAVFS_FW_COMMON_FUSE_COUNT];
@@ -1246,11 +1272,7 @@ typedef struct {
uint32_t dGbV_dT_vmin;
uint32_t dGbV_dT_vmax;
- //Unused: PMFW-9370
- uint32_t V2F_vmin_range_low;
- uint32_t V2F_vmin_range_high;
- uint32_t V2F_vmax_range_low;
- uint32_t V2F_vmax_range_high;
+ uint32_t PaddingV2F[4];
AvfsDcBtcParams_t DcBtcGfxParams;
QuadraticInt_t SSCurve_GFX;
@@ -1327,18 +1349,18 @@ typedef struct {
uint16_t PsmDidtReleaseTimer;
uint32_t PsmDidtStallPattern; //Will be written to both pattern 1 and didt_static_level_prog
// CAC EDC
- uint32_t Leakage_C0; // in IEEE float
- uint32_t Leakage_C1; // in IEEE float
- uint32_t Leakage_C2; // in IEEE float
- uint32_t Leakage_C3; // in IEEE float
- uint32_t Leakage_C4; // in IEEE float
- uint32_t Leakage_C5; // in IEEE float
- uint32_t GFX_CLK_SCALAR; // in IEEE float
- uint32_t GFX_CLK_INTERCEPT; // in IEEE float
- uint32_t GFX_CAC_M; // in IEEE float
- uint32_t GFX_CAC_B; // in IEEE float
- uint32_t VDD_GFX_CurrentLimitGuardband; // in IEEE float
- uint32_t DynToTotalCacScalar; // in IEEE
+ uint32_t CacEdcCacLeakageC0;
+ uint32_t CacEdcCacLeakageC1;
+ uint32_t CacEdcCacLeakageC2;
+ uint32_t CacEdcCacLeakageC3;
+ uint32_t CacEdcCacLeakageC4;
+ uint32_t CacEdcCacLeakageC5;
+ uint32_t CacEdcGfxClkScalar;
+ uint32_t CacEdcGfxClkIntercept;
+ uint32_t CacEdcCac_m;
+ uint32_t CacEdcCac_b;
+ uint32_t CacEdcCurrLimitGuardband;
+ uint32_t CacEdcDynToTotalCacRatio;
// GFX EDC XVMIN
uint32_t XVmin_Gfx_EdcThreshScalar;
uint32_t XVmin_Gfx_EdcEnableFreq;
@@ -1467,7 +1489,7 @@ typedef struct {
uint8_t VddqOffEnabled;
uint8_t PaddingUmcFlags[2];
- uint32_t PostVoltageSetBacoDelay; // in microseconds. Amount of time FW will wait after power good is established or PSI0 command is issued
+ uint32_t Paddign1;
uint32_t BacoEntryDelay; // in milliseconds. Amount of time FW will wait to trigger BACO entry after receiving entry notification from OS
uint8_t FuseWritePowerMuxPresent;
@@ -1530,7 +1552,7 @@ typedef struct {
int16_t FuzzyFan_ErrorSetDelta;
int16_t FuzzyFan_ErrorRateSetDelta;
int16_t FuzzyFan_PwmSetDelta;
- uint16_t FuzzyFan_Reserved;
+ uint16_t FanPadding2;
uint16_t FwCtfLimit[TEMP_COUNT];
@@ -1547,9 +1569,10 @@ typedef struct {
uint16_t FanSpare[1];
uint8_t FanIntakeSensorSupport;
uint8_t FanIntakePadding;
- uint32_t FanAmbientPerfBoostThreshold;
uint32_t FanSpare2[12];
+ uint32_t ODFeatureCtrlMask;
+
uint16_t TemperatureLimit_Hynix; // In degrees Celsius. Memory temperature limit associated with Hynix
uint16_t TemperatureLimit_Micron; // In degrees Celsius. Memory temperature limit associated with Micron
uint16_t TemperatureFwCtfLimit_Hynix;
@@ -1637,7 +1660,7 @@ typedef struct {
uint16_t AverageDclk0Frequency ;
uint16_t AverageVclk1Frequency ;
uint16_t AverageDclk1Frequency ;
- uint16_t PCIeBusy ;
+ uint16_t AveragePCIeBusy ;
uint16_t dGPU_W_MAX ;
uint16_t padding ;
@@ -1665,12 +1688,12 @@ typedef struct {
uint16_t AverageGfxActivity ;
uint16_t AverageUclkActivity ;
- uint16_t Vcn0ActivityPercentage ;
+ uint16_t AverageVcn0ActivityPercentage;
uint16_t Vcn1ActivityPercentage ;
uint32_t EnergyAccumulator;
uint16_t AverageSocketPower;
- uint16_t MovingAverageTotalBoardPower;
+ uint16_t AverageTotalBoardPower;
uint16_t AvgTemperature[TEMP_COUNT];
uint16_t AvgTemperatureFanIntake;
@@ -1684,7 +1707,8 @@ typedef struct {
uint8_t ThrottlingPercentage[THROTTLER_COUNT];
- uint8_t padding1[3];
+ uint8_t VmaxThrottlingPercentage;
+ uint8_t padding1[2];
//metrics for D3hot entry/exit and driver ARM msgs
uint32_t D3HotEntryCountPerMode[D3HOT_SEQUENCE_COUNT];
@@ -1693,7 +1717,7 @@ typedef struct {
uint16_t ApuSTAPMSmartShiftLimit;
uint16_t ApuSTAPMLimit;
- uint16_t MovingAvgApuSocketPower;
+ uint16_t AvgApuSocketPower;
uint16_t AverageUclkActivity_MAX;
@@ -1823,6 +1847,17 @@ typedef struct {
#define TABLE_TRANSFER_FAILED 0xFF
#define TABLE_TRANSFER_PENDING 0xAB
+#define TABLE_PPT_FAILED 0x100
+#define TABLE_TDC_FAILED 0x200
+#define TABLE_TEMP_FAILED 0x400
+#define TABLE_FAN_TARGET_TEMP_FAILED 0x800
+#define TABLE_FAN_STOP_TEMP_FAILED 0x1000
+#define TABLE_FAN_START_TEMP_FAILED 0x2000
+#define TABLE_FAN_PWM_MIN_FAILED 0x4000
+#define TABLE_ACOUSTIC_TARGET_RPM_FAILED 0x8000
+#define TABLE_ACOUSTIC_LIMIT_RPM_FAILED 0x10000
+#define TABLE_MGPU_ACOUSTIC_TARGET_RPM_FAILED 0x20000
+
// Table types
#define TABLE_PPTABLE 0
#define TABLE_COMBO_PPTABLE 1
@@ -1849,5 +1884,6 @@ typedef struct {
#define IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING 0x7
#define IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL 0x8
#define IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY 0x9
+#define IH_INTERRUPT_CONTEXT_ID_DYNAMIC_TABLE 0xA
#endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
index 46b4565..727d5b4 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
@@ -28,7 +28,7 @@
#define SMU14_DRIVER_IF_VERSION_INV 0xFFFFFFFF
#define SMU14_DRIVER_IF_VERSION_SMU_V14_0_0 0x7
#define SMU14_DRIVER_IF_VERSION_SMU_V14_0_1 0x6
-#define SMU14_DRIVER_IF_VERSION_SMU_V14_0_2 0x26
+#define SMU14_DRIVER_IF_VERSION_SMU_V14_0_2 0x2E
#define FEATURE_MASK(feature) (1ULL << feature)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
index 5899d01..e83ea2b 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
@@ -1077,12 +1077,9 @@ static void smu_v14_0_2_get_od_setting_limits(struct smu_context *smu,
switch (od_feature_bit) {
case PP_OD_FEATURE_GFXCLK_FMIN:
- od_min_setting = overdrive_lowerlimits->GfxclkFmin;
- od_max_setting = overdrive_upperlimits->GfxclkFmin;
- break;
case PP_OD_FEATURE_GFXCLK_FMAX:
- od_min_setting = overdrive_lowerlimits->GfxclkFmax;
- od_max_setting = overdrive_upperlimits->GfxclkFmax;
+ od_min_setting = overdrive_lowerlimits->GfxclkFoffset;
+ od_max_setting = overdrive_upperlimits->GfxclkFoffset;
break;
case PP_OD_FEATURE_UCLK_FMIN:
od_min_setting = overdrive_lowerlimits->UclkFmin;
@@ -1269,10 +1266,16 @@ static int smu_v14_0_2_print_clk_levels(struct smu_context *smu,
PP_OD_FEATURE_GFXCLK_BIT))
break;
- size += sysfs_emit_at(buf, size, "OD_SCLK:\n");
- size += sysfs_emit_at(buf, size, "0: %uMhz\n1: %uMhz\n",
- od_table->OverDriveTable.GfxclkFmin,
- od_table->OverDriveTable.GfxclkFmax);
+ PPTable_t *pptable = smu->smu_table.driver_pptable;
+ const OverDriveLimits_t * const overdrive_upperlimits =
+ &pptable->SkuTable.OverDriveLimitsBasicMax;
+ const OverDriveLimits_t * const overdrive_lowerlimits =
+ &pptable->SkuTable.OverDriveLimitsBasicMin;
+
+ size += sysfs_emit_at(buf, size, "OD_SCLK_OFFSET:\n");
+ size += sysfs_emit_at(buf, size, "0: %dMhz\n1: %uMhz\n",
+ overdrive_lowerlimits->GfxclkFoffset,
+ overdrive_upperlimits->GfxclkFoffset);
break;
case SMU_OD_MCLK:
@@ -1414,7 +1417,7 @@ static int smu_v14_0_2_print_clk_levels(struct smu_context *smu,
PP_OD_FEATURE_GFXCLK_FMAX,
NULL,
&max_value);
- size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
+ size += sysfs_emit_at(buf, size, "SCLK_OFFSET: %7dMhz %10uMhz\n",
min_value, max_value);
}
@@ -1796,7 +1799,7 @@ static int smu_v14_0_2_set_power_profile_mode(struct smu_context *smu,
DpmActivityMonitorCoeffInt_t *activity_monitor =
&(activity_monitor_external.DpmActivityMonitorCoeffInt);
int workload_type, ret = 0;
-
+ uint32_t current_profile_mode = smu->power_profile_mode;
smu->power_profile_mode = input[size];
if (smu->power_profile_mode >= PP_SMC_POWER_PROFILE_COUNT) {
@@ -1854,6 +1857,11 @@ static int smu_v14_0_2_set_power_profile_mode(struct smu_context *smu,
}
}
+ if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_COMPUTE)
+ smu_v14_0_deep_sleep_control(smu, false);
+ else if (current_profile_mode == PP_SMC_POWER_PROFILE_COMPUTE)
+ smu_v14_0_deep_sleep_control(smu, true);
+
/* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */
workload_type = smu_cmn_to_asic_specific_index(smu,
CMN2ASIC_MAPPING_WORKLOAD,
@@ -2158,7 +2166,7 @@ static ssize_t smu_v14_0_2_get_gpu_metrics(struct smu_context *smu,
gpu_metrics->average_gfx_activity = metrics->AverageGfxActivity;
gpu_metrics->average_umc_activity = metrics->AverageUclkActivity;
- gpu_metrics->average_mm_activity = max(metrics->Vcn0ActivityPercentage,
+ gpu_metrics->average_mm_activity = max(metrics->AverageVcn0ActivityPercentage,
metrics->Vcn1ActivityPercentage);
gpu_metrics->average_socket_power = metrics->AverageSocketPower;
@@ -2217,8 +2225,7 @@ static void smu_v14_0_2_dump_od_table(struct smu_context *smu,
{
struct amdgpu_device *adev = smu->adev;
- dev_dbg(adev->dev, "OD: Gfxclk: (%d, %d)\n", od_table->OverDriveTable.GfxclkFmin,
- od_table->OverDriveTable.GfxclkFmax);
+ dev_dbg(adev->dev, "OD: Gfxclk offset: (%d)\n", od_table->OverDriveTable.GfxclkFoffset);
dev_dbg(adev->dev, "OD: Uclk: (%d, %d)\n", od_table->OverDriveTable.UclkFmin,
od_table->OverDriveTable.UclkFmax);
}
@@ -2309,10 +2316,8 @@ static int smu_v14_0_2_set_default_od_settings(struct smu_context *smu)
memcpy(user_od_table,
boot_od_table,
sizeof(OverDriveTableExternal_t));
- user_od_table->OverDriveTable.GfxclkFmin =
- user_od_table_bak.OverDriveTable.GfxclkFmin;
- user_od_table->OverDriveTable.GfxclkFmax =
- user_od_table_bak.OverDriveTable.GfxclkFmax;
+ user_od_table->OverDriveTable.GfxclkFoffset =
+ user_od_table_bak.OverDriveTable.GfxclkFoffset;
user_od_table->OverDriveTable.UclkFmin =
user_od_table_bak.OverDriveTable.UclkFmin;
user_od_table->OverDriveTable.UclkFmax =
@@ -2441,22 +2446,6 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu,
}
switch (input[i]) {
- case 0:
- smu_v14_0_2_get_od_setting_limits(smu,
- PP_OD_FEATURE_GFXCLK_FMIN,
- &minimum,
- &maximum);
- if (input[i + 1] < minimum ||
- input[i + 1] > maximum) {
- dev_info(adev->dev, "GfxclkFmin (%ld) must be within [%u, %u]!\n",
- input[i + 1], minimum, maximum);
- return -EINVAL;
- }
-
- od_table->OverDriveTable.GfxclkFmin = input[i + 1];
- od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_GFXCLK_BIT;
- break;
-
case 1:
smu_v14_0_2_get_od_setting_limits(smu,
PP_OD_FEATURE_GFXCLK_FMAX,
@@ -2469,7 +2458,7 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu,
return -EINVAL;
}
- od_table->OverDriveTable.GfxclkFmax = input[i + 1];
+ od_table->OverDriveTable.GfxclkFoffset = input[i + 1];
od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_GFXCLK_BIT;
break;
@@ -2480,13 +2469,6 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu,
}
}
- if (od_table->OverDriveTable.GfxclkFmin > od_table->OverDriveTable.GfxclkFmax) {
- dev_err(adev->dev,
- "Invalid setting: GfxclkFmin(%u) is bigger than GfxclkFmax(%u)\n",
- (uint32_t)od_table->OverDriveTable.GfxclkFmin,
- (uint32_t)od_table->OverDriveTable.GfxclkFmax);
- return -EINVAL;
- }
break;
case PP_OD_EDIT_MCLK_VDDC_TABLE:
diff --git a/drivers/gpu/drm/bridge/aux-bridge.c b/drivers/gpu/drm/bridge/aux-bridge.c
index b29980f..295e9d0 100644
--- a/drivers/gpu/drm/bridge/aux-bridge.c
+++ b/drivers/gpu/drm/bridge/aux-bridge.c
@@ -58,9 +58,10 @@ int drm_aux_bridge_register(struct device *parent)
adev->id = ret;
adev->name = "aux_bridge";
adev->dev.parent = parent;
- adev->dev.of_node = of_node_get(parent->of_node);
adev->dev.release = drm_aux_bridge_release;
+ device_set_of_node_from_dev(&adev->dev, parent);
+
ret = auxiliary_device_init(adev);
if (ret) {
ida_free(&drm_aux_bridge_ida, adev->id);
diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
index 290e253..f3afdab 100644
--- a/drivers/gpu/drm/bridge/tc358767.c
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -2391,6 +2391,7 @@ static int tc_probe_bridge_endpoint(struct tc_data *tc)
if (tc->pre_emphasis[0] < 0 || tc->pre_emphasis[0] > 2 ||
tc->pre_emphasis[1] < 0 || tc->pre_emphasis[1] > 2) {
dev_err(dev, "Incorrect Pre-Emphasis setting, use either 0=0dB 1=3.5dB 2=6dB\n");
+ of_node_put(node);
return -EINVAL;
}
}
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index faa253b..14ac351 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -123,9 +123,8 @@
config DRM_I915_GVT_KVMGT
tristate "Enable KVM host support Intel GVT-g graphics virtualization"
depends on DRM_I915
- depends on X86
+ depends on KVM_X86
depends on 64BIT
- depends on KVM
depends on VFIO
select DRM_I915_GVT
select KVM_EXTERNAL_WRITE_TRACKING
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 0a9ffc1..10fd460 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -890,7 +890,7 @@ void xe_device_l2_flush(struct xe_device *xe)
spin_lock(>->global_invl_lock);
xe_mmio_write32(gt, XE2_GLOBAL_INVAL, 0x1);
- if (xe_mmio_wait32(gt, XE2_GLOBAL_INVAL, 0x1, 0x0, 150, NULL, true))
+ if (xe_mmio_wait32(gt, XE2_GLOBAL_INVAL, 0x1, 0x0, 500, NULL, true))
xe_gt_err_once(gt, "Global invalidation timeout\n");
spin_unlock(>->global_invl_lock);
diff --git a/drivers/gpu/drm/xe/xe_force_wake.c b/drivers/gpu/drm/xe/xe_force_wake.c
index b263fff..7d9fc48 100644
--- a/drivers/gpu/drm/xe/xe_force_wake.c
+++ b/drivers/gpu/drm/xe/xe_force_wake.c
@@ -115,9 +115,15 @@ static int __domain_wait(struct xe_gt *gt, struct xe_force_wake_domain *domain,
XE_FORCE_WAKE_ACK_TIMEOUT_MS * USEC_PER_MSEC,
&value, true);
if (ret)
- xe_gt_notice(gt, "Force wake domain %d failed to ack %s (%pe) reg[%#x] = %#x\n",
- domain->id, str_wake_sleep(wake), ERR_PTR(ret),
- domain->reg_ack.addr, value);
+ xe_gt_err(gt, "Force wake domain %d failed to ack %s (%pe) reg[%#x] = %#x\n",
+ domain->id, str_wake_sleep(wake), ERR_PTR(ret),
+ domain->reg_ack.addr, value);
+ if (value == ~0) {
+ xe_gt_err(gt,
+ "Force wake domain %d: %s. MMIO unreliable (forcewake register returns 0xFFFFFFFF)!\n",
+ domain->id, str_wake_sleep(wake));
+ ret = -EIO;
+ }
return ret;
}
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index d16eb9a..17986bf 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -898,6 +898,24 @@ static int guc_ct_send_recv(struct xe_guc_ct *ct, const u32 *action, u32 len,
ret = wait_event_timeout(ct->g2h_fence_wq, g2h_fence.done, HZ);
/*
+ * Occasionally it is seen that the G2H worker starts running after a delay of more than
+ * a second even after being queued and activated by the Linux workqueue subsystem. This
+ * leads to G2H timeout error. The root cause of issue lies with scheduling latency of
+ * Lunarlake Hybrid CPU. Issue dissappears if we disable Lunarlake atom cores from BIOS
+ * and this is beyond xe kmd.
+ *
+ * TODO: Drop this change once workqueue scheduling delay issue is fixed on LNL Hybrid CPU.
+ */
+ if (!ret) {
+ flush_work(&ct->g2h_worker);
+ if (g2h_fence.done) {
+ xe_gt_warn(gt, "G2H fence %u, action %04x, done\n",
+ g2h_fence.seqno, action[0]);
+ ret = 1;
+ }
+ }
+
+ /*
* Ensure we serialize with completion side to prevent UAF with fence going out of scope on
* the stack, since we have no clue if it will fire after the timeout before we can erase
* from the xa. Also we have some dependent loads and stores below for which we need the
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 8a9254e..d333be9 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1726,8 +1726,13 @@ void xe_guc_submit_stop(struct xe_guc *guc)
mutex_lock(&guc->submission_state.lock);
- xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
+ xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
+ /* Prevent redundant attempts to stop parallel queues */
+ if (q->guc->id != index)
+ continue;
+
guc_exec_queue_stop(guc, q);
+ }
mutex_unlock(&guc->submission_state.lock);
@@ -1765,8 +1770,13 @@ int xe_guc_submit_start(struct xe_guc *guc)
mutex_lock(&guc->submission_state.lock);
atomic_dec(&guc->submission_state.stopped);
- xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
+ xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
+ /* Prevent redundant attempts to start parallel queues */
+ if (q->guc->id != index)
+ continue;
+
guc_exec_queue_start(q);
+ }
mutex_unlock(&guc->submission_state.lock);
wake_up_all(&guc->ct.wq);
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index c6cf227..2e72c06 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -54,8 +54,9 @@ static struct xe_user_fence *user_fence_create(struct xe_device *xe, u64 addr,
{
struct xe_user_fence *ufence;
u64 __user *ptr = u64_to_user_ptr(addr);
+ u64 __maybe_unused prefetch_val;
- if (!access_ok(ptr, sizeof(*ptr)))
+ if (get_user(prefetch_val, ptr))
return ERR_PTR(-EFAULT);
ufence = kzalloc(sizeof(*ufence), GFP_KERNEL);
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 8a991b3..92cff3f 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -509,6 +509,7 @@
#define I2C_DEVICE_ID_GOODIX_01E8 0x01e8
#define I2C_DEVICE_ID_GOODIX_01E9 0x01e9
#define I2C_DEVICE_ID_GOODIX_01F0 0x01f0
+#define I2C_DEVICE_ID_GOODIX_0D42 0x0d42
#define USB_VENDOR_ID_GOODTOUCH 0x1aad
#define USB_DEVICE_ID_GOODTOUCH_000f 0x000f
@@ -868,6 +869,7 @@
#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1 0xc539
#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_1 0xc53f
#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_POWERPLAY 0xc53a
+#define USB_DEVICE_ID_LOGITECH_BOLT_RECEIVER 0xc548
#define USB_DEVICE_ID_SPACETRAVELLER 0xc623
#define USB_DEVICE_ID_SPACENAVIGATOR 0xc626
#define USB_DEVICE_ID_DINOVO_DESKTOP 0xc704
diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c
index 3b0c779..f66194f 100644
--- a/drivers/hid/hid-lenovo.c
+++ b/drivers/hid/hid-lenovo.c
@@ -473,6 +473,7 @@ static int lenovo_input_mapping(struct hid_device *hdev,
return lenovo_input_mapping_tp10_ultrabook_kbd(hdev, hi, field,
usage, bit, max);
case USB_DEVICE_ID_LENOVO_X1_TAB:
+ case USB_DEVICE_ID_LENOVO_X1_TAB3:
return lenovo_input_mapping_x1_tab_kbd(hdev, hi, field, usage, bit, max);
default:
return 0;
@@ -583,6 +584,7 @@ static ssize_t attr_fn_lock_store(struct device *dev,
break;
case USB_DEVICE_ID_LENOVO_TP10UBKBD:
case USB_DEVICE_ID_LENOVO_X1_TAB:
+ case USB_DEVICE_ID_LENOVO_X1_TAB3:
ret = lenovo_led_set_tp10ubkbd(hdev, TP10UBKBD_FN_LOCK_LED, value);
if (ret)
return ret;
@@ -776,6 +778,7 @@ static int lenovo_event(struct hid_device *hdev, struct hid_field *field,
return lenovo_event_cptkbd(hdev, field, usage, value);
case USB_DEVICE_ID_LENOVO_TP10UBKBD:
case USB_DEVICE_ID_LENOVO_X1_TAB:
+ case USB_DEVICE_ID_LENOVO_X1_TAB3:
return lenovo_event_tp10ubkbd(hdev, field, usage, value);
default:
return 0;
@@ -1056,6 +1059,7 @@ static int lenovo_led_brightness_set(struct led_classdev *led_cdev,
break;
case USB_DEVICE_ID_LENOVO_TP10UBKBD:
case USB_DEVICE_ID_LENOVO_X1_TAB:
+ case USB_DEVICE_ID_LENOVO_X1_TAB3:
ret = lenovo_led_set_tp10ubkbd(hdev, tp10ubkbd_led[led_nr], value);
break;
}
@@ -1286,6 +1290,7 @@ static int lenovo_probe(struct hid_device *hdev,
break;
case USB_DEVICE_ID_LENOVO_TP10UBKBD:
case USB_DEVICE_ID_LENOVO_X1_TAB:
+ case USB_DEVICE_ID_LENOVO_X1_TAB3:
ret = lenovo_probe_tp10ubkbd(hdev);
break;
default:
@@ -1372,6 +1377,7 @@ static void lenovo_remove(struct hid_device *hdev)
break;
case USB_DEVICE_ID_LENOVO_TP10UBKBD:
case USB_DEVICE_ID_LENOVO_X1_TAB:
+ case USB_DEVICE_ID_LENOVO_X1_TAB3:
lenovo_remove_tp10ubkbd(hdev);
break;
}
@@ -1421,6 +1427,8 @@ static const struct hid_device_id lenovo_devices[] = {
*/
{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB) },
+ { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
+ USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB3) },
{ }
};
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 52004ae7..e936019 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -2146,6 +2146,10 @@ static const struct hid_device_id mt_devices[] = {
HID_DEVICE(BUS_BLUETOOTH, HID_GROUP_MULTITOUCH_WIN_8,
USB_VENDOR_ID_LOGITECH,
USB_DEVICE_ID_LOGITECH_CASA_TOUCHPAD) },
+ { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU,
+ HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8,
+ USB_VENDOR_ID_LOGITECH,
+ USB_DEVICE_ID_LOGITECH_BOLT_RECEIVER) },
/* MosArt panels */
{ .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE,
diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c
index be5d342..43664a2 100644
--- a/drivers/hid/i2c-hid/i2c-hid-core.c
+++ b/drivers/hid/i2c-hid/i2c-hid-core.c
@@ -50,6 +50,7 @@
#define I2C_HID_QUIRK_BAD_INPUT_SIZE BIT(3)
#define I2C_HID_QUIRK_NO_WAKEUP_AFTER_RESET BIT(4)
#define I2C_HID_QUIRK_NO_SLEEP_ON_SUSPEND BIT(5)
+#define I2C_HID_QUIRK_DELAY_WAKEUP_AFTER_RESUME BIT(6)
/* Command opcodes */
#define I2C_HID_OPCODE_RESET 0x01
@@ -140,6 +141,8 @@ static const struct i2c_hid_quirks {
{ USB_VENDOR_ID_ELAN, HID_ANY_ID,
I2C_HID_QUIRK_NO_WAKEUP_AFTER_RESET |
I2C_HID_QUIRK_BOGUS_IRQ },
+ { I2C_VENDOR_ID_GOODIX, I2C_DEVICE_ID_GOODIX_0D42,
+ I2C_HID_QUIRK_DELAY_WAKEUP_AFTER_RESUME },
{ 0, 0 }
};
@@ -981,6 +984,13 @@ static int i2c_hid_core_resume(struct i2c_hid *ihid)
return -ENXIO;
}
+ /* On Goodix 27c6:0d42 wait extra time before device wakeup.
+ * It's not clear why but if we send wakeup too early, the device will
+ * never trigger input interrupts.
+ */
+ if (ihid->quirks & I2C_HID_QUIRK_DELAY_WAKEUP_AFTER_RESUME)
+ msleep(1500);
+
/* Instead of resetting device, simply powers the device on. This
* solves "incomplete reports" on Raydium devices 2386:3118 and
* 2386:4B33 and fixes various SIS touchscreens no longer sending
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index 2ebcb2d..7ad8356 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -1532,9 +1532,11 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res,
u32 tbl_indx;
int rc;
+ spin_lock_bh(&rcfw->tbl_lock);
tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw);
rcfw->qp_tbl[tbl_indx].qp_id = BNXT_QPLIB_QP_ID_INVALID;
rcfw->qp_tbl[tbl_indx].qp_handle = NULL;
+ spin_unlock_bh(&rcfw->tbl_lock);
bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req,
CMDQ_BASE_OPCODE_DESTROY_QP,
@@ -1545,8 +1547,10 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res,
sizeof(resp), 0);
rc = bnxt_qplib_rcfw_send_message(rcfw, &msg);
if (rc) {
+ spin_lock_bh(&rcfw->tbl_lock);
rcfw->qp_tbl[tbl_indx].qp_id = qp->id;
rcfw->qp_tbl[tbl_indx].qp_handle = qp;
+ spin_unlock_bh(&rcfw->tbl_lock);
return rc;
}
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
index 7294221..e82bd37 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -290,7 +290,6 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw,
struct bnxt_qplib_hwq *hwq;
u32 sw_prod, cmdq_prod;
struct pci_dev *pdev;
- unsigned long flags;
u16 cookie;
u8 *preq;
@@ -301,7 +300,7 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw,
/* Cmdq are in 16-byte units, each request can consume 1 or more
* cmdqe
*/
- spin_lock_irqsave(&hwq->lock, flags);
+ spin_lock_bh(&hwq->lock);
required_slots = bnxt_qplib_get_cmd_slots(msg->req);
free_slots = HWQ_FREE_SLOTS(hwq);
cookie = cmdq->seq_num & RCFW_MAX_COOKIE_VALUE;
@@ -311,7 +310,7 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw,
dev_info_ratelimited(&pdev->dev,
"CMDQ is full req/free %d/%d!",
required_slots, free_slots);
- spin_unlock_irqrestore(&hwq->lock, flags);
+ spin_unlock_bh(&hwq->lock);
return -EAGAIN;
}
if (msg->block)
@@ -367,7 +366,7 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw,
wmb();
writel(cmdq_prod, cmdq->cmdq_mbox.prod);
writel(RCFW_CMDQ_TRIG_VAL, cmdq->cmdq_mbox.db);
- spin_unlock_irqrestore(&hwq->lock, flags);
+ spin_unlock_bh(&hwq->lock);
/* Return the CREQ response pointer */
return 0;
}
@@ -486,7 +485,6 @@ static int __bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw,
{
struct creq_qp_event *evnt = (struct creq_qp_event *)msg->resp;
struct bnxt_qplib_crsqe *crsqe;
- unsigned long flags;
u16 cookie;
int rc;
u8 opcode;
@@ -512,12 +510,12 @@ static int __bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw,
rc = __poll_for_resp(rcfw, cookie);
if (rc) {
- spin_lock_irqsave(&rcfw->cmdq.hwq.lock, flags);
+ spin_lock_bh(&rcfw->cmdq.hwq.lock);
crsqe = &rcfw->crsqe_tbl[cookie];
crsqe->is_waiter_alive = false;
if (rc == -ENODEV)
set_bit(FIRMWARE_STALL_DETECTED, &rcfw->cmdq.flags);
- spin_unlock_irqrestore(&rcfw->cmdq.hwq.lock, flags);
+ spin_unlock_bh(&rcfw->cmdq.hwq.lock);
return -ETIMEDOUT;
}
@@ -628,7 +626,6 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw,
u16 cookie, blocked = 0;
bool is_waiter_alive;
struct pci_dev *pdev;
- unsigned long flags;
u32 wait_cmds = 0;
int rc = 0;
@@ -637,17 +634,21 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw,
case CREQ_QP_EVENT_EVENT_QP_ERROR_NOTIFICATION:
err_event = (struct creq_qp_error_notification *)qp_event;
qp_id = le32_to_cpu(err_event->xid);
+ spin_lock(&rcfw->tbl_lock);
tbl_indx = map_qp_id_to_tbl_indx(qp_id, rcfw);
qp = rcfw->qp_tbl[tbl_indx].qp_handle;
+ if (!qp) {
+ spin_unlock(&rcfw->tbl_lock);
+ break;
+ }
+ bnxt_qplib_mark_qp_error(qp);
+ rc = rcfw->creq.aeq_handler(rcfw, qp_event, qp);
+ spin_unlock(&rcfw->tbl_lock);
dev_dbg(&pdev->dev, "Received QP error notification\n");
dev_dbg(&pdev->dev,
"qpid 0x%x, req_err=0x%x, resp_err=0x%x\n",
qp_id, err_event->req_err_state_reason,
err_event->res_err_state_reason);
- if (!qp)
- break;
- bnxt_qplib_mark_qp_error(qp);
- rc = rcfw->creq.aeq_handler(rcfw, qp_event, qp);
break;
default:
/*
@@ -659,8 +660,7 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw,
*
*/
- spin_lock_irqsave_nested(&hwq->lock, flags,
- SINGLE_DEPTH_NESTING);
+ spin_lock_nested(&hwq->lock, SINGLE_DEPTH_NESTING);
cookie = le16_to_cpu(qp_event->cookie);
blocked = cookie & RCFW_CMD_IS_BLOCKING;
cookie &= RCFW_MAX_COOKIE_VALUE;
@@ -672,7 +672,7 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw,
dev_info(&pdev->dev,
"rcfw timedout: cookie = %#x, free_slots = %d",
cookie, crsqe->free_slots);
- spin_unlock_irqrestore(&hwq->lock, flags);
+ spin_unlock(&hwq->lock);
return rc;
}
@@ -720,7 +720,7 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw,
__destroy_timedout_ah(rcfw,
(struct creq_create_ah_resp *)
qp_event);
- spin_unlock_irqrestore(&hwq->lock, flags);
+ spin_unlock(&hwq->lock);
}
*num_wait += wait_cmds;
return rc;
@@ -734,12 +734,11 @@ static void bnxt_qplib_service_creq(struct tasklet_struct *t)
u32 type, budget = CREQ_ENTRY_POLL_BUDGET;
struct bnxt_qplib_hwq *hwq = &creq->hwq;
struct creq_base *creqe;
- unsigned long flags;
u32 num_wakeup = 0;
u32 hw_polled = 0;
/* Service the CREQ until budget is over */
- spin_lock_irqsave(&hwq->lock, flags);
+ spin_lock_bh(&hwq->lock);
while (budget > 0) {
creqe = bnxt_qplib_get_qe(hwq, hwq->cons, NULL);
if (!CREQ_CMP_VALID(creqe, creq->creq_db.dbinfo.flags))
@@ -782,7 +781,7 @@ static void bnxt_qplib_service_creq(struct tasklet_struct *t)
if (hw_polled)
bnxt_qplib_ring_nq_db(&creq->creq_db.dbinfo,
rcfw->res->cctx, true);
- spin_unlock_irqrestore(&hwq->lock, flags);
+ spin_unlock_bh(&hwq->lock);
if (num_wakeup)
wake_up_nr(&rcfw->cmdq.waitq, num_wakeup);
}
@@ -978,6 +977,7 @@ int bnxt_qplib_alloc_rcfw_channel(struct bnxt_qplib_res *res,
GFP_KERNEL);
if (!rcfw->qp_tbl)
goto fail;
+ spin_lock_init(&rcfw->tbl_lock);
rcfw->max_timeout = res->cctx->hwrm_cmd_max_timeout;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
index 45996e6..07779ae 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
@@ -224,6 +224,8 @@ struct bnxt_qplib_rcfw {
struct bnxt_qplib_crsqe *crsqe_tbl;
int qp_tbl_size;
struct bnxt_qplib_qp_node *qp_tbl;
+ /* To synchronize the qp-handle hash table */
+ spinlock_t tbl_lock;
u64 oos_prev;
u32 init_oos_stats;
u32 cmdq_depth;
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 10a4c738..e059f92 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -473,6 +473,7 @@ static const struct ib_device_ops c4iw_dev_ops = {
.fill_res_cq_entry = c4iw_fill_res_cq_entry,
.fill_res_cm_id_entry = c4iw_fill_res_cm_id_entry,
.fill_res_mr_entry = c4iw_fill_res_mr_entry,
+ .fill_res_qp_entry = c4iw_fill_res_qp_entry,
.get_dev_fw_str = get_dev_fw_str,
.get_dma_mr = c4iw_get_dma_mr,
.get_hw_stats = c4iw_get_mib,
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index e39b1a1..10ce3b4 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -4268,14 +4268,14 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
MLX5_SET(qpc, qpc, retry_count, attr->retry_cnt);
if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC && attr->max_rd_atomic)
- MLX5_SET(qpc, qpc, log_sra_max, ilog2(attr->max_rd_atomic));
+ MLX5_SET(qpc, qpc, log_sra_max, fls(attr->max_rd_atomic - 1));
if (attr_mask & IB_QP_SQ_PSN)
MLX5_SET(qpc, qpc, next_send_psn, attr->sq_psn);
if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC && attr->max_dest_rd_atomic)
MLX5_SET(qpc, qpc, log_rra_max,
- ilog2(attr->max_dest_rd_atomic));
+ fls(attr->max_dest_rd_atomic - 1));
if (attr_mask & (IB_QP_ACCESS_FLAGS | IB_QP_MAX_DEST_RD_ATOMIC)) {
err = set_qpc_atomic_flags(qp, attr, attr_mask, qpc);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 179ee4a..67108c3 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -546,6 +546,26 @@ static int mddev_set_closing_and_sync_blockdev(struct mddev *mddev, int opener_n
return 0;
}
+/*
+ * The only difference from bio_chain_endio() is that the current
+ * bi_status of bio does not affect the bi_status of parent.
+ */
+static void md_end_flush(struct bio *bio)
+{
+ struct bio *parent = bio->bi_private;
+
+ /*
+ * If any flush io error before the power failure,
+ * disk data may be lost.
+ */
+ if (bio->bi_status)
+ pr_err("md: %pg flush io error %d\n", bio->bi_bdev,
+ blk_status_to_errno(bio->bi_status));
+
+ bio_put(bio);
+ bio_endio(parent);
+}
+
bool md_flush_request(struct mddev *mddev, struct bio *bio)
{
struct md_rdev *rdev;
@@ -565,7 +585,9 @@ bool md_flush_request(struct mddev *mddev, struct bio *bio)
new = bio_alloc_bioset(rdev->bdev, 0,
REQ_OP_WRITE | REQ_PREFLUSH, GFP_NOIO,
&mddev->bio_set);
- bio_chain(new, bio);
+ new->bi_private = bio;
+ new->bi_end_io = md_end_flush;
+ bio_inc_remaining(bio);
submit_bio(new);
}
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index f3bf1116..862b1fb 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -4061,9 +4061,12 @@ static int raid10_run(struct mddev *mddev)
}
if (!mddev_is_dm(conf->mddev)) {
- ret = raid10_set_queue_limits(mddev);
- if (ret)
+ int err = raid10_set_queue_limits(mddev);
+
+ if (err) {
+ ret = err;
goto out_free_conf;
+ }
}
/* need to check that every block has at least one working mirror */
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 4e8710c..5290f5a 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -2733,26 +2733,27 @@ static u32 ksz_get_phy_flags(struct dsa_switch *ds, int port)
return MICREL_KSZ8_P1_ERRATA;
break;
case KSZ8567_CHIP_ID:
+ /* KSZ8567R Errata DS80000752C Module 4 */
+ case KSZ8765_CHIP_ID:
+ case KSZ8794_CHIP_ID:
+ case KSZ8795_CHIP_ID:
+ /* KSZ879x/KSZ877x/KSZ876x Errata DS80000687C Module 2 */
case KSZ9477_CHIP_ID:
+ /* KSZ9477S Errata DS80000754A Module 4 */
case KSZ9567_CHIP_ID:
+ /* KSZ9567S Errata DS80000756A Module 4 */
case KSZ9896_CHIP_ID:
+ /* KSZ9896C Errata DS80000757A Module 3 */
case KSZ9897_CHIP_ID:
- /* KSZ9477 Errata DS80000754C
- *
- * Module 4: Energy Efficient Ethernet (EEE) feature select must
- * be manually disabled
+ /* KSZ9897R Errata DS80000758C Module 4 */
+ /* Energy Efficient Ethernet (EEE) feature select must be manually disabled
* The EEE feature is enabled by default, but it is not fully
* operational. It must be manually disabled through register
* controls. If not disabled, the PHY ports can auto-negotiate
* to enable EEE, and this feature can cause link drops when
* linked to another device supporting EEE.
*
- * The same item appears in the errata for the KSZ9567, KSZ9896,
- * and KSZ9897.
- *
- * A similar item appears in the errata for the KSZ8567, but
- * provides an alternative workaround. For now, use the simple
- * workaround of disabling the EEE feature for this device too.
+ * The same item appears in the errata for all switches above.
*/
return MICREL_NO_EEE;
}
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index c34caf9..a546822 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -206,6 +206,7 @@ struct mv88e6xxx_gpio_ops;
struct mv88e6xxx_avb_ops;
struct mv88e6xxx_ptp_ops;
struct mv88e6xxx_pcs_ops;
+struct mv88e6xxx_cc_coeffs;
struct mv88e6xxx_irq {
u16 masked;
@@ -408,6 +409,7 @@ struct mv88e6xxx_chip {
struct cyclecounter tstamp_cc;
struct timecounter tstamp_tc;
struct delayed_work overflow_work;
+ const struct mv88e6xxx_cc_coeffs *cc_coeffs;
struct ptp_clock *ptp_clock;
struct ptp_clock_info ptp_clock_info;
@@ -731,10 +733,6 @@ struct mv88e6xxx_ptp_ops {
int arr1_sts_reg;
int dep_sts_reg;
u32 rx_filters;
- u32 cc_shift;
- u32 cc_mult;
- u32 cc_mult_num;
- u32 cc_mult_dem;
};
struct mv88e6xxx_pcs_ops {
diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index 5394a8c..04053fd 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -1713,6 +1713,7 @@ int mv88e6393x_port_set_policy(struct mv88e6xxx_chip *chip, int port,
ptr = shift / 8;
shift %= 8;
mask >>= ptr * 8;
+ ptr <<= 8;
err = mv88e6393x_port_policy_read(chip, port, ptr, ®);
if (err)
diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c
index 56391e0..aed4a4b 100644
--- a/drivers/net/dsa/mv88e6xxx/ptp.c
+++ b/drivers/net/dsa/mv88e6xxx/ptp.c
@@ -18,6 +18,13 @@
#define MV88E6XXX_MAX_ADJ_PPB 1000000
+struct mv88e6xxx_cc_coeffs {
+ u32 cc_shift;
+ u32 cc_mult;
+ u32 cc_mult_num;
+ u32 cc_mult_dem;
+};
+
/* Family MV88E6250:
* Raw timestamps are in units of 10-ns clock periods.
*
@@ -25,22 +32,43 @@
* simplifies to
* clkadj = scaled_ppm * 2^7 / 5^5
*/
-#define MV88E6250_CC_SHIFT 28
-#define MV88E6250_CC_MULT (10 << MV88E6250_CC_SHIFT)
-#define MV88E6250_CC_MULT_NUM (1 << 7)
-#define MV88E6250_CC_MULT_DEM 3125ULL
+#define MV88E6XXX_CC_10NS_SHIFT 28
+static const struct mv88e6xxx_cc_coeffs mv88e6xxx_cc_10ns_coeffs = {
+ .cc_shift = MV88E6XXX_CC_10NS_SHIFT,
+ .cc_mult = 10 << MV88E6XXX_CC_10NS_SHIFT,
+ .cc_mult_num = 1 << 7,
+ .cc_mult_dem = 3125ULL,
+};
-/* Other families:
+/* Other families except MV88E6393X in internal clock mode:
* Raw timestamps are in units of 8-ns clock periods.
*
* clkadj = scaled_ppm * 8*2^28 / (10^6 * 2^16)
* simplifies to
* clkadj = scaled_ppm * 2^9 / 5^6
*/
-#define MV88E6XXX_CC_SHIFT 28
-#define MV88E6XXX_CC_MULT (8 << MV88E6XXX_CC_SHIFT)
-#define MV88E6XXX_CC_MULT_NUM (1 << 9)
-#define MV88E6XXX_CC_MULT_DEM 15625ULL
+#define MV88E6XXX_CC_8NS_SHIFT 28
+static const struct mv88e6xxx_cc_coeffs mv88e6xxx_cc_8ns_coeffs = {
+ .cc_shift = MV88E6XXX_CC_8NS_SHIFT,
+ .cc_mult = 8 << MV88E6XXX_CC_8NS_SHIFT,
+ .cc_mult_num = 1 << 9,
+ .cc_mult_dem = 15625ULL
+};
+
+/* Family MV88E6393X using internal clock:
+ * Raw timestamps are in units of 4-ns clock periods.
+ *
+ * clkadj = scaled_ppm * 4*2^28 / (10^6 * 2^16)
+ * simplifies to
+ * clkadj = scaled_ppm * 2^8 / 5^6
+ */
+#define MV88E6XXX_CC_4NS_SHIFT 28
+static const struct mv88e6xxx_cc_coeffs mv88e6xxx_cc_4ns_coeffs = {
+ .cc_shift = MV88E6XXX_CC_4NS_SHIFT,
+ .cc_mult = 4 << MV88E6XXX_CC_4NS_SHIFT,
+ .cc_mult_num = 1 << 8,
+ .cc_mult_dem = 15625ULL
+};
#define TAI_EVENT_WORK_INTERVAL msecs_to_jiffies(100)
@@ -83,6 +111,33 @@ static int mv88e6352_set_gpio_func(struct mv88e6xxx_chip *chip, int pin,
return chip->info->ops->gpio_ops->set_pctl(chip, pin, func);
}
+static const struct mv88e6xxx_cc_coeffs *
+mv88e6xxx_cc_coeff_get(struct mv88e6xxx_chip *chip)
+{
+ u16 period_ps;
+ int err;
+
+ err = mv88e6xxx_tai_read(chip, MV88E6XXX_TAI_CLOCK_PERIOD, &period_ps, 1);
+ if (err) {
+ dev_err(chip->dev, "failed to read cycle counter period: %d\n",
+ err);
+ return ERR_PTR(err);
+ }
+
+ switch (period_ps) {
+ case 4000:
+ return &mv88e6xxx_cc_4ns_coeffs;
+ case 8000:
+ return &mv88e6xxx_cc_8ns_coeffs;
+ case 10000:
+ return &mv88e6xxx_cc_10ns_coeffs;
+ default:
+ dev_err(chip->dev, "unexpected cycle counter period of %u ps\n",
+ period_ps);
+ return ERR_PTR(-ENODEV);
+ }
+}
+
static u64 mv88e6352_ptp_clock_read(const struct cyclecounter *cc)
{
struct mv88e6xxx_chip *chip = cc_to_chip(cc);
@@ -204,7 +259,6 @@ static void mv88e6352_tai_event_work(struct work_struct *ugly)
static int mv88e6xxx_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
{
struct mv88e6xxx_chip *chip = ptp_to_chip(ptp);
- const struct mv88e6xxx_ptp_ops *ptp_ops = chip->info->ops->ptp_ops;
int neg_adj = 0;
u32 diff, mult;
u64 adj;
@@ -214,10 +268,10 @@ static int mv88e6xxx_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
scaled_ppm = -scaled_ppm;
}
- mult = ptp_ops->cc_mult;
- adj = ptp_ops->cc_mult_num;
+ mult = chip->cc_coeffs->cc_mult;
+ adj = chip->cc_coeffs->cc_mult_num;
adj *= scaled_ppm;
- diff = div_u64(adj, ptp_ops->cc_mult_dem);
+ diff = div_u64(adj, chip->cc_coeffs->cc_mult_dem);
mv88e6xxx_reg_lock(chip);
@@ -364,10 +418,6 @@ const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops = {
(1 << HWTSTAMP_FILTER_PTP_V2_EVENT) |
(1 << HWTSTAMP_FILTER_PTP_V2_SYNC) |
(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ),
- .cc_shift = MV88E6XXX_CC_SHIFT,
- .cc_mult = MV88E6XXX_CC_MULT,
- .cc_mult_num = MV88E6XXX_CC_MULT_NUM,
- .cc_mult_dem = MV88E6XXX_CC_MULT_DEM,
};
const struct mv88e6xxx_ptp_ops mv88e6250_ptp_ops = {
@@ -391,10 +441,6 @@ const struct mv88e6xxx_ptp_ops mv88e6250_ptp_ops = {
(1 << HWTSTAMP_FILTER_PTP_V2_EVENT) |
(1 << HWTSTAMP_FILTER_PTP_V2_SYNC) |
(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ),
- .cc_shift = MV88E6250_CC_SHIFT,
- .cc_mult = MV88E6250_CC_MULT,
- .cc_mult_num = MV88E6250_CC_MULT_NUM,
- .cc_mult_dem = MV88E6250_CC_MULT_DEM,
};
const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = {
@@ -418,10 +464,6 @@ const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = {
(1 << HWTSTAMP_FILTER_PTP_V2_EVENT) |
(1 << HWTSTAMP_FILTER_PTP_V2_SYNC) |
(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ),
- .cc_shift = MV88E6XXX_CC_SHIFT,
- .cc_mult = MV88E6XXX_CC_MULT,
- .cc_mult_num = MV88E6XXX_CC_MULT_NUM,
- .cc_mult_dem = MV88E6XXX_CC_MULT_DEM,
};
const struct mv88e6xxx_ptp_ops mv88e6390_ptp_ops = {
@@ -446,10 +488,6 @@ const struct mv88e6xxx_ptp_ops mv88e6390_ptp_ops = {
(1 << HWTSTAMP_FILTER_PTP_V2_EVENT) |
(1 << HWTSTAMP_FILTER_PTP_V2_SYNC) |
(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ),
- .cc_shift = MV88E6XXX_CC_SHIFT,
- .cc_mult = MV88E6XXX_CC_MULT,
- .cc_mult_num = MV88E6XXX_CC_MULT_NUM,
- .cc_mult_dem = MV88E6XXX_CC_MULT_DEM,
};
static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc)
@@ -462,10 +500,10 @@ static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc)
return 0;
}
-/* With a 125MHz input clock, the 32-bit timestamp counter overflows in ~34.3
+/* With a 250MHz input clock, the 32-bit timestamp counter overflows in ~17.2
* seconds; this task forces periodic reads so that we don't miss any.
*/
-#define MV88E6XXX_TAI_OVERFLOW_PERIOD (HZ * 16)
+#define MV88E6XXX_TAI_OVERFLOW_PERIOD (HZ * 8)
static void mv88e6xxx_ptp_overflow_check(struct work_struct *work)
{
struct delayed_work *dw = to_delayed_work(work);
@@ -484,11 +522,15 @@ int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip)
int i;
/* Set up the cycle counter */
+ chip->cc_coeffs = mv88e6xxx_cc_coeff_get(chip);
+ if (IS_ERR(chip->cc_coeffs))
+ return PTR_ERR(chip->cc_coeffs);
+
memset(&chip->tstamp_cc, 0, sizeof(chip->tstamp_cc));
chip->tstamp_cc.read = mv88e6xxx_ptp_clock_read;
chip->tstamp_cc.mask = CYCLECOUNTER_MASK(32);
- chip->tstamp_cc.mult = ptp_ops->cc_mult;
- chip->tstamp_cc.shift = ptp_ops->cc_shift;
+ chip->tstamp_cc.mult = chip->cc_coeffs->cc_mult;
+ chip->tstamp_cc.shift = chip->cc_coeffs->cc_shift;
timecounter_init(&chip->tstamp_tc, &chip->tstamp_cc,
ktime_to_ns(ktime_get_real()));
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6e422e2..99d025b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2254,10 +2254,11 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
if (!bnxt_get_rx_ts_p5(bp, &ts, cmpl_ts)) {
struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+ unsigned long flags;
- spin_lock_bh(&ptp->ptp_lock);
+ spin_lock_irqsave(&ptp->ptp_lock, flags);
ns = timecounter_cyc2time(&ptp->tc, ts);
- spin_unlock_bh(&ptp->ptp_lock);
+ spin_unlock_irqrestore(&ptp->ptp_lock, flags);
memset(skb_hwtstamps(skb), 0,
sizeof(*skb_hwtstamps(skb)));
skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(ns);
@@ -2757,17 +2758,18 @@ static int bnxt_async_event_process(struct bnxt *bp,
case ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE:
if (BNXT_PTP_USE_RTC(bp)) {
struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+ unsigned long flags;
u64 ns;
if (!ptp)
goto async_event_process_exit;
- spin_lock_bh(&ptp->ptp_lock);
+ spin_lock_irqsave(&ptp->ptp_lock, flags);
bnxt_ptp_update_current_time(bp);
ns = (((u64)BNXT_EVENT_PHC_RTC_UPDATE(data1) <<
BNXT_PHC_BITS) | ptp->current_time);
bnxt_ptp_rtc_timecounter_init(ptp, ns);
- spin_unlock_bh(&ptp->ptp_lock);
+ spin_unlock_irqrestore(&ptp->ptp_lock, flags);
}
break;
}
@@ -13494,9 +13496,11 @@ static void bnxt_force_fw_reset(struct bnxt *bp)
return;
if (ptp) {
- spin_lock_bh(&ptp->ptp_lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&ptp->ptp_lock, flags);
set_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
- spin_unlock_bh(&ptp->ptp_lock);
+ spin_unlock_irqrestore(&ptp->ptp_lock, flags);
} else {
set_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
}
@@ -13561,9 +13565,11 @@ void bnxt_fw_reset(struct bnxt *bp)
int n = 0, tmo;
if (ptp) {
- spin_lock_bh(&ptp->ptp_lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&ptp->ptp_lock, flags);
set_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
- spin_unlock_bh(&ptp->ptp_lock);
+ spin_unlock_irqrestore(&ptp->ptp_lock, flags);
} else {
set_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index 37d4242..fa514be8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -62,13 +62,14 @@ static int bnxt_ptp_settime(struct ptp_clock_info *ptp_info,
struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg,
ptp_info);
u64 ns = timespec64_to_ns(ts);
+ unsigned long flags;
if (BNXT_PTP_USE_RTC(ptp->bp))
return bnxt_ptp_cfg_settime(ptp->bp, ns);
- spin_lock_bh(&ptp->ptp_lock);
+ spin_lock_irqsave(&ptp->ptp_lock, flags);
timecounter_init(&ptp->tc, &ptp->cc, ns);
- spin_unlock_bh(&ptp->ptp_lock);
+ spin_unlock_irqrestore(&ptp->ptp_lock, flags);
return 0;
}
@@ -100,13 +101,14 @@ static int bnxt_refclk_read(struct bnxt *bp, struct ptp_system_timestamp *sts,
static void bnxt_ptp_get_current_time(struct bnxt *bp)
{
struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+ unsigned long flags;
if (!ptp)
return;
- spin_lock_bh(&ptp->ptp_lock);
+ spin_lock_irqsave(&ptp->ptp_lock, flags);
WRITE_ONCE(ptp->old_time, ptp->current_time);
bnxt_refclk_read(bp, NULL, &ptp->current_time);
- spin_unlock_bh(&ptp->ptp_lock);
+ spin_unlock_irqrestore(&ptp->ptp_lock, flags);
}
static int bnxt_hwrm_port_ts_query(struct bnxt *bp, u32 flags, u64 *ts,
@@ -149,17 +151,18 @@ static int bnxt_ptp_gettimex(struct ptp_clock_info *ptp_info,
{
struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg,
ptp_info);
+ unsigned long flags;
u64 ns, cycles;
int rc;
- spin_lock_bh(&ptp->ptp_lock);
+ spin_lock_irqsave(&ptp->ptp_lock, flags);
rc = bnxt_refclk_read(ptp->bp, sts, &cycles);
if (rc) {
- spin_unlock_bh(&ptp->ptp_lock);
+ spin_unlock_irqrestore(&ptp->ptp_lock, flags);
return rc;
}
ns = timecounter_cyc2time(&ptp->tc, cycles);
- spin_unlock_bh(&ptp->ptp_lock);
+ spin_unlock_irqrestore(&ptp->ptp_lock, flags);
*ts = ns_to_timespec64(ns);
return 0;
@@ -177,6 +180,7 @@ void bnxt_ptp_update_current_time(struct bnxt *bp)
static int bnxt_ptp_adjphc(struct bnxt_ptp_cfg *ptp, s64 delta)
{
struct hwrm_port_mac_cfg_input *req;
+ unsigned long flags;
int rc;
rc = hwrm_req_init(ptp->bp, req, HWRM_PORT_MAC_CFG);
@@ -190,9 +194,9 @@ static int bnxt_ptp_adjphc(struct bnxt_ptp_cfg *ptp, s64 delta)
if (rc) {
netdev_err(ptp->bp->dev, "ptp adjphc failed. rc = %x\n", rc);
} else {
- spin_lock_bh(&ptp->ptp_lock);
+ spin_lock_irqsave(&ptp->ptp_lock, flags);
bnxt_ptp_update_current_time(ptp->bp);
- spin_unlock_bh(&ptp->ptp_lock);
+ spin_unlock_irqrestore(&ptp->ptp_lock, flags);
}
return rc;
@@ -202,13 +206,14 @@ static int bnxt_ptp_adjtime(struct ptp_clock_info *ptp_info, s64 delta)
{
struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg,
ptp_info);
+ unsigned long flags;
if (BNXT_PTP_USE_RTC(ptp->bp))
return bnxt_ptp_adjphc(ptp, delta);
- spin_lock_bh(&ptp->ptp_lock);
+ spin_lock_irqsave(&ptp->ptp_lock, flags);
timecounter_adjtime(&ptp->tc, delta);
- spin_unlock_bh(&ptp->ptp_lock);
+ spin_unlock_irqrestore(&ptp->ptp_lock, flags);
return 0;
}
@@ -236,14 +241,15 @@ static int bnxt_ptp_adjfine(struct ptp_clock_info *ptp_info, long scaled_ppm)
struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg,
ptp_info);
struct bnxt *bp = ptp->bp;
+ unsigned long flags;
if (!BNXT_MH(bp))
return bnxt_ptp_adjfine_rtc(bp, scaled_ppm);
- spin_lock_bh(&ptp->ptp_lock);
+ spin_lock_irqsave(&ptp->ptp_lock, flags);
timecounter_read(&ptp->tc);
ptp->cc.mult = adjust_by_scaled_ppm(ptp->cmult, scaled_ppm);
- spin_unlock_bh(&ptp->ptp_lock);
+ spin_unlock_irqrestore(&ptp->ptp_lock, flags);
return 0;
}
@@ -251,12 +257,13 @@ void bnxt_ptp_pps_event(struct bnxt *bp, u32 data1, u32 data2)
{
struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
struct ptp_clock_event event;
+ unsigned long flags;
u64 ns, pps_ts;
pps_ts = EVENT_PPS_TS(data2, data1);
- spin_lock_bh(&ptp->ptp_lock);
+ spin_lock_irqsave(&ptp->ptp_lock, flags);
ns = timecounter_cyc2time(&ptp->tc, pps_ts);
- spin_unlock_bh(&ptp->ptp_lock);
+ spin_unlock_irqrestore(&ptp->ptp_lock, flags);
switch (EVENT_DATA2_PPS_EVENT_TYPE(data2)) {
case ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_INTERNAL:
@@ -393,16 +400,17 @@ static int bnxt_get_target_cycles(struct bnxt_ptp_cfg *ptp, u64 target_ns,
{
u64 cycles_now;
u64 nsec_now, nsec_delta;
+ unsigned long flags;
int rc;
- spin_lock_bh(&ptp->ptp_lock);
+ spin_lock_irqsave(&ptp->ptp_lock, flags);
rc = bnxt_refclk_read(ptp->bp, NULL, &cycles_now);
if (rc) {
- spin_unlock_bh(&ptp->ptp_lock);
+ spin_unlock_irqrestore(&ptp->ptp_lock, flags);
return rc;
}
nsec_now = timecounter_cyc2time(&ptp->tc, cycles_now);
- spin_unlock_bh(&ptp->ptp_lock);
+ spin_unlock_irqrestore(&ptp->ptp_lock, flags);
nsec_delta = target_ns - nsec_now;
*cycles_delta = div64_u64(nsec_delta << ptp->cc.shift, ptp->cc.mult);
@@ -689,6 +697,7 @@ static int bnxt_stamp_tx_skb(struct bnxt *bp, int slot)
struct skb_shared_hwtstamps timestamp;
struct bnxt_ptp_tx_req *txts_req;
unsigned long now = jiffies;
+ unsigned long flags;
u64 ts = 0, ns = 0;
u32 tmo = 0;
int rc;
@@ -702,9 +711,9 @@ static int bnxt_stamp_tx_skb(struct bnxt *bp, int slot)
tmo, slot);
if (!rc) {
memset(×tamp, 0, sizeof(timestamp));
- spin_lock_bh(&ptp->ptp_lock);
+ spin_lock_irqsave(&ptp->ptp_lock, flags);
ns = timecounter_cyc2time(&ptp->tc, ts);
- spin_unlock_bh(&ptp->ptp_lock);
+ spin_unlock_irqrestore(&ptp->ptp_lock, flags);
timestamp.hwtstamp = ns_to_ktime(ns);
skb_tstamp_tx(txts_req->tx_skb, ×tamp);
ptp->stats.ts_pkts++;
@@ -730,6 +739,7 @@ static long bnxt_ptp_ts_aux_work(struct ptp_clock_info *ptp_info)
unsigned long now = jiffies;
struct bnxt *bp = ptp->bp;
u16 cons = ptp->txts_cons;
+ unsigned long flags;
u32 num_requests;
int rc = 0;
@@ -757,9 +767,9 @@ static long bnxt_ptp_ts_aux_work(struct ptp_clock_info *ptp_info)
bnxt_ptp_get_current_time(bp);
ptp->next_period = now + HZ;
if (time_after_eq(now, ptp->next_overflow_check)) {
- spin_lock_bh(&ptp->ptp_lock);
+ spin_lock_irqsave(&ptp->ptp_lock, flags);
timecounter_read(&ptp->tc);
- spin_unlock_bh(&ptp->ptp_lock);
+ spin_unlock_irqrestore(&ptp->ptp_lock, flags);
ptp->next_overflow_check = now + BNXT_PHC_OVERFLOW_PERIOD;
}
if (rc == -EAGAIN)
@@ -819,6 +829,7 @@ void bnxt_tx_ts_cmp(struct bnxt *bp, struct bnxt_napi *bnapi,
u32 opaque = tscmp->tx_ts_cmp_opaque;
struct bnxt_tx_ring_info *txr;
struct bnxt_sw_tx_bd *tx_buf;
+ unsigned long flags;
u64 ts, ns;
u16 cons;
@@ -833,9 +844,9 @@ void bnxt_tx_ts_cmp(struct bnxt *bp, struct bnxt_napi *bnapi,
le32_to_cpu(tscmp->tx_ts_cmp_flags_type),
le32_to_cpu(tscmp->tx_ts_cmp_errors_v));
} else {
- spin_lock_bh(&ptp->ptp_lock);
+ spin_lock_irqsave(&ptp->ptp_lock, flags);
ns = timecounter_cyc2time(&ptp->tc, ts);
- spin_unlock_bh(&ptp->ptp_lock);
+ spin_unlock_irqrestore(&ptp->ptp_lock, flags);
timestamp.hwtstamp = ns_to_ktime(ns);
skb_tstamp_tx(tx_buf->skb, ×tamp);
}
@@ -975,6 +986,7 @@ void bnxt_ptp_rtc_timecounter_init(struct bnxt_ptp_cfg *ptp, u64 ns)
int bnxt_ptp_init_rtc(struct bnxt *bp, bool phc_cfg)
{
struct timespec64 tsp;
+ unsigned long flags;
u64 ns;
int rc;
@@ -993,9 +1005,9 @@ int bnxt_ptp_init_rtc(struct bnxt *bp, bool phc_cfg)
if (rc)
return rc;
}
- spin_lock_bh(&bp->ptp_cfg->ptp_lock);
+ spin_lock_irqsave(&bp->ptp_cfg->ptp_lock, flags);
bnxt_ptp_rtc_timecounter_init(bp->ptp_cfg, ns);
- spin_unlock_bh(&bp->ptp_cfg->ptp_lock);
+ spin_unlock_irqrestore(&bp->ptp_cfg->ptp_lock, flags);
return 0;
}
@@ -1063,10 +1075,12 @@ int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg)
atomic64_set(&ptp->stats.ts_err, 0);
if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
- spin_lock_bh(&ptp->ptp_lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&ptp->ptp_lock, flags);
bnxt_refclk_read(bp, NULL, &ptp->current_time);
WRITE_ONCE(ptp->old_time, ptp->current_time);
- spin_unlock_bh(&ptp->ptp_lock);
+ spin_unlock_irqrestore(&ptp->ptp_lock, flags);
ptp_schedule_worker(ptp->ptp_clock, 0);
}
ptp->txts_tmo = BNXT_PTP_DFLT_TX_TMO;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
index a9a2f9a..f322466 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
@@ -146,11 +146,13 @@ struct bnxt_ptp_cfg {
};
#if BITS_PER_LONG == 32
-#define BNXT_READ_TIME64(ptp, dst, src) \
-do { \
- spin_lock_bh(&(ptp)->ptp_lock); \
- (dst) = (src); \
- spin_unlock_bh(&(ptp)->ptp_lock); \
+#define BNXT_READ_TIME64(ptp, dst, src) \
+do { \
+ unsigned long flags; \
+ \
+ spin_lock_irqsave(&(ptp)->ptp_lock, flags); \
+ (dst) = (src); \
+ spin_unlock_irqrestore(&(ptp)->ptp_lock, flags); \
} while (0)
#else
#define BNXT_READ_TIME64(ptp, dst, src) \
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index a8596eb..875fe37 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1381,10 +1381,8 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev)
be_get_wrb_params_from_skb(adapter, skb, &wrb_params);
wrb_cnt = be_xmit_enqueue(adapter, txo, skb, &wrb_params);
- if (unlikely(!wrb_cnt)) {
- dev_kfree_skb_any(skb);
- goto drop;
- }
+ if (unlikely(!wrb_cnt))
+ goto drop_skb;
/* if os2bmc is enabled and if the pkt is destined to bmc,
* enqueue the pkt a 2nd time with mgmt bit set.
@@ -1393,7 +1391,7 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev)
BE_WRB_F_SET(wrb_params.features, OS2BMC, 1);
wrb_cnt = be_xmit_enqueue(adapter, txo, skb, &wrb_params);
if (unlikely(!wrb_cnt))
- goto drop;
+ goto drop_skb;
else
skb_get(skb);
}
@@ -1407,6 +1405,8 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev)
be_xmit_flush(adapter, txo);
return NETDEV_TX_OK;
+drop_skb:
+ dev_kfree_skb_any(skb);
drop:
tx_stats(txo)->tx_drv_drops++;
/* Flush the already enqueued tx requests */
diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c
index 9767586b..11da139 100644
--- a/drivers/net/ethernet/freescale/fman/mac.c
+++ b/drivers/net/ethernet/freescale/fman/mac.c
@@ -197,55 +197,67 @@ static int mac_probe(struct platform_device *_of_dev)
err = -EINVAL;
goto _return_of_node_put;
}
+ mac_dev->fman_dev = &of_dev->dev;
/* Get the FMan cell-index */
err = of_property_read_u32(dev_node, "cell-index", &val);
if (err) {
dev_err(dev, "failed to read cell-index for %pOF\n", dev_node);
err = -EINVAL;
- goto _return_of_node_put;
+ goto _return_dev_put;
}
/* cell-index 0 => FMan id 1 */
fman_id = (u8)(val + 1);
- priv->fman = fman_bind(&of_dev->dev);
+ priv->fman = fman_bind(mac_dev->fman_dev);
if (!priv->fman) {
dev_err(dev, "fman_bind(%pOF) failed\n", dev_node);
err = -ENODEV;
- goto _return_of_node_put;
+ goto _return_dev_put;
}
+ /* Two references have been taken in of_find_device_by_node()
+ * and fman_bind(). Release one of them here. The second one
+ * will be released in mac_remove().
+ */
+ put_device(mac_dev->fman_dev);
of_node_put(dev_node);
+ dev_node = NULL;
/* Get the address of the memory mapped registers */
mac_dev->res = platform_get_mem_or_io(_of_dev, 0);
if (!mac_dev->res) {
dev_err(dev, "could not get registers\n");
- return -EINVAL;
+ err = -EINVAL;
+ goto _return_dev_put;
}
err = devm_request_resource(dev, fman_get_mem_region(priv->fman),
mac_dev->res);
if (err) {
dev_err_probe(dev, err, "could not request resource\n");
- return err;
+ goto _return_dev_put;
}
mac_dev->vaddr = devm_ioremap(dev, mac_dev->res->start,
resource_size(mac_dev->res));
if (!mac_dev->vaddr) {
dev_err(dev, "devm_ioremap() failed\n");
- return -EIO;
+ err = -EIO;
+ goto _return_dev_put;
}
- if (!of_device_is_available(mac_node))
- return -ENODEV;
+ if (!of_device_is_available(mac_node)) {
+ err = -ENODEV;
+ goto _return_dev_put;
+ }
/* Get the cell-index */
err = of_property_read_u32(mac_node, "cell-index", &val);
if (err) {
dev_err(dev, "failed to read cell-index for %pOF\n", mac_node);
- return -EINVAL;
+ err = -EINVAL;
+ goto _return_dev_put;
}
priv->cell_index = (u8)val;
@@ -259,22 +271,26 @@ static int mac_probe(struct platform_device *_of_dev)
if (unlikely(nph < 0)) {
dev_err(dev, "of_count_phandle_with_args(%pOF, fsl,fman-ports) failed\n",
mac_node);
- return nph;
+ err = nph;
+ goto _return_dev_put;
}
if (nph != ARRAY_SIZE(mac_dev->port)) {
dev_err(dev, "Not supported number of fman-ports handles of mac node %pOF from device tree\n",
mac_node);
- return -EINVAL;
+ err = -EINVAL;
+ goto _return_dev_put;
}
- for (i = 0; i < ARRAY_SIZE(mac_dev->port); i++) {
+ /* PORT_NUM determines the size of the port array */
+ for (i = 0; i < PORT_NUM; i++) {
/* Find the port node */
dev_node = of_parse_phandle(mac_node, "fsl,fman-ports", i);
if (!dev_node) {
dev_err(dev, "of_parse_phandle(%pOF, fsl,fman-ports) failed\n",
mac_node);
- return -EINVAL;
+ err = -EINVAL;
+ goto _return_dev_arr_put;
}
of_dev = of_find_device_by_node(dev_node);
@@ -282,17 +298,24 @@ static int mac_probe(struct platform_device *_of_dev)
dev_err(dev, "of_find_device_by_node(%pOF) failed\n",
dev_node);
err = -EINVAL;
- goto _return_of_node_put;
+ goto _return_dev_arr_put;
}
+ mac_dev->fman_port_devs[i] = &of_dev->dev;
- mac_dev->port[i] = fman_port_bind(&of_dev->dev);
+ mac_dev->port[i] = fman_port_bind(mac_dev->fman_port_devs[i]);
if (!mac_dev->port[i]) {
dev_err(dev, "dev_get_drvdata(%pOF) failed\n",
dev_node);
err = -EINVAL;
- goto _return_of_node_put;
+ goto _return_dev_arr_put;
}
+ /* Two references have been taken in of_find_device_by_node()
+ * and fman_port_bind(). Release one of them here. The second
+ * one will be released in mac_remove().
+ */
+ put_device(mac_dev->fman_port_devs[i]);
of_node_put(dev_node);
+ dev_node = NULL;
}
/* Get the PHY connection type */
@@ -312,7 +335,7 @@ static int mac_probe(struct platform_device *_of_dev)
err = init(mac_dev, mac_node, ¶ms);
if (err < 0)
- return err;
+ goto _return_dev_arr_put;
if (!is_zero_ether_addr(mac_dev->addr))
dev_info(dev, "FMan MAC address: %pM\n", mac_dev->addr);
@@ -327,6 +350,12 @@ static int mac_probe(struct platform_device *_of_dev)
return err;
+_return_dev_arr_put:
+ /* mac_dev is kzalloc'ed */
+ for (i = 0; i < PORT_NUM; i++)
+ put_device(mac_dev->fman_port_devs[i]);
+_return_dev_put:
+ put_device(mac_dev->fman_dev);
_return_of_node_put:
of_node_put(dev_node);
return err;
@@ -335,6 +364,11 @@ static int mac_probe(struct platform_device *_of_dev)
static void mac_remove(struct platform_device *pdev)
{
struct mac_device *mac_dev = platform_get_drvdata(pdev);
+ int i;
+
+ for (i = 0; i < PORT_NUM; i++)
+ put_device(mac_dev->fman_port_devs[i]);
+ put_device(mac_dev->fman_dev);
platform_device_unregister(mac_dev->priv->eth_dev);
}
diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h
index fe74791..8b5b43d 100644
--- a/drivers/net/ethernet/freescale/fman/mac.h
+++ b/drivers/net/ethernet/freescale/fman/mac.h
@@ -19,12 +19,13 @@
struct fman_mac;
struct mac_priv_s;
+#define PORT_NUM 2
struct mac_device {
void __iomem *vaddr;
struct device *dev;
struct resource *res;
u8 addr[ETH_ALEN];
- struct fman_port *port[2];
+ struct fman_port *port[PORT_NUM];
struct phylink *phylink;
struct phylink_config phylink_config;
phy_interface_t phy_if;
@@ -52,6 +53,9 @@ struct mac_device {
struct fman_mac *fman_mac;
struct mac_priv_s *priv;
+
+ struct device *fman_dev;
+ struct device *fman_port_devs[PORT_NUM];
};
static inline struct mac_device
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 807eb3b..841e5af 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -1293,8 +1293,10 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer,
/* save the buffer addr until the last read operation */
*save_buf = read_buf;
+ }
- /* get data ready for the first time to read */
+ /* get data ready for the first time to read */
+ if (!*ppos) {
ret = hns3_dbg_read_cmd(dbg_data, hns3_dbg_cmd[index].cmd,
read_buf, hns3_dbg_cmd[index].buf_len);
if (ret)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 4cbc4d0..b09f0cc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -11,6 +11,7 @@
#include <linux/irq.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
+#include <linux/iommu.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/skbuff.h>
@@ -380,6 +381,24 @@ static const struct hns3_rx_ptype hns3_rx_ptype_tbl[] = {
#define HNS3_INVALID_PTYPE \
ARRAY_SIZE(hns3_rx_ptype_tbl)
+static void hns3_dma_map_sync(struct device *dev, unsigned long iova)
+{
+ struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+ struct iommu_iotlb_gather iotlb_gather;
+ size_t granule;
+
+ if (!domain || !iommu_is_dma_domain(domain))
+ return;
+
+ granule = 1 << __ffs(domain->pgsize_bitmap);
+ iova = ALIGN_DOWN(iova, granule);
+ iotlb_gather.start = iova;
+ iotlb_gather.end = iova + granule - 1;
+ iotlb_gather.pgsize = granule;
+
+ iommu_iotlb_sync(domain, &iotlb_gather);
+}
+
static irqreturn_t hns3_irq_handle(int irq, void *vector)
{
struct hns3_enet_tqp_vector *tqp_vector = vector;
@@ -1032,6 +1051,8 @@ static bool hns3_can_use_tx_sgl(struct hns3_enet_ring *ring,
static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring)
{
u32 alloc_size = ring->tqp->handle->kinfo.tx_spare_buf_size;
+ struct net_device *netdev = ring_to_netdev(ring);
+ struct hns3_nic_priv *priv = netdev_priv(netdev);
struct hns3_tx_spare *tx_spare;
struct page *page;
dma_addr_t dma;
@@ -1073,6 +1094,7 @@ static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring)
tx_spare->buf = page_address(page);
tx_spare->len = PAGE_SIZE << order;
ring->tx_spare = tx_spare;
+ ring->tx_copybreak = priv->tx_copybreak;
return;
dma_mapping_error:
@@ -1724,7 +1746,9 @@ static int hns3_map_and_fill_desc(struct hns3_enet_ring *ring, void *priv,
unsigned int type)
{
struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use];
+ struct hnae3_handle *handle = ring->tqp->handle;
struct device *dev = ring_to_dev(ring);
+ struct hnae3_ae_dev *ae_dev;
unsigned int size;
dma_addr_t dma;
@@ -1756,6 +1780,13 @@ static int hns3_map_and_fill_desc(struct hns3_enet_ring *ring, void *priv,
return -ENOMEM;
}
+ /* Add a SYNC command to sync io-pgtale to avoid errors in pgtable
+ * prefetch
+ */
+ ae_dev = hns3_get_ae_dev(handle);
+ if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3)
+ hns3_dma_map_sync(dev, dma);
+
desc_cb->priv = priv;
desc_cb->length = size;
desc_cb->dma = dma;
@@ -2452,7 +2483,6 @@ static int hns3_nic_set_features(struct net_device *netdev,
return ret;
}
- netdev->features = features;
return 0;
}
@@ -4868,6 +4898,30 @@ static void hns3_nic_dealloc_vector_data(struct hns3_nic_priv *priv)
devm_kfree(&pdev->dev, priv->tqp_vector);
}
+static void hns3_update_tx_spare_buf_config(struct hns3_nic_priv *priv)
+{
+#define HNS3_MIN_SPARE_BUF_SIZE (2 * 1024 * 1024)
+#define HNS3_MAX_PACKET_SIZE (64 * 1024)
+
+ struct iommu_domain *domain = iommu_get_domain_for_dev(priv->dev);
+ struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(priv->ae_handle);
+ struct hnae3_handle *handle = priv->ae_handle;
+
+ if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3)
+ return;
+
+ if (!(domain && iommu_is_dma_domain(domain)))
+ return;
+
+ priv->min_tx_copybreak = HNS3_MAX_PACKET_SIZE;
+ priv->min_tx_spare_buf_size = HNS3_MIN_SPARE_BUF_SIZE;
+
+ if (priv->tx_copybreak < priv->min_tx_copybreak)
+ priv->tx_copybreak = priv->min_tx_copybreak;
+ if (handle->kinfo.tx_spare_buf_size < priv->min_tx_spare_buf_size)
+ handle->kinfo.tx_spare_buf_size = priv->min_tx_spare_buf_size;
+}
+
static void hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv,
unsigned int ring_type)
{
@@ -5101,6 +5155,7 @@ int hns3_init_all_ring(struct hns3_nic_priv *priv)
int i, j;
int ret;
+ hns3_update_tx_spare_buf_config(priv);
for (i = 0; i < ring_num; i++) {
ret = hns3_alloc_ring_memory(&priv->ring[i]);
if (ret) {
@@ -5305,6 +5360,8 @@ static int hns3_client_init(struct hnae3_handle *handle)
priv->ae_handle = handle;
priv->tx_timeout_count = 0;
priv->max_non_tso_bd_num = ae_dev->dev_specs.max_non_tso_bd_num;
+ priv->min_tx_copybreak = 0;
+ priv->min_tx_spare_buf_size = 0;
set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
handle->msg_enable = netif_msg_init(debug, DEFAULT_MSG_LEVEL);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index d36c4ed..caf7a4d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -596,6 +596,8 @@ struct hns3_nic_priv {
struct hns3_enet_coalesce rx_coal;
u32 tx_copybreak;
u32 rx_copybreak;
+ u32 min_tx_copybreak;
+ u32 min_tx_spare_buf_size;
};
union l3_hdr_info {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index b1e9883..97eaeec 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -1933,6 +1933,31 @@ static int hns3_set_tx_spare_buf_size(struct net_device *netdev,
return ret;
}
+static int hns3_check_tx_copybreak(struct net_device *netdev, u32 copybreak)
+{
+ struct hns3_nic_priv *priv = netdev_priv(netdev);
+
+ if (copybreak < priv->min_tx_copybreak) {
+ netdev_err(netdev, "tx copybreak %u should be no less than %u!\n",
+ copybreak, priv->min_tx_copybreak);
+ return -EINVAL;
+ }
+ return 0;
+}
+
+static int hns3_check_tx_spare_buf_size(struct net_device *netdev, u32 buf_size)
+{
+ struct hns3_nic_priv *priv = netdev_priv(netdev);
+
+ if (buf_size < priv->min_tx_spare_buf_size) {
+ netdev_err(netdev,
+ "tx spare buf size %u should be no less than %u!\n",
+ buf_size, priv->min_tx_spare_buf_size);
+ return -EINVAL;
+ }
+ return 0;
+}
+
static int hns3_set_tunable(struct net_device *netdev,
const struct ethtool_tunable *tuna,
const void *data)
@@ -1949,6 +1974,10 @@ static int hns3_set_tunable(struct net_device *netdev,
switch (tuna->id) {
case ETHTOOL_TX_COPYBREAK:
+ ret = hns3_check_tx_copybreak(netdev, *(u32 *)data);
+ if (ret)
+ return ret;
+
priv->tx_copybreak = *(u32 *)data;
for (i = 0; i < h->kinfo.num_tqps; i++)
@@ -1963,6 +1992,10 @@ static int hns3_set_tunable(struct net_device *netdev,
break;
case ETHTOOL_TX_COPYBREAK_BUF_SIZE:
+ ret = hns3_check_tx_spare_buf_size(netdev, *(u32 *)data);
+ if (ret)
+ return ret;
+
old_tx_spare_buf_size = h->kinfo.tx_spare_buf_size;
new_tx_spare_buf_size = *(u32 *)data;
netdev_info(netdev, "request to set tx spare buf size from %u to %u\n",
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index bd86efd..728f477 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -6,6 +6,7 @@
#include <linux/etherdevice.h>
#include <linux/init.h>
#include <linux/interrupt.h>
+#include <linux/irq.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/netdevice.h>
@@ -3584,6 +3585,17 @@ static int hclge_set_vf_link_state(struct hnae3_handle *handle, int vf,
return ret;
}
+static void hclge_set_reset_pending(struct hclge_dev *hdev,
+ enum hnae3_reset_type reset_type)
+{
+ /* When an incorrect reset type is executed, the get_reset_level
+ * function generates the HNAE3_NONE_RESET flag. As a result, this
+ * type do not need to pending.
+ */
+ if (reset_type != HNAE3_NONE_RESET)
+ set_bit(reset_type, &hdev->reset_pending);
+}
+
static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
{
u32 cmdq_src_reg, msix_src_reg, hw_err_src_reg;
@@ -3604,7 +3616,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
*/
if (BIT(HCLGE_VECTOR0_IMPRESET_INT_B) & msix_src_reg) {
dev_info(&hdev->pdev->dev, "IMP reset interrupt\n");
- set_bit(HNAE3_IMP_RESET, &hdev->reset_pending);
+ hclge_set_reset_pending(hdev, HNAE3_IMP_RESET);
set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state);
*clearval = BIT(HCLGE_VECTOR0_IMPRESET_INT_B);
hdev->rst_stats.imp_rst_cnt++;
@@ -3614,7 +3626,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
if (BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B) & msix_src_reg) {
dev_info(&hdev->pdev->dev, "global reset interrupt\n");
set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state);
- set_bit(HNAE3_GLOBAL_RESET, &hdev->reset_pending);
+ hclge_set_reset_pending(hdev, HNAE3_GLOBAL_RESET);
*clearval = BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B);
hdev->rst_stats.global_rst_cnt++;
return HCLGE_VECTOR0_EVENT_RST;
@@ -3769,7 +3781,7 @@ static int hclge_misc_irq_init(struct hclge_dev *hdev)
snprintf(hdev->misc_vector.name, HNAE3_INT_NAME_LEN, "%s-misc-%s",
HCLGE_NAME, pci_name(hdev->pdev));
ret = request_irq(hdev->misc_vector.vector_irq, hclge_misc_irq_handle,
- 0, hdev->misc_vector.name, hdev);
+ IRQ_NOAUTOEN, hdev->misc_vector.name, hdev);
if (ret) {
hclge_free_vector(hdev, 0);
dev_err(&hdev->pdev->dev, "request misc irq(%d) fail\n",
@@ -4062,7 +4074,7 @@ static void hclge_do_reset(struct hclge_dev *hdev)
case HNAE3_FUNC_RESET:
dev_info(&pdev->dev, "PF reset requested\n");
/* schedule again to check later */
- set_bit(HNAE3_FUNC_RESET, &hdev->reset_pending);
+ hclge_set_reset_pending(hdev, HNAE3_FUNC_RESET);
hclge_reset_task_schedule(hdev);
break;
default:
@@ -4096,6 +4108,8 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hnae3_ae_dev *ae_dev,
clear_bit(HNAE3_FLR_RESET, addr);
}
+ clear_bit(HNAE3_NONE_RESET, addr);
+
if (hdev->reset_type != HNAE3_NONE_RESET &&
rst_level < hdev->reset_type)
return HNAE3_NONE_RESET;
@@ -4237,7 +4251,7 @@ static bool hclge_reset_err_handle(struct hclge_dev *hdev)
return false;
} else if (hdev->rst_stats.reset_fail_cnt < MAX_RESET_FAIL_CNT) {
hdev->rst_stats.reset_fail_cnt++;
- set_bit(hdev->reset_type, &hdev->reset_pending);
+ hclge_set_reset_pending(hdev, hdev->reset_type);
dev_info(&hdev->pdev->dev,
"re-schedule reset task(%u)\n",
hdev->rst_stats.reset_fail_cnt);
@@ -4480,8 +4494,20 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
static void hclge_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
enum hnae3_reset_type rst_type)
{
+#define HCLGE_SUPPORT_RESET_TYPE \
+ (BIT(HNAE3_FLR_RESET) | BIT(HNAE3_FUNC_RESET) | \
+ BIT(HNAE3_GLOBAL_RESET) | BIT(HNAE3_IMP_RESET))
+
struct hclge_dev *hdev = ae_dev->priv;
+ if (!(BIT(rst_type) & HCLGE_SUPPORT_RESET_TYPE)) {
+ /* To prevent reset triggered by hclge_reset_event */
+ set_bit(HNAE3_NONE_RESET, &hdev->default_reset_request);
+ dev_warn(&hdev->pdev->dev, "unsupported reset type %d\n",
+ rst_type);
+ return;
+ }
+
set_bit(rst_type, &hdev->default_reset_request);
}
@@ -11891,9 +11917,6 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
hclge_init_rxd_adv_layout(hdev);
- /* Enable MISC vector(vector0) */
- hclge_enable_vector(&hdev->misc_vector, true);
-
ret = hclge_init_wol(hdev);
if (ret)
dev_warn(&pdev->dev,
@@ -11906,6 +11929,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
hclge_state_init(hdev);
hdev->last_reset_time = jiffies;
+ /* Enable MISC vector(vector0) */
+ enable_irq(hdev->misc_vector.vector_irq);
+ hclge_enable_vector(&hdev->misc_vector, true);
+
dev_info(&hdev->pdev->dev, "%s driver initialization finished.\n",
HCLGE_DRIVER_NAME);
@@ -12311,7 +12338,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
/* Disable MISC vector(vector0) */
hclge_enable_vector(&hdev->misc_vector, false);
- synchronize_irq(hdev->misc_vector.vector_irq);
+ disable_irq(hdev->misc_vector.vector_irq);
/* Disable all hw interrupts */
hclge_config_mac_tnl_int(hdev, false);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
index 5505cae..bab16c2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
@@ -58,6 +58,9 @@ bool hclge_ptp_set_tx_info(struct hnae3_handle *handle, struct sk_buff *skb)
struct hclge_dev *hdev = vport->back;
struct hclge_ptp *ptp = hdev->ptp;
+ if (!ptp)
+ return false;
+
if (!test_bit(HCLGE_PTP_FLAG_TX_EN, &ptp->flags) ||
test_and_set_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state)) {
ptp->tx_skipped++;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c
index 43c1c18..8c05719 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c
@@ -510,9 +510,9 @@ static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data)
static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data,
struct hnae3_knic_private_info *kinfo)
{
-#define HCLGE_RING_REG_OFFSET 0x200
#define HCLGE_RING_INT_REG_OFFSET 0x4
+ struct hnae3_queue *tqp;
int i, j, reg_num;
int data_num_sum;
u32 *reg = data;
@@ -533,10 +533,11 @@ static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data,
reg_num = ARRAY_SIZE(ring_reg_addr_list);
for (j = 0; j < kinfo->num_tqps; j++) {
reg += hclge_reg_get_tlv(HCLGE_REG_TAG_RING, reg_num, reg);
+ tqp = kinfo->tqp[j];
for (i = 0; i < reg_num; i++)
- *reg++ = hclge_read_dev(&hdev->hw,
- ring_reg_addr_list[i] +
- HCLGE_RING_REG_OFFSET * j);
+ *reg++ = readl_relaxed(tqp->io_base -
+ HCLGE_TQP_REG_OFFSET +
+ ring_reg_addr_list[i]);
}
data_num_sum += (reg_num + HCLGE_REG_TLV_SPACE) * kinfo->num_tqps;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 094a7c7..896f1eb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1395,6 +1395,17 @@ static int hclgevf_notify_roce_client(struct hclgevf_dev *hdev,
return ret;
}
+static void hclgevf_set_reset_pending(struct hclgevf_dev *hdev,
+ enum hnae3_reset_type reset_type)
+{
+ /* When an incorrect reset type is executed, the get_reset_level
+ * function generates the HNAE3_NONE_RESET flag. As a result, this
+ * type do not need to pending.
+ */
+ if (reset_type != HNAE3_NONE_RESET)
+ set_bit(reset_type, &hdev->reset_pending);
+}
+
static int hclgevf_reset_wait(struct hclgevf_dev *hdev)
{
#define HCLGEVF_RESET_WAIT_US 20000
@@ -1544,7 +1555,7 @@ static void hclgevf_reset_err_handle(struct hclgevf_dev *hdev)
hdev->rst_stats.rst_fail_cnt);
if (hdev->rst_stats.rst_fail_cnt < HCLGEVF_RESET_MAX_FAIL_CNT)
- set_bit(hdev->reset_type, &hdev->reset_pending);
+ hclgevf_set_reset_pending(hdev, hdev->reset_type);
if (hclgevf_is_reset_pending(hdev)) {
set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
@@ -1664,6 +1675,8 @@ static enum hnae3_reset_type hclgevf_get_reset_level(unsigned long *addr)
clear_bit(HNAE3_FLR_RESET, addr);
}
+ clear_bit(HNAE3_NONE_RESET, addr);
+
return rst_level;
}
@@ -1673,14 +1686,15 @@ static void hclgevf_reset_event(struct pci_dev *pdev,
struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
struct hclgevf_dev *hdev = ae_dev->priv;
- dev_info(&hdev->pdev->dev, "received reset request from VF enet\n");
-
if (hdev->default_reset_request)
hdev->reset_level =
hclgevf_get_reset_level(&hdev->default_reset_request);
else
hdev->reset_level = HNAE3_VF_FUNC_RESET;
+ dev_info(&hdev->pdev->dev, "received reset request from VF enet, reset level is %d\n",
+ hdev->reset_level);
+
/* reset of this VF requested */
set_bit(HCLGEVF_RESET_REQUESTED, &hdev->reset_state);
hclgevf_reset_task_schedule(hdev);
@@ -1691,8 +1705,20 @@ static void hclgevf_reset_event(struct pci_dev *pdev,
static void hclgevf_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
enum hnae3_reset_type rst_type)
{
+#define HCLGEVF_SUPPORT_RESET_TYPE \
+ (BIT(HNAE3_VF_RESET) | BIT(HNAE3_VF_FUNC_RESET) | \
+ BIT(HNAE3_VF_PF_FUNC_RESET) | BIT(HNAE3_VF_FULL_RESET) | \
+ BIT(HNAE3_FLR_RESET) | BIT(HNAE3_VF_EXP_RESET))
+
struct hclgevf_dev *hdev = ae_dev->priv;
+ if (!(BIT(rst_type) & HCLGEVF_SUPPORT_RESET_TYPE)) {
+ /* To prevent reset triggered by hclge_reset_event */
+ set_bit(HNAE3_NONE_RESET, &hdev->default_reset_request);
+ dev_info(&hdev->pdev->dev, "unsupported reset type %d\n",
+ rst_type);
+ return;
+ }
set_bit(rst_type, &hdev->default_reset_request);
}
@@ -1849,14 +1875,14 @@ static void hclgevf_reset_service_task(struct hclgevf_dev *hdev)
*/
if (hdev->reset_attempts > HCLGEVF_MAX_RESET_ATTEMPTS_CNT) {
/* prepare for full reset of stack + pcie interface */
- set_bit(HNAE3_VF_FULL_RESET, &hdev->reset_pending);
+ hclgevf_set_reset_pending(hdev, HNAE3_VF_FULL_RESET);
/* "defer" schedule the reset task again */
set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
} else {
hdev->reset_attempts++;
- set_bit(hdev->reset_level, &hdev->reset_pending);
+ hclgevf_set_reset_pending(hdev, hdev->reset_level);
set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
}
hclgevf_reset_task_schedule(hdev);
@@ -1979,7 +2005,7 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev,
rst_ing_reg = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING);
dev_info(&hdev->pdev->dev,
"receive reset interrupt 0x%x!\n", rst_ing_reg);
- set_bit(HNAE3_VF_RESET, &hdev->reset_pending);
+ hclgevf_set_reset_pending(hdev, HNAE3_VF_RESET);
set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state);
*clearval = ~(1U << HCLGEVF_VECTOR0_RST_INT_B);
@@ -2289,6 +2315,7 @@ static void hclgevf_state_init(struct hclgevf_dev *hdev)
clear_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state);
INIT_DELAYED_WORK(&hdev->service_task, hclgevf_service_task);
+ timer_setup(&hdev->reset_timer, hclgevf_reset_timer, 0);
mutex_init(&hdev->mbx_resp.mbx_mutex);
sema_init(&hdev->reset_sem, 1);
@@ -2988,7 +3015,6 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
HCLGEVF_DRIVER_NAME);
hclgevf_task_schedule(hdev, round_jiffies_relative(HZ));
- timer_setup(&hdev->reset_timer, hclgevf_reset_timer, 0);
return 0;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c
index 6db415d..7d9d9db 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c
@@ -123,10 +123,10 @@ int hclgevf_get_regs_len(struct hnae3_handle *handle)
void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version,
void *data)
{
-#define HCLGEVF_RING_REG_OFFSET 0x200
#define HCLGEVF_RING_INT_REG_OFFSET 0x4
struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+ struct hnae3_queue *tqp;
int i, j, reg_um;
u32 *reg = data;
@@ -147,10 +147,11 @@ void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version,
reg_um = ARRAY_SIZE(ring_reg_addr_list);
for (j = 0; j < hdev->num_tqps; j++) {
reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_RING, reg_um, reg);
+ tqp = &hdev->htqp[j].q;
for (i = 0; i < reg_um; i++)
- *reg++ = hclgevf_read_dev(&hdev->hw,
- ring_reg_addr_list[i] +
- HCLGEVF_RING_REG_OFFSET * j);
+ *reg++ = readl_relaxed(tqp->io_base -
+ HCLGEVF_TQP_REG_OFFSET +
+ ring_reg_addr_list[i]);
}
reg_um = ARRAY_SIZE(tqp_intr_reg_addr_list);
diff --git a/drivers/net/ethernet/i825xx/sun3_82586.c b/drivers/net/ethernet/i825xx/sun3_82586.c
index f2d4669..58a3d28 100644
--- a/drivers/net/ethernet/i825xx/sun3_82586.c
+++ b/drivers/net/ethernet/i825xx/sun3_82586.c
@@ -1012,6 +1012,7 @@ sun3_82586_send_packet(struct sk_buff *skb, struct net_device *dev)
if(skb->len > XMIT_BUFF_SIZE)
{
printk("%s: Sorry, max. framelength is %d bytes. The length of your frame is %d bytes.\n",dev->name,XMIT_BUFF_SIZE,skb->len);
+ dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
index 928c8bd..c6779d9 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
@@ -989,5 +989,11 @@ ice_devlink_port_new(struct devlink *devlink,
if (err)
return err;
+ if (!ice_is_eswitch_mode_switchdev(pf)) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "SF ports are only supported in eswitch switchdev mode");
+ return -EOPNOTSUPP;
+ }
+
return ice_alloc_dynamic_port(pf, new_attr, extack, devlink_port);
}
diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c
index 74c0e73..d5ad6d8 100644
--- a/drivers/net/ethernet/intel/ice/ice_dpll.c
+++ b/drivers/net/ethernet/intel/ice/ice_dpll.c
@@ -10,6 +10,7 @@
#define ICE_DPLL_PIN_IDX_INVALID 0xff
#define ICE_DPLL_RCLK_NUM_PER_PF 1
#define ICE_DPLL_PIN_ESYNC_PULSE_HIGH_PERCENT 25
+#define ICE_DPLL_PIN_GEN_RCLK_FREQ 1953125
/**
* enum ice_dpll_pin_type - enumerate ice pin types:
@@ -2064,6 +2065,73 @@ static int ice_dpll_init_worker(struct ice_pf *pf)
}
/**
+ * ice_dpll_init_info_pins_generic - initializes generic pins info
+ * @pf: board private structure
+ * @input: if input pins initialized
+ *
+ * Init information for generic pins, cache them in PF's pins structures.
+ *
+ * Return:
+ * * 0 - success
+ * * negative - init failure reason
+ */
+static int ice_dpll_init_info_pins_generic(struct ice_pf *pf, bool input)
+{
+ struct ice_dpll *de = &pf->dplls.eec, *dp = &pf->dplls.pps;
+ static const char labels[][sizeof("99")] = {
+ "0", "1", "2", "3", "4", "5", "6", "7", "8",
+ "9", "10", "11", "12", "13", "14", "15" };
+ u32 cap = DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE;
+ enum ice_dpll_pin_type pin_type;
+ int i, pin_num, ret = -EINVAL;
+ struct ice_dpll_pin *pins;
+ u32 phase_adj_max;
+
+ if (input) {
+ pin_num = pf->dplls.num_inputs;
+ pins = pf->dplls.inputs;
+ phase_adj_max = pf->dplls.input_phase_adj_max;
+ pin_type = ICE_DPLL_PIN_TYPE_INPUT;
+ cap |= DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE;
+ } else {
+ pin_num = pf->dplls.num_outputs;
+ pins = pf->dplls.outputs;
+ phase_adj_max = pf->dplls.output_phase_adj_max;
+ pin_type = ICE_DPLL_PIN_TYPE_OUTPUT;
+ }
+ if (pin_num > ARRAY_SIZE(labels))
+ return ret;
+
+ for (i = 0; i < pin_num; i++) {
+ pins[i].idx = i;
+ pins[i].prop.board_label = labels[i];
+ pins[i].prop.phase_range.min = phase_adj_max;
+ pins[i].prop.phase_range.max = -phase_adj_max;
+ pins[i].prop.capabilities = cap;
+ pins[i].pf = pf;
+ ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL);
+ if (ret)
+ break;
+ if (input && pins[i].freq == ICE_DPLL_PIN_GEN_RCLK_FREQ)
+ pins[i].prop.type = DPLL_PIN_TYPE_MUX;
+ else
+ pins[i].prop.type = DPLL_PIN_TYPE_EXT;
+ if (!input)
+ continue;
+ ret = ice_aq_get_cgu_ref_prio(&pf->hw, de->dpll_idx, i,
+ &de->input_prio[i]);
+ if (ret)
+ break;
+ ret = ice_aq_get_cgu_ref_prio(&pf->hw, dp->dpll_idx, i,
+ &dp->input_prio[i]);
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
+/**
* ice_dpll_init_info_direct_pins - initializes direct pins info
* @pf: board private structure
* @pin_type: type of pins being initialized
@@ -2101,6 +2169,8 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
default:
return -EINVAL;
}
+ if (num_pins != ice_cgu_get_num_pins(hw, input))
+ return ice_dpll_init_info_pins_generic(pf, input);
for (i = 0; i < num_pins; i++) {
caps = 0;
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 3a33e6b..ec8db83 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -34,7 +34,6 @@ static const struct ice_cgu_pin_desc ice_e810t_sfp_cgu_inputs[] = {
ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common },
{ "GNSS-1PPS", ZL_REF4P, DPLL_PIN_TYPE_GNSS,
ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz },
- { "OCXO", ZL_REF4N, DPLL_PIN_TYPE_INT_OSCILLATOR, 0, },
};
static const struct ice_cgu_pin_desc ice_e810t_qsfp_cgu_inputs[] = {
@@ -52,7 +51,6 @@ static const struct ice_cgu_pin_desc ice_e810t_qsfp_cgu_inputs[] = {
ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common },
{ "GNSS-1PPS", ZL_REF4P, DPLL_PIN_TYPE_GNSS,
ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz },
- { "OCXO", ZL_REF4N, DPLL_PIN_TYPE_INT_OSCILLATOR, },
};
static const struct ice_cgu_pin_desc ice_e810t_sfp_cgu_outputs[] = {
@@ -5965,6 +5963,25 @@ ice_cgu_get_pin_desc(struct ice_hw *hw, bool input, int *size)
}
/**
+ * ice_cgu_get_num_pins - get pin description array size
+ * @hw: pointer to the hw struct
+ * @input: if request is done against input or output pins
+ *
+ * Return: size of pin description array for given hw.
+ */
+int ice_cgu_get_num_pins(struct ice_hw *hw, bool input)
+{
+ const struct ice_cgu_pin_desc *t;
+ int size;
+
+ t = ice_cgu_get_pin_desc(hw, input, &size);
+ if (t)
+ return size;
+
+ return 0;
+}
+
+/**
* ice_cgu_get_pin_type - get pin's type
* @hw: pointer to the hw struct
* @pin: pin index
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 0852a34..6cedc1a 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -404,6 +404,7 @@ int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data);
int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data);
int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data);
bool ice_is_pca9575_present(struct ice_hw *hw);
+int ice_cgu_get_num_pins(struct ice_hw *hw, bool input);
enum dpll_pin_type ice_cgu_get_pin_type(struct ice_hw *hw, u8 pin, bool input);
struct dpll_pin_frequency *
ice_cgu_get_pin_freq_supp(struct ice_hw *hw, u8 pin, bool input, u8 *num);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index f1d08816..b83df5f 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -907,7 +907,7 @@ static int igb_request_msix(struct igb_adapter *adapter)
int i, err = 0, vector = 0, free_vector = 0;
err = request_irq(adapter->msix_entries[vector].vector,
- igb_msix_other, 0, netdev->name, adapter);
+ igb_msix_other, IRQF_NO_THREAD, netdev->name, adapter);
if (err)
goto err_out;
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
index 4746a6b..8af75cb 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
@@ -337,6 +337,51 @@ static int octep_oq_check_hw_for_pkts(struct octep_device *oct,
}
/**
+ * octep_oq_next_pkt() - Move to the next packet in Rx queue.
+ *
+ * @oq: Octeon Rx queue data structure.
+ * @buff_info: Current packet buffer info.
+ * @read_idx: Current packet index in the ring.
+ * @desc_used: Current packet descriptor number.
+ *
+ * Free the resources associated with a packet.
+ * Increment packet index in the ring and packet descriptor number.
+ */
+static void octep_oq_next_pkt(struct octep_oq *oq,
+ struct octep_rx_buffer *buff_info,
+ u32 *read_idx, u32 *desc_used)
+{
+ dma_unmap_page(oq->dev, oq->desc_ring[*read_idx].buffer_ptr,
+ PAGE_SIZE, DMA_FROM_DEVICE);
+ buff_info->page = NULL;
+ (*read_idx)++;
+ (*desc_used)++;
+ if (*read_idx == oq->max_count)
+ *read_idx = 0;
+}
+
+/**
+ * octep_oq_drop_rx() - Free the resources associated with a packet.
+ *
+ * @oq: Octeon Rx queue data structure.
+ * @buff_info: Current packet buffer info.
+ * @read_idx: Current packet index in the ring.
+ * @desc_used: Current packet descriptor number.
+ *
+ */
+static void octep_oq_drop_rx(struct octep_oq *oq,
+ struct octep_rx_buffer *buff_info,
+ u32 *read_idx, u32 *desc_used)
+{
+ int data_len = buff_info->len - oq->max_single_buffer_size;
+
+ while (data_len > 0) {
+ octep_oq_next_pkt(oq, buff_info, read_idx, desc_used);
+ data_len -= oq->buffer_size;
+ };
+}
+
+/**
* __octep_oq_process_rx() - Process hardware Rx queue and push to stack.
*
* @oct: Octeon device private data structure.
@@ -367,10 +412,7 @@ static int __octep_oq_process_rx(struct octep_device *oct,
desc_used = 0;
for (pkt = 0; pkt < pkts_to_process; pkt++) {
buff_info = (struct octep_rx_buffer *)&oq->buff_info[read_idx];
- dma_unmap_page(oq->dev, oq->desc_ring[read_idx].buffer_ptr,
- PAGE_SIZE, DMA_FROM_DEVICE);
resp_hw = page_address(buff_info->page);
- buff_info->page = NULL;
/* Swap the length field that is in Big-Endian to CPU */
buff_info->len = be64_to_cpu(resp_hw->length);
@@ -394,36 +436,33 @@ static int __octep_oq_process_rx(struct octep_device *oct,
data_offset = OCTEP_OQ_RESP_HW_SIZE;
rx_ol_flags = 0;
}
+
+ octep_oq_next_pkt(oq, buff_info, &read_idx, &desc_used);
+
+ skb = build_skb((void *)resp_hw, PAGE_SIZE);
+ if (!skb) {
+ octep_oq_drop_rx(oq, buff_info,
+ &read_idx, &desc_used);
+ oq->stats.alloc_failures++;
+ continue;
+ }
+ skb_reserve(skb, data_offset);
+
rx_bytes += buff_info->len;
if (buff_info->len <= oq->max_single_buffer_size) {
- skb = build_skb((void *)resp_hw, PAGE_SIZE);
- skb_reserve(skb, data_offset);
skb_put(skb, buff_info->len);
- read_idx++;
- desc_used++;
- if (read_idx == oq->max_count)
- read_idx = 0;
} else {
struct skb_shared_info *shinfo;
u16 data_len;
- skb = build_skb((void *)resp_hw, PAGE_SIZE);
- skb_reserve(skb, data_offset);
/* Head fragment includes response header(s);
* subsequent fragments contains only data.
*/
skb_put(skb, oq->max_single_buffer_size);
- read_idx++;
- desc_used++;
- if (read_idx == oq->max_count)
- read_idx = 0;
-
shinfo = skb_shinfo(skb);
data_len = buff_info->len - oq->max_single_buffer_size;
while (data_len) {
- dma_unmap_page(oq->dev, oq->desc_ring[read_idx].buffer_ptr,
- PAGE_SIZE, DMA_FROM_DEVICE);
buff_info = (struct octep_rx_buffer *)
&oq->buff_info[read_idx];
if (data_len < oq->buffer_size) {
@@ -438,11 +477,8 @@ static int __octep_oq_process_rx(struct octep_device *oct,
buff_info->page, 0,
buff_info->len,
buff_info->len);
- buff_info->page = NULL;
- read_idx++;
- desc_used++;
- if (read_idx == oq->max_count)
- read_idx = 0;
+
+ octep_oq_next_pkt(oq, buff_info, &read_idx, &desc_used);
}
}
diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.h b/drivers/net/ethernet/mediatek/mtk_wed_wo.h
index 87a67fa..c01b1e8 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed_wo.h
+++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.h
@@ -91,8 +91,8 @@ enum mtk_wed_dummy_cr_idx {
#define MT7981_FIRMWARE_WO "mediatek/mt7981_wo.bin"
#define MT7986_FIRMWARE_WO0 "mediatek/mt7986_wo_0.bin"
#define MT7986_FIRMWARE_WO1 "mediatek/mt7986_wo_1.bin"
-#define MT7988_FIRMWARE_WO0 "mediatek/mt7988_wo_0.bin"
-#define MT7988_FIRMWARE_WO1 "mediatek/mt7988_wo_1.bin"
+#define MT7988_FIRMWARE_WO0 "mediatek/mt7988/mt7988_wo_0.bin"
+#define MT7988_FIRMWARE_WO1 "mediatek/mt7988/mt7988_wo_1.bin"
#define MTK_WO_MCU_CFG_LS_BASE 0
#define MTK_WO_MCU_CFG_LS_HW_VER_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x000)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 060e5b9..d6f3745 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -389,15 +389,27 @@ static void mlxsw_pci_wqe_frag_unmap(struct mlxsw_pci *mlxsw_pci, char *wqe,
dma_unmap_single(&pdev->dev, mapaddr, frag_len, direction);
}
-static struct sk_buff *mlxsw_pci_rdq_build_skb(struct page *pages[],
+static struct sk_buff *mlxsw_pci_rdq_build_skb(struct mlxsw_pci_queue *q,
+ struct page *pages[],
u16 byte_count)
{
+ struct mlxsw_pci_queue *cq = q->u.rdq.cq;
unsigned int linear_data_size;
+ struct page_pool *page_pool;
struct sk_buff *skb;
int page_index = 0;
bool linear_only;
void *data;
+ linear_only = byte_count + MLXSW_PCI_RX_BUF_SW_OVERHEAD <= PAGE_SIZE;
+ linear_data_size = linear_only ? byte_count :
+ PAGE_SIZE -
+ MLXSW_PCI_RX_BUF_SW_OVERHEAD;
+
+ page_pool = cq->u.cq.page_pool;
+ page_pool_dma_sync_for_cpu(page_pool, pages[page_index],
+ MLXSW_PCI_SKB_HEADROOM, linear_data_size);
+
data = page_address(pages[page_index]);
net_prefetch(data);
@@ -405,11 +417,6 @@ static struct sk_buff *mlxsw_pci_rdq_build_skb(struct page *pages[],
if (unlikely(!skb))
return ERR_PTR(-ENOMEM);
- linear_only = byte_count + MLXSW_PCI_RX_BUF_SW_OVERHEAD <= PAGE_SIZE;
- linear_data_size = linear_only ? byte_count :
- PAGE_SIZE -
- MLXSW_PCI_RX_BUF_SW_OVERHEAD;
-
skb_reserve(skb, MLXSW_PCI_SKB_HEADROOM);
skb_put(skb, linear_data_size);
@@ -425,6 +432,7 @@ static struct sk_buff *mlxsw_pci_rdq_build_skb(struct page *pages[],
page = pages[page_index];
frag_size = min(byte_count, PAGE_SIZE);
+ page_pool_dma_sync_for_cpu(page_pool, page, 0, frag_size);
skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
page, 0, frag_size, PAGE_SIZE);
byte_count -= frag_size;
@@ -760,7 +768,7 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
if (err)
goto out;
- skb = mlxsw_pci_rdq_build_skb(pages, byte_count);
+ skb = mlxsw_pci_rdq_build_skb(q, pages, byte_count);
if (IS_ERR(skb)) {
dev_err_ratelimited(&pdev->dev, "Failed to build skb for RDQ\n");
mlxsw_pci_rdq_pages_recycle(q, pages, num_sg_entries);
@@ -988,12 +996,13 @@ static int mlxsw_pci_cq_page_pool_init(struct mlxsw_pci_queue *q,
if (cq_type != MLXSW_PCI_CQ_RDQ)
return 0;
- pp_params.flags = PP_FLAG_DMA_MAP;
+ pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
pp_params.pool_size = MLXSW_PCI_WQE_COUNT * mlxsw_pci->num_sg_entries;
pp_params.nid = dev_to_node(&mlxsw_pci->pdev->dev);
pp_params.dev = &mlxsw_pci->pdev->dev;
pp_params.napi = &q->u.cq.napi;
pp_params.dma_dir = DMA_FROM_DEVICE;
+ pp_params.max_len = PAGE_SIZE;
page_pool = page_pool_create(&pp_params);
if (IS_ERR(page_pool))
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
index d761a12..7ea798a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
@@ -481,11 +481,33 @@ mlxsw_sp_ipip_ol_netdev_change_gre6(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_ipip_entry *ipip_entry,
struct netlink_ext_ack *extack)
{
+ u32 new_kvdl_index, old_kvdl_index = ipip_entry->dip_kvdl_index;
+ struct in6_addr old_addr6 = ipip_entry->parms.daddr.addr6;
struct mlxsw_sp_ipip_parms new_parms;
+ int err;
new_parms = mlxsw_sp_ipip_netdev_parms_init_gre6(ipip_entry->ol_dev);
- return mlxsw_sp_ipip_ol_netdev_change_gre(mlxsw_sp, ipip_entry,
- &new_parms, extack);
+
+ err = mlxsw_sp_ipv6_addr_kvdl_index_get(mlxsw_sp,
+ &new_parms.daddr.addr6,
+ &new_kvdl_index);
+ if (err)
+ return err;
+ ipip_entry->dip_kvdl_index = new_kvdl_index;
+
+ err = mlxsw_sp_ipip_ol_netdev_change_gre(mlxsw_sp, ipip_entry,
+ &new_parms, extack);
+ if (err)
+ goto err_change_gre;
+
+ mlxsw_sp_ipv6_addr_put(mlxsw_sp, &old_addr6);
+
+ return 0;
+
+err_change_gre:
+ ipip_entry->dip_kvdl_index = old_kvdl_index;
+ mlxsw_sp_ipv6_addr_put(mlxsw_sp, &new_parms.daddr.addr6);
+ return err;
}
static int
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
index 5b174cb..d94081c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
@@ -16,6 +16,7 @@
#include "spectrum.h"
#include "spectrum_ptp.h"
#include "core.h"
+#include "txheader.h"
#define MLXSW_SP1_PTP_CLOCK_CYCLES_SHIFT 29
#define MLXSW_SP1_PTP_CLOCK_FREQ_KHZ 156257 /* 6.4nSec */
@@ -1684,6 +1685,12 @@ int mlxsw_sp_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
struct sk_buff *skb,
const struct mlxsw_tx_info *tx_info)
{
+ if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) {
+ this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped);
+ dev_kfree_skb_any(skb);
+ return -ENOMEM;
+ }
+
mlxsw_sp_txhdr_construct(skb, tx_info);
return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 800dfb6..7d6d859 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -3197,7 +3197,6 @@ mlxsw_sp_nexthop_sh_counter_get(struct mlxsw_sp *mlxsw_sp,
{
struct mlxsw_sp_nexthop_group *nh_grp = nh->nhgi->nh_grp;
struct mlxsw_sp_nexthop_counter *nhct;
- void *ptr;
int err;
nhct = xa_load(&nh_grp->nhgi->nexthop_counters, nh->id);
@@ -3210,12 +3209,10 @@ mlxsw_sp_nexthop_sh_counter_get(struct mlxsw_sp *mlxsw_sp,
if (IS_ERR(nhct))
return nhct;
- ptr = xa_store(&nh_grp->nhgi->nexthop_counters, nh->id, nhct,
- GFP_KERNEL);
- if (IS_ERR(ptr)) {
- err = PTR_ERR(ptr);
+ err = xa_err(xa_store(&nh_grp->nhgi->nexthop_counters, nh->id, nhct,
+ GFP_KERNEL));
+ if (err)
goto err_store;
- }
return nhct;
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 0cc9baa..713a89b 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4682,7 +4682,9 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
if ((status & 0xffff) == 0xffff || !(status & tp->irq_mask))
return IRQ_NONE;
- if (unlikely(status & SYSErr)) {
+ /* At least RTL8168fp may unexpectedly set the SYSErr bit */
+ if (unlikely(status & SYSErr &&
+ tp->mac_version <= RTL_GIGA_MAC_VER_06)) {
rtl8169_pcierr_interrupt(tp->dev);
goto out;
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index e016535..77b35ab 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -203,8 +203,12 @@ static void _dwmac4_dump_dma_regs(struct stmmac_priv *priv,
readl(ioaddr + DMA_CHAN_TX_CONTROL(dwmac4_addrs, channel));
reg_space[DMA_CHAN_RX_CONTROL(default_addrs, channel) / 4] =
readl(ioaddr + DMA_CHAN_RX_CONTROL(dwmac4_addrs, channel));
+ reg_space[DMA_CHAN_TX_BASE_ADDR_HI(default_addrs, channel) / 4] =
+ readl(ioaddr + DMA_CHAN_TX_BASE_ADDR_HI(dwmac4_addrs, channel));
reg_space[DMA_CHAN_TX_BASE_ADDR(default_addrs, channel) / 4] =
readl(ioaddr + DMA_CHAN_TX_BASE_ADDR(dwmac4_addrs, channel));
+ reg_space[DMA_CHAN_RX_BASE_ADDR_HI(default_addrs, channel) / 4] =
+ readl(ioaddr + DMA_CHAN_RX_BASE_ADDR_HI(dwmac4_addrs, channel));
reg_space[DMA_CHAN_RX_BASE_ADDR(default_addrs, channel) / 4] =
readl(ioaddr + DMA_CHAN_RX_BASE_ADDR(dwmac4_addrs, channel));
reg_space[DMA_CHAN_TX_END_ADDR(default_addrs, channel) / 4] =
@@ -225,8 +229,12 @@ static void _dwmac4_dump_dma_regs(struct stmmac_priv *priv,
readl(ioaddr + DMA_CHAN_CUR_TX_DESC(dwmac4_addrs, channel));
reg_space[DMA_CHAN_CUR_RX_DESC(default_addrs, channel) / 4] =
readl(ioaddr + DMA_CHAN_CUR_RX_DESC(dwmac4_addrs, channel));
+ reg_space[DMA_CHAN_CUR_TX_BUF_ADDR_HI(default_addrs, channel) / 4] =
+ readl(ioaddr + DMA_CHAN_CUR_TX_BUF_ADDR_HI(dwmac4_addrs, channel));
reg_space[DMA_CHAN_CUR_TX_BUF_ADDR(default_addrs, channel) / 4] =
readl(ioaddr + DMA_CHAN_CUR_TX_BUF_ADDR(dwmac4_addrs, channel));
+ reg_space[DMA_CHAN_CUR_RX_BUF_ADDR_HI(default_addrs, channel) / 4] =
+ readl(ioaddr + DMA_CHAN_CUR_RX_BUF_ADDR_HI(dwmac4_addrs, channel));
reg_space[DMA_CHAN_CUR_RX_BUF_ADDR(default_addrs, channel) / 4] =
readl(ioaddr + DMA_CHAN_CUR_RX_BUF_ADDR(dwmac4_addrs, channel));
reg_space[DMA_CHAN_STATUS(default_addrs, channel) / 4] =
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
index 17d9120..4f980dc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
@@ -127,7 +127,9 @@ static inline u32 dma_chanx_base_addr(const struct dwmac4_addrs *addrs,
#define DMA_CHAN_SLOT_CTRL_STATUS(addrs, x) (dma_chanx_base_addr(addrs, x) + 0x3c)
#define DMA_CHAN_CUR_TX_DESC(addrs, x) (dma_chanx_base_addr(addrs, x) + 0x44)
#define DMA_CHAN_CUR_RX_DESC(addrs, x) (dma_chanx_base_addr(addrs, x) + 0x4c)
+#define DMA_CHAN_CUR_TX_BUF_ADDR_HI(addrs, x) (dma_chanx_base_addr(addrs, x) + 0x50)
#define DMA_CHAN_CUR_TX_BUF_ADDR(addrs, x) (dma_chanx_base_addr(addrs, x) + 0x54)
+#define DMA_CHAN_CUR_RX_BUF_ADDR_HI(addrs, x) (dma_chanx_base_addr(addrs, x) + 0x58)
#define DMA_CHAN_CUR_RX_BUF_ADDR(addrs, x) (dma_chanx_base_addr(addrs, x) + 0x5c)
#define DMA_CHAN_STATUS(addrs, x) (dma_chanx_base_addr(addrs, x) + 0x60)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index d3895d7..208dbc6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4304,11 +4304,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
if (dma_mapping_error(priv->device, des))
goto dma_map_err;
- tx_q->tx_skbuff_dma[first_entry].buf = des;
- tx_q->tx_skbuff_dma[first_entry].len = skb_headlen(skb);
- tx_q->tx_skbuff_dma[first_entry].map_as_page = false;
- tx_q->tx_skbuff_dma[first_entry].buf_type = STMMAC_TXBUF_T_SKB;
-
if (priv->dma_cap.addr64 <= 32) {
first->des0 = cpu_to_le32(des);
@@ -4327,6 +4322,23 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0), queue);
+ /* In case two or more DMA transmit descriptors are allocated for this
+ * non-paged SKB data, the DMA buffer address should be saved to
+ * tx_q->tx_skbuff_dma[].buf corresponding to the last descriptor,
+ * and leave the other tx_q->tx_skbuff_dma[].buf as NULL to guarantee
+ * that stmmac_tx_clean() does not unmap the entire DMA buffer too early
+ * since the tail areas of the DMA buffer can be accessed by DMA engine
+ * sooner or later.
+ * By saving the DMA buffer address to tx_q->tx_skbuff_dma[].buf
+ * corresponding to the last descriptor, stmmac_tx_clean() will unmap
+ * this DMA buffer right after the DMA engine completely finishes the
+ * full buffer transmission.
+ */
+ tx_q->tx_skbuff_dma[tx_q->cur_tx].buf = des;
+ tx_q->tx_skbuff_dma[tx_q->cur_tx].len = skb_headlen(skb);
+ tx_q->tx_skbuff_dma[tx_q->cur_tx].map_as_page = false;
+ tx_q->tx_skbuff_dma[tx_q->cur_tx].buf_type = STMMAC_TXBUF_T_SKB;
+
/* Prepare fragments */
for (i = 0; i < nfrags; i++) {
const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index a60bfb1..70f9818 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1702,20 +1702,24 @@ static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[])
return -EINVAL;
if (data[IFLA_GTP_FD0]) {
- u32 fd0 = nla_get_u32(data[IFLA_GTP_FD0]);
+ int fd0 = nla_get_u32(data[IFLA_GTP_FD0]);
- sk0 = gtp_encap_enable_socket(fd0, UDP_ENCAP_GTP0, gtp);
- if (IS_ERR(sk0))
- return PTR_ERR(sk0);
+ if (fd0 >= 0) {
+ sk0 = gtp_encap_enable_socket(fd0, UDP_ENCAP_GTP0, gtp);
+ if (IS_ERR(sk0))
+ return PTR_ERR(sk0);
+ }
}
if (data[IFLA_GTP_FD1]) {
- u32 fd1 = nla_get_u32(data[IFLA_GTP_FD1]);
+ int fd1 = nla_get_u32(data[IFLA_GTP_FD1]);
- sk1u = gtp_encap_enable_socket(fd1, UDP_ENCAP_GTP1U, gtp);
- if (IS_ERR(sk1u)) {
- gtp_encap_disable_sock(sk0);
- return PTR_ERR(sk1u);
+ if (fd1 >= 0) {
+ sk1u = gtp_encap_enable_socket(fd1, UDP_ENCAP_GTP1U, gtp);
+ if (IS_ERR(sk1u)) {
+ gtp_encap_disable_sock(sk0);
+ return PTR_ERR(sk1u);
+ }
}
}
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 153b97f..23180f7 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -2798,6 +2798,31 @@ static struct hv_driver netvsc_drv = {
},
};
+/* Set VF's namespace same as the synthetic NIC */
+static void netvsc_event_set_vf_ns(struct net_device *ndev)
+{
+ struct net_device_context *ndev_ctx = netdev_priv(ndev);
+ struct net_device *vf_netdev;
+ int ret;
+
+ vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
+ if (!vf_netdev)
+ return;
+
+ if (!net_eq(dev_net(ndev), dev_net(vf_netdev))) {
+ ret = dev_change_net_namespace(vf_netdev, dev_net(ndev),
+ "eth%d");
+ if (ret)
+ netdev_err(vf_netdev,
+ "Cannot move to same namespace as %s: %d\n",
+ ndev->name, ret);
+ else
+ netdev_info(vf_netdev,
+ "Moved VF to namespace with: %s\n",
+ ndev->name);
+ }
+}
+
/*
* On Hyper-V, every VF interface is matched with a corresponding
* synthetic interface. The synthetic interface is presented first
@@ -2810,6 +2835,11 @@ static int netvsc_netdev_event(struct notifier_block *this,
struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
int ret = 0;
+ if (event_dev->netdev_ops == &device_ops && event == NETDEV_REGISTER) {
+ netvsc_event_set_vf_ns(event_dev);
+ return NOTIFY_DONE;
+ }
+
ret = check_dev_is_matching_vf(event_dev);
if (ret != 0)
return NOTIFY_DONE;
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 26034f8..ee21592 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -3798,8 +3798,7 @@ static void macsec_free_netdev(struct net_device *dev)
{
struct macsec_dev *macsec = macsec_priv(dev);
- if (macsec->secy.tx_sc.md_dst)
- metadata_dst_free(macsec->secy.tx_sc.md_dst);
+ dst_release(&macsec->secy.tx_sc.md_dst->dst);
free_percpu(macsec->stats);
free_percpu(macsec->secy.tx_sc.stats);
diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c
index 4dc057c..e70fb66 100644
--- a/drivers/net/mctp/mctp-i2c.c
+++ b/drivers/net/mctp/mctp-i2c.c
@@ -588,6 +588,9 @@ static int mctp_i2c_header_create(struct sk_buff *skb, struct net_device *dev,
if (len > MCTP_I2C_MAXMTU)
return -EMSGSIZE;
+ if (!daddr || !saddr)
+ return -EINVAL;
+
lldst = *((u8 *)daddr);
llsrc = *((u8 *)saddr);
diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c
index 41e80f7..16c382c 100644
--- a/drivers/net/netdevsim/fib.c
+++ b/drivers/net/netdevsim/fib.c
@@ -1377,10 +1377,12 @@ static ssize_t nsim_nexthop_bucket_activity_write(struct file *file,
if (pos != 0)
return -EINVAL;
- if (size > sizeof(buf))
+ if (size > sizeof(buf) - 1)
return -EINVAL;
if (copy_from_user(buf, user_buf, size))
return -EFAULT;
+ buf[size] = 0;
+
if (sscanf(buf, "%u %hu", &nhid, &bucket_index) != 2)
return -EINVAL;
diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
index fc247f4..3ab64e0 100644
--- a/drivers/net/phy/dp83822.c
+++ b/drivers/net/phy/dp83822.c
@@ -45,8 +45,8 @@
/* Control Register 2 bits */
#define DP83822_FX_ENABLE BIT(14)
-#define DP83822_HW_RESET BIT(15)
-#define DP83822_SW_RESET BIT(14)
+#define DP83822_SW_RESET BIT(15)
+#define DP83822_DIG_RESTART BIT(14)
/* PHY STS bits */
#define DP83822_PHYSTS_DUPLEX BIT(2)
diff --git a/drivers/net/plip/plip.c b/drivers/net/plip/plip.c
index e39bfae..d81163b 100644
--- a/drivers/net/plip/plip.c
+++ b/drivers/net/plip/plip.c
@@ -815,7 +815,7 @@ plip_send_packet(struct net_device *dev, struct net_local *nl,
return HS_TIMEOUT;
}
}
- break;
+ fallthrough;
case PLIP_PK_LENGTH_LSB:
if (plip_send(nibble_timeout, dev,
diff --git a/drivers/net/pse-pd/pse_core.c b/drivers/net/pse-pd/pse_core.c
index f8e6854..2906ce1 100644
--- a/drivers/net/pse-pd/pse_core.c
+++ b/drivers/net/pse-pd/pse_core.c
@@ -113,7 +113,7 @@ static void pse_release_pis(struct pse_controller_dev *pcdev)
{
int i;
- for (i = 0; i <= pcdev->nr_lines; i++) {
+ for (i = 0; i < pcdev->nr_lines; i++) {
of_node_put(pcdev->pi[i].pairset[0].np);
of_node_put(pcdev->pi[i].pairset[1].np);
of_node_put(pcdev->pi[i].np);
@@ -647,7 +647,7 @@ static int of_pse_match_pi(struct pse_controller_dev *pcdev,
{
int i;
- for (i = 0; i <= pcdev->nr_lines; i++) {
+ for (i = 0; i < pcdev->nr_lines; i++) {
if (pcdev->pi[i].np == np)
return i;
}
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 4823dbd..0c011d8 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1076,6 +1076,7 @@ static const struct usb_device_id products[] = {
USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7),
.driver_info = (unsigned long)&qmi_wwan_info,
},
+ {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0122)}, /* Quectel RG650V */
{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0125)}, /* Quectel EC25, EC20 R2.0 Mini PCIe */
{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0306)}, /* Quectel EP06/EG06/EM06 */
{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0512)}, /* Quectel EG12/EM12 */
@@ -1426,6 +1427,7 @@ static const struct usb_device_id products[] = {
{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */
{QMI_QUIRK_SET_DTR(0x2c7c, 0x030e, 4)}, /* Quectel EM05GV2 */
{QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)}, /* Fibocom NL678 series */
+ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0112, 0)}, /* Fibocom FG132 */
{QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */
{QMI_FIXED_INTF(0x0489, 0xe0b5, 0)}, /* Foxconn T77W968 LTE with eSIM support*/
{QMI_FIXED_INTF(0x2692, 0x9025, 4)}, /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index a5612c7..468c7397 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -10069,6 +10069,7 @@ static const struct usb_device_id rtl8152_table[] = {
{ USB_DEVICE(VENDOR_ID_LENOVO, 0x3062) },
{ USB_DEVICE(VENDOR_ID_LENOVO, 0x3069) },
{ USB_DEVICE(VENDOR_ID_LENOVO, 0x3082) },
+ { USB_DEVICE(VENDOR_ID_LENOVO, 0x3098) },
{ USB_DEVICE(VENDOR_ID_LENOVO, 0x7205) },
{ USB_DEVICE(VENDOR_ID_LENOVO, 0x720c) },
{ USB_DEVICE(VENDOR_ID_LENOVO, 0x7214) },
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index ee1b5fd..44179f4 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1767,7 +1767,8 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
// can rename the link if it knows better.
if ((dev->driver_info->flags & FLAG_ETHER) != 0 &&
((dev->driver_info->flags & FLAG_POINTTOPOINT) == 0 ||
- (net->dev_addr [0] & 0x02) == 0))
+ /* somebody touched it*/
+ !is_zero_ether_addr(net->dev_addr)))
strscpy(net->name, "eth%d", sizeof(net->name));
/* WLAN devices should always be named "wlan%d" */
if ((dev->driver_info->flags & FLAG_WLAN) != 0)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index f8131f92..792e9ea 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -4155,7 +4155,7 @@ struct virtnet_stats_ctx {
u32 desc_num[3];
/* The actual supported stat types. */
- u32 bitmap[3];
+ u64 bitmap[3];
/* Used to calculate the reply buffer size. */
u32 size[3];
diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
index dbaf26d..16d07d6 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
@@ -3043,9 +3043,14 @@ ath10k_wmi_tlv_op_cleanup_mgmt_tx_send(struct ath10k *ar,
struct sk_buff *msdu)
{
struct ath10k_skb_cb *cb = ATH10K_SKB_CB(msdu);
+ struct ath10k_mgmt_tx_pkt_addr *pkt_addr;
struct ath10k_wmi *wmi = &ar->wmi;
- idr_remove(&wmi->mgmt_pending_tx, cb->msdu_id);
+ spin_lock_bh(&ar->data_lock);
+ pkt_addr = idr_remove(&wmi->mgmt_pending_tx, cb->msdu_id);
+ spin_unlock_bh(&ar->data_lock);
+
+ kfree(pkt_addr);
return 0;
}
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index 4861179..5e061f7 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -2441,6 +2441,7 @@ wmi_process_mgmt_tx_comp(struct ath10k *ar, struct mgmt_tx_compl_params *param)
dma_unmap_single(ar->dev, pkt_addr->paddr,
msdu->len, DMA_TO_DEVICE);
info = IEEE80211_SKB_CB(msdu);
+ kfree(pkt_addr);
if (param->status) {
info->flags &= ~IEEE80211_TX_STAT_ACK;
@@ -9612,6 +9613,7 @@ static int ath10k_wmi_mgmt_tx_clean_up_pending(int msdu_id, void *ptr,
dma_unmap_single(ar->dev, pkt_addr->paddr,
msdu->len, DMA_TO_DEVICE);
ieee80211_free_txskb(ar->hw, msdu);
+ kfree(pkt_addr);
return 0;
}
diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c
index c087d8a..40088e6 100644
--- a/drivers/net/wireless/ath/ath11k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_rx.c
@@ -5291,8 +5291,11 @@ int ath11k_dp_rx_process_mon_status(struct ath11k_base *ab, int mac_id,
hal_status == HAL_TLV_STATUS_PPDU_DONE) {
rx_mon_stats->status_ppdu_done++;
pmon->mon_ppdu_status = DP_PPDU_STATUS_DONE;
- ath11k_dp_rx_mon_dest_process(ar, mac_id, budget, napi);
- pmon->mon_ppdu_status = DP_PPDU_STATUS_START;
+ if (!ab->hw_params.full_monitor_mode) {
+ ath11k_dp_rx_mon_dest_process(ar, mac_id,
+ budget, napi);
+ pmon->mon_ppdu_status = DP_PPDU_STATUS_START;
+ }
}
if (ppdu_info->peer_id == HAL_INVALID_PEERID ||
diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index f29ac6d..19702b6 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -306,7 +306,7 @@ static void wil_rx_add_radiotap_header(struct wil6210_priv *wil,
struct sk_buff *skb)
{
struct wil6210_rtap {
- struct ieee80211_radiotap_header rthdr;
+ struct ieee80211_radiotap_header_fixed rthdr;
/* fields should be in the order of bits in rthdr.it_present */
/* flags */
u8 flags;
diff --git a/drivers/net/wireless/broadcom/brcm80211/Kconfig b/drivers/net/wireless/broadcom/brcm80211/Kconfig
index 3a1a35b..19d0c00 100644
--- a/drivers/net/wireless/broadcom/brcm80211/Kconfig
+++ b/drivers/net/wireless/broadcom/brcm80211/Kconfig
@@ -27,6 +27,7 @@
config BRCM_TRACING
bool "Broadcom device tracing"
depends on BRCMSMAC || BRCMFMAC
+ depends on TRACING
help
If you say Y here, the Broadcom wireless drivers will register
with ftrace to dump event information into the trace ringbuffer.
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2100.c b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
index b663600..fe75941 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
@@ -2518,7 +2518,7 @@ static void isr_rx_monitor(struct ipw2100_priv *priv, int i,
* to build this manually element by element, we can write it much
* more efficiently than we can parse it. ORDER MATTERS HERE */
struct ipw_rt_hdr {
- struct ieee80211_radiotap_header rt_hdr;
+ struct ieee80211_radiotap_header_fixed rt_hdr;
s8 rt_dbmsignal; /* signal in dbM, kluged to signed */
} *ipw_rt;
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.h b/drivers/net/wireless/intel/ipw2x00/ipw2200.h
index 8ebf091..226286c 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2200.h
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.h
@@ -1143,7 +1143,7 @@ struct ipw_prom_priv {
* structure is provided regardless of any bits unset.
*/
struct ipw_rt_hdr {
- struct ieee80211_radiotap_header rt_hdr;
+ struct ieee80211_radiotap_header_fixed rt_hdr;
u64 rt_tsf; /* TSF */ /* XXX */
u8 rt_flags; /* radiotap packet flags */
u8 rt_rate; /* rate in 500kb/s */
diff --git a/drivers/net/wireless/intel/iwlegacy/common.c b/drivers/net/wireless/intel/iwlegacy/common.c
index 9d33a66..958dd4f 100644
--- a/drivers/net/wireless/intel/iwlegacy/common.c
+++ b/drivers/net/wireless/intel/iwlegacy/common.c
@@ -3122,6 +3122,7 @@ il_enqueue_hcmd(struct il_priv *il, struct il_host_cmd *cmd)
struct il_cmd_meta *out_meta;
dma_addr_t phys_addr;
unsigned long flags;
+ u8 *out_payload;
u32 idx;
u16 fix_size;
@@ -3157,6 +3158,16 @@ il_enqueue_hcmd(struct il_priv *il, struct il_host_cmd *cmd)
out_cmd = txq->cmd[idx];
out_meta = &txq->meta[idx];
+ /* The payload is in the same place in regular and huge
+ * command buffers, but we need to let the compiler know when
+ * we're using a larger payload buffer to avoid "field-
+ * spanning write" warnings at run-time for huge commands.
+ */
+ if (cmd->flags & CMD_SIZE_HUGE)
+ out_payload = ((struct il_device_cmd_huge *)out_cmd)->cmd.payload;
+ else
+ out_payload = out_cmd->cmd.payload;
+
if (WARN_ON(out_meta->flags & CMD_MAPPED)) {
spin_unlock_irqrestore(&il->hcmd_lock, flags);
return -ENOSPC;
@@ -3170,7 +3181,7 @@ il_enqueue_hcmd(struct il_priv *il, struct il_host_cmd *cmd)
out_meta->callback = cmd->callback;
out_cmd->hdr.cmd = cmd->id;
- memcpy(&out_cmd->cmd.payload, cmd->data, cmd->len);
+ memcpy(out_payload, cmd->data, cmd->len);
/* At this point, the out_cmd now has all of the incoming cmd
* information */
@@ -4962,6 +4973,8 @@ il_pci_resume(struct device *device)
*/
pci_write_config_byte(pdev, PCI_CFG_RETRY_TIMEOUT, 0x00);
+ _il_wr(il, CSR_INT, 0xffffffff);
+ _il_wr(il, CSR_FH_INT_STATUS, 0xffffffff);
il_enable_interrupts(il);
if (!(_il_rd(il, CSR_GP_CNTRL) & CSR_GP_CNTRL_REG_FLAG_HW_RF_KILL_SW))
diff --git a/drivers/net/wireless/intel/iwlegacy/common.h b/drivers/net/wireless/intel/iwlegacy/common.h
index 2147781..725c2a8 100644
--- a/drivers/net/wireless/intel/iwlegacy/common.h
+++ b/drivers/net/wireless/intel/iwlegacy/common.h
@@ -560,6 +560,18 @@ struct il_device_cmd {
#define TFD_MAX_PAYLOAD_SIZE (sizeof(struct il_device_cmd))
+/**
+ * struct il_device_cmd_huge
+ *
+ * For use when sending huge commands.
+ */
+struct il_device_cmd_huge {
+ struct il_cmd_header hdr; /* uCode API */
+ union {
+ u8 payload[IL_MAX_CMD_SIZE - sizeof(struct il_cmd_header)];
+ } __packed cmd;
+} __packed;
+
struct il_host_cmd {
const void *data;
unsigned long reply_page;
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index a7cea0a..0bc3229 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -429,38 +429,28 @@ int iwl_acpi_get_eckv(struct iwl_fw_runtime *fwrt, u32 *extl_clk)
return ret;
}
-static int iwl_acpi_sar_set_profile(union acpi_object *table,
- struct iwl_sar_profile *profile,
- bool enabled, u8 num_chains,
- u8 num_sub_bands)
+static int
+iwl_acpi_parse_chains_table(union acpi_object *table,
+ struct iwl_sar_profile_chain *chains,
+ u8 num_chains, u8 num_sub_bands)
{
- int i, j, idx = 0;
-
- /*
- * The table from ACPI is flat, but we store it in a
- * structured array.
- */
- for (i = 0; i < BIOS_SAR_MAX_CHAINS_PER_PROFILE; i++) {
- for (j = 0; j < BIOS_SAR_MAX_SUB_BANDS_NUM; j++) {
+ for (u8 chain = 0; chain < num_chains; chain++) {
+ for (u8 subband = 0; subband < BIOS_SAR_MAX_SUB_BANDS_NUM;
+ subband++) {
/* if we don't have the values, use the default */
- if (i >= num_chains || j >= num_sub_bands) {
- profile->chains[i].subbands[j] = 0;
+ if (subband >= num_sub_bands) {
+ chains[chain].subbands[subband] = 0;
+ } else if (table->type != ACPI_TYPE_INTEGER ||
+ table->integer.value > U8_MAX) {
+ return -EINVAL;
} else {
- if (table[idx].type != ACPI_TYPE_INTEGER ||
- table[idx].integer.value > U8_MAX)
- return -EINVAL;
-
- profile->chains[i].subbands[j] =
- table[idx].integer.value;
-
- idx++;
+ chains[chain].subbands[subband] =
+ table->integer.value;
+ table++;
}
}
}
- /* Only if all values were valid can the profile be enabled */
- profile->enabled = enabled;
-
return 0;
}
@@ -543,9 +533,11 @@ int iwl_acpi_get_wrds_table(struct iwl_fw_runtime *fwrt)
/* The profile from WRDS is officially profile 1, but goes
* into sar_profiles[0] (because we don't have a profile 0).
*/
- ret = iwl_acpi_sar_set_profile(table, &fwrt->sar_profiles[0],
- flags & IWL_SAR_ENABLE_MSK,
- num_chains, num_sub_bands);
+ ret = iwl_acpi_parse_chains_table(table, fwrt->sar_profiles[0].chains,
+ num_chains, num_sub_bands);
+ if (!ret && flags & IWL_SAR_ENABLE_MSK)
+ fwrt->sar_profiles[0].enabled = true;
+
out_free:
kfree(data);
return ret;
@@ -557,7 +549,7 @@ int iwl_acpi_get_ewrd_table(struct iwl_fw_runtime *fwrt)
bool enabled;
int i, n_profiles, tbl_rev, pos;
int ret = 0;
- u8 num_chains, num_sub_bands;
+ u8 num_sub_bands;
data = iwl_acpi_get_object(fwrt->dev, ACPI_EWRD_METHOD);
if (IS_ERR(data))
@@ -573,7 +565,6 @@ int iwl_acpi_get_ewrd_table(struct iwl_fw_runtime *fwrt)
goto out_free;
}
- num_chains = ACPI_SAR_NUM_CHAINS_REV2;
num_sub_bands = ACPI_SAR_NUM_SUB_BANDS_REV2;
goto read_table;
@@ -589,7 +580,6 @@ int iwl_acpi_get_ewrd_table(struct iwl_fw_runtime *fwrt)
goto out_free;
}
- num_chains = ACPI_SAR_NUM_CHAINS_REV1;
num_sub_bands = ACPI_SAR_NUM_SUB_BANDS_REV1;
goto read_table;
@@ -605,7 +595,6 @@ int iwl_acpi_get_ewrd_table(struct iwl_fw_runtime *fwrt)
goto out_free;
}
- num_chains = ACPI_SAR_NUM_CHAINS_REV0;
num_sub_bands = ACPI_SAR_NUM_SUB_BANDS_REV0;
goto read_table;
@@ -637,23 +626,54 @@ int iwl_acpi_get_ewrd_table(struct iwl_fw_runtime *fwrt)
/* the tables start at element 3 */
pos = 3;
+ BUILD_BUG_ON(ACPI_SAR_NUM_CHAINS_REV0 != ACPI_SAR_NUM_CHAINS_REV1);
+ BUILD_BUG_ON(ACPI_SAR_NUM_CHAINS_REV2 != 2 * ACPI_SAR_NUM_CHAINS_REV0);
+
+ /* parse non-cdb chains for all profiles */
for (i = 0; i < n_profiles; i++) {
union acpi_object *table = &wifi_pkg->package.elements[pos];
+
/* The EWRD profiles officially go from 2 to 4, but we
* save them in sar_profiles[1-3] (because we don't
* have profile 0). So in the array we start from 1.
*/
- ret = iwl_acpi_sar_set_profile(table,
- &fwrt->sar_profiles[i + 1],
- enabled, num_chains,
- num_sub_bands);
+ ret = iwl_acpi_parse_chains_table(table,
+ fwrt->sar_profiles[i + 1].chains,
+ ACPI_SAR_NUM_CHAINS_REV0,
+ num_sub_bands);
if (ret < 0)
- break;
+ goto out_free;
/* go to the next table */
- pos += num_chains * num_sub_bands;
+ pos += ACPI_SAR_NUM_CHAINS_REV0 * num_sub_bands;
}
+ /* non-cdb table revisions */
+ if (tbl_rev < 2)
+ goto set_enabled;
+
+ /* parse cdb chains for all profiles */
+ for (i = 0; i < n_profiles; i++) {
+ struct iwl_sar_profile_chain *chains;
+ union acpi_object *table;
+
+ table = &wifi_pkg->package.elements[pos];
+ chains = &fwrt->sar_profiles[i + 1].chains[ACPI_SAR_NUM_CHAINS_REV0];
+ ret = iwl_acpi_parse_chains_table(table,
+ chains,
+ ACPI_SAR_NUM_CHAINS_REV0,
+ num_sub_bands);
+ if (ret < 0)
+ goto out_free;
+
+ /* go to the next table */
+ pos += ACPI_SAR_NUM_CHAINS_REV0 * num_sub_bands;
+ }
+
+set_enabled:
+ for (i = 0; i < n_profiles; i++)
+ fwrt->sar_profiles[i + 1].enabled = enabled;
+
out_free:
kfree(data);
return ret;
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/init.c b/drivers/net/wireless/intel/iwlwifi/fw/init.c
index d8b083b..de87e0e 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/init.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/init.c
@@ -39,10 +39,12 @@ void iwl_fw_runtime_init(struct iwl_fw_runtime *fwrt, struct iwl_trans *trans,
}
IWL_EXPORT_SYMBOL(iwl_fw_runtime_init);
+/* Assumes the appropriate lock is held by the caller */
void iwl_fw_runtime_suspend(struct iwl_fw_runtime *fwrt)
{
iwl_fw_suspend_timestamp(fwrt);
- iwl_dbg_tlv_time_point(fwrt, IWL_FW_INI_TIME_POINT_HOST_D3_START, NULL);
+ iwl_dbg_tlv_time_point_sync(fwrt, IWL_FW_INI_TIME_POINT_HOST_D3_START,
+ NULL);
}
IWL_EXPORT_SYMBOL(iwl_fw_runtime_suspend);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index 2abfc98..c620911 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -1413,26 +1413,36 @@ _iwl_op_mode_start(struct iwl_drv *drv, struct iwlwifi_opmode_table *op)
const struct iwl_op_mode_ops *ops = op->ops;
struct dentry *dbgfs_dir = NULL;
struct iwl_op_mode *op_mode = NULL;
+ int retry, max_retry = !!iwlwifi_mod_params.fw_restart * IWL_MAX_INIT_RETRY;
/* also protects start/stop from racing against each other */
lockdep_assert_held(&iwlwifi_opmode_table_mtx);
-#ifdef CONFIG_IWLWIFI_DEBUGFS
- drv->dbgfs_op_mode = debugfs_create_dir(op->name,
- drv->dbgfs_drv);
- dbgfs_dir = drv->dbgfs_op_mode;
-#endif
-
- op_mode = ops->start(drv->trans, drv->trans->cfg,
- &drv->fw, dbgfs_dir);
- if (op_mode)
- return op_mode;
+ for (retry = 0; retry <= max_retry; retry++) {
#ifdef CONFIG_IWLWIFI_DEBUGFS
- debugfs_remove_recursive(drv->dbgfs_op_mode);
- drv->dbgfs_op_mode = NULL;
+ drv->dbgfs_op_mode = debugfs_create_dir(op->name,
+ drv->dbgfs_drv);
+ dbgfs_dir = drv->dbgfs_op_mode;
#endif
+ op_mode = ops->start(drv->trans, drv->trans->cfg,
+ &drv->fw, dbgfs_dir);
+
+ if (op_mode)
+ return op_mode;
+
+ if (test_bit(STATUS_TRANS_DEAD, &drv->trans->status))
+ break;
+
+ IWL_ERR(drv, "retry init count %d\n", retry);
+
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+ debugfs_remove_recursive(drv->dbgfs_op_mode);
+ drv->dbgfs_op_mode = NULL;
+#endif
+ }
+
return NULL;
}
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.h b/drivers/net/wireless/intel/iwlwifi/iwl-drv.h
index 1549ff4..6a1d318 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.h
@@ -98,6 +98,9 @@ void iwl_drv_stop(struct iwl_drv *drv);
#define VISIBLE_IF_IWLWIFI_KUNIT static
#endif
+/* max retry for init flow */
+#define IWL_MAX_INIT_RETRY 2
+
#define FW_NAME_PRE_BUFSIZE 64
struct iwl_trans;
const char *iwl_drv_get_fwname_pre(struct iwl_trans *trans, char *buf);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index 49a6aff..244ca8c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -1398,7 +1398,9 @@ int iwl_mvm_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
iwl_mvm_pause_tcm(mvm, true);
+ mutex_lock(&mvm->mutex);
iwl_fw_runtime_suspend(&mvm->fwrt);
+ mutex_unlock(&mvm->mutex);
return __iwl_mvm_suspend(hw, wowlan, false);
}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 08546e6..f30b0fc 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -1307,8 +1307,8 @@ static void iwl_mvm_disconnect_iterator(void *data, u8 *mac,
void iwl_mvm_send_recovery_cmd(struct iwl_mvm *mvm, u32 flags)
{
u32 error_log_size = mvm->fw->ucode_capa.error_log_size;
+ u32 status = 0;
int ret;
- u32 resp;
struct iwl_fw_error_recovery_cmd recovery_cmd = {
.flags = cpu_to_le32(flags),
@@ -1316,7 +1316,6 @@ void iwl_mvm_send_recovery_cmd(struct iwl_mvm *mvm, u32 flags)
};
struct iwl_host_cmd host_cmd = {
.id = WIDE_ID(SYSTEM_GROUP, FW_ERROR_RECOVERY_CMD),
- .flags = CMD_WANT_SKB,
.data = {&recovery_cmd, },
.len = {sizeof(recovery_cmd), },
};
@@ -1336,7 +1335,7 @@ void iwl_mvm_send_recovery_cmd(struct iwl_mvm *mvm, u32 flags)
recovery_cmd.buf_size = cpu_to_le32(error_log_size);
}
- ret = iwl_mvm_send_cmd(mvm, &host_cmd);
+ ret = iwl_mvm_send_cmd_status(mvm, &host_cmd, &status);
kfree(mvm->error_recovery_buf);
mvm->error_recovery_buf = NULL;
@@ -1347,11 +1346,10 @@ void iwl_mvm_send_recovery_cmd(struct iwl_mvm *mvm, u32 flags)
/* skb respond is only relevant in ERROR_RECOVERY_UPDATE_DB */
if (flags & ERROR_RECOVERY_UPDATE_DB) {
- resp = le32_to_cpu(*(__le32 *)host_cmd.resp_pkt->data);
- if (resp) {
+ if (status) {
IWL_ERR(mvm,
"Failed to send recovery cmd blob was invalid %d\n",
- resp);
+ status);
ieee80211_iterate_interfaces(mvm->hw, 0,
iwl_mvm_disconnect_iterator,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index a327893..80b9a11 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -1293,12 +1293,14 @@ int iwl_mvm_mac_start(struct ieee80211_hw *hw)
{
struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
int ret;
+ int retry, max_retry = 0;
mutex_lock(&mvm->mutex);
/* we are starting the mac not in error flow, and restart is enabled */
if (!test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status) &&
iwlwifi_mod_params.fw_restart) {
+ max_retry = IWL_MAX_INIT_RETRY;
/*
* This will prevent mac80211 recovery flows to trigger during
* init failures
@@ -1306,7 +1308,13 @@ int iwl_mvm_mac_start(struct ieee80211_hw *hw)
set_bit(IWL_MVM_STATUS_STARTING, &mvm->status);
}
- ret = __iwl_mvm_mac_start(mvm);
+ for (retry = 0; retry <= max_retry; retry++) {
+ ret = __iwl_mvm_mac_start(mvm);
+ if (!ret)
+ break;
+
+ IWL_ERR(mvm, "mac start retry %d\n", retry);
+ }
clear_bit(IWL_MVM_STATUS_STARTING, &mvm->status);
mutex_unlock(&mvm->mutex);
@@ -1970,7 +1978,6 @@ static void iwl_mvm_mac_remove_interface(struct ieee80211_hw *hw,
mvm->p2p_device_vif = NULL;
}
- iwl_mvm_unset_link_mapping(mvm, vif, &vif->bss_conf);
iwl_mvm_mac_ctxt_remove(mvm, vif);
RCU_INIT_POINTER(mvm->vif_id_to_mac[mvmvif->id], NULL);
@@ -1979,6 +1986,7 @@ static void iwl_mvm_mac_remove_interface(struct ieee80211_hw *hw,
mvm->monitor_on = false;
out:
+ iwl_mvm_unset_link_mapping(mvm, vif, &vif->bss_conf);
if (vif->type == NL80211_IFTYPE_AP ||
vif->type == NL80211_IFTYPE_ADHOC) {
iwl_mvm_dealloc_int_sta(mvm, &mvmvif->deflink.mcast_sta);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
index f2378e0..e252f0d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
@@ -41,8 +41,6 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw,
/* reset deflink MLO parameters */
mvmvif->deflink.fw_link_id = IWL_MVM_FW_LINK_ID_INVALID;
mvmvif->deflink.active = 0;
- /* the first link always points to the default one */
- mvmvif->link[0] = &mvmvif->deflink;
ret = iwl_mvm_mld_mac_ctxt_add(mvm, vif);
if (ret)
@@ -60,9 +58,19 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw,
IEEE80211_VIF_SUPPORTS_CQM_RSSI;
}
- ret = iwl_mvm_add_link(mvm, vif, &vif->bss_conf);
- if (ret)
- goto out_free_bf;
+ /* We want link[0] to point to the default link, unless we have MLO and
+ * in this case this will be modified later by .change_vif_links()
+ * If we are in the restart flow with an MLD connection, we will wait
+ * to .change_vif_links() to setup the links.
+ */
+ if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status) ||
+ !ieee80211_vif_is_mld(vif)) {
+ mvmvif->link[0] = &mvmvif->deflink;
+
+ ret = iwl_mvm_add_link(mvm, vif, &vif->bss_conf);
+ if (ret)
+ goto out_free_bf;
+ }
/* Save a pointer to p2p device vif, so it can later be used to
* update the p2p device MAC when a GO is started/stopped
@@ -350,11 +358,6 @@ __iwl_mvm_mld_assign_vif_chanctx(struct iwl_mvm *mvm,
rcu_read_unlock();
}
- if (vif->type == NL80211_IFTYPE_STATION)
- iwl_mvm_send_ap_tx_power_constraint_cmd(mvm, vif,
- link_conf,
- false);
-
/* then activate */
ret = iwl_mvm_link_changed(mvm, vif, link_conf,
LINK_CONTEXT_MODIFY_ACTIVE |
@@ -363,6 +366,11 @@ __iwl_mvm_mld_assign_vif_chanctx(struct iwl_mvm *mvm,
if (ret)
goto out;
+ if (vif->type == NL80211_IFTYPE_STATION)
+ iwl_mvm_send_ap_tx_power_constraint_cmd(mvm, vif,
+ link_conf,
+ false);
+
/*
* Power state must be updated before quotas,
* otherwise fw will complain.
@@ -1194,7 +1202,11 @@ iwl_mvm_mld_change_vif_links(struct ieee80211_hw *hw,
mutex_lock(&mvm->mutex);
- if (old_links == 0) {
+ /* If we're in RESTART flow, the default link wasn't added in
+ * drv_add_interface(), and link[0] doesn't point to it.
+ */
+ if (old_links == 0 && !test_bit(IWL_MVM_STATUS_IN_HW_RESTART,
+ &mvm->status)) {
err = iwl_mvm_disable_link(mvm, vif, &vif->bss_conf);
if (err)
goto out_err;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index 3ce9150..ddcbd80a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -1774,7 +1774,7 @@ iwl_mvm_umac_scan_cfg_channels_v7_6g(struct iwl_mvm *mvm,
&cp->channel_config[ch_cnt];
u32 s_ssid_bitmap = 0, bssid_bitmap = 0, flags = 0;
- u8 j, k, n_s_ssids = 0, n_bssids = 0;
+ u8 k, n_s_ssids = 0, n_bssids = 0;
u8 max_s_ssids, max_bssids;
bool force_passive = false, found = false, allow_passive = true,
unsolicited_probe_on_chan = false, psc_no_listen = false;
@@ -1799,7 +1799,7 @@ iwl_mvm_umac_scan_cfg_channels_v7_6g(struct iwl_mvm *mvm,
cfg->v5.iter_count = 1;
cfg->v5.iter_interval = 0;
- for (j = 0; j < params->n_6ghz_params; j++) {
+ for (u32 j = 0; j < params->n_6ghz_params; j++) {
s8 tmp_psd_20;
if (!(scan_6ghz_params[j].channel_idx == i))
@@ -1873,7 +1873,7 @@ iwl_mvm_umac_scan_cfg_channels_v7_6g(struct iwl_mvm *mvm,
* SSID.
* TODO: improve this logic
*/
- for (j = 0; j < params->n_6ghz_params; j++) {
+ for (u32 j = 0; j < params->n_6ghz_params; j++) {
if (!(scan_6ghz_params[j].channel_idx == i))
continue;
diff --git a/drivers/net/wireless/marvell/libertas/radiotap.h b/drivers/net/wireless/marvell/libertas/radiotap.h
index 1ed5608..d543bfe 100644
--- a/drivers/net/wireless/marvell/libertas/radiotap.h
+++ b/drivers/net/wireless/marvell/libertas/radiotap.h
@@ -2,7 +2,7 @@
#include <net/ieee80211_radiotap.h>
struct tx_radiotap_hdr {
- struct ieee80211_radiotap_header hdr;
+ struct ieee80211_radiotap_header_fixed hdr;
u8 rate;
u8 txpower;
u8 rts_retries;
@@ -31,7 +31,7 @@ struct tx_radiotap_hdr {
#define IEEE80211_FC_DSTODS 0x0300
struct rx_radiotap_hdr {
- struct ieee80211_radiotap_header hdr;
+ struct ieee80211_radiotap_header_fixed hdr;
u8 flags;
u8 rate;
u8 antsignal;
diff --git a/drivers/net/wireless/mediatek/mt76/mcu.c b/drivers/net/wireless/mediatek/mt76/mcu.c
index 98da82b..3353012 100644
--- a/drivers/net/wireless/mediatek/mt76/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mcu.c
@@ -84,13 +84,16 @@ int mt76_mcu_skb_send_and_get_msg(struct mt76_dev *dev, struct sk_buff *skb,
mutex_lock(&dev->mcu.mutex);
if (dev->mcu_ops->mcu_skb_prepare_msg) {
+ orig_skb = skb;
ret = dev->mcu_ops->mcu_skb_prepare_msg(dev, skb, cmd, &seq);
if (ret < 0)
goto out;
}
retry:
- orig_skb = skb_get(skb);
+ /* orig skb might be needed for retry, mcu_skb_send_msg consumes it */
+ if (orig_skb)
+ skb_get(orig_skb);
ret = dev->mcu_ops->mcu_skb_send_msg(dev, skb, cmd, &seq);
if (ret < 0)
goto out;
@@ -105,7 +108,7 @@ int mt76_mcu_skb_send_and_get_msg(struct mt76_dev *dev, struct sk_buff *skb,
do {
skb = mt76_mcu_get_response(dev, expires);
if (!skb && !test_bit(MT76_MCU_RESET, &dev->phy.state) &&
- retry++ < dev->mcu_ops->max_retry) {
+ orig_skb && retry++ < dev->mcu_ops->max_retry) {
dev_err(dev->dev, "Retry message %08x (seq %d)\n",
cmd, seq);
skb = orig_skb;
diff --git a/drivers/net/wireless/microchip/wilc1000/mon.c b/drivers/net/wireless/microchip/wilc1000/mon.c
index 03b7229..c3d27aa 100644
--- a/drivers/net/wireless/microchip/wilc1000/mon.c
+++ b/drivers/net/wireless/microchip/wilc1000/mon.c
@@ -7,12 +7,12 @@
#include "cfg80211.h"
struct wilc_wfi_radiotap_hdr {
- struct ieee80211_radiotap_header hdr;
+ struct ieee80211_radiotap_header_fixed hdr;
u8 rate;
} __packed;
struct wilc_wfi_radiotap_cb_hdr {
- struct ieee80211_radiotap_header hdr;
+ struct ieee80211_radiotap_header_fixed hdr;
u8 rate;
u8 dump;
u16 tx_flags;
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/sw.c
index d069a81..cc699ef 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/sw.c
@@ -352,7 +352,6 @@ static const struct usb_device_id rtl8192d_usb_ids[] = {
{RTL_USB_DEVICE(USB_VENDOR_ID_REALTEK, 0x8194, rtl92du_hal_cfg)},
{RTL_USB_DEVICE(USB_VENDOR_ID_REALTEK, 0x8111, rtl92du_hal_cfg)},
{RTL_USB_DEVICE(USB_VENDOR_ID_REALTEK, 0x0193, rtl92du_hal_cfg)},
- {RTL_USB_DEVICE(USB_VENDOR_ID_REALTEK, 0x8171, rtl92du_hal_cfg)},
{RTL_USB_DEVICE(USB_VENDOR_ID_REALTEK, 0xe194, rtl92du_hal_cfg)},
{RTL_USB_DEVICE(0x2019, 0xab2c, rtl92du_hal_cfg)},
{RTL_USB_DEVICE(0x2019, 0xab2d, rtl92du_hal_cfg)},
diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
index e83ab6f..b17a429 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.c
+++ b/drivers/net/wireless/realtek/rtw88/usb.c
@@ -771,7 +771,6 @@ static void rtw_usb_dynamic_rx_agg_v1(struct rtw_dev *rtwdev, bool enable)
u8 size, timeout;
u16 val16;
- rtw_write32_set(rtwdev, REG_RXDMA_AGG_PG_TH, BIT_EN_PRE_CALC);
rtw_write8_set(rtwdev, REG_TXDMA_PQ_MAP, BIT_RXDMA_AGG_EN);
rtw_write8_clr(rtwdev, REG_RXDMA_AGG_PG_TH + 3, BIT(7));
diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index df51b29..8d27374 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -6445,6 +6445,8 @@ static void _update_wl_info_v7(struct rtw89_dev *rtwdev, u8 rid)
/* todo DBCC related event */
rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC] wl_info phy_now=%d\n", phy_now);
+ rtw89_debug(rtwdev, RTW89_DBG_BTC,
+ "[BTC] rlink cnt_2g=%d cnt_5g=%d\n", cnt_2g, cnt_5g);
if (wl_rinfo->dbcc_en != rtwdev->dbcc_en) {
wl_rinfo->dbcc_chg = 1;
diff --git a/drivers/net/wireless/realtek/rtw89/pci.c b/drivers/net/wireless/realtek/rtw89/pci.c
index 02afeb3..5aef7fa 100644
--- a/drivers/net/wireless/realtek/rtw89/pci.c
+++ b/drivers/net/wireless/realtek/rtw89/pci.c
@@ -3026,23 +3026,53 @@ static void rtw89_pci_declaim_device(struct rtw89_dev *rtwdev,
pci_disable_device(pdev);
}
-static void rtw89_pci_cfg_dac(struct rtw89_dev *rtwdev)
+static bool rtw89_pci_chip_is_manual_dac(struct rtw89_dev *rtwdev)
{
- struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv;
const struct rtw89_chip_info *chip = rtwdev->chip;
- if (!rtwpci->enable_dac)
- return;
-
switch (chip->chip_id) {
case RTL8852A:
case RTL8852B:
case RTL8851B:
case RTL8852BT:
- break;
+ return true;
default:
- return;
+ return false;
}
+}
+
+static bool rtw89_pci_is_dac_compatible_bridge(struct rtw89_dev *rtwdev)
+{
+ struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv;
+ struct pci_dev *bridge = pci_upstream_bridge(rtwpci->pdev);
+
+ if (!rtw89_pci_chip_is_manual_dac(rtwdev))
+ return true;
+
+ if (!bridge)
+ return false;
+
+ switch (bridge->vendor) {
+ case PCI_VENDOR_ID_INTEL:
+ return true;
+ case PCI_VENDOR_ID_ASMEDIA:
+ if (bridge->device == 0x2806)
+ return true;
+ break;
+ }
+
+ return false;
+}
+
+static void rtw89_pci_cfg_dac(struct rtw89_dev *rtwdev)
+{
+ struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv;
+
+ if (!rtwpci->enable_dac)
+ return;
+
+ if (!rtw89_pci_chip_is_manual_dac(rtwdev))
+ return;
rtw89_pci_config_byte_set(rtwdev, RTW89_PCIE_L1_CTRL, RTW89_PCIE_BIT_EN_64BITS);
}
@@ -3061,6 +3091,9 @@ static int rtw89_pci_setup_mapping(struct rtw89_dev *rtwdev,
goto err;
}
+ if (!rtw89_pci_is_dac_compatible_bridge(rtwdev))
+ goto no_dac;
+
ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(36));
if (!ret) {
rtwpci->enable_dac = true;
@@ -3073,6 +3106,7 @@ static int rtw89_pci_setup_mapping(struct rtw89_dev *rtwdev,
goto err_release_regions;
}
}
+no_dac:
resource_len = pci_resource_len(pdev, bar_id);
rtwpci->mmap = pci_iomap(pdev, bar_id, resource_len);
diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c
index f0e528a..3f424f1 100644
--- a/drivers/net/wireless/virtual/mac80211_hwsim.c
+++ b/drivers/net/wireless/virtual/mac80211_hwsim.c
@@ -763,7 +763,7 @@ static const struct rhashtable_params hwsim_rht_params = {
};
struct hwsim_radiotap_hdr {
- struct ieee80211_radiotap_header hdr;
+ struct ieee80211_radiotap_header_fixed hdr;
__le64 rt_tsft;
u8 rt_flags;
u8 rt_rate;
@@ -772,7 +772,7 @@ struct hwsim_radiotap_hdr {
} __packed;
struct hwsim_radiotap_ack_hdr {
- struct ieee80211_radiotap_header hdr;
+ struct ieee80211_radiotap_header_fixed hdr;
u8 rt_flags;
u8 pad;
__le16 rt_channel;
diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c
index 17431f1..65a7ed4 100644
--- a/drivers/net/wwan/wwan_core.c
+++ b/drivers/net/wwan/wwan_core.c
@@ -1038,7 +1038,7 @@ static const struct nla_policy wwan_rtnl_policy[IFLA_WWAN_MAX + 1] = {
static struct rtnl_link_ops wwan_rtnl_link_ops __read_mostly = {
.kind = "wwan",
- .maxtype = __IFLA_WWAN_MAX,
+ .maxtype = IFLA_WWAN_MAX,
.alloc = wwan_rtnl_alloc,
.validate = wwan_rtnl_validate,
.newlink = wwan_rtnl_newlink,
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 4f68414..f161580 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -3105,7 +3105,9 @@ int pci_host_probe(struct pci_host_bridge *bridge)
list_for_each_entry(child, &bus->children, node)
pcie_bus_configure_settings(child);
+ pci_lock_rescan_remove();
pci_bus_add_devices(bus);
+ pci_unlock_rescan_remove();
return 0;
}
EXPORT_SYMBOL_GPL(pci_host_probe);
diff --git a/drivers/pci/pwrctl/pci-pwrctl-pwrseq.c b/drivers/pci/pwrctl/pci-pwrctl-pwrseq.c
index a23a431..0e6bd47 100644
--- a/drivers/pci/pwrctl/pci-pwrctl-pwrseq.c
+++ b/drivers/pci/pwrctl/pci-pwrctl-pwrseq.c
@@ -6,9 +6,9 @@
#include <linux/device.h>
#include <linux/mod_devicetable.h>
#include <linux/module.h>
-#include <linux/of.h>
#include <linux/pci-pwrctl.h>
#include <linux/platform_device.h>
+#include <linux/property.h>
#include <linux/pwrseq/consumer.h>
#include <linux/slab.h>
#include <linux/types.h>
@@ -18,6 +18,40 @@ struct pci_pwrctl_pwrseq_data {
struct pwrseq_desc *pwrseq;
};
+struct pci_pwrctl_pwrseq_pdata {
+ const char *target;
+ /*
+ * Called before doing anything else to perform device-specific
+ * verification between requesting the power sequencing handle.
+ */
+ int (*validate_device)(struct device *dev);
+};
+
+static int pci_pwrctl_pwrseq_qcm_wcn_validate_device(struct device *dev)
+{
+ /*
+ * Old device trees for some platforms already define wifi nodes for
+ * the WCN family of chips since before power sequencing was added
+ * upstream.
+ *
+ * These nodes don't consume the regulator outputs from the PMU, and
+ * if we allow this driver to bind to one of such "incomplete" nodes,
+ * we'll see a kernel log error about the indefinite probe deferral.
+ *
+ * Check the existence of the regulator supply that exists on all
+ * WCN models before moving forward.
+ */
+ if (!device_property_present(dev, "vddaon-supply"))
+ return -ENODEV;
+
+ return 0;
+}
+
+static const struct pci_pwrctl_pwrseq_pdata pci_pwrctl_pwrseq_qcom_wcn_pdata = {
+ .target = "wlan",
+ .validate_device = pci_pwrctl_pwrseq_qcm_wcn_validate_device,
+};
+
static void devm_pci_pwrctl_pwrseq_power_off(void *data)
{
struct pwrseq_desc *pwrseq = data;
@@ -27,15 +61,26 @@ static void devm_pci_pwrctl_pwrseq_power_off(void *data)
static int pci_pwrctl_pwrseq_probe(struct platform_device *pdev)
{
+ const struct pci_pwrctl_pwrseq_pdata *pdata;
struct pci_pwrctl_pwrseq_data *data;
struct device *dev = &pdev->dev;
int ret;
+ pdata = device_get_match_data(dev);
+ if (!pdata || !pdata->target)
+ return -EINVAL;
+
+ if (pdata->validate_device) {
+ ret = pdata->validate_device(dev);
+ if (ret)
+ return ret;
+ }
+
data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
if (!data)
return -ENOMEM;
- data->pwrseq = devm_pwrseq_get(dev, of_device_get_match_data(dev));
+ data->pwrseq = devm_pwrseq_get(dev, pdata->target);
if (IS_ERR(data->pwrseq))
return dev_err_probe(dev, PTR_ERR(data->pwrseq),
"Failed to get the power sequencer\n");
@@ -64,17 +109,17 @@ static const struct of_device_id pci_pwrctl_pwrseq_of_match[] = {
{
/* ATH11K in QCA6390 package. */
.compatible = "pci17cb,1101",
- .data = "wlan",
+ .data = &pci_pwrctl_pwrseq_qcom_wcn_pdata,
},
{
/* ATH11K in WCN6855 package. */
.compatible = "pci17cb,1103",
- .data = "wlan",
+ .data = &pci_pwrctl_pwrseq_qcom_wcn_pdata,
},
{
/* ATH12K in WCN7850 package. */
.compatible = "pci17cb,1107",
- .data = "wlan",
+ .data = &pci_pwrctl_pwrseq_qcom_wcn_pdata,
},
{ }
};
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 7a48220..abdca3f 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -3908,6 +3908,16 @@ static int platform_profile_setup(struct asus_wmi *asus)
if (!asus->throttle_thermal_policy_dev)
return 0;
+ /*
+ * We need to set the default thermal profile during probe or otherwise
+ * the system will often remain in silent mode, causing low performance.
+ */
+ err = throttle_thermal_policy_set_default(asus);
+ if (err < 0) {
+ pr_warn("Failed to set default thermal profile\n");
+ return err;
+ }
+
dev_info(dev, "Using throttle_thermal_policy for platform_profile support\n");
asus->platform_profile_handler.profile_get = asus_wmi_platform_profile_get;
diff --git a/drivers/platform/x86/dell/dell-wmi-base.c b/drivers/platform/x86/dell/dell-wmi-base.c
index 502783a..24fd7ff 100644
--- a/drivers/platform/x86/dell/dell-wmi-base.c
+++ b/drivers/platform/x86/dell/dell-wmi-base.c
@@ -264,6 +264,15 @@ static const struct key_entry dell_wmi_keymap_type_0010[] = {
/*Speaker Mute*/
{ KE_KEY, 0x109, { KEY_MUTE} },
+ /* S2Idle screen off */
+ { KE_IGNORE, 0x120, { KEY_RESERVED }},
+
+ /* Leaving S4 or S2Idle suspend */
+ { KE_IGNORE, 0x130, { KEY_RESERVED }},
+
+ /* Entering S2Idle suspend */
+ { KE_IGNORE, 0x140, { KEY_RESERVED }},
+
/* Mic mute */
{ KE_KEY, 0x150, { KEY_MICMUTE } },
diff --git a/drivers/platform/x86/intel/pmc/adl.c b/drivers/platform/x86/intel/pmc/adl.c
index 9d9c07f..e787855 100644
--- a/drivers/platform/x86/intel/pmc/adl.c
+++ b/drivers/platform/x86/intel/pmc/adl.c
@@ -295,8 +295,6 @@ const struct pmc_reg_map adl_reg_map = {
.ppfear_buckets = CNP_PPFEAR_NUM_ENTRIES,
.pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET,
.pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT,
- .acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET,
- .acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE,
.ltr_ignore_max = ADL_NUM_IP_IGN_ALLOWED,
.lpm_num_modes = ADL_LPM_NUM_MODES,
.lpm_num_maps = ADL_LPM_NUM_MAPS,
diff --git a/drivers/platform/x86/intel/pmc/cnp.c b/drivers/platform/x86/intel/pmc/cnp.c
index 513c026..dd72974 100644
--- a/drivers/platform/x86/intel/pmc/cnp.c
+++ b/drivers/platform/x86/intel/pmc/cnp.c
@@ -200,8 +200,6 @@ const struct pmc_reg_map cnp_reg_map = {
.ppfear_buckets = CNP_PPFEAR_NUM_ENTRIES,
.pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET,
.pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT,
- .acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET,
- .acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE,
.ltr_ignore_max = CNP_NUM_IP_IGN_ALLOWED,
.etr3_offset = ETR3_OFFSET,
};
diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c
index ecb47f8b..4e9c8c9 100644
--- a/drivers/platform/x86/intel/pmc/core.c
+++ b/drivers/platform/x86/intel/pmc/core.c
@@ -11,7 +11,6 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <linux/acpi_pmtmr.h>
#include <linux/bitfield.h>
#include <linux/debugfs.h>
#include <linux/delay.h>
@@ -1258,39 +1257,6 @@ static bool pmc_core_is_pson_residency_enabled(struct pmc_dev *pmcdev)
return val == 1;
}
-/*
- * Enable or disable ACPI PM Timer
- *
- * This function is intended to be a callback for ACPI PM suspend/resume event.
- * The ACPI PM Timer is enabled on resume only if it was enabled during suspend.
- */
-static void pmc_core_acpi_pm_timer_suspend_resume(void *data, bool suspend)
-{
- struct pmc_dev *pmcdev = data;
- struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN];
- const struct pmc_reg_map *map = pmc->map;
- bool enabled;
- u32 reg;
-
- if (!map->acpi_pm_tmr_ctl_offset)
- return;
-
- guard(mutex)(&pmcdev->lock);
-
- if (!suspend && !pmcdev->enable_acpi_pm_timer_on_resume)
- return;
-
- reg = pmc_core_reg_read(pmc, map->acpi_pm_tmr_ctl_offset);
- enabled = !(reg & map->acpi_pm_tmr_disable_bit);
- if (suspend)
- reg |= map->acpi_pm_tmr_disable_bit;
- else
- reg &= ~map->acpi_pm_tmr_disable_bit;
- pmc_core_reg_write(pmc, map->acpi_pm_tmr_ctl_offset, reg);
-
- pmcdev->enable_acpi_pm_timer_on_resume = suspend && enabled;
-}
-
static void pmc_core_dbgfs_unregister(struct pmc_dev *pmcdev)
{
debugfs_remove_recursive(pmcdev->dbgfs_dir);
@@ -1486,7 +1452,6 @@ static int pmc_core_probe(struct platform_device *pdev)
struct pmc_dev *pmcdev;
const struct x86_cpu_id *cpu_id;
int (*core_init)(struct pmc_dev *pmcdev);
- const struct pmc_reg_map *map;
struct pmc *primary_pmc;
int ret;
@@ -1545,11 +1510,6 @@ static int pmc_core_probe(struct platform_device *pdev)
pm_report_max_hw_sleep(FIELD_MAX(SLP_S0_RES_COUNTER_MASK) *
pmc_core_adjust_slp_s0_step(primary_pmc, 1));
- map = primary_pmc->map;
- if (map->acpi_pm_tmr_ctl_offset)
- acpi_pmtmr_register_suspend_resume_callback(pmc_core_acpi_pm_timer_suspend_resume,
- pmcdev);
-
device_initialized = true;
dev_info(&pdev->dev, " initialized\n");
@@ -1559,12 +1519,6 @@ static int pmc_core_probe(struct platform_device *pdev)
static void pmc_core_remove(struct platform_device *pdev)
{
struct pmc_dev *pmcdev = platform_get_drvdata(pdev);
- const struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN];
- const struct pmc_reg_map *map = pmc->map;
-
- if (map->acpi_pm_tmr_ctl_offset)
- acpi_pmtmr_unregister_suspend_resume_callback();
-
pmc_core_dbgfs_unregister(pmcdev);
pmc_core_clean_structure(pdev);
}
diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h
index 75fd593a..b9d3291 100644
--- a/drivers/platform/x86/intel/pmc/core.h
+++ b/drivers/platform/x86/intel/pmc/core.h
@@ -68,8 +68,6 @@ struct telem_endpoint;
#define SPT_PMC_LTR_SCC 0x3A0
#define SPT_PMC_LTR_ISH 0x3A4
-#define SPT_PMC_ACPI_PM_TMR_CTL_OFFSET 0x18FC
-
/* Sunrise Point: PGD PFET Enable Ack Status Registers */
enum ppfear_regs {
SPT_PMC_XRAM_PPFEAR0A = 0x590,
@@ -150,8 +148,6 @@ enum ppfear_regs {
#define SPT_PMC_VRIC1_SLPS0LVEN BIT(13)
#define SPT_PMC_VRIC1_XTALSDQDIS BIT(22)
-#define SPT_PMC_BIT_ACPI_PM_TMR_DISABLE BIT(1)
-
/* Cannonlake Power Management Controller register offsets */
#define CNP_PMC_SLPS0_DBG_OFFSET 0x10B4
#define CNP_PMC_PM_CFG_OFFSET 0x1818
@@ -355,8 +351,6 @@ struct pmc_reg_map {
const u8 *lpm_reg_index;
const u32 pson_residency_offset;
const u32 pson_residency_counter_step;
- const u32 acpi_pm_tmr_ctl_offset;
- const u32 acpi_pm_tmr_disable_bit;
};
/**
@@ -432,8 +426,6 @@ struct pmc_dev {
u32 die_c6_offset;
struct telem_endpoint *punit_ep;
struct pmc_info *regmap_list;
-
- bool enable_acpi_pm_timer_on_resume;
};
enum pmc_index {
diff --git a/drivers/platform/x86/intel/pmc/core_ssram.c b/drivers/platform/x86/intel/pmc/core_ssram.c
index c259c96..8504154 100644
--- a/drivers/platform/x86/intel/pmc/core_ssram.c
+++ b/drivers/platform/x86/intel/pmc/core_ssram.c
@@ -29,7 +29,7 @@
#define LPM_REG_COUNT 28
#define LPM_MODE_OFFSET 1
-DEFINE_FREE(pmc_core_iounmap, void __iomem *, iounmap(_T));
+DEFINE_FREE(pmc_core_iounmap, void __iomem *, if (_T) iounmap(_T))
static u32 pmc_core_find_guid(struct pmc_info *list, const struct pmc_reg_map *map)
{
@@ -262,6 +262,8 @@ pmc_core_ssram_get_pmc(struct pmc_dev *pmcdev, int pmc_idx, u32 offset)
ssram_base = ssram_pcidev->resource[0].start;
tmp_ssram = ioremap(ssram_base, SSRAM_HDR_SIZE);
+ if (!tmp_ssram)
+ return -ENOMEM;
if (pmc_idx != PMC_IDX_MAIN) {
/*
diff --git a/drivers/platform/x86/intel/pmc/icl.c b/drivers/platform/x86/intel/pmc/icl.c
index cbbd440..71b0fd6 100644
--- a/drivers/platform/x86/intel/pmc/icl.c
+++ b/drivers/platform/x86/intel/pmc/icl.c
@@ -46,8 +46,6 @@ const struct pmc_reg_map icl_reg_map = {
.ppfear_buckets = ICL_PPFEAR_NUM_ENTRIES,
.pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET,
.pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT,
- .acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET,
- .acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE,
.ltr_ignore_max = ICL_NUM_IP_IGN_ALLOWED,
.etr3_offset = ETR3_OFFSET,
};
diff --git a/drivers/platform/x86/intel/pmc/mtl.c b/drivers/platform/x86/intel/pmc/mtl.c
index 91f2fa7..c7d15d8 100644
--- a/drivers/platform/x86/intel/pmc/mtl.c
+++ b/drivers/platform/x86/intel/pmc/mtl.c
@@ -462,8 +462,6 @@ const struct pmc_reg_map mtl_socm_reg_map = {
.ppfear_buckets = MTL_SOCM_PPFEAR_NUM_ENTRIES,
.pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET,
.pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT,
- .acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET,
- .acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE,
.lpm_num_maps = ADL_LPM_NUM_MAPS,
.ltr_ignore_max = MTL_SOCM_NUM_IP_IGN_ALLOWED,
.lpm_res_counter_step_x2 = TGL_PMC_LPM_RES_COUNTER_STEP_X2,
diff --git a/drivers/platform/x86/intel/pmc/tgl.c b/drivers/platform/x86/intel/pmc/tgl.c
index 371b4e3..e0580de 100644
--- a/drivers/platform/x86/intel/pmc/tgl.c
+++ b/drivers/platform/x86/intel/pmc/tgl.c
@@ -197,8 +197,6 @@ const struct pmc_reg_map tgl_reg_map = {
.ppfear_buckets = ICL_PPFEAR_NUM_ENTRIES,
.pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET,
.pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT,
- .acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET,
- .acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE,
.ltr_ignore_max = TGL_NUM_IP_IGN_ALLOWED,
.lpm_num_maps = TGL_LPM_NUM_MAPS,
.lpm_res_counter_step_x2 = TGL_PMC_LPM_RES_COUNTER_STEP_X2,
diff --git a/drivers/powercap/dtpm_devfreq.c b/drivers/powercap/dtpm_devfreq.c
index f40bce8..d1dff6c 100644
--- a/drivers/powercap/dtpm_devfreq.c
+++ b/drivers/powercap/dtpm_devfreq.c
@@ -178,7 +178,7 @@ static int __dtpm_devfreq_setup(struct devfreq *devfreq, struct dtpm *parent)
ret = dev_pm_qos_add_request(dev, &dtpm_devfreq->qos_req,
DEV_PM_QOS_MAX_FREQUENCY,
PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE);
- if (ret) {
+ if (ret < 0) {
pr_err("Failed to add QoS request: %d\n", ret);
goto out_dtpm_unregister;
}
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index de15fc0..b52513e 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -3651,7 +3651,7 @@ static int do_device_access(struct sdeb_store_info *sip, struct scsi_cmnd *scp,
enum dma_data_direction dir;
struct scsi_data_buffer *sdb = &scp->sdb;
u8 *fsp;
- int i;
+ int i, total = 0;
/*
* Even though reads are inherently atomic (in this driver), we expect
@@ -3688,18 +3688,16 @@ static int do_device_access(struct sdeb_store_info *sip, struct scsi_cmnd *scp,
fsp + (block * sdebug_sector_size),
sdebug_sector_size, sg_skip, do_write);
sdeb_data_sector_unlock(sip, do_write);
- if (ret != sdebug_sector_size) {
- ret += (i * sdebug_sector_size);
+ total += ret;
+ if (ret != sdebug_sector_size)
break;
- }
sg_skip += sdebug_sector_size;
if (++block >= sdebug_store_sectors)
block = 0;
}
- ret = num * sdebug_sector_size;
sdeb_data_unlock(sip, atomic);
- return ret;
+ return total;
}
/* Returns number of bytes copied or -1 if error. */
diff --git a/drivers/soundwire/intel_ace2x.c b/drivers/soundwire/intel_ace2x.c
index fff312c..4f3dd70 100644
--- a/drivers/soundwire/intel_ace2x.c
+++ b/drivers/soundwire/intel_ace2x.c
@@ -376,11 +376,12 @@ static int intel_hw_params(struct snd_pcm_substream *substream,
static int intel_prepare(struct snd_pcm_substream *substream,
struct snd_soc_dai *dai)
{
+ struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream);
struct sdw_cdns *cdns = snd_soc_dai_get_drvdata(dai);
struct sdw_intel *sdw = cdns_to_intel(cdns);
struct sdw_cdns_dai_runtime *dai_runtime;
+ struct snd_pcm_hw_params *hw_params;
int ch, dir;
- int ret = 0;
dai_runtime = cdns->dai_runtime_array[dai->id];
if (!dai_runtime) {
@@ -389,12 +390,8 @@ static int intel_prepare(struct snd_pcm_substream *substream,
return -EIO;
}
+ hw_params = &rtd->dpcm[substream->stream].hw_params;
if (dai_runtime->suspended) {
- struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream);
- struct snd_pcm_hw_params *hw_params;
-
- hw_params = &rtd->dpcm[substream->stream].hw_params;
-
dai_runtime->suspended = false;
/*
@@ -415,15 +412,11 @@ static int intel_prepare(struct snd_pcm_substream *substream,
/* the SHIM will be configured in the callback functions */
sdw_cdns_config_stream(cdns, ch, dir, dai_runtime->pdi);
-
- /* Inform DSP about PDI stream number */
- ret = intel_params_stream(sdw, substream, dai,
- hw_params,
- sdw->instance,
- dai_runtime->pdi->intel_alh_id);
}
- return ret;
+ /* Inform DSP about PDI stream number */
+ return intel_params_stream(sdw, substream, dai, hw_params, sdw->instance,
+ dai_runtime->pdi->intel_alh_id);
}
static int
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 191de19..3fa990f 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -1003,6 +1003,7 @@ static int dspi_setup(struct spi_device *spi)
u32 cs_sck_delay = 0, sck_cs_delay = 0;
struct fsl_dspi_platform_data *pdata;
unsigned char pasc = 0, asc = 0;
+ struct gpio_desc *gpio_cs;
struct chip_data *chip;
unsigned long clkrate;
bool cs = true;
@@ -1077,7 +1078,10 @@ static int dspi_setup(struct spi_device *spi)
chip->ctar_val |= SPI_CTAR_LSBFE;
}
- gpiod_direction_output(spi_get_csgpiod(spi, 0), false);
+ gpio_cs = spi_get_csgpiod(spi, 0);
+ if (gpio_cs)
+ gpiod_direction_output(gpio_cs, false);
+
dspi_deassert_cs(spi, &cs);
spi_set_ctldata(spi, chip);
diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c
index f6e40f9..768d748 100644
--- a/drivers/spi/spi-geni-qcom.c
+++ b/drivers/spi/spi-geni-qcom.c
@@ -1116,6 +1116,11 @@ static int spi_geni_probe(struct platform_device *pdev)
init_completion(&mas->tx_reset_done);
init_completion(&mas->rx_reset_done);
spin_lock_init(&mas->lock);
+
+ ret = geni_icc_get(&mas->se, NULL);
+ if (ret)
+ return ret;
+
pm_runtime_use_autosuspend(&pdev->dev);
pm_runtime_set_autosuspend_delay(&pdev->dev, 250);
ret = devm_pm_runtime_enable(dev);
@@ -1125,9 +1130,6 @@ static int spi_geni_probe(struct platform_device *pdev)
if (device_property_read_bool(&pdev->dev, "spi-slave"))
spi->target = true;
- ret = geni_icc_get(&mas->se, NULL);
- if (ret)
- return ret;
/* Set the bus quota to a reasonable value for register access */
mas->se.icc_paths[GENI_TO_CORE].avg_bw = Bps_to_icc(CORE_2X_50_MHZ);
mas->se.icc_paths[CPU_TO_GENI].avg_bw = GENI_DEFAULT_BW;
diff --git a/drivers/spi/spi-mtk-snfi.c b/drivers/spi/spi-mtk-snfi.c
index ddd98dd..c5677fd 100644
--- a/drivers/spi/spi-mtk-snfi.c
+++ b/drivers/spi/spi-mtk-snfi.c
@@ -1187,7 +1187,7 @@ static int mtk_snand_write_page_cache(struct mtk_snand *snf,
/**
* mtk_snand_is_page_ops() - check if the op is a controller supported page op.
- * @op spi-mem op to check
+ * @op: spi-mem op to check
*
* Check whether op can be executed with read_from_cache or program_load
* mode in the controller.
diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index 4c4ff07..fc72a89 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -2044,6 +2044,7 @@ static const struct stm32_spi_cfg stm32mp25_spi_cfg = {
.baud_rate_div_max = STM32H7_SPI_MBR_DIV_MAX,
.has_fifo = true,
.prevent_dma_burst = true,
+ .has_device_mode = true,
};
static const struct of_device_id stm32_spi_of_match[] = {
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index a63dcf4..f584659 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -8219,7 +8219,7 @@ static void ufshcd_update_rtc(struct ufs_hba *hba)
err = ufshcd_query_attr(hba, UPIU_QUERY_OPCODE_WRITE_ATTR, QUERY_ATTR_IDN_SECONDS_PASSED,
0, 0, &val);
- ufshcd_rpm_put_sync(hba);
+ ufshcd_rpm_put(hba);
if (err)
dev_err(hba->dev, "%s: Failed to update rtc %d\n", __func__, err);
diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig
index ea36c69..de03507 100644
--- a/drivers/video/fbdev/Kconfig
+++ b/drivers/video/fbdev/Kconfig
@@ -1236,7 +1236,6 @@
config FB_VOODOO1
tristate "3Dfx Voodoo Graphics (sst1) support"
depends on FB && PCI
- depends on FB_DEVICE
select FB_IOMEM_HELPERS
help
Say Y here if you have a 3Dfx Voodoo Graphics (Voodoo1/sst1) or
@@ -1374,6 +1373,7 @@
config FB_WM8505
bool "Wondermedia WM8xxx-series frame buffer support"
depends on (FB = y) && HAS_IOMEM && (ARCH_VT8500 || COMPILE_TEST)
+ select FB_IOMEM_FOPS
select FB_SYS_FILLRECT if (!FB_WMT_GE_ROPS)
select FB_SYS_COPYAREA if (!FB_WMT_GE_ROPS)
select FB_SYS_IMAGEBLIT
@@ -1660,19 +1660,6 @@
and 8, 15 or 16 bpp color; 90 degrees clockwise display rotation for
panels <= 320 pixel horizontal resolution.
-config FB_DA8XX
- tristate "DA8xx/OMAP-L1xx/AM335x Framebuffer support"
- depends on FB && HAVE_CLK && HAS_IOMEM
- depends on ARCH_DAVINCI_DA8XX || SOC_AM33XX || COMPILE_TEST
- select FB_CFB_REV_PIXELS_IN_BYTE
- select FB_IOMEM_HELPERS
- select FB_MODE_HELPERS
- select VIDEOMODE_HELPERS
- help
- This is the frame buffer device driver for the TI LCD controller
- found on DA8xx/OMAP-L1xx/AM335x SoCs.
- If unsure, say N.
-
config FB_VIRTUAL
tristate "Virtual Frame Buffer support (ONLY FOR TESTING!)"
depends on FB
diff --git a/drivers/video/fbdev/Makefile b/drivers/video/fbdev/Makefile
index 3eecd51..b3d12f9 100644
--- a/drivers/video/fbdev/Makefile
+++ b/drivers/video/fbdev/Makefile
@@ -121,7 +121,6 @@
obj-$(CONFIG_FB_EFI) += efifb.o
obj-$(CONFIG_FB_VGA16) += vga16fb.o
obj-$(CONFIG_FB_OF) += offb.o
-obj-$(CONFIG_FB_DA8XX) += da8xx-fb.o
obj-$(CONFIG_FB_SSD1307) += ssd1307fb.o
obj-$(CONFIG_FB_SIMPLE) += simplefb.o
diff --git a/drivers/video/fbdev/bw2.c b/drivers/video/fbdev/bw2.c
index 4a64940..e757462 100644
--- a/drivers/video/fbdev/bw2.c
+++ b/drivers/video/fbdev/bw2.c
@@ -147,7 +147,7 @@ bw2_blank(int blank, struct fb_info *info)
return 0;
}
-static struct sbus_mmap_map bw2_mmap_map[] = {
+static const struct sbus_mmap_map bw2_mmap_map[] = {
{
.size = SBUS_MMAP_FBSIZE(1)
},
diff --git a/drivers/video/fbdev/cg14.c b/drivers/video/fbdev/cg14.c
index 430e1a7..5389f8f 100644
--- a/drivers/video/fbdev/cg14.c
+++ b/drivers/video/fbdev/cg14.c
@@ -360,7 +360,7 @@ static void cg14_init_fix(struct fb_info *info, int linebytes,
info->fix.accel = FB_ACCEL_SUN_CG14;
}
-static struct sbus_mmap_map __cg14_mmap_map[CG14_MMAP_ENTRIES] = {
+static const struct sbus_mmap_map __cg14_mmap_map[CG14_MMAP_ENTRIES] = {
{
.voff = CG14_REGS,
.poff = 0x80000000,
diff --git a/drivers/video/fbdev/cg3.c b/drivers/video/fbdev/cg3.c
index e4c53c6..a58a483 100644
--- a/drivers/video/fbdev/cg3.c
+++ b/drivers/video/fbdev/cg3.c
@@ -209,7 +209,7 @@ static int cg3_blank(int blank, struct fb_info *info)
return 0;
}
-static struct sbus_mmap_map cg3_mmap_map[] = {
+static const struct sbus_mmap_map cg3_mmap_map[] = {
{
.voff = CG3_MMAP_OFFSET,
.poff = CG3_RAM_OFFSET,
diff --git a/drivers/video/fbdev/cg6.c b/drivers/video/fbdev/cg6.c
index 0b60df5..56d7446 100644
--- a/drivers/video/fbdev/cg6.c
+++ b/drivers/video/fbdev/cg6.c
@@ -545,7 +545,7 @@ static int cg6_blank(int blank, struct fb_info *info)
return 0;
}
-static struct sbus_mmap_map cg6_mmap_map[] = {
+static const struct sbus_mmap_map cg6_mmap_map[] = {
{
.voff = CG6_FBC,
.poff = CG6_FBC_OFFSET,
diff --git a/drivers/video/fbdev/da8xx-fb.c b/drivers/video/fbdev/da8xx-fb.c
deleted file mode 100644
index fad1e13..0000000
--- a/drivers/video/fbdev/da8xx-fb.c
+++ /dev/null
@@ -1,1665 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2008-2009 MontaVista Software Inc.
- * Copyright (C) 2008-2009 Texas Instruments Inc
- *
- * Based on the LCD driver for TI Avalanche processors written by
- * Ajay Singh and Shalom Hai.
- */
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/fb.h>
-#include <linux/dma-mapping.h>
-#include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/uaccess.h>
-#include <linux/pm_runtime.h>
-#include <linux/interrupt.h>
-#include <linux/wait.h>
-#include <linux/clk.h>
-#include <linux/cpufreq.h>
-#include <linux/console.h>
-#include <linux/regulator/consumer.h>
-#include <linux/spinlock.h>
-#include <linux/slab.h>
-#include <linux/delay.h>
-#include <linux/lcm.h>
-#include <video/da8xx-fb.h>
-#include <asm/div64.h>
-
-#define DRIVER_NAME "da8xx_lcdc"
-
-#define LCD_VERSION_1 1
-#define LCD_VERSION_2 2
-
-/* LCD Status Register */
-#define LCD_END_OF_FRAME1 BIT(9)
-#define LCD_END_OF_FRAME0 BIT(8)
-#define LCD_PL_LOAD_DONE BIT(6)
-#define LCD_FIFO_UNDERFLOW BIT(5)
-#define LCD_SYNC_LOST BIT(2)
-#define LCD_FRAME_DONE BIT(0)
-
-/* LCD DMA Control Register */
-#define LCD_DMA_BURST_SIZE(x) ((x) << 4)
-#define LCD_DMA_BURST_1 0x0
-#define LCD_DMA_BURST_2 0x1
-#define LCD_DMA_BURST_4 0x2
-#define LCD_DMA_BURST_8 0x3
-#define LCD_DMA_BURST_16 0x4
-#define LCD_V1_END_OF_FRAME_INT_ENA BIT(2)
-#define LCD_V2_END_OF_FRAME0_INT_ENA BIT(8)
-#define LCD_V2_END_OF_FRAME1_INT_ENA BIT(9)
-#define LCD_DUAL_FRAME_BUFFER_ENABLE BIT(0)
-
-/* LCD Control Register */
-#define LCD_CLK_DIVISOR(x) ((x) << 8)
-#define LCD_RASTER_MODE 0x01
-
-/* LCD Raster Control Register */
-#define LCD_PALETTE_LOAD_MODE(x) ((x) << 20)
-#define PALETTE_AND_DATA 0x00
-#define PALETTE_ONLY 0x01
-#define DATA_ONLY 0x02
-
-#define LCD_MONO_8BIT_MODE BIT(9)
-#define LCD_RASTER_ORDER BIT(8)
-#define LCD_TFT_MODE BIT(7)
-#define LCD_V1_UNDERFLOW_INT_ENA BIT(6)
-#define LCD_V2_UNDERFLOW_INT_ENA BIT(5)
-#define LCD_V1_PL_INT_ENA BIT(4)
-#define LCD_V2_PL_INT_ENA BIT(6)
-#define LCD_MONOCHROME_MODE BIT(1)
-#define LCD_RASTER_ENABLE BIT(0)
-#define LCD_TFT_ALT_ENABLE BIT(23)
-#define LCD_STN_565_ENABLE BIT(24)
-#define LCD_V2_DMA_CLK_EN BIT(2)
-#define LCD_V2_LIDD_CLK_EN BIT(1)
-#define LCD_V2_CORE_CLK_EN BIT(0)
-#define LCD_V2_LPP_B10 26
-#define LCD_V2_TFT_24BPP_MODE BIT(25)
-#define LCD_V2_TFT_24BPP_UNPACK BIT(26)
-
-/* LCD Raster Timing 2 Register */
-#define LCD_AC_BIAS_TRANSITIONS_PER_INT(x) ((x) << 16)
-#define LCD_AC_BIAS_FREQUENCY(x) ((x) << 8)
-#define LCD_SYNC_CTRL BIT(25)
-#define LCD_SYNC_EDGE BIT(24)
-#define LCD_INVERT_PIXEL_CLOCK BIT(22)
-#define LCD_INVERT_LINE_CLOCK BIT(21)
-#define LCD_INVERT_FRAME_CLOCK BIT(20)
-
-/* LCD Block */
-#define LCD_PID_REG 0x0
-#define LCD_CTRL_REG 0x4
-#define LCD_STAT_REG 0x8
-#define LCD_RASTER_CTRL_REG 0x28
-#define LCD_RASTER_TIMING_0_REG 0x2C
-#define LCD_RASTER_TIMING_1_REG 0x30
-#define LCD_RASTER_TIMING_2_REG 0x34
-#define LCD_DMA_CTRL_REG 0x40
-#define LCD_DMA_FRM_BUF_BASE_ADDR_0_REG 0x44
-#define LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG 0x48
-#define LCD_DMA_FRM_BUF_BASE_ADDR_1_REG 0x4C
-#define LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG 0x50
-
-/* Interrupt Registers available only in Version 2 */
-#define LCD_RAW_STAT_REG 0x58
-#define LCD_MASKED_STAT_REG 0x5c
-#define LCD_INT_ENABLE_SET_REG 0x60
-#define LCD_INT_ENABLE_CLR_REG 0x64
-#define LCD_END_OF_INT_IND_REG 0x68
-
-/* Clock registers available only on Version 2 */
-#define LCD_CLK_ENABLE_REG 0x6c
-#define LCD_CLK_RESET_REG 0x70
-#define LCD_CLK_MAIN_RESET BIT(3)
-
-#define LCD_NUM_BUFFERS 2
-
-#define PALETTE_SIZE 256
-
-#define CLK_MIN_DIV 2
-#define CLK_MAX_DIV 255
-
-static void __iomem *da8xx_fb_reg_base;
-static unsigned int lcd_revision;
-static irq_handler_t lcdc_irq_handler;
-static wait_queue_head_t frame_done_wq;
-static int frame_done_flag;
-
-static unsigned int lcdc_read(unsigned int addr)
-{
- return (unsigned int)__raw_readl(da8xx_fb_reg_base + (addr));
-}
-
-static void lcdc_write(unsigned int val, unsigned int addr)
-{
- __raw_writel(val, da8xx_fb_reg_base + (addr));
-}
-
-struct da8xx_fb_par {
- struct device *dev;
- dma_addr_t p_palette_base;
- unsigned char *v_palette_base;
- dma_addr_t vram_phys;
- unsigned long vram_size;
- void *vram_virt;
- unsigned int dma_start;
- unsigned int dma_end;
- struct clk *lcdc_clk;
- int irq;
- unsigned int palette_sz;
- int blank;
- wait_queue_head_t vsync_wait;
- int vsync_flag;
- int vsync_timeout;
- spinlock_t lock_for_chan_update;
-
- /*
- * LCDC has 2 ping pong DMA channels, channel 0
- * and channel 1.
- */
- unsigned int which_dma_channel_done;
-#ifdef CONFIG_CPU_FREQ
- struct notifier_block freq_transition;
-#endif
- unsigned int lcdc_clk_rate;
- struct regulator *lcd_supply;
- u32 pseudo_palette[16];
- struct fb_videomode mode;
- struct lcd_ctrl_config cfg;
-};
-
-static struct fb_var_screeninfo da8xx_fb_var;
-
-static struct fb_fix_screeninfo da8xx_fb_fix = {
- .id = "DA8xx FB Drv",
- .type = FB_TYPE_PACKED_PIXELS,
- .type_aux = 0,
- .visual = FB_VISUAL_PSEUDOCOLOR,
- .xpanstep = 0,
- .ypanstep = 1,
- .ywrapstep = 0,
- .accel = FB_ACCEL_NONE
-};
-
-static struct fb_videomode known_lcd_panels[] = {
- /* Sharp LCD035Q3DG01 */
- [0] = {
- .name = "Sharp_LCD035Q3DG01",
- .xres = 320,
- .yres = 240,
- .pixclock = KHZ2PICOS(4607),
- .left_margin = 6,
- .right_margin = 8,
- .upper_margin = 2,
- .lower_margin = 2,
- .hsync_len = 0,
- .vsync_len = 0,
- .sync = FB_SYNC_CLK_INVERT,
- },
- /* Sharp LK043T1DG01 */
- [1] = {
- .name = "Sharp_LK043T1DG01",
- .xres = 480,
- .yres = 272,
- .pixclock = KHZ2PICOS(7833),
- .left_margin = 2,
- .right_margin = 2,
- .upper_margin = 2,
- .lower_margin = 2,
- .hsync_len = 41,
- .vsync_len = 10,
- .sync = 0,
- .flag = 0,
- },
- [2] = {
- /* Hitachi SP10Q010 */
- .name = "SP10Q010",
- .xres = 320,
- .yres = 240,
- .pixclock = KHZ2PICOS(7833),
- .left_margin = 10,
- .right_margin = 10,
- .upper_margin = 10,
- .lower_margin = 10,
- .hsync_len = 10,
- .vsync_len = 10,
- .sync = 0,
- .flag = 0,
- },
- [3] = {
- /* Densitron 84-0023-001T */
- .name = "Densitron_84-0023-001T",
- .xres = 320,
- .yres = 240,
- .pixclock = KHZ2PICOS(6400),
- .left_margin = 0,
- .right_margin = 0,
- .upper_margin = 0,
- .lower_margin = 0,
- .hsync_len = 30,
- .vsync_len = 3,
- .sync = 0,
- },
-};
-
-static bool da8xx_fb_is_raster_enabled(void)
-{
- return !!(lcdc_read(LCD_RASTER_CTRL_REG) & LCD_RASTER_ENABLE);
-}
-
-/* Enable the Raster Engine of the LCD Controller */
-static void lcd_enable_raster(void)
-{
- u32 reg;
-
- /* Put LCDC in reset for several cycles */
- if (lcd_revision == LCD_VERSION_2)
- /* Write 1 to reset LCDC */
- lcdc_write(LCD_CLK_MAIN_RESET, LCD_CLK_RESET_REG);
- mdelay(1);
-
- /* Bring LCDC out of reset */
- if (lcd_revision == LCD_VERSION_2)
- lcdc_write(0, LCD_CLK_RESET_REG);
- mdelay(1);
-
- /* Above reset sequence doesnot reset register context */
- reg = lcdc_read(LCD_RASTER_CTRL_REG);
- if (!(reg & LCD_RASTER_ENABLE))
- lcdc_write(reg | LCD_RASTER_ENABLE, LCD_RASTER_CTRL_REG);
-}
-
-/* Disable the Raster Engine of the LCD Controller */
-static void lcd_disable_raster(enum da8xx_frame_complete wait_for_frame_done)
-{
- u32 reg;
- int ret;
-
- reg = lcdc_read(LCD_RASTER_CTRL_REG);
- if (reg & LCD_RASTER_ENABLE)
- lcdc_write(reg & ~LCD_RASTER_ENABLE, LCD_RASTER_CTRL_REG);
- else
- /* return if already disabled */
- return;
-
- if ((wait_for_frame_done == DA8XX_FRAME_WAIT) &&
- (lcd_revision == LCD_VERSION_2)) {
- frame_done_flag = 0;
- ret = wait_event_interruptible_timeout(frame_done_wq,
- frame_done_flag != 0,
- msecs_to_jiffies(50));
- if (ret == 0)
- pr_err("LCD Controller timed out\n");
- }
-}
-
-static void lcd_blit(int load_mode, struct da8xx_fb_par *par)
-{
- u32 start;
- u32 end;
- u32 reg_ras;
- u32 reg_dma;
- u32 reg_int;
-
- /* init reg to clear PLM (loading mode) fields */
- reg_ras = lcdc_read(LCD_RASTER_CTRL_REG);
- reg_ras &= ~(3 << 20);
-
- reg_dma = lcdc_read(LCD_DMA_CTRL_REG);
-
- if (load_mode == LOAD_DATA) {
- start = par->dma_start;
- end = par->dma_end;
-
- reg_ras |= LCD_PALETTE_LOAD_MODE(DATA_ONLY);
- if (lcd_revision == LCD_VERSION_1) {
- reg_dma |= LCD_V1_END_OF_FRAME_INT_ENA;
- } else {
- reg_int = lcdc_read(LCD_INT_ENABLE_SET_REG) |
- LCD_V2_END_OF_FRAME0_INT_ENA |
- LCD_V2_END_OF_FRAME1_INT_ENA |
- LCD_FRAME_DONE | LCD_SYNC_LOST;
- lcdc_write(reg_int, LCD_INT_ENABLE_SET_REG);
- }
- reg_dma |= LCD_DUAL_FRAME_BUFFER_ENABLE;
-
- lcdc_write(start, LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
- lcdc_write(end, LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG);
- lcdc_write(start, LCD_DMA_FRM_BUF_BASE_ADDR_1_REG);
- lcdc_write(end, LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG);
- } else if (load_mode == LOAD_PALETTE) {
- start = par->p_palette_base;
- end = start + par->palette_sz - 1;
-
- reg_ras |= LCD_PALETTE_LOAD_MODE(PALETTE_ONLY);
-
- if (lcd_revision == LCD_VERSION_1) {
- reg_ras |= LCD_V1_PL_INT_ENA;
- } else {
- reg_int = lcdc_read(LCD_INT_ENABLE_SET_REG) |
- LCD_V2_PL_INT_ENA;
- lcdc_write(reg_int, LCD_INT_ENABLE_SET_REG);
- }
-
- lcdc_write(start, LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
- lcdc_write(end, LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG);
- }
-
- lcdc_write(reg_dma, LCD_DMA_CTRL_REG);
- lcdc_write(reg_ras, LCD_RASTER_CTRL_REG);
-
- /*
- * The Raster enable bit must be set after all other control fields are
- * set.
- */
- lcd_enable_raster();
-}
-
-/* Configure the Burst Size and fifo threhold of DMA */
-static int lcd_cfg_dma(int burst_size, int fifo_th)
-{
- u32 reg;
-
- reg = lcdc_read(LCD_DMA_CTRL_REG) & 0x00000001;
- switch (burst_size) {
- case 1:
- reg |= LCD_DMA_BURST_SIZE(LCD_DMA_BURST_1);
- break;
- case 2:
- reg |= LCD_DMA_BURST_SIZE(LCD_DMA_BURST_2);
- break;
- case 4:
- reg |= LCD_DMA_BURST_SIZE(LCD_DMA_BURST_4);
- break;
- case 8:
- reg |= LCD_DMA_BURST_SIZE(LCD_DMA_BURST_8);
- break;
- case 16:
- default:
- reg |= LCD_DMA_BURST_SIZE(LCD_DMA_BURST_16);
- break;
- }
-
- reg |= (fifo_th << 8);
-
- lcdc_write(reg, LCD_DMA_CTRL_REG);
-
- return 0;
-}
-
-static void lcd_cfg_ac_bias(int period, int transitions_per_int)
-{
- u32 reg;
-
- /* Set the AC Bias Period and Number of Transisitons per Interrupt */
- reg = lcdc_read(LCD_RASTER_TIMING_2_REG) & 0xFFF00000;
- reg |= LCD_AC_BIAS_FREQUENCY(period) |
- LCD_AC_BIAS_TRANSITIONS_PER_INT(transitions_per_int);
- lcdc_write(reg, LCD_RASTER_TIMING_2_REG);
-}
-
-static void lcd_cfg_horizontal_sync(int back_porch, int pulse_width,
- int front_porch)
-{
- u32 reg;
-
- reg = lcdc_read(LCD_RASTER_TIMING_0_REG) & 0x3ff;
- reg |= (((back_porch-1) & 0xff) << 24)
- | (((front_porch-1) & 0xff) << 16)
- | (((pulse_width-1) & 0x3f) << 10);
- lcdc_write(reg, LCD_RASTER_TIMING_0_REG);
-
- /*
- * LCDC Version 2 adds some extra bits that increase the allowable
- * size of the horizontal timing registers.
- * remember that the registers use 0 to represent 1 so all values
- * that get set into register need to be decremented by 1
- */
- if (lcd_revision == LCD_VERSION_2) {
- /* Mask off the bits we want to change */
- reg = lcdc_read(LCD_RASTER_TIMING_2_REG) & ~0x780000ff;
- reg |= ((front_porch-1) & 0x300) >> 8;
- reg |= ((back_porch-1) & 0x300) >> 4;
- reg |= ((pulse_width-1) & 0x3c0) << 21;
- lcdc_write(reg, LCD_RASTER_TIMING_2_REG);
- }
-}
-
-static void lcd_cfg_vertical_sync(int back_porch, int pulse_width,
- int front_porch)
-{
- u32 reg;
-
- reg = lcdc_read(LCD_RASTER_TIMING_1_REG) & 0x3ff;
- reg |= ((back_porch & 0xff) << 24)
- | ((front_porch & 0xff) << 16)
- | (((pulse_width-1) & 0x3f) << 10);
- lcdc_write(reg, LCD_RASTER_TIMING_1_REG);
-}
-
-static int lcd_cfg_display(const struct lcd_ctrl_config *cfg,
- struct fb_videomode *panel)
-{
- u32 reg;
- u32 reg_int;
-
- reg = lcdc_read(LCD_RASTER_CTRL_REG) & ~(LCD_TFT_MODE |
- LCD_MONO_8BIT_MODE |
- LCD_MONOCHROME_MODE);
-
- switch (cfg->panel_shade) {
- case MONOCHROME:
- reg |= LCD_MONOCHROME_MODE;
- if (cfg->mono_8bit_mode)
- reg |= LCD_MONO_8BIT_MODE;
- break;
- case COLOR_ACTIVE:
- reg |= LCD_TFT_MODE;
- if (cfg->tft_alt_mode)
- reg |= LCD_TFT_ALT_ENABLE;
- break;
-
- case COLOR_PASSIVE:
- /* AC bias applicable only for Pasive panels */
- lcd_cfg_ac_bias(cfg->ac_bias, cfg->ac_bias_intrpt);
- if (cfg->bpp == 12 && cfg->stn_565_mode)
- reg |= LCD_STN_565_ENABLE;
- break;
-
- default:
- return -EINVAL;
- }
-
- /* enable additional interrupts here */
- if (lcd_revision == LCD_VERSION_1) {
- reg |= LCD_V1_UNDERFLOW_INT_ENA;
- } else {
- reg_int = lcdc_read(LCD_INT_ENABLE_SET_REG) |
- LCD_V2_UNDERFLOW_INT_ENA;
- lcdc_write(reg_int, LCD_INT_ENABLE_SET_REG);
- }
-
- lcdc_write(reg, LCD_RASTER_CTRL_REG);
-
- reg = lcdc_read(LCD_RASTER_TIMING_2_REG);
-
- reg |= LCD_SYNC_CTRL;
-
- if (cfg->sync_edge)
- reg |= LCD_SYNC_EDGE;
- else
- reg &= ~LCD_SYNC_EDGE;
-
- if ((panel->sync & FB_SYNC_HOR_HIGH_ACT) == 0)
- reg |= LCD_INVERT_LINE_CLOCK;
- else
- reg &= ~LCD_INVERT_LINE_CLOCK;
-
- if ((panel->sync & FB_SYNC_VERT_HIGH_ACT) == 0)
- reg |= LCD_INVERT_FRAME_CLOCK;
- else
- reg &= ~LCD_INVERT_FRAME_CLOCK;
-
- lcdc_write(reg, LCD_RASTER_TIMING_2_REG);
-
- return 0;
-}
-
-static int lcd_cfg_frame_buffer(struct da8xx_fb_par *par, u32 width, u32 height,
- u32 bpp, u32 raster_order)
-{
- u32 reg;
-
- if (bpp > 16 && lcd_revision == LCD_VERSION_1)
- return -EINVAL;
-
- /* Set the Panel Width */
- /* Pixels per line = (PPL + 1)*16 */
- if (lcd_revision == LCD_VERSION_1) {
- /*
- * 0x3F in bits 4..9 gives max horizontal resolution = 1024
- * pixels.
- */
- width &= 0x3f0;
- } else {
- /*
- * 0x7F in bits 4..10 gives max horizontal resolution = 2048
- * pixels.
- */
- width &= 0x7f0;
- }
-
- reg = lcdc_read(LCD_RASTER_TIMING_0_REG);
- reg &= 0xfffffc00;
- if (lcd_revision == LCD_VERSION_1) {
- reg |= ((width >> 4) - 1) << 4;
- } else {
- width = (width >> 4) - 1;
- reg |= ((width & 0x3f) << 4) | ((width & 0x40) >> 3);
- }
- lcdc_write(reg, LCD_RASTER_TIMING_0_REG);
-
- /* Set the Panel Height */
- /* Set bits 9:0 of Lines Per Pixel */
- reg = lcdc_read(LCD_RASTER_TIMING_1_REG);
- reg = ((height - 1) & 0x3ff) | (reg & 0xfffffc00);
- lcdc_write(reg, LCD_RASTER_TIMING_1_REG);
-
- /* Set bit 10 of Lines Per Pixel */
- if (lcd_revision == LCD_VERSION_2) {
- reg = lcdc_read(LCD_RASTER_TIMING_2_REG);
- reg |= ((height - 1) & 0x400) << 16;
- lcdc_write(reg, LCD_RASTER_TIMING_2_REG);
- }
-
- /* Set the Raster Order of the Frame Buffer */
- reg = lcdc_read(LCD_RASTER_CTRL_REG) & ~(1 << 8);
- if (raster_order)
- reg |= LCD_RASTER_ORDER;
-
- par->palette_sz = 16 * 2;
-
- switch (bpp) {
- case 1:
- case 2:
- case 4:
- case 16:
- break;
- case 24:
- reg |= LCD_V2_TFT_24BPP_MODE;
- break;
- case 32:
- reg |= LCD_V2_TFT_24BPP_MODE;
- reg |= LCD_V2_TFT_24BPP_UNPACK;
- break;
- case 8:
- par->palette_sz = 256 * 2;
- break;
-
- default:
- return -EINVAL;
- }
-
- lcdc_write(reg, LCD_RASTER_CTRL_REG);
-
- return 0;
-}
-
-#define CNVT_TOHW(val, width) ((((val) << (width)) + 0x7FFF - (val)) >> 16)
-static int fb_setcolreg(unsigned regno, unsigned red, unsigned green,
- unsigned blue, unsigned transp,
- struct fb_info *info)
-{
- struct da8xx_fb_par *par = info->par;
- unsigned short *palette = (unsigned short *) par->v_palette_base;
- u_short pal;
- int update_hw = 0;
-
- if (regno > 255)
- return 1;
-
- if (info->fix.visual == FB_VISUAL_DIRECTCOLOR)
- return 1;
-
- if (info->var.bits_per_pixel > 16 && lcd_revision == LCD_VERSION_1)
- return -EINVAL;
-
- switch (info->fix.visual) {
- case FB_VISUAL_TRUECOLOR:
- red = CNVT_TOHW(red, info->var.red.length);
- green = CNVT_TOHW(green, info->var.green.length);
- blue = CNVT_TOHW(blue, info->var.blue.length);
- break;
- case FB_VISUAL_PSEUDOCOLOR:
- switch (info->var.bits_per_pixel) {
- case 4:
- if (regno > 15)
- return -EINVAL;
-
- if (info->var.grayscale) {
- pal = regno;
- } else {
- red >>= 4;
- green >>= 8;
- blue >>= 12;
-
- pal = red & 0x0f00;
- pal |= green & 0x00f0;
- pal |= blue & 0x000f;
- }
- if (regno == 0)
- pal |= 0x2000;
- palette[regno] = pal;
- break;
-
- case 8:
- red >>= 4;
- green >>= 8;
- blue >>= 12;
-
- pal = (red & 0x0f00);
- pal |= (green & 0x00f0);
- pal |= (blue & 0x000f);
-
- if (palette[regno] != pal) {
- update_hw = 1;
- palette[regno] = pal;
- }
- break;
- }
- break;
- }
-
- /* Truecolor has hardware independent palette */
- if (info->fix.visual == FB_VISUAL_TRUECOLOR) {
- u32 v;
-
- if (regno > 15)
- return -EINVAL;
-
- v = (red << info->var.red.offset) |
- (green << info->var.green.offset) |
- (blue << info->var.blue.offset);
-
- ((u32 *) (info->pseudo_palette))[regno] = v;
- if (palette[0] != 0x4000) {
- update_hw = 1;
- palette[0] = 0x4000;
- }
- }
-
- /* Update the palette in the h/w as needed. */
- if (update_hw)
- lcd_blit(LOAD_PALETTE, par);
-
- return 0;
-}
-#undef CNVT_TOHW
-
-static void da8xx_fb_lcd_reset(void)
-{
- /* DMA has to be disabled */
- lcdc_write(0, LCD_DMA_CTRL_REG);
- lcdc_write(0, LCD_RASTER_CTRL_REG);
-
- if (lcd_revision == LCD_VERSION_2) {
- lcdc_write(0, LCD_INT_ENABLE_SET_REG);
- /* Write 1 to reset */
- lcdc_write(LCD_CLK_MAIN_RESET, LCD_CLK_RESET_REG);
- lcdc_write(0, LCD_CLK_RESET_REG);
- }
-}
-
-static int da8xx_fb_config_clk_divider(struct da8xx_fb_par *par,
- unsigned lcdc_clk_div,
- unsigned lcdc_clk_rate)
-{
- int ret;
-
- if (par->lcdc_clk_rate != lcdc_clk_rate) {
- ret = clk_set_rate(par->lcdc_clk, lcdc_clk_rate);
- if (ret) {
- dev_err(par->dev,
- "unable to set clock rate at %u\n",
- lcdc_clk_rate);
- return ret;
- }
- par->lcdc_clk_rate = clk_get_rate(par->lcdc_clk);
- }
-
- /* Configure the LCD clock divisor. */
- lcdc_write(LCD_CLK_DIVISOR(lcdc_clk_div) |
- (LCD_RASTER_MODE & 0x1), LCD_CTRL_REG);
-
- if (lcd_revision == LCD_VERSION_2)
- lcdc_write(LCD_V2_DMA_CLK_EN | LCD_V2_LIDD_CLK_EN |
- LCD_V2_CORE_CLK_EN, LCD_CLK_ENABLE_REG);
-
- return 0;
-}
-
-static unsigned int da8xx_fb_calc_clk_divider(struct da8xx_fb_par *par,
- unsigned pixclock,
- unsigned *lcdc_clk_rate)
-{
- unsigned lcdc_clk_div;
-
- pixclock = PICOS2KHZ(pixclock) * 1000;
-
- *lcdc_clk_rate = par->lcdc_clk_rate;
-
- if (pixclock < (*lcdc_clk_rate / CLK_MAX_DIV)) {
- *lcdc_clk_rate = clk_round_rate(par->lcdc_clk,
- pixclock * CLK_MAX_DIV);
- lcdc_clk_div = CLK_MAX_DIV;
- } else if (pixclock > (*lcdc_clk_rate / CLK_MIN_DIV)) {
- *lcdc_clk_rate = clk_round_rate(par->lcdc_clk,
- pixclock * CLK_MIN_DIV);
- lcdc_clk_div = CLK_MIN_DIV;
- } else {
- lcdc_clk_div = *lcdc_clk_rate / pixclock;
- }
-
- return lcdc_clk_div;
-}
-
-static int da8xx_fb_calc_config_clk_divider(struct da8xx_fb_par *par,
- struct fb_videomode *mode)
-{
- unsigned lcdc_clk_rate;
- unsigned lcdc_clk_div = da8xx_fb_calc_clk_divider(par, mode->pixclock,
- &lcdc_clk_rate);
-
- return da8xx_fb_config_clk_divider(par, lcdc_clk_div, lcdc_clk_rate);
-}
-
-static unsigned da8xx_fb_round_clk(struct da8xx_fb_par *par,
- unsigned pixclock)
-{
- unsigned lcdc_clk_div, lcdc_clk_rate;
-
- lcdc_clk_div = da8xx_fb_calc_clk_divider(par, pixclock, &lcdc_clk_rate);
- return KHZ2PICOS(lcdc_clk_rate / (1000 * lcdc_clk_div));
-}
-
-static int lcd_init(struct da8xx_fb_par *par, const struct lcd_ctrl_config *cfg,
- struct fb_videomode *panel)
-{
- u32 bpp;
- int ret = 0;
-
- ret = da8xx_fb_calc_config_clk_divider(par, panel);
- if (ret) {
- dev_err(par->dev, "unable to configure clock\n");
- return ret;
- }
-
- if (panel->sync & FB_SYNC_CLK_INVERT)
- lcdc_write((lcdc_read(LCD_RASTER_TIMING_2_REG) |
- LCD_INVERT_PIXEL_CLOCK), LCD_RASTER_TIMING_2_REG);
- else
- lcdc_write((lcdc_read(LCD_RASTER_TIMING_2_REG) &
- ~LCD_INVERT_PIXEL_CLOCK), LCD_RASTER_TIMING_2_REG);
-
- /* Configure the DMA burst size and fifo threshold. */
- ret = lcd_cfg_dma(cfg->dma_burst_sz, cfg->fifo_th);
- if (ret < 0)
- return ret;
-
- /* Configure the vertical and horizontal sync properties. */
- lcd_cfg_vertical_sync(panel->upper_margin, panel->vsync_len,
- panel->lower_margin);
- lcd_cfg_horizontal_sync(panel->left_margin, panel->hsync_len,
- panel->right_margin);
-
- /* Configure for disply */
- ret = lcd_cfg_display(cfg, panel);
- if (ret < 0)
- return ret;
-
- bpp = cfg->bpp;
-
- if (bpp == 12)
- bpp = 16;
- ret = lcd_cfg_frame_buffer(par, (unsigned int)panel->xres,
- (unsigned int)panel->yres, bpp,
- cfg->raster_order);
- if (ret < 0)
- return ret;
-
- /* Configure FDD */
- lcdc_write((lcdc_read(LCD_RASTER_CTRL_REG) & 0xfff00fff) |
- (cfg->fdd << 12), LCD_RASTER_CTRL_REG);
-
- return 0;
-}
-
-/* IRQ handler for version 2 of LCDC */
-static irqreturn_t lcdc_irq_handler_rev02(int irq, void *arg)
-{
- struct da8xx_fb_par *par = arg;
- u32 stat = lcdc_read(LCD_MASKED_STAT_REG);
-
- if ((stat & LCD_SYNC_LOST) && (stat & LCD_FIFO_UNDERFLOW)) {
- lcd_disable_raster(DA8XX_FRAME_NOWAIT);
- lcdc_write(stat, LCD_MASKED_STAT_REG);
- lcd_enable_raster();
- } else if (stat & LCD_PL_LOAD_DONE) {
- /*
- * Must disable raster before changing state of any control bit.
- * And also must be disabled before clearing the PL loading
- * interrupt via the following write to the status register. If
- * this is done after then one gets multiple PL done interrupts.
- */
- lcd_disable_raster(DA8XX_FRAME_NOWAIT);
-
- lcdc_write(stat, LCD_MASKED_STAT_REG);
-
- /* Disable PL completion interrupt */
- lcdc_write(LCD_V2_PL_INT_ENA, LCD_INT_ENABLE_CLR_REG);
-
- /* Setup and start data loading mode */
- lcd_blit(LOAD_DATA, par);
- } else {
- lcdc_write(stat, LCD_MASKED_STAT_REG);
-
- if (stat & LCD_END_OF_FRAME0) {
- par->which_dma_channel_done = 0;
- lcdc_write(par->dma_start,
- LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
- lcdc_write(par->dma_end,
- LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG);
- par->vsync_flag = 1;
- wake_up_interruptible(&par->vsync_wait);
- }
-
- if (stat & LCD_END_OF_FRAME1) {
- par->which_dma_channel_done = 1;
- lcdc_write(par->dma_start,
- LCD_DMA_FRM_BUF_BASE_ADDR_1_REG);
- lcdc_write(par->dma_end,
- LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG);
- par->vsync_flag = 1;
- wake_up_interruptible(&par->vsync_wait);
- }
-
- /* Set only when controller is disabled and at the end of
- * active frame
- */
- if (stat & BIT(0)) {
- frame_done_flag = 1;
- wake_up_interruptible(&frame_done_wq);
- }
- }
-
- lcdc_write(0, LCD_END_OF_INT_IND_REG);
- return IRQ_HANDLED;
-}
-
-/* IRQ handler for version 1 LCDC */
-static irqreturn_t lcdc_irq_handler_rev01(int irq, void *arg)
-{
- struct da8xx_fb_par *par = arg;
- u32 stat = lcdc_read(LCD_STAT_REG);
- u32 reg_ras;
-
- if ((stat & LCD_SYNC_LOST) && (stat & LCD_FIFO_UNDERFLOW)) {
- lcd_disable_raster(DA8XX_FRAME_NOWAIT);
- lcdc_write(stat, LCD_STAT_REG);
- lcd_enable_raster();
- } else if (stat & LCD_PL_LOAD_DONE) {
- /*
- * Must disable raster before changing state of any control bit.
- * And also must be disabled before clearing the PL loading
- * interrupt via the following write to the status register. If
- * this is done after then one gets multiple PL done interrupts.
- */
- lcd_disable_raster(DA8XX_FRAME_NOWAIT);
-
- lcdc_write(stat, LCD_STAT_REG);
-
- /* Disable PL completion inerrupt */
- reg_ras = lcdc_read(LCD_RASTER_CTRL_REG);
- reg_ras &= ~LCD_V1_PL_INT_ENA;
- lcdc_write(reg_ras, LCD_RASTER_CTRL_REG);
-
- /* Setup and start data loading mode */
- lcd_blit(LOAD_DATA, par);
- } else {
- lcdc_write(stat, LCD_STAT_REG);
-
- if (stat & LCD_END_OF_FRAME0) {
- par->which_dma_channel_done = 0;
- lcdc_write(par->dma_start,
- LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
- lcdc_write(par->dma_end,
- LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG);
- par->vsync_flag = 1;
- wake_up_interruptible(&par->vsync_wait);
- }
-
- if (stat & LCD_END_OF_FRAME1) {
- par->which_dma_channel_done = 1;
- lcdc_write(par->dma_start,
- LCD_DMA_FRM_BUF_BASE_ADDR_1_REG);
- lcdc_write(par->dma_end,
- LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG);
- par->vsync_flag = 1;
- wake_up_interruptible(&par->vsync_wait);
- }
- }
-
- return IRQ_HANDLED;
-}
-
-static int fb_check_var(struct fb_var_screeninfo *var,
- struct fb_info *info)
-{
- int err = 0;
- struct da8xx_fb_par *par = info->par;
- int bpp = var->bits_per_pixel >> 3;
- unsigned long line_size = var->xres_virtual * bpp;
-
- if (var->bits_per_pixel > 16 && lcd_revision == LCD_VERSION_1)
- return -EINVAL;
-
- switch (var->bits_per_pixel) {
- case 1:
- case 8:
- var->red.offset = 0;
- var->red.length = 8;
- var->green.offset = 0;
- var->green.length = 8;
- var->blue.offset = 0;
- var->blue.length = 8;
- var->transp.offset = 0;
- var->transp.length = 0;
- var->nonstd = 0;
- break;
- case 4:
- var->red.offset = 0;
- var->red.length = 4;
- var->green.offset = 0;
- var->green.length = 4;
- var->blue.offset = 0;
- var->blue.length = 4;
- var->transp.offset = 0;
- var->transp.length = 0;
- var->nonstd = FB_NONSTD_REV_PIX_IN_B;
- break;
- case 16: /* RGB 565 */
- var->red.offset = 11;
- var->red.length = 5;
- var->green.offset = 5;
- var->green.length = 6;
- var->blue.offset = 0;
- var->blue.length = 5;
- var->transp.offset = 0;
- var->transp.length = 0;
- var->nonstd = 0;
- break;
- case 24:
- var->red.offset = 16;
- var->red.length = 8;
- var->green.offset = 8;
- var->green.length = 8;
- var->blue.offset = 0;
- var->blue.length = 8;
- var->nonstd = 0;
- break;
- case 32:
- var->transp.offset = 24;
- var->transp.length = 8;
- var->red.offset = 16;
- var->red.length = 8;
- var->green.offset = 8;
- var->green.length = 8;
- var->blue.offset = 0;
- var->blue.length = 8;
- var->nonstd = 0;
- break;
- default:
- err = -EINVAL;
- }
-
- var->red.msb_right = 0;
- var->green.msb_right = 0;
- var->blue.msb_right = 0;
- var->transp.msb_right = 0;
-
- if (line_size * var->yres_virtual > par->vram_size)
- var->yres_virtual = par->vram_size / line_size;
-
- if (var->yres > var->yres_virtual)
- var->yres = var->yres_virtual;
-
- if (var->xres > var->xres_virtual)
- var->xres = var->xres_virtual;
-
- if (var->xres + var->xoffset > var->xres_virtual)
- var->xoffset = var->xres_virtual - var->xres;
- if (var->yres + var->yoffset > var->yres_virtual)
- var->yoffset = var->yres_virtual - var->yres;
-
- var->pixclock = da8xx_fb_round_clk(par, var->pixclock);
-
- return err;
-}
-
-#ifdef CONFIG_CPU_FREQ
-static int lcd_da8xx_cpufreq_transition(struct notifier_block *nb,
- unsigned long val, void *data)
-{
- struct da8xx_fb_par *par;
-
- par = container_of(nb, struct da8xx_fb_par, freq_transition);
- if (val == CPUFREQ_POSTCHANGE) {
- if (par->lcdc_clk_rate != clk_get_rate(par->lcdc_clk)) {
- par->lcdc_clk_rate = clk_get_rate(par->lcdc_clk);
- lcd_disable_raster(DA8XX_FRAME_WAIT);
- da8xx_fb_calc_config_clk_divider(par, &par->mode);
- if (par->blank == FB_BLANK_UNBLANK)
- lcd_enable_raster();
- }
- }
-
- return 0;
-}
-
-static int lcd_da8xx_cpufreq_register(struct da8xx_fb_par *par)
-{
- par->freq_transition.notifier_call = lcd_da8xx_cpufreq_transition;
-
- return cpufreq_register_notifier(&par->freq_transition,
- CPUFREQ_TRANSITION_NOTIFIER);
-}
-
-static void lcd_da8xx_cpufreq_deregister(struct da8xx_fb_par *par)
-{
- cpufreq_unregister_notifier(&par->freq_transition,
- CPUFREQ_TRANSITION_NOTIFIER);
-}
-#endif
-
-static void fb_remove(struct platform_device *dev)
-{
- struct fb_info *info = platform_get_drvdata(dev);
- struct da8xx_fb_par *par = info->par;
- int ret;
-
-#ifdef CONFIG_CPU_FREQ
- lcd_da8xx_cpufreq_deregister(par);
-#endif
- if (par->lcd_supply) {
- ret = regulator_disable(par->lcd_supply);
- if (ret)
- dev_warn(&dev->dev, "Failed to disable regulator (%pe)\n",
- ERR_PTR(ret));
- }
-
- lcd_disable_raster(DA8XX_FRAME_WAIT);
- lcdc_write(0, LCD_RASTER_CTRL_REG);
-
- /* disable DMA */
- lcdc_write(0, LCD_DMA_CTRL_REG);
-
- unregister_framebuffer(info);
- fb_dealloc_cmap(&info->cmap);
- pm_runtime_put_sync(&dev->dev);
- pm_runtime_disable(&dev->dev);
- framebuffer_release(info);
-}
-
-/*
- * Function to wait for vertical sync which for this LCD peripheral
- * translates into waiting for the current raster frame to complete.
- */
-static int fb_wait_for_vsync(struct fb_info *info)
-{
- struct da8xx_fb_par *par = info->par;
- int ret;
-
- /*
- * Set flag to 0 and wait for isr to set to 1. It would seem there is a
- * race condition here where the ISR could have occurred just before or
- * just after this set. But since we are just coarsely waiting for
- * a frame to complete then that's OK. i.e. if the frame completed
- * just before this code executed then we have to wait another full
- * frame time but there is no way to avoid such a situation. On the
- * other hand if the frame completed just after then we don't need
- * to wait long at all. Either way we are guaranteed to return to the
- * user immediately after a frame completion which is all that is
- * required.
- */
- par->vsync_flag = 0;
- ret = wait_event_interruptible_timeout(par->vsync_wait,
- par->vsync_flag != 0,
- par->vsync_timeout);
- if (ret < 0)
- return ret;
- if (ret == 0)
- return -ETIMEDOUT;
-
- return 0;
-}
-
-static int fb_ioctl(struct fb_info *info, unsigned int cmd,
- unsigned long arg)
-{
- struct lcd_sync_arg sync_arg;
-
- switch (cmd) {
- case FBIOGET_CONTRAST:
- case FBIOPUT_CONTRAST:
- case FBIGET_BRIGHTNESS:
- case FBIPUT_BRIGHTNESS:
- case FBIGET_COLOR:
- case FBIPUT_COLOR:
- return -ENOTTY;
- case FBIPUT_HSYNC:
- if (copy_from_user(&sync_arg, (char *)arg,
- sizeof(struct lcd_sync_arg)))
- return -EFAULT;
- lcd_cfg_horizontal_sync(sync_arg.back_porch,
- sync_arg.pulse_width,
- sync_arg.front_porch);
- break;
- case FBIPUT_VSYNC:
- if (copy_from_user(&sync_arg, (char *)arg,
- sizeof(struct lcd_sync_arg)))
- return -EFAULT;
- lcd_cfg_vertical_sync(sync_arg.back_porch,
- sync_arg.pulse_width,
- sync_arg.front_porch);
- break;
- case FBIO_WAITFORVSYNC:
- return fb_wait_for_vsync(info);
- default:
- return -EINVAL;
- }
- return 0;
-}
-
-static int cfb_blank(int blank, struct fb_info *info)
-{
- struct da8xx_fb_par *par = info->par;
- int ret = 0;
-
- if (par->blank == blank)
- return 0;
-
- par->blank = blank;
- switch (blank) {
- case FB_BLANK_UNBLANK:
- lcd_enable_raster();
-
- if (par->lcd_supply) {
- ret = regulator_enable(par->lcd_supply);
- if (ret)
- return ret;
- }
- break;
- case FB_BLANK_NORMAL:
- case FB_BLANK_VSYNC_SUSPEND:
- case FB_BLANK_HSYNC_SUSPEND:
- case FB_BLANK_POWERDOWN:
- if (par->lcd_supply) {
- ret = regulator_disable(par->lcd_supply);
- if (ret)
- return ret;
- }
-
- lcd_disable_raster(DA8XX_FRAME_WAIT);
- break;
- default:
- ret = -EINVAL;
- }
-
- return ret;
-}
-
-/*
- * Set new x,y offsets in the virtual display for the visible area and switch
- * to the new mode.
- */
-static int da8xx_pan_display(struct fb_var_screeninfo *var,
- struct fb_info *fbi)
-{
- int ret = 0;
- struct fb_var_screeninfo new_var;
- struct da8xx_fb_par *par = fbi->par;
- struct fb_fix_screeninfo *fix = &fbi->fix;
- unsigned int end;
- unsigned int start;
- unsigned long irq_flags;
-
- if (var->xoffset != fbi->var.xoffset ||
- var->yoffset != fbi->var.yoffset) {
- memcpy(&new_var, &fbi->var, sizeof(new_var));
- new_var.xoffset = var->xoffset;
- new_var.yoffset = var->yoffset;
- if (fb_check_var(&new_var, fbi))
- ret = -EINVAL;
- else {
- memcpy(&fbi->var, &new_var, sizeof(new_var));
-
- start = fix->smem_start +
- new_var.yoffset * fix->line_length +
- new_var.xoffset * fbi->var.bits_per_pixel / 8;
- end = start + fbi->var.yres * fix->line_length - 1;
- par->dma_start = start;
- par->dma_end = end;
- spin_lock_irqsave(&par->lock_for_chan_update,
- irq_flags);
- if (par->which_dma_channel_done == 0) {
- lcdc_write(par->dma_start,
- LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
- lcdc_write(par->dma_end,
- LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG);
- } else if (par->which_dma_channel_done == 1) {
- lcdc_write(par->dma_start,
- LCD_DMA_FRM_BUF_BASE_ADDR_1_REG);
- lcdc_write(par->dma_end,
- LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG);
- }
- spin_unlock_irqrestore(&par->lock_for_chan_update,
- irq_flags);
- }
- }
-
- return ret;
-}
-
-static int da8xxfb_set_par(struct fb_info *info)
-{
- struct da8xx_fb_par *par = info->par;
- int ret;
- bool raster = da8xx_fb_is_raster_enabled();
-
- if (raster)
- lcd_disable_raster(DA8XX_FRAME_WAIT);
-
- fb_var_to_videomode(&par->mode, &info->var);
-
- par->cfg.bpp = info->var.bits_per_pixel;
-
- info->fix.visual = (par->cfg.bpp <= 8) ?
- FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_TRUECOLOR;
- info->fix.line_length = (par->mode.xres * par->cfg.bpp) / 8;
-
- ret = lcd_init(par, &par->cfg, &par->mode);
- if (ret < 0) {
- dev_err(par->dev, "lcd init failed\n");
- return ret;
- }
-
- par->dma_start = info->fix.smem_start +
- info->var.yoffset * info->fix.line_length +
- info->var.xoffset * info->var.bits_per_pixel / 8;
- par->dma_end = par->dma_start +
- info->var.yres * info->fix.line_length - 1;
-
- lcdc_write(par->dma_start, LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
- lcdc_write(par->dma_end, LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG);
- lcdc_write(par->dma_start, LCD_DMA_FRM_BUF_BASE_ADDR_1_REG);
- lcdc_write(par->dma_end, LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG);
-
- if (raster)
- lcd_enable_raster();
-
- return 0;
-}
-
-static const struct fb_ops da8xx_fb_ops = {
- .owner = THIS_MODULE,
- FB_DEFAULT_IOMEM_OPS,
- .fb_check_var = fb_check_var,
- .fb_set_par = da8xxfb_set_par,
- .fb_setcolreg = fb_setcolreg,
- .fb_pan_display = da8xx_pan_display,
- .fb_ioctl = fb_ioctl,
- .fb_blank = cfb_blank,
-};
-
-static struct fb_videomode *da8xx_fb_get_videomode(struct platform_device *dev)
-{
- struct da8xx_lcdc_platform_data *fb_pdata = dev_get_platdata(&dev->dev);
- struct fb_videomode *lcdc_info;
- int i;
-
- for (i = 0, lcdc_info = known_lcd_panels;
- i < ARRAY_SIZE(known_lcd_panels); i++, lcdc_info++) {
- if (strcmp(fb_pdata->type, lcdc_info->name) == 0)
- break;
- }
-
- if (i == ARRAY_SIZE(known_lcd_panels)) {
- dev_err(&dev->dev, "no panel found\n");
- return NULL;
- }
- dev_info(&dev->dev, "found %s panel\n", lcdc_info->name);
-
- return lcdc_info;
-}
-
-static int fb_probe(struct platform_device *device)
-{
- struct da8xx_lcdc_platform_data *fb_pdata =
- dev_get_platdata(&device->dev);
- struct lcd_ctrl_config *lcd_cfg;
- struct fb_videomode *lcdc_info;
- struct fb_info *da8xx_fb_info;
- struct da8xx_fb_par *par;
- struct clk *tmp_lcdc_clk;
- int ret;
- unsigned long ulcm;
-
- if (fb_pdata == NULL) {
- dev_err(&device->dev, "Can not get platform data\n");
- return -ENOENT;
- }
-
- lcdc_info = da8xx_fb_get_videomode(device);
- if (lcdc_info == NULL)
- return -ENODEV;
-
- da8xx_fb_reg_base = devm_platform_ioremap_resource(device, 0);
- if (IS_ERR(da8xx_fb_reg_base))
- return PTR_ERR(da8xx_fb_reg_base);
-
- tmp_lcdc_clk = devm_clk_get(&device->dev, "fck");
- if (IS_ERR(tmp_lcdc_clk))
- return dev_err_probe(&device->dev, PTR_ERR(tmp_lcdc_clk),
- "Can not get device clock\n");
-
- pm_runtime_enable(&device->dev);
- pm_runtime_get_sync(&device->dev);
-
- /* Determine LCD IP Version */
- switch (lcdc_read(LCD_PID_REG)) {
- case 0x4C100102:
- lcd_revision = LCD_VERSION_1;
- break;
- case 0x4F200800:
- case 0x4F201000:
- lcd_revision = LCD_VERSION_2;
- break;
- default:
- dev_warn(&device->dev, "Unknown PID Reg value 0x%x, "
- "defaulting to LCD revision 1\n",
- lcdc_read(LCD_PID_REG));
- lcd_revision = LCD_VERSION_1;
- break;
- }
-
- lcd_cfg = (struct lcd_ctrl_config *)fb_pdata->controller_data;
-
- if (!lcd_cfg) {
- ret = -EINVAL;
- goto err_pm_runtime_disable;
- }
-
- da8xx_fb_info = framebuffer_alloc(sizeof(struct da8xx_fb_par),
- &device->dev);
- if (!da8xx_fb_info) {
- ret = -ENOMEM;
- goto err_pm_runtime_disable;
- }
-
- par = da8xx_fb_info->par;
- par->dev = &device->dev;
- par->lcdc_clk = tmp_lcdc_clk;
- par->lcdc_clk_rate = clk_get_rate(par->lcdc_clk);
-
- par->lcd_supply = devm_regulator_get_optional(&device->dev, "lcd");
- if (IS_ERR(par->lcd_supply)) {
- if (PTR_ERR(par->lcd_supply) == -EPROBE_DEFER) {
- ret = -EPROBE_DEFER;
- goto err_release_fb;
- }
-
- par->lcd_supply = NULL;
- } else {
- ret = regulator_enable(par->lcd_supply);
- if (ret)
- goto err_release_fb;
- }
-
- fb_videomode_to_var(&da8xx_fb_var, lcdc_info);
- par->cfg = *lcd_cfg;
-
- da8xx_fb_lcd_reset();
-
- /* allocate frame buffer */
- par->vram_size = lcdc_info->xres * lcdc_info->yres * lcd_cfg->bpp;
- ulcm = lcm((lcdc_info->xres * lcd_cfg->bpp)/8, PAGE_SIZE);
- par->vram_size = roundup(par->vram_size/8, ulcm);
- par->vram_size = par->vram_size * LCD_NUM_BUFFERS;
-
- par->vram_virt = dmam_alloc_coherent(par->dev,
- par->vram_size,
- &par->vram_phys,
- GFP_KERNEL | GFP_DMA);
- if (!par->vram_virt) {
- dev_err(&device->dev,
- "GLCD: kmalloc for frame buffer failed\n");
- ret = -EINVAL;
- goto err_disable_reg;
- }
-
- da8xx_fb_info->screen_base = (char __iomem *) par->vram_virt;
- da8xx_fb_fix.smem_start = par->vram_phys;
- da8xx_fb_fix.smem_len = par->vram_size;
- da8xx_fb_fix.line_length = (lcdc_info->xres * lcd_cfg->bpp) / 8;
-
- par->dma_start = par->vram_phys;
- par->dma_end = par->dma_start + lcdc_info->yres *
- da8xx_fb_fix.line_length - 1;
-
- /* allocate palette buffer */
- par->v_palette_base = dmam_alloc_coherent(par->dev, PALETTE_SIZE,
- &par->p_palette_base,
- GFP_KERNEL | GFP_DMA);
- if (!par->v_palette_base) {
- dev_err(&device->dev,
- "GLCD: kmalloc for palette buffer failed\n");
- ret = -EINVAL;
- goto err_release_fb;
- }
-
- par->irq = platform_get_irq(device, 0);
- if (par->irq < 0) {
- ret = -ENOENT;
- goto err_release_fb;
- }
-
- da8xx_fb_var.grayscale =
- lcd_cfg->panel_shade == MONOCHROME ? 1 : 0;
- da8xx_fb_var.bits_per_pixel = lcd_cfg->bpp;
-
- /* Initialize fbinfo */
- da8xx_fb_info->fix = da8xx_fb_fix;
- da8xx_fb_info->var = da8xx_fb_var;
- da8xx_fb_info->fbops = &da8xx_fb_ops;
- da8xx_fb_info->pseudo_palette = par->pseudo_palette;
- da8xx_fb_info->fix.visual = (da8xx_fb_info->var.bits_per_pixel <= 8) ?
- FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_TRUECOLOR;
-
- ret = fb_alloc_cmap(&da8xx_fb_info->cmap, PALETTE_SIZE, 0);
- if (ret)
- goto err_disable_reg;
- da8xx_fb_info->cmap.len = par->palette_sz;
-
- /* initialize var_screeninfo */
- da8xx_fb_var.activate = FB_ACTIVATE_FORCE;
- fb_set_var(da8xx_fb_info, &da8xx_fb_var);
-
- platform_set_drvdata(device, da8xx_fb_info);
-
- /* initialize the vsync wait queue */
- init_waitqueue_head(&par->vsync_wait);
- par->vsync_timeout = HZ / 5;
- par->which_dma_channel_done = -1;
- spin_lock_init(&par->lock_for_chan_update);
-
- /* Register the Frame Buffer */
- if (register_framebuffer(da8xx_fb_info) < 0) {
- dev_err(&device->dev,
- "GLCD: Frame Buffer Registration Failed!\n");
- ret = -EINVAL;
- goto err_dealloc_cmap;
- }
-
-#ifdef CONFIG_CPU_FREQ
- ret = lcd_da8xx_cpufreq_register(par);
- if (ret) {
- dev_err(&device->dev, "failed to register cpufreq\n");
- goto err_cpu_freq;
- }
-#endif
-
- if (lcd_revision == LCD_VERSION_1)
- lcdc_irq_handler = lcdc_irq_handler_rev01;
- else {
- init_waitqueue_head(&frame_done_wq);
- lcdc_irq_handler = lcdc_irq_handler_rev02;
- }
-
- ret = devm_request_irq(&device->dev, par->irq, lcdc_irq_handler, 0,
- DRIVER_NAME, par);
- if (ret)
- goto irq_freq;
- return 0;
-
-irq_freq:
-#ifdef CONFIG_CPU_FREQ
- lcd_da8xx_cpufreq_deregister(par);
-err_cpu_freq:
-#endif
- unregister_framebuffer(da8xx_fb_info);
-
-err_dealloc_cmap:
- fb_dealloc_cmap(&da8xx_fb_info->cmap);
-
-err_disable_reg:
- if (par->lcd_supply)
- regulator_disable(par->lcd_supply);
-err_release_fb:
- framebuffer_release(da8xx_fb_info);
-
-err_pm_runtime_disable:
- pm_runtime_put_sync(&device->dev);
- pm_runtime_disable(&device->dev);
-
- return ret;
-}
-
-#ifdef CONFIG_PM_SLEEP
-static struct lcdc_context {
- u32 clk_enable;
- u32 ctrl;
- u32 dma_ctrl;
- u32 raster_timing_0;
- u32 raster_timing_1;
- u32 raster_timing_2;
- u32 int_enable_set;
- u32 dma_frm_buf_base_addr_0;
- u32 dma_frm_buf_ceiling_addr_0;
- u32 dma_frm_buf_base_addr_1;
- u32 dma_frm_buf_ceiling_addr_1;
- u32 raster_ctrl;
-} reg_context;
-
-static void lcd_context_save(void)
-{
- if (lcd_revision == LCD_VERSION_2) {
- reg_context.clk_enable = lcdc_read(LCD_CLK_ENABLE_REG);
- reg_context.int_enable_set = lcdc_read(LCD_INT_ENABLE_SET_REG);
- }
-
- reg_context.ctrl = lcdc_read(LCD_CTRL_REG);
- reg_context.dma_ctrl = lcdc_read(LCD_DMA_CTRL_REG);
- reg_context.raster_timing_0 = lcdc_read(LCD_RASTER_TIMING_0_REG);
- reg_context.raster_timing_1 = lcdc_read(LCD_RASTER_TIMING_1_REG);
- reg_context.raster_timing_2 = lcdc_read(LCD_RASTER_TIMING_2_REG);
- reg_context.dma_frm_buf_base_addr_0 =
- lcdc_read(LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
- reg_context.dma_frm_buf_ceiling_addr_0 =
- lcdc_read(LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG);
- reg_context.dma_frm_buf_base_addr_1 =
- lcdc_read(LCD_DMA_FRM_BUF_BASE_ADDR_1_REG);
- reg_context.dma_frm_buf_ceiling_addr_1 =
- lcdc_read(LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG);
- reg_context.raster_ctrl = lcdc_read(LCD_RASTER_CTRL_REG);
- return;
-}
-
-static void lcd_context_restore(void)
-{
- if (lcd_revision == LCD_VERSION_2) {
- lcdc_write(reg_context.clk_enable, LCD_CLK_ENABLE_REG);
- lcdc_write(reg_context.int_enable_set, LCD_INT_ENABLE_SET_REG);
- }
-
- lcdc_write(reg_context.ctrl, LCD_CTRL_REG);
- lcdc_write(reg_context.dma_ctrl, LCD_DMA_CTRL_REG);
- lcdc_write(reg_context.raster_timing_0, LCD_RASTER_TIMING_0_REG);
- lcdc_write(reg_context.raster_timing_1, LCD_RASTER_TIMING_1_REG);
- lcdc_write(reg_context.raster_timing_2, LCD_RASTER_TIMING_2_REG);
- lcdc_write(reg_context.dma_frm_buf_base_addr_0,
- LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
- lcdc_write(reg_context.dma_frm_buf_ceiling_addr_0,
- LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG);
- lcdc_write(reg_context.dma_frm_buf_base_addr_1,
- LCD_DMA_FRM_BUF_BASE_ADDR_1_REG);
- lcdc_write(reg_context.dma_frm_buf_ceiling_addr_1,
- LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG);
- lcdc_write(reg_context.raster_ctrl, LCD_RASTER_CTRL_REG);
- return;
-}
-
-static int fb_suspend(struct device *dev)
-{
- struct fb_info *info = dev_get_drvdata(dev);
- struct da8xx_fb_par *par = info->par;
- int ret;
-
- console_lock();
- if (par->lcd_supply) {
- ret = regulator_disable(par->lcd_supply);
- if (ret)
- return ret;
- }
-
- fb_set_suspend(info, 1);
- lcd_disable_raster(DA8XX_FRAME_WAIT);
- lcd_context_save();
- pm_runtime_put_sync(dev);
- console_unlock();
-
- return 0;
-}
-static int fb_resume(struct device *dev)
-{
- struct fb_info *info = dev_get_drvdata(dev);
- struct da8xx_fb_par *par = info->par;
- int ret;
-
- console_lock();
- pm_runtime_get_sync(dev);
- lcd_context_restore();
- if (par->blank == FB_BLANK_UNBLANK) {
- lcd_enable_raster();
-
- if (par->lcd_supply) {
- ret = regulator_enable(par->lcd_supply);
- if (ret)
- return ret;
- }
- }
-
- fb_set_suspend(info, 0);
- console_unlock();
-
- return 0;
-}
-#endif
-
-static SIMPLE_DEV_PM_OPS(fb_pm_ops, fb_suspend, fb_resume);
-
-static struct platform_driver da8xx_fb_driver = {
- .probe = fb_probe,
- .remove = fb_remove,
- .driver = {
- .name = DRIVER_NAME,
- .pm = &fb_pm_ops,
- },
-};
-module_platform_driver(da8xx_fb_driver);
-
-MODULE_DESCRIPTION("Framebuffer driver for TI da8xx/omap-l1xx");
-MODULE_AUTHOR("Texas Instruments");
-MODULE_LICENSE("GPL");
diff --git a/drivers/video/fbdev/ffb.c b/drivers/video/fbdev/ffb.c
index 0b7e7b3..34b6abf 100644
--- a/drivers/video/fbdev/ffb.c
+++ b/drivers/video/fbdev/ffb.c
@@ -710,7 +710,7 @@ static int ffb_blank(int blank, struct fb_info *info)
return 0;
}
-static struct sbus_mmap_map ffb_mmap_map[] = {
+static const struct sbus_mmap_map ffb_mmap_map[] = {
{
.voff = FFB_SFB8R_VOFF,
.poff = FFB_SFB8R_POFF,
diff --git a/drivers/video/fbdev/leo.c b/drivers/video/fbdev/leo.c
index 271e2e8..b9fb059 100644
--- a/drivers/video/fbdev/leo.c
+++ b/drivers/video/fbdev/leo.c
@@ -338,7 +338,7 @@ static int leo_blank(int blank, struct fb_info *info)
return 0;
}
-static struct sbus_mmap_map leo_mmap_map[] = {
+static const struct sbus_mmap_map leo_mmap_map[] = {
{
.voff = LEO_SS0_MAP,
.poff = LEO_OFF_SS0,
diff --git a/drivers/video/fbdev/nvidia/nv_hw.c b/drivers/video/fbdev/nvidia/nv_hw.c
index 9b0a324..75afaa0 100644
--- a/drivers/video/fbdev/nvidia/nv_hw.c
+++ b/drivers/video/fbdev/nvidia/nv_hw.c
@@ -1509,10 +1509,10 @@ void NVLoadStateExt(struct nvidia_par *par, RIVA_HW_STATE * state)
NV_WR32(par->PFIFO, 0x0495 * 4, 0x00000001);
NV_WR32(par->PFIFO, 0x0140 * 4, 0x00000001);
- if (!state) {
- par->CurrentState = NULL;
- return;
- }
+ if (!state) {
+ par->CurrentState = NULL;
+ return;
+ }
if (par->Architecture >= NV_ARCH_10) {
if (par->twoHeads) {
diff --git a/drivers/video/fbdev/p9100.c b/drivers/video/fbdev/p9100.c
index 124468f..0bc0f78 100644
--- a/drivers/video/fbdev/p9100.c
+++ b/drivers/video/fbdev/p9100.c
@@ -206,7 +206,7 @@ p9100_blank(int blank, struct fb_info *info)
return 0;
}
-static struct sbus_mmap_map p9100_mmap_map[] = {
+static const struct sbus_mmap_map p9100_mmap_map[] = {
{ CG3_MMAP_OFFSET, 0, SBUS_MMAP_FBSIZE(1) },
{ 0, 0, 0 }
};
diff --git a/drivers/video/fbdev/sbuslib.c b/drivers/video/fbdev/sbuslib.c
index 634e3d1..4c79654 100644
--- a/drivers/video/fbdev/sbuslib.c
+++ b/drivers/video/fbdev/sbuslib.c
@@ -38,7 +38,7 @@ static unsigned long sbusfb_mmapsize(long size, unsigned long fbsize)
return fbsize * (-size);
}
-int sbusfb_mmap_helper(struct sbus_mmap_map *map,
+int sbusfb_mmap_helper(const struct sbus_mmap_map *map,
unsigned long physbase,
unsigned long fbsize,
unsigned long iospace,
diff --git a/drivers/video/fbdev/sbuslib.h b/drivers/video/fbdev/sbuslib.h
index 6466b4c..e9af2dc 100644
--- a/drivers/video/fbdev/sbuslib.h
+++ b/drivers/video/fbdev/sbuslib.h
@@ -19,7 +19,7 @@ struct sbus_mmap_map {
extern void sbusfb_fill_var(struct fb_var_screeninfo *var,
struct device_node *dp, int bpp);
-extern int sbusfb_mmap_helper(struct sbus_mmap_map *map,
+extern int sbusfb_mmap_helper(const struct sbus_mmap_map *map,
unsigned long physbase, unsigned long fbsize,
unsigned long iospace,
struct vm_area_struct *vma);
diff --git a/drivers/video/fbdev/sstfb.c b/drivers/video/fbdev/sstfb.c
index f8ae54c..2ea947f 100644
--- a/drivers/video/fbdev/sstfb.c
+++ b/drivers/video/fbdev/sstfb.c
@@ -716,6 +716,7 @@ static void sstfb_setvgapass( struct fb_info *info, int enable )
pci_write_config_dword(sst_dev, PCI_INIT_ENABLE, tmp);
}
+#ifdef CONFIG_FB_DEVICE
static ssize_t store_vgapass(struct device *device, struct device_attribute *attr,
const char *buf, size_t count)
{
@@ -739,7 +740,8 @@ static ssize_t show_vgapass(struct device *device, struct device_attribute *attr
static struct device_attribute device_attrs[] = {
__ATTR(vgapass, S_IRUGO|S_IWUSR, show_vgapass, store_vgapass)
- };
+};
+#endif
static int sstfb_ioctl(struct fb_info *info, unsigned int cmd,
unsigned long arg)
@@ -1436,9 +1438,10 @@ static int sstfb_probe(struct pci_dev *pdev, const struct pci_device_id *id)
sstfb_clear_screen(info);
+#ifdef CONFIG_FB_DEVICE
if (device_create_file(info->dev, &device_attrs[0]))
printk(KERN_WARNING "sstfb: can't create sysfs entry.\n");
-
+#endif
fb_info(info, "%s frame buffer device at 0x%p\n",
fix->id, info->screen_base);
@@ -1468,7 +1471,9 @@ static void sstfb_remove(struct pci_dev *pdev)
info = pci_get_drvdata(pdev);
par = info->par;
+#ifdef CONFIG_FB_DEVICE
device_remove_file(info->dev, &device_attrs[0]);
+#endif
sst_shutdown(info);
iounmap(info->screen_base);
iounmap(par->mmio_vbase);
diff --git a/drivers/video/fbdev/tcx.c b/drivers/video/fbdev/tcx.c
index 6eb8bb2..f9a0085 100644
--- a/drivers/video/fbdev/tcx.c
+++ b/drivers/video/fbdev/tcx.c
@@ -236,7 +236,7 @@ tcx_blank(int blank, struct fb_info *info)
return 0;
}
-static struct sbus_mmap_map __tcx_mmap_map[TCX_MMAP_ENTRIES] = {
+static const struct sbus_mmap_map __tcx_mmap_map[TCX_MMAP_ENTRIES] = {
{
.voff = TCX_RAM8BIT,
.size = SBUS_MMAP_FBSIZE(1)
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index 1775fcc..698c43d 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -179,14 +179,16 @@ extern int v9fs_vfs_rename(struct mnt_idmap *idmap,
struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags);
-extern struct inode *v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid,
- bool new);
+extern struct inode *v9fs_inode_from_fid(struct v9fs_session_info *v9ses,
+ struct p9_fid *fid,
+ struct super_block *sb, int new);
extern const struct inode_operations v9fs_dir_inode_operations_dotl;
extern const struct inode_operations v9fs_file_inode_operations_dotl;
extern const struct inode_operations v9fs_symlink_inode_operations_dotl;
extern const struct netfs_request_ops v9fs_req_ops;
-extern struct inode *v9fs_fid_iget_dotl(struct super_block *sb,
- struct p9_fid *fid, bool new);
+extern struct inode *v9fs_inode_from_fid_dotl(struct v9fs_session_info *v9ses,
+ struct p9_fid *fid,
+ struct super_block *sb, int new);
/* other default globals */
#define V9FS_PORT 564
@@ -225,12 +227,30 @@ static inline int v9fs_proto_dotl(struct v9fs_session_info *v9ses)
*/
static inline struct inode *
v9fs_get_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
- struct super_block *sb, bool new)
+ struct super_block *sb)
{
if (v9fs_proto_dotl(v9ses))
- return v9fs_fid_iget_dotl(sb, fid, new);
+ return v9fs_inode_from_fid_dotl(v9ses, fid, sb, 0);
else
- return v9fs_fid_iget(sb, fid, new);
+ return v9fs_inode_from_fid(v9ses, fid, sb, 0);
+}
+
+/**
+ * v9fs_get_new_inode_from_fid - Helper routine to populate an inode by
+ * issuing a attribute request
+ * @v9ses: session information
+ * @fid: fid to issue attribute request for
+ * @sb: superblock on which to create inode
+ *
+ */
+static inline struct inode *
+v9fs_get_new_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+ struct super_block *sb)
+{
+ if (v9fs_proto_dotl(v9ses))
+ return v9fs_inode_from_fid_dotl(v9ses, fid, sb, 1);
+ else
+ return v9fs_inode_from_fid(v9ses, fid, sb, 1);
}
#endif
diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h
index 7923c3c..d3aefbe 100644
--- a/fs/9p/v9fs_vfs.h
+++ b/fs/9p/v9fs_vfs.h
@@ -42,7 +42,7 @@ struct inode *v9fs_alloc_inode(struct super_block *sb);
void v9fs_free_inode(struct inode *inode);
void v9fs_set_netfs_context(struct inode *inode);
int v9fs_init_inode(struct v9fs_session_info *v9ses,
- struct inode *inode, struct p9_qid *qid, umode_t mode, dev_t rdev);
+ struct inode *inode, umode_t mode, dev_t rdev);
void v9fs_evict_inode(struct inode *inode);
#if (BITS_PER_LONG == 32)
#define QID2INO(q) ((ino_t) (((q)->path+2) ^ (((q)->path) >> 32)))
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index effb3aa..3e68521 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -256,12 +256,9 @@ void v9fs_set_netfs_context(struct inode *inode)
}
int v9fs_init_inode(struct v9fs_session_info *v9ses,
- struct inode *inode, struct p9_qid *qid, umode_t mode, dev_t rdev)
+ struct inode *inode, umode_t mode, dev_t rdev)
{
int err = 0;
- struct v9fs_inode *v9inode = V9FS_I(inode);
-
- memcpy(&v9inode->qid, qid, sizeof(struct p9_qid));
inode_init_owner(&nop_mnt_idmap, inode, NULL, mode);
inode->i_blocks = 0;
@@ -295,7 +292,6 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses,
inode->i_op = &v9fs_file_inode_operations;
inode->i_fop = &v9fs_file_operations;
}
- mapping_set_large_folios(inode->i_mapping);
break;
case S_IFLNK:
@@ -366,59 +362,105 @@ void v9fs_evict_inode(struct inode *inode)
clear_inode(inode);
}
-struct inode *
-v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid, bool new)
+static int v9fs_test_inode(struct inode *inode, void *data)
+{
+ int umode;
+ dev_t rdev;
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+ struct p9_wstat *st = (struct p9_wstat *)data;
+ struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode);
+
+ umode = p9mode2unixmode(v9ses, st, &rdev);
+ /* don't match inode of different type */
+ if (inode_wrong_type(inode, umode))
+ return 0;
+
+ /* compare qid details */
+ if (memcmp(&v9inode->qid.version,
+ &st->qid.version, sizeof(v9inode->qid.version)))
+ return 0;
+
+ if (v9inode->qid.type != st->qid.type)
+ return 0;
+
+ if (v9inode->qid.path != st->qid.path)
+ return 0;
+ return 1;
+}
+
+static int v9fs_test_new_inode(struct inode *inode, void *data)
+{
+ return 0;
+}
+
+static int v9fs_set_inode(struct inode *inode, void *data)
+{
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+ struct p9_wstat *st = (struct p9_wstat *)data;
+
+ memcpy(&v9inode->qid, &st->qid, sizeof(st->qid));
+ return 0;
+}
+
+static struct inode *v9fs_qid_iget(struct super_block *sb,
+ struct p9_qid *qid,
+ struct p9_wstat *st,
+ int new)
{
dev_t rdev;
int retval;
umode_t umode;
struct inode *inode;
- struct p9_wstat *st;
struct v9fs_session_info *v9ses = sb->s_fs_info;
+ int (*test)(struct inode *inode, void *data);
- inode = iget_locked(sb, QID2INO(&fid->qid));
- if (unlikely(!inode))
+ if (new)
+ test = v9fs_test_new_inode;
+ else
+ test = v9fs_test_inode;
+
+ inode = iget5_locked(sb, QID2INO(qid), test, v9fs_set_inode, st);
+ if (!inode)
return ERR_PTR(-ENOMEM);
- if (!(inode->i_state & I_NEW)) {
- if (!new) {
- goto done;
- } else {
- p9_debug(P9_DEBUG_VFS, "WARNING: Inode collision %ld\n",
- inode->i_ino);
- iput(inode);
- remove_inode_hash(inode);
- inode = iget_locked(sb, QID2INO(&fid->qid));
- WARN_ON(!(inode->i_state & I_NEW));
- }
- }
-
+ if (!(inode->i_state & I_NEW))
+ return inode;
/*
* initialize the inode with the stat info
* FIXME!! we may need support for stale inodes
* later.
*/
- st = p9_client_stat(fid);
- if (IS_ERR(st)) {
- retval = PTR_ERR(st);
- goto error;
- }
-
+ inode->i_ino = QID2INO(qid);
umode = p9mode2unixmode(v9ses, st, &rdev);
- retval = v9fs_init_inode(v9ses, inode, &fid->qid, umode, rdev);
- v9fs_stat2inode(st, inode, sb, 0);
- p9stat_free(st);
- kfree(st);
+ retval = v9fs_init_inode(v9ses, inode, umode, rdev);
if (retval)
goto error;
+ v9fs_stat2inode(st, inode, sb, 0);
v9fs_set_netfs_context(inode);
v9fs_cache_inode_get_cookie(inode);
unlock_new_inode(inode);
-done:
return inode;
error:
iget_failed(inode);
return ERR_PTR(retval);
+
+}
+
+struct inode *
+v9fs_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+ struct super_block *sb, int new)
+{
+ struct p9_wstat *st;
+ struct inode *inode = NULL;
+
+ st = p9_client_stat(fid);
+ if (IS_ERR(st))
+ return ERR_CAST(st);
+
+ inode = v9fs_qid_iget(sb, &st->qid, st, new);
+ p9stat_free(st);
+ kfree(st);
+ return inode;
}
/**
@@ -450,15 +492,8 @@ static int v9fs_at_to_dotl_flags(int flags)
*/
static void v9fs_dec_count(struct inode *inode)
{
- if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2) {
- if (inode->i_nlink) {
- drop_nlink(inode);
- } else {
- p9_debug(P9_DEBUG_VFS,
- "WARNING: unexpected i_nlink zero %d inode %ld\n",
- inode->i_nlink, inode->i_ino);
- }
- }
+ if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2)
+ drop_nlink(inode);
}
/**
@@ -509,9 +544,6 @@ static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags)
} else
v9fs_dec_count(inode);
- if (inode->i_nlink <= 0) /* no more refs unhash it */
- remove_inode_hash(inode);
-
v9fs_invalidate_inode_attr(inode);
v9fs_invalidate_inode_attr(dir);
@@ -577,7 +609,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
/*
* instantiate inode and assign the unopened fid to the dentry
*/
- inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb, true);
+ inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
p9_debug(P9_DEBUG_VFS,
@@ -705,8 +737,10 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
inode = NULL;
else if (IS_ERR(fid))
inode = ERR_CAST(fid);
+ else if (v9ses->cache & (CACHE_META|CACHE_LOOSE))
+ inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb);
else
- inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb, false);
+ inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
/*
* If we had a rename on the server and a parallel lookup
* for the new name, then make sure we instantiate with
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index c61b97b..143ac03 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -52,50 +52,80 @@ static kgid_t v9fs_get_fsgid_for_create(struct inode *dir_inode)
return current_fsgid();
}
+static int v9fs_test_inode_dotl(struct inode *inode, void *data)
+{
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+ struct p9_stat_dotl *st = (struct p9_stat_dotl *)data;
+ /* don't match inode of different type */
+ if (inode_wrong_type(inode, st->st_mode))
+ return 0;
-struct inode *
-v9fs_fid_iget_dotl(struct super_block *sb, struct p9_fid *fid, bool new)
+ if (inode->i_generation != st->st_gen)
+ return 0;
+
+ /* compare qid details */
+ if (memcmp(&v9inode->qid.version,
+ &st->qid.version, sizeof(v9inode->qid.version)))
+ return 0;
+
+ if (v9inode->qid.type != st->qid.type)
+ return 0;
+
+ if (v9inode->qid.path != st->qid.path)
+ return 0;
+ return 1;
+}
+
+/* Always get a new inode */
+static int v9fs_test_new_inode_dotl(struct inode *inode, void *data)
+{
+ return 0;
+}
+
+static int v9fs_set_inode_dotl(struct inode *inode, void *data)
+{
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+ struct p9_stat_dotl *st = (struct p9_stat_dotl *)data;
+
+ memcpy(&v9inode->qid, &st->qid, sizeof(st->qid));
+ inode->i_generation = st->st_gen;
+ return 0;
+}
+
+static struct inode *v9fs_qid_iget_dotl(struct super_block *sb,
+ struct p9_qid *qid,
+ struct p9_fid *fid,
+ struct p9_stat_dotl *st,
+ int new)
{
int retval;
struct inode *inode;
- struct p9_stat_dotl *st;
struct v9fs_session_info *v9ses = sb->s_fs_info;
+ int (*test)(struct inode *inode, void *data);
- inode = iget_locked(sb, QID2INO(&fid->qid));
- if (unlikely(!inode))
+ if (new)
+ test = v9fs_test_new_inode_dotl;
+ else
+ test = v9fs_test_inode_dotl;
+
+ inode = iget5_locked(sb, QID2INO(qid), test, v9fs_set_inode_dotl, st);
+ if (!inode)
return ERR_PTR(-ENOMEM);
- if (!(inode->i_state & I_NEW)) {
- if (!new) {
- goto done;
- } else { /* deal with race condition in inode number reuse */
- p9_debug(P9_DEBUG_ERROR, "WARNING: Inode collision %lx\n",
- inode->i_ino);
- iput(inode);
- remove_inode_hash(inode);
- inode = iget_locked(sb, QID2INO(&fid->qid));
- WARN_ON(!(inode->i_state & I_NEW));
- }
- }
-
+ if (!(inode->i_state & I_NEW))
+ return inode;
/*
* initialize the inode with the stat info
* FIXME!! we may need support for stale inodes
* later.
*/
- st = p9_client_getattr_dotl(fid, P9_STATS_BASIC | P9_STATS_GEN);
- if (IS_ERR(st)) {
- retval = PTR_ERR(st);
- goto error;
- }
-
- retval = v9fs_init_inode(v9ses, inode, &fid->qid,
+ inode->i_ino = QID2INO(qid);
+ retval = v9fs_init_inode(v9ses, inode,
st->st_mode, new_decode_dev(st->st_rdev));
- v9fs_stat2inode_dotl(st, inode, 0);
- kfree(st);
if (retval)
goto error;
+ v9fs_stat2inode_dotl(st, inode, 0);
v9fs_set_netfs_context(inode);
v9fs_cache_inode_get_cookie(inode);
retval = v9fs_get_acl(inode, fid);
@@ -103,11 +133,27 @@ v9fs_fid_iget_dotl(struct super_block *sb, struct p9_fid *fid, bool new)
goto error;
unlock_new_inode(inode);
-done:
return inode;
error:
iget_failed(inode);
return ERR_PTR(retval);
+
+}
+
+struct inode *
+v9fs_inode_from_fid_dotl(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+ struct super_block *sb, int new)
+{
+ struct p9_stat_dotl *st;
+ struct inode *inode = NULL;
+
+ st = p9_client_getattr_dotl(fid, P9_STATS_BASIC | P9_STATS_GEN);
+ if (IS_ERR(st))
+ return ERR_CAST(st);
+
+ inode = v9fs_qid_iget_dotl(sb, &st->qid, fid, st, new);
+ kfree(st);
+ return inode;
}
struct dotl_openflag_map {
@@ -259,7 +305,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
goto out;
}
- inode = v9fs_fid_iget_dotl(dir->i_sb, fid, true);
+ inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n", err);
@@ -309,6 +355,7 @@ static int v9fs_vfs_mkdir_dotl(struct mnt_idmap *idmap,
umode_t omode)
{
int err;
+ struct v9fs_session_info *v9ses;
struct p9_fid *fid = NULL, *dfid = NULL;
kgid_t gid;
const unsigned char *name;
@@ -318,6 +365,7 @@ static int v9fs_vfs_mkdir_dotl(struct mnt_idmap *idmap,
struct posix_acl *dacl = NULL, *pacl = NULL;
p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry);
+ v9ses = v9fs_inode2v9ses(dir);
omode |= S_IFDIR;
if (dir->i_mode & S_ISGID)
@@ -352,7 +400,7 @@ static int v9fs_vfs_mkdir_dotl(struct mnt_idmap *idmap,
}
/* instantiate inode and assign the unopened fid to the dentry */
- inode = v9fs_fid_iget_dotl(dir->i_sb, fid, true);
+ inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n",
@@ -749,6 +797,7 @@ v9fs_vfs_mknod_dotl(struct mnt_idmap *idmap, struct inode *dir,
kgid_t gid;
const unsigned char *name;
umode_t mode;
+ struct v9fs_session_info *v9ses;
struct p9_fid *fid = NULL, *dfid = NULL;
struct inode *inode;
struct p9_qid qid;
@@ -758,6 +807,7 @@ v9fs_vfs_mknod_dotl(struct mnt_idmap *idmap, struct inode *dir,
dir->i_ino, dentry, omode,
MAJOR(rdev), MINOR(rdev));
+ v9ses = v9fs_inode2v9ses(dir);
dfid = v9fs_parent_fid(dentry);
if (IS_ERR(dfid)) {
err = PTR_ERR(dfid);
@@ -788,7 +838,7 @@ v9fs_vfs_mknod_dotl(struct mnt_idmap *idmap, struct inode *dir,
err);
goto error;
}
- inode = v9fs_fid_iget_dotl(dir->i_sb, fid, true);
+ inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n",
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index f52fdf4..489db16 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -139,7 +139,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
else
sb->s_d_op = &v9fs_dentry_operations;
- inode = v9fs_get_inode_from_fid(v9ses, fid, sb, true);
+ inode = v9fs_get_new_inode_from_fid(v9ses, fid, sb);
if (IS_ERR(inode)) {
retval = PTR_ERR(inode);
goto release_sb;
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index b306c09..c9d6201 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -130,6 +130,7 @@ struct afs_call {
wait_queue_head_t waitq; /* processes awaiting completion */
struct work_struct async_work; /* async I/O processor */
struct work_struct work; /* actual work processor */
+ struct work_struct free_work; /* Deferred free processor */
struct rxrpc_call *rxcall; /* RxRPC call handle */
struct rxrpc_peer *peer; /* Remote endpoint */
struct key *key; /* security for this call */
@@ -1333,6 +1334,7 @@ extern int __net_init afs_open_socket(struct afs_net *);
extern void __net_exit afs_close_socket(struct afs_net *);
extern void afs_charge_preallocation(struct work_struct *);
extern void afs_put_call(struct afs_call *);
+void afs_deferred_put_call(struct afs_call *call);
void afs_make_call(struct afs_call *call, gfp_t gfp);
void afs_wait_for_call_to_complete(struct afs_call *call);
extern struct afs_call *afs_alloc_flat_call(struct afs_net *,
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index c453428..9f2a3bb 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -18,6 +18,7 @@
struct workqueue_struct *afs_async_calls;
+static void afs_deferred_free_worker(struct work_struct *work);
static void afs_wake_up_call_waiter(struct sock *, struct rxrpc_call *, unsigned long);
static void afs_wake_up_async_call(struct sock *, struct rxrpc_call *, unsigned long);
static void afs_process_async_call(struct work_struct *);
@@ -149,6 +150,7 @@ static struct afs_call *afs_alloc_call(struct afs_net *net,
call->debug_id = atomic_inc_return(&rxrpc_debug_id);
refcount_set(&call->ref, 1);
INIT_WORK(&call->async_work, afs_process_async_call);
+ INIT_WORK(&call->free_work, afs_deferred_free_worker);
init_waitqueue_head(&call->waitq);
spin_lock_init(&call->state_lock);
call->iter = &call->def_iter;
@@ -159,6 +161,36 @@ static struct afs_call *afs_alloc_call(struct afs_net *net,
return call;
}
+static void afs_free_call(struct afs_call *call)
+{
+ struct afs_net *net = call->net;
+ int o;
+
+ ASSERT(!work_pending(&call->async_work));
+
+ rxrpc_kernel_put_peer(call->peer);
+
+ if (call->rxcall) {
+ rxrpc_kernel_shutdown_call(net->socket, call->rxcall);
+ rxrpc_kernel_put_call(net->socket, call->rxcall);
+ call->rxcall = NULL;
+ }
+ if (call->type->destructor)
+ call->type->destructor(call);
+
+ afs_unuse_server_notime(call->net, call->server, afs_server_trace_put_call);
+ kfree(call->request);
+
+ o = atomic_read(&net->nr_outstanding_calls);
+ trace_afs_call(call->debug_id, afs_call_trace_free, 0, o,
+ __builtin_return_address(0));
+ kfree(call);
+
+ o = atomic_dec_return(&net->nr_outstanding_calls);
+ if (o == 0)
+ wake_up_var(&net->nr_outstanding_calls);
+}
+
/*
* Dispose of a reference on a call.
*/
@@ -173,32 +205,34 @@ void afs_put_call(struct afs_call *call)
o = atomic_read(&net->nr_outstanding_calls);
trace_afs_call(debug_id, afs_call_trace_put, r - 1, o,
__builtin_return_address(0));
+ if (zero)
+ afs_free_call(call);
+}
- if (zero) {
- ASSERT(!work_pending(&call->async_work));
- ASSERT(call->type->name != NULL);
+static void afs_deferred_free_worker(struct work_struct *work)
+{
+ struct afs_call *call = container_of(work, struct afs_call, free_work);
- rxrpc_kernel_put_peer(call->peer);
+ afs_free_call(call);
+}
- if (call->rxcall) {
- rxrpc_kernel_shutdown_call(net->socket, call->rxcall);
- rxrpc_kernel_put_call(net->socket, call->rxcall);
- call->rxcall = NULL;
- }
- if (call->type->destructor)
- call->type->destructor(call);
+/*
+ * Dispose of a reference on a call, deferring the cleanup to a workqueue
+ * to avoid lock recursion.
+ */
+void afs_deferred_put_call(struct afs_call *call)
+{
+ struct afs_net *net = call->net;
+ unsigned int debug_id = call->debug_id;
+ bool zero;
+ int r, o;
- afs_unuse_server_notime(call->net, call->server, afs_server_trace_put_call);
- kfree(call->request);
-
- trace_afs_call(call->debug_id, afs_call_trace_free, 0, o,
- __builtin_return_address(0));
- kfree(call);
-
- o = atomic_dec_return(&net->nr_outstanding_calls);
- if (o == 0)
- wake_up_var(&net->nr_outstanding_calls);
- }
+ zero = __refcount_dec_and_test(&call->ref, &r);
+ o = atomic_read(&net->nr_outstanding_calls);
+ trace_afs_call(debug_id, afs_call_trace_put, r - 1, o,
+ __builtin_return_address(0));
+ if (zero)
+ schedule_work(&call->free_work);
}
static struct afs_call *afs_get_call(struct afs_call *call,
@@ -640,7 +674,8 @@ static void afs_wake_up_call_waiter(struct sock *sk, struct rxrpc_call *rxcall,
}
/*
- * wake up an asynchronous call
+ * Wake up an asynchronous call. The caller is holding the call notify
+ * spinlock around this, so we can't call afs_put_call().
*/
static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall,
unsigned long call_user_ID)
@@ -657,7 +692,7 @@ static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall,
__builtin_return_address(0));
if (!queue_work(afs_async_calls, &call->async_work))
- afs_put_call(call);
+ afs_deferred_put_call(call);
}
}
diff --git a/fs/backing-file.c b/fs/backing-file.c
index 8860dac..09a9be9 100644
--- a/fs/backing-file.c
+++ b/fs/backing-file.c
@@ -80,7 +80,7 @@ struct backing_aio {
refcount_t ref;
struct kiocb *orig_iocb;
/* used for aio completion */
- void (*end_write)(struct file *);
+ void (*end_write)(struct file *, loff_t, ssize_t);
struct work_struct work;
long res;
};
@@ -109,7 +109,7 @@ static void backing_aio_cleanup(struct backing_aio *aio, long res)
struct kiocb *orig_iocb = aio->orig_iocb;
if (aio->end_write)
- aio->end_write(orig_iocb->ki_filp);
+ aio->end_write(orig_iocb->ki_filp, iocb->ki_pos, res);
orig_iocb->ki_pos = iocb->ki_pos;
backing_aio_put(aio);
@@ -239,7 +239,7 @@ ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter,
ret = vfs_iter_write(file, iter, &iocb->ki_pos, rwf);
if (ctx->end_write)
- ctx->end_write(ctx->user_file);
+ ctx->end_write(ctx->user_file, iocb->ki_pos, ret);
} else {
struct backing_aio *aio;
@@ -317,7 +317,7 @@ ssize_t backing_file_splice_write(struct pipe_inode_info *pipe,
revert_creds(old_cred);
if (ctx->end_write)
- ctx->end_write(ctx->user_file);
+ ctx->end_write(ctx->user_file, ppos ? *ppos : 0, ret);
return ret;
}
diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c
index 6e161f8..c84a915 100644
--- a/fs/bcachefs/alloc_background.c
+++ b/fs/bcachefs/alloc_background.c
@@ -1977,7 +1977,7 @@ static void bch2_do_discards_fast_work(struct work_struct *work)
ca->mi.bucket_size,
GFP_KERNEL);
- int ret = bch2_trans_do(c, NULL, NULL,
+ int ret = bch2_trans_commit_do(c, NULL, NULL,
BCH_WATERMARK_btree|
BCH_TRANS_COMMIT_no_enospc,
bch2_clear_bucket_needs_discard(trans, POS(ca->dev_idx, bucket)));
@@ -2137,14 +2137,15 @@ static void bch2_do_invalidates_work(struct work_struct *work)
struct bkey_s_c k = next_lru_key(trans, &iter, ca, &wrapped);
ret = bkey_err(k);
- if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
- continue;
if (ret)
- break;
+ goto restart_err;
if (!k.k)
break;
ret = invalidate_one_bucket(trans, &iter, k, &nr_to_invalidate);
+restart_err:
+ if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
+ continue;
if (ret)
break;
@@ -2350,24 +2351,19 @@ int bch2_dev_remove_alloc(struct bch_fs *c, struct bch_dev *ca)
/* Bucket IO clocks: */
-int bch2_bucket_io_time_reset(struct btree_trans *trans, unsigned dev,
- size_t bucket_nr, int rw)
+static int __bch2_bucket_io_time_reset(struct btree_trans *trans, unsigned dev,
+ size_t bucket_nr, int rw)
{
struct bch_fs *c = trans->c;
+
struct btree_iter iter;
- struct bkey_i_alloc_v4 *a;
- u64 now;
- int ret = 0;
-
- if (bch2_trans_relock(trans))
- bch2_trans_begin(trans);
-
- a = bch2_trans_start_alloc_update_noupdate(trans, &iter, POS(dev, bucket_nr));
- ret = PTR_ERR_OR_ZERO(a);
+ struct bkey_i_alloc_v4 *a =
+ bch2_trans_start_alloc_update_noupdate(trans, &iter, POS(dev, bucket_nr));
+ int ret = PTR_ERR_OR_ZERO(a);
if (ret)
return ret;
- now = bch2_current_io_time(c, rw);
+ u64 now = bch2_current_io_time(c, rw);
if (a->v.io_time[rw] == now)
goto out;
@@ -2380,6 +2376,15 @@ int bch2_bucket_io_time_reset(struct btree_trans *trans, unsigned dev,
return ret;
}
+int bch2_bucket_io_time_reset(struct btree_trans *trans, unsigned dev,
+ size_t bucket_nr, int rw)
+{
+ if (bch2_trans_relock(trans))
+ bch2_trans_begin(trans);
+
+ return nested_lockrestart_do(trans, __bch2_bucket_io_time_reset(trans, dev, bucket_nr, rw));
+}
+
/* Startup/shutdown (ro/rw): */
void bch2_recalc_capacity(struct bch_fs *c)
diff --git a/fs/bcachefs/alloc_background.h b/fs/bcachefs/alloc_background.h
index f8e87c6..163a67b 100644
--- a/fs/bcachefs/alloc_background.h
+++ b/fs/bcachefs/alloc_background.h
@@ -168,6 +168,9 @@ static inline bool data_type_movable(enum bch_data_type type)
static inline u64 alloc_lru_idx_fragmentation(struct bch_alloc_v4 a,
struct bch_dev *ca)
{
+ if (a.data_type >= BCH_DATA_NR)
+ return 0;
+
if (!data_type_movable(a.data_type) ||
!bch2_bucket_sectors_fragmented(ca, a))
return 0;
diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c
index d0e0b56..372178c 100644
--- a/fs/bcachefs/alloc_foreground.c
+++ b/fs/bcachefs/alloc_foreground.c
@@ -162,6 +162,10 @@ static void open_bucket_free_unused(struct bch_fs *c, struct open_bucket *ob)
ARRAY_SIZE(c->open_buckets_partial));
spin_lock(&c->freelist_lock);
+ rcu_read_lock();
+ bch2_dev_rcu(c, ob->dev)->nr_partial_buckets++;
+ rcu_read_unlock();
+
ob->on_partial_list = true;
c->open_buckets_partial[c->open_buckets_partial_nr++] =
ob - c->open_buckets;
@@ -684,7 +688,7 @@ struct open_bucket *bch2_bucket_alloc(struct bch_fs *c, struct bch_dev *ca,
struct bch_dev_usage usage;
struct open_bucket *ob;
- bch2_trans_do(c, NULL, NULL, 0,
+ bch2_trans_do(c,
PTR_ERR_OR_ZERO(ob = bch2_bucket_alloc_trans(trans, ca, watermark,
data_type, cl, false, &usage)));
return ob;
@@ -972,7 +976,7 @@ static int bucket_alloc_set_partial(struct bch_fs *c,
u64 avail;
bch2_dev_usage_read_fast(ca, &usage);
- avail = dev_buckets_free(ca, usage, watermark);
+ avail = dev_buckets_free(ca, usage, watermark) + ca->nr_partial_buckets;
if (!avail)
continue;
@@ -981,6 +985,10 @@ static int bucket_alloc_set_partial(struct bch_fs *c,
i);
ob->on_partial_list = false;
+ rcu_read_lock();
+ bch2_dev_rcu(c, ob->dev)->nr_partial_buckets--;
+ rcu_read_unlock();
+
ret = add_new_bucket(c, ptrs, devs_may_alloc,
nr_replicas, nr_effective,
have_cache, ob);
@@ -1191,7 +1199,13 @@ void bch2_open_buckets_stop(struct bch_fs *c, struct bch_dev *ca,
--c->open_buckets_partial_nr;
swap(c->open_buckets_partial[i],
c->open_buckets_partial[c->open_buckets_partial_nr]);
+
ob->on_partial_list = false;
+
+ rcu_read_lock();
+ bch2_dev_rcu(c, ob->dev)->nr_partial_buckets--;
+ rcu_read_unlock();
+
spin_unlock(&c->freelist_lock);
bch2_open_bucket_put(c, ob);
spin_lock(&c->freelist_lock);
@@ -1610,8 +1624,7 @@ void bch2_open_buckets_to_text(struct printbuf *out, struct bch_fs *c,
ob < c->open_buckets + ARRAY_SIZE(c->open_buckets);
ob++) {
spin_lock(&ob->lock);
- if (ob->valid && !ob->on_partial_list &&
- (!ca || ob->dev == ca->dev_idx))
+ if (ob->valid && (!ca || ob->dev == ca->dev_idx))
bch2_open_bucket_to_text(out, c, ob);
spin_unlock(&ob->lock);
}
diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index f4151ee..e94a83b 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -555,6 +555,7 @@ struct bch_dev {
u64 alloc_cursor[3];
unsigned nr_open_buckets;
+ unsigned nr_partial_buckets;
unsigned nr_btree_reserve;
size_t inc_gen_needs_gc;
diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index 94bbd85..0ca3fee 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -820,12 +820,22 @@ static int bch2_alloc_write_key(struct btree_trans *trans,
* fix that here:
*/
alloc_data_type_set(&gc, gc.data_type);
-
if (gc.data_type != old_gc.data_type ||
gc.dirty_sectors != old_gc.dirty_sectors) {
ret = bch2_alloc_key_to_dev_counters(trans, ca, &old_gc, &gc, BTREE_TRIGGER_gc);
if (ret)
return ret;
+
+ /*
+ * Ugly: alloc_key_to_dev_counters(..., BTREE_TRIGGER_gc) is not
+ * safe w.r.t. transaction restarts, so fixup the gc_bucket so
+ * we don't run it twice:
+ */
+ percpu_down_read(&c->mark_lock);
+ struct bucket *gc_m = gc_bucket(ca, iter->pos.offset);
+ gc_m->data_type = gc.data_type;
+ gc_m->dirty_sectors = gc.dirty_sectors;
+ percpu_up_read(&c->mark_lock);
}
if (fsck_err_on(new.data_type != gc.data_type,
diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index cf93340..6296a11 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -1871,7 +1871,7 @@ static void btree_node_write_work(struct work_struct *work)
}
} else {
- ret = bch2_trans_do(c, NULL, NULL, 0,
+ ret = bch2_trans_do(c,
bch2_btree_node_update_key_get_iter(trans, b, &wbio->key,
BCH_WATERMARK_interior_updates|
BCH_TRANS_COMMIT_journal_reclaim|
diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index 0883cf6..eef9b89 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -882,6 +882,18 @@ static noinline int btree_node_iter_and_journal_peek(struct btree_trans *trans,
__bch2_btree_and_journal_iter_init_node_iter(trans, &jiter, l->b, l->iter, path->pos);
k = bch2_btree_and_journal_iter_peek(&jiter);
+ if (!k.k) {
+ struct printbuf buf = PRINTBUF;
+
+ prt_str(&buf, "node not found at pos ");
+ bch2_bpos_to_text(&buf, path->pos);
+ prt_str(&buf, " at btree ");
+ bch2_btree_pos_to_text(&buf, c, l->b);
+
+ ret = bch2_fs_topology_error(c, "%s", buf.buf);
+ printbuf_exit(&buf);
+ goto err;
+ }
bch2_bkey_buf_reassemble(out, c, k);
@@ -889,6 +901,7 @@ static noinline int btree_node_iter_and_journal_peek(struct btree_trans *trans,
c->opts.btree_node_prefetch)
ret = btree_path_prefetch_j(trans, path, &jiter);
+err:
bch2_btree_and_journal_iter_exit(&jiter);
return ret;
}
diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h
index 31a58bf..0bda054 100644
--- a/fs/bcachefs/btree_iter.h
+++ b/fs/bcachefs/btree_iter.h
@@ -912,6 +912,8 @@ struct bkey_s_c bch2_btree_iter_peek_and_restart_outlined(struct btree_iter *);
_ret; \
})
+#define bch2_trans_do(_c, _do) bch2_trans_run(_c, lockrestart_do(trans, _do))
+
struct btree_trans *__bch2_trans_get(struct bch_fs *, unsigned);
void bch2_trans_put(struct btree_trans *);
diff --git a/fs/bcachefs/btree_update.c b/fs/bcachefs/btree_update.c
index 514df61..5d809e8 100644
--- a/fs/bcachefs/btree_update.c
+++ b/fs/bcachefs/btree_update.c
@@ -668,7 +668,7 @@ int bch2_btree_insert(struct bch_fs *c, enum btree_id id, struct bkey_i *k,
struct disk_reservation *disk_res, int flags,
enum btree_iter_update_trigger_flags iter_flags)
{
- return bch2_trans_do(c, disk_res, NULL, flags,
+ return bch2_trans_commit_do(c, disk_res, NULL, flags,
bch2_btree_insert_trans(trans, id, k, iter_flags));
}
@@ -865,7 +865,7 @@ __bch2_fs_log_msg(struct bch_fs *c, unsigned commit_flags, const char *fmt,
memcpy(l->d, buf.buf, buf.pos);
c->journal.early_journal_entries.nr += jset_u64s(u64s);
} else {
- ret = bch2_trans_do(c, NULL, NULL,
+ ret = bch2_trans_commit_do(c, NULL, NULL,
BCH_TRANS_COMMIT_lazy_rw|commit_flags,
__bch2_trans_log_msg(trans, &buf, u64s));
}
diff --git a/fs/bcachefs/btree_update.h b/fs/bcachefs/btree_update.h
index 6a454f2..70b3c98 100644
--- a/fs/bcachefs/btree_update.h
+++ b/fs/bcachefs/btree_update.h
@@ -192,7 +192,7 @@ static inline int bch2_trans_commit(struct btree_trans *trans,
nested_lockrestart_do(_trans, _do ?: bch2_trans_commit(_trans, (_disk_res),\
(_journal_seq), (_flags)))
-#define bch2_trans_do(_c, _disk_res, _journal_seq, _flags, _do) \
+#define bch2_trans_commit_do(_c, _disk_res, _journal_seq, _flags, _do) \
bch2_trans_run(_c, commit_do(trans, _disk_res, _journal_seq, _flags, _do))
#define trans_for_each_update(_trans, _i) \
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index 190bc1e..64f0928 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -2239,10 +2239,8 @@ static void async_btree_node_rewrite_work(struct work_struct *work)
struct async_btree_rewrite *a =
container_of(work, struct async_btree_rewrite, work);
struct bch_fs *c = a->c;
- int ret;
- ret = bch2_trans_do(c, NULL, NULL, 0,
- async_btree_node_rewrite_trans(trans, a));
+ int ret = bch2_trans_do(c, async_btree_node_rewrite_trans(trans, a));
bch_err_fn_ratelimited(c, ret);
bch2_write_ref_put(c, BCH_WRITE_REF_node_rewrite);
kfree(a);
diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c
index 546cd01..ec7d9a5 100644
--- a/fs/bcachefs/buckets.c
+++ b/fs/bcachefs/buckets.c
@@ -1160,11 +1160,11 @@ int bch2_trans_mark_dev_sbs(struct bch_fs *c)
#define SECTORS_CACHE 1024
int __bch2_disk_reservation_add(struct bch_fs *c, struct disk_reservation *res,
- u64 sectors, int flags)
+ u64 sectors, enum bch_reservation_flags flags)
{
struct bch_fs_pcpu *pcpu;
u64 old, get;
- s64 sectors_available;
+ u64 sectors_available;
int ret;
percpu_down_read(&c->mark_lock);
@@ -1202,6 +1202,9 @@ int __bch2_disk_reservation_add(struct bch_fs *c, struct disk_reservation *res,
percpu_u64_set(&c->pcpu->sectors_available, 0);
sectors_available = avail_factor(__bch2_fs_usage_read_short(c).free);
+ if (sectors_available && (flags & BCH_DISK_RESERVATION_PARTIAL))
+ sectors = min(sectors, sectors_available);
+
if (sectors <= sectors_available ||
(flags & BCH_DISK_RESERVATION_NOFAIL)) {
atomic64_set(&c->sectors_available,
diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h
index e2cb7b2..fd5e6cc 100644
--- a/fs/bcachefs/buckets.h
+++ b/fs/bcachefs/buckets.h
@@ -344,14 +344,16 @@ static inline void bch2_disk_reservation_put(struct bch_fs *c,
}
}
-#define BCH_DISK_RESERVATION_NOFAIL (1 << 0)
+enum bch_reservation_flags {
+ BCH_DISK_RESERVATION_NOFAIL = 1 << 0,
+ BCH_DISK_RESERVATION_PARTIAL = 1 << 1,
+};
-int __bch2_disk_reservation_add(struct bch_fs *,
- struct disk_reservation *,
- u64, int);
+int __bch2_disk_reservation_add(struct bch_fs *, struct disk_reservation *,
+ u64, enum bch_reservation_flags);
static inline int bch2_disk_reservation_add(struct bch_fs *c, struct disk_reservation *res,
- u64 sectors, int flags)
+ u64 sectors, enum bch_reservation_flags flags)
{
#ifdef __KERNEL__
u64 old, new;
diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c
index cbfd88f..2182b55 100644
--- a/fs/bcachefs/chardev.c
+++ b/fs/bcachefs/chardev.c
@@ -225,6 +225,7 @@ static long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_a
opt_set(thr->opts, stdio, (u64)(unsigned long)&thr->thr.stdio);
opt_set(thr->opts, read_only, 1);
+ opt_set(thr->opts, ratelimit_errors, 0);
/* We need request_key() to be called before we punt to kthread: */
opt_set(thr->opts, nostart, true);
diff --git a/fs/bcachefs/darray.c b/fs/bcachefs/darray.c
index 4f06cd8..e86d36d 100644
--- a/fs/bcachefs/darray.c
+++ b/fs/bcachefs/darray.c
@@ -2,6 +2,7 @@
#include <linux/log2.h>
#include <linux/slab.h>
+#include <linux/vmalloc.h>
#include "darray.h"
int __bch2_darray_resize_noprof(darray_char *d, size_t element_size, size_t new_size, gfp_t gfp)
@@ -9,7 +10,19 @@ int __bch2_darray_resize_noprof(darray_char *d, size_t element_size, size_t new_
if (new_size > d->size) {
new_size = roundup_pow_of_two(new_size);
- void *data = kvmalloc_array_noprof(new_size, element_size, gfp);
+ /*
+ * This is a workaround: kvmalloc() doesn't support > INT_MAX
+ * allocations, but vmalloc() does.
+ * The limit needs to be lifted from kvmalloc, and when it does
+ * we'll go back to just using that.
+ */
+ size_t bytes;
+ if (unlikely(check_mul_overflow(new_size, element_size, &bytes)))
+ return -ENOMEM;
+
+ void *data = likely(bytes < INT_MAX)
+ ? kvmalloc_noprof(bytes, gfp)
+ : vmalloc_noprof(bytes);
if (!data)
return -ENOMEM;
diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c
index a6ee0be..8e75a85 100644
--- a/fs/bcachefs/data_update.c
+++ b/fs/bcachefs/data_update.c
@@ -236,7 +236,8 @@ static int __bch2_data_update_index_update(struct btree_trans *trans,
if (((1U << i) & m->data_opts.rewrite_ptrs) &&
(ptr = bch2_extent_has_ptr(old, p, bkey_i_to_s(insert))) &&
!ptr->cached) {
- bch2_extent_ptr_set_cached(bkey_i_to_s(insert), ptr);
+ bch2_extent_ptr_set_cached(c, &m->op.opts,
+ bkey_i_to_s(insert), ptr);
rewrites_found |= 1U << i;
}
i++;
@@ -284,7 +285,8 @@ static int __bch2_data_update_index_update(struct btree_trans *trans,
durability - ptr_durability >= m->op.opts.data_replicas) {
durability -= ptr_durability;
- bch2_extent_ptr_set_cached(bkey_i_to_s(insert), &entry->ptr);
+ bch2_extent_ptr_set_cached(c, &m->op.opts,
+ bkey_i_to_s(insert), &entry->ptr);
goto restart_drop_extra_replicas;
}
}
@@ -295,7 +297,7 @@ static int __bch2_data_update_index_update(struct btree_trans *trans,
bch2_extent_ptr_decoded_append(insert, &p);
bch2_bkey_narrow_crcs(insert, (struct bch_extent_crc_unpacked) { 0 });
- bch2_extent_normalize(c, bkey_i_to_s(insert));
+ bch2_extent_normalize_by_opts(c, &m->op.opts, bkey_i_to_s(insert));
ret = bch2_sum_sector_overwrites(trans, &iter, insert,
&should_check_enospc,
@@ -558,7 +560,8 @@ void bch2_data_update_to_text(struct printbuf *out, struct data_update *m)
int bch2_extent_drop_ptrs(struct btree_trans *trans,
struct btree_iter *iter,
struct bkey_s_c k,
- struct data_update_opts data_opts)
+ struct bch_io_opts *io_opts,
+ struct data_update_opts *data_opts)
{
struct bch_fs *c = trans->c;
struct bkey_i *n;
@@ -569,11 +572,11 @@ int bch2_extent_drop_ptrs(struct btree_trans *trans,
if (ret)
return ret;
- while (data_opts.kill_ptrs) {
- unsigned i = 0, drop = __fls(data_opts.kill_ptrs);
+ while (data_opts->kill_ptrs) {
+ unsigned i = 0, drop = __fls(data_opts->kill_ptrs);
bch2_bkey_drop_ptrs_noerror(bkey_i_to_s(n), ptr, i++ == drop);
- data_opts.kill_ptrs ^= 1U << drop;
+ data_opts->kill_ptrs ^= 1U << drop;
}
/*
@@ -581,7 +584,7 @@ int bch2_extent_drop_ptrs(struct btree_trans *trans,
* will do the appropriate thing with it (turning it into a
* KEY_TYPE_error key, or just a discard if it was a cached extent)
*/
- bch2_extent_normalize(c, bkey_i_to_s(n));
+ bch2_extent_normalize_by_opts(c, io_opts, bkey_i_to_s(n));
/*
* Since we're not inserting through an extent iterator
@@ -720,7 +723,7 @@ int bch2_data_update_init(struct btree_trans *trans,
m->data_opts.rewrite_ptrs = 0;
/* if iter == NULL, it's just a promote */
if (iter)
- ret = bch2_extent_drop_ptrs(trans, iter, k, m->data_opts);
+ ret = bch2_extent_drop_ptrs(trans, iter, k, &io_opts, &m->data_opts);
goto out;
}
diff --git a/fs/bcachefs/data_update.h b/fs/bcachefs/data_update.h
index 8d36365..e4b5072 100644
--- a/fs/bcachefs/data_update.h
+++ b/fs/bcachefs/data_update.h
@@ -40,7 +40,8 @@ void bch2_data_update_read_done(struct data_update *,
int bch2_extent_drop_ptrs(struct btree_trans *,
struct btree_iter *,
struct bkey_s_c,
- struct data_update_opts);
+ struct bch_io_opts *,
+ struct data_update_opts *);
void bch2_data_update_exit(struct data_update *);
int bch2_data_update_init(struct btree_trans *, struct btree_iter *,
diff --git a/fs/bcachefs/dirent.c b/fs/bcachefs/dirent.c
index 84dd4a87..faffc98 100644
--- a/fs/bcachefs/dirent.c
+++ b/fs/bcachefs/dirent.c
@@ -250,13 +250,6 @@ int bch2_dirent_create(struct btree_trans *trans, subvol_inum dir,
return ret;
}
-static void dirent_copy_target(struct bkey_i_dirent *dst,
- struct bkey_s_c_dirent src)
-{
- dst->v.d_inum = src.v->d_inum;
- dst->v.d_type = src.v->d_type;
-}
-
int bch2_dirent_read_target(struct btree_trans *trans, subvol_inum dir,
struct bkey_s_c_dirent d, subvol_inum *target)
{
diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h
index 8945145..53ad996 100644
--- a/fs/bcachefs/dirent.h
+++ b/fs/bcachefs/dirent.h
@@ -34,6 +34,13 @@ static inline unsigned dirent_val_u64s(unsigned len)
int bch2_dirent_read_target(struct btree_trans *, subvol_inum,
struct bkey_s_c_dirent, subvol_inum *);
+static inline void dirent_copy_target(struct bkey_i_dirent *dst,
+ struct bkey_s_c_dirent src)
+{
+ dst->v.d_inum = src.v->d_inum;
+ dst->v.d_type = src.v->d_type;
+}
+
int bch2_dirent_create_snapshot(struct btree_trans *, u32, u64, u32,
const struct bch_hash_info *, u8,
const struct qstr *, u64, u64 *,
diff --git a/fs/bcachefs/disk_accounting.c b/fs/bcachefs/disk_accounting.c
index e309fb7..07eb8fa 100644
--- a/fs/bcachefs/disk_accounting.c
+++ b/fs/bcachefs/disk_accounting.c
@@ -856,8 +856,10 @@ int bch2_dev_usage_init(struct bch_dev *ca, bool gc)
};
u64 v[3] = { ca->mi.nbuckets - ca->mi.first_bucket, 0, 0 };
- int ret = bch2_trans_do(c, NULL, NULL, 0,
- bch2_disk_accounting_mod(trans, &acc, v, ARRAY_SIZE(v), gc));
+ int ret = bch2_trans_do(c, ({
+ bch2_disk_accounting_mod(trans, &acc, v, ARRAY_SIZE(v), gc) ?:
+ (!gc ? bch2_trans_commit(trans, NULL, NULL, 0) : 0);
+ }));
bch_err_fn(c, ret);
return ret;
}
diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c
index e410cfe..749dcf3 100644
--- a/fs/bcachefs/ec.c
+++ b/fs/bcachefs/ec.c
@@ -266,12 +266,12 @@ static int __mark_stripe_bucket(struct btree_trans *trans,
if (!deleting) {
a->stripe = s.k->p.offset;
a->stripe_redundancy = s.v->nr_redundant;
+ alloc_data_type_set(a, data_type);
} else {
a->stripe = 0;
a->stripe_redundancy = 0;
+ alloc_data_type_set(a, BCH_DATA_user);
}
-
- alloc_data_type_set(a, data_type);
err:
printbuf_exit(&buf);
return ret;
@@ -1186,7 +1186,7 @@ static void ec_stripe_delete_work(struct work_struct *work)
if (!idx)
break;
- int ret = bch2_trans_do(c, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
+ int ret = bch2_trans_commit_do(c, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
ec_stripe_delete(trans, idx));
bch_err_fn(c, ret);
if (ret)
@@ -1519,14 +1519,14 @@ static void ec_stripe_create(struct ec_stripe_new *s)
goto err;
}
- ret = bch2_trans_do(c, &s->res, NULL,
- BCH_TRANS_COMMIT_no_check_rw|
- BCH_TRANS_COMMIT_no_enospc,
- ec_stripe_key_update(trans,
- s->have_existing_stripe
- ? bkey_i_to_stripe(&s->existing_stripe.key)
- : NULL,
- bkey_i_to_stripe(&s->new_stripe.key)));
+ ret = bch2_trans_commit_do(c, &s->res, NULL,
+ BCH_TRANS_COMMIT_no_check_rw|
+ BCH_TRANS_COMMIT_no_enospc,
+ ec_stripe_key_update(trans,
+ s->have_existing_stripe
+ ? bkey_i_to_stripe(&s->existing_stripe.key)
+ : NULL,
+ bkey_i_to_stripe(&s->new_stripe.key)));
bch_err_msg(c, ret, "creating stripe key");
if (ret) {
goto err;
@@ -1870,6 +1870,10 @@ __bch2_ec_stripe_head_get(struct btree_trans *trans,
}
h = ec_new_stripe_head_alloc(c, disk_label, algo, redundancy, watermark);
+ if (!h) {
+ h = ERR_PTR(-BCH_ERR_ENOMEM_stripe_head_alloc);
+ goto err;
+ }
found:
if (h->rw_devs_change_count != c->rw_devs_change_count)
ec_stripe_head_devs_update(c, h);
diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h
index 6492635..a1bc6c7 100644
--- a/fs/bcachefs/errcode.h
+++ b/fs/bcachefs/errcode.h
@@ -83,6 +83,7 @@
x(ENOMEM, ENOMEM_fs_other_alloc) \
x(ENOMEM, ENOMEM_dev_alloc) \
x(ENOMEM, ENOMEM_disk_accounting) \
+ x(ENOMEM, ENOMEM_stripe_head_alloc) \
x(ENOSPC, ENOSPC_disk_reservation) \
x(ENOSPC, ENOSPC_bucket_alloc) \
x(ENOSPC, ENOSPC_disk_label_add) \
@@ -222,6 +223,7 @@
x(BCH_ERR_invalid_sb_layout, invalid_sb_layout_type) \
x(BCH_ERR_invalid_sb_layout, invalid_sb_layout_nr_superblocks) \
x(BCH_ERR_invalid_sb_layout, invalid_sb_layout_superblocks_overlap) \
+ x(BCH_ERR_invalid_sb_layout, invalid_sb_layout_sb_max_size_bits) \
x(BCH_ERR_invalid_sb, invalid_sb_members_missing) \
x(BCH_ERR_invalid_sb, invalid_sb_members) \
x(BCH_ERR_invalid_sb, invalid_sb_disk_groups) \
diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c
index 7a79f69..b679def 100644
--- a/fs/bcachefs/error.c
+++ b/fs/bcachefs/error.c
@@ -251,7 +251,10 @@ int __bch2_fsck_err(struct bch_fs *c,
* delete the key)
* - and we don't need to warn if we're not prompting
*/
- WARN_ON(!(flags & FSCK_AUTOFIX) && !trans && bch2_current_has_btree_trans(c));
+ WARN_ON((flags & FSCK_CAN_FIX) &&
+ !(flags & FSCK_AUTOFIX) &&
+ !trans &&
+ bch2_current_has_btree_trans(c));
if ((flags & FSCK_CAN_FIX) &&
test_bit(err, c->sb.errors_silent))
diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index cc0d220..c4e91d1 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -978,31 +978,54 @@ bch2_extent_has_ptr(struct bkey_s_c k1, struct extent_ptr_decoded p1, struct bke
return NULL;
}
-void bch2_extent_ptr_set_cached(struct bkey_s k, struct bch_extent_ptr *ptr)
+static bool want_cached_ptr(struct bch_fs *c, struct bch_io_opts *opts,
+ struct bch_extent_ptr *ptr)
+{
+ if (!opts->promote_target ||
+ !bch2_dev_in_target(c, ptr->dev, opts->promote_target))
+ return false;
+
+ struct bch_dev *ca = bch2_dev_rcu_noerror(c, ptr->dev);
+
+ return ca && bch2_dev_is_readable(ca) && !dev_ptr_stale_rcu(ca, ptr);
+}
+
+void bch2_extent_ptr_set_cached(struct bch_fs *c,
+ struct bch_io_opts *opts,
+ struct bkey_s k,
+ struct bch_extent_ptr *ptr)
{
struct bkey_ptrs ptrs = bch2_bkey_ptrs(k);
union bch_extent_entry *entry;
- union bch_extent_entry *ec = NULL;
+ struct extent_ptr_decoded p;
- bkey_extent_entry_for_each(ptrs, entry) {
- if (&entry->ptr == ptr) {
- ptr->cached = true;
- if (ec)
- extent_entry_drop(k, ec);
- return;
- }
-
- if (extent_entry_is_stripe_ptr(entry))
- ec = entry;
- else if (extent_entry_is_ptr(entry))
- ec = NULL;
+ rcu_read_lock();
+ if (!want_cached_ptr(c, opts, ptr)) {
+ bch2_bkey_drop_ptr_noerror(k, ptr);
+ goto out;
}
+ /*
+ * Stripes can't contain cached data, for - reasons.
+ *
+ * Possibly something we can fix in the future?
+ */
+ bkey_for_each_ptr_decode(k.k, ptrs, p, entry)
+ if (&entry->ptr == ptr) {
+ if (p.has_ec)
+ bch2_bkey_drop_ptr_noerror(k, ptr);
+ else
+ ptr->cached = true;
+ goto out;
+ }
+
BUG();
+out:
+ rcu_read_unlock();
}
/*
- * bch_extent_normalize - clean up an extent, dropping stale pointers etc.
+ * bch2_extent_normalize - clean up an extent, dropping stale pointers etc.
*
* Returns true if @k should be dropped entirely
*
@@ -1016,8 +1039,39 @@ bool bch2_extent_normalize(struct bch_fs *c, struct bkey_s k)
rcu_read_lock();
bch2_bkey_drop_ptrs(k, ptr,
ptr->cached &&
- (ca = bch2_dev_rcu(c, ptr->dev)) &&
- dev_ptr_stale_rcu(ca, ptr) > 0);
+ (!(ca = bch2_dev_rcu(c, ptr->dev)) ||
+ dev_ptr_stale_rcu(ca, ptr) > 0));
+ rcu_read_unlock();
+
+ return bkey_deleted(k.k);
+}
+
+/*
+ * bch2_extent_normalize_by_opts - clean up an extent, dropping stale pointers etc.
+ *
+ * Like bch2_extent_normalize(), but also only keeps a single cached pointer on
+ * the promote target.
+ */
+bool bch2_extent_normalize_by_opts(struct bch_fs *c,
+ struct bch_io_opts *opts,
+ struct bkey_s k)
+{
+ struct bkey_ptrs ptrs;
+ bool have_cached_ptr;
+
+ rcu_read_lock();
+restart_drop_ptrs:
+ ptrs = bch2_bkey_ptrs(k);
+ have_cached_ptr = false;
+
+ bkey_for_each_ptr(ptrs, ptr)
+ if (ptr->cached) {
+ if (have_cached_ptr || !want_cached_ptr(c, opts, ptr)) {
+ bch2_bkey_drop_ptr(k, ptr);
+ goto restart_drop_ptrs;
+ }
+ have_cached_ptr = true;
+ }
rcu_read_unlock();
return bkey_deleted(k.k);
diff --git a/fs/bcachefs/extents.h b/fs/bcachefs/extents.h
index 923a5f1..bcffcf6 100644
--- a/fs/bcachefs/extents.h
+++ b/fs/bcachefs/extents.h
@@ -686,9 +686,12 @@ bool bch2_extents_match(struct bkey_s_c, struct bkey_s_c);
struct bch_extent_ptr *
bch2_extent_has_ptr(struct bkey_s_c, struct extent_ptr_decoded, struct bkey_s);
-void bch2_extent_ptr_set_cached(struct bkey_s, struct bch_extent_ptr *);
+void bch2_extent_ptr_set_cached(struct bch_fs *, struct bch_io_opts *,
+ struct bkey_s, struct bch_extent_ptr *);
+bool bch2_extent_normalize_by_opts(struct bch_fs *, struct bch_io_opts *, struct bkey_s);
bool bch2_extent_normalize(struct bch_fs *, struct bkey_s);
+
void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *, const struct bch_extent_ptr *);
void bch2_bkey_ptrs_to_text(struct printbuf *, struct bch_fs *,
struct bkey_s_c);
diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c
index 48a1ab9..9597280 100644
--- a/fs/bcachefs/fs-io-buffered.c
+++ b/fs/bcachefs/fs-io-buffered.c
@@ -856,6 +856,12 @@ static int __bch2_buffered_write(struct bch_inode_info *inode,
folios_trunc(&fs, fi);
end = min(end, folio_end_pos(darray_last(fs)));
} else {
+ if (!folio_test_uptodate(f)) {
+ ret = bch2_read_single_folio(f, mapping);
+ if (ret)
+ goto out;
+ }
+
folios_trunc(&fs, fi + 1);
end = f_pos + f_reserved;
}
diff --git a/fs/bcachefs/fs-io-pagecache.c b/fs/bcachefs/fs-io-pagecache.c
index af3a245..1d4910e 100644
--- a/fs/bcachefs/fs-io-pagecache.c
+++ b/fs/bcachefs/fs-io-pagecache.c
@@ -399,14 +399,17 @@ void bch2_folio_reservation_put(struct bch_fs *c,
bch2_quota_reservation_put(c, inode, &res->quota);
}
-int bch2_folio_reservation_get(struct bch_fs *c,
+static int __bch2_folio_reservation_get(struct bch_fs *c,
struct bch_inode_info *inode,
struct folio *folio,
struct bch2_folio_reservation *res,
- size_t offset, size_t len)
+ size_t offset, size_t len,
+ bool partial)
{
struct bch_folio *s = bch2_folio_create(folio, 0);
unsigned i, disk_sectors = 0, quota_sectors = 0;
+ struct disk_reservation disk_res = {};
+ size_t reserved = len;
int ret;
if (!s)
@@ -422,23 +425,56 @@ int bch2_folio_reservation_get(struct bch_fs *c,
}
if (disk_sectors) {
- ret = bch2_disk_reservation_add(c, &res->disk, disk_sectors, 0);
+ ret = bch2_disk_reservation_add(c, &disk_res, disk_sectors,
+ partial ? BCH_DISK_RESERVATION_PARTIAL : 0);
if (unlikely(ret))
return ret;
+
+ if (unlikely(disk_res.sectors != disk_sectors)) {
+ disk_sectors = quota_sectors = 0;
+
+ for (i = round_down(offset, block_bytes(c)) >> 9;
+ i < round_up(offset + len, block_bytes(c)) >> 9;
+ i++) {
+ disk_sectors += sectors_to_reserve(&s->s[i], res->disk.nr_replicas);
+ if (disk_sectors > disk_res.sectors) {
+ /*
+ * Make sure to get a reservation that's
+ * aligned to the filesystem blocksize:
+ */
+ unsigned reserved_offset = round_down(i << 9, block_bytes(c));
+ reserved = clamp(reserved_offset, offset, offset + len) - offset;
+
+ if (!reserved) {
+ bch2_disk_reservation_put(c, &disk_res);
+ return -BCH_ERR_ENOSPC_disk_reservation;
+ }
+ break;
+ }
+ quota_sectors += s->s[i].state == SECTOR_unallocated;
+ }
+ }
}
if (quota_sectors) {
ret = bch2_quota_reservation_add(c, inode, &res->quota, quota_sectors, true);
if (unlikely(ret)) {
- struct disk_reservation tmp = { .sectors = disk_sectors };
-
- bch2_disk_reservation_put(c, &tmp);
- res->disk.sectors -= disk_sectors;
+ bch2_disk_reservation_put(c, &disk_res);
return ret;
}
}
- return 0;
+ res->disk.sectors += disk_res.sectors;
+ return partial ? reserved : 0;
+}
+
+int bch2_folio_reservation_get(struct bch_fs *c,
+ struct bch_inode_info *inode,
+ struct folio *folio,
+ struct bch2_folio_reservation *res,
+ size_t offset, size_t len)
+{
+ return __bch2_folio_reservation_get(c, inode, folio, res, offset, len, false);
}
ssize_t bch2_folio_reservation_get_partial(struct bch_fs *c,
@@ -447,23 +483,7 @@ ssize_t bch2_folio_reservation_get_partial(struct bch_fs *c,
struct bch2_folio_reservation *res,
size_t offset, size_t len)
{
- size_t l, reserved = 0;
- int ret;
-
- while ((l = len - reserved)) {
- while ((ret = bch2_folio_reservation_get(c, inode, folio, res, offset, l))) {
- if ((offset & (block_bytes(c) - 1)) + l <= block_bytes(c))
- return reserved ?: ret;
-
- len = reserved + l;
- l /= 2;
- }
-
- offset += l;
- reserved += l;
- }
-
- return reserved;
+ return __bch2_folio_reservation_get(c, inode, folio, res, offset, len, true);
}
static void bch2_clear_folio_bits(struct folio *folio)
diff --git a/fs/bcachefs/fs-io.c b/fs/bcachefs/fs-io.c
index 71d0fa3..2456c41 100644
--- a/fs/bcachefs/fs-io.c
+++ b/fs/bcachefs/fs-io.c
@@ -182,7 +182,7 @@ static int bch2_flush_inode(struct bch_fs *c,
struct bch_inode_unpacked u;
int ret = bch2_inode_find_by_inum(c, inode_inum(inode), &u) ?:
- bch2_journal_flush_seq(&c->journal, u.bi_journal_seq) ?:
+ bch2_journal_flush_seq(&c->journal, u.bi_journal_seq, TASK_INTERRUPTIBLE) ?:
bch2_inode_flush_nocow_writes(c, inode);
bch2_write_ref_put(c, BCH_WRITE_REF_fsync);
return ret;
@@ -587,7 +587,7 @@ static noinline int __bchfs_fallocate(struct bch_inode_info *inode, int mode,
POS(inode->v.i_ino, start_sector),
BTREE_ITER_slots|BTREE_ITER_intent);
- while (!ret && bkey_lt(iter.pos, end_pos)) {
+ while (!ret) {
s64 i_sectors_delta = 0;
struct quota_res quota_res = { 0 };
struct bkey_s_c k;
@@ -598,6 +598,9 @@ static noinline int __bchfs_fallocate(struct bch_inode_info *inode, int mode,
bch2_trans_begin(trans);
+ if (bkey_ge(iter.pos, end_pos))
+ break;
+
ret = bch2_subvolume_get_snapshot(trans,
inode->ei_inum.subvol, &snapshot);
if (ret)
@@ -634,12 +637,15 @@ static noinline int __bchfs_fallocate(struct bch_inode_info *inode, int mode,
if (bch2_clamp_data_hole(&inode->v,
&hole_start,
&hole_end,
- opts.data_replicas, true))
+ opts.data_replicas, true)) {
ret = drop_locks_do(trans,
(bch2_clamp_data_hole(&inode->v,
&hole_start,
&hole_end,
opts.data_replicas, false), 0));
+ if (ret)
+ goto bkey_err;
+ }
bch2_btree_iter_set_pos(&iter, POS(iter.pos.inode, hole_start));
if (ret)
@@ -667,10 +673,13 @@ static noinline int __bchfs_fallocate(struct bch_inode_info *inode, int mode,
bch2_i_sectors_acct(c, inode, "a_res, i_sectors_delta);
if (bch2_mark_pagecache_reserved(inode, &hole_start,
- iter.pos.offset, true))
- drop_locks_do(trans,
+ iter.pos.offset, true)) {
+ ret = drop_locks_do(trans,
bch2_mark_pagecache_reserved(inode, &hole_start,
iter.pos.offset, false));
+ if (ret)
+ goto bkey_err;
+ }
bkey_err:
bch2_quota_reservation_put(c, inode, "a_res);
if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index d7bd28b..a41d0d8a 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -656,7 +656,7 @@ static struct dentry *bch2_lookup(struct inode *vdir, struct dentry *dentry,
struct bch_hash_info hash = bch2_hash_info_init(c, &dir->ei_inode);
struct bch_inode_info *inode;
- bch2_trans_do(c, NULL, NULL, 0,
+ bch2_trans_do(c,
PTR_ERR_OR_ZERO(inode = bch2_lookup_trans(trans, inode_inum(dir),
&hash, &dentry->d_name)));
if (IS_ERR(inode))
@@ -869,7 +869,7 @@ static int bch2_rename2(struct mnt_idmap *idmap,
ret = bch2_subvol_is_ro_trans(trans, src_dir->ei_inum.subvol) ?:
bch2_subvol_is_ro_trans(trans, dst_dir->ei_inum.subvol);
if (ret)
- goto err;
+ goto err_tx_restart;
if (inode_attr_changing(dst_dir, src_inode, Inode_opt_project)) {
ret = bch2_fs_quota_transfer(c, src_inode,
@@ -1266,7 +1266,7 @@ static int bch2_fiemap(struct inode *vinode, struct fiemap_extent_info *info,
bch2_trans_iter_init(trans, &iter, BTREE_ID_extents,
POS(ei->v.i_ino, start), 0);
- while (true) {
+ while (!ret || bch2_err_matches(ret, BCH_ERR_transaction_restart)) {
enum btree_id data_btree = BTREE_ID_extents;
bch2_trans_begin(trans);
@@ -1274,14 +1274,14 @@ static int bch2_fiemap(struct inode *vinode, struct fiemap_extent_info *info,
u32 snapshot;
ret = bch2_subvolume_get_snapshot(trans, ei->ei_inum.subvol, &snapshot);
if (ret)
- goto err;
+ continue;
bch2_btree_iter_set_snapshot(&iter, snapshot);
k = bch2_btree_iter_peek_upto(&iter, end);
ret = bkey_err(k);
if (ret)
- goto err;
+ continue;
if (!k.k)
break;
@@ -1301,7 +1301,7 @@ static int bch2_fiemap(struct inode *vinode, struct fiemap_extent_info *info,
ret = bch2_read_indirect_extent(trans, &data_btree,
&offset_into_extent, &cur);
if (ret)
- break;
+ continue;
k = bkey_i_to_s_c(cur.k);
bch2_bkey_buf_realloc(&prev, c, k.k->u64s);
@@ -1329,10 +1329,6 @@ static int bch2_fiemap(struct inode *vinode, struct fiemap_extent_info *info,
bch2_btree_iter_set_pos(&iter,
POS(iter.pos.inode, iter.pos.offset + sectors));
-err:
- if (ret &&
- !bch2_err_matches(ret, BCH_ERR_transaction_restart))
- break;
}
bch2_trans_iter_exit(trans, &iter);
@@ -2040,7 +2036,7 @@ static int bch2_show_options(struct seq_file *seq, struct dentry *root)
bch2_opts_to_text(&buf, c->opts, c, c->disk_sb.sb,
OPT_MOUNT, OPT_HIDDEN, OPT_SHOW_MOUNT_STYLE);
printbuf_nul_terminate(&buf);
- seq_puts(seq, buf.buf);
+ seq_printf(seq, ",%s", buf.buf);
int ret = buf.allocation_failure ? -ENOMEM : 0;
printbuf_exit(&buf);
diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index a1087fd..75c8a97 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -929,35 +929,138 @@ static int get_visible_inodes(struct btree_trans *trans,
return ret;
}
-static int hash_redo_key(struct btree_trans *trans,
- const struct bch_hash_desc desc,
- struct bch_hash_info *hash_info,
- struct btree_iter *k_iter, struct bkey_s_c k)
+static int dirent_has_target(struct btree_trans *trans, struct bkey_s_c_dirent d)
{
- struct bkey_i *delete;
- struct bkey_i *tmp;
+ if (d.v->d_type == DT_SUBVOL) {
+ u32 snap;
+ u64 inum;
+ int ret = subvol_lookup(trans, le32_to_cpu(d.v->d_child_subvol), &snap, &inum);
+ if (ret && !bch2_err_matches(ret, ENOENT))
+ return ret;
+ return !ret;
+ } else {
+ struct btree_iter iter;
+ struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes,
+ SPOS(0, le64_to_cpu(d.v->d_inum), d.k->p.snapshot), 0);
+ int ret = bkey_err(k);
+ if (ret)
+ return ret;
- delete = bch2_trans_kmalloc(trans, sizeof(*delete));
- if (IS_ERR(delete))
- return PTR_ERR(delete);
+ ret = bkey_is_inode(k.k);
+ bch2_trans_iter_exit(trans, &iter);
+ return ret;
+ }
+}
- tmp = bch2_bkey_make_mut_noupdate(trans, k);
- if (IS_ERR(tmp))
- return PTR_ERR(tmp);
+/*
+ * Prefer to delete the first one, since that will be the one at the wrong
+ * offset:
+ * return value: 0 -> delete k1, 1 -> delete k2
+ */
+static int hash_pick_winner(struct btree_trans *trans,
+ const struct bch_hash_desc desc,
+ struct bch_hash_info *hash_info,
+ struct bkey_s_c k1,
+ struct bkey_s_c k2)
+{
+ if (bkey_val_bytes(k1.k) == bkey_val_bytes(k2.k) &&
+ !memcmp(k1.v, k2.v, bkey_val_bytes(k1.k)))
+ return 0;
- bkey_init(&delete->k);
- delete->k.p = k_iter->pos;
- return bch2_btree_iter_traverse(k_iter) ?:
- bch2_trans_update(trans, k_iter, delete, 0) ?:
- bch2_hash_set_in_snapshot(trans, desc, hash_info,
- (subvol_inum) { 0, k.k->p.inode },
- k.k->p.snapshot, tmp,
- STR_HASH_must_create|
- BTREE_UPDATE_internal_snapshot_node) ?:
- bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc);
+ switch (desc.btree_id) {
+ case BTREE_ID_dirents: {
+ int ret = dirent_has_target(trans, bkey_s_c_to_dirent(k1));
+ if (ret < 0)
+ return ret;
+ if (!ret)
+ return 0;
+
+ ret = dirent_has_target(trans, bkey_s_c_to_dirent(k2));
+ if (ret < 0)
+ return ret;
+ if (!ret)
+ return 1;
+ return 2;
+ }
+ default:
+ return 0;
+ }
+}
+
+static int fsck_update_backpointers(struct btree_trans *trans,
+ struct snapshots_seen *s,
+ const struct bch_hash_desc desc,
+ struct bch_hash_info *hash_info,
+ struct bkey_i *new)
+{
+ if (new->k.type != KEY_TYPE_dirent)
+ return 0;
+
+ struct bkey_i_dirent *d = bkey_i_to_dirent(new);
+ struct inode_walker target = inode_walker_init();
+ int ret = 0;
+
+ if (d->v.d_type == DT_SUBVOL) {
+ BUG();
+ } else {
+ ret = get_visible_inodes(trans, &target, s, le64_to_cpu(d->v.d_inum));
+ if (ret)
+ goto err;
+
+ darray_for_each(target.inodes, i) {
+ i->inode.bi_dir_offset = d->k.p.offset;
+ ret = __bch2_fsck_write_inode(trans, &i->inode);
+ if (ret)
+ goto err;
+ }
+ }
+err:
+ inode_walker_exit(&target);
+ return ret;
+}
+
+static int fsck_rename_dirent(struct btree_trans *trans,
+ struct snapshots_seen *s,
+ const struct bch_hash_desc desc,
+ struct bch_hash_info *hash_info,
+ struct bkey_s_c_dirent old)
+{
+ struct qstr old_name = bch2_dirent_get_name(old);
+ struct bkey_i_dirent *new = bch2_trans_kmalloc(trans, bkey_bytes(old.k) + 32);
+ int ret = PTR_ERR_OR_ZERO(new);
+ if (ret)
+ return ret;
+
+ bkey_dirent_init(&new->k_i);
+ dirent_copy_target(new, old);
+ new->k.p = old.k->p;
+
+ for (unsigned i = 0; i < 1000; i++) {
+ unsigned len = sprintf(new->v.d_name, "%.*s.fsck_renamed-%u",
+ old_name.len, old_name.name, i);
+ unsigned u64s = BKEY_U64s + dirent_val_u64s(len);
+
+ if (u64s > U8_MAX)
+ return -EINVAL;
+
+ new->k.u64s = u64s;
+
+ ret = bch2_hash_set_in_snapshot(trans, bch2_dirent_hash_desc, hash_info,
+ (subvol_inum) { 0, old.k->p.inode },
+ old.k->p.snapshot, &new->k_i,
+ BTREE_UPDATE_internal_snapshot_node);
+ if (!bch2_err_matches(ret, EEXIST))
+ break;
+ }
+
+ if (ret)
+ return ret;
+
+ return fsck_update_backpointers(trans, s, desc, hash_info, &new->k_i);
}
static int hash_check_key(struct btree_trans *trans,
+ struct snapshots_seen *s,
const struct bch_hash_desc desc,
struct bch_hash_info *hash_info,
struct btree_iter *k_iter, struct bkey_s_c hash_k)
@@ -986,16 +1089,9 @@ static int hash_check_key(struct btree_trans *trans,
if (bkey_eq(k.k->p, hash_k.k->p))
break;
- if (fsck_err_on(k.k->type == desc.key_type &&
- !desc.cmp_bkey(k, hash_k),
- trans, hash_table_key_duplicate,
- "duplicate hash table keys:\n%s",
- (printbuf_reset(&buf),
- bch2_bkey_val_to_text(&buf, c, hash_k),
- buf.buf))) {
- ret = bch2_hash_delete_at(trans, desc, hash_info, k_iter, 0) ?: 1;
- break;
- }
+ if (k.k->type == desc.key_type &&
+ !desc.cmp_bkey(k, hash_k))
+ goto duplicate_entries;
if (bkey_deleted(k.k)) {
bch2_trans_iter_exit(trans, &iter);
@@ -1008,18 +1104,66 @@ static int hash_check_key(struct btree_trans *trans,
return ret;
bad_hash:
if (fsck_err(trans, hash_table_key_wrong_offset,
- "hash table key at wrong offset: btree %s inode %llu offset %llu, hashed to %llu\n%s",
+ "hash table key at wrong offset: btree %s inode %llu offset %llu, hashed to %llu\n %s",
bch2_btree_id_str(desc.btree_id), hash_k.k->p.inode, hash_k.k->p.offset, hash,
(printbuf_reset(&buf),
bch2_bkey_val_to_text(&buf, c, hash_k), buf.buf))) {
- ret = hash_redo_key(trans, desc, hash_info, k_iter, hash_k);
- bch_err_fn(c, ret);
+ struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, hash_k);
+ if (IS_ERR(new))
+ return PTR_ERR(new);
+
+ k = bch2_hash_set_or_get_in_snapshot(trans, &iter, desc, hash_info,
+ (subvol_inum) { 0, hash_k.k->p.inode },
+ hash_k.k->p.snapshot, new,
+ STR_HASH_must_create|
+ BTREE_ITER_with_updates|
+ BTREE_UPDATE_internal_snapshot_node);
+ ret = bkey_err(k);
if (ret)
- return ret;
- ret = -BCH_ERR_transaction_restart_nested;
+ goto out;
+ if (k.k)
+ goto duplicate_entries;
+
+ ret = bch2_hash_delete_at(trans, desc, hash_info, k_iter,
+ BTREE_UPDATE_internal_snapshot_node) ?:
+ fsck_update_backpointers(trans, s, desc, hash_info, new) ?:
+ bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc) ?:
+ -BCH_ERR_transaction_restart_nested;
+ goto out;
}
fsck_err:
goto out;
+duplicate_entries:
+ ret = hash_pick_winner(trans, desc, hash_info, hash_k, k);
+ if (ret < 0)
+ goto out;
+
+ if (!fsck_err(trans, hash_table_key_duplicate,
+ "duplicate hash table keys%s:\n%s",
+ ret != 2 ? "" : ", both point to valid inodes",
+ (printbuf_reset(&buf),
+ bch2_bkey_val_to_text(&buf, c, hash_k),
+ prt_newline(&buf),
+ bch2_bkey_val_to_text(&buf, c, k),
+ buf.buf)))
+ goto out;
+
+ switch (ret) {
+ case 0:
+ ret = bch2_hash_delete_at(trans, desc, hash_info, k_iter, 0);
+ break;
+ case 1:
+ ret = bch2_hash_delete_at(trans, desc, hash_info, &iter, 0);
+ break;
+ case 2:
+ ret = fsck_rename_dirent(trans, s, desc, hash_info, bkey_s_c_to_dirent(hash_k)) ?:
+ bch2_hash_delete_at(trans, desc, hash_info, k_iter, 0);
+ goto out;
+ }
+
+ ret = bch2_trans_commit(trans, NULL, NULL, 0) ?:
+ -BCH_ERR_transaction_restart_nested;
+ goto out;
}
static struct bkey_s_c_dirent dirent_get_by_pos(struct btree_trans *trans,
@@ -1096,10 +1240,36 @@ static int check_inode_dirent_inode(struct btree_trans *trans,
return ret;
}
+static int get_snapshot_root_inode(struct btree_trans *trans,
+ struct bch_inode_unpacked *root,
+ u64 inum)
+{
+ struct btree_iter iter;
+ struct bkey_s_c k;
+ int ret = 0;
+
+ for_each_btree_key_reverse_norestart(trans, iter, BTREE_ID_inodes,
+ SPOS(0, inum, U32_MAX),
+ BTREE_ITER_all_snapshots, k, ret) {
+ if (k.k->p.offset != inum)
+ break;
+ if (bkey_is_inode(k.k))
+ goto found_root;
+ }
+ if (ret)
+ goto err;
+ BUG();
+found_root:
+ BUG_ON(bch2_inode_unpack(k, root));
+err:
+ bch2_trans_iter_exit(trans, &iter);
+ return ret;
+}
+
static int check_inode(struct btree_trans *trans,
struct btree_iter *iter,
struct bkey_s_c k,
- struct bch_inode_unpacked *prev,
+ struct bch_inode_unpacked *snapshot_root,
struct snapshots_seen *s)
{
struct bch_fs *c = trans->c;
@@ -1123,16 +1293,19 @@ static int check_inode(struct btree_trans *trans,
BUG_ON(bch2_inode_unpack(k, &u));
- if (prev->bi_inum != u.bi_inum)
- *prev = u;
+ if (snapshot_root->bi_inum != u.bi_inum) {
+ ret = get_snapshot_root_inode(trans, snapshot_root, u.bi_inum);
+ if (ret)
+ goto err;
+ }
- if (fsck_err_on(prev->bi_hash_seed != u.bi_hash_seed ||
- inode_d_type(prev) != inode_d_type(&u),
+ if (fsck_err_on(u.bi_hash_seed != snapshot_root->bi_hash_seed ||
+ INODE_STR_HASH(&u) != INODE_STR_HASH(snapshot_root),
trans, inode_snapshot_mismatch,
"inodes in different snapshots don't match")) {
- bch_err(c, "repair not implemented yet");
- ret = -BCH_ERR_fsck_repair_unimplemented;
- goto err_noprint;
+ u.bi_hash_seed = snapshot_root->bi_hash_seed;
+ SET_INODE_STR_HASH(&u, INODE_STR_HASH(snapshot_root));
+ do_update = true;
}
if (u.bi_dir || u.bi_dir_offset) {
@@ -1285,7 +1458,7 @@ static int check_inode(struct btree_trans *trans,
int bch2_check_inodes(struct bch_fs *c)
{
- struct bch_inode_unpacked prev = { 0 };
+ struct bch_inode_unpacked snapshot_root = {};
struct snapshots_seen s;
snapshots_seen_init(&s);
@@ -1295,7 +1468,7 @@ int bch2_check_inodes(struct bch_fs *c)
POS_MIN,
BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k,
NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
- check_inode(trans, &iter, k, &prev, &s)));
+ check_inode(trans, &iter, k, &snapshot_root, &s)));
snapshots_seen_exit(&s);
bch_err_fn(c, ret);
@@ -2307,7 +2480,7 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter,
*hash_info = bch2_hash_info_init(c, &i->inode);
dir->first_this_inode = false;
- ret = hash_check_key(trans, bch2_dirent_hash_desc, hash_info, iter, k);
+ ret = hash_check_key(trans, s, bch2_dirent_hash_desc, hash_info, iter, k);
if (ret < 0)
goto err;
if (ret) {
@@ -2421,7 +2594,7 @@ static int check_xattr(struct btree_trans *trans, struct btree_iter *iter,
*hash_info = bch2_hash_info_init(c, &i->inode);
inode->first_this_inode = false;
- ret = hash_check_key(trans, bch2_xattr_hash_desc, hash_info, iter, k);
+ ret = hash_check_key(trans, NULL, bch2_xattr_hash_desc, hash_info, iter, k);
bch_err_fn(c, ret);
return ret;
}
@@ -2509,7 +2682,7 @@ static int check_root_trans(struct btree_trans *trans)
/* Get root directory, create if it doesn't exist: */
int bch2_check_root(struct bch_fs *c)
{
- int ret = bch2_trans_do(c, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
+ int ret = bch2_trans_commit_do(c, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
check_root_trans(trans));
bch_err_fn(c, ret);
return ret;
diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c
index 344ccb7..039cb7a 100644
--- a/fs/bcachefs/inode.c
+++ b/fs/bcachefs/inode.c
@@ -163,8 +163,8 @@ static noinline int bch2_inode_unpack_v1(struct bkey_s_c_inode inode,
unsigned fieldnr = 0, field_bits;
int ret;
-#define x(_name, _bits) \
- if (fieldnr++ == INODE_NR_FIELDS(inode.v)) { \
+#define x(_name, _bits) \
+ if (fieldnr++ == INODEv1_NR_FIELDS(inode.v)) { \
unsigned offset = offsetof(struct bch_inode_unpacked, _name);\
memset((void *) unpacked + offset, 0, \
sizeof(*unpacked) - offset); \
@@ -283,6 +283,8 @@ static noinline int bch2_inode_unpack_slowpath(struct bkey_s_c k,
{
memset(unpacked, 0, sizeof(*unpacked));
+ unpacked->bi_snapshot = k.k->p.snapshot;
+
switch (k.k->type) {
case KEY_TYPE_inode: {
struct bkey_s_c_inode inode = bkey_s_c_to_inode(k);
@@ -293,10 +295,10 @@ static noinline int bch2_inode_unpack_slowpath(struct bkey_s_c k,
unpacked->bi_flags = le32_to_cpu(inode.v->bi_flags);
unpacked->bi_mode = le16_to_cpu(inode.v->bi_mode);
- if (INODE_NEW_VARINT(inode.v)) {
+ if (INODEv1_NEW_VARINT(inode.v)) {
return bch2_inode_unpack_v2(unpacked, inode.v->fields,
bkey_val_end(inode),
- INODE_NR_FIELDS(inode.v));
+ INODEv1_NR_FIELDS(inode.v));
} else {
return bch2_inode_unpack_v1(inode, unpacked);
}
@@ -471,10 +473,10 @@ int bch2_inode_validate(struct bch_fs *c, struct bkey_s_c k,
struct bkey_s_c_inode inode = bkey_s_c_to_inode(k);
int ret = 0;
- bkey_fsck_err_on(INODE_STR_HASH(inode.v) >= BCH_STR_HASH_NR,
+ bkey_fsck_err_on(INODEv1_STR_HASH(inode.v) >= BCH_STR_HASH_NR,
c, inode_str_hash_invalid,
"invalid str hash type (%llu >= %u)",
- INODE_STR_HASH(inode.v), BCH_STR_HASH_NR);
+ INODEv1_STR_HASH(inode.v), BCH_STR_HASH_NR);
ret = __bch2_inode_validate(c, k, flags);
fsck_err:
@@ -533,6 +535,10 @@ static void __bch2_inode_unpacked_to_text(struct printbuf *out,
prt_printf(out, "(%x)\n", inode->bi_flags);
prt_printf(out, "journal_seq=%llu\n", inode->bi_journal_seq);
+ prt_printf(out, "hash_seed=%llx\n", inode->bi_hash_seed);
+ prt_printf(out, "hash_type=");
+ bch2_prt_str_hash_type(out, INODE_STR_HASH(inode));
+ prt_newline(out);
prt_printf(out, "bi_size=%llu\n", inode->bi_size);
prt_printf(out, "bi_sectors=%llu\n", inode->bi_sectors);
prt_printf(out, "bi_version=%llu\n", inode->bi_version);
@@ -800,10 +806,8 @@ void bch2_inode_init_early(struct bch_fs *c,
memset(inode_u, 0, sizeof(*inode_u));
- /* ick */
- inode_u->bi_flags |= str_hash << INODE_STR_HASH_OFFSET;
- get_random_bytes(&inode_u->bi_hash_seed,
- sizeof(inode_u->bi_hash_seed));
+ SET_INODE_STR_HASH(inode_u, str_hash);
+ get_random_bytes(&inode_u->bi_hash_seed, sizeof(inode_u->bi_hash_seed));
}
void bch2_inode_init_late(struct bch_inode_unpacked *inode_u, u64 now,
@@ -1087,8 +1091,7 @@ int bch2_inode_find_by_inum_trans(struct btree_trans *trans,
int bch2_inode_find_by_inum(struct bch_fs *c, subvol_inum inum,
struct bch_inode_unpacked *inode)
{
- return bch2_trans_do(c, NULL, NULL, 0,
- bch2_inode_find_by_inum_trans(trans, inum, inode));
+ return bch2_trans_do(c, bch2_inode_find_by_inum_trans(trans, inum, inode));
}
int bch2_inode_nlink_inc(struct bch_inode_unpacked *bi)
diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h
index c8e9844..eab82b5 100644
--- a/fs/bcachefs/inode.h
+++ b/fs/bcachefs/inode.h
@@ -92,6 +92,7 @@ struct bch_inode_unpacked {
BCH_INODE_FIELDS_v3()
#undef x
};
+BITMASK(INODE_STR_HASH, struct bch_inode_unpacked, bi_flags, 20, 24);
struct bkey_inode_buf {
struct bkey_i_inode_v3 inode;
diff --git a/fs/bcachefs/inode_format.h b/fs/bcachefs/inode_format.h
index a204e46..7928d0c 100644
--- a/fs/bcachefs/inode_format.h
+++ b/fs/bcachefs/inode_format.h
@@ -150,9 +150,9 @@ enum __bch_inode_flags {
#undef x
};
-LE32_BITMASK(INODE_STR_HASH, struct bch_inode, bi_flags, 20, 24);
-LE32_BITMASK(INODE_NR_FIELDS, struct bch_inode, bi_flags, 24, 31);
-LE32_BITMASK(INODE_NEW_VARINT, struct bch_inode, bi_flags, 31, 32);
+LE32_BITMASK(INODEv1_STR_HASH, struct bch_inode, bi_flags, 20, 24);
+LE32_BITMASK(INODEv1_NR_FIELDS, struct bch_inode, bi_flags, 24, 31);
+LE32_BITMASK(INODEv1_NEW_VARINT,struct bch_inode, bi_flags, 31, 32);
LE64_BITMASK(INODEv2_STR_HASH, struct bch_inode_v2, bi_flags, 20, 24);
LE64_BITMASK(INODEv2_NR_FIELDS, struct bch_inode_v2, bi_flags, 24, 31);
diff --git a/fs/bcachefs/io_misc.c b/fs/bcachefs/io_misc.c
index 307ed0a..f283051 100644
--- a/fs/bcachefs/io_misc.c
+++ b/fs/bcachefs/io_misc.c
@@ -377,7 +377,7 @@ static int __bch2_resume_logged_op_finsert(struct btree_trans *trans,
* check for missing subvolume before fpunch, as in resume we don't want
* it to be a fatal error
*/
- ret = __bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot, warn_errors);
+ ret = lockrestart_do(trans, __bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot, warn_errors));
if (ret)
return ret;
diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c
index e4fc17c..fc246f3 100644
--- a/fs/bcachefs/io_read.c
+++ b/fs/bcachefs/io_read.c
@@ -409,8 +409,8 @@ static void bch2_read_retry_nodecode(struct bch_fs *c, struct bch_read_bio *rbio
bch2_trans_begin(trans);
rbio->bio.bi_status = 0;
- k = bch2_btree_iter_peek_slot(&iter);
- if (bkey_err(k))
+ ret = lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_slot(&iter)));
+ if (ret)
goto err;
bch2_bkey_buf_reassemble(&sk, c, k);
@@ -557,8 +557,8 @@ static int __bch2_rbio_narrow_crcs(struct btree_trans *trans,
static noinline void bch2_rbio_narrow_crcs(struct bch_read_bio *rbio)
{
- bch2_trans_do(rbio->c, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
- __bch2_rbio_narrow_crcs(trans, rbio));
+ bch2_trans_commit_do(rbio->c, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
+ __bch2_rbio_narrow_crcs(trans, rbio));
}
/* Inner part that may run in process context */
diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c
index b5fe9e0..8609e25 100644
--- a/fs/bcachefs/io_write.c
+++ b/fs/bcachefs/io_write.c
@@ -1437,7 +1437,7 @@ static void __bch2_write(struct bch_write_op *op)
* freeing up space on specific disks, which means that
* allocations for specific disks may hang arbitrarily long:
*/
- ret = bch2_trans_do(c, NULL, NULL, 0,
+ ret = bch2_trans_run(c, lockrestart_do(trans,
bch2_alloc_sectors_start_trans(trans,
op->target,
op->opts.erasure_code && !(op->flags & BCH_WRITE_CACHED),
@@ -1447,7 +1447,7 @@ static void __bch2_write(struct bch_write_op *op)
op->nr_replicas_required,
op->watermark,
op->flags,
- &op->cl, &wp));
+ &op->cl, &wp)));
if (unlikely(ret)) {
if (bch2_err_matches(ret, BCH_ERR_operation_blocked))
break;
diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c
index dc099f0..2dc0d60 100644
--- a/fs/bcachefs/journal.c
+++ b/fs/bcachefs/journal.c
@@ -758,7 +758,7 @@ int bch2_journal_flush_seq_async(struct journal *j, u64 seq,
return ret;
}
-int bch2_journal_flush_seq(struct journal *j, u64 seq)
+int bch2_journal_flush_seq(struct journal *j, u64 seq, unsigned task_state)
{
u64 start_time = local_clock();
int ret, ret2;
@@ -769,7 +769,9 @@ int bch2_journal_flush_seq(struct journal *j, u64 seq)
if (seq <= j->flushed_seq_ondisk)
return 0;
- ret = wait_event_interruptible(j->wait, (ret2 = bch2_journal_flush_seq_async(j, seq, NULL)));
+ ret = wait_event_state(j->wait,
+ (ret2 = bch2_journal_flush_seq_async(j, seq, NULL)),
+ task_state);
if (!ret)
bch2_time_stats_update(j->flush_seq_time, start_time);
@@ -788,7 +790,7 @@ void bch2_journal_flush_async(struct journal *j, struct closure *parent)
int bch2_journal_flush(struct journal *j)
{
- return bch2_journal_flush_seq(j, atomic64_read(&j->seq));
+ return bch2_journal_flush_seq(j, atomic64_read(&j->seq), TASK_UNINTERRUPTIBLE);
}
/*
@@ -851,7 +853,7 @@ int bch2_journal_meta(struct journal *j)
bch2_journal_res_put(j, &res);
- return bch2_journal_flush_seq(j, res.seq);
+ return bch2_journal_flush_seq(j, res.seq, TASK_UNINTERRUPTIBLE);
}
/* block/unlock the journal: */
diff --git a/fs/bcachefs/journal.h b/fs/bcachefs/journal.h
index 377a375..2762be6 100644
--- a/fs/bcachefs/journal.h
+++ b/fs/bcachefs/journal.h
@@ -401,7 +401,7 @@ void bch2_journal_entry_res_resize(struct journal *,
int bch2_journal_flush_seq_async(struct journal *, u64, struct closure *);
void bch2_journal_flush_async(struct journal *, struct closure *);
-int bch2_journal_flush_seq(struct journal *, u64);
+int bch2_journal_flush_seq(struct journal *, u64, unsigned);
int bch2_journal_flush(struct journal *);
bool bch2_journal_noflush_seq(struct journal *, u64);
int bch2_journal_meta(struct journal *);
diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c
index 8c456d8..0ef4a86 100644
--- a/fs/bcachefs/move.c
+++ b/fs/bcachefs/move.c
@@ -266,7 +266,7 @@ int bch2_move_extent(struct moving_context *ctxt,
if (!data_opts.rewrite_ptrs &&
!data_opts.extra_replicas) {
if (data_opts.kill_ptrs)
- return bch2_extent_drop_ptrs(trans, iter, k, data_opts);
+ return bch2_extent_drop_ptrs(trans, iter, k, &io_opts, &data_opts);
return 0;
}
diff --git a/fs/bcachefs/opts.c b/fs/bcachefs/opts.c
index 8409723..6673cbd 100644
--- a/fs/bcachefs/opts.c
+++ b/fs/bcachefs/opts.c
@@ -63,7 +63,7 @@ const char * const bch2_compression_opts[] = {
NULL
};
-const char * const bch2_str_hash_types[] = {
+const char * const __bch2_str_hash_types[] = {
BCH_STR_HASH_TYPES()
NULL
};
@@ -115,6 +115,7 @@ PRT_STR_OPT_BOUNDSCHECKED(fs_usage_type, enum bch_fs_usage_type);
PRT_STR_OPT_BOUNDSCHECKED(data_type, enum bch_data_type);
PRT_STR_OPT_BOUNDSCHECKED(csum_type, enum bch_csum_type);
PRT_STR_OPT_BOUNDSCHECKED(compression_type, enum bch_compression_type);
+PRT_STR_OPT_BOUNDSCHECKED(str_hash_type, enum bch_str_hash_type);
static int bch2_opt_fix_errors_parse(struct bch_fs *c, const char *val, u64 *res,
struct printbuf *err)
@@ -596,6 +597,9 @@ int bch2_parse_mount_opts(struct bch_fs *c, struct bch_opts *opts,
copied_opts_start = copied_opts;
while ((opt = strsep(&copied_opts, ",")) != NULL) {
+ if (!*opt)
+ continue;
+
name = strsep(&opt, "=");
val = opt;
diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h
index cb2e244..23dda01 100644
--- a/fs/bcachefs/opts.h
+++ b/fs/bcachefs/opts.h
@@ -18,7 +18,7 @@ extern const char * const bch2_sb_compat[];
extern const char * const __bch2_btree_ids[];
extern const char * const bch2_csum_opts[];
extern const char * const bch2_compression_opts[];
-extern const char * const bch2_str_hash_types[];
+extern const char * const __bch2_str_hash_types[];
extern const char * const bch2_str_hash_opts[];
extern const char * const __bch2_data_types[];
extern const char * const bch2_member_states[];
@@ -29,6 +29,7 @@ void bch2_prt_fs_usage_type(struct printbuf *, enum bch_fs_usage_type);
void bch2_prt_data_type(struct printbuf *, enum bch_data_type);
void bch2_prt_csum_type(struct printbuf *, enum bch_csum_type);
void bch2_prt_compression_type(struct printbuf *, enum bch_compression_type);
+void bch2_prt_str_hash_type(struct printbuf *, enum bch_str_hash_type);
static inline const char *bch2_d_type_str(unsigned d_type)
{
diff --git a/fs/bcachefs/quota.c b/fs/bcachefs/quota.c
index c32a05e..74f45a81 100644
--- a/fs/bcachefs/quota.c
+++ b/fs/bcachefs/quota.c
@@ -869,7 +869,7 @@ static int bch2_set_quota(struct super_block *sb, struct kqid qid,
bkey_quota_init(&new_quota.k_i);
new_quota.k.p = POS(qid.type, from_kqid(&init_user_ns, qid));
- ret = bch2_trans_do(c, NULL, NULL, 0,
+ ret = bch2_trans_commit_do(c, NULL, NULL, 0,
bch2_set_quota_trans(trans, &new_quota, qdq)) ?:
__bch2_quota_set(c, bkey_i_to_s_c(&new_quota.k_i), qdq);
diff --git a/fs/bcachefs/rebalance.c b/fs/bcachefs/rebalance.c
index 2d299a3..cd66473 100644
--- a/fs/bcachefs/rebalance.c
+++ b/fs/bcachefs/rebalance.c
@@ -70,7 +70,9 @@ static int __bch2_set_rebalance_needs_scan(struct btree_trans *trans, u64 inum)
int bch2_set_rebalance_needs_scan(struct bch_fs *c, u64 inum)
{
- int ret = bch2_trans_do(c, NULL, NULL, BCH_TRANS_COMMIT_no_enospc|BCH_TRANS_COMMIT_lazy_rw,
+ int ret = bch2_trans_commit_do(c, NULL, NULL,
+ BCH_TRANS_COMMIT_no_enospc|
+ BCH_TRANS_COMMIT_lazy_rw,
__bch2_set_rebalance_needs_scan(trans, inum));
rebalance_wakeup(c);
return ret;
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 55e1504..32d15aa 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -94,11 +94,10 @@ static void bch2_reconstruct_alloc(struct bch_fs *c)
__set_bit_le64(BCH_FSCK_ERR_accounting_mismatch, ext->errors_silent);
c->sb.compat &= ~(1ULL << BCH_COMPAT_alloc_info);
- bch2_write_super(c);
- mutex_unlock(&c->sb_lock);
-
c->opts.recovery_passes |= bch2_recovery_passes_from_stable(le64_to_cpu(ext->recovery_passes_required[0]));
+ bch2_write_super(c);
+ mutex_unlock(&c->sb_lock);
bch2_shoot_down_journal_keys(c, BTREE_ID_alloc,
0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
@@ -1002,6 +1001,7 @@ int bch2_fs_initialize(struct bch_fs *c)
struct bch_inode_unpacked root_inode, lostfound_inode;
struct bkey_inode_buf packed_inode;
struct qstr lostfound = QSTR("lost+found");
+ struct bch_member *m;
int ret;
bch_notice(c, "initializing new filesystem");
@@ -1018,6 +1018,14 @@ int bch2_fs_initialize(struct bch_fs *c)
SET_BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb, bcachefs_metadata_version_current);
bch2_write_super(c);
}
+
+ for_each_member_device(c, ca) {
+ m = bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx);
+ SET_BCH_MEMBER_FREESPACE_INITIALIZED(m, false);
+ ca->mi = bch2_mi_to_cpu(m);
+ }
+
+ bch2_write_super(c);
mutex_unlock(&c->sb_lock);
c->curr_recovery_pass = BCH_RECOVERY_PASS_NR;
@@ -1091,7 +1099,7 @@ int bch2_fs_initialize(struct bch_fs *c)
bch2_inode_init_early(c, &lostfound_inode);
- ret = bch2_trans_do(c, NULL, NULL, 0,
+ ret = bch2_trans_commit_do(c, NULL, NULL, 0,
bch2_create_trans(trans,
BCACHEFS_ROOT_SUBVOL_INUM,
&root_inode, &lostfound_inode,
diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c
index ae715ff..8767c33 100644
--- a/fs/bcachefs/sb-downgrade.c
+++ b/fs/bcachefs/sb-downgrade.c
@@ -143,6 +143,9 @@ UPGRADE_TABLE()
static int have_stripes(struct bch_fs *c)
{
+ if (IS_ERR_OR_NULL(c->btree_roots_known[BTREE_ID_stripes].b))
+ return 0;
+
return !btree_node_fake(c->btree_roots_known[BTREE_ID_stripes].b);
}
diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h
index aab328a..937275d 100644
--- a/fs/bcachefs/sb-errors_format.h
+++ b/fs/bcachefs/sb-errors_format.h
@@ -267,8 +267,8 @@ enum bch_fsck_flags {
x(journal_entry_dup_same_device, 246, 0) \
x(inode_bi_subvol_missing, 247, 0) \
x(inode_bi_subvol_wrong, 248, 0) \
- x(inode_points_to_missing_dirent, 249, 0) \
- x(inode_points_to_wrong_dirent, 250, 0) \
+ x(inode_points_to_missing_dirent, 249, FSCK_AUTOFIX) \
+ x(inode_points_to_wrong_dirent, 250, FSCK_AUTOFIX) \
x(inode_bi_parent_nonzero, 251, 0) \
x(dirent_to_missing_parent_subvol, 252, 0) \
x(dirent_not_visible_in_parent_subvol, 253, 0) \
diff --git a/fs/bcachefs/str_hash.h b/fs/bcachefs/str_hash.h
index 215eed4..ec2b1fe 100644
--- a/fs/bcachefs/str_hash.h
+++ b/fs/bcachefs/str_hash.h
@@ -46,8 +46,7 @@ bch2_hash_info_init(struct bch_fs *c, const struct bch_inode_unpacked *bi)
{
/* XXX ick */
struct bch_hash_info info = {
- .type = (bi->bi_flags >> INODE_STR_HASH_OFFSET) &
- ~(~0U << INODE_STR_HASH_BITS),
+ .type = INODE_STR_HASH(bi),
.siphash_key = { .k0 = bi->bi_hash_seed }
};
@@ -253,19 +252,20 @@ int bch2_hash_needs_whiteout(struct btree_trans *trans,
}
static __always_inline
-int bch2_hash_set_in_snapshot(struct btree_trans *trans,
+struct bkey_s_c bch2_hash_set_or_get_in_snapshot(struct btree_trans *trans,
+ struct btree_iter *iter,
const struct bch_hash_desc desc,
const struct bch_hash_info *info,
subvol_inum inum, u32 snapshot,
struct bkey_i *insert,
enum btree_iter_update_trigger_flags flags)
{
- struct btree_iter iter, slot = { NULL };
+ struct btree_iter slot = {};
struct bkey_s_c k;
bool found = false;
int ret;
- for_each_btree_key_upto_norestart(trans, iter, desc.btree_id,
+ for_each_btree_key_upto_norestart(trans, *iter, desc.btree_id,
SPOS(insert->k.p.inode,
desc.hash_bkey(info, bkey_i_to_s_c(insert)),
snapshot),
@@ -280,7 +280,7 @@ int bch2_hash_set_in_snapshot(struct btree_trans *trans,
}
if (!slot.path && !(flags & STR_HASH_must_replace))
- bch2_trans_copy_iter(&slot, &iter);
+ bch2_trans_copy_iter(&slot, iter);
if (k.k->type != KEY_TYPE_hash_whiteout)
goto not_found;
@@ -290,29 +290,50 @@ int bch2_hash_set_in_snapshot(struct btree_trans *trans,
ret = -BCH_ERR_ENOSPC_str_hash_create;
out:
bch2_trans_iter_exit(trans, &slot);
- bch2_trans_iter_exit(trans, &iter);
-
- return ret;
+ bch2_trans_iter_exit(trans, iter);
+ return ret ? bkey_s_c_err(ret) : bkey_s_c_null;
found:
found = true;
not_found:
-
- if (!found && (flags & STR_HASH_must_replace)) {
+ if (found && (flags & STR_HASH_must_create)) {
+ bch2_trans_iter_exit(trans, &slot);
+ return k;
+ } else if (!found && (flags & STR_HASH_must_replace)) {
ret = -BCH_ERR_ENOENT_str_hash_set_must_replace;
- } else if (found && (flags & STR_HASH_must_create)) {
- ret = -BCH_ERR_EEXIST_str_hash_set;
} else {
if (!found && slot.path)
- swap(iter, slot);
+ swap(*iter, slot);
- insert->k.p = iter.pos;
- ret = bch2_trans_update(trans, &iter, insert, flags);
+ insert->k.p = iter->pos;
+ ret = bch2_trans_update(trans, iter, insert, flags);
}
goto out;
}
static __always_inline
+int bch2_hash_set_in_snapshot(struct btree_trans *trans,
+ const struct bch_hash_desc desc,
+ const struct bch_hash_info *info,
+ subvol_inum inum, u32 snapshot,
+ struct bkey_i *insert,
+ enum btree_iter_update_trigger_flags flags)
+{
+ struct btree_iter iter;
+ struct bkey_s_c k = bch2_hash_set_or_get_in_snapshot(trans, &iter, desc, info, inum,
+ snapshot, insert, flags);
+ int ret = bkey_err(k);
+ if (ret)
+ return ret;
+ if (k.k) {
+ bch2_trans_iter_exit(trans, &iter);
+ return -BCH_ERR_EEXIST_str_hash_set;
+ }
+
+ return 0;
+}
+
+static __always_inline
int bch2_hash_set(struct btree_trans *trans,
const struct bch_hash_desc desc,
const struct bch_hash_info *info,
@@ -363,8 +384,11 @@ int bch2_hash_delete(struct btree_trans *trans,
struct btree_iter iter;
struct bkey_s_c k = bch2_hash_lookup(trans, &iter, desc, info, inum, key,
BTREE_ITER_intent);
- int ret = bkey_err(k) ?:
- bch2_hash_delete_at(trans, desc, info, &iter, 0);
+ int ret = bkey_err(k);
+ if (ret)
+ return ret;
+
+ ret = bch2_hash_delete_at(trans, desc, info, &iter, 0);
bch2_trans_iter_exit(trans, &iter);
return ret;
}
diff --git a/fs/bcachefs/subvolume.c b/fs/bcachefs/subvolume.c
index 91d8187..80e5efa 100644
--- a/fs/bcachefs/subvolume.c
+++ b/fs/bcachefs/subvolume.c
@@ -319,8 +319,7 @@ int bch2_subvol_is_ro_trans(struct btree_trans *trans, u32 subvol)
int bch2_subvol_is_ro(struct bch_fs *c, u32 subvol)
{
- return bch2_trans_do(c, NULL, NULL, 0,
- bch2_subvol_is_ro_trans(trans, subvol));
+ return bch2_trans_do(c, bch2_subvol_is_ro_trans(trans, subvol));
}
int bch2_snapshot_get_subvol(struct btree_trans *trans, u32 snapshot,
@@ -676,8 +675,8 @@ static int __bch2_fs_upgrade_for_subvolumes(struct btree_trans *trans)
/* set bi_subvol on root inode */
int bch2_fs_upgrade_for_subvolumes(struct bch_fs *c)
{
- int ret = bch2_trans_do(c, NULL, NULL, BCH_TRANS_COMMIT_lazy_rw,
- __bch2_fs_upgrade_for_subvolumes(trans));
+ int ret = bch2_trans_commit_do(c, NULL, NULL, BCH_TRANS_COMMIT_lazy_rw,
+ __bch2_fs_upgrade_for_subvolumes(trans));
bch_err_fn(c, ret);
return ret;
}
diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c
index ce7410d..7c71594 100644
--- a/fs/bcachefs/super-io.c
+++ b/fs/bcachefs/super-io.c
@@ -287,6 +287,11 @@ static int validate_sb_layout(struct bch_sb_layout *layout, struct printbuf *out
return -BCH_ERR_invalid_sb_layout_nr_superblocks;
}
+ if (layout->sb_max_size_bits > BCH_SB_LAYOUT_SIZE_BITS_MAX) {
+ prt_printf(out, "Invalid superblock layout: max_size_bits too high");
+ return -BCH_ERR_invalid_sb_layout_sb_max_size_bits;
+ }
+
max_sectors = 1 << layout->sb_max_size_bits;
prev_offset = le64_to_cpu(layout->sb_offset[0]);
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 77d811a..657fd37 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -1972,7 +1972,7 @@ int bch2_dev_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets)
};
u64 v[3] = { nbuckets - old_nbuckets, 0, 0 };
- ret = bch2_trans_do(ca->fs, NULL, NULL, 0,
+ ret = bch2_trans_commit_do(ca->fs, NULL, NULL, 0,
bch2_disk_accounting_mod(trans, &acc, v, ARRAY_SIZE(v), false)) ?:
bch2_dev_freespace_init(c, ca, old_nbuckets, nbuckets);
if (ret)
diff --git a/fs/bcachefs/tests.c b/fs/bcachefs/tests.c
index b2f2097..315038a 100644
--- a/fs/bcachefs/tests.c
+++ b/fs/bcachefs/tests.c
@@ -450,7 +450,7 @@ static int insert_test_overlapping_extent(struct bch_fs *c, u64 inum, u64 start,
k.k_i.k.p.snapshot = snapid;
k.k_i.k.size = len;
- ret = bch2_trans_do(c, NULL, NULL, 0,
+ ret = bch2_trans_commit_do(c, NULL, NULL, 0,
bch2_btree_insert_nonextent(trans, BTREE_ID_extents, &k.k_i,
BTREE_UPDATE_internal_snapshot_node));
bch_err_fn(c, ret);
@@ -510,7 +510,7 @@ static int test_snapshots(struct bch_fs *c, u64 nr)
if (ret)
return ret;
- ret = bch2_trans_do(c, NULL, NULL, 0,
+ ret = bch2_trans_commit_do(c, NULL, NULL, 0,
bch2_snapshot_node_create(trans, U32_MAX,
snapids,
snapid_subvols,
diff --git a/fs/bcachefs/xattr.c b/fs/bcachefs/xattr.c
index 56c8d3f..952aca4 100644
--- a/fs/bcachefs/xattr.c
+++ b/fs/bcachefs/xattr.c
@@ -330,7 +330,7 @@ static int bch2_xattr_get_handler(const struct xattr_handler *handler,
{
struct bch_inode_info *inode = to_bch_ei(vinode);
struct bch_fs *c = inode->v.i_sb->s_fs_info;
- int ret = bch2_trans_do(c, NULL, NULL, 0,
+ int ret = bch2_trans_do(c,
bch2_xattr_get_trans(trans, inode, name, buffer, size, handler->flags));
if (ret < 0 && bch2_err_matches(ret, ENOENT))
diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index fec5c6cd..7e0f960 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -49,6 +49,7 @@ void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_fs_info *fs_info,
bbio->end_io = end_io;
bbio->private = private;
atomic_set(&bbio->pending_ios, 1);
+ WRITE_ONCE(bbio->status, BLK_STS_OK);
}
/*
@@ -113,41 +114,29 @@ static void __btrfs_bio_end_io(struct btrfs_bio *bbio)
}
}
-static void btrfs_orig_write_end_io(struct bio *bio);
-
-static void btrfs_bbio_propagate_error(struct btrfs_bio *bbio,
- struct btrfs_bio *orig_bbio)
-{
- /*
- * For writes we tolerate nr_mirrors - 1 write failures, so we can't
- * just blindly propagate a write failure here. Instead increment the
- * error count in the original I/O context so that it is guaranteed to
- * be larger than the error tolerance.
- */
- if (bbio->bio.bi_end_io == &btrfs_orig_write_end_io) {
- struct btrfs_io_stripe *orig_stripe = orig_bbio->bio.bi_private;
- struct btrfs_io_context *orig_bioc = orig_stripe->bioc;
-
- atomic_add(orig_bioc->max_errors, &orig_bioc->error);
- } else {
- orig_bbio->bio.bi_status = bbio->bio.bi_status;
- }
-}
-
void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status)
{
bbio->bio.bi_status = status;
if (bbio->bio.bi_pool == &btrfs_clone_bioset) {
struct btrfs_bio *orig_bbio = bbio->private;
- if (bbio->bio.bi_status)
- btrfs_bbio_propagate_error(bbio, orig_bbio);
btrfs_cleanup_bio(bbio);
bbio = orig_bbio;
}
- if (atomic_dec_and_test(&bbio->pending_ios))
+ /*
+ * At this point, bbio always points to the original btrfs_bio. Save
+ * the first error in it.
+ */
+ if (status != BLK_STS_OK)
+ cmpxchg(&bbio->status, BLK_STS_OK, status);
+
+ if (atomic_dec_and_test(&bbio->pending_ios)) {
+ /* Load split bio's error which might be set above. */
+ if (status == BLK_STS_OK)
+ bbio->bio.bi_status = READ_ONCE(bbio->status);
__btrfs_bio_end_io(bbio);
+ }
}
static int next_repair_mirror(struct btrfs_failed_bio *fbio, int cur_mirror)
diff --git a/fs/btrfs/bio.h b/fs/btrfs/bio.h
index e4861234..e2fe160 100644
--- a/fs/btrfs/bio.h
+++ b/fs/btrfs/bio.h
@@ -79,6 +79,9 @@ struct btrfs_bio {
/* File system that this I/O operates on. */
struct btrfs_fs_info *fs_info;
+ /* Save the first error status of split bio. */
+ blk_status_t status;
+
/*
* This member must come last, bio_alloc_bioset will allocate enough
* bytes for entire btrfs_bio but relies on bio being last.
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 7980b2e..4423d8b 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -3819,6 +3819,8 @@ void btrfs_free_reserved_bytes(struct btrfs_block_group *cache,
spin_lock(&cache->lock);
if (cache->ro)
space_info->bytes_readonly += num_bytes;
+ else if (btrfs_is_zoned(cache->fs_info))
+ space_info->bytes_zone_unusable += num_bytes;
cache->reserved -= num_bytes;
space_info->bytes_reserved -= num_bytes;
space_info->max_extent_size = 0;
diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c
index b95ef44..968dae9 100644
--- a/fs/btrfs/defrag.c
+++ b/fs/btrfs/defrag.c
@@ -763,12 +763,12 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start,
* We can get a merged extent, in that case, we need to re-search
* tree to get the original em for defrag.
*
- * If @newer_than is 0 or em::generation < newer_than, we can trust
- * this em, as either we don't care about the generation, or the
- * merged extent map will be rejected anyway.
+ * This is because even if we have adjacent extents that are contiguous
+ * and compatible (same type and flags), we still want to defrag them
+ * so that we use less metadata (extent items in the extent tree and
+ * file extent items in the inode's subvolume tree).
*/
- if (em && (em->flags & EXTENT_FLAG_MERGED) &&
- newer_than && em->generation >= newer_than) {
+ if (em && (em->flags & EXTENT_FLAG_MERGED)) {
free_extent_map(em);
em = NULL;
}
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index 001c0c2..1e8cd7c 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -347,8 +347,8 @@ btrfs_search_dir_index_item(struct btrfs_root *root, struct btrfs_path *path,
return di;
}
/* Adjust return code if the key was not found in the next leaf. */
- if (ret > 0)
- ret = 0;
+ if (ret >= 0)
+ ret = -ENOENT;
return ERR_PTR(ret);
}
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 4ad5db6..b11bfe6 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1959,7 +1959,7 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)
fs_info->qgroup_seq = 1;
fs_info->qgroup_ulist = NULL;
fs_info->qgroup_rescan_running = false;
- fs_info->qgroup_drop_subtree_thres = BTRFS_MAX_LEVEL;
+ fs_info->qgroup_drop_subtree_thres = BTRFS_QGROUP_DROP_SUBTREE_THRES_DEFAULT;
mutex_init(&fs_info->qgroup_rescan_lock);
}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 309a8ae..872cca5 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -262,22 +262,23 @@ static noinline int lock_delalloc_folios(struct inode *inode,
for (i = 0; i < found_folios; i++) {
struct folio *folio = fbatch.folios[i];
- u32 len = end + 1 - start;
+ u64 range_start;
+ u32 range_len;
if (folio == locked_folio)
continue;
- if (btrfs_folio_start_writer_lock(fs_info, folio, start,
- len))
- goto out;
-
+ folio_lock(folio);
if (!folio_test_dirty(folio) || folio->mapping != mapping) {
- btrfs_folio_end_writer_lock(fs_info, folio, start,
- len);
+ folio_unlock(folio);
goto out;
}
+ range_start = max_t(u64, folio_pos(folio), start);
+ range_len = min_t(u64, folio_pos(folio) + folio_size(folio),
+ end + 1) - range_start;
+ btrfs_folio_set_writer_lock(fs_info, folio, range_start, range_len);
- processed_end = folio_pos(folio) + folio_size(folio) - 1;
+ processed_end = range_start + range_len - 1;
}
folio_batch_release(&fbatch);
cond_resched();
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 25d191f..1d93e120 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -230,7 +230,12 @@ static bool mergeable_maps(const struct extent_map *prev, const struct extent_ma
if (extent_map_end(prev) != next->start)
return false;
- if (prev->flags != next->flags)
+ /*
+ * The merged flag is not an on-disk flag, it just indicates we had the
+ * extent maps of 2 (or more) adjacent extents merged, so factor it out.
+ */
+ if ((prev->flags & ~EXTENT_FLAG_MERGED) !=
+ (next->flags & ~EXTENT_FLAG_MERGED))
return false;
if (next->disk_bytenr < EXTENT_MAP_LAST_BYTE - 1)
@@ -243,13 +248,19 @@ static bool mergeable_maps(const struct extent_map *prev, const struct extent_ma
/*
* Handle the on-disk data extents merge for @prev and @next.
*
+ * @prev: left extent to merge
+ * @next: right extent to merge
+ * @merged: the extent we will not discard after the merge; updated with new values
+ *
+ * After this, one of the two extents is the new merged extent and the other is
+ * removed from the tree and likely freed. Note that @merged is one of @prev/@next
+ * so there is const/non-const aliasing occurring here.
+ *
* Only touches disk_bytenr/disk_num_bytes/offset/ram_bytes.
* For now only uncompressed regular extent can be merged.
- *
- * @prev and @next will be both updated to point to the new merged range.
- * Thus one of them should be removed by the caller.
*/
-static void merge_ondisk_extents(struct extent_map *prev, struct extent_map *next)
+static void merge_ondisk_extents(const struct extent_map *prev, const struct extent_map *next,
+ struct extent_map *merged)
{
u64 new_disk_bytenr;
u64 new_disk_num_bytes;
@@ -284,15 +295,10 @@ static void merge_ondisk_extents(struct extent_map *prev, struct extent_map *nex
new_disk_bytenr;
new_offset = prev->disk_bytenr + prev->offset - new_disk_bytenr;
- prev->disk_bytenr = new_disk_bytenr;
- prev->disk_num_bytes = new_disk_num_bytes;
- prev->ram_bytes = new_disk_num_bytes;
- prev->offset = new_offset;
-
- next->disk_bytenr = new_disk_bytenr;
- next->disk_num_bytes = new_disk_num_bytes;
- next->ram_bytes = new_disk_num_bytes;
- next->offset = new_offset;
+ merged->disk_bytenr = new_disk_bytenr;
+ merged->disk_num_bytes = new_disk_num_bytes;
+ merged->ram_bytes = new_disk_num_bytes;
+ merged->offset = new_offset;
}
static void dump_extent_map(struct btrfs_fs_info *fs_info, const char *prefix,
@@ -361,7 +367,7 @@ static void try_merge_map(struct btrfs_inode *inode, struct extent_map *em)
em->generation = max(em->generation, merge->generation);
if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE)
- merge_ondisk_extents(merge, em);
+ merge_ondisk_extents(merge, em, em);
em->flags |= EXTENT_FLAG_MERGED;
validate_extent_map(fs_info, em);
@@ -378,7 +384,7 @@ static void try_merge_map(struct btrfs_inode *inode, struct extent_map *em)
if (rb && can_merge_extent_map(merge) && mergeable_maps(em, merge)) {
em->len += merge->len;
if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE)
- merge_ondisk_extents(em, merge);
+ merge_ondisk_extents(em, merge, em);
validate_extent_map(fs_info, em);
rb_erase(&merge->rb_node, &tree->root);
RB_CLEAR_NODE(&merge->rb_node);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5618ca0..da51edb 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4368,11 +4368,8 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
*/
if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) {
di = btrfs_search_dir_index_item(root, path, dir_ino, &fname.disk_name);
- if (IS_ERR_OR_NULL(di)) {
- if (!di)
- ret = -ENOENT;
- else
- ret = PTR_ERR(di);
+ if (IS_ERR(di)) {
+ ret = PTR_ERR(di);
btrfs_abort_transaction(trans, ret);
goto out;
}
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 1332ec5..a0e8dec 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1407,7 +1407,7 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
fs_info->quota_root = NULL;
fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON;
fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE;
- fs_info->qgroup_drop_subtree_thres = BTRFS_MAX_LEVEL;
+ fs_info->qgroup_drop_subtree_thres = BTRFS_QGROUP_DROP_SUBTREE_THRES_DEFAULT;
spin_unlock(&fs_info->qgroup_lock);
btrfs_free_qgroup_config(fs_info);
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 98adf4e..c229256 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -121,6 +121,8 @@ struct btrfs_inode;
#define BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN (1ULL << 63)
#define BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING (1ULL << 62)
+#define BTRFS_QGROUP_DROP_SUBTREE_THRES_DEFAULT (3)
+
/*
* Record a dirty extent, and info qgroup to update quota on it
*/
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 98fa0f3..926d7a9 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -340,6 +340,15 @@ static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
fallthrough;
case Opt_compress:
case Opt_compress_type:
+ /*
+ * Provide the same semantics as older kernels that don't use fs
+ * context, specifying the "compress" option clears
+ * "force-compress" without the need to pass
+ * "compress-force=[no|none]" before specifying "compress".
+ */
+ if (opt != Opt_compress_force && opt != Opt_compress_force_type)
+ btrfs_clear_opt(ctx->mount_opt, FORCE_COMPRESS);
+
if (opt == Opt_compress || opt == Opt_compress_force) {
ctx->compress_type = BTRFS_COMPRESS_ZLIB;
ctx->compress_level = BTRFS_ZLIB_DEFAULT_LEVEL;
@@ -1498,8 +1507,7 @@ static int btrfs_reconfigure(struct fs_context *fc)
sync_filesystem(sb);
set_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
- if (!mount_reconfigure &&
- !btrfs_check_options(fs_info, &ctx->mount_opt, fc->sb_flags))
+ if (!btrfs_check_options(fs_info, &ctx->mount_opt, fc->sb_flags))
return -EINVAL;
ret = btrfs_check_features(fs_info, !(fc->sb_flags & SB_RDONLY));
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 8f340ad..eb51b60 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1105,6 +1105,7 @@ static void btrfs_close_one_device(struct btrfs_device *device)
if (device->bdev) {
fs_devices->open_devices--;
device->bdev = NULL;
+ device->bdev_file = NULL;
}
clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
btrfs_destroy_dev_zone_info(device);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index f33fbce..dafdf76 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2288,6 +2288,13 @@ static int fuse_writepages_fill(struct folio *folio,
struct folio *tmp_folio;
int err;
+ if (!data->ff) {
+ err = -EIO;
+ data->ff = fuse_write_file_get(fi);
+ if (!data->ff)
+ goto out_unlock;
+ }
+
if (wpa && fuse_writepage_need_send(fc, &folio->page, ap, data)) {
fuse_writepages_send(data);
data->wpa = NULL;
@@ -2351,13 +2358,13 @@ static int fuse_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
- struct fuse_inode *fi = get_fuse_inode(inode);
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_fill_wb_data data;
int err;
+ err = -EIO;
if (fuse_is_bad(inode))
- return -EIO;
+ goto out;
if (wbc->sync_mode == WB_SYNC_NONE &&
fc->num_background >= fc->congestion_threshold)
@@ -2365,9 +2372,7 @@ static int fuse_writepages(struct address_space *mapping,
data.inode = inode;
data.wpa = NULL;
- data.ff = fuse_write_file_get(fi);
- if (!data.ff)
- return -EIO;
+ data.ff = NULL;
err = -ENOMEM;
data.orig_pages = kcalloc(fc->max_pages,
@@ -2381,10 +2386,11 @@ static int fuse_writepages(struct address_space *mapping,
WARN_ON(!data.wpa->ia.ap.num_pages);
fuse_writepages_send(&data);
}
+ if (data.ff)
+ fuse_file_put(data.ff, false);
kfree(data.orig_pages);
out:
- fuse_file_put(data.ff, false);
return err;
}
diff --git a/fs/fuse/passthrough.c b/fs/fuse/passthrough.c
index 62aee82..bbac547 100644
--- a/fs/fuse/passthrough.c
+++ b/fs/fuse/passthrough.c
@@ -18,11 +18,11 @@ static void fuse_file_accessed(struct file *file)
fuse_invalidate_atime(inode);
}
-static void fuse_file_modified(struct file *file)
+static void fuse_passthrough_end_write(struct file *file, loff_t pos, ssize_t ret)
{
struct inode *inode = file_inode(file);
- fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE);
+ fuse_write_update_attr(inode, pos, ret);
}
ssize_t fuse_passthrough_read_iter(struct kiocb *iocb, struct iov_iter *iter)
@@ -63,7 +63,7 @@ ssize_t fuse_passthrough_write_iter(struct kiocb *iocb,
struct backing_file_ctx ctx = {
.cred = ff->cred,
.user_file = file,
- .end_write = fuse_file_modified,
+ .end_write = fuse_passthrough_end_write,
};
pr_debug("%s: backing_file=0x%p, pos=%lld, len=%zu\n", __func__,
@@ -110,7 +110,7 @@ ssize_t fuse_passthrough_splice_write(struct pipe_inode_info *pipe,
struct backing_file_ctx ctx = {
.cred = ff->cred,
.user_file = out,
- .end_write = fuse_file_modified,
+ .end_write = fuse_passthrough_end_write,
};
pr_debug("%s: backing_file=0x%p, pos=%lld, len=%zu, flags=0x%x\n", __func__,
@@ -234,7 +234,6 @@ int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map)
goto out;
backing_sb = file_inode(file)->i_sb;
- pr_info("%s: %x:%pD %i\n", __func__, backing_sb->s_dev, file, backing_sb->s_stack_depth);
res = -ELOOP;
if (backing_sb->s_stack_depth >= fc->max_stack_depth)
goto out_fput;
diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c
index 974ecf5..3ab4100 100644
--- a/fs/jfs/jfs_dmap.c
+++ b/fs/jfs/jfs_dmap.c
@@ -187,7 +187,7 @@ int dbMount(struct inode *ipbmap)
}
bmp->db_numag = le32_to_cpu(dbmp_le->dn_numag);
- if (!bmp->db_numag || bmp->db_numag >= MAXAG) {
+ if (!bmp->db_numag || bmp->db_numag > MAXAG) {
err = -EINVAL;
goto err_release_metapage;
}
diff --git a/fs/namespace.c b/fs/namespace.c
index 93c3778..d26f5e6 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -3944,7 +3944,9 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
new = copy_tree(old, old->mnt.mnt_root, copy_flags);
if (IS_ERR(new)) {
namespace_unlock();
- free_mnt_ns(new_ns);
+ ns_free_inum(&new_ns->ns);
+ dec_mnt_namespaces(new_ns->ucounts);
+ mnt_ns_release(new_ns);
return ERR_CAST(new);
}
if (user_ns != ns->user_ns) {
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index c40e226..af46a59 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -67,7 +67,8 @@ static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_in
* Decant the list of folios to read into a rolling buffer.
*/
static size_t netfs_load_buffer_from_ra(struct netfs_io_request *rreq,
- struct folio_queue *folioq)
+ struct folio_queue *folioq,
+ struct folio_batch *put_batch)
{
unsigned int order, nr;
size_t size = 0;
@@ -82,6 +83,9 @@ static size_t netfs_load_buffer_from_ra(struct netfs_io_request *rreq,
order = folio_order(folio);
folioq->orders[i] = order;
size += PAGE_SIZE << order;
+
+ if (!folio_batch_add(put_batch, folio))
+ folio_batch_release(put_batch);
}
for (int i = nr; i < folioq_nr_slots(folioq); i++)
@@ -120,6 +124,9 @@ static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq)
* that we will need to release later - but we don't want to do
* that until after we've started the I/O.
*/
+ struct folio_batch put_batch;
+
+ folio_batch_init(&put_batch);
while (rreq->submitted < subreq->start + rsize) {
struct folio_queue *tail = rreq->buffer_tail, *new;
size_t added;
@@ -132,10 +139,11 @@ static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq)
new->prev = tail;
tail->next = new;
rreq->buffer_tail = new;
- added = netfs_load_buffer_from_ra(rreq, new);
+ added = netfs_load_buffer_from_ra(rreq, new, &put_batch);
rreq->iter.count += added;
rreq->submitted += added;
}
+ folio_batch_release(&put_batch);
}
subreq->len = rsize;
@@ -348,6 +356,7 @@ static int netfs_wait_for_read(struct netfs_io_request *rreq)
static int netfs_prime_buffer(struct netfs_io_request *rreq)
{
struct folio_queue *folioq;
+ struct folio_batch put_batch;
size_t added;
folioq = kmalloc(sizeof(*folioq), GFP_KERNEL);
@@ -360,39 +369,14 @@ static int netfs_prime_buffer(struct netfs_io_request *rreq)
rreq->submitted = rreq->start;
iov_iter_folio_queue(&rreq->iter, ITER_DEST, folioq, 0, 0, 0);
- added = netfs_load_buffer_from_ra(rreq, folioq);
+ folio_batch_init(&put_batch);
+ added = netfs_load_buffer_from_ra(rreq, folioq, &put_batch);
+ folio_batch_release(&put_batch);
rreq->iter.count += added;
rreq->submitted += added;
return 0;
}
-/*
- * Drop the ref on each folio that we inherited from the VM readahead code. We
- * still have the folio locks to pin the page until we complete the I/O.
- *
- * Note that we can't just release the batch in each queue struct as we use the
- * occupancy count in other places.
- */
-static void netfs_put_ra_refs(struct folio_queue *folioq)
-{
- struct folio_batch fbatch;
-
- folio_batch_init(&fbatch);
- while (folioq) {
- for (unsigned int slot = 0; slot < folioq_count(folioq); slot++) {
- struct folio *folio = folioq_folio(folioq, slot);
- if (!folio)
- continue;
- trace_netfs_folio(folio, netfs_folio_trace_read_put);
- if (!folio_batch_add(&fbatch, folio))
- folio_batch_release(&fbatch);
- }
- folioq = folioq->next;
- }
-
- folio_batch_release(&fbatch);
-}
-
/**
* netfs_readahead - Helper to manage a read request
* @ractl: The description of the readahead request
@@ -436,9 +420,6 @@ void netfs_readahead(struct readahead_control *ractl)
goto cleanup_free;
netfs_read_to_pagecache(rreq);
- /* Release the folio refs whilst we're waiting for the I/O. */
- netfs_put_ra_refs(rreq->buffer);
-
netfs_put_request(rreq, true, netfs_rreq_trace_put_return);
return;
diff --git a/fs/netfs/locking.c b/fs/netfs/locking.c
index 21eab56..2249ecd 100644
--- a/fs/netfs/locking.c
+++ b/fs/netfs/locking.c
@@ -109,6 +109,7 @@ int netfs_start_io_write(struct inode *inode)
up_write(&inode->i_rwsem);
return -ERESTARTSYS;
}
+ downgrade_write(&inode->i_rwsem);
return 0;
}
EXPORT_SYMBOL(netfs_start_io_write);
@@ -123,7 +124,7 @@ EXPORT_SYMBOL(netfs_start_io_write);
void netfs_end_io_write(struct inode *inode)
__releases(inode->i_rwsem)
{
- up_write(&inode->i_rwsem);
+ up_read(&inode->i_rwsem);
}
EXPORT_SYMBOL(netfs_end_io_write);
diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c
index b18c65b..3cbb289 100644
--- a/fs/netfs/read_collect.c
+++ b/fs/netfs/read_collect.c
@@ -77,6 +77,8 @@ static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq,
folio_unlock(folio);
}
}
+
+ folioq_clear(folioq, slot);
}
/*
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 56b2616..551d295 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1359,21 +1359,47 @@ static void destroy_delegation(struct nfs4_delegation *dp)
destroy_unhashed_deleg(dp);
}
+/**
+ * revoke_delegation - perform nfs4 delegation structure cleanup
+ * @dp: pointer to the delegation
+ *
+ * This function assumes that it's called either from the administrative
+ * interface (nfsd4_revoke_states()) that's revoking a specific delegation
+ * stateid or it's called from a laundromat thread (nfsd4_landromat()) that
+ * determined that this specific state has expired and needs to be revoked
+ * (both mark state with the appropriate stid sc_status mode). It is also
+ * assumed that a reference was taken on the @dp state.
+ *
+ * If this function finds that the @dp state is SC_STATUS_FREED it means
+ * that a FREE_STATEID operation for this stateid has been processed and
+ * we can proceed to removing it from recalled list. However, if @dp state
+ * isn't marked SC_STATUS_FREED, it means we need place it on the cl_revoked
+ * list and wait for the FREE_STATEID to arrive from the client. At the same
+ * time, we need to mark it as SC_STATUS_FREEABLE to indicate to the
+ * nfsd4_free_stateid() function that this stateid has already been added
+ * to the cl_revoked list and that nfsd4_free_stateid() is now responsible
+ * for removing it from the list. Inspection of where the delegation state
+ * in the revocation process is protected by the clp->cl_lock.
+ */
static void revoke_delegation(struct nfs4_delegation *dp)
{
struct nfs4_client *clp = dp->dl_stid.sc_client;
WARN_ON(!list_empty(&dp->dl_recall_lru));
+ WARN_ON_ONCE(!(dp->dl_stid.sc_status &
+ (SC_STATUS_REVOKED | SC_STATUS_ADMIN_REVOKED)));
trace_nfsd_stid_revoke(&dp->dl_stid);
- if (dp->dl_stid.sc_status &
- (SC_STATUS_REVOKED | SC_STATUS_ADMIN_REVOKED)) {
- spin_lock(&clp->cl_lock);
- refcount_inc(&dp->dl_stid.sc_count);
- list_add(&dp->dl_recall_lru, &clp->cl_revoked);
- spin_unlock(&clp->cl_lock);
+ spin_lock(&clp->cl_lock);
+ if (dp->dl_stid.sc_status & SC_STATUS_FREED) {
+ list_del_init(&dp->dl_recall_lru);
+ goto out;
}
+ list_add(&dp->dl_recall_lru, &clp->cl_revoked);
+ dp->dl_stid.sc_status |= SC_STATUS_FREEABLE;
+out:
+ spin_unlock(&clp->cl_lock);
destroy_unhashed_deleg(dp);
}
@@ -1780,6 +1806,7 @@ void nfsd4_revoke_states(struct net *net, struct super_block *sb)
mutex_unlock(&stp->st_mutex);
break;
case SC_TYPE_DELEG:
+ refcount_inc(&stid->sc_count);
dp = delegstateid(stid);
spin_lock(&state_lock);
if (!unhash_delegation_locked(
@@ -6545,6 +6572,7 @@ nfs4_laundromat(struct nfsd_net *nn)
dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
if (!state_expired(<, dp->dl_time))
break;
+ refcount_inc(&dp->dl_stid.sc_count);
unhash_delegation_locked(dp, SC_STATUS_REVOKED);
list_add(&dp->dl_recall_lru, &reaplist);
}
@@ -7157,7 +7185,9 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
s->sc_status |= SC_STATUS_CLOSED;
spin_unlock(&s->sc_lock);
dp = delegstateid(s);
- list_del_init(&dp->dl_recall_lru);
+ if (s->sc_status & SC_STATUS_FREEABLE)
+ list_del_init(&dp->dl_recall_lru);
+ s->sc_status |= SC_STATUS_FREED;
spin_unlock(&cl->cl_lock);
nfs4_put_stid(s);
ret = nfs_ok;
@@ -7487,7 +7517,9 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0)))
return status;
- status = nfsd4_lookup_stateid(cstate, stateid, SC_TYPE_DELEG, 0, &s, nn);
+ status = nfsd4_lookup_stateid(cstate, stateid, SC_TYPE_DELEG,
+ SC_STATUS_REVOKED | SC_STATUS_FREEABLE,
+ &s, nn);
if (status)
goto out;
dp = delegstateid(s);
@@ -8684,7 +8716,7 @@ nfs4_state_shutdown_net(struct net *net)
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
shrinker_free(nn->nfsd_client_shrinker);
- cancel_work(&nn->nfsd_shrinker_work);
+ cancel_work_sync(&nn->nfsd_shrinker_work);
cancel_delayed_work_sync(&nn->laundromat_work);
locks_end_grace(&nn->nfsd4_manager);
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 79c743c..35b3564 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -114,6 +114,8 @@ struct nfs4_stid {
/* For a deleg stateid kept around only to process free_stateid's: */
#define SC_STATUS_REVOKED BIT(1)
#define SC_STATUS_ADMIN_REVOKED BIT(2)
+#define SC_STATUS_FREEABLE BIT(3)
+#define SC_STATUS_FREED BIT(4)
unsigned short sc_status;
struct list_head sc_cp_list;
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 9c0b7cd..10def4b 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -77,7 +77,8 @@ void nilfs_forget_buffer(struct buffer_head *bh)
const unsigned long clear_bits =
(BIT(BH_Uptodate) | BIT(BH_Dirty) | BIT(BH_Mapped) |
BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) |
- BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected));
+ BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected) |
+ BIT(BH_Delay));
lock_buffer(bh);
set_mask_bits(&bh->b_state, clear_bits, 0);
@@ -400,13 +401,15 @@ void nilfs_clear_folio_dirty(struct folio *folio)
folio_clear_uptodate(folio);
folio_clear_mappedtodisk(folio);
+ folio_clear_checked(folio);
head = folio_buffers(folio);
if (head) {
const unsigned long clear_bits =
(BIT(BH_Uptodate) | BIT(BH_Dirty) | BIT(BH_Mapped) |
BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) |
- BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected));
+ BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected) |
+ BIT(BH_Delay));
bh = head;
do {
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index ad131a2..06af219 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1129,9 +1129,12 @@ int ocfs2_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
trace_ocfs2_setattr(inode, dentry,
(unsigned long long)OCFS2_I(inode)->ip_blkno,
dentry->d_name.len, dentry->d_name.name,
- attr->ia_valid, attr->ia_mode,
- from_kuid(&init_user_ns, attr->ia_uid),
- from_kgid(&init_user_ns, attr->ia_gid));
+ attr->ia_valid,
+ attr->ia_valid & ATTR_MODE ? attr->ia_mode : 0,
+ attr->ia_valid & ATTR_UID ?
+ from_kuid(&init_user_ns, attr->ia_uid) : 0,
+ attr->ia_valid & ATTR_GID ?
+ from_kgid(&init_user_ns, attr->ia_gid) : 0);
/* ensuring we don't even attempt to truncate a symlink */
if (S_ISLNK(inode->i_mode))
@@ -1784,6 +1787,14 @@ int ocfs2_remove_inode_range(struct inode *inode,
return 0;
if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+ int id_count = ocfs2_max_inline_data_with_xattr(inode->i_sb, di);
+
+ if (byte_start > id_count || byte_start + byte_len > id_count) {
+ ret = -EINVAL;
+ mlog_errno(ret);
+ goto out;
+ }
+
ret = ocfs2_truncate_inline(inode, di_bh, byte_start,
byte_start + byte_len, 0);
if (ret) {
diff --git a/fs/open.c b/fs/open.c
index acaeb3e..5da4df2 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1457,6 +1457,8 @@ SYSCALL_DEFINE4(openat2, int, dfd, const char __user *, filename,
if (unlikely(usize < OPEN_HOW_SIZE_VER0))
return -EINVAL;
+ if (unlikely(usize > PAGE_SIZE))
+ return -E2BIG;
err = copy_struct_from_user(&tmp, sizeof(tmp), how, usize);
if (err)
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 4504493..4444c78 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -231,6 +231,11 @@ static void ovl_file_modified(struct file *file)
ovl_copyattr(file_inode(file));
}
+static void ovl_file_end_write(struct file *file, loff_t pos, ssize_t ret)
+{
+ ovl_file_modified(file);
+}
+
static void ovl_file_accessed(struct file *file)
{
struct inode *inode, *upperinode;
@@ -294,7 +299,7 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
struct backing_file_ctx ctx = {
.cred = ovl_creds(inode->i_sb),
.user_file = file,
- .end_write = ovl_file_modified,
+ .end_write = ovl_file_end_write,
};
if (!iov_iter_count(iter))
@@ -364,7 +369,7 @@ static ssize_t ovl_splice_write(struct pipe_inode_info *pipe, struct file *out,
struct backing_file_ctx ctx = {
.cred = ovl_creds(inode->i_sb),
.user_file = out,
- .end_write = ovl_file_modified,
+ .end_write = ovl_file_end_write,
};
inode_lock(inode);
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 1f54a54..5e391cb 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -77,7 +77,7 @@ static int seq_fdinfo_open(struct inode *inode, struct file *file)
return single_open(file, seq_show, inode);
}
-/**
+/*
* Shared /proc/pid/fdinfo and /proc/pid/fdinfo/fd permission helper to ensure
* that the current task has PTRACE_MODE_READ in addition to the normal
* POSIX-like checks.
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 000e1ef..20cafdf 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -1780,7 +1780,7 @@ static int cifs_init_netfs(void)
nomem_subreqpool:
kmem_cache_destroy(cifs_io_subrequest_cachep);
nomem_subreq:
- mempool_destroy(&cifs_io_request_pool);
+ mempool_exit(&cifs_io_request_pool);
nomem_reqpool:
kmem_cache_destroy(cifs_io_request_cachep);
nomem_req:
diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index 28c4e57..5c5a520 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -920,8 +920,15 @@ static int smb3_reconfigure(struct fs_context *fc)
else {
kfree_sensitive(ses->password);
ses->password = kstrdup(ctx->password, GFP_KERNEL);
+ if (!ses->password)
+ return -ENOMEM;
kfree_sensitive(ses->password2);
ses->password2 = kstrdup(ctx->password2, GFP_KERNEL);
+ if (!ses->password2) {
+ kfree_sensitive(ses->password);
+ ses->password = NULL;
+ return -ENOMEM;
+ }
}
STEAL_STRING(cifs_sb, ctx, domainname);
STEAL_STRING(cifs_sb, ctx, nodename);
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 68cdd89..7c0bd0b 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -692,6 +692,34 @@ void dup_userfaultfd_complete(struct list_head *fcs)
}
}
+void dup_userfaultfd_fail(struct list_head *fcs)
+{
+ struct userfaultfd_fork_ctx *fctx, *n;
+
+ /*
+ * An error has occurred on fork, we will tear memory down, but have
+ * allocated memory for fctx's and raised reference counts for both the
+ * original and child contexts (and on the mm for each as a result).
+ *
+ * These would ordinarily be taken care of by a user handling the event,
+ * but we are no longer doing so, so manually clean up here.
+ *
+ * mm tear down will take care of cleaning up VMA contexts.
+ */
+ list_for_each_entry_safe(fctx, n, fcs, list) {
+ struct userfaultfd_ctx *octx = fctx->orig;
+ struct userfaultfd_ctx *ctx = fctx->new;
+
+ atomic_dec(&octx->mmap_changing);
+ VM_BUG_ON(atomic_read(&octx->mmap_changing) < 0);
+ userfaultfd_ctx_put(octx);
+ userfaultfd_ctx_put(ctx);
+
+ list_del(&fctx->list);
+ kfree(fctx);
+ }
+}
+
void mremap_userfaultfd_prep(struct vm_area_struct *vma,
struct vm_userfaultfd_ctx *vm_ctx)
{
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 5f04947..5ca8d01 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -185,17 +185,20 @@ xfs_initialize_perag_data(
}
/*
- * Free up the per-ag resources associated with the mount structure.
+ * Free up the per-ag resources within the specified AG range.
*/
void
-xfs_free_perag(
- struct xfs_mount *mp)
+xfs_free_perag_range(
+ struct xfs_mount *mp,
+ xfs_agnumber_t first_agno,
+ xfs_agnumber_t end_agno)
+
{
- struct xfs_perag *pag;
xfs_agnumber_t agno;
- for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
- pag = xa_erase(&mp->m_perags, agno);
+ for (agno = first_agno; agno < end_agno; agno++) {
+ struct xfs_perag *pag = xa_erase(&mp->m_perags, agno);
+
ASSERT(pag);
XFS_IS_CORRUPT(pag->pag_mount, atomic_read(&pag->pag_ref) != 0);
xfs_defer_drain_free(&pag->pag_intents_drain);
@@ -270,54 +273,37 @@ xfs_agino_range(
return __xfs_agino_range(mp, xfs_ag_block_count(mp, agno), first, last);
}
-/*
- * Free perag within the specified AG range, it is only used to free unused
- * perags under the error handling path.
- */
-void
-xfs_free_unused_perag_range(
+int
+xfs_update_last_ag_size(
struct xfs_mount *mp,
- xfs_agnumber_t agstart,
- xfs_agnumber_t agend)
+ xfs_agnumber_t prev_agcount)
{
- struct xfs_perag *pag;
- xfs_agnumber_t index;
+ struct xfs_perag *pag = xfs_perag_grab(mp, prev_agcount - 1);
- for (index = agstart; index < agend; index++) {
- pag = xa_erase(&mp->m_perags, index);
- if (!pag)
- break;
- xfs_buf_cache_destroy(&pag->pag_bcache);
- xfs_defer_drain_free(&pag->pag_intents_drain);
- kfree(pag);
- }
+ if (!pag)
+ return -EFSCORRUPTED;
+ pag->block_count = __xfs_ag_block_count(mp, prev_agcount - 1,
+ mp->m_sb.sb_agcount, mp->m_sb.sb_dblocks);
+ __xfs_agino_range(mp, pag->block_count, &pag->agino_min,
+ &pag->agino_max);
+ xfs_perag_rele(pag);
+ return 0;
}
int
xfs_initialize_perag(
struct xfs_mount *mp,
- xfs_agnumber_t agcount,
+ xfs_agnumber_t old_agcount,
+ xfs_agnumber_t new_agcount,
xfs_rfsblock_t dblocks,
xfs_agnumber_t *maxagi)
{
struct xfs_perag *pag;
xfs_agnumber_t index;
- xfs_agnumber_t first_initialised = NULLAGNUMBER;
int error;
- /*
- * Walk the current per-ag tree so we don't try to initialise AGs
- * that already exist (growfs case). Allocate and insert all the
- * AGs we don't find ready for initialisation.
- */
- for (index = 0; index < agcount; index++) {
- pag = xfs_perag_get(mp, index);
- if (pag) {
- xfs_perag_put(pag);
- continue;
- }
-
- pag = kzalloc(sizeof(*pag), GFP_KERNEL | __GFP_RETRY_MAYFAIL);
+ for (index = old_agcount; index < new_agcount; index++) {
+ pag = kzalloc(sizeof(*pag), GFP_KERNEL);
if (!pag) {
error = -ENOMEM;
goto out_unwind_new_pags;
@@ -353,21 +339,17 @@ xfs_initialize_perag(
/* Active ref owned by mount indicates AG is online. */
atomic_set(&pag->pag_active_ref, 1);
- /* first new pag is fully initialized */
- if (first_initialised == NULLAGNUMBER)
- first_initialised = index;
-
/*
* Pre-calculated geometry
*/
- pag->block_count = __xfs_ag_block_count(mp, index, agcount,
+ pag->block_count = __xfs_ag_block_count(mp, index, new_agcount,
dblocks);
pag->min_block = XFS_AGFL_BLOCK(mp);
__xfs_agino_range(mp, pag->block_count, &pag->agino_min,
&pag->agino_max);
}
- index = xfs_set_inode_alloc(mp, agcount);
+ index = xfs_set_inode_alloc(mp, new_agcount);
if (maxagi)
*maxagi = index;
@@ -381,8 +363,7 @@ xfs_initialize_perag(
out_free_pag:
kfree(pag);
out_unwind_new_pags:
- /* unwind any prior newly initialized pags */
- xfs_free_unused_perag_range(mp, first_initialised, agcount);
+ xfs_free_perag_range(mp, old_agcount, index);
return error;
}
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index d9cccd0..9edfe0e 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -144,12 +144,13 @@ __XFS_AG_OPSTATE(prefers_metadata, PREFERS_METADATA)
__XFS_AG_OPSTATE(allows_inodes, ALLOWS_INODES)
__XFS_AG_OPSTATE(agfl_needs_reset, AGFL_NEEDS_RESET)
-void xfs_free_unused_perag_range(struct xfs_mount *mp, xfs_agnumber_t agstart,
- xfs_agnumber_t agend);
-int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t agcount,
- xfs_rfsblock_t dcount, xfs_agnumber_t *maxagi);
+int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t old_agcount,
+ xfs_agnumber_t agcount, xfs_rfsblock_t dcount,
+ xfs_agnumber_t *maxagi);
+void xfs_free_perag_range(struct xfs_mount *mp, xfs_agnumber_t first_agno,
+ xfs_agnumber_t end_agno);
int xfs_initialize_perag_data(struct xfs_mount *mp, xfs_agnumber_t agno);
-void xfs_free_perag(struct xfs_mount *mp);
+int xfs_update_last_ag_size(struct xfs_mount *mp, xfs_agnumber_t prev_agcount);
/* Passive AG references */
struct xfs_perag *xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno);
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 6747829..155bbaa 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -1084,9 +1084,11 @@ xrep_metadata_inode_forks(
return error;
/* Make sure the attr fork looks ok before we delete it. */
- error = xrep_metadata_inode_subtype(sc, XFS_SCRUB_TYPE_BMBTA);
- if (error)
- return error;
+ if (xfs_inode_hasattr(sc->ip)) {
+ error = xrep_metadata_inode_subtype(sc, XFS_SCRUB_TYPE_BMBTA);
+ if (error)
+ return error;
+ }
/* Clear the reflink flag since metadata never shares. */
if (xfs_is_reflink_inode(sc->ip)) {
diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c
index 09e893c..5180cbf 100644
--- a/fs/xfs/xfs_buf_item_recover.c
+++ b/fs/xfs/xfs_buf_item_recover.c
@@ -22,6 +22,9 @@
#include "xfs_inode.h"
#include "xfs_dir2.h"
#include "xfs_quota.h"
+#include "xfs_alloc.h"
+#include "xfs_ag.h"
+#include "xfs_sb.h"
/*
* This is the number of entries in the l_buf_cancel_table used during
@@ -685,6 +688,67 @@ xlog_recover_do_inode_buffer(
}
/*
+ * Update the in-memory superblock and perag structures from the primary SB
+ * buffer.
+ *
+ * This is required because transactions running after growfs may require the
+ * updated values to be set in a previous fully commit transaction.
+ */
+static int
+xlog_recover_do_primary_sb_buffer(
+ struct xfs_mount *mp,
+ struct xlog_recover_item *item,
+ struct xfs_buf *bp,
+ struct xfs_buf_log_format *buf_f,
+ xfs_lsn_t current_lsn)
+{
+ struct xfs_dsb *dsb = bp->b_addr;
+ xfs_agnumber_t orig_agcount = mp->m_sb.sb_agcount;
+ int error;
+
+ xlog_recover_do_reg_buffer(mp, item, bp, buf_f, current_lsn);
+
+ if (orig_agcount == 0) {
+ xfs_alert(mp, "Trying to grow file system without AGs");
+ return -EFSCORRUPTED;
+ }
+
+ /*
+ * Update the in-core super block from the freshly recovered on-disk one.
+ */
+ xfs_sb_from_disk(&mp->m_sb, dsb);
+
+ if (mp->m_sb.sb_agcount < orig_agcount) {
+ xfs_alert(mp, "Shrinking AG count in log recovery not supported");
+ return -EFSCORRUPTED;
+ }
+
+ /*
+ * Growfs can also grow the last existing AG. In this case we also need
+ * to update the length in the in-core perag structure and values
+ * depending on it.
+ */
+ error = xfs_update_last_ag_size(mp, orig_agcount);
+ if (error)
+ return error;
+
+ /*
+ * Initialize the new perags, and also update various block and inode
+ * allocator setting based off the number of AGs or total blocks.
+ * Because of the latter this also needs to happen if the agcount did
+ * not change.
+ */
+ error = xfs_initialize_perag(mp, orig_agcount, mp->m_sb.sb_agcount,
+ mp->m_sb.sb_dblocks, &mp->m_maxagi);
+ if (error) {
+ xfs_warn(mp, "Failed recovery per-ag init: %d", error);
+ return error;
+ }
+ mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);
+ return 0;
+}
+
+/*
* V5 filesystems know the age of the buffer on disk being recovered. We can
* have newer objects on disk than we are replaying, and so for these cases we
* don't want to replay the current change as that will make the buffer contents
@@ -967,6 +1031,12 @@ xlog_recover_buf_commit_pass2(
dirty = xlog_recover_do_dquot_buffer(mp, log, item, bp, buf_f);
if (!dirty)
goto out_release;
+ } else if ((xfs_blft_from_flags(buf_f) & XFS_BLFT_SB_BUF) &&
+ xfs_buf_daddr(bp) == 0) {
+ error = xlog_recover_do_primary_sb_buffer(mp, item, bp, buf_f,
+ current_lsn);
+ if (error)
+ goto out_release;
} else {
xlog_recover_do_reg_buffer(mp, item, bp, buf_f, current_lsn);
}
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 3643cc8..b247d89 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -87,6 +87,7 @@ xfs_growfs_data_private(
struct xfs_mount *mp, /* mount point for filesystem */
struct xfs_growfs_data *in) /* growfs data input struct */
{
+ xfs_agnumber_t oagcount = mp->m_sb.sb_agcount;
struct xfs_buf *bp;
int error;
xfs_agnumber_t nagcount;
@@ -94,7 +95,6 @@ xfs_growfs_data_private(
xfs_rfsblock_t nb, nb_div, nb_mod;
int64_t delta;
bool lastag_extended = false;
- xfs_agnumber_t oagcount;
struct xfs_trans *tp;
struct aghdr_init_data id = {};
struct xfs_perag *last_pag;
@@ -138,16 +138,14 @@ xfs_growfs_data_private(
if (delta == 0)
return 0;
- oagcount = mp->m_sb.sb_agcount;
- /* allocate the new per-ag structures */
- if (nagcount > oagcount) {
- error = xfs_initialize_perag(mp, nagcount, nb, &nagimax);
- if (error)
- return error;
- } else if (nagcount < oagcount) {
- /* TODO: shrinking the entire AGs hasn't yet completed */
+ /* TODO: shrinking the entire AGs hasn't yet completed */
+ if (nagcount < oagcount)
return -EINVAL;
- }
+
+ /* allocate the new per-ag structures */
+ error = xfs_initialize_perag(mp, oagcount, nagcount, nb, &nagimax);
+ if (error)
+ return error;
if (delta > 0)
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata,
@@ -231,7 +229,7 @@ xfs_growfs_data_private(
xfs_trans_cancel(tp);
out_free_unused_perag:
if (nagcount > oagcount)
- xfs_free_unused_perag_range(mp, oagcount, nagcount);
+ xfs_free_perag_range(mp, oagcount, nagcount);
return error;
}
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index a13bf53..704aaad 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -3393,13 +3393,6 @@ xlog_do_recover(
/* re-initialise in-core superblock and geometry structures */
mp->m_features |= xfs_sb_version_to_features(sbp);
xfs_reinit_percpu_counters(mp);
- error = xfs_initialize_perag(mp, sbp->sb_agcount, sbp->sb_dblocks,
- &mp->m_maxagi);
- if (error) {
- xfs_warn(mp, "Failed post-recovery per-ag init: %d", error);
- return error;
- }
- mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);
/* Normal transactions can now occur */
clear_bit(XLOG_ACTIVE_RECOVERY, &log->l_opstate);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 1fdd79c..25bbcc3 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -810,8 +810,8 @@ xfs_mountfs(
/*
* Allocate and initialize the per-ag data.
*/
- error = xfs_initialize_perag(mp, sbp->sb_agcount, mp->m_sb.sb_dblocks,
- &mp->m_maxagi);
+ error = xfs_initialize_perag(mp, 0, sbp->sb_agcount,
+ mp->m_sb.sb_dblocks, &mp->m_maxagi);
if (error) {
xfs_warn(mp, "Failed per-ag init: %d", error);
goto out_free_dir;
@@ -1048,7 +1048,7 @@ xfs_mountfs(
xfs_buftarg_drain(mp->m_logdev_targp);
xfs_buftarg_drain(mp->m_ddev_targp);
out_free_perag:
- xfs_free_perag(mp);
+ xfs_free_perag_range(mp, 0, mp->m_sb.sb_agcount);
out_free_dir:
xfs_da_unmount(mp);
out_remove_uuid:
@@ -1129,8 +1129,7 @@ xfs_unmountfs(
xfs_errortag_clearall(mp);
#endif
shrinker_free(mp->m_inodegc_shrinker);
- xfs_free_perag(mp);
-
+ xfs_free_perag_range(mp, 0, mp->m_sb.sb_agcount);
xfs_errortag_del(mp);
xfs_error_sysfs_del(mp);
xchk_stats_unregister(mp->m_scrub_stats);
diff --git a/include/linux/backing-file.h b/include/linux/backing-file.h
index 4b61b0e..2eed0ff 100644
--- a/include/linux/backing-file.h
+++ b/include/linux/backing-file.h
@@ -16,7 +16,7 @@ struct backing_file_ctx {
const struct cred *cred;
struct file *user_file;
void (*accessed)(struct file *);
- void (*end_write)(struct file *);
+ void (*end_write)(struct file *, loff_t, ssize_t);
};
struct file *backing_file_open(const struct path *user_path, int flags,
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 19d8ca8..bdadb0b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -635,6 +635,7 @@ enum bpf_type_flag {
*/
PTR_UNTRUSTED = BIT(6 + BPF_BASE_TYPE_BITS),
+ /* MEM can be uninitialized. */
MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS),
/* DYNPTR points to memory local to the bpf program. */
@@ -700,6 +701,13 @@ enum bpf_type_flag {
*/
MEM_ALIGNED = BIT(17 + BPF_BASE_TYPE_BITS),
+ /* MEM is being written to, often combined with MEM_UNINIT. Non-presence
+ * of MEM_WRITE means that MEM is only being read. MEM_WRITE without the
+ * MEM_UNINIT means that memory needs to be initialized since it is also
+ * read.
+ */
+ MEM_WRITE = BIT(18 + BPF_BASE_TYPE_BITS),
+
__BPF_TYPE_FLAG_MAX,
__BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1,
};
@@ -758,10 +766,10 @@ enum bpf_arg_type {
ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET,
ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK,
ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID,
- /* pointer to memory does not need to be initialized, helper function must fill
- * all bytes or clear them in error case.
+ /* Pointer to memory does not need to be initialized, since helper function
+ * fills all bytes or clears them in error case.
*/
- ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | ARG_PTR_TO_MEM,
+ ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | MEM_WRITE | ARG_PTR_TO_MEM,
/* Pointer to valid memory of size known at compile time. */
ARG_PTR_TO_FIXED_SIZE_MEM = MEM_FIXED_SIZE | ARG_PTR_TO_MEM,
diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h
index aaf004d..e45162e 100644
--- a/include/linux/bpf_mem_alloc.h
+++ b/include/linux/bpf_mem_alloc.h
@@ -33,6 +33,9 @@ int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg
int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size);
void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma);
+/* Check the allocation size for kmalloc equivalent allocator */
+int bpf_mem_alloc_check_size(bool percpu, size_t size);
+
/* kmalloc/kfree equivalent: */
void *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size);
void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr);
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 9f2a6b8..fa78f49 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -146,6 +146,7 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp)
BPF_LINK_TYPE(BPF_LINK_TYPE_NETFILTER, netfilter)
BPF_LINK_TYPE(BPF_LINK_TYPE_TCX, tcx)
BPF_LINK_TYPE(BPF_LINK_TYPE_NETKIT, netkit)
+BPF_LINK_TYPE(BPF_LINK_TYPE_SOCKMAP, sockmap)
#endif
#ifdef CONFIG_PERF_EVENTS
BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf)
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 11690da..ec9c050 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -54,12 +54,11 @@ static inline long mm_ksm_zero_pages(struct mm_struct *mm)
return atomic_long_read(&mm->ksm_zero_pages);
}
-static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
{
+ /* Adding mm to ksm is best effort on fork. */
if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags))
- return __ksm_enter(mm);
-
- return 0;
+ __ksm_enter(mm);
}
static inline int ksm_execve(struct mm_struct *mm)
@@ -107,9 +106,8 @@ static inline int ksm_disable(struct mm_struct *mm)
return 0;
}
-static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
{
- return 0;
}
static inline int ksm_execve(struct mm_struct *mm)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index db567d2..45be36e 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1313,8 +1313,6 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn);
-kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn);
-kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map);
void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty);
unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ecf63d2..61fff5d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3818,8 +3818,9 @@ void *sparse_buffer_alloc(unsigned long size);
struct page * __populate_section_memmap(unsigned long pfn,
unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
struct dev_pagemap *pgmap);
-void pmd_init(void *addr);
void pud_init(void *addr);
+void pmd_init(void *addr);
+void kernel_pte_init(void *addr);
pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node);
pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4d20c77..8896705 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3325,6 +3325,12 @@ static inline void netif_tx_wake_all_queues(struct net_device *dev)
static __always_inline void netif_tx_stop_queue(struct netdev_queue *dev_queue)
{
+ /* Paired with READ_ONCE() from dev_watchdog() */
+ WRITE_ONCE(dev_queue->trans_start, jiffies);
+
+ /* This barrier is paired with smp_mb() from dev_watchdog() */
+ smp_mb__before_atomic();
+
/* Must be an atomic op see netif_txq_try_stop() */
set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
}
@@ -3451,6 +3457,12 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
if (likely(dql_avail(&dev_queue->dql) >= 0))
return;
+ /* Paired with READ_ONCE() from dev_watchdog() */
+ WRITE_ONCE(dev_queue->trans_start, jiffies);
+
+ /* This barrier is paired with smp_mb() from dev_watchdog() */
+ smp_mb__before_atomic();
+
set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state);
/*
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 39c7cf8..43844510 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -38,6 +38,7 @@
#else
#define can_do_masked_user_access() 0
#define masked_user_access_begin(src) NULL
+ #define mask_user_address(src) (src)
#endif
/*
@@ -159,19 +160,27 @@ _inline_copy_from_user(void *to, const void __user *from, unsigned long n)
{
unsigned long res = n;
might_fault();
- if (!should_fail_usercopy() && likely(access_ok(from, n))) {
+ if (should_fail_usercopy())
+ goto fail;
+ if (can_do_masked_user_access())
+ from = mask_user_address(from);
+ else {
+ if (!access_ok(from, n))
+ goto fail;
/*
* Ensure that bad access_ok() speculation will not
* lead to nasty side effects *after* the copy is
* finished:
*/
barrier_nospec();
- instrument_copy_from_user_before(to, from, n);
- res = raw_copy_from_user(to, from, n);
- instrument_copy_from_user_after(to, from, n, res);
}
- if (unlikely(res))
- memset(to + (n - res), 0, res);
+ instrument_copy_from_user_before(to, from, n);
+ res = raw_copy_from_user(to, from, n);
+ instrument_copy_from_user_after(to, from, n, res);
+ if (likely(!res))
+ return 0;
+fail:
+ memset(to + (n - res), 0, res);
return res;
}
extern __must_check unsigned long
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 9fc6ce1..cb40f1a 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -249,6 +249,7 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *);
extern void dup_userfaultfd_complete(struct list_head *);
+void dup_userfaultfd_fail(struct list_head *);
extern void mremap_userfaultfd_prep(struct vm_area_struct *,
struct vm_userfaultfd_ctx *);
@@ -351,6 +352,10 @@ static inline void dup_userfaultfd_complete(struct list_head *l)
{
}
+static inline void dup_userfaultfd_fail(struct list_head *l)
+{
+}
+
static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma,
struct vm_userfaultfd_ctx *ctx)
{
diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 5d655e1..f66bc85 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -403,6 +403,7 @@ int bt_sock_register(int proto, const struct net_proto_family *ops);
void bt_sock_unregister(int proto);
void bt_sock_link(struct bt_sock_list *l, struct sock *s);
void bt_sock_unlink(struct bt_sock_list *l, struct sock *s);
+bool bt_sock_linked(struct bt_sock_list *l, struct sock *s);
struct sock *bt_sock_alloc(struct net *net, struct socket *sock,
struct proto *prot, int proto, gfp_t prio, int kern);
int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 69ec1eb..941dc62 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -6130,6 +6130,50 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy,
struct wiphy_delayed_work *dwork);
/**
+ * wiphy_delayed_work_pending - Find out whether a wiphy delayable
+ * work item is currently pending.
+ *
+ * @wiphy: the wiphy, for debug purposes
+ * @dwork: the delayed work in question
+ *
+ * Return: true if timer is pending, false otherwise
+ *
+ * How wiphy_delayed_work_queue() works is by setting a timer which
+ * when it expires calls wiphy_work_queue() to queue the wiphy work.
+ * Because wiphy_delayed_work_queue() uses mod_timer(), if it is
+ * called twice and the second call happens before the first call
+ * deadline, the work will rescheduled for the second deadline and
+ * won't run before that.
+ *
+ * wiphy_delayed_work_pending() can be used to detect if calling
+ * wiphy_work_delayed_work_queue() would start a new work schedule
+ * or delayed a previous one. As seen below it cannot be used to
+ * detect precisely if the work has finished to execute nor if it
+ * is currently executing.
+ *
+ * CPU0 CPU1
+ * wiphy_delayed_work_queue(wk)
+ * mod_timer(wk->timer)
+ * wiphy_delayed_work_pending(wk) -> true
+ *
+ * [...]
+ * expire_timers(wk->timer)
+ * detach_timer(wk->timer)
+ * wiphy_delayed_work_pending(wk) -> false
+ * wk->timer->function() |
+ * wiphy_work_queue(wk) | delayed work pending
+ * list_add_tail() | returns false but
+ * queue_work(cfg80211_wiphy_work) | wk->func() has not
+ * | been run yet
+ * [...] |
+ * cfg80211_wiphy_work() |
+ * wk->func() V
+ *
+ */
+bool wiphy_delayed_work_pending(struct wiphy *wiphy,
+ struct wiphy_delayed_work *dwork);
+
+/**
* enum ieee80211_ap_reg_power - regulatory power for an Access Point
*
* @IEEE80211_REG_UNSET_AP: Access Point has no regulatory power mode
diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h
index 02fbc03..813e163 100644
--- a/include/net/ieee80211_radiotap.h
+++ b/include/net/ieee80211_radiotap.h
@@ -24,25 +24,27 @@
* struct ieee80211_radiotap_header - base radiotap header
*/
struct ieee80211_radiotap_header {
- /**
- * @it_version: radiotap version, always 0
- */
- uint8_t it_version;
+ __struct_group(ieee80211_radiotap_header_fixed, hdr, __packed,
+ /**
+ * @it_version: radiotap version, always 0
+ */
+ uint8_t it_version;
- /**
- * @it_pad: padding (or alignment)
- */
- uint8_t it_pad;
+ /**
+ * @it_pad: padding (or alignment)
+ */
+ uint8_t it_pad;
- /**
- * @it_len: overall radiotap header length
- */
- __le16 it_len;
+ /**
+ * @it_len: overall radiotap header length
+ */
+ __le16 it_len;
- /**
- * @it_present: (first) present word
- */
- __le32 it_present;
+ /**
+ * @it_present: (first) present word
+ */
+ __le32 it_present;
+ );
/**
* @it_optional: all remaining presence bitmaps
@@ -50,6 +52,9 @@ struct ieee80211_radiotap_header {
__le32 it_optional[];
} __packed;
+static_assert(offsetof(struct ieee80211_radiotap_header, it_optional) == sizeof(struct ieee80211_radiotap_header_fixed),
+ "struct member likely outside of __struct_group()");
+
/* version is always 0 */
#define PKTHDR_RADIOTAP_VERSION 0
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 6194fbb..6a07047 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -354,7 +354,7 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4,
memset(fl4, 0, sizeof(*fl4));
if (oif) {
- fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index_rcu(net, oif);
+ fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index(net, oif);
/* Legacy VRF/l3mdev use case */
fl4->flowi4_oif = fl4->flowi4_l3mdev ? 0 : oif;
}
diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index d489d92..ae60d66 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -51,7 +51,6 @@ struct netns_xfrm {
struct hlist_head *policy_byidx;
unsigned int policy_idx_hmask;
unsigned int idx_generator;
- struct hlist_head policy_inexact[XFRM_POLICY_MAX];
struct xfrm_policy_hash policy_bydst[XFRM_POLICY_MAX];
unsigned int policy_count[XFRM_POLICY_MAX * 2];
struct work_struct policy_hash_work;
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index b6bfdc6..a0bdd58 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -349,20 +349,25 @@ struct xfrm_if_cb {
void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb);
void xfrm_if_unregister_cb(void);
+struct xfrm_dst_lookup_params {
+ struct net *net;
+ int tos;
+ int oif;
+ xfrm_address_t *saddr;
+ xfrm_address_t *daddr;
+ u32 mark;
+ __u8 ipproto;
+ union flowi_uli uli;
+};
+
struct net_device;
struct xfrm_type;
struct xfrm_dst;
struct xfrm_policy_afinfo {
struct dst_ops *dst_ops;
- struct dst_entry *(*dst_lookup)(struct net *net,
- int tos, int oif,
- const xfrm_address_t *saddr,
- const xfrm_address_t *daddr,
- u32 mark);
- int (*get_saddr)(struct net *net, int oif,
- xfrm_address_t *saddr,
- xfrm_address_t *daddr,
- u32 mark);
+ struct dst_entry *(*dst_lookup)(const struct xfrm_dst_lookup_params *params);
+ int (*get_saddr)(xfrm_address_t *saddr,
+ const struct xfrm_dst_lookup_params *params);
int (*fill_dst)(struct xfrm_dst *xdst,
struct net_device *dev,
const struct flowi *fl);
@@ -1764,10 +1769,7 @@ static inline int xfrm_user_policy(struct sock *sk, int optname,
}
#endif
-struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif,
- const xfrm_address_t *saddr,
- const xfrm_address_t *daddr,
- int family, u32 mark);
+struct dst_entry *__xfrm_dst_lookup(int family, const struct xfrm_dst_lookup_params *params);
struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp);
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 1d7c5282..69975c9 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -172,7 +172,6 @@
EM(netfs_folio_trace_read, "read") \
EM(netfs_folio_trace_read_done, "read-done") \
EM(netfs_folio_trace_read_gaps, "read-gaps") \
- EM(netfs_folio_trace_read_put, "read-put") \
EM(netfs_folio_trace_read_unlock, "read-unlock") \
EM(netfs_folio_trace_redirtied, "redirtied") \
EM(netfs_folio_trace_store, "store") \
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e8241b3..4a939c9 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1121,6 +1121,9 @@ enum bpf_attach_type {
#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
+/* Add BPF_LINK_TYPE(type, name) in bpf_types.h to keep bpf_link_type_strs[]
+ * in sync with the definitions below.
+ */
enum bpf_link_type {
BPF_LINK_TYPE_UNSPEC = 0,
BPF_LINK_TYPE_RAW_TRACEPOINT = 1,
diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h
index 99333cb..c117672 100644
--- a/include/uapi/sound/asoc.h
+++ b/include/uapi/sound/asoc.h
@@ -88,7 +88,7 @@
/* ABI version */
#define SND_SOC_TPLG_ABI_VERSION 0x5 /* current version */
-#define SND_SOC_TPLG_ABI_VERSION_MIN 0x4 /* oldest version supported */
+#define SND_SOC_TPLG_ABI_VERSION_MIN 0x5 /* oldest version supported */
/* Max size of TLV data */
#define SND_SOC_TPLG_TLV_SIZE 32
diff --git a/include/video/da8xx-fb.h b/include/video/da8xx-fb.h
deleted file mode 100644
index 1d19ae6..0000000
--- a/include/video/da8xx-fb.h
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * Header file for TI DA8XX LCD controller platform data.
- *
- * Copyright (C) 2008-2009 MontaVista Software Inc.
- * Copyright (C) 2008-2009 Texas Instruments Inc
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
-
-#ifndef DA8XX_FB_H
-#define DA8XX_FB_H
-
-enum panel_shade {
- MONOCHROME = 0,
- COLOR_ACTIVE,
- COLOR_PASSIVE,
-};
-
-enum raster_load_mode {
- LOAD_DATA = 1,
- LOAD_PALETTE,
-};
-
-enum da8xx_frame_complete {
- DA8XX_FRAME_WAIT,
- DA8XX_FRAME_NOWAIT,
-};
-
-struct da8xx_lcdc_platform_data {
- const char manu_name[10];
- void *controller_data;
- const char type[25];
-};
-
-struct lcd_ctrl_config {
- enum panel_shade panel_shade;
-
- /* AC Bias Pin Frequency */
- int ac_bias;
-
- /* AC Bias Pin Transitions per Interrupt */
- int ac_bias_intrpt;
-
- /* DMA burst size */
- int dma_burst_sz;
-
- /* Bits per pixel */
- int bpp;
-
- /* FIFO DMA Request Delay */
- int fdd;
-
- /* TFT Alternative Signal Mapping (Only for active) */
- unsigned char tft_alt_mode;
-
- /* 12 Bit Per Pixel (5-6-5) Mode (Only for passive) */
- unsigned char stn_565_mode;
-
- /* Mono 8-bit Mode: 1=D0-D7 or 0=D0-D3 */
- unsigned char mono_8bit_mode;
-
- /* Horizontal and Vertical Sync Edge: 0=rising 1=falling */
- unsigned char sync_edge;
-
- /* Raster Data Order Select: 1=Most-to-least 0=Least-to-most */
- unsigned char raster_order;
-
- /* DMA FIFO threshold */
- int fifo_th;
-};
-
-struct lcd_sync_arg {
- int back_porch;
- int front_porch;
- int pulse_width;
-};
-
-/* ioctls */
-#define FBIOGET_CONTRAST _IOR('F', 1, int)
-#define FBIOPUT_CONTRAST _IOW('F', 2, int)
-#define FBIGET_BRIGHTNESS _IOR('F', 3, int)
-#define FBIPUT_BRIGHTNESS _IOW('F', 3, int)
-#define FBIGET_COLOR _IOR('F', 5, int)
-#define FBIPUT_COLOR _IOW('F', 6, int)
-#define FBIPUT_HSYNC _IOW('F', 9, int)
-#define FBIPUT_VSYNC _IOW('F', 10, int)
-
-/* Proprietary FB_SYNC_ flags */
-#define FB_SYNC_CLK_INVERT 0x40000000
-
-#endif /* ifndef DA8XX_FB_H */
-
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index e7113d7..025d7e2 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -24,6 +24,23 @@
DEFINE_STATIC_KEY_ARRAY_FALSE(cgroup_bpf_enabled_key, MAX_CGROUP_BPF_ATTACH_TYPE);
EXPORT_SYMBOL(cgroup_bpf_enabled_key);
+/*
+ * cgroup bpf destruction makes heavy use of work items and there can be a lot
+ * of concurrent destructions. Use a separate workqueue so that cgroup bpf
+ * destruction work items don't end up filling up max_active of system_wq
+ * which may lead to deadlock.
+ */
+static struct workqueue_struct *cgroup_bpf_destroy_wq;
+
+static int __init cgroup_bpf_wq_init(void)
+{
+ cgroup_bpf_destroy_wq = alloc_workqueue("cgroup_bpf_destroy", 0, 1);
+ if (!cgroup_bpf_destroy_wq)
+ panic("Failed to alloc workqueue for cgroup bpf destroy.\n");
+ return 0;
+}
+core_initcall(cgroup_bpf_wq_init);
+
/* __always_inline is necessary to prevent indirect call through run_prog
* function pointer.
*/
@@ -334,7 +351,7 @@ static void cgroup_bpf_release_fn(struct percpu_ref *ref)
struct cgroup *cgrp = container_of(ref, struct cgroup, bpf.refcnt);
INIT_WORK(&cgrp->bpf.release_work, cgroup_bpf_release);
- queue_work(system_wq, &cgrp->bpf.release_work);
+ queue_work(cgroup_bpf_destroy_wq, &cgrp->bpf.release_work);
}
/* Get underlying bpf_prog of bpf_prog_list entry, regardless if it's through
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 1a43d06..3d45ebe 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -111,7 +111,7 @@ const struct bpf_func_proto bpf_map_pop_elem_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_CONST_MAP_PTR,
- .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT,
+ .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT | MEM_WRITE,
};
BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value)
@@ -124,7 +124,7 @@ const struct bpf_func_proto bpf_map_peek_elem_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_CONST_MAP_PTR,
- .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT,
+ .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT | MEM_WRITE,
};
BPF_CALL_3(bpf_map_lookup_percpu_elem, struct bpf_map *, map, void *, key, u32, cpu)
@@ -538,7 +538,7 @@ const struct bpf_func_proto bpf_strtol_proto = {
.arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg2_type = ARG_CONST_SIZE,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
+ .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED,
.arg4_size = sizeof(s64),
};
@@ -566,7 +566,7 @@ const struct bpf_func_proto bpf_strtoul_proto = {
.arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg2_type = ARG_CONST_SIZE,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
+ .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED,
.arg4_size = sizeof(u64),
};
@@ -1742,7 +1742,7 @@ static const struct bpf_func_proto bpf_dynptr_from_mem_proto = {
.arg1_type = ARG_PTR_TO_UNINIT_MEM,
.arg2_type = ARG_CONST_SIZE_OR_ZERO,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT,
+ .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT | MEM_WRITE,
};
BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern *, src,
@@ -2851,21 +2851,47 @@ struct bpf_iter_bits {
__u64 __opaque[2];
} __aligned(8);
+#define BITS_ITER_NR_WORDS_MAX 511
+
struct bpf_iter_bits_kern {
union {
- unsigned long *bits;
- unsigned long bits_copy;
+ __u64 *bits;
+ __u64 bits_copy;
};
- u32 nr_bits;
+ int nr_bits;
int bit;
} __aligned(8);
+/* On 64-bit hosts, unsigned long and u64 have the same size, so passing
+ * a u64 pointer and an unsigned long pointer to find_next_bit() will
+ * return the same result, as both point to the same 8-byte area.
+ *
+ * For 32-bit little-endian hosts, using a u64 pointer or unsigned long
+ * pointer also makes no difference. This is because the first iterated
+ * unsigned long is composed of bits 0-31 of the u64 and the second unsigned
+ * long is composed of bits 32-63 of the u64.
+ *
+ * However, for 32-bit big-endian hosts, this is not the case. The first
+ * iterated unsigned long will be bits 32-63 of the u64, so swap these two
+ * ulong values within the u64.
+ */
+static void swap_ulong_in_u64(u64 *bits, unsigned int nr)
+{
+#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN)
+ unsigned int i;
+
+ for (i = 0; i < nr; i++)
+ bits[i] = (bits[i] >> 32) | ((u64)(u32)bits[i] << 32);
+#endif
+}
+
/**
* bpf_iter_bits_new() - Initialize a new bits iterator for a given memory area
* @it: The new bpf_iter_bits to be created
* @unsafe_ptr__ign: A pointer pointing to a memory area to be iterated over
* @nr_words: The size of the specified memory area, measured in 8-byte units.
- * Due to the limitation of memalloc, it can't be greater than 512.
+ * The maximum value of @nr_words is @BITS_ITER_NR_WORDS_MAX. This limit may be
+ * further reduced by the BPF memory allocator implementation.
*
* This function initializes a new bpf_iter_bits structure for iterating over
* a memory area which is specified by the @unsafe_ptr__ign and @nr_words. It
@@ -2892,6 +2918,8 @@ bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_w
if (!unsafe_ptr__ign || !nr_words)
return -EINVAL;
+ if (nr_words > BITS_ITER_NR_WORDS_MAX)
+ return -E2BIG;
/* Optimization for u64 mask */
if (nr_bits == 64) {
@@ -2899,10 +2927,15 @@ bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_w
if (err)
return -EFAULT;
+ swap_ulong_in_u64(&kit->bits_copy, nr_words);
+
kit->nr_bits = nr_bits;
return 0;
}
+ if (bpf_mem_alloc_check_size(false, nr_bytes))
+ return -E2BIG;
+
/* Fallback to memalloc */
kit->bits = bpf_mem_alloc(&bpf_global_ma, nr_bytes);
if (!kit->bits)
@@ -2914,6 +2947,8 @@ bpf_iter_b