Merge tag 'gpio-fixes-for-v6.12-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux
Pull gpio fixes from Bartosz Golaszewski:
- fix an uninitialized variable in GPIO swnode code
- add a missing return value check for devm_mutex_init()
- fix an old issue with debugfs output
* tag 'gpio-fixes-for-v6.12-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux:
gpiolib: fix debugfs dangling chip separator
gpiolib: fix debugfs newline separators
gpio: sloppy-logic-analyzer: Check for error code from devm_mutex_init() call
gpio: fix uninit-value in swnode_find_gpio
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/caching/cachefiles.rst b/Documentation/filesystems/caching/cachefiles.rst
index e04a27b..b3ccc78 100644
--- a/Documentation/filesystems/caching/cachefiles.rst
+++ b/Documentation/filesystems/caching/cachefiles.rst
@@ -115,7 +115,7 @@
This mask can also be set through sysfs, eg::
- echo 5 >/sys/modules/cachefiles/parameters/debug
+ echo 5 > /sys/module/cachefiles/parameters/debug
Starting the Cache
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/rust/arch-support.rst b/Documentation/rust/arch-support.rst
index 750ff37..54be7dd 100644
--- a/Documentation/rust/arch-support.rst
+++ b/Documentation/rust/arch-support.rst
@@ -17,7 +17,7 @@
============= ================ ==============================================
``arm64`` Maintained Little Endian only.
``loongarch`` Maintained \-
-``riscv`` Maintained ``riscv64`` only.
+``riscv`` Maintained ``riscv64`` and LLVM/Clang only.
``um`` Maintained \-
``x86`` Maintained ``x86_64`` only.
============= ================ ==============================================
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/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 5619869..c7d311d 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -19,6 +19,7 @@
#include <linux/ratelimit.h>
#include <linux/rseq.h>
#include <linux/syscalls.h>
+#include <linux/pkeys.h>
#include <asm/daifflags.h>
#include <asm/debug-monitors.h>
@@ -66,10 +67,63 @@ struct rt_sigframe_user_layout {
unsigned long end_offset;
};
+/*
+ * Holds any EL0-controlled state that influences unprivileged memory accesses.
+ * This includes both accesses done in userspace and uaccess done in the kernel.
+ *
+ * This state needs to be carefully managed to ensure that it doesn't cause
+ * uaccess to fail when setting up the signal frame, and the signal handler
+ * itself also expects a well-defined state when entered.
+ */
+struct user_access_state {
+ u64 por_el0;
+};
+
#define BASE_SIGFRAME_SIZE round_up(sizeof(struct rt_sigframe), 16)
#define TERMINATOR_SIZE round_up(sizeof(struct _aarch64_ctx), 16)
#define EXTRA_CONTEXT_SIZE round_up(sizeof(struct extra_context), 16)
+/*
+ * Save the user access state into ua_state and reset it to disable any
+ * restrictions.
+ */
+static void save_reset_user_access_state(struct user_access_state *ua_state)
+{
+ if (system_supports_poe()) {
+ u64 por_enable_all = 0;
+
+ for (int pkey = 0; pkey < arch_max_pkey(); pkey++)
+ por_enable_all |= POE_RXW << (pkey * POR_BITS_PER_PKEY);
+
+ ua_state->por_el0 = read_sysreg_s(SYS_POR_EL0);
+ write_sysreg_s(por_enable_all, SYS_POR_EL0);
+ /* Ensure that any subsequent uaccess observes the updated value */
+ isb();
+ }
+}
+
+/*
+ * Set the user access state for invoking the signal handler.
+ *
+ * No uaccess should be done after that function is called.
+ */
+static void set_handler_user_access_state(void)
+{
+ if (system_supports_poe())
+ write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0);
+}
+
+/*
+ * Restore the user access state to the values saved in ua_state.
+ *
+ * No uaccess should be done after that function is called.
+ */
+static void restore_user_access_state(const struct user_access_state *ua_state)
+{
+ if (system_supports_poe())
+ write_sysreg_s(ua_state->por_el0, SYS_POR_EL0);
+}
+
static void init_user_layout(struct rt_sigframe_user_layout *user)
{
const size_t reserved_size =
@@ -261,18 +315,20 @@ static int restore_fpmr_context(struct user_ctxs *user)
return err;
}
-static int preserve_poe_context(struct poe_context __user *ctx)
+static int preserve_poe_context(struct poe_context __user *ctx,
+ const struct user_access_state *ua_state)
{
int err = 0;
__put_user_error(POE_MAGIC, &ctx->head.magic, err);
__put_user_error(sizeof(*ctx), &ctx->head.size, err);
- __put_user_error(read_sysreg_s(SYS_POR_EL0), &ctx->por_el0, err);
+ __put_user_error(ua_state->por_el0, &ctx->por_el0, err);
return err;
}
-static int restore_poe_context(struct user_ctxs *user)
+static int restore_poe_context(struct user_ctxs *user,
+ struct user_access_state *ua_state)
{
u64 por_el0;
int err = 0;
@@ -282,7 +338,7 @@ static int restore_poe_context(struct user_ctxs *user)
__get_user_error(por_el0, &(user->poe->por_el0), err);
if (!err)
- write_sysreg_s(por_el0, SYS_POR_EL0);
+ ua_state->por_el0 = por_el0;
return err;
}
@@ -850,7 +906,8 @@ static int parse_user_sigframe(struct user_ctxs *user,
}
static int restore_sigframe(struct pt_regs *regs,
- struct rt_sigframe __user *sf)
+ struct rt_sigframe __user *sf,
+ struct user_access_state *ua_state)
{
sigset_t set;
int i, err;
@@ -899,7 +956,7 @@ static int restore_sigframe(struct pt_regs *regs,
err = restore_zt_context(&user);
if (err == 0 && system_supports_poe() && user.poe)
- err = restore_poe_context(&user);
+ err = restore_poe_context(&user, ua_state);
return err;
}
@@ -908,6 +965,7 @@ SYSCALL_DEFINE0(rt_sigreturn)
{
struct pt_regs *regs = current_pt_regs();
struct rt_sigframe __user *frame;
+ struct user_access_state ua_state;
/* Always make any pending restarted system calls return -EINTR */
current->restart_block.fn = do_no_restart_syscall;
@@ -924,12 +982,14 @@ SYSCALL_DEFINE0(rt_sigreturn)
if (!access_ok(frame, sizeof (*frame)))
goto badframe;
- if (restore_sigframe(regs, frame))
+ if (restore_sigframe(regs, frame, &ua_state))
goto badframe;
if (restore_altstack(&frame->uc.uc_stack))
goto badframe;
+ restore_user_access_state(&ua_state);
+
return regs->regs[0];
badframe:
@@ -1035,7 +1095,8 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
}
static int setup_sigframe(struct rt_sigframe_user_layout *user,
- struct pt_regs *regs, sigset_t *set)
+ struct pt_regs *regs, sigset_t *set,
+ const struct user_access_state *ua_state)
{
int i, err = 0;
struct rt_sigframe __user *sf = user->sigframe;
@@ -1097,10 +1158,9 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
struct poe_context __user *poe_ctx =
apply_user_offset(user, user->poe_offset);
- err |= preserve_poe_context(poe_ctx);
+ err |= preserve_poe_context(poe_ctx, ua_state);
}
-
/* ZA state if present */
if (system_supports_sme() && err == 0 && user->za_offset) {
struct za_context __user *za_ctx =
@@ -1237,9 +1297,6 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
sme_smstop();
}
- if (system_supports_poe())
- write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0);
-
if (ka->sa.sa_flags & SA_RESTORER)
sigtramp = ka->sa.sa_restorer;
else
@@ -1253,6 +1310,7 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
{
struct rt_sigframe_user_layout user;
struct rt_sigframe __user *frame;
+ struct user_access_state ua_state;
int err = 0;
fpsimd_signal_preserve_current_state();
@@ -1260,13 +1318,14 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
if (get_sigframe(&user, ksig, regs))
return 1;
+ save_reset_user_access_state(&ua_state);
frame = user.sigframe;
__put_user_error(0, &frame->uc.uc_flags, err);
__put_user_error(NULL, &frame->uc.uc_link, err);
err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
- err |= setup_sigframe(&user, regs, set);
+ err |= setup_sigframe(&user, regs, set, &ua_state);
if (err == 0) {
setup_return(regs, &ksig->ka, &user, usig);
if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
@@ -1276,6 +1335,11 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
}
}
+ if (err == 0)
+ set_handler_user_access_state();
+ else
+ restore_user_access_state(&ua_state);
+
return err;
}
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/Kconfig b/arch/riscv/Kconfig
index 6254594..f4c5705 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -177,7 +177,7 @@
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RETHOOK if !XIP_KERNEL
select HAVE_RSEQ
- select HAVE_RUST if RUSTC_SUPPORTS_RISCV
+ select HAVE_RUST if RUSTC_SUPPORTS_RISCV && CC_IS_CLANG
select HAVE_SAMPLE_FTRACE_DIRECT
select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
select HAVE_STACKPROTECTOR
diff --git a/arch/riscv/errata/Makefile b/arch/riscv/errata/Makefile
index 8a27394..f0da9d7 100644
--- a/arch/riscv/errata/Makefile
+++ b/arch/riscv/errata/Makefile
@@ -2,6 +2,12 @@
KBUILD_CFLAGS += -fno-pie
endif
+ifdef CONFIG_RISCV_ALTERNATIVE_EARLY
+ifdef CONFIG_FORTIFY_SOURCE
+KBUILD_CFLAGS += -D__NO_FORTIFY
+endif
+endif
+
obj-$(CONFIG_ERRATA_ANDES) += andes/
obj-$(CONFIG_ERRATA_SIFIVE) += sifive/
obj-$(CONFIG_ERRATA_THEAD) += thead/
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 7f88cc4..69dc8aa 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -36,6 +36,11 @@
KASAN_SANITIZE_cpufeature.o := n
KASAN_SANITIZE_sbi_ecall.o := n
endif
+ifdef CONFIG_FORTIFY_SOURCE
+CFLAGS_alternative.o += -D__NO_FORTIFY
+CFLAGS_cpufeature.o += -D__NO_FORTIFY
+CFLAGS_sbi_ecall.o += -D__NO_FORTIFY
+endif
endif
extra-y += vmlinux.lds
diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c
index 6e0d333..2fd2969 100644
--- a/arch/riscv/kernel/acpi.c
+++ b/arch/riscv/kernel/acpi.c
@@ -210,7 +210,7 @@ void __init __iomem *__acpi_map_table(unsigned long phys, unsigned long size)
if (!size)
return NULL;
- return early_ioremap(phys, size);
+ return early_memremap(phys, size);
}
void __init __acpi_unmap_table(void __iomem *map, unsigned long size)
@@ -218,7 +218,7 @@ void __init __acpi_unmap_table(void __iomem *map, unsigned long size)
if (!map || !size)
return;
- early_iounmap(map, size);
+ early_memunmap(map, size);
}
void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index e94180b..c2f3129 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -4,8 +4,6 @@
* Copyright (C) 2017 SiFive
*/
-#define GENERATING_ASM_OFFSETS
-
#include <linux/kbuild.h>
#include <linux/mm.h>
#include <linux/sched.h>
diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c
index b320b1d..2d40736 100644
--- a/arch/riscv/kernel/cacheinfo.c
+++ b/arch/riscv/kernel/cacheinfo.c
@@ -80,8 +80,7 @@ int populate_cache_leaves(unsigned int cpu)
{
struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
struct cacheinfo *this_leaf = this_cpu_ci->info_list;
- struct device_node *np = of_cpu_device_node_get(cpu);
- struct device_node *prev = NULL;
+ struct device_node *np, *prev;
int levels = 1, level = 1;
if (!acpi_disabled) {
@@ -105,6 +104,10 @@ int populate_cache_leaves(unsigned int cpu)
return 0;
}
+ np = of_cpu_device_node_get(cpu);
+ if (!np)
+ return -ENOENT;
+
if (of_property_read_bool(np, "cache-size"))
ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level);
if (of_property_read_bool(np, "i-cache-size"))
diff --git a/arch/riscv/kernel/cpu-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c
index 28b58fc..a1e38ec 100644
--- a/arch/riscv/kernel/cpu-hotplug.c
+++ b/arch/riscv/kernel/cpu-hotplug.c
@@ -58,7 +58,7 @@ void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu)
if (cpu_ops->cpu_is_stopped)
ret = cpu_ops->cpu_is_stopped(cpu);
if (ret)
- pr_warn("CPU%d may not have stopped: %d\n", cpu, ret);
+ pr_warn("CPU%u may not have stopped: %d\n", cpu, ret);
}
/*
diff --git a/arch/riscv/kernel/efi-header.S b/arch/riscv/kernel/efi-header.S
index 515b2df..c5f17c27 100644
--- a/arch/riscv/kernel/efi-header.S
+++ b/arch/riscv/kernel/efi-header.S
@@ -64,7 +64,7 @@
.long efi_header_end - _start // SizeOfHeaders
.long 0 // CheckSum
.short IMAGE_SUBSYSTEM_EFI_APPLICATION // Subsystem
- .short 0 // DllCharacteristics
+ .short IMAGE_DLL_CHARACTERISTICS_NX_COMPAT // DllCharacteristics
.quad 0 // SizeOfStackReserve
.quad 0 // SizeOfStackCommit
.quad 0 // SizeOfHeapReserve
diff --git a/arch/riscv/kernel/pi/Makefile b/arch/riscv/kernel/pi/Makefile
index d5bf1bc..81d69d4 100644
--- a/arch/riscv/kernel/pi/Makefile
+++ b/arch/riscv/kernel/pi/Makefile
@@ -16,8 +16,12 @@
KBUILD_CFLAGS += -mcmodel=medany
CFLAGS_cmdline_early.o += -D__NO_FORTIFY
-CFLAGS_lib-fdt_ro.o += -D__NO_FORTIFY
CFLAGS_fdt_early.o += -D__NO_FORTIFY
+# lib/string.c already defines __NO_FORTIFY
+CFLAGS_ctype.o += -D__NO_FORTIFY
+CFLAGS_lib-fdt.o += -D__NO_FORTIFY
+CFLAGS_lib-fdt_ro.o += -D__NO_FORTIFY
+CFLAGS_archrandom_early.o += -D__NO_FORTIFY
$(obj)/%.pi.o: OBJCOPYFLAGS := --prefix-symbols=__pi_ \
--remove-section=.note.gnu.property \
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index d4fd8af..1b98671 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -136,8 +136,6 @@
#define REG_PTR(insn, pos, regs) \
(ulong *)((ulong)(regs) + REG_OFFSET(insn, pos))
-#define GET_RM(insn) (((insn) >> 12) & 7)
-
#define GET_RS1(insn, regs) (*REG_PTR(insn, SH_RS1, regs))
#define GET_RS2(insn, regs) (*REG_PTR(insn, SH_RS2, regs))
#define GET_RS1S(insn, regs) (*REG_PTR(RVC_RS1S(insn), 0, regs))
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 960feb1..3f1c4b2 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -18,6 +18,7 @@
ccflags-y := -fno-stack-protector
ccflags-y += -DDISABLE_BRANCH_PROFILING
+ccflags-y += -fno-builtin
ifneq ($(c-gettimeofday-y),)
CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y)
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/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/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c
index 285fe7a..3e8051f 100644
--- a/drivers/firmware/arm_sdei.c
+++ b/drivers/firmware/arm_sdei.c
@@ -763,7 +763,7 @@ static int sdei_device_freeze(struct device *dev)
int err;
/* unregister private events */
- cpuhp_remove_state(sdei_entry_point);
+ cpuhp_remove_state(sdei_hp_state);
err = sdei_unregister_shared();
if (err)
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/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/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/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/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/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/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index f137c82..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 */
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/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/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/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/fs/afs/dir.c b/fs/afs/dir.c
index f8622ed..ada363af 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -12,6 +12,7 @@
#include <linux/swap.h>
#include <linux/ctype.h>
#include <linux/sched.h>
+#include <linux/iversion.h>
#include <linux/task_io_accounting_ops.h>
#include "internal.h"
#include "afs_fs.h"
@@ -1823,6 +1824,8 @@ static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir,
static void afs_rename_success(struct afs_operation *op)
{
+ struct afs_vnode *vnode = AFS_FS_I(d_inode(op->dentry));
+
_enter("op=%08x", op->debug_id);
op->ctime = op->file[0].scb.status.mtime_client;
@@ -1832,6 +1835,22 @@ static void afs_rename_success(struct afs_operation *op)
op->ctime = op->file[1].scb.status.mtime_client;
afs_vnode_commit_status(op, &op->file[1]);
}
+
+ /* If we're moving a subdir between dirs, we need to update
+ * its DV counter too as the ".." will be altered.
+ */
+ if (S_ISDIR(vnode->netfs.inode.i_mode) &&
+ op->file[0].vnode != op->file[1].vnode) {
+ u64 new_dv;
+
+ write_seqlock(&vnode->cb_lock);
+
+ new_dv = vnode->status.data_version + 1;
+ vnode->status.data_version = new_dv;
+ inode_set_iversion_raw(&vnode->netfs.inode, new_dv);
+
+ write_sequnlock(&vnode->cb_lock);
+ }
}
static void afs_rename_edit_dir(struct afs_operation *op)
@@ -1873,6 +1892,12 @@ static void afs_rename_edit_dir(struct afs_operation *op)
&vnode->fid, afs_edit_dir_for_rename_2);
}
+ if (S_ISDIR(vnode->netfs.inode.i_mode) &&
+ new_dvnode != orig_dvnode &&
+ test_bit(AFS_VNODE_DIR_VALID, &vnode->flags))
+ afs_edit_dir_update_dotdot(vnode, new_dvnode,
+ afs_edit_dir_for_rename_sub);
+
new_inode = d_inode(new_dentry);
if (new_inode) {
spin_lock(&new_inode->i_lock);
diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c
index a71bff1..fe223fb 100644
--- a/fs/afs/dir_edit.c
+++ b/fs/afs/dir_edit.c
@@ -127,10 +127,10 @@ static struct folio *afs_dir_get_folio(struct afs_vnode *vnode, pgoff_t index)
/*
* Scan a directory block looking for a dirent of the right name.
*/
-static int afs_dir_scan_block(union afs_xdr_dir_block *block, struct qstr *name,
+static int afs_dir_scan_block(const union afs_xdr_dir_block *block, const struct qstr *name,
unsigned int blocknum)
{
- union afs_xdr_dirent *de;
+ const union afs_xdr_dirent *de;
u64 bitmap;
int d, len, n;
@@ -492,3 +492,90 @@ void afs_edit_dir_remove(struct afs_vnode *vnode,
clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
goto out_unmap;
}
+
+/*
+ * Edit a subdirectory that has been moved between directories to update the
+ * ".." entry.
+ */
+void afs_edit_dir_update_dotdot(struct afs_vnode *vnode, struct afs_vnode *new_dvnode,
+ enum afs_edit_dir_reason why)
+{
+ union afs_xdr_dir_block *block;
+ union afs_xdr_dirent *de;
+ struct folio *folio;
+ unsigned int nr_blocks, b;
+ pgoff_t index;
+ loff_t i_size;
+ int slot;
+
+ _enter("");
+
+ i_size = i_size_read(&vnode->netfs.inode);
+ if (i_size < AFS_DIR_BLOCK_SIZE) {
+ clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
+ return;
+ }
+ nr_blocks = i_size / AFS_DIR_BLOCK_SIZE;
+
+ /* Find a block that has sufficient slots available. Each folio
+ * contains two or more directory blocks.
+ */
+ for (b = 0; b < nr_blocks; b++) {
+ index = b / AFS_DIR_BLOCKS_PER_PAGE;
+ folio = afs_dir_get_folio(vnode, index);
+ if (!folio)
+ goto error;
+
+ block = kmap_local_folio(folio, b * AFS_DIR_BLOCK_SIZE - folio_pos(folio));
+
+ /* Abandon the edit if we got a callback break. */
+ if (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags))
+ goto invalidated;
+
+ slot = afs_dir_scan_block(block, &dotdot_name, b);
+ if (slot >= 0)
+ goto found_dirent;
+
+ kunmap_local(block);
+ folio_unlock(folio);
+ folio_put(folio);
+ }
+
+ /* Didn't find the dirent to clobber. Download the directory again. */
+ trace_afs_edit_dir(vnode, why, afs_edit_dir_update_nodd,
+ 0, 0, 0, 0, "..");
+ clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
+ goto out;
+
+found_dirent:
+ de = &block->dirents[slot];
+ de->u.vnode = htonl(new_dvnode->fid.vnode);
+ de->u.unique = htonl(new_dvnode->fid.unique);
+
+ trace_afs_edit_dir(vnode, why, afs_edit_dir_update_dd, b, slot,
+ ntohl(de->u.vnode), ntohl(de->u.unique), "..");
+
+ kunmap_local(block);
+ folio_unlock(folio);
+ folio_put(folio);
+ inode_set_iversion_raw(&vnode->netfs.inode, vnode->status.data_version);
+
+out:
+ _leave("");
+ return;
+
+invalidated:
+ kunmap_local(block);
+ folio_unlock(folio);
+ folio_put(folio);
+ trace_afs_edit_dir(vnode, why, afs_edit_dir_update_inval,
+ 0, 0, 0, 0, "..");
+ clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
+ goto out;
+
+error:
+ trace_afs_edit_dir(vnode, why, afs_edit_dir_update_error,
+ 0, 0, 0, 0, "..");
+ clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
+ goto out;
+}
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 52aab09..c9d6201 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -1073,6 +1073,8 @@ extern void afs_check_for_remote_deletion(struct afs_operation *);
extern void afs_edit_dir_add(struct afs_vnode *, struct qstr *, struct afs_fid *,
enum afs_edit_dir_reason);
extern void afs_edit_dir_remove(struct afs_vnode *, struct qstr *, enum afs_edit_dir_reason);
+void afs_edit_dir_update_dotdot(struct afs_vnode *vnode, struct afs_vnode *new_dvnode,
+ enum afs_edit_dir_reason why);
/*
* dir_silly.c
diff --git a/fs/autofs/dev-ioctl.c b/fs/autofs/dev-ioctl.c
index f011e02..6d57efb 100644
--- a/fs/autofs/dev-ioctl.c
+++ b/fs/autofs/dev-ioctl.c
@@ -110,6 +110,7 @@ static inline void free_dev_ioctl(struct autofs_dev_ioctl *param)
*/
static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param)
{
+ unsigned int inr = _IOC_NR(cmd);
int err;
err = check_dev_ioctl_version(cmd, param);
@@ -133,7 +134,7 @@ static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param)
* check_name() return for AUTOFS_DEV_IOCTL_TIMEOUT_CMD.
*/
err = check_name(param->path);
- if (cmd == AUTOFS_DEV_IOCTL_TIMEOUT_CMD)
+ if (inr == AUTOFS_DEV_IOCTL_TIMEOUT_CMD)
err = err ? 0 : -EINVAL;
if (err) {
pr_warn("invalid path supplied for cmd(0x%08x)\n",
@@ -141,8 +142,6 @@ static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param)
goto out;
}
} else {
- unsigned int inr = _IOC_NR(cmd);
-
if (inr == AUTOFS_DEV_IOCTL_OPENMOUNT_CMD ||
inr == AUTOFS_DEV_IOCTL_REQUESTER_CMD ||
inr == AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD) {
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 5836870..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;
@@ -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_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/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/ec.c b/fs/bcachefs/ec.c
index a0aa5bb..749dcf3 100644
--- a/fs/bcachefs/ec.c
+++ b/fs/bcachefs/ec.c
@@ -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/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.c b/fs/bcachefs/fs-io.c
index 15d3f07..2456c41 100644
--- a/fs/bcachefs/fs-io.c
+++ b/fs/bcachefs/fs-io.c
@@ -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/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/recovery.c b/fs/bcachefs/recovery.c
index 454b5a3..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;
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/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/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/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/extent_map.c b/fs/btrfs/extent_map.c
index 668c617..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)
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/dax.c b/fs/dax.c
index c62acd2..21b4740 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1262,35 +1262,46 @@ static s64 dax_unshare_iter(struct iomap_iter *iter)
{
struct iomap *iomap = &iter->iomap;
const struct iomap *srcmap = iomap_iter_srcmap(iter);
- loff_t pos = iter->pos;
- loff_t length = iomap_length(iter);
+ loff_t copy_pos = iter->pos;
+ u64 copy_len = iomap_length(iter);
+ u32 mod;
int id = 0;
s64 ret = 0;
void *daddr = NULL, *saddr = NULL;
- /* don't bother with blocks that are not shared to start with */
- if (!(iomap->flags & IOMAP_F_SHARED))
- return length;
+ if (!iomap_want_unshare_iter(iter))
+ return iomap_length(iter);
- id = dax_read_lock();
- ret = dax_iomap_direct_access(iomap, pos, length, &daddr, NULL);
- if (ret < 0)
- goto out_unlock;
-
- /* zero the distance if srcmap is HOLE or UNWRITTEN */
- if (srcmap->flags & IOMAP_F_SHARED || srcmap->type == IOMAP_UNWRITTEN) {
- memset(daddr, 0, length);
- dax_flush(iomap->dax_dev, daddr, length);
- ret = length;
- goto out_unlock;
+ /*
+ * Extend the file range to be aligned to fsblock/pagesize, because
+ * we need to copy entire blocks, not just the byte range specified.
+ * Invalidate the mapping because we're about to CoW.
+ */
+ mod = offset_in_page(copy_pos);
+ if (mod) {
+ copy_len += mod;
+ copy_pos -= mod;
}
- ret = dax_iomap_direct_access(srcmap, pos, length, &saddr, NULL);
+ mod = offset_in_page(copy_pos + copy_len);
+ if (mod)
+ copy_len += PAGE_SIZE - mod;
+
+ invalidate_inode_pages2_range(iter->inode->i_mapping,
+ copy_pos >> PAGE_SHIFT,
+ (copy_pos + copy_len - 1) >> PAGE_SHIFT);
+
+ id = dax_read_lock();
+ ret = dax_iomap_direct_access(iomap, copy_pos, copy_len, &daddr, NULL);
if (ret < 0)
goto out_unlock;
- if (copy_mc_to_kernel(daddr, saddr, length) == 0)
- ret = length;
+ ret = dax_iomap_direct_access(srcmap, copy_pos, copy_len, &saddr, NULL);
+ if (ret < 0)
+ goto out_unlock;
+
+ if (copy_mc_to_kernel(daddr, saddr, copy_len) == 0)
+ ret = iomap_length(iter);
else
ret = -EIO;
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 320d586..bed3dbe 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -709,7 +709,9 @@ static int erofs_fc_get_tree(struct fs_context *fc)
if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid)
return get_tree_nodev(fc, erofs_fc_fill_super);
- ret = get_tree_bdev(fc, erofs_fc_fill_super);
+ ret = get_tree_bdev_flags(fc, erofs_fc_fill_super,
+ IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) ?
+ GET_TREE_BDEV_QUIET_LOOKUP : 0);
#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
if (ret == -ENOTBLK) {
if (!fc->source)
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index aa587b2..ef0b68b 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1277,22 +1277,7 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter)
loff_t length = iomap_length(iter);
loff_t written = 0;
- /* Don't bother with blocks that are not shared to start with. */
- if (!(iomap->flags & IOMAP_F_SHARED))
- return length;
-
- /*
- * Don't bother with delalloc reservations, holes or unwritten extents.
- *
- * Note that we use srcmap directly instead of iomap_iter_srcmap as
- * unsharing requires providing a separate source map, and the presence
- * of one is a good indicator that unsharing is needed, unlike
- * IOMAP_F_SHARED which can be set for any data that goes into the COW
- * fork for XFS.
- */
- if (iter->srcmap.type == IOMAP_HOLE ||
- iter->srcmap.type == IOMAP_DELALLOC ||
- iter->srcmap.type == IOMAP_UNWRITTEN)
+ if (!iomap_want_unshare_iter(iter))
return length;
do {
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 5436eb0..10def4b 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -401,6 +401,7 @@ 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) {
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 5888745..06af219 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1787,6 +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/super.c b/fs/super.c
index 1db2304..c9c7223 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1596,13 +1596,14 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
EXPORT_SYMBOL_GPL(setup_bdev_super);
/**
- * get_tree_bdev - Get a superblock based on a single block device
+ * get_tree_bdev_flags - Get a superblock based on a single block device
* @fc: The filesystem context holding the parameters
* @fill_super: Helper to initialise a new superblock
+ * @flags: GET_TREE_BDEV_* flags
*/
-int get_tree_bdev(struct fs_context *fc,
- int (*fill_super)(struct super_block *,
- struct fs_context *))
+int get_tree_bdev_flags(struct fs_context *fc,
+ int (*fill_super)(struct super_block *sb,
+ struct fs_context *fc), unsigned int flags)
{
struct super_block *s;
int error = 0;
@@ -1613,10 +1614,10 @@ int get_tree_bdev(struct fs_context *fc,
error = lookup_bdev(fc->source, &dev);
if (error) {
- errorf(fc, "%s: Can't lookup blockdev", fc->source);
+ if (!(flags & GET_TREE_BDEV_QUIET_LOOKUP))
+ errorf(fc, "%s: Can't lookup blockdev", fc->source);
return error;
}
-
fc->sb_flags |= SB_NOSEC;
s = sget_dev(fc, dev);
if (IS_ERR(s))
@@ -1644,6 +1645,19 @@ int get_tree_bdev(struct fs_context *fc,
fc->root = dget(s->s_root);
return 0;
}
+EXPORT_SYMBOL_GPL(get_tree_bdev_flags);
+
+/**
+ * get_tree_bdev - Get a superblock based on a single block device
+ * @fc: The filesystem context holding the parameters
+ * @fill_super: Helper to initialise a new superblock
+ */
+int get_tree_bdev(struct fs_context *fc,
+ int (*fill_super)(struct super_block *,
+ struct fs_context *))
+{
+ return get_tree_bdev_flags(fc, fill_super, 0);
+}
EXPORT_SYMBOL(get_tree_bdev);
static int test_bdev_super(struct super_block *s, void *data)
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/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 916531d..86da16f 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -707,7 +707,7 @@ imap_needs_cow(
return false;
/* when zeroing we don't have to COW holes or unwritten extents */
- if (flags & IOMAP_ZERO) {
+ if (flags & (IOMAP_UNSHARE | IOMAP_ZERO)) {
if (!nimaps ||
imap->br_startblock == HOLESTARTBLOCK ||
imap->br_state == XFS_EXT_UNWRITTEN)
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/compiler-gcc.h b/include/linux/compiler-gcc.h
index f805ada..cd6f9aa 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -80,7 +80,11 @@
#define __noscs __attribute__((__no_sanitize__("shadow-call-stack")))
#endif
+#ifdef __SANITIZE_HWADDRESS__
+#define __no_sanitize_address __attribute__((__no_sanitize__("hwaddress")))
+#else
#define __no_sanitize_address __attribute__((__no_sanitize_address__))
+#endif
#if defined(__SANITIZE_THREAD__)
#define __no_sanitize_thread __attribute__((__no_sanitize_thread__))
diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h
index c13e99c..4b4bfef 100644
--- a/include/linux/fs_context.h
+++ b/include/linux/fs_context.h
@@ -160,6 +160,12 @@ extern int get_tree_keyed(struct fs_context *fc,
int setup_bdev_super(struct super_block *sb, int sb_flags,
struct fs_context *fc);
+
+#define GET_TREE_BDEV_QUIET_LOOKUP 0x0001
+int get_tree_bdev_flags(struct fs_context *fc,
+ int (*fill_super)(struct super_block *sb,
+ struct fs_context *fc), unsigned int flags);
+
extern int get_tree_bdev(struct fs_context *fc,
int (*fill_super)(struct super_block *sb,
struct fs_context *fc));
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index d0420e9..f61407e 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -270,6 +270,25 @@ static inline loff_t iomap_last_written_block(struct inode *inode, loff_t pos,
return round_up(pos + written, i_blocksize(inode));
}
+/*
+ * Check if the range needs to be unshared for a FALLOC_FL_UNSHARE_RANGE
+ * operation.
+ *
+ * Don't bother with blocks that are not shared to start with; or mappings that
+ * cannot be shared, such as inline data, delalloc reservations, holes or
+ * unwritten extents.
+ *
+ * Note that we use srcmap directly instead of iomap_iter_srcmap as unsharing
+ * requires providing a separate source map, and the presence of one is a good
+ * indicator that unsharing is needed, unlike IOMAP_F_SHARED which can be set
+ * for any data that goes into the COW fork for XFS.
+ */
+static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter)
+{
+ return (iter->iomap.flags & IOMAP_F_SHARED) &&
+ iter->srcmap.type == IOMAP_MAPPED;
+}
+
ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
const struct iomap_ops *ops, void *private);
int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops);
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/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/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/trace/events/afs.h b/include/trace/events/afs.h
index 450c44c..a0aed1a 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -331,7 +331,11 @@ enum yfs_cm_operation {
EM(afs_edit_dir_delete, "delete") \
EM(afs_edit_dir_delete_error, "d_err ") \
EM(afs_edit_dir_delete_inval, "d_invl") \
- E_(afs_edit_dir_delete_noent, "d_nent")
+ EM(afs_edit_dir_delete_noent, "d_nent") \
+ EM(afs_edit_dir_update_dd, "u_ddot") \
+ EM(afs_edit_dir_update_error, "u_fail") \
+ EM(afs_edit_dir_update_inval, "u_invl") \
+ E_(afs_edit_dir_update_nodd, "u_nodd")
#define afs_edit_dir_reasons \
EM(afs_edit_dir_for_create, "Create") \
@@ -340,6 +344,7 @@ enum yfs_cm_operation {
EM(afs_edit_dir_for_rename_0, "Renam0") \
EM(afs_edit_dir_for_rename_1, "Renam1") \
EM(afs_edit_dir_for_rename_2, "Renam2") \
+ EM(afs_edit_dir_for_rename_sub, "RnmSub") \
EM(afs_edit_dir_for_rmdir, "RmDir ") \
EM(afs_edit_dir_for_silly_0, "S_Ren0") \
EM(afs_edit_dir_for_silly_1, "S_Ren1") \
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 ca3f0a2..3d45ebe 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -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_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_w
return err;
}
+ swap_ulong_in_u64(kit->bits, nr_words);
+
kit->nr_bits = nr_bits;
return 0;
}
@@ -2930,17 +2965,16 @@ bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_w
__bpf_kfunc int *bpf_iter_bits_next(struct bpf_iter_bits *it)
{
struct bpf_iter_bits_kern *kit = (void *)it;
- u32 nr_bits = kit->nr_bits;
- const unsigned long *bits;
- int bit;
+ int bit = kit->bit, nr_bits = kit->nr_bits;
+ const void *bits;
- if (nr_bits == 0)
+ if (!nr_bits || bit >= nr_bits)
return NULL;
bits = nr_bits == 64 ? &kit->bits_copy : kit->bits;
- bit = find_next_bit(bits, nr_bits, kit->bit + 1);
+ bit = find_next_bit(bits, nr_bits, bit + 1);
if (bit >= nr_bits) {
- kit->nr_bits = 0;
+ kit->bit = bit;
return NULL;
}
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 0218a51..9b60eda 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -655,7 +655,7 @@ static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key)
if (!key || key->prefixlen > trie->max_prefixlen)
goto find_leftmost;
- node_stack = kmalloc_array(trie->max_prefixlen,
+ node_stack = kmalloc_array(trie->max_prefixlen + 1,
sizeof(struct lpm_trie_node *),
GFP_ATOMIC | __GFP_NOWARN);
if (!node_stack)
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index b3858a7..146f5b5 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -35,6 +35,8 @@
*/
#define LLIST_NODE_SZ sizeof(struct llist_node)
+#define BPF_MEM_ALLOC_SIZE_MAX 4096
+
/* similar to kmalloc, but sizeof == 8 bucket is gone */
static u8 size_index[24] __ro_after_init = {
3, /* 8 */
@@ -65,7 +67,7 @@ static u8 size_index[24] __ro_after_init = {
static int bpf_mem_cache_idx(size_t size)
{
- if (!size || size > 4096)
+ if (!size || size > BPF_MEM_ALLOC_SIZE_MAX)
return -1;
if (size <= 192)
@@ -1005,3 +1007,13 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags)
return !ret ? NULL : ret + LLIST_NODE_SZ;
}
+
+int bpf_mem_alloc_check_size(bool percpu, size_t size)
+{
+ /* The size of percpu allocation doesn't have LLIST_NODE_SZ overhead */
+ if ((percpu && size > BPF_MEM_ALLOC_SIZE_MAX) ||
+ (!percpu && size > BPF_MEM_ALLOC_SIZE_MAX - LLIST_NODE_SZ))
+ return -E2BIG;
+
+ return 0;
+}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 587a6c7..bb99bad 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6804,20 +6804,10 @@ static int check_stack_slot_within_bounds(struct bpf_verifier_env *env,
struct bpf_func_state *state,
enum bpf_access_type t)
{
- struct bpf_insn_aux_data *aux = &env->insn_aux_data[env->insn_idx];
- int min_valid_off, max_bpf_stack;
-
- /* If accessing instruction is a spill/fill from bpf_fastcall pattern,
- * add room for all caller saved registers below MAX_BPF_STACK.
- * In case if bpf_fastcall rewrite won't happen maximal stack depth
- * would be checked by check_max_stack_depth_subprog().
- */
- max_bpf_stack = MAX_BPF_STACK;
- if (aux->fastcall_pattern)
- max_bpf_stack += CALLER_SAVED_REGS * BPF_REG_SIZE;
+ int min_valid_off;
if (t == BPF_WRITE || env->allow_uninit_stack)
- min_valid_off = -max_bpf_stack;
+ min_valid_off = -MAX_BPF_STACK;
else
min_valid_off = -state->allocated_stack;
@@ -17886,9 +17876,11 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
struct bpf_verifier_state_list *sl, **pprev;
struct bpf_verifier_state *cur = env->cur_state, *new, *loop_entry;
int i, j, n, err, states_cnt = 0;
- bool force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx);
- bool add_new_state = force_new_state;
- bool force_exact;
+ bool force_new_state, add_new_state, force_exact;
+
+ force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx) ||
+ /* Avoid accumulating infinitely long jmp history */
+ cur->jmp_history_cnt > 40;
/* bpf progs typically have pruning point every 4 instructions
* http://vger.kernel.org/bpfconf2019.html#session-1
@@ -17898,6 +17890,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
* In tests that amounts to up to 50% reduction into total verifier
* memory consumption and 20% verifier time speedup.
*/
+ add_new_state = force_new_state;
if (env->jmps_processed - env->prev_jmps_processed >= 2 &&
env->insn_processed - env->prev_insn_processed >= 8)
add_new_state = true;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 5886b95c..044c7ba 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -5789,7 +5789,7 @@ static bool cgroup_check_hierarchy_limits(struct cgroup *parent)
{
struct cgroup *cgroup;
int ret = false;
- int level = 1;
+ int level = 0;
lockdep_assert_held(&cgroup_mutex);
@@ -5797,7 +5797,7 @@ static bool cgroup_check_hierarchy_limits(struct cgroup *parent)
if (cgroup->nr_descendants >= cgroup->max_descendants)
goto fail;
- if (level > cgroup->max_depth)
+ if (level >= cgroup->max_depth)
goto fail;
level++;
diff --git a/kernel/fork.c b/kernel/fork.c
index 89ceb4a..3bf38d2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -653,11 +653,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
mm->exec_vm = oldmm->exec_vm;
mm->stack_vm = oldmm->stack_vm;
- retval = ksm_fork(mm, oldmm);
- if (retval)
- goto out;
- khugepaged_fork(mm, oldmm);
-
/* Use __mt_dup() to efficiently build an identical maple tree. */
retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL);
if (unlikely(retval))
@@ -760,6 +755,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
vma_iter_free(&vmi);
if (!retval) {
mt_set_in_rcu(vmi.mas.tree);
+ ksm_fork(mm, oldmm);
+ khugepaged_fork(mm, oldmm);
} else if (mpnt) {
/*
* The entire maple tree has already been duplicated. If the
@@ -775,7 +772,10 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
mmap_write_unlock(mm);
flush_tlb_mm(oldmm);
mmap_write_unlock(oldmm);
- dup_userfaultfd_complete(&uf);
+ if (!retval)
+ dup_userfaultfd_complete(&uf);
+ else
+ dup_userfaultfd_fail(&uf);
fail_uprobe_end:
uprobe_end_dup_mmap();
return retval;
diff --git a/kernel/resource.c b/kernel/resource.c
index b730bd2..4101016 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -459,9 +459,7 @@ int walk_system_ram_res_rev(u64 start, u64 end, void *arg,
rams_size += 16;
}
- rams[i].start = res.start;
- rams[i++].end = res.end;
-
+ rams[i++] = res;
start = res.end + 1;
}
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 5900b06..8b98ab2 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -862,7 +862,8 @@ static DEFINE_MUTEX(scx_ops_enable_mutex);
DEFINE_STATIC_KEY_FALSE(__scx_ops_enabled);
DEFINE_STATIC_PERCPU_RWSEM(scx_fork_rwsem);
static atomic_t scx_ops_enable_state_var = ATOMIC_INIT(SCX_OPS_DISABLED);
-static atomic_t scx_ops_bypass_depth = ATOMIC_INIT(0);
+static int scx_ops_bypass_depth;
+static DEFINE_RAW_SPINLOCK(__scx_ops_bypass_lock);
static bool scx_ops_init_task_enabled;
static bool scx_switching_all;
DEFINE_STATIC_KEY_FALSE(__scx_switched_all);
@@ -4298,18 +4299,20 @@ bool task_should_scx(struct task_struct *p)
*/
static void scx_ops_bypass(bool bypass)
{
- int depth, cpu;
+ int cpu;
+ unsigned long flags;
+ raw_spin_lock_irqsave(&__scx_ops_bypass_lock, flags);
if (bypass) {
- depth = atomic_inc_return(&scx_ops_bypass_depth);
- WARN_ON_ONCE(depth <= 0);
- if (depth != 1)
- return;
+ scx_ops_bypass_depth++;
+ WARN_ON_ONCE(scx_ops_bypass_depth <= 0);
+ if (scx_ops_bypass_depth != 1)
+ goto unlock;
} else {
- depth = atomic_dec_return(&scx_ops_bypass_depth);
- WARN_ON_ONCE(depth < 0);
- if (depth != 0)
- return;
+ scx_ops_bypass_depth--;
+ WARN_ON_ONCE(scx_ops_bypass_depth < 0);
+ if (scx_ops_bypass_depth != 0)
+ goto unlock;
}
/*
@@ -4326,7 +4329,7 @@ static void scx_ops_bypass(bool bypass)
struct rq_flags rf;
struct task_struct *p, *n;
- rq_lock_irqsave(rq, &rf);
+ rq_lock(rq, &rf);
if (bypass) {
WARN_ON_ONCE(rq->scx.flags & SCX_RQ_BYPASSING);
@@ -4362,11 +4365,13 @@ static void scx_ops_bypass(bool bypass)
sched_enq_and_set_task(&ctx);
}
- rq_unlock_irqrestore(rq, &rf);
+ rq_unlock(rq, &rf);
/* resched to restore ticks and idle state */
resched_cpu(cpu);
}
+unlock:
+ raw_spin_unlock_irqrestore(&__scx_ops_bypass_lock, flags);
}
static void free_exit_info(struct scx_exit_info *ei)
diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index 233ab20..98016e1 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -22,11 +22,8 @@
config CC_HAS_KASAN_GENERIC
def_bool $(cc-option, -fsanitize=kernel-address)
-# GCC appears to ignore no_sanitize_address when -fsanitize=kernel-hwaddress
-# is passed. See https://bugzilla.kernel.org/show_bug.cgi?id=218854 (and
-# the linked LKML thread) for more details.
config CC_HAS_KASAN_SW_TAGS
- def_bool !CC_IS_GCC && $(cc-option, -fsanitize=kernel-hwaddress)
+ def_bool $(cc-option, -fsanitize=kernel-hwaddress)
# This option is only required for software KASAN modes.
# Old GCC versions do not have proper support for no_sanitize_address.
@@ -101,7 +98,7 @@
help
Enables Software Tag-Based KASAN.
- Requires Clang.
+ Requires GCC 11+ or Clang.
Supported only on arm64 CPUs and relies on Top Byte Ignore.
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 1abb32c..908e75a 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -461,6 +461,8 @@ size_t copy_page_from_iter_atomic(struct page *page, size_t offset,
size_t bytes, struct iov_iter *i)
{
size_t n, copied = 0;
+ bool uses_kmap = IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) ||
+ PageHighMem(page);
if (!page_copy_sane(page, offset, bytes))
return 0;
@@ -471,7 +473,7 @@ size_t copy_page_from_iter_atomic(struct page *page, size_t offset,
char *p;
n = bytes - copied;
- if (PageHighMem(page)) {
+ if (uses_kmap) {
page += offset / PAGE_SIZE;
offset %= PAGE_SIZE;
n = min_t(size_t, n, PAGE_SIZE - offset);
@@ -482,7 +484,7 @@ size_t copy_page_from_iter_atomic(struct page *page, size_t offset,
kunmap_atomic(p);
copied += n;
offset += n;
- } while (PageHighMem(page) && copied != bytes && n > 0);
+ } while (uses_kmap && copied != bytes && n > 0);
return copied;
}
@@ -1021,15 +1023,18 @@ static ssize_t iter_folioq_get_pages(struct iov_iter *iter,
size_t offset = iov_offset, fsize = folioq_folio_size(folioq, slot);
size_t part = PAGE_SIZE - offset % PAGE_SIZE;
- part = umin(part, umin(maxsize - extracted, fsize - offset));
- count -= part;
- iov_offset += part;
- extracted += part;
+ if (offset < fsize) {
+ part = umin(part, umin(maxsize - extracted, fsize - offset));
+ count -= part;
+ iov_offset += part;
+ extracted += part;
- *pages = folio_page(folio, offset / PAGE_SIZE);
- get_page(*pages);
- pages++;
- maxpages--;
+ *pages = folio_page(folio, offset / PAGE_SIZE);
+ get_page(*pages);
+ pages++;
+ maxpages--;
+ }
+
if (maxpages == 0 || extracted >= maxsize)
break;
diff --git a/lib/slub_kunit.c b/lib/slub_kunit.c
index 80e39f0..33564f9 100644
--- a/lib/slub_kunit.c
+++ b/lib/slub_kunit.c
@@ -141,7 +141,7 @@ static void test_kmalloc_redzone_access(struct kunit *test)
{
struct kmem_cache *s = test_kmem_cache_create("TestSlub_RZ_kmalloc", 32,
SLAB_KMALLOC|SLAB_STORE_USER|SLAB_RED_ZONE);
- u8 *p = __kmalloc_cache_noprof(s, GFP_KERNEL, 18);
+ u8 *p = alloc_hooks(__kmalloc_cache_noprof(s, GFP_KERNEL, 18));
kasan_disable_current();
diff --git a/mm/Kconfig b/mm/Kconfig
index 4c9f5ea..33fa51d 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1085,7 +1085,6 @@
depends on MMU
config GET_FREE_REGION
- depends on SPARSEMEM
bool
config DEVICE_PRIVATE
diff --git a/mm/memory.c b/mm/memory.c
index 3ccee51..bdf77a3 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4187,6 +4187,8 @@ static struct folio *alloc_swap_folio(struct vm_fault *vmf)
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+static DECLARE_WAIT_QUEUE_HEAD(swapcache_wq);
+
/*
* We enter with non-exclusive mmap_lock (to exclude vma changes,
* but allow concurrent faults), and pte mapped but not yet locked.
@@ -4199,6 +4201,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct folio *swapcache, *folio = NULL;
+ DECLARE_WAITQUEUE(wait, current);
struct page *page;
struct swap_info_struct *si = NULL;
rmap_t rmap_flags = RMAP_NONE;
@@ -4297,7 +4300,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
* Relax a bit to prevent rapid
* repeated page faults.
*/
+ add_wait_queue(&swapcache_wq, &wait);
schedule_timeout_uninterruptible(1);
+ remove_wait_queue(&swapcache_wq, &wait);
goto out_page;
}
need_clear_cache = true;
@@ -4604,8 +4609,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
pte_unmap_unlock(vmf->pte, vmf->ptl);
out:
/* Clear the swap cache pin for direct swapin after PTL unlock */
- if (need_clear_cache)
+ if (need_clear_cache) {
swapcache_clear(si, entry, nr_pages);
+ if (waitqueue_active(&swapcache_wq))
+ wake_up(&swapcache_wq);
+ }
if (si)
put_swap_device(si);
return ret;
@@ -4620,8 +4628,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
folio_unlock(swapcache);
folio_put(swapcache);
}
- if (need_clear_cache)
+ if (need_clear_cache) {
swapcache_clear(si, entry, nr_pages);
+ if (waitqueue_active(&swapcache_wq))
+ wake_up(&swapcache_wq);
+ }
if (si)
put_swap_device(si);
return ret;
diff --git a/mm/mmap.c b/mm/mmap.c
index 9c0fb43..1e0e34c 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1418,6 +1418,13 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
vmg.flags = vm_flags;
}
+ /*
+ * clear PTEs while the vma is still in the tree so that rmap
+ * cannot race with the freeing later in the truncate scenario.
+ * This is also needed for call_mmap(), which is why vm_ops
+ * close function is called.
+ */
+ vms_clean_up_area(&vms, &mas_detach);
vma = vma_merge_new_range(&vmg);
if (vma)
goto expanded;
@@ -1439,11 +1446,6 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
if (file) {
vma->vm_file = get_file(file);
- /*
- * call_mmap() may map PTE, so ensure there are no existing PTEs
- * and call the vm_ops close function if one exists.
- */
- vms_clean_up_area(&vms, &mas_detach);
error = call_mmap(file, vma);
if (error)
goto unmap_and_free_vma;
@@ -1640,6 +1642,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
unsigned long populate = 0;
unsigned long ret = -EINVAL;
struct file *file;
+ vm_flags_t vm_flags;
pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/mm/remap_file_pages.rst.\n",
current->comm, current->pid);
@@ -1656,12 +1659,60 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
if (pgoff + (size >> PAGE_SHIFT) < pgoff)
return ret;
- if (mmap_write_lock_killable(mm))
+ if (mmap_read_lock_killable(mm))
return -EINTR;
+ /*
+ * Look up VMA under read lock first so we can perform the security
+ * without holding locks (which can be problematic). We reacquire a
+ * write lock later and check nothing changed underneath us.
+ */
+ vma = vma_lookup(mm, start);
+
+ if (!vma || !(vma->vm_flags & VM_SHARED)) {
+ mmap_read_unlock(mm);
+ return -EINVAL;
+ }
+
+ prot |= vma->vm_flags & VM_READ ? PROT_READ : 0;
+ prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0;
+ prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0;
+
+ flags &= MAP_NONBLOCK;
+ flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE;
+ if (vma->vm_flags & VM_LOCKED)
+ flags |= MAP_LOCKED;
+
+ /* Save vm_flags used to calculate prot and flags, and recheck later. */
+ vm_flags = vma->vm_flags;
+ file = get_file(vma->vm_file);
+
+ mmap_read_unlock(mm);
+
+ /* Call outside mmap_lock to be consistent with other callers. */
+ ret = security_mmap_file(file, prot, flags);
+ if (ret) {
+ fput(file);
+ return ret;
+ }
+
+ ret = -EINVAL;
+
+ /* OK security check passed, take write lock + let it rip. */
+ if (mmap_write_lock_killable(mm)) {
+ fput(file);
+ return -EINTR;
+ }
+
vma = vma_lookup(mm, start);
- if (!vma || !(vma->vm_flags & VM_SHARED))
+ if (!vma)
+ goto out;
+
+ /* Make sure things didn't change under us. */
+ if (vma->vm_flags != vm_flags)
+ goto out;
+ if (vma->vm_file != file)
goto out;
if (start + size > vma->vm_end) {
@@ -1689,25 +1740,11 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
goto out;
}
- prot |= vma->vm_flags & VM_READ ? PROT_READ : 0;
- prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0;
- prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0;
-
- flags &= MAP_NONBLOCK;
- flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE;
- if (vma->vm_flags & VM_LOCKED)
- flags |= MAP_LOCKED;
-
- file = get_file(vma->vm_file);
- ret = security_mmap_file(vma->vm_file, prot, flags);
- if (ret)
- goto out_fput;
ret = do_mmap(vma->vm_file, start, size,
prot, flags, 0, pgoff, &populate, NULL);
-out_fput:
- fput(file);
out:
mmap_write_unlock(mm);
+ fput(file);
if (populate)
mm_populate(ret, populate);
if (!IS_ERR_VALUE(ret))
@@ -1754,7 +1791,8 @@ static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
VMG_STATE(vmg, mm, vmi, addr, addr + len, flags, PHYS_PFN(addr));
vmg.prev = vma;
- vma_iter_next_range(vmi);
+ /* vmi is positioned at prev, which this mode expects. */
+ vmg.merge_flags = VMG_FLAG_JUST_EXPAND;
if (vma_merge_new_range(&vmg))
goto out;
diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c
index be52b93..a3877e9 100644
--- a/mm/numa_memblks.c
+++ b/mm/numa_memblks.c
@@ -349,7 +349,7 @@ static void __init numa_clear_kernel_node_hotplug(void)
for_each_reserved_mem_region(mb_region) {
int nid = memblock_get_region_node(mb_region);
- if (nid != MAX_NUMNODES)
+ if (numa_valid_node(nid))
node_set(nid, reserved_nodemask);
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8afab648..94a2ffe 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2893,12 +2893,12 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone,
page = __rmqueue(zone, order, migratetype, alloc_flags);
/*
- * If the allocation fails, allow OOM handling access
- * to HIGHATOMIC reserves as failing now is worse than
- * failing a high-order atomic allocation in the
- * future.
+ * If the allocation fails, allow OOM handling and
+ * order-0 (atomic) allocs access to HIGHATOMIC
+ * reserves as failing now is worse than failing a
+ * high-order atomic allocation in the future.
*/
- if (!page && (alloc_flags & ALLOC_OOM))
+ if (!page && (alloc_flags & (ALLOC_OOM|ALLOC_NON_BLOCK)))
page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
if (!page) {
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 461ea3b..5f9f015 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -744,7 +744,8 @@ struct folio *folio_walk_start(struct folio_walk *fw,
pud = pudp_get(pudp);
if (pud_none(pud))
goto not_found;
- if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) && pud_leaf(pud)) {
+ if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) &&
+ (!pud_present(pud) || pud_leaf(pud))) {
ptl = pud_lock(vma->vm_mm, pudp);
pud = pudp_get(pudp);
@@ -753,6 +754,10 @@ struct folio *folio_walk_start(struct folio_walk *fw,
fw->pudp = pudp;
fw->pud = pud;
+ /*
+ * TODO: FW_MIGRATION support for PUD migration entries
+ * once there are relevant users.
+ */
if (!pud_present(pud) || pud_devmap(pud) || pud_special(pud)) {
spin_unlock(ptl);
goto not_found;
@@ -769,12 +774,13 @@ struct folio *folio_walk_start(struct folio_walk *fw,
}
pmd_table:
- VM_WARN_ON_ONCE(pud_leaf(*pudp));
+ VM_WARN_ON_ONCE(!pud_present(pud) || pud_leaf(pud));
pmdp = pmd_offset(pudp, addr);
pmd = pmdp_get_lockless(pmdp);
if (pmd_none(pmd))
goto not_found;
- if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) && pmd_leaf(pmd)) {
+ if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) &&
+ (!pmd_present(pmd) || pmd_leaf(pmd))) {
ptl = pmd_lock(vma->vm_mm, pmdp);
pmd = pmdp_get(pmdp);
@@ -786,7 +792,7 @@ struct folio *folio_walk_start(struct folio_walk *fw,
if (pmd_none(pmd)) {
spin_unlock(ptl);
goto not_found;
- } else if (!pmd_leaf(pmd)) {
+ } else if (pmd_present(pmd) && !pmd_leaf(pmd)) {
spin_unlock(ptl);
goto pte_table;
} else if (pmd_present(pmd)) {
@@ -812,7 +818,7 @@ struct folio *folio_walk_start(struct folio_walk *fw,
}
pte_table:
- VM_WARN_ON_ONCE(pmd_leaf(pmdp_get_lockless(pmdp)));
+ VM_WARN_ON_ONCE(!pmd_present(pmd) || pmd_leaf(pmd));
ptep = pte_offset_map_lock(vma->vm_mm, pmdp, addr, &ptl);
if (!ptep)
goto not_found;
diff --git a/mm/shmem.c b/mm/shmem.c
index c5adb98..4ba1d00 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1166,7 +1166,9 @@ static int shmem_getattr(struct mnt_idmap *idmap,
stat->attributes_mask |= (STATX_ATTR_APPEND |
STATX_ATTR_IMMUTABLE |
STATX_ATTR_NODUMP);
+ inode_lock_shared(inode);
generic_fillattr(idmap, request_mask, inode, stat);
+ inode_unlock_shared(inode);
if (shmem_huge_global_enabled(inode, 0, 0, false, NULL, 0))
stat->blksize = HPAGE_PMD_SIZE;
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 3d26c25..552b92d 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1209,7 +1209,7 @@ __do_krealloc(const void *p, size_t new_size, gfp_t flags)
/* Zero out spare memory. */
if (want_init_on_alloc(flags)) {
kasan_disable_current();
- memset((void *)p + new_size, 0, ks - new_size);
+ memset(kasan_reset_tag(p) + new_size, 0, ks - new_size);
kasan_enable_current();
}
diff --git a/mm/vma.c b/mm/vma.c
index 4737afc..b21ffec 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -917,6 +917,7 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg)
pgoff_t pgoff = vmg->pgoff;
pgoff_t pglen = PHYS_PFN(end - start);
bool can_merge_left, can_merge_right;
+ bool just_expand = vmg->merge_flags & VMG_FLAG_JUST_EXPAND;
mmap_assert_write_locked(vmg->mm);
VM_WARN_ON(vmg->vma);
@@ -930,7 +931,7 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg)
return NULL;
can_merge_left = can_vma_merge_left(vmg);
- can_merge_right = can_vma_merge_right(vmg, can_merge_left);
+ can_merge_right = !just_expand && can_vma_merge_right(vmg, can_merge_left);
/* If we can merge with the next VMA, adjust vmg accordingly. */
if (can_merge_right) {
@@ -953,7 +954,11 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg)
if (can_merge_right && !can_merge_remove_vma(next))
vmg->end = end;
- vma_prev(vmg->vmi); /* Equivalent to going to the previous range */
+ /* In expand-only case we are already positioned at prev. */
+ if (!just_expand) {
+ /* Equivalent to going to the previous range. */
+ vma_prev(vmg->vmi);
+ }
}
/*
@@ -967,12 +972,14 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg)
}
/* If expansion failed, reset state. Allows us to retry merge later. */
- vmg->vma = NULL;
- vmg->start = start;
- vmg->end = end;
- vmg->pgoff = pgoff;
- if (vmg->vma == prev)
- vma_iter_set(vmg->vmi, start);
+ if (!just_expand) {
+ vmg->vma = NULL;
+ vmg->start = start;
+ vmg->end = end;
+ vmg->pgoff = pgoff;
+ if (vmg->vma == prev)
+ vma_iter_set(vmg->vmi, start);
+ }
return NULL;
}
diff --git a/mm/vma.h b/mm/vma.h
index 819f994..55457cb 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -59,6 +59,17 @@ enum vma_merge_state {
VMA_MERGE_SUCCESS,
};
+enum vma_merge_flags {
+ VMG_FLAG_DEFAULT = 0,
+ /*
+ * If we can expand, simply do so. We know there is nothing to merge to
+ * the right. Does not reset state upon failure to merge. The VMA
+ * iterator is assumed to be positioned at the previous VMA, rather than
+ * at the gap.
+ */
+ VMG_FLAG_JUST_EXPAND = 1 << 0,
+};
+
/* Represents a VMA merge operation. */
struct vma_merge_struct {
struct mm_struct *mm;
@@ -75,6 +86,7 @@ struct vma_merge_struct {
struct mempolicy *policy;
struct vm_userfaultfd_ctx uffd_ctx;
struct anon_vma_name *anon_name;
+ enum vma_merge_flags merge_flags;
enum vma_merge_state state;
};
@@ -99,6 +111,7 @@ static inline pgoff_t vma_pgoff_offset(struct vm_area_struct *vma,
.flags = flags_, \
.pgoff = pgoff_, \
.state = VMA_MERGE_START, \
+ .merge_flags = VMG_FLAG_DEFAULT, \
}
#define VMG_VMA_STATE(name, vmi_, prev_, vma_, start_, end_) \
@@ -118,6 +131,7 @@ static inline pgoff_t vma_pgoff_offset(struct vm_area_struct *vma,
.uffd_ctx = vma_->vm_userfaultfd_ctx, \
.anon_name = anon_vma_name(vma_), \
.state = VMA_MERGE_START, \
+ .merge_flags = VMG_FLAG_DEFAULT, \
}
#ifdef CONFIG_DEBUG_VM_MAPLE_TREE
@@ -241,15 +255,9 @@ static inline void vms_abort_munmap_vmas(struct vma_munmap_struct *vms,
* failure method of leaving a gap where the MAP_FIXED mapping failed.
*/
mas_set_range(mas, vms->start, vms->end - 1);
- if (unlikely(mas_store_gfp(mas, NULL, GFP_KERNEL))) {
- pr_warn_once("%s: (%d) Unable to abort munmap() operation\n",
- current->comm, current->pid);
- /* Leaving vmas detached and in-tree may hamper recovery */
- reattach_vmas(mas_detach);
- } else {
- /* Clean up the insertion of the unfortunate gap */
- vms_complete_munmap_vmas(vms, mas_detach);
- }
+ mas_store_gfp(mas, NULL, GFP_KERNEL|__GFP_NOFAIL);
+ /* Clean up the insertion of the unfortunate gap */
+ vms_complete_munmap_vmas(vms, mas_detach);
}
int
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index ae7a581..c0203a2 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -206,6 +206,12 @@ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen,
return ERR_PTR(err);
}
+ /* If command return a status event skb will be set to NULL as there are
+ * no parameters.
+ */
+ if (!skb)
+ return ERR_PTR(-ENODATA);
+
return skb;
}
EXPORT_SYMBOL(__hci_cmd_sync_sk);
@@ -255,6 +261,11 @@ int __hci_cmd_sync_status_sk(struct hci_dev *hdev, u16 opcode, u32 plen,
u8 status;
skb = __hci_cmd_sync_sk(hdev, opcode, plen, param, event, timeout, sk);
+
+ /* If command return a status event, skb will be set to -ENODATA */
+ if (skb == ERR_PTR(-ENODATA))
+ return 0;
+
if (IS_ERR(skb)) {
if (!event)
bt_dev_err(hdev, "Opcode 0x%4.4x failed: %ld", opcode,
@@ -262,13 +273,6 @@ int __hci_cmd_sync_status_sk(struct hci_dev *hdev, u16 opcode, u32 plen,
return PTR_ERR(skb);
}
- /* If command return a status event skb will be set to NULL as there are
- * no parameters, in case of failure IS_ERR(skb) would have be set to
- * the actual error would be found with PTR_ERR(skb).
- */
- if (!skb)
- return 0;
-
status = skb->data[0];
kfree_skb(skb);
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 6d7a442..501ec42 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -246,6 +246,7 @@ static void reset_ctx(struct xdp_page_head *head)
head->ctx.data_meta = head->orig_ctx.data_meta;
head->ctx.data_end = head->orig_ctx.data_end;
xdp_update_frame_from_buff(&head->ctx, head->frame);
+ head->frame->mem = head->orig_ctx.rxq->mem;
}
static int xdp_recv_frames(struct xdp_frame **frames, int nframes,
diff --git a/net/core/dev.c b/net/core/dev.c
index ea5fbcd..8453e14 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3639,6 +3639,9 @@ int skb_csum_hwoffload_help(struct sk_buff *skb,
return 0;
if (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) {
+ if (vlan_get_protocol(skb) == htons(ETH_P_IPV6) &&
+ skb_network_header_len(skb) != sizeof(struct ipv6hdr))
+ goto sw_checksum;
switch (skb->csum_offset) {
case offsetof(struct tcphdr, check):
case offsetof(struct udphdr, check):
@@ -3646,6 +3649,7 @@ int skb_csum_hwoffload_help(struct sk_buff *skb,
}
}
+sw_checksum:
return skb_checksum_help(skb);
}
EXPORT_SYMBOL(skb_csum_hwoffload_help);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e30e7ea..2ba5cd9 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2032,7 +2032,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 },
[IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 },
[IFLA_GSO_MAX_SEGS] = { .type = NLA_U32 },
- [IFLA_GSO_MAX_SIZE] = { .type = NLA_U32 },
+ [IFLA_GSO_MAX_SIZE] = NLA_POLICY_MIN(NLA_U32, MAX_TCP_HEADER + 1),
[IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
[IFLA_CARRIER_CHANGES] = { .type = NLA_U32 }, /* ignored */
[IFLA_PHYS_SWITCH_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
@@ -2057,7 +2057,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_TSO_MAX_SIZE] = { .type = NLA_REJECT },
[IFLA_TSO_MAX_SEGS] = { .type = NLA_REJECT },
[IFLA_ALLMULTI] = { .type = NLA_REJECT },
- [IFLA_GSO_IPV4_MAX_SIZE] = { .type = NLA_U32 },
+ [IFLA_GSO_IPV4_MAX_SIZE] = NLA_POLICY_MIN(NLA_U32, MAX_TCP_HEADER + 1),
[IFLA_GRO_IPV4_MAX_SIZE] = { .type = NLA_U32 },
};
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 07d6aa4..78347d7 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -1760,6 +1760,10 @@ static int sock_map_link_update_prog(struct bpf_link *link,
ret = -EINVAL;
goto out;
}
+ if (!sockmap_link->map) {
+ ret = -ENOLINK;
+ goto out;
+ }
ret = sock_map_prog_link_lookup(sockmap_link->map, &pprog, &plink,
sockmap_link->attach_type);
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index d591c73..25505f9 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -218,7 +218,7 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn,
ip_tunnel_flags_copy(flags, parms->i_flags);
- hlist_for_each_entry_rcu(t, head, hash_node) {
+ hlist_for_each_entry_rcu(t, head, hash_node, lockdep_rtnl_is_held()) {
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr &&
link == READ_ONCE(t->parms.link) &&
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index e7658c5..370993c 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -221,11 +221,11 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk,
int flags,
int *addr_len)
{
- struct tcp_sock *tcp = tcp_sk(sk);
int peek = flags & MSG_PEEK;
- u32 seq = tcp->copied_seq;
struct sk_psock *psock;
+ struct tcp_sock *tcp;
int copied = 0;
+ u32 seq;
if (unlikely(flags & MSG_ERRQUEUE))
return inet_recv_error(sk, msg, len, addr_len);
@@ -238,7 +238,8 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk,
return tcp_recvmsg(sk, msg, len, flags, addr_len);
lock_sock(sk);
-
+ tcp = tcp_sk(sk);
+ seq = tcp->copied_seq;
/* We may have received data on the sk_receive_queue pre-accept and
* then we can not use read_skb in this context because we haven't
* assigned a sk_socket yet so have no link to the ops. The work-around
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index 7db0437..9ae2b27 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -268,12 +268,12 @@ static int nf_reject6_fill_skb_dst(struct sk_buff *skb_in)
void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
int hook)
{
- struct sk_buff *nskb;
- struct tcphdr _otcph;
- const struct tcphdr *otcph;
- unsigned int otcplen, hh_len;
const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
struct dst_entry *dst = NULL;
+ const struct tcphdr *otcph;
+ struct sk_buff *nskb;
+ struct tcphdr _otcph;
+ unsigned int otcplen;
struct flowi6 fl6;
if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
@@ -312,9 +312,8 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
if (IS_ERR(dst))
return;
- hh_len = (dst->dev->hard_header_len + 15)&~15;
- nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr)
- + sizeof(struct tcphdr) + dst->trailer_len,
+ nskb = alloc_skb(LL_MAX_HEADER + sizeof(struct ipv6hdr) +
+ sizeof(struct tcphdr) + dst->trailer_len,
GFP_ATOMIC);
if (!nskb) {
@@ -327,7 +326,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
nskb->mark = fl6.flowi6_mark;
- skb_reserve(nskb, hh_len + dst->header_len);
+ skb_reserve(nskb, LL_MAX_HEADER);
nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP, ip6_dst_hoplimit(dst));
nf_reject_ip6_tcphdr_put(nskb, oldskb, otcph, otcplen);
diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig
index 13438cc..cf0f778 100644
--- a/net/mac80211/Kconfig
+++ b/net/mac80211/Kconfig
@@ -96,7 +96,7 @@
config MAC80211_MESSAGE_TRACING
bool "Trace all mac80211 debug messages"
- depends on MAC80211
+ depends on MAC80211 && TRACING
help
Select this option to have mac80211 register the
mac80211_msg trace subsystem with tracepoints to
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 847304a..6dfc61a 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -3046,6 +3046,7 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
enum nl80211_tx_power_setting txp_type = type;
bool update_txp_type = false;
bool has_monitor = false;
+ int old_power = local->user_power_level;
lockdep_assert_wiphy(local->hw.wiphy);
@@ -3128,6 +3129,10 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
}
}
+ if (local->emulate_chanctx &&
+ (old_power != local->user_power_level))
+ ieee80211_hw_conf_chan(local);
+
return 0;
}
@@ -3138,7 +3143,8 @@ static int ieee80211_get_tx_power(struct wiphy *wiphy,
struct ieee80211_local *local = wiphy_priv(wiphy);
struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
- if (local->ops->get_txpower)
+ if (local->ops->get_txpower &&
+ (sdata->flags & IEEE80211_SDATA_IN_DRIVER))
return drv_get_txpower(local, sdata, dbm);
if (local->emulate_chanctx)
@@ -4826,12 +4832,12 @@ void ieee80211_color_change_finalize_work(struct wiphy *wiphy,
ieee80211_color_change_finalize(link);
}
-void ieee80211_color_collision_detection_work(struct work_struct *work)
+void ieee80211_color_collision_detection_work(struct wiphy *wiphy,
+ struct wiphy_work *work)
{
- struct delayed_work *delayed_work = to_delayed_work(work);
struct ieee80211_link_data *link =
- container_of(delayed_work, struct ieee80211_link_data,
- color_collision_detect_work);
+ container_of(work, struct ieee80211_link_data,
+ color_collision_detect_work.work);
struct ieee80211_sub_if_data *sdata = link->sdata;
cfg80211_obss_color_collision_notify(sdata->dev, link->color_bitmap,
@@ -4884,7 +4890,8 @@ ieee80211_obss_color_collision_notify(struct ieee80211_vif *vif,
return;
}
- if (delayed_work_pending(&link->color_collision_detect_work)) {
+ if (wiphy_delayed_work_pending(sdata->local->hw.wiphy,
+ &link->color_collision_detect_work)) {
rcu_read_unlock();
return;
}
@@ -4893,9 +4900,9 @@ ieee80211_obss_color_collision_notify(struct ieee80211_vif *vif,
/* queue the color collision detection event every 500 ms in order to
* avoid sending too much netlink messages to userspace.
*/
- ieee80211_queue_delayed_work(&sdata->local->hw,
- &link->color_collision_detect_work,
- msecs_to_jiffies(500));
+ wiphy_delayed_work_queue(sdata->local->hw.wiphy,
+ &link->color_collision_detect_work,
+ msecs_to_jiffies(500));
rcu_read_unlock();
}
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 4f03909..3d3c913 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -892,9 +892,10 @@ struct ieee80211_chanctx {
/* temporary data for search algorithm etc. */
struct ieee80211_chan_req req;
- struct ieee80211_chanctx_conf conf;
-
bool radar_detected;
+
+ /* MUST be last - ends in a flexible-array member. */
+ struct ieee80211_chanctx_conf conf;
};
struct mac80211_qos_map {
@@ -1053,7 +1054,7 @@ struct ieee80211_link_data {
} csa;
struct wiphy_work color_change_finalize_work;
- struct delayed_work color_collision_detect_work;
+ struct wiphy_delayed_work color_collision_detect_work;
u64 color_bitmap;
/* context reservation -- protected with wiphy mutex */
@@ -2005,7 +2006,8 @@ int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
/* color change handling */
void ieee80211_color_change_finalize_work(struct wiphy *wiphy,
struct wiphy_work *work);
-void ieee80211_color_collision_detection_work(struct work_struct *work);
+void ieee80211_color_collision_detection_work(struct wiphy *wiphy,
+ struct wiphy_work *work);
/* interface handling */
#define MAC80211_SUPPORTED_FEATURES_TX (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | \
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 6fac3ba..67ecfea 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -987,6 +987,26 @@ void ieee80211_reenable_keys(struct ieee80211_sub_if_data *sdata)
}
}
+static void
+ieee80211_key_iter(struct ieee80211_hw *hw,
+ struct ieee80211_vif *vif,
+ struct ieee80211_key *key,
+ void (*iter)(struct ieee80211_hw *hw,
+ struct ieee80211_vif *vif,
+ struct ieee80211_sta *sta,
+ struct ieee80211_key_conf *key,
+ void *data),
+ void *iter_data)
+{
+ /* skip keys of station in removal process */
+ if (key->sta && key->sta->removed)
+ return;
+ if (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE))
+ return;
+ iter(hw, vif, key->sta ? &key->sta->sta : NULL,
+ &key->conf, iter_data);
+}
+
void ieee80211_iter_keys(struct ieee80211_hw *hw,
struct ieee80211_vif *vif,
void (*iter)(struct ieee80211_hw *hw,
@@ -1005,16 +1025,13 @@ void ieee80211_iter_keys(struct ieee80211_hw *hw,
if (vif) {
sdata = vif_to_sdata(vif);
list_for_each_entry_safe(key, tmp, &sdata->key_list, list)
- iter(hw, &sdata->vif,
- key->sta ? &key->sta->sta : NULL,
- &key->conf, iter_data);
+ ieee80211_key_iter(hw, vif, key, iter, iter_data);
} else {
list_for_each_entry(sdata, &local->interfaces, list)
list_for_each_entry_safe(key, tmp,
&sdata->key_list, list)
- iter(hw, &sdata->vif,
- key->sta ? &key->sta->sta : NULL,
- &key->conf, iter_data);
+ ieee80211_key_iter(hw, &sdata->vif, key,
+ iter, iter_data);
}
}
EXPORT_SYMBOL(ieee80211_iter_keys);
@@ -1031,17 +1048,8 @@ _ieee80211_iter_keys_rcu(struct ieee80211_hw *hw,
{
struct ieee80211_key *key;
- list_for_each_entry_rcu(key, &sdata->key_list, list) {
- /* skip keys of station in removal process */
- if (key->sta && key->sta->removed)
- continue;
- if (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE))
- continue;
-
- iter(hw, &sdata->vif,
- key->sta ? &key->sta->sta : NULL,
- &key->conf, iter_data);
- }
+ list_for_each_entry_rcu(key, &sdata->key_list, list)
+ ieee80211_key_iter(hw, &sdata->vif, key, iter, iter_data);
}
void ieee80211_iter_keys_rcu(struct ieee80211_hw *hw,
diff --git a/net/mac80211/link.c b/net/mac80211/link.c
index 0bbac64..46092fb 100644
--- a/net/mac80211/link.c
+++ b/net/mac80211/link.c
@@ -41,8 +41,8 @@ void ieee80211_link_init(struct ieee80211_sub_if_data *sdata,
ieee80211_csa_finalize_work);
wiphy_work_init(&link->color_change_finalize_work,
ieee80211_color_change_finalize_work);
- INIT_DELAYED_WORK(&link->color_collision_detect_work,
- ieee80211_color_collision_detection_work);
+ wiphy_delayed_work_init(&link->color_collision_detect_work,
+ ieee80211_color_collision_detection_work);
INIT_LIST_HEAD(&link->assigned_chanctx_list);
INIT_LIST_HEAD(&link->reserved_chanctx_list);
wiphy_delayed_work_init(&link->dfs_cac_timer_work,
@@ -72,7 +72,8 @@ void ieee80211_link_stop(struct ieee80211_link_data *link)
if (link->sdata->vif.type == NL80211_IFTYPE_STATION)
ieee80211_mgd_stop_link(link);
- cancel_delayed_work_sync(&link->color_collision_detect_work);
+ wiphy_delayed_work_cancel(link->sdata->local->hw.wiphy,
+ &link->color_collision_detect_work);
wiphy_work_cancel(link->sdata->local->hw.wiphy,
&link->color_change_finalize_work);
wiphy_work_cancel(link->sdata->local->hw.wiphy,
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 8908469..ee1211a 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -167,6 +167,8 @@ static u32 ieee80211_calc_hw_conf_chan(struct ieee80211_local *local,
}
power = ieee80211_chandef_max_power(&chandef);
+ if (local->user_power_level != IEEE80211_UNSET_POWER_LEVEL)
+ power = min(local->user_power_level, power);
rcu_read_lock();
list_for_each_entry_rcu(sdata, &local->interfaces, list) {
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 6d0e201..d263091 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2864,8 +2864,10 @@ static int mptcp_init_sock(struct sock *sk)
if (unlikely(!net->mib.mptcp_statistics) && !mptcp_mib_alloc(net))
return -ENOMEM;
+ rcu_read_lock();
ret = mptcp_init_sched(mptcp_sk(sk),
mptcp_sched_find(mptcp_get_scheduler(net)));
+ rcu_read_unlock();
if (ret)
return ret;
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 330609a..7dfc534 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -904,6 +904,9 @@ static void nft_payload_set_eval(const struct nft_expr *expr,
((priv->base != NFT_PAYLOAD_TRANSPORT_HEADER &&
priv->base != NFT_PAYLOAD_INNER_HEADER) ||
skb->ip_summed != CHECKSUM_PARTIAL)) {
+ if (offset + priv->len > skb->len)
+ goto err;
+
fsum = skb_checksum(skb, offset, priv->len, 0);
tsum = csum_partial(src, priv->len, 0);
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index da5d929..7098406 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1269,7 +1269,7 @@ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af,
/* and once again: */
list_for_each_entry(t, &xt_net->tables[af], list)
- if (strcmp(t->name, name) == 0)
+ if (strcmp(t->name, name) == 0 && owner == t->me)
return t;
module_put(owner);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 17d97bb..bbc778c 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1518,6 +1518,7 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
return 0;
err_dev_insert:
+ tcf_block_offload_unbind(block, q, ei);
err_block_offload_bind:
tcf_chain0_head_change_cb_del(block, ei);
err_chain0_head_change_cb_add:
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 2eefa47..a1d27bc 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -791,7 +791,7 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len)
drops = max_t(int, n, 0);
rcu_read_lock();
while ((parentid = sch->parent)) {
- if (TC_H_MAJ(parentid) == TC_H_MAJ(TC_H_INGRESS))
+ if (parentid == TC_H_ROOT)
break;
if (sch->flags & TCQ_F_NOPARENT)
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 661adfc..74ca188 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1236,6 +1236,7 @@ static void _cfg80211_unregister_wdev(struct wireless_dev *wdev,
/* deleted from the list, so can't be found from nl80211 any more */
cqm_config = rcu_access_pointer(wdev->cqm_config);
kfree_rcu(cqm_config, rcu_head);
+ RCU_INIT_POINTER(wdev->cqm_config, NULL);
/*
* Ensure that all events have been processed and
@@ -1704,6 +1705,13 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy,
}
EXPORT_SYMBOL_GPL(wiphy_delayed_work_flush);
+bool wiphy_delayed_work_pending(struct wiphy *wiphy,
+ struct wiphy_delayed_work *dwork)
+{
+ return timer_pending(&dwork->timer);
+}
+EXPORT_SYMBOL_GPL(wiphy_delayed_work_pending);
+
static int __init cfg80211_init(void)
{
int err;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 59a90bf..d0aed41 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -3050,6 +3050,10 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy,
freq = ieee80211_channel_to_freq_khz(ap_info->channel, band);
data.channel = ieee80211_get_channel_khz(wiphy, freq);
+ /* Skip if RNR element specifies an unsupported channel */
+ if (!data.channel)
+ continue;
+
/* Skip if BSS entry generated from MBSSID or DIRECT source
* frame data available already.
*/
diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c
index f018bd7..9f849e0 100644
--- a/sound/hda/intel-dsp-config.c
+++ b/sound/hda/intel-dsp-config.c
@@ -723,6 +723,10 @@ static const struct config_entry acpi_config_table[] = {
/* BayTrail */
{
.flags = FLAG_SST_OR_SOF_BYT,
+ .acpi_hid = "LPE0F28",
+ },
+ {
+ .flags = FLAG_SST_OR_SOF_BYT,
.acpi_hid = "80860F28",
},
/* CherryTrail */
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 3567b14..571fa8a 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -7521,6 +7521,7 @@ enum {
ALC286_FIXUP_SONY_MIC_NO_PRESENCE,
ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT,
ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+ ALC269_FIXUP_DELL1_LIMIT_INT_MIC_BOOST,
ALC269_FIXUP_DELL2_MIC_NO_PRESENCE,
ALC269_FIXUP_DELL3_MIC_NO_PRESENCE,
ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
@@ -7551,10 +7552,12 @@ enum {
ALC290_FIXUP_SUBWOOFER_HSJACK,
ALC269_FIXUP_THINKPAD_ACPI,
ALC269_FIXUP_DMIC_THINKPAD_ACPI,
+ ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13,
ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO,
ALC255_FIXUP_ACER_MIC_NO_PRESENCE,
ALC255_FIXUP_ASUS_MIC_NO_PRESENCE,
ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+ ALC255_FIXUP_DELL1_LIMIT_INT_MIC_BOOST,
ALC255_FIXUP_DELL2_MIC_NO_PRESENCE,
ALC255_FIXUP_HEADSET_MODE,
ALC255_FIXUP_HEADSET_MODE_NO_HP_MIC,
@@ -7996,6 +7999,16 @@ static const struct hda_fixup alc269_fixups[] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc269_fixup_pincfg_U7x7_headset_mic,
},
+ [ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x14, 0x90170151 }, /* use as internal speaker (LFE) */
+ { 0x1b, 0x90170152 }, /* use as internal speaker (back) */
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC269_FIXUP_LIMIT_INT_MIC_BOOST
+ },
[ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO] = {
.type = HDA_FIXUP_PINS,
.v.pins = (const struct hda_pintbl[]) {
@@ -8114,6 +8127,12 @@ static const struct hda_fixup alc269_fixups[] = {
.chained = true,
.chain_id = ALC269_FIXUP_HEADSET_MODE
},
+ [ALC269_FIXUP_DELL1_LIMIT_INT_MIC_BOOST] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc269_fixup_limit_int_mic_boost,
+ .chained = true,
+ .chain_id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE
+ },
[ALC269_FIXUP_DELL2_MIC_NO_PRESENCE] = {
.type = HDA_FIXUP_PINS,
.v.pins = (const struct hda_pintbl[]) {
@@ -8394,6 +8413,12 @@ static const struct hda_fixup alc269_fixups[] = {
.chained = true,
.chain_id = ALC255_FIXUP_HEADSET_MODE
},
+ [ALC255_FIXUP_DELL1_LIMIT_INT_MIC_BOOST] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc269_fixup_limit_int_mic_boost,
+ .chained = true,
+ .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE
+ },
[ALC255_FIXUP_DELL2_MIC_NO_PRESENCE] = {
.type = HDA_FIXUP_PINS,
.v.pins = (const struct hda_pintbl[]) {
@@ -10725,6 +10750,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1558, 0x1404, "Clevo N150CU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1558, 0x14a1, "Clevo L141MU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1558, 0x2624, "Clevo L240TU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x28c1, "Clevo V370VND", ALC2XX_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x1558, 0x4018, "Clevo NV40M[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1558, 0x4019, "Clevo NV40MZ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1558, 0x4020, "Clevo NV40MB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
@@ -10982,6 +11008,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1d05, 0x115c, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP),
SND_PCI_QUIRK(0x1d05, 0x121b, "TongFang GMxAGxx", ALC269_FIXUP_NO_SHUTUP),
SND_PCI_QUIRK(0x1d05, 0x1387, "TongFang GMxIXxx", ALC2XX_FIXUP_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1d05, 0x1409, "TongFang GMxIXxx", ALC2XX_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x1d17, 0x3288, "Haier Boyue G42", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS),
SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE),
@@ -10989,6 +11016,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC),
SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
SND_PCI_QUIRK(0x2782, 0x0214, "VAIO VJFE-CL", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+ SND_PCI_QUIRK(0x2782, 0x0228, "Infinix ZERO BOOK 13", ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13),
SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO),
SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME),
SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC),
@@ -11076,6 +11104,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
{.id = ALC269_FIXUP_DELL2_MIC_NO_PRESENCE, .name = "dell-headset-dock"},
{.id = ALC269_FIXUP_DELL3_MIC_NO_PRESENCE, .name = "dell-headset3"},
{.id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, .name = "dell-headset4"},
+ {.id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE_QUIET, .name = "dell-headset4-quiet"},
{.id = ALC283_FIXUP_CHROME_BOOK, .name = "alc283-dac-wcaps"},
{.id = ALC283_FIXUP_SENSE_COMBO_JACK, .name = "alc283-sense-combo"},
{.id = ALC292_FIXUP_TPT440_DOCK, .name = "tpt440-dock"},
@@ -11630,16 +11659,16 @@ static const struct snd_hda_pin_quirk alc269_fallback_pin_fixup_tbl[] = {
SND_HDA_PIN_QUIRK(0x10ec0289, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
{0x19, 0x40000000},
{0x1b, 0x40000000}),
- SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
+ SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE_QUIET,
{0x19, 0x40000000},
{0x1b, 0x40000000}),
SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
{0x19, 0x40000000},
{0x1a, 0x40000000}),
- SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+ SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_LIMIT_INT_MIC_BOOST,
{0x19, 0x40000000},
{0x1a, 0x40000000}),
- SND_HDA_PIN_QUIRK(0x10ec0274, 0x1028, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB,
+ SND_HDA_PIN_QUIRK(0x10ec0274, 0x1028, "Dell", ALC269_FIXUP_DELL1_LIMIT_INT_MIC_BOOST,
{0x19, 0x40000000},
{0x1a, 0x40000000}),
SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC2XX_FIXUP_HEADSET_MIC,
diff --git a/sound/soc/codecs/cs42l51.c b/sound/soc/codecs/cs42l51.c
index e4827b8..6e51954 100644
--- a/sound/soc/codecs/cs42l51.c
+++ b/sound/soc/codecs/cs42l51.c
@@ -747,8 +747,10 @@ int cs42l51_probe(struct device *dev, struct regmap *regmap)
cs42l51->reset_gpio = devm_gpiod_get_optional(dev, "reset",
GPIOD_OUT_LOW);
- if (IS_ERR(cs42l51->reset_gpio))
- return PTR_ERR(cs42l51->reset_gpio);
+ if (IS_ERR(cs42l51->reset_gpio)) {
+ ret = PTR_ERR(cs42l51->reset_gpio);
+ goto error;
+ }
if (cs42l51->reset_gpio) {
dev_dbg(dev, "Release reset gpio\n");
@@ -780,6 +782,7 @@ int cs42l51_probe(struct device *dev, struct regmap *regmap)
return 0;
error:
+ gpiod_set_value_cansleep(cs42l51->reset_gpio, 1);
regulator_bulk_disable(ARRAY_SIZE(cs42l51->supplies),
cs42l51->supplies);
return ret;
diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c
index 16f3425..8551393 100644
--- a/sound/soc/codecs/rt5640.c
+++ b/sound/soc/codecs/rt5640.c
@@ -2419,10 +2419,20 @@ static irqreturn_t rt5640_jd_gpio_irq(int irq, void *data)
return IRQ_HANDLED;
}
-static void rt5640_cancel_work(void *data)
+static void rt5640_disable_irq_and_cancel_work(void *data)
{
struct rt5640_priv *rt5640 = data;
+ if (rt5640->jd_gpio_irq_requested) {
+ free_irq(rt5640->jd_gpio_irq, rt5640);
+ rt5640->jd_gpio_irq_requested = false;
+ }
+
+ if (rt5640->irq_requested) {
+ free_irq(rt5640->irq, rt5640);
+ rt5640->irq_requested = false;
+ }
+
cancel_delayed_work_sync(&rt5640->jack_work);
cancel_delayed_work_sync(&rt5640->bp_work);
}
@@ -2463,13 +2473,7 @@ static void rt5640_disable_jack_detect(struct snd_soc_component *component)
if (!rt5640->jack)
return;
- if (rt5640->jd_gpio_irq_requested)
- free_irq(rt5640->jd_gpio_irq, rt5640);
-
- if (rt5640->irq_requested)
- free_irq(rt5640->irq, rt5640);
-
- rt5640_cancel_work(rt5640);
+ rt5640_disable_irq_and_cancel_work(rt5640);
if (rt5640->jack->status & SND_JACK_MICROPHONE) {
rt5640_disable_micbias1_ovcd_irq(component);
@@ -2477,8 +2481,6 @@ static void rt5640_disable_jack_detect(struct snd_soc_component *component)
snd_soc_jack_report(rt5640->jack, 0, SND_JACK_BTN_0);
}
- rt5640->jd_gpio_irq_requested = false;
- rt5640->irq_requested = false;
rt5640->jd_gpio = NULL;
rt5640->jack = NULL;
}
@@ -2798,7 +2800,8 @@ static int rt5640_suspend(struct snd_soc_component *component)
if (rt5640->jack) {
/* disable jack interrupts during system suspend */
disable_irq(rt5640->irq);
- rt5640_cancel_work(rt5640);
+ cancel_delayed_work_sync(&rt5640->jack_work);
+ cancel_delayed_work_sync(&rt5640->bp_work);
}
snd_soc_component_force_bias_level(component, SND_SOC_BIAS_OFF);
@@ -3032,7 +3035,7 @@ static int rt5640_i2c_probe(struct i2c_client *i2c)
INIT_DELAYED_WORK(&rt5640->jack_work, rt5640_jack_work);
/* Make sure work is stopped on probe-error / remove */
- ret = devm_add_action_or_reset(&i2c->dev, rt5640_cancel_work, rt5640);
+ ret = devm_add_action_or_reset(&i2c->dev, rt5640_disable_irq_and_cancel_work, rt5640);
if (ret)
return ret;
diff --git a/sound/soc/codecs/wcd937x.c b/sound/soc/codecs/wcd937x.c
index 45f32d2..08fb13a 100644
--- a/sound/soc/codecs/wcd937x.c
+++ b/sound/soc/codecs/wcd937x.c
@@ -715,12 +715,17 @@ static int wcd937x_codec_enable_aux_pa(struct snd_soc_dapm_widget *w,
struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
struct wcd937x_priv *wcd937x = snd_soc_component_get_drvdata(component);
int hph_mode = wcd937x->hph_mode;
+ u8 val;
switch (event) {
case SND_SOC_DAPM_PRE_PMU:
+ val = WCD937X_DIGITAL_PDM_WD_CTL2_EN |
+ WCD937X_DIGITAL_PDM_WD_CTL2_TIMEOUT_SEL |
+ WCD937X_DIGITAL_PDM_WD_CTL2_HOLD_OFF;
snd_soc_component_update_bits(component,
WCD937X_DIGITAL_PDM_WD_CTL2,
- BIT(0), BIT(0));
+ WCD937X_DIGITAL_PDM_WD_CTL2_MASK,
+ val);
break;
case SND_SOC_DAPM_POST_PMU:
usleep_range(1000, 1010);
@@ -741,7 +746,8 @@ static int wcd937x_codec_enable_aux_pa(struct snd_soc_dapm_widget *w,
hph_mode);
snd_soc_component_update_bits(component,
WCD937X_DIGITAL_PDM_WD_CTL2,
- BIT(0), 0x00);
+ WCD937X_DIGITAL_PDM_WD_CTL2_MASK,
+ 0x00);
break;
}
@@ -2049,6 +2055,8 @@ static const struct snd_kcontrol_new wcd937x_snd_controls[] = {
wcd937x_get_swr_port, wcd937x_set_swr_port),
SOC_SINGLE_EXT("HPHR Switch", WCD937X_HPH_R, 0, 1, 0,
wcd937x_get_swr_port, wcd937x_set_swr_port),
+ SOC_SINGLE_EXT("LO Switch", WCD937X_LO, 0, 1, 0,
+ wcd937x_get_swr_port, wcd937x_set_swr_port),
SOC_SINGLE_EXT("ADC1 Switch", WCD937X_ADC1, 1, 1, 0,
wcd937x_get_swr_port, wcd937x_set_swr_port),
diff --git a/sound/soc/codecs/wcd937x.h b/sound/soc/codecs/wcd937x.h
index 35f3d48..4afa48dc 100644
--- a/sound/soc/codecs/wcd937x.h
+++ b/sound/soc/codecs/wcd937x.h
@@ -391,6 +391,10 @@
#define WCD937X_DIGITAL_PDM_WD_CTL0 0x3465
#define WCD937X_DIGITAL_PDM_WD_CTL1 0x3466
#define WCD937X_DIGITAL_PDM_WD_CTL2 0x3467
+#define WCD937X_DIGITAL_PDM_WD_CTL2_HOLD_OFF BIT(2)
+#define WCD937X_DIGITAL_PDM_WD_CTL2_TIMEOUT_SEL BIT(1)
+#define WCD937X_DIGITAL_PDM_WD_CTL2_EN BIT(0)
+#define WCD937X_DIGITAL_PDM_WD_CTL2_MASK GENMASK(2, 0)
#define WCD937X_DIGITAL_INTR_MODE 0x346A
#define WCD937X_DIGITAL_INTR_MASK_0 0x346B
#define WCD937X_DIGITAL_INTR_MASK_1 0x346C
diff --git a/sound/soc/intel/atom/sst/sst_acpi.c b/sound/soc/intel/atom/sst/sst_acpi.c
index 9956dc6..2571806 100644
--- a/sound/soc/intel/atom/sst/sst_acpi.c
+++ b/sound/soc/intel/atom/sst/sst_acpi.c
@@ -125,6 +125,28 @@ static const struct sst_res_info bytcr_res_info = {
.acpi_ipc_irq_index = 0
};
+/* For "LPE0F28" ACPI device found on some Android factory OS models */
+static const struct sst_res_info lpe8086_res_info = {
+ .shim_offset = 0x140000,
+ .shim_size = 0x000100,
+ .shim_phy_addr = SST_BYT_SHIM_PHY_ADDR,
+ .ssp0_offset = 0xa0000,
+ .ssp0_size = 0x1000,
+ .dma0_offset = 0x98000,
+ .dma0_size = 0x4000,
+ .dma1_offset = 0x9c000,
+ .dma1_size = 0x4000,
+ .iram_offset = 0x0c0000,
+ .iram_size = 0x14000,
+ .dram_offset = 0x100000,
+ .dram_size = 0x28000,
+ .mbox_offset = 0x144000,
+ .mbox_size = 0x1000,
+ .acpi_lpe_res_index = 1,
+ .acpi_ddr_index = 0,
+ .acpi_ipc_irq_index = 0
+};
+
static struct sst_platform_info byt_rvp_platform_data = {
.probe_data = &byt_fwparse_info,
.ipc_info = &byt_ipc_info,
@@ -268,10 +290,38 @@ static int sst_acpi_probe(struct platform_device *pdev)
mach->pdata = &chv_platform_data;
pdata = mach->pdata;
- ret = kstrtouint(id->id, 16, &dev_id);
- if (ret < 0) {
- dev_err(dev, "Unique device id conversion error: %d\n", ret);
- return ret;
+ if (!strcmp(id->id, "LPE0F28")) {
+ struct resource *rsrc;
+
+ /* Use regular BYT SST PCI VID:PID */
+ dev_id = 0x80860F28;
+ byt_rvp_platform_data.res_info = &lpe8086_res_info;
+
+ /*
+ * The "LPE0F28" ACPI device has separate IO-mem resources for:
+ * DDR, SHIM, MBOX, IRAM, DRAM, CFG
+ * None of which covers the entire LPE base address range.
+ * lpe8086_res_info.acpi_lpe_res_index points to the SHIM.
+ * Patch this to cover the entire base address range as expected
+ * by sst_platform_get_resources().
+ */
+ rsrc = platform_get_resource(pdev, IORESOURCE_MEM,
+ pdata->res_info->acpi_lpe_res_index);
+ if (!rsrc) {
+ dev_err(dev, "Invalid SHIM base\n");
+ return -EIO;
+ }
+ rsrc->start -= pdata->res_info->shim_offset;
+ rsrc->end = rsrc->start + 0x200000 - 1;
+ } else {
+ ret = kstrtouint(id->id, 16, &dev_id);
+ if (ret < 0) {
+ dev_err(dev, "Unique device id conversion error: %d\n", ret);
+ return ret;
+ }
+
+ if (soc_intel_is_byt_cr(pdev))
+ byt_rvp_platform_data.res_info = &bytcr_res_info;
}
dev_dbg(dev, "ACPI device id: %x\n", dev_id);
@@ -280,11 +330,6 @@ static int sst_acpi_probe(struct platform_device *pdev)
if (ret < 0)
return ret;
- if (soc_intel_is_byt_cr(pdev)) {
- /* override resource info */
- byt_rvp_platform_data.res_info = &bytcr_res_info;
- }
-
/* update machine parameters */
mach->mach_params.acpi_ipc_irq_index =
pdata->res_info->acpi_ipc_irq_index;
@@ -344,6 +389,7 @@ static void sst_acpi_remove(struct platform_device *pdev)
}
static const struct acpi_device_id sst_acpi_ids[] = {
+ { "LPE0F28", (unsigned long)&snd_soc_acpi_intel_baytrail_machines},
{ "80860F28", (unsigned long)&snd_soc_acpi_intel_baytrail_machines},
{ "808622A8", (unsigned long)&snd_soc_acpi_intel_cherrytrail_machines},
{ },
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 2ed49ac..54f77f5 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -17,6 +17,7 @@
#include <linux/acpi.h>
#include <linux/clk.h>
#include <linux/device.h>
+#include <linux/device/bus.h>
#include <linux/dmi.h>
#include <linux/gpio/consumer.h>
#include <linux/gpio/machine.h>
@@ -32,6 +33,8 @@
#include "../atom/sst-atom-controls.h"
#include "../common/soc-intel-quirks.h"
+#define BYT_RT5640_FALLBACK_CODEC_DEV_NAME "i2c-rt5640"
+
enum {
BYT_RT5640_DMIC1_MAP,
BYT_RT5640_DMIC2_MAP,
@@ -1129,6 +1132,21 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
BYT_RT5640_SSP0_AIF2 |
BYT_RT5640_MCLK_EN),
},
+ { /* Vexia Edu Atla 10 tablet */
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
+ DMI_MATCH(DMI_BOARD_NAME, "Aptio CRB"),
+ /* Above strings are too generic, also match on BIOS date */
+ DMI_MATCH(DMI_BIOS_DATE, "08/25/2014"),
+ },
+ .driver_data = (void *)(BYT_RT5640_IN1_MAP |
+ BYT_RT5640_JD_SRC_JD2_IN4N |
+ BYT_RT5640_OVCD_TH_2000UA |
+ BYT_RT5640_OVCD_SF_0P75 |
+ BYT_RT5640_DIFF_MIC |
+ BYT_RT5640_SSP0_AIF2 |
+ BYT_RT5640_MCLK_EN),
+ },
{ /* Voyo Winpad A15 */
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
@@ -1698,9 +1716,33 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
codec_dev = acpi_get_first_physical_node(adev);
acpi_dev_put(adev);
- if (!codec_dev)
- return -EPROBE_DEFER;
- priv->codec_dev = get_device(codec_dev);
+
+ if (codec_dev) {
+ priv->codec_dev = get_device(codec_dev);
+ } else {
+ /*
+ * Special case for Android tablets where the codec i2c_client
+ * has been manually instantiated by x86_android_tablets.ko due
+ * to a broken DSDT.
+ */
+ codec_dev = bus_find_device_by_name(&i2c_bus_type, NULL,
+ BYT_RT5640_FALLBACK_CODEC_DEV_NAME);
+ if (!codec_dev)
+ return -EPROBE_DEFER;
+
+ if (!i2c_verify_client(codec_dev)) {
+ dev_err(dev, "Error '%s' is not an i2c_client\n",
+ BYT_RT5640_FALLBACK_CODEC_DEV_NAME);
+ put_device(codec_dev);
+ }
+
+ /* fixup codec name */
+ strscpy(byt_rt5640_codec_name, BYT_RT5640_FALLBACK_CODEC_DEV_NAME,
+ sizeof(byt_rt5640_codec_name));
+
+ /* bus_find_device() returns a reference no need to get() */
+ priv->codec_dev = codec_dev;
+ }
/*
* swap SSP0 if bytcr is detected
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index c34934c..99521c7 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -1147,6 +1147,8 @@ static int dapm_widget_list_create(struct snd_soc_dapm_widget_list **list,
if (*list == NULL)
return -ENOMEM;
+ (*list)->num_widgets = size;
+
list_for_each_entry(w, widgets, work_list)
(*list)->widgets[i++] = w;
diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index 2a9594f..6456e87 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -4042,6 +4042,9 @@ int snd_usb_mixer_apply_create_quirk(struct usb_mixer_interface *mixer)
break;
err = dell_dock_mixer_init(mixer);
break;
+ case USB_ID(0x0bda, 0x402e): /* Dell WD19 dock */
+ err = dell_dock_mixer_create(mixer);
+ break;
case USB_ID(0x2a39, 0x3fd2): /* RME ADI-2 Pro */
case USB_ID(0x2a39, 0x3fd3): /* RME ADI-2 DAC */
diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h
index 5a7dfeb..488f8e7 100644
--- a/tools/arch/arm64/include/asm/cputype.h
+++ b/tools/arch/arm64/include/asm/cputype.h
@@ -94,6 +94,7 @@
#define ARM_CPU_PART_NEOVERSE_V3 0xD84
#define ARM_CPU_PART_CORTEX_X925 0xD85
#define ARM_CPU_PART_CORTEX_A725 0xD87
+#define ARM_CPU_PART_NEOVERSE_N3 0xD8E
#define APM_CPU_PART_XGENE 0x000
#define APM_CPU_VAR_POTENZA 0x00
@@ -176,6 +177,7 @@
#define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3)
#define MIDR_CORTEX_X925 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X925)
#define MIDR_CORTEX_A725 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A725)
+#define MIDR_NEOVERSE_N3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N3)
#define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
#define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index a7c06a4..3ae84c3 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -36,6 +36,20 @@
#define EFER_FFXSR (1<<_EFER_FFXSR)
#define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS)
+/*
+ * Architectural memory types that are common to MTRRs, PAT, VMX MSRs, etc.
+ * Most MSRs support/allow only a subset of memory types, but the values
+ * themselves are common across all relevant MSRs.
+ */
+#define X86_MEMTYPE_UC 0ull /* Uncacheable, a.k.a. Strong Uncacheable */
+#define X86_MEMTYPE_WC 1ull /* Write Combining */
+/* RESERVED 2 */
+/* RESERVED 3 */
+#define X86_MEMTYPE_WT 4ull /* Write Through */
+#define X86_MEMTYPE_WP 5ull /* Write Protected */
+#define X86_MEMTYPE_WB 6ull /* Write Back */
+#define X86_MEMTYPE_UC_MINUS 7ull /* Weak Uncacheabled (PAT only) */
+
/* FRED MSRs */
#define MSR_IA32_FRED_RSP0 0x1cc /* Level 0 stack pointer */
#define MSR_IA32_FRED_RSP1 0x1cd /* Level 1 stack pointer */
@@ -365,6 +379,12 @@
#define MSR_IA32_CR_PAT 0x00000277
+#define PAT_VALUE(p0, p1, p2, p3, p4, p5, p6, p7) \
+ ((X86_MEMTYPE_ ## p0) | (X86_MEMTYPE_ ## p1 << 8) | \
+ (X86_MEMTYPE_ ## p2 << 16) | (X86_MEMTYPE_ ## p3 << 24) | \
+ (X86_MEMTYPE_ ## p4 << 32) | (X86_MEMTYPE_ ## p5 << 40) | \
+ (X86_MEMTYPE_ ## p6 << 48) | (X86_MEMTYPE_ ## p7 << 56))
+
#define MSR_IA32_DEBUGCTLMSR 0x000001d9
#define MSR_IA32_LASTBRANCHFROMIP 0x000001db
#define MSR_IA32_LASTBRANCHTOIP 0x000001dc
@@ -1159,15 +1179,6 @@
#define MSR_IA32_VMX_VMFUNC 0x00000491
#define MSR_IA32_VMX_PROCBASED_CTLS3 0x00000492
-/* VMX_BASIC bits and bitmasks */
-#define VMX_BASIC_VMCS_SIZE_SHIFT 32
-#define VMX_BASIC_TRUE_CTLS (1ULL << 55)
-#define VMX_BASIC_64 0x0001000000000000LLU
-#define VMX_BASIC_MEM_TYPE_SHIFT 50
-#define VMX_BASIC_MEM_TYPE_MASK 0x003c000000000000LLU
-#define VMX_BASIC_MEM_TYPE_WB 6LLU
-#define VMX_BASIC_INOUT 0x0040000000000000LLU
-
/* Resctrl MSRs: */
/* - Intel: */
#define MSR_IA32_L3_QOS_CFG 0xc81
@@ -1185,11 +1196,6 @@
#define MSR_IA32_SMBA_BW_BASE 0xc0000280
#define MSR_IA32_EVT_CFG_BASE 0xc0000400
-/* MSR_IA32_VMX_MISC bits */
-#define MSR_IA32_VMX_MISC_INTEL_PT (1ULL << 14)
-#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
-#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F
-
/* AMD-V MSRs */
#define MSR_VM_CR 0xc0010114
#define MSR_VM_IGNNE 0xc0010115
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index bf57a82..a8debbf 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -439,6 +439,7 @@ struct kvm_sync_regs {
#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4)
#define KVM_X86_QUIRK_FIX_HYPERCALL_INSN (1 << 5)
#define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS (1 << 6)
+#define KVM_X86_QUIRK_SLOT_ZAP_ALL (1 << 7)
#define KVM_STATE_NESTED_FORMAT_VMX 0
#define KVM_STATE_NESTED_FORMAT_SVM 1
diff --git a/tools/arch/x86/include/uapi/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h
index 9de35df..63182a0 100644
--- a/tools/arch/x86/include/uapi/asm/unistd_32.h
+++ b/tools/arch/x86/include/uapi/asm/unistd_32.h
@@ -11,6 +11,9 @@
#ifndef __NR_getpgid
#define __NR_getpgid 132
#endif
+#ifndef __NR_capget
+#define __NR_capget 184
+#endif
#ifndef __NR_gettid
#define __NR_gettid 224
#endif
diff --git a/tools/arch/x86/include/uapi/asm/unistd_64.h b/tools/arch/x86/include/uapi/asm/unistd_64.h
index d0f2043..77311e8 100644
--- a/tools/arch/x86/include/uapi/asm/unistd_64.h
+++ b/tools/arch/x86/include/uapi/asm/unistd_64.h
@@ -11,6 +11,9 @@
#ifndef __NR_getpgid
#define __NR_getpgid 121
#endif
+#ifndef __NR_capget
+#define __NR_capget 125
+#endif
#ifndef __NR_gettid
#define __NR_gettid 186
#endif
diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
index 0eb24d2..60044b6 100644
--- a/tools/include/linux/bits.h
+++ b/tools/include/linux/bits.h
@@ -36,4 +36,19 @@
#define GENMASK_ULL(h, l) \
(GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l))
+#if !defined(__ASSEMBLY__)
+/*
+ * Missing asm support
+ *
+ * __GENMASK_U128() depends on _BIT128() which would not work
+ * in the asm code, as it shifts an 'unsigned __init128' data
+ * type instead of direct representation of 128 bit constants
+ * such as long and unsigned long. The fundamental problem is
+ * that a 128 bit constant will get silently truncated by the
+ * gcc compiler.
+ */
+#define GENMASK_U128(h, l) \
+ (GENMASK_INPUT_CHECK(h, l) + __GENMASK_U128(h, l))
+#endif
+
#endif /* __LINUX_BITS_H */
diff --git a/tools/include/linux/unaligned.h b/tools/include/linux/unaligned.h
index bc0633b..395a446 100644
--- a/tools/include/linux/unaligned.h
+++ b/tools/include/linux/unaligned.h
@@ -9,16 +9,7 @@
#pragma GCC diagnostic push
#pragma GCC diagnostic ignored "-Wpacked"
#pragma GCC diagnostic ignored "-Wattributes"
-
-#define __get_unaligned_t(type, ptr) ({ \
- const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \
- __pptr->x; \
-})
-
-#define __put_unaligned_t(type, val, ptr) do { \
- struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \
- __pptr->x = (val); \
-} while (0)
+#include <vdso/unaligned.h>
#define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr))
#define put_unaligned(val, ptr) __put_unaligned_t(typeof(*(ptr)), (val), (ptr))
diff --git a/tools/include/uapi/linux/bits.h b/tools/include/uapi/linux/bits.h
index 3c2a101..5ee30f8 100644
--- a/tools/include/uapi/linux/bits.h
+++ b/tools/include/uapi/linux/bits.h
@@ -12,4 +12,7 @@
(((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \
(~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h))))
+#define __GENMASK_U128(h, l) \
+ ((_BIT128((h)) << 1) - (_BIT128(l)))
+
#endif /* _UAPI_LINUX_BITS_H */
diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h
index a429381..e16be0d 100644
--- a/tools/include/uapi/linux/const.h
+++ b/tools/include/uapi/linux/const.h
@@ -28,6 +28,23 @@
#define _BITUL(x) (_UL(1) << (x))
#define _BITULL(x) (_ULL(1) << (x))
+#if !defined(__ASSEMBLY__)
+/*
+ * Missing asm support
+ *
+ * __BIT128() would not work in the asm code, as it shifts an
+ * 'unsigned __init128' data type as direct representation of
+ * 128 bit constants is not supported in the gcc compiler, as
+ * they get silently truncated.
+ *
+ * TODO: Please revisit this implementation when gcc compiler
+ * starts representing 128 bit constants directly like long
+ * and unsigned long etc. Subsequently drop the comment for
+ * GENMASK_U128() which would then start supporting asm code.
+ */
+#define _BIT128(x) ((unsigned __int128)(1) << (x))
+#endif
+
#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1)
#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask))
diff --git a/tools/include/vdso/unaligned.h b/tools/include/vdso/unaligned.h
new file mode 100644
index 0000000..eee3d2a
--- /dev/null
+++ b/tools/include/vdso/unaligned.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __VDSO_UNALIGNED_H
+#define __VDSO_UNALIGNED_H
+
+#define __get_unaligned_t(type, ptr) ({ \
+ const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \
+ __pptr->x; \
+})
+
+#define __put_unaligned_t(type, val, ptr) do { \
+ struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \
+ __pptr->x = (val); \
+} while (0)
+
+#endif /* __VDSO_UNALIGNED_H */
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 4ddb27a..d433267 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -704,8 +704,8 @@
BUILD_BPF_SKEL := 0
else
CLANG_VERSION := $(shell $(CLANG) --version | head -1 | sed 's/.*clang version \([[:digit:]]\+.[[:digit:]]\+.[[:digit:]]\+\).*/\1/g')
- ifeq ($(call version-lt3,$(CLANG_VERSION),16.0.6),1)
- $(warning Warning: Disabled BPF skeletons as at least $(CLANG) version 16.0.6 is reported to be a working setup with the current of BPF based perf features)
+ ifeq ($(call version-lt3,$(CLANG_VERSION),12.0.1),1)
+ $(warning Warning: Disabled BPF skeletons as reliable BTF generation needs at least $(CLANG) version 12.0.1)
BUILD_BPF_SKEL := 0
endif
endif
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index f6e8475..d3f11b9 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1399,7 +1399,7 @@ static const struct syscall_fmt syscall_fmts[] = {
.arg = { [2] = { .scnprintf = SCA_WAITID_OPTIONS, /* options */ }, }, },
{ .name = "waitid", .errpid = true,
.arg = { [3] = { .scnprintf = SCA_WAITID_OPTIONS, /* options */ }, }, },
- { .name = "write", .errpid = true,
+ { .name = "write",
.arg = { [1] = { .scnprintf = SCA_BUF /* buf */, .from_user = true, }, }, },
};
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 29adbb4..a05c1c1 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -22,6 +22,7 @@
"include/vdso/bits.h"
"include/linux/const.h"
"include/vdso/const.h"
+ "include/vdso/unaligned.h"
"include/linux/hash.h"
"include/linux/list-sort.h"
"include/uapi/linux/hw_breakpoint.h"
diff --git a/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh b/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh
index b5dc10b..bead723 100755
--- a/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh
+++ b/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh
@@ -19,35 +19,74 @@
TEST_RESULT=0
# skip if not supported
-BLACKFUNC=`head -n 1 /sys/kernel/debug/kprobes/blacklist 2> /dev/null | cut -f2`
-if [ -z "$BLACKFUNC" ]; then
+BLACKFUNC_LIST=`head -n 5 /sys/kernel/debug/kprobes/blacklist 2> /dev/null | cut -f2`
+if [ -z "$BLACKFUNC_LIST" ]; then
print_overall_skipped
exit 0
fi
+# try to find vmlinux with DWARF debug info
+VMLINUX_FILE=$(perf probe -v random_probe |& grep "Using.*for symbols" | sed -r 's/^Using (.*) for symbols$/\1/')
+
# remove all previously added probes
clear_all_probes
### adding blacklisted function
-
-# functions from blacklist should be skipped by perf probe
-! $CMD_PERF probe $BLACKFUNC > $LOGS_DIR/adding_blacklisted.log 2> $LOGS_DIR/adding_blacklisted.err
-PERF_EXIT_CODE=$?
-
REGEX_SCOPE_FAIL="Failed to find scope of probe point"
REGEX_SKIP_MESSAGE=" is blacklisted function, skip it\."
-REGEX_NOT_FOUND_MESSAGE="Probe point \'$BLACKFUNC\' not found."
+REGEX_NOT_FOUND_MESSAGE="Probe point \'$RE_EVENT\' not found."
REGEX_ERROR_MESSAGE="Error: Failed to add events."
REGEX_INVALID_ARGUMENT="Failed to write event: Invalid argument"
REGEX_SYMBOL_FAIL="Failed to find symbol at $RE_ADDRESS"
-REGEX_OUT_SECTION="$BLACKFUNC is out of \.\w+, skip it"
-../common/check_all_lines_matched.pl "$REGEX_SKIP_MESSAGE" "$REGEX_NOT_FOUND_MESSAGE" "$REGEX_ERROR_MESSAGE" "$REGEX_SCOPE_FAIL" "$REGEX_INVALID_ARGUMENT" "$REGEX_SYMBOL_FAIL" "$REGEX_OUT_SECTION" < $LOGS_DIR/adding_blacklisted.err
-CHECK_EXIT_CODE=$?
+REGEX_OUT_SECTION="$RE_EVENT is out of \.\w+, skip it"
+REGEX_MISSING_DECL_LINE="A function DIE doesn't have decl_line. Maybe broken DWARF?"
-print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "adding blacklisted function $BLACKFUNC"
-(( TEST_RESULT += $? ))
+BLACKFUNC=""
+SKIP_DWARF=0
+for BLACKFUNC in $BLACKFUNC_LIST; do
+ echo "Probing $BLACKFUNC"
+
+ # functions from blacklist should be skipped by perf probe
+ ! $CMD_PERF probe $BLACKFUNC > $LOGS_DIR/adding_blacklisted.log 2> $LOGS_DIR/adding_blacklisted.err
+ PERF_EXIT_CODE=$?
+
+ # check for bad DWARF polluting the result
+ ../common/check_all_patterns_found.pl "$REGEX_MISSING_DECL_LINE" >/dev/null < $LOGS_DIR/adding_blacklisted.err
+
+ if [ $? -eq 0 ]; then
+ SKIP_DWARF=1
+ echo "Result polluted by broken DWARF, trying another probe"
+
+ # confirm that the broken DWARF comes from assembler
+ if [ -n "$VMLINUX_FILE" ]; then
+ readelf -wi "$VMLINUX_FILE" |
+ awk -v probe="$BLACKFUNC" '/DW_AT_language/ { comp_lang = $0 }
+ $0 ~ probe { if (comp_lang) { print comp_lang }; exit }' |
+ grep -q "MIPS assembler"
+
+ CHECK_EXIT_CODE=$?
+ if [ $CHECK_EXIT_CODE -ne 0 ]; then
+ SKIP_DWARF=0 # broken DWARF while available
+ break
+ fi
+ fi
+ else
+ ../common/check_all_lines_matched.pl "$REGEX_SKIP_MESSAGE" "$REGEX_NOT_FOUND_MESSAGE" "$REGEX_ERROR_MESSAGE" "$REGEX_SCOPE_FAIL" "$REGEX_INVALID_ARGUMENT" "$REGEX_SYMBOL_FAIL" "$REGEX_OUT_SECTION" < $LOGS_DIR/adding_blacklisted.err
+ CHECK_EXIT_CODE=$?
+
+ SKIP_DWARF=0
+ break
+ fi
+done
+
+if [ $SKIP_DWARF -eq 1 ]; then
+ print_testcase_skipped "adding blacklisted function $BLACKFUNC"
+else
+ print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "adding blacklisted function $BLACKFUNC"
+ (( TEST_RESULT += $? ))
+fi
### listing not-added probe
diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
index b2f17cc..4a62ed5 100644
--- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
+++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
@@ -288,6 +288,10 @@ int sys_enter_rename(struct syscall_enter_args *args)
augmented_args->arg.size = PERF_ALIGN(oldpath_len + 1, sizeof(u64));
len += augmented_args->arg.size;
+ /* Every read from userspace is limited to value size */
+ if (augmented_args->arg.size > sizeof(augmented_args->arg.value))
+ return 1; /* Failure: don't filter */
+
struct augmented_arg *arg2 = (void *)&augmented_args->arg.value + augmented_args->arg.size;
newpath_len = augmented_arg__read_str(arg2, newpath_arg, sizeof(augmented_args->arg.value));
@@ -315,6 +319,10 @@ int sys_enter_renameat2(struct syscall_enter_args *args)
augmented_args->arg.size = PERF_ALIGN(oldpath_len + 1, sizeof(u64));
len += augmented_args->arg.size;
+ /* Every read from userspace is limited to value size */
+ if (augmented_args->arg.size > sizeof(augmented_args->arg.value))
+ return 1; /* Failure: don't filter */
+
struct augmented_arg *arg2 = (void *)&augmented_args->arg.value + augmented_args->arg.size;
newpath_len = augmented_arg__read_str(arg2, newpath_arg, sizeof(augmented_args->arg.value));
@@ -423,8 +431,9 @@ static bool pid_filter__has(struct pids_filtered *pids, pid_t pid)
static int augment_sys_enter(void *ctx, struct syscall_enter_args *args)
{
bool augmented, do_output = false;
- int zero = 0, size, aug_size, index, output = 0,
+ int zero = 0, size, aug_size, index,
value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value);
+ u64 output = 0; /* has to be u64, otherwise it won't pass the verifier */
unsigned int nr, *beauty_map;
struct beauty_payload_enter *payload;
void *arg, *payload_offset;
@@ -477,6 +486,8 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args)
augmented = true;
} else if (size < 0 && size >= -6) { /* buffer */
index = -(size + 1);
+ barrier_var(index); // Prevent clang (noticed with v18) from removing the &= 7 trick.
+ index &= 7; // Satisfy the bounds checking with the verifier in some kernels.
aug_size = args->args[index];
if (aug_size > TRACE_AUG_MAX_BUF)
@@ -488,10 +499,17 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args)
}
}
+ /* Augmented data size is limited to sizeof(augmented_arg->unnamed union with value field) */
+ if (aug_size > value_size)
+ aug_size = value_size;
+
/* write data to payload */
if (augmented) {
int written = offsetof(struct augmented_arg, value) + aug_size;
+ if (written < 0 || written > sizeof(struct augmented_arg))
+ return 1;
+
((struct augmented_arg *)payload_offset)->size = aug_size;
output += written;
payload_offset += written;
@@ -499,7 +517,7 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args)
}
}
- if (!do_output)
+ if (!do_output || (sizeof(struct syscall_enter_args) + output) > sizeof(struct beauty_payload_enter))
return 1;
return augmented__beauty_output(ctx, payload, sizeof(struct syscall_enter_args) + output);
diff --git a/tools/perf/util/cap.c b/tools/perf/util/cap.c
index 7574a67..69d9a2b 100644
--- a/tools/perf/util/cap.c
+++ b/tools/perf/util/cap.c
@@ -7,13 +7,9 @@
#include "debug.h"
#include <errno.h>
#include <string.h>
-#include <unistd.h>
#include <linux/capability.h>
#include <sys/syscall.h>
-
-#ifndef SYS_capget
-#define SYS_capget 90
-#endif
+#include <unistd.h>
#define MAX_LINUX_CAPABILITY_U32S _LINUX_CAPABILITY_U32S_3
@@ -21,9 +17,9 @@ bool perf_cap__capable(int cap, bool *used_root)
{
struct __user_cap_header_struct header = {
.version = _LINUX_CAPABILITY_VERSION_3,
- .pid = getpid(),
+ .pid = 0,
};
- struct __user_cap_data_struct data[MAX_LINUX_CAPABILITY_U32S];
+ struct __user_cap_data_struct data[MAX_LINUX_CAPABILITY_U32S] = {};
__u32 cap_val;
*used_root = false;
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 31a223e..ee3d43a 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -19,6 +19,7 @@
#include "util/bpf-filter.h"
#include "util/env.h"
#include "util/kvm-stat.h"
+#include "util/stat.h"
#include "util/kwork.h"
#include "util/sample.h"
#include "util/lock-contention.h"
@@ -1355,6 +1356,7 @@ PyMODINIT_FUNC PyInit_perf(void)
unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH;
+#ifdef HAVE_KVM_STAT_SUPPORT
bool kvm_entry_event(struct evsel *evsel __maybe_unused)
{
return false;
@@ -1384,6 +1386,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
char *decode __maybe_unused)
{
}
+#endif // HAVE_KVM_STAT_SUPPORT
int find_scripts(char **scripts_array __maybe_unused, char **scripts_path_array __maybe_unused,
int num __maybe_unused, int pathlen __maybe_unused)
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index 7c15dec..6c45ded 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -46,6 +46,11 @@ static const char *const *syscalltbl_native = syscalltbl_mips_n64;
#include <asm/syscalls.c>
const int syscalltbl_native_max_id = SYSCALLTBL_LOONGARCH_MAX_ID;
static const char *const *syscalltbl_native = syscalltbl_loongarch;
+#else
+const int syscalltbl_native_max_id = 0;
+static const char *const syscalltbl_native[] = {
+ [0] = "unknown",
+};
#endif
struct syscall {
@@ -182,6 +187,11 @@ int syscalltbl__id(struct syscalltbl *tbl, const char *name)
return audit_name_to_syscall(name, tbl->audit_machine);
}
+int syscalltbl__id_at_idx(struct syscalltbl *tbl __maybe_unused, int idx)
+{
+ return idx;
+}
+
int syscalltbl__strglobmatch_next(struct syscalltbl *tbl __maybe_unused,
const char *syscall_glob __maybe_unused, int *idx __maybe_unused)
{
diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
index 27749c5..248ab79 100644
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -320,7 +320,7 @@ u32 bpf_cpumask_weight(const struct cpumask *cpumask) __ksym;
/*
* Access a cpumask in read-only mode (typically to check bits).
*/
-const struct cpumask *cast_mask(struct bpf_cpumask *mask)
+static __always_inline const struct cpumask *cast_mask(struct bpf_cpumask *mask)
{
return (const struct cpumask *)mask;
}
diff --git a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_get_next_key.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_get_next_key.c
new file mode 100644
index 0000000..0ba0156
--- /dev/null
+++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_get_next_key.c
@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <linux/bpf.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <unistd.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
+#include <pthread.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include <test_maps.h>
+
+struct test_lpm_key {
+ __u32 prefix;
+ __u32 data;
+};
+
+struct get_next_key_ctx {
+ struct test_lpm_key key;
+ bool start;
+ bool stop;
+ int map_fd;
+ int loop;
+};
+
+static void *get_next_key_fn(void *arg)
+{
+ struct get_next_key_ctx *ctx = arg;
+ struct test_lpm_key next_key;
+ int i = 0;
+
+ while (!ctx->start)
+ usleep(1);
+
+ while (!ctx->stop && i++ < ctx->loop)
+ bpf_map_get_next_key(ctx->map_fd, &ctx->key, &next_key);
+
+ return NULL;
+}
+
+static void abort_get_next_key(struct get_next_key_ctx *ctx, pthread_t *tids,
+ unsigned int nr)
+{
+ unsigned int i;
+
+ ctx->stop = true;
+ ctx->start = true;
+ for (i = 0; i < nr; i++)
+ pthread_join(tids[i], NULL);
+}
+
+/* This test aims to prevent regression of future. As long as the kernel does
+ * not panic, it is considered as success.
+ */
+void test_lpm_trie_map_get_next_key(void)
+{
+#define MAX_NR_THREADS 8
+ LIBBPF_OPTS(bpf_map_create_opts, create_opts,
+ .map_flags = BPF_F_NO_PREALLOC);
+ struct test_lpm_key key = {};
+ __u32 val = 0;
+ int map_fd;
+ const __u32 max_prefixlen = 8 * (sizeof(key) - sizeof(key.prefix));
+ const __u32 max_entries = max_prefixlen + 1;
+ unsigned int i, nr = MAX_NR_THREADS, loop = 65536;
+ pthread_t tids[MAX_NR_THREADS];
+ struct get_next_key_ctx ctx;
+ int err;
+
+ map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, "lpm_trie_map",
+ sizeof(struct test_lpm_key), sizeof(__u32),
+ max_entries, &create_opts);
+ CHECK(map_fd == -1, "bpf_map_create()", "error:%s\n",
+ strerror(errno));
+
+ for (i = 0; i <= max_prefixlen; i++) {
+ key.prefix = i;
+ err = bpf_map_update_elem(map_fd, &key, &val, BPF_ANY);
+ CHECK(err, "bpf_map_update_elem()", "error:%s\n",
+ strerror(errno));
+ }
+
+ ctx.start = false;
+ ctx.stop = false;
+ ctx.map_fd = map_fd;
+ ctx.loop = loop;
+ memcpy(&ctx.key, &key, sizeof(key));
+
+ for (i = 0; i < nr; i++) {
+ err = pthread_create(&tids[i], NULL, get_next_key_fn, &ctx);
+ if (err) {
+ abort_get_next_key(&ctx, tids, i);
+ CHECK(err, "pthread_create", "error %d\n", err);
+ }
+ }
+
+ ctx.start = true;
+ for (i = 0; i < nr; i++)
+ pthread_join(tids[i], NULL);
+
+ printf("%s:PASS\n", __func__);
+
+ close(map_fd);
+}
diff --git a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c
index f4da4d5..156cc27 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c
@@ -15,6 +15,8 @@ int bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign,
int *bpf_iter_bits_next(struct bpf_iter_bits *it) __ksym __weak;
void bpf_iter_bits_destroy(struct bpf_iter_bits *it) __ksym __weak;
+u64 bits_array[511] = {};
+
SEC("iter.s/cgroup")
__description("bits iter without destroy")
__failure __msg("Unreleased reference")
@@ -110,16 +112,16 @@ int bit_index(void)
}
SEC("syscall")
-__description("bits nomem")
+__description("bits too big")
__success __retval(0)
-int bits_nomem(void)
+int bits_too_big(void)
{
u64 data[4];
int nr = 0;
int *bit;
__builtin_memset(&data, 0xff, sizeof(data));
- bpf_for_each(bits, bit, &data[0], 513) /* Be greater than 512 */
+ bpf_for_each(bits, bit, &data[0], 512) /* Be greater than 511 */
nr++;
return nr;
}
@@ -151,3 +153,56 @@ int zero_words(void)
nr++;
return nr;
}
+
+SEC("syscall")
+__description("huge words")
+__success __retval(0)
+int huge_words(void)
+{
+ u64 data[8] = {0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1};
+ int nr = 0;
+ int *bit;
+
+ bpf_for_each(bits, bit, &data[0], 67108865)
+ nr++;
+ return nr;
+}
+
+SEC("syscall")
+__description("max words")
+__success __retval(4)
+int max_words(void)
+{
+ volatile int nr = 0;
+ int *bit;
+
+ bits_array[0] = (1ULL << 63) | 1U;
+ bits_array[510] = (1ULL << 33) | (1ULL << 32);
+
+ bpf_for_each(bits, bit, bits_array, 511) {
+ if (nr == 0 && *bit != 0)
+ break;
+ if (nr == 2 && *bit != 32672)
+ break;
+ nr++;
+ }
+ return nr;
+}
+
+SEC("syscall")
+__description("bad words")
+__success __retval(0)
+int bad_words(void)
+{
+ void *bad_addr = (void *)(3UL << 30);
+ int nr = 0;
+ int *bit;
+
+ bpf_for_each(bits, bit, bad_addr, 1)
+ nr++;
+
+ bpf_for_each(bits, bit, bad_addr, 4)
+ nr++;
+
+ return nr;
+}
diff --git a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
index 9da97d2..5094c28 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
@@ -790,61 +790,6 @@ __naked static void cumulative_stack_depth_subprog(void)
:: __imm(bpf_get_smp_processor_id) : __clobber_all);
}
-SEC("raw_tp")
-__arch_x86_64
-__log_level(4)
-__msg("stack depth 512")
-__xlated("0: r1 = 42")
-__xlated("1: *(u64 *)(r10 -512) = r1")
-__xlated("2: w0 = ")
-__xlated("3: r0 = &(void __percpu *)(r0)")
-__xlated("4: r0 = *(u32 *)(r0 +0)")
-__xlated("5: exit")
-__success
-__naked int bpf_fastcall_max_stack_ok(void)
-{
- asm volatile(
- "r1 = 42;"
- "*(u64 *)(r10 - %[max_bpf_stack]) = r1;"
- "*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;"
- "call %[bpf_get_smp_processor_id];"
- "r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);"
- "exit;"
- :
- : __imm_const(max_bpf_stack, MAX_BPF_STACK),
- __imm_const(max_bpf_stack_8, MAX_BPF_STACK + 8),
- __imm(bpf_get_smp_processor_id)
- : __clobber_all
- );
-}
-
-SEC("raw_tp")
-__arch_x86_64
-__log_level(4)
-__msg("stack depth 520")
-__failure
-__naked int bpf_fastcall_max_stack_fail(void)
-{
- asm volatile(
- "r1 = 42;"
- "*(u64 *)(r10 - %[max_bpf_stack]) = r1;"
- "*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;"
- "call %[bpf_get_smp_processor_id];"
- "r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);"
- /* call to prandom blocks bpf_fastcall rewrite */
- "*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;"
- "call %[bpf_get_prandom_u32];"
- "r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);"
- "exit;"
- :
- : __imm_const(max_bpf_stack, MAX_BPF_STACK),
- __imm_const(max_bpf_stack_8, MAX_BPF_STACK + 8),
- __imm(bpf_get_smp_processor_id),
- __imm(bpf_get_prandom_u32)
- : __clobber_all
- );
-}
-
SEC("cgroup/getsockname_unix")
__xlated("0: r2 = 1")
/* bpf_cast_to_kern_ctx is replaced by a single assignment */
diff --git a/tools/testing/selftests/bpf/progs/verifier_search_pruning.c b/tools/testing/selftests/bpf/progs/verifier_search_pruning.c
index 5a14498..f40e572 100644
--- a/tools/testing/selftests/bpf/progs/verifier_search_pruning.c
+++ b/tools/testing/selftests/bpf/progs/verifier_search_pruning.c
@@ -2,6 +2,7 @@
/* Converted from tools/testing/selftests/bpf/verifier/search_pruning.c */
#include <linux/bpf.h>
+#include <../../../include/linux/filter.h>
#include <bpf/bpf_helpers.h>
#include "bpf_misc.h"
@@ -336,4 +337,26 @@ l0_%=: r1 = 42; \
: __clobber_all);
}
+/* Without checkpoint forcibly inserted at the back-edge a loop this
+ * test would take a very long time to verify.
+ */
+SEC("kprobe")
+__failure __log_level(4)
+__msg("BPF program is too large.")
+__naked void short_loop1(void)
+{
+ asm volatile (
+ " r7 = *(u16 *)(r1 +0);"
+ "1: r7 += 0x1ab064b9;"
+ " .8byte %[jset];" /* same as 'if r7 & 0x702000 goto 1b;' */
+ " r7 &= 0x1ee60e;"
+ " r7 += r1;"
+ " if r7 s> 0x37d2 goto +0;"
+ " r0 = 0;"
+ " exit;"
+ :
+ : __imm_insn(jset, BPF_JMP_IMM(BPF_JSET, BPF_REG_7, 0x702000, -2))
+ : __clobber_all);
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/veristat.cfg b/tools/testing/selftests/bpf/veristat.cfg
index 1a38506..e661ffd 100644
--- a/tools/testing/selftests/bpf/veristat.cfg
+++ b/tools/testing/selftests/bpf/veristat.cfg
@@ -15,3 +15,4 @@
test_verif_scale*
test_xdp_noinline*
xdp_synproxy*
+verifier_search_pruning*
diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c
index 852e728..717539e 100644
--- a/tools/testing/selftests/mm/uffd-common.c
+++ b/tools/testing/selftests/mm/uffd-common.c
@@ -18,7 +18,7 @@ bool test_uffdio_wp = true;
unsigned long long *count_verify;
uffd_test_ops_t *uffd_test_ops;
uffd_test_case_ops_t *uffd_test_case_ops;
-pthread_barrier_t ready_for_fork;
+atomic_bool ready_for_fork;
static int uffd_mem_fd_create(off_t mem_size, bool hugetlb)
{
@@ -519,8 +519,7 @@ void *uffd_poll_thread(void *arg)
pollfd[1].fd = pipefd[cpu*2];
pollfd[1].events = POLLIN;
- /* Ready for parent thread to fork */
- pthread_barrier_wait(&ready_for_fork);
+ ready_for_fork = true;
for (;;) {
ret = poll(pollfd, 2, -1);
diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h
index 3e6228d..a70ae10 100644
--- a/tools/testing/selftests/mm/uffd-common.h
+++ b/tools/testing/selftests/mm/uffd-common.h
@@ -33,6 +33,7 @@
#include <inttypes.h>
#include <stdint.h>
#include <sys/random.h>
+#include <stdatomic.h>
#include "../kselftest.h"
#include "vm_util.h"
@@ -104,7 +105,7 @@ extern bool map_shared;
extern bool test_uffdio_wp;
extern unsigned long long *count_verify;
extern volatile bool test_uffdio_copy_eexist;
-extern pthread_barrier_t ready_for_fork;
+extern atomic_bool ready_for_fork;
extern uffd_test_ops_t anon_uffd_test_ops;
extern uffd_test_ops_t shmem_uffd_test_ops;
diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c
index c8a3b1c..a2e71b1 100644
--- a/tools/testing/selftests/mm/uffd-unit-tests.c
+++ b/tools/testing/selftests/mm/uffd-unit-tests.c
@@ -241,8 +241,7 @@ static void *fork_event_consumer(void *data)
fork_event_args *args = data;
struct uffd_msg msg = { 0 };
- /* Ready for parent thread to fork */
- pthread_barrier_wait(&ready_for_fork);
+ ready_for_fork = true;
/* Read until a full msg received */
while (uffd_read_msg(args->parent_uffd, &msg));
@@ -311,12 +310,11 @@ static int pagemap_test_fork(int uffd, bool with_event, bool test_pin)
/* Prepare a thread to resolve EVENT_FORK */
if (with_event) {
- pthread_barrier_init(&ready_for_fork, NULL, 2);
+ ready_for_fork = false;
if (pthread_create(&thread, NULL, fork_event_consumer, &args))
err("pthread_create()");
- /* Wait for child thread to start before forking */
- pthread_barrier_wait(&ready_for_fork);
- pthread_barrier_destroy(&ready_for_fork);
+ while (!ready_for_fork)
+ ; /* Wait for the poll_thread to start executing before forking */
}
child = fork();
@@ -781,7 +779,7 @@ static void uffd_sigbus_test_common(bool wp)
char c;
struct uffd_args args = { 0 };
- pthread_barrier_init(&ready_for_fork, NULL, 2);
+ ready_for_fork = false;
fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
@@ -798,9 +796,8 @@ static void uffd_sigbus_test_common(bool wp)
if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args))
err("uffd_poll_thread create");
- /* Wait for child thread to start before forking */
- pthread_barrier_wait(&ready_for_fork);
- pthread_barrier_destroy(&ready_for_fork);
+ while (!ready_for_fork)
+ ; /* Wait for the poll_thread to start executing before forking */
pid = fork();
if (pid < 0)
@@ -841,7 +838,7 @@ static void uffd_events_test_common(bool wp)
char c;
struct uffd_args args = { 0 };
- pthread_barrier_init(&ready_for_fork, NULL, 2);
+ ready_for_fork = false;
fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
if (uffd_register(uffd, area_dst, nr_pages * page_size,
@@ -852,9 +849,8 @@ static void uffd_events_test_common(bool wp)
if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args))
err("uffd_poll_thread create");
- /* Wait for child thread to start before forking */
- pthread_barrier_wait(&ready_for_fork);
- pthread_barrier_destroy(&ready_for_fork);
+ while (!ready_for_fork)
+ ; /* Wait for the poll_thread to start executing before forking */
pid = fork();
if (pid < 0)
diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat.sh
index 96c9706..becc7c3 100755
--- a/tools/testing/selftests/net/forwarding/ip6gre_flat.sh
+++ b/tools/testing/selftests/net/forwarding/ip6gre_flat.sh
@@ -8,6 +8,7 @@
ALL_TESTS="
gre_flat
gre_mtu_change
+ gre_flat_remote_change
"
NUM_NETIFS=6
@@ -44,6 +45,19 @@
test_mtu_change
}
+gre_flat_remote_change()
+{
+ flat_remote_change
+
+ test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 (new remote)"
+ test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 (new remote)"
+
+ flat_remote_restore
+
+ test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 (old remote)"
+ test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 (old remote)"
+}
+
cleanup()
{
pre_cleanup
diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh
index ff9fb0d..e533511 100755
--- a/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh
+++ b/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh
@@ -8,6 +8,7 @@
ALL_TESTS="
gre_flat
gre_mtu_change
+ gre_flat_remote_change
"
NUM_NETIFS=6
@@ -44,6 +45,19 @@
test_mtu_change
}
+gre_flat_remote_change()
+{
+ flat_remote_change
+
+ test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with key (new remote)"
+ test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with key (new remote)"
+
+ flat_remote_restore
+
+ test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with key (old remote)"
+ test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with key (old remote)"
+}
+
cleanup()
{
pre_cleanup
diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh
index 12c1387..7e0cbfd 100755
--- a/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh
+++ b/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh
@@ -8,6 +8,7 @@
ALL_TESTS="
gre_flat
gre_mtu_change
+ gre_flat_remote_change
"
NUM_NETIFS=6
@@ -44,6 +45,19 @@
test_mtu_change gre
}
+gre_flat_remote_change()
+{
+ flat_remote_change
+
+ test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with ikey/okey (new remote)"
+ test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with ikey/okey (new remote)"
+
+ flat_remote_restore
+
+ test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with ikey/okey (old remote)"
+ test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with ikey/okey (old remote)"
+}
+
cleanup()
{
pre_cleanup
diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier.sh
index 83b55c3..e084449 100755
--- a/tools/testing/selftests/net/forwarding/ip6gre_hier.sh
+++ b/tools/testing/selftests/net/forwarding/ip6gre_hier.sh
@@ -8,6 +8,7 @@
ALL_TESTS="
gre_hier
gre_mtu_change
+ gre_hier_remote_change
"
NUM_NETIFS=6
@@ -44,6 +45,19 @@
test_mtu_change gre
}
+gre_hier_remote_change()
+{
+ hier_remote_change
+
+ test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 (new remote)"
+ test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 (new remote)"
+
+ hier_remote_restore
+
+ test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 (old remote)"
+ test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 (old remote)"
+}
+
cleanup()
{
pre_cleanup
diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh
index 2566079..741bc9c 100755
--- a/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh
+++ b/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh
@@ -8,6 +8,7 @@
ALL_TESTS="
gre_hier
gre_mtu_change
+ gre_hier_remote_change
"
NUM_NETIFS=6
@@ -44,6 +45,19 @@
test_mtu_change gre
}
+gre_hier_remote_change()
+{
+ hier_remote_change
+
+ test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with key (new remote)"
+ test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with key (new remote)"
+
+ hier_remote_restore
+
+ test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with key (old remote)"
+ test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with key (old remote)"
+}
+
cleanup()
{
pre_cleanup
diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh
index ad1bcd6..ad9eab4 100755
--- a/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh
+++ b/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh
@@ -8,6 +8,7 @@
ALL_TESTS="
gre_hier
gre_mtu_change
+ gre_hier_remote_change
"
NUM_NETIFS=6
@@ -44,6 +45,19 @@
test_mtu_change gre
}
+gre_hier_remote_change()
+{
+ hier_remote_change
+
+ test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with ikey/okey (new remote)"
+ test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with ikey/okey (new remote)"
+
+ hier_remote_restore
+
+ test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with ikey/okey (old remote)"
+ test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with ikey/okey (old remote)"
+}
+
cleanup()
{
pre_cleanup
diff --git a/tools/testing/selftests/net/forwarding/ip6gre_lib.sh b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh
index 24f4ab3..2d91281 100644
--- a/tools/testing/selftests/net/forwarding/ip6gre_lib.sh
+++ b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh
@@ -436,3 +436,83 @@
check_err $?
log_test "ping GRE IPv6, packet size 1800 after MTU change"
}
+
+topo_flat_remote_change()
+{
+ local old1=$1; shift
+ local new1=$1; shift
+ local old2=$1; shift
+ local new2=$1; shift
+
+ ip link set dev g1a type ip6gre local $new1 remote $new2
+ __addr_add_del g1a add "$new1/128"
+ __addr_add_del g1a del "$old1/128"
+ ip -6 route add $new2/128 via 2001:db8:10::2
+ ip -6 route del $old2/128
+
+ ip link set dev g2a type ip6gre local $new2 remote $new1
+ __addr_add_del g2a add "$new2/128"
+ __addr_add_del g2a del "$old2/128"
+ ip -6 route add vrf v$ol2 $new1/128 via 2001:db8:10::1
+ ip -6 route del vrf v$ol2 $old1/128
+}
+
+flat_remote_change()
+{
+ local old1=2001:db8:3::1
+ local new1=2001:db8:3::10
+ local old2=2001:db8:3::2
+ local new2=2001:db8:3::20
+
+ topo_flat_remote_change $old1 $new1 $old2 $new2
+}
+
+flat_remote_restore()
+{
+ local old1=2001:db8:3::10
+ local new1=2001:db8:3::1
+ local old2=2001:db8:3::20
+ local new2=2001:db8:3::2
+
+ topo_flat_remote_change $old1 $new1 $old2 $new2
+}
+
+topo_hier_remote_change()
+{
+ local old1=$1; shift
+ local new1=$1; shift
+ local old2=$1; shift
+ local new2=$1; shift
+
+ __addr_add_del dummy1 del "$old1/64"
+ __addr_add_del dummy1 add "$new1/64"
+ ip link set dev g1a type ip6gre local $new1 remote $new2
+ ip -6 route add vrf v$ul1 $new2/128 via 2001:db8:10::2
+ ip -6 route del vrf v$ul1 $old2/128
+
+ __addr_add_del dummy2 del "$old2/64"
+ __addr_add_del dummy2 add "$new2/64"
+ ip link set dev g2a type ip6gre local $new2 remote $new1
+ ip -6 route add vrf v$ul2 $new1/128 via 2001:db8:10::1
+ ip -6 route del vrf v$ul2 $old1/128
+}
+
+hier_remote_change()
+{
+ local old1=2001:db8:3::1
+ local new1=2001:db8:3::10
+ local old2=2001:db8:3::2
+ local new2=2001:db8:3::20
+
+ topo_hier_remote_change $old1 $new1 $old2 $new2
+}
+
+hier_remote_restore()
+{
+ local old1=2001:db8:3::10
+ local new1=2001:db8:3::1
+ local old2=2001:db8:3::20
+ local new2=2001:db8:3::2
+
+ topo_hier_remote_change $old1 $new1 $old2 $new2
+}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 57325d5..b48b4e5 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -259,6 +259,15 @@
mptcp_lib_ns_init disabled_ns
print_larger_title "New MPTCP socket can be blocked via sysctl"
+
+ # mainly to cover more code
+ if ! ip netns exec ${disabled_ns} sysctl net.mptcp >/dev/null; then
+ mptcp_lib_pr_fail "not able to list net.mptcp sysctl knobs"
+ mptcp_lib_result_fail "not able to list net.mptcp sysctl knobs"
+ ret=${KSFT_FAIL}
+ return 1
+ fi
+
# net.mptcp.enabled should be enabled by default
if [ "$(ip netns exec ${disabled_ns} sysctl net.mptcp.enabled | awk '{ print $3 }')" -ne 1 ]; then
mptcp_lib_pr_fail "net.mptcp.enabled sysctl is not 1 by default"
diff --git a/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c
index dc056fe..254ff03 100644
--- a/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c
+++ b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c
@@ -98,7 +98,7 @@ static int conntrack_data_insert(struct mnl_socket *sock, struct nlmsghdr *nlh,
char buf[MNL_SOCKET_BUFFER_SIZE];
struct nlmsghdr *rplnlh;
unsigned int portid;
- int err, ret;
+ int ret;
portid = mnl_socket_get_portid(sock);
@@ -217,7 +217,7 @@ static int conntracK_count_zone(struct mnl_socket *sock, uint16_t zone)
struct nfgenmsg *nfh;
struct nlattr *nest;
unsigned int portid;
- int err, ret;
+ int ret;
portid = mnl_socket_get_portid(sock);
@@ -264,7 +264,7 @@ static int conntrack_flush_zone(struct mnl_socket *sock, uint16_t zone)
struct nfgenmsg *nfh;
struct nlattr *nest;
unsigned int portid;
- int err, ret;
+ int ret;
portid = mnl_socket_get_portid(sock);
diff --git a/tools/testing/selftests/net/netfilter/nft_flowtable.sh b/tools/testing/selftests/net/netfilter/nft_flowtable.sh
index b399555..a4ee549 100755
--- a/tools/testing/selftests/net/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/net/netfilter/nft_flowtable.sh
@@ -71,6 +71,8 @@
lmtu=1500
rmtu=2000
+filesize=$((2 * 1024 * 1024))
+
usage(){
echo "nft_flowtable.sh [OPTIONS]"
echo
@@ -81,12 +83,13 @@
exit 1
}
-while getopts "o:l:r:" o
+while getopts "o:l:r:s:" o
do
case $o in
o) omtu=$OPTARG;;
l) lmtu=$OPTARG;;
r) rmtu=$OPTARG;;
+ s) filesize=$OPTARG;;
*) usage;;
esac
done
@@ -217,18 +220,10 @@
make_file()
{
- name=$1
+ name="$1"
+ sz="$2"
- SIZE=$((RANDOM % (1024 * 128)))
- SIZE=$((SIZE + (1024 * 8)))
- TSIZE=$((SIZE * 1024))
-
- dd if=/dev/urandom of="$name" bs=1024 count=$SIZE 2> /dev/null
-
- SIZE=$((RANDOM % 1024))
- SIZE=$((SIZE + 128))
- TSIZE=$((TSIZE + SIZE))
- dd if=/dev/urandom conf=notrunc of="$name" bs=1 count=$SIZE 2> /dev/null
+ head -c "$sz" < /dev/urandom > "$name"
}
check_counters()
@@ -246,18 +241,18 @@
local fs
fs=$(du -sb "$nsin")
local max_orig=${fs%%/*}
- local max_repl=$((max_orig/4))
+ local max_repl=$((max_orig))
# flowtable fastpath should bypass normal routing one, i.e. the counters in forward hook
# should always be lower than the size of the transmitted file (max_orig).
if [ "$orig_cnt" -gt "$max_orig" ];then
- echo "FAIL: $what: original counter $orig_cnt exceeds expected value $max_orig" 1>&2
+ echo "FAIL: $what: original counter $orig_cnt exceeds expected value $max_orig, reply counter $repl_cnt" 1>&2
ret=1
ok=0
fi
if [ "$repl_cnt" -gt $max_repl ];then
- echo "FAIL: $what: reply counter $repl_cnt exceeds expected value $max_repl" 1>&2
+ echo "FAIL: $what: reply counter $repl_cnt exceeds expected value $max_repl, original counter $orig_cnt" 1>&2
ret=1
ok=0
fi
@@ -455,7 +450,7 @@
return $lret
}
-make_file "$nsin"
+make_file "$nsin" "$filesize"
# First test:
# No PMTU discovery, nsr1 is expected to fragment packets from ns1 to ns2 as needed.
@@ -664,8 +659,16 @@
l=$(((RANDOM%mtu) + low))
r=$(((RANDOM%mtu) + low))
- echo "re-run with random mtus: -o $o -l $l -r $r"
- $0 -o "$o" -l "$l" -r "$r"
+ MINSIZE=$((2 * 1000 * 1000))
+ MAXSIZE=$((64 * 1000 * 1000))
+
+ filesize=$(((RANDOM * RANDOM) % MAXSIZE))
+ if [ "$filesize" -lt "$MINSIZE" ]; then
+ filesize=$((filesize+MINSIZE))
+ fi
+
+ echo "re-run with random mtus and file size: -o $o -l $l -r $r -s $filesize"
+ $0 -o "$o" -l "$l" -r "$r" -s "$filesize"
fi
exit $ret
diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile
index 06ae9c1..0117622 100644
--- a/tools/testing/selftests/sched_ext/Makefile
+++ b/tools/testing/selftests/sched_ext/Makefile
@@ -184,7 +184,7 @@
testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets)))
-$(SCXOBJ_DIR)/runner.o: runner.c | $(SCXOBJ_DIR)
+$(SCXOBJ_DIR)/runner.o: runner.c | $(SCXOBJ_DIR) $(BPFOBJ)
$(CC) $(CFLAGS) -c $< -o $@
# Create all of the test targets object files, whose testcase objects will be
diff --git a/tools/testing/selftests/sched_ext/create_dsq.bpf.c b/tools/testing/selftests/sched_ext/create_dsq.bpf.c
index 23f79ed..2cfc4ff 100644
--- a/tools/testing/selftests/sched_ext/create_dsq.bpf.c
+++ b/tools/testing/selftests/sched_ext/create_dsq.bpf.c
@@ -51,8 +51,8 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(create_dsq_init)
SEC(".struct_ops.link")
struct sched_ext_ops create_dsq_ops = {
- .init_task = create_dsq_init_task,
- .exit_task = create_dsq_exit_task,
- .init = create_dsq_init,
+ .init_task = (void *) create_dsq_init_task,
+ .exit_task = (void *) create_dsq_exit_task,
+ .init = (void *) create_dsq_init,
.name = "create_dsq",
};
diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c
index e97ad41..37d9bf6 100644
--- a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c
+++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c
@@ -35,8 +35,8 @@ void BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_exit, struct scx_exit_info *ei)
SEC(".struct_ops.link")
struct sched_ext_ops ddsp_bogus_dsq_fail_ops = {
- .select_cpu = ddsp_bogus_dsq_fail_select_cpu,
- .exit = ddsp_bogus_dsq_fail_exit,
+ .select_cpu = (void *) ddsp_bogus_dsq_fail_select_cpu,
+ .exit = (void *) ddsp_bogus_dsq_fail_exit,
.name = "ddsp_bogus_dsq_fail",
.timeout_ms = 1000U,
};
diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c
index dde7e7d..dffc97d 100644
--- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c
+++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c
@@ -32,8 +32,8 @@ void BPF_STRUCT_OPS(ddsp_vtimelocal_fail_exit, struct scx_exit_info *ei)
SEC(".struct_ops.link")
struct sched_ext_ops ddsp_vtimelocal_fail_ops = {
- .select_cpu = ddsp_vtimelocal_fail_select_cpu,
- .exit = ddsp_vtimelocal_fail_exit,
+ .select_cpu = (void *) ddsp_vtimelocal_fail_select_cpu,
+ .exit = (void *) ddsp_vtimelocal_fail_exit,
.name = "ddsp_vtimelocal_fail",
.timeout_ms = 1000U,
};
diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
index efb4672..6a7db15 100644
--- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
+++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
@@ -56,10 +56,10 @@ void BPF_STRUCT_OPS(dsp_local_on_exit, struct scx_exit_info *ei)
SEC(".struct_ops.link")
struct sched_ext_ops dsp_local_on_ops = {
- .select_cpu = dsp_local_on_select_cpu,
- .enqueue = dsp_local_on_enqueue,
- .dispatch = dsp_local_on_dispatch,
- .exit = dsp_local_on_exit,
+ .select_cpu = (void *) dsp_local_on_select_cpu,
+ .enqueue = (void *) dsp_local_on_enqueue,
+ .dispatch = (void *) dsp_local_on_dispatch,
+ .exit = (void *) dsp_local_on_exit,
.name = "dsp_local_on",
.timeout_ms = 1000U,
};
diff --git a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c
index b0b9953..e1bd13e 100644
--- a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c
+++ b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c
@@ -12,10 +12,18 @@
char _license[] SEC("license") = "GPL";
+u32 exit_kind;
+
+void BPF_STRUCT_OPS_SLEEPABLE(enq_last_no_enq_fails_exit, struct scx_exit_info *info)
+{
+ exit_kind = info->kind;
+}
+
SEC(".struct_ops.link")
struct sched_ext_ops enq_last_no_enq_fails_ops = {
.name = "enq_last_no_enq_fails",
/* Need to define ops.enqueue() with SCX_OPS_ENQ_LAST */
.flags = SCX_OPS_ENQ_LAST,
+ .exit = (void *) enq_last_no_enq_fails_exit,
.timeout_ms = 1000U,
};
diff --git a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c
index 2a3eda5..73e6799 100644
--- a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c
+++ b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c
@@ -31,8 +31,12 @@ static enum scx_test_status run(void *ctx)
struct bpf_link *link;
link = bpf_map__attach_struct_ops(skel->maps.enq_last_no_enq_fails_ops);
- if (link) {
- SCX_ERR("Incorrectly succeeded in to attaching scheduler");
+ if (!link) {
+ SCX_ERR("Incorrectly failed at attaching scheduler");
+ return SCX_TEST_FAIL;
+ }
+ if (!skel->bss->exit_kind) {
+ SCX_ERR("Incorrectly stayed loaded");
return SCX_TEST_FAIL;
}
@@ -50,7 +54,7 @@ static void cleanup(void *ctx)
struct scx_test enq_last_no_enq_fails = {
.name = "enq_last_no_enq_fails",
- .description = "Verify we fail to load a scheduler if we specify "
+ .description = "Verify we eject a scheduler if we specify "
"the SCX_OPS_ENQ_LAST flag without defining "
"ops.enqueue()",
.setup = setup,
diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
index b3dfc10..1efb50d 100644
--- a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
+++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
@@ -36,8 +36,8 @@ void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p,
SEC(".struct_ops.link")
struct sched_ext_ops enq_select_cpu_fails_ops = {
- .select_cpu = enq_select_cpu_fails_select_cpu,
- .enqueue = enq_select_cpu_fails_enqueue,
+ .select_cpu = (void *) enq_select_cpu_fails_select_cpu,
+ .enqueue = (void *) enq_select_cpu_fails_enqueue,
.name = "enq_select_cpu_fails",
.timeout_ms = 1000U,
};
diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c
index ae12dda..d75d4fa 100644
--- a/tools/testing/selftests/sched_ext/exit.bpf.c
+++ b/tools/testing/selftests/sched_ext/exit.bpf.c
@@ -15,6 +15,8 @@ UEI_DEFINE(uei);
#define EXIT_CLEANLY() scx_bpf_exit(exit_point, "%d", exit_point)
+#define DSQ_ID 0
+
s32 BPF_STRUCT_OPS(exit_select_cpu, struct task_struct *p,
s32 prev_cpu, u64 wake_flags)
{
@@ -31,7 +33,7 @@ void BPF_STRUCT_OPS(exit_enqueue, struct task_struct *p, u64 enq_flags)
if (exit_point == EXIT_ENQUEUE)
EXIT_CLEANLY();
- scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+ scx_bpf_dispatch(p, DSQ_ID, SCX_SLICE_DFL, enq_flags);
}
void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p)
@@ -39,7 +41,7 @@ void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p)
if (exit_point == EXIT_DISPATCH)
EXIT_CLEANLY();
- scx_bpf_consume(SCX_DSQ_GLOBAL);
+ scx_bpf_consume(DSQ_ID);
}
void BPF_STRUCT_OPS(exit_enable, struct task_struct *p)
@@ -67,18 +69,18 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(exit_init)
if (exit_point == EXIT_INIT)
EXIT_CLEANLY();
- return 0;
+ return scx_bpf_create_dsq(DSQ_ID, -1);
}
SEC(".struct_ops.link")
struct sched_ext_ops exit_ops = {
- .select_cpu = exit_select_cpu,
- .enqueue = exit_enqueue,
- .dispatch = exit_dispatch,
- .init_task = exit_init_task,
- .enable = exit_enable,
- .exit = exit_exit,
- .init = exit_init,
+ .select_cpu = (void *) exit_select_cpu,
+ .enqueue = (void *) exit_enqueue,
+ .dispatch = (void *) exit_dispatch,
+ .init_task = (void *) exit_init_task,
+ .enable = (void *) exit_enable,
+ .exit = (void *) exit_exit,
+ .init = (void *) exit_init,
.name = "exit",
.timeout_ms = 1000U,
};
diff --git a/tools/testing/selftests/sched_ext/hotplug.bpf.c b/tools/testing/selftests/sched_ext/hotplug.bpf.c
index 8f2601d..6c9f25c 100644
--- a/tools/testing/selftests/sched_ext/hotplug.bpf.c
+++ b/tools/testing/selftests/sched_ext/hotplug.bpf.c
@@ -46,16 +46,16 @@ void BPF_STRUCT_OPS_SLEEPABLE(hotplug_cpu_offline, s32 cpu)
SEC(".struct_ops.link")
struct sched_ext_ops hotplug_cb_ops = {
- .cpu_online = hotplug_cpu_online,
- .cpu_offline = hotplug_cpu_offline,
- .exit = hotplug_exit,
+ .cpu_online = (void *) hotplug_cpu_online,
+ .cpu_offline = (void *) hotplug_cpu_offline,
+ .exit = (void *) hotplug_exit,
.name = "hotplug_cbs",
.timeout_ms = 1000U,
};
SEC(".struct_ops.link")
struct sched_ext_ops hotplug_nocb_ops = {
- .exit = hotplug_exit,
+ .exit = (void *) hotplug_exit,
.name = "hotplug_nocbs",
.timeout_ms = 1000U,
};
diff --git a/tools/testing/selftests/sched_ext/init_enable_count.bpf.c b/tools/testing/selftests/sched_ext/init_enable_count.bpf.c
index 47ea89a..5eb9edb 100644
--- a/tools/testing/selftests/sched_ext/init_enable_count.bpf.c
+++ b/tools/testing/selftests/sched_ext/init_enable_count.bpf.c
@@ -45,9 +45,9 @@ void BPF_STRUCT_OPS(cnt_disable, struct task_struct *p)
SEC(".struct_ops.link")
struct sched_ext_ops init_enable_count_ops = {
- .init_task = cnt_init_task,
- .exit_task = cnt_exit_task,
- .enable = cnt_enable,
- .disable = cnt_disable,
+ .init_task = (void *) cnt_init_task,
+ .exit_task = (void *) cnt_exit_task,
+ .enable = (void *) cnt_enable,
+ .disable = (void *) cnt_disable,
.name = "init_enable_count",
};
diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c
index 00bfa9c..4d4cd8d 100644
--- a/tools/testing/selftests/sched_ext/maximal.bpf.c
+++ b/tools/testing/selftests/sched_ext/maximal.bpf.c
@@ -131,34 +131,34 @@ void BPF_STRUCT_OPS(maximal_exit, struct scx_exit_info *info)
SEC(".struct_ops.link")
struct sched_ext_ops maximal_ops = {
- .select_cpu = maximal_select_cpu,
- .enqueue = maximal_enqueue,
- .dequeue = maximal_dequeue,
- .dispatch = maximal_dispatch,
- .runnable = maximal_runnable,
- .running = maximal_running,
- .stopping = maximal_stopping,
- .quiescent = maximal_quiescent,
- .yield = maximal_yield,
- .core_sched_before = maximal_core_sched_before,
- .set_weight = maximal_set_weight,
- .set_cpumask = maximal_set_cpumask,
- .update_idle = maximal_update_idle,
- .cpu_acquire = maximal_cpu_acquire,
- .cpu_release = maximal_cpu_release,
- .cpu_online = maximal_cpu_online,
- .cpu_offline = maximal_cpu_offline,
- .init_task = maximal_init_task,
- .enable = maximal_enable,
- .exit_task = maximal_exit_task,
- .disable = maximal_disable,
- .cgroup_init = maximal_cgroup_init,
- .cgroup_exit = maximal_cgroup_exit,
- .cgroup_prep_move = maximal_cgroup_prep_move,
- .cgroup_move = maximal_cgroup_move,
- .cgroup_cancel_move = maximal_cgroup_cancel_move,
- .cgroup_set_weight = maximal_cgroup_set_weight,
- .init = maximal_init,
- .exit = maximal_exit,
+ .select_cpu = (void *) maximal_select_cpu,
+ .enqueue = (void *) maximal_enqueue,
+ .dequeue = (void *) maximal_dequeue,
+ .dispatch = (void *) maximal_dispatch,
+ .runnable = (void *) maximal_runnable,
+ .running = (void *) maximal_running,
+ .stopping = (void *) maximal_stopping,
+ .quiescent = (void *) maximal_quiescent,
+ .yield = (void *) maximal_yield,
+ .core_sched_before = (void *) maximal_core_sched_before,
+ .set_weight = (void *) maximal_set_weight,
+ .set_cpumask = (void *) maximal_set_cpumask,
+ .update_idle = (void *) maximal_update_idle,
+ .cpu_acquire = (void *) maximal_cpu_acquire,
+ .cpu_release = (void *) maximal_cpu_release,
+ .cpu_online = (void *) maximal_cpu_online,
+ .cpu_offline = (void *) maximal_cpu_offline,
+ .init_task = (void *) maximal_init_task,
+ .enable = (void *) maximal_enable,
+ .exit_task = (void *) maximal_exit_task,
+ .disable = (void *) maximal_disable,
+ .cgroup_init = (void *) maximal_cgroup_init,
+ .cgroup_exit = (void *) maximal_cgroup_exit,
+ .cgroup_prep_move = (void *) maximal_cgroup_prep_move,
+ .cgroup_move = (void *) maximal_cgroup_move,
+ .cgroup_cancel_move = (void *) maximal_cgroup_cancel_move,
+ .cgroup_set_weight = (void *) maximal_cgroup_set_weight,
+ .init = (void *) maximal_init,
+ .exit = (void *) maximal_exit,
.name = "maximal",
};
diff --git a/tools/testing/selftests/sched_ext/maybe_null.bpf.c b/tools/testing/selftests/sched_ext/maybe_null.bpf.c
index 27d0f38..cf4ae87 100644
--- a/tools/testing/selftests/sched_ext/maybe_null.bpf.c
+++ b/tools/testing/selftests/sched_ext/maybe_null.bpf.c
@@ -29,8 +29,8 @@ bool BPF_STRUCT_OPS(maybe_null_success_yield, struct task_struct *from,
SEC(".struct_ops.link")
struct sched_ext_ops maybe_null_success = {
- .dispatch = maybe_null_success_dispatch,
- .yield = maybe_null_success_yield,
- .enable = maybe_null_running,
+ .dispatch = (void *) maybe_null_success_dispatch,
+ .yield = (void *) maybe_null_success_yield,
+ .enable = (void *) maybe_null_running,
.name = "minimal",
};
diff --git a/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c b/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c
index c064105..ec724d7 100644
--- a/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c
+++ b/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c
@@ -19,7 +19,7 @@ void BPF_STRUCT_OPS(maybe_null_fail_dispatch, s32 cpu, struct task_struct *p)
SEC(".struct_ops.link")
struct sched_ext_ops maybe_null_fail = {
- .dispatch = maybe_null_fail_dispatch,
- .enable = maybe_null_running,
+ .dispatch = (void *) maybe_null_fail_dispatch,
+ .enable = (void *) maybe_null_running,
.name = "maybe_null_fail_dispatch",
};
diff --git a/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c b/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c
index 3c17400..e6552ca 100644
--- a/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c
+++ b/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c
@@ -22,7 +22,7 @@ bool BPF_STRUCT_OPS(maybe_null_fail_yield, struct task_struct *from,
SEC(".struct_ops.link")
struct sched_ext_ops maybe_null_fail = {
- .yield = maybe_null_fail_yield,
- .enable = maybe_null_running,
+ .yield = (void *) maybe_null_fail_yield,
+ .enable = (void *) maybe_null_running,
.name = "maybe_null_fail_yield",
};
diff --git a/tools/testing/selftests/sched_ext/prog_run.bpf.c b/tools/testing/selftests/sched_ext/prog_run.bpf.c
index 6a4d7c4..00c2676 100644
--- a/tools/testing/selftests/sched_ext/prog_run.bpf.c
+++ b/tools/testing/selftests/sched_ext/prog_run.bpf.c
@@ -28,6 +28,6 @@ void BPF_STRUCT_OPS(prog_run_exit, struct scx_exit_info *ei)
SEC(".struct_ops.link")
struct sched_ext_ops prog_run_ops = {
- .exit = prog_run_exit,
+ .exit = (void *) prog_run_exit,
.name = "prog_run",
};
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c
index 2ed2991..f171ac4 100644
--- a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c
+++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c
@@ -35,6 +35,6 @@ void BPF_STRUCT_OPS(select_cpu_dfl_enqueue, struct task_struct *p,
SEC(".struct_ops.link")
struct sched_ext_ops select_cpu_dfl_ops = {
- .enqueue = select_cpu_dfl_enqueue,
+ .enqueue = (void *) select_cpu_dfl_enqueue,
.name = "select_cpu_dfl",
};
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c
index 4bb5abb..9efdbb7 100644
--- a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c
+++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c
@@ -82,8 +82,8 @@ s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_init_task,
SEC(".struct_ops.link")
struct sched_ext_ops select_cpu_dfl_nodispatch_ops = {
- .select_cpu = select_cpu_dfl_nodispatch_select_cpu,
- .enqueue = select_cpu_dfl_nodispatch_enqueue,
- .init_task = select_cpu_dfl_nodispatch_init_task,
+ .select_cpu = (void *) select_cpu_dfl_nodispatch_select_cpu,
+ .enqueue = (void *) select_cpu_dfl_nodispatch_enqueue,
+ .init_task = (void *) select_cpu_dfl_nodispatch_init_task,
.name = "select_cpu_dfl_nodispatch",
};
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c
index f0b96a4..59bfc4f3 100644
--- a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c
+++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c
@@ -35,7 +35,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_select_cpu, struct task_struct *p,
SEC(".struct_ops.link")
struct sched_ext_ops select_cpu_dispatch_ops = {
- .select_cpu = select_cpu_dispatch_select_cpu,
+ .select_cpu = (void *) select_cpu_dispatch_select_cpu,
.name = "select_cpu_dispatch",
.timeout_ms = 1000U,
};
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c
index 7b42ddc..3bbd5fc 100644
--- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c
+++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c
@@ -30,8 +30,8 @@ void BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_exit, struct scx_exit_info *ei)
SEC(".struct_ops.link")
struct sched_ext_ops select_cpu_dispatch_bad_dsq_ops = {
- .select_cpu = select_cpu_dispatch_bad_dsq_select_cpu,
- .exit = select_cpu_dispatch_bad_dsq_exit,
+ .select_cpu = (void *) select_cpu_dispatch_bad_dsq_select_cpu,
+ .exit = (void *) select_cpu_dispatch_bad_dsq_exit,
.name = "select_cpu_dispatch_bad_dsq",
.timeout_ms = 1000U,
};
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c
index 653e3dc..0fda57f 100644
--- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c
+++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c
@@ -31,8 +31,8 @@ void BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_exit, struct scx_exit_info *ei)
SEC(".struct_ops.link")
struct sched_ext_ops select_cpu_dispatch_dbl_dsp_ops = {
- .select_cpu = select_cpu_dispatch_dbl_dsp_select_cpu,
- .exit = select_cpu_dispatch_dbl_dsp_exit,
+ .select_cpu = (void *) select_cpu_dispatch_dbl_dsp_select_cpu,
+ .exit = (void *) select_cpu_dispatch_dbl_dsp_exit,
.name = "select_cpu_dispatch_dbl_dsp",
.timeout_ms = 1000U,
};
diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
index 7f3ebf4..e6c67bc 100644
--- a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
+++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
@@ -81,12 +81,12 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(select_cpu_vtime_init)
SEC(".struct_ops.link")
struct sched_ext_ops select_cpu_vtime_ops = {
- .select_cpu = select_cpu_vtime_select_cpu,
- .dispatch = select_cpu_vtime_dispatch,
- .running = select_cpu_vtime_running,
- .stopping = select_cpu_vtime_stopping,
- .enable = select_cpu_vtime_enable,
- .init = select_cpu_vtime_init,
+ .select_cpu = (void *) select_cpu_vtime_select_cpu,
+ .dispatch = (void *) select_cpu_vtime_dispatch,
+ .running = (void *) select_cpu_vtime_running,
+ .stopping = (void *) select_cpu_vtime_stopping,
+ .enable = (void *) select_cpu_vtime_enable,
+ .init = (void *) select_cpu_vtime_init,
.name = "select_cpu_vtime",
.timeout_ms = 1000U,
};
diff --git a/tools/testing/vma/vma.c b/tools/testing/vma/vma.c
index c53f220..b33b473 100644
--- a/tools/testing/vma/vma.c
+++ b/tools/testing/vma/vma.c
@@ -1522,6 +1522,45 @@ static bool test_copy_vma(void)
return true;
}
+static bool test_expand_only_mode(void)
+{
+ unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
+ struct mm_struct mm = {};
+ VMA_ITERATOR(vmi, &mm, 0);
+ struct vm_area_struct *vma_prev, *vma;
+ VMG_STATE(vmg, &mm, &vmi, 0x5000, 0x9000, flags, 5);
+
+ /*
+ * Place a VMA prior to the one we're expanding so we assert that we do
+ * not erroneously try to traverse to the previous VMA even though we
+ * have, through the use of VMG_FLAG_JUST_EXPAND, indicated we do not
+ * need to do so.
+ */
+ alloc_and_link_vma(&mm, 0, 0x2000, 0, flags);
+
+ /*
+ * We will be positioned at the prev VMA, but looking to expand to
+ * 0x9000.
+ */
+ vma_iter_set(&vmi, 0x3000);
+ vma_prev = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags);
+ vmg.prev = vma_prev;
+ vmg.merge_flags = VMG_FLAG_JUST_EXPAND;
+
+ vma = vma_merge_new_range(&vmg);
+ ASSERT_NE(vma, NULL);
+ ASSERT_EQ(vma, vma_prev);
+ ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS);
+ ASSERT_EQ(vma->vm_start, 0x3000);
+ ASSERT_EQ(vma->vm_end, 0x9000);
+ ASSERT_EQ(vma->vm_pgoff, 3);
+ ASSERT_TRUE(vma_write_started(vma));
+ ASSERT_EQ(vma_iter_addr(&vmi), 0x3000);
+
+ cleanup_mm(&mm, &vmi);
+ return true;
+}
+
int main(void)
{
int num_tests = 0, num_fail = 0;
@@ -1553,6 +1592,7 @@ int main(void)
TEST(vmi_prealloc_fail);
TEST(merge_extend);
TEST(copy_vma);
+ TEST(expand_only_mode);
#undef TEST
