From b9023b91dd020ad7e093baa5122b6968c48cc9e0 Mon Sep 17 00:00:00 2001 From: Balasubramani Vivekanandan Date: Thu, 26 Sep 2019 15:51:01 +0200 Subject: tick: broadcast-hrtimer: Fix a race in bc_set_next When a cpu requests broadcasting, before starting the tick broadcast hrtimer, bc_set_next() checks if the timer callback (bc_handler) is active using hrtimer_try_to_cancel(). But hrtimer_try_to_cancel() does not provide the required synchronization when the callback is active on other core. The callback could have already executed tick_handle_oneshot_broadcast() and could have also returned. But still there is a small time window where the hrtimer_try_to_cancel() returns -1. In that case bc_set_next() returns without doing anything, but the next_event of the tick broadcast clock device is already set to a timeout value. In the race condition diagram below, CPU #1 is running the timer callback and CPU #2 is entering idle state and so calls bc_set_next(). In the worst case, the next_event will contain an expiry time, but the hrtimer will not be started which happens when the racing callback returns HRTIMER_NORESTART. The hrtimer might never recover if all further requests from the CPUs to subscribe to tick broadcast have timeout greater than the next_event of tick broadcast clock device. This leads to cascading of failures and finally noticed as rcu stall warnings Here is a depiction of the race condition CPU #1 (Running timer callback) CPU #2 (Enter idle and subscribe to tick broadcast) --------------------- --------------------- __run_hrtimer() tick_broadcast_enter() bc_handler() __tick_broadcast_oneshot_control() tick_handle_oneshot_broadcast() raw_spin_lock(&tick_broadcast_lock); dev->next_event = KTIME_MAX; //wait for tick_broadcast_lock //next_event for tick broadcast clock set to KTIME_MAX since no other cores subscribed to tick broadcasting raw_spin_unlock(&tick_broadcast_lock); if (dev->next_event == KTIME_MAX) return HRTIMER_NORESTART // callback function exits without restarting the hrtimer //tick_broadcast_lock acquired raw_spin_lock(&tick_broadcast_lock); tick_broadcast_set_event() clockevents_program_event() dev->next_event = expires; bc_set_next() hrtimer_try_to_cancel() //returns -1 since the timer callback is active. Exits without restarting the timer cpu_base->running = NULL; The comment that hrtimer cannot be armed from within the callback is wrong. It is fine to start the hrtimer from within the callback. Also it is safe to start the hrtimer from the enter/exit idle code while the broadcast handler is active. The enter/exit idle code and the broadcast handler are synchronized using tick_broadcast_lock. So there is no need for the existing try to cancel logic. All this can be removed which will eliminate the race condition as well. Fixes: 5d1638acb9f6 ("tick: Introduce hrtimer based broadcast") Originally-by: Thomas Gleixner Signed-off-by: Balasubramani Vivekanandan Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190926135101.12102-2-balasubramani_vivekanandan@mentor.com --- kernel/time/tick-broadcast-hrtimer.c | 62 +++++++++++++++++------------------- 1 file changed, 29 insertions(+), 33 deletions(-) (limited to 'kernel') diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c index c1f5bb590b5e..b5a65e212df2 100644 --- a/kernel/time/tick-broadcast-hrtimer.c +++ b/kernel/time/tick-broadcast-hrtimer.c @@ -42,39 +42,39 @@ static int bc_shutdown(struct clock_event_device *evt) */ static int bc_set_next(ktime_t expires, struct clock_event_device *bc) { - int bc_moved; /* - * We try to cancel the timer first. If the callback is on - * flight on some other cpu then we let it handle it. If we - * were able to cancel the timer nothing can rearm it as we - * own broadcast_lock. + * This is called either from enter/exit idle code or from the + * broadcast handler. In all cases tick_broadcast_lock is held. * - * However we can also be called from the event handler of - * ce_broadcast_hrtimer itself when it expires. We cannot - * restart the timer because we are in the callback, but we - * can set the expiry time and let the callback return - * HRTIMER_RESTART. + * hrtimer_cancel() cannot be called here neither from the + * broadcast handler nor from the enter/exit idle code. The idle + * code can run into the problem described in bc_shutdown() and the + * broadcast handler cannot wait for itself to complete for obvious + * reasons. * - * Since we are in the idle loop at this point and because - * hrtimer_{start/cancel} functions call into tracing, - * calls to these functions must be bound within RCU_NONIDLE. + * Each caller tries to arm the hrtimer on its own CPU, but if the + * hrtimer callbback function is currently running, then + * hrtimer_start() cannot move it and the timer stays on the CPU on + * which it is assigned at the moment. + * + * As this can be called from idle code, the hrtimer_start() + * invocation has to be wrapped with RCU_NONIDLE() as + * hrtimer_start() can call into tracing. */ - RCU_NONIDLE( - { - bc_moved = hrtimer_try_to_cancel(&bctimer) >= 0; - if (bc_moved) { - hrtimer_start(&bctimer, expires, - HRTIMER_MODE_ABS_PINNED_HARD); - } - } - ); - - if (bc_moved) { - /* Bind the "device" to the cpu */ - bc->bound_on = smp_processor_id(); - } else if (bc->bound_on == smp_processor_id()) { - hrtimer_set_expires(&bctimer, expires); - } + RCU_NONIDLE( { + hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED_HARD); + /* + * The core tick broadcast mode expects bc->bound_on to be set + * correctly to prevent a CPU which has the broadcast hrtimer + * armed from going deep idle. + * + * As tick_broadcast_lock is held, nothing can change the cpu + * base which was just established in hrtimer_start() above. So + * the below access is safe even without holding the hrtimer + * base lock. + */ + bc->bound_on = bctimer.base->cpu_base->cpu; + } ); return 0; } @@ -100,10 +100,6 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t) { ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer); - if (clockevent_state_oneshot(&ce_broadcast_hrtimer)) - if (ce_broadcast_hrtimer.next_event != KTIME_MAX) - return HRTIMER_RESTART; - return HRTIMER_NORESTART; } -- cgit v1.2.3 From f14c234b4bc5184fd40d9a47830e5b32c3b36d49 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Tue, 1 Oct 2019 11:10:53 +1000 Subject: clone3: switch to copy_struct_from_user() Switch clone3() syscall from it's own copying struct clone_args from userspace to the new dedicated copy_struct_from_user() helper. The change is very straightforward, and helps unify the syscall interface for struct-from-userspace syscalls. Additionally, explicitly define CLONE_ARGS_SIZE_VER0 to match the other users of the struct-extension pattern. Signed-off-by: Aleksa Sarai Reviewed-by: Kees Cook Reviewed-by: Christian Brauner [christian.brauner@ubuntu.com: improve commit message] Link: https://lore.kernel.org/r/20191001011055.19283-3-cyphar@cyphar.com Signed-off-by: Christian Brauner --- kernel/fork.c | 34 +++++++--------------------------- 1 file changed, 7 insertions(+), 27 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index f9572f416126..2ef529869c64 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2525,39 +2525,19 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, #ifdef __ARCH_WANT_SYS_CLONE3 noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args __user *uargs, - size_t size) + size_t usize) { + int err; struct clone_args args; - if (unlikely(size > PAGE_SIZE)) + if (unlikely(usize > PAGE_SIZE)) return -E2BIG; - - if (unlikely(size < sizeof(struct clone_args))) + if (unlikely(usize < CLONE_ARGS_SIZE_VER0)) return -EINVAL; - if (unlikely(!access_ok(uargs, size))) - return -EFAULT; - - if (size > sizeof(struct clone_args)) { - unsigned char __user *addr; - unsigned char __user *end; - unsigned char val; - - addr = (void __user *)uargs + sizeof(struct clone_args); - end = (void __user *)uargs + size; - - for (; addr < end; addr++) { - if (get_user(val, addr)) - return -EFAULT; - if (val) - return -E2BIG; - } - - size = sizeof(struct clone_args); - } - - if (copy_from_user(&args, uargs, size)) - return -EFAULT; + err = copy_struct_from_user(&args, sizeof(args), uargs, usize); + if (err) + return err; /* * Verify that higher 32bits of exit_signal are unset and that -- cgit v1.2.3 From dff3a85feceade213daf153556fd32a3b0a73c63 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Tue, 1 Oct 2019 11:10:54 +1000 Subject: sched_setattr: switch to copy_struct_from_user() Switch sched_setattr() syscall from it's own copying struct sched_attr from userspace to the new dedicated copy_struct_from_user() helper. The change is very straightforward, and helps unify the syscall interface for struct-from-userspace syscalls. Ideally we could also unify sched_getattr(2)-style syscalls as well, but unfortunately the correct semantics for such syscalls are much less clear (see [1] for more detail). In future we could come up with a more sane idea for how the syscall interface should look. [1]: commit 1251201c0d34 ("sched/core: Fix uclamp ABI bug, clean up and robustify sched_read_attr() ABI logic and code") Signed-off-by: Aleksa Sarai Reviewed-by: Kees Cook Reviewed-by: Christian Brauner [christian.brauner@ubuntu.com: improve commit message] Link: https://lore.kernel.org/r/20191001011055.19283-4-cyphar@cyphar.com Signed-off-by: Christian Brauner --- kernel/sched/core.c | 43 +++++++------------------------------------ 1 file changed, 7 insertions(+), 36 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7880f4f64d0e..dd05a378631a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5106,9 +5106,6 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a u32 size; int ret; - if (!access_ok(uattr, SCHED_ATTR_SIZE_VER0)) - return -EFAULT; - /* Zero the full structure, so that a short copy will be nice: */ memset(attr, 0, sizeof(*attr)); @@ -5116,45 +5113,19 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a if (ret) return ret; - /* Bail out on silly large: */ - if (size > PAGE_SIZE) - goto err_size; - /* ABI compatibility quirk: */ if (!size) size = SCHED_ATTR_SIZE_VER0; - - if (size < SCHED_ATTR_SIZE_VER0) + if (size < SCHED_ATTR_SIZE_VER0 || size > PAGE_SIZE) goto err_size; - /* - * If we're handed a bigger struct than we know of, - * ensure all the unknown bits are 0 - i.e. new - * user-space does not rely on any kernel feature - * extensions we dont know about yet. - */ - if (size > sizeof(*attr)) { - unsigned char __user *addr; - unsigned char __user *end; - unsigned char val; - - addr = (void __user *)uattr + sizeof(*attr); - end = (void __user *)uattr + size; - - for (; addr < end; addr++) { - ret = get_user(val, addr); - if (ret) - return ret; - if (val) - goto err_size; - } - size = sizeof(*attr); + ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size); + if (ret) { + if (ret == -E2BIG) + goto err_size; + return ret; } - ret = copy_from_user(attr, uattr, size); - if (ret) - return -EFAULT; - if ((attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) && size < SCHED_ATTR_SIZE_VER1) return -EINVAL; @@ -5354,7 +5325,7 @@ sched_attr_copy_to_user(struct sched_attr __user *uattr, * sys_sched_getattr - similar to sched_getparam, but with sched_attr * @pid: the pid in question. * @uattr: structure containing the extended parameters. - * @usize: sizeof(attr) that user-space knows about, for forwards and backwards compatibility. + * @usize: sizeof(attr) for fwd/bwd comp. * @flags: for future extension. */ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, -- cgit v1.2.3 From c2ba8f41ad366dc12840dd87d8f1565185845126 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Tue, 1 Oct 2019 11:10:55 +1000 Subject: perf_event_open: switch to copy_struct_from_user() Switch perf_event_open() syscall from it's own copying struct perf_event_attr from userspace to the new dedicated copy_struct_from_user() helper. The change is very straightforward, and helps unify the syscall interface for struct-from-userspace syscalls. Signed-off-by: Aleksa Sarai Reviewed-by: Kees Cook Reviewed-by: Christian Brauner [christian.brauner@ubuntu.com: improve commit message] Link: https://lore.kernel.org/r/20191001011055.19283-5-cyphar@cyphar.com Signed-off-by: Christian Brauner --- kernel/events/core.c | 47 +++++++++-------------------------------------- 1 file changed, 9 insertions(+), 38 deletions(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 4655adbbae10..3f0cb82e4fbc 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10586,55 +10586,26 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, u32 size; int ret; - if (!access_ok(uattr, PERF_ATTR_SIZE_VER0)) - return -EFAULT; - - /* - * zero the full structure, so that a short copy will be nice. - */ + /* Zero the full structure, so that a short copy will be nice. */ memset(attr, 0, sizeof(*attr)); ret = get_user(size, &uattr->size); if (ret) return ret; - if (size > PAGE_SIZE) /* silly large */ - goto err_size; - - if (!size) /* abi compat */ + /* ABI compatibility quirk: */ + if (!size) size = PERF_ATTR_SIZE_VER0; - - if (size < PERF_ATTR_SIZE_VER0) + if (size < PERF_ATTR_SIZE_VER0 || size > PAGE_SIZE) goto err_size; - /* - * If we're handed a bigger struct than we know of, - * ensure all the unknown bits are 0 - i.e. new - * user-space does not rely on any kernel feature - * extensions we dont know about yet. - */ - if (size > sizeof(*attr)) { - unsigned char __user *addr; - unsigned char __user *end; - unsigned char val; - - addr = (void __user *)uattr + sizeof(*attr); - end = (void __user *)uattr + size; - - for (; addr < end; addr++) { - ret = get_user(val, addr); - if (ret) - return ret; - if (val) - goto err_size; - } - size = sizeof(*attr); + ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size); + if (ret) { + if (ret == -E2BIG) + goto err_size; + return ret; } - ret = copy_from_user(attr, uattr, size); - if (ret) - return -EFAULT; - attr->size = size; if (attr->__reserved_1) -- cgit v1.2.3 From 73956fc07dd7b25d4a33ab3fdd6247c60d0b237c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 1 Oct 2019 10:50:33 +0200 Subject: membarrier: Fix RCU locking bug caused by faulty merge The following commit: 227a4aadc75b ("sched/membarrier: Fix p->mm->membarrier_state racy load") got fat fingered by me when merging it with other patches. It meant to move the RCU section out of the for loop but ended up doing it partially, leaving a superfluous rcu_read_lock() inside, causing havok. Reported-by: Ingo Molnar Signed-off-by: Peter Zijlstra (Intel) Cc: Borislav Petkov Cc: Chris Metcalf Cc: Christoph Lameter Cc: Eric W. Biederman Cc: Kirill Tkhai Cc: Linus Torvalds Cc: Mathieu Desnoyers Cc: Mike Galbraith Cc: Oleg Nesterov Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Russell King - ARM Linux admin Cc: Thomas Gleixner Cc: linux-tip-commits@vger.kernel.org Fixes: 227a4aadc75b ("sched/membarrier: Fix p->mm->membarrier_state racy load") Link: https://lkml.kernel.org/r/20191001085033.GP4519@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/sched/membarrier.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index a39bed2c784f..168479a7d61b 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -174,7 +174,6 @@ static int membarrier_private_expedited(int flags) */ if (cpu == raw_smp_processor_id()) continue; - rcu_read_lock(); p = rcu_dereference(cpu_rq(cpu)->curr); if (p && p->mm == mm) __cpumask_set_cpu(cpu, tmpmask); -- cgit v1.2.3 From 501bd0166eb949820c8e4204e62aaee5c89c84d9 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 27 Sep 2019 17:28:42 +0200 Subject: fork: add kernel-doc for clone3 Add kernel-doc for the clone3() syscall. Link: https://lore.kernel.org/r/20191001114701.24661-2-christian.brauner@ubuntu.com Signed-off-by: Christian Brauner --- kernel/fork.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index f9572f416126..bf11cf39579a 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2604,6 +2604,17 @@ static bool clone3_args_valid(const struct kernel_clone_args *kargs) return true; } +/** + * clone3 - create a new process with specific properties + * @uargs: argument structure + * @size: size of @uargs + * + * clone3() is the extensible successor to clone()/clone2(). + * It takes a struct as argument that is versioned by its size. + * + * Return: On success, a positive PID for the child process. + * On error, a negative errno number. + */ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size) { int err; -- cgit v1.2.3 From 86cdd2fdc4e39c388d39c7ba2396d1a9dfd66226 Mon Sep 17 00:00:00 2001 From: Dmitry Goldin Date: Fri, 4 Oct 2019 10:40:07 +0000 Subject: kheaders: make headers archive reproducible In commit 43d8ce9d65a5 ("Provide in-kernel headers to make extending kernel easier") a new mechanism was introduced, for kernels >=5.2, which embeds the kernel headers in the kernel image or a module and exposes them in procfs for use by userland tools. The archive containing the header files has nondeterminism caused by header files metadata. This patch normalizes the metadata and utilizes KBUILD_BUILD_TIMESTAMP if provided and otherwise falls back to the default behaviour. In commit f7b101d33046 ("kheaders: Move from proc to sysfs") it was modified to use sysfs and the script for generation of the archive was renamed to what is being patched. Signed-off-by: Dmitry Goldin Reviewed-by: Greg Kroah-Hartman Reviewed-by: Joel Fernandes (Google) Signed-off-by: Masahiro Yamada --- kernel/gen_kheaders.sh | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index 9ff449888d9c..aff79e461fc9 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -71,7 +71,10 @@ done | cpio --quiet -pd $cpio_dir >/dev/null 2>&1 find $cpio_dir -type f -print0 | xargs -0 -P8 -n1 perl -pi -e 'BEGIN {undef $/;}; s/\/\*((?!SPDX).)*?\*\///smg;' -tar -Jcf $tarfile -C $cpio_dir/ . > /dev/null +# Create archive and try to normalize metadata for reproducibility +tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \ + --owner=0 --group=0 --sort=name --numeric-owner \ + -Jcf $tarfile -C $cpio_dir/ . > /dev/null echo "$src_files_md5" > kernel/kheaders.md5 echo "$obj_files_md5" >> kernel/kheaders.md5 -- cgit v1.2.3 From 2cf2aa6a69db0b17b3979144287af8775c1c1534 Mon Sep 17 00:00:00 2001 From: Andrey Smirnov Date: Sat, 5 Oct 2019 10:23:30 +0200 Subject: dma-mapping: fix false positivse warnings in dma_common_free_remap() Commit 5cf4537975bb ("dma-mapping: introduce a dma_common_find_pages helper") changed invalid input check in dma_common_free_remap() from: if (!area || !area->flags != VM_DMA_COHERENT) to if (!area || !area->flags != VM_DMA_COHERENT || !area->pages) which seem to produce false positives for memory obtained via dma_common_contiguous_remap() This triggers the following warning message when doing "reboot" on ZII VF610 Dev Board Rev B: WARNING: CPU: 0 PID: 1 at kernel/dma/remap.c:112 dma_common_free_remap+0x88/0x8c trying to free invalid coherent area: 9ef82980 Modules linked in: CPU: 0 PID: 1 Comm: systemd-shutdow Not tainted 5.3.0-rc6-next-20190820 #119 Hardware name: Freescale Vybrid VF5xx/VF6xx (Device Tree) Backtrace: [<8010d1ec>] (dump_backtrace) from [<8010d588>] (show_stack+0x20/0x24) r7:8015ed78 r6:00000009 r5:00000000 r4:9f4d9b14 [<8010d568>] (show_stack) from [<8077e3f0>] (dump_stack+0x24/0x28) [<8077e3cc>] (dump_stack) from [<801197a0>] (__warn.part.3+0xcc/0xe4) [<801196d4>] (__warn.part.3) from [<80119830>] (warn_slowpath_fmt+0x78/0x94) r6:00000070 r5:808e540c r4:81c03048 [<801197bc>] (warn_slowpath_fmt) from [<8015ed78>] (dma_common_free_remap+0x88/0x8c) r3:9ef82980 r2:808e53e0 r7:00001000 r6:a0b1e000 r5:a0b1e000 r4:00001000 [<8015ecf0>] (dma_common_free_remap) from [<8010fa9c>] (remap_allocator_free+0x60/0x68) r5:81c03048 r4:9f4d9b78 [<8010fa3c>] (remap_allocator_free) from [<801100d0>] (__arm_dma_free.constprop.3+0xf8/0x148) r5:81c03048 r4:9ef82900 [<8010ffd8>] (__arm_dma_free.constprop.3) from [<80110144>] (arm_dma_free+0x24/0x2c) r5:9f563410 r4:80110120 [<80110120>] (arm_dma_free) from [<8015d80c>] (dma_free_attrs+0xa0/0xdc) [<8015d76c>] (dma_free_attrs) from [<8020f3e4>] (dma_pool_destroy+0xc0/0x154) r8:9efa8860 r7:808f02f0 r6:808f02d0 r5:9ef82880 r4:9ef82780 [<8020f324>] (dma_pool_destroy) from [<805525d0>] (ehci_mem_cleanup+0x6c/0x150) r7:9f563410 r6:9efa8810 r5:00000000 r4:9efd0148 [<80552564>] (ehci_mem_cleanup) from [<80558e0c>] (ehci_stop+0xac/0xc0) r5:9efd0148 r4:9efd0000 [<80558d60>] (ehci_stop) from [<8053c4bc>] (usb_remove_hcd+0xf4/0x1b0) r7:9f563410 r6:9efd0074 r5:81c03048 r4:9efd0000 [<8053c3c8>] (usb_remove_hcd) from [<8056361c>] (host_stop+0x48/0xb8) r7:9f563410 r6:9efd0000 r5:9f5f4040 r4:9f5f5040 [<805635d4>] (host_stop) from [<80563d0c>] (ci_hdrc_host_destroy+0x34/0x38) r7:9f563410 r6:9f5f5040 r5:9efa8800 r4:9f5f4040 [<80563cd8>] (ci_hdrc_host_destroy) from [<8055ef18>] (ci_hdrc_remove+0x50/0x10c) [<8055eec8>] (ci_hdrc_remove) from [<804a2ed8>] (platform_drv_remove+0x34/0x4c) r7:9f563410 r6:81c4f99c r5:9efa8810 r4:9efa8810 [<804a2ea4>] (platform_drv_remove) from [<804a18a8>] (device_release_driver_internal+0xec/0x19c) r5:00000000 r4:9efa8810 [<804a17bc>] (device_release_driver_internal) from [<804a1978>] (device_release_driver+0x20/0x24) r7:9f563410 r6:81c41ed0 r5:9efa8810 r4:9f4a1dac [<804a1958>] (device_release_driver) from [<804a01b8>] (bus_remove_device+0xdc/0x108) [<804a00dc>] (bus_remove_device) from [<8049c204>] (device_del+0x150/0x36c) r7:9f563410 r6:81c03048 r5:9efa8854 r4:9efa8810 [<8049c0b4>] (device_del) from [<804a3368>] (platform_device_del.part.2+0x20/0x84) r10:9f563414 r9:809177e0 r8:81cb07dc r7:81c78320 r6:9f563454 r5:9efa8800 r4:9efa8800 [<804a3348>] (platform_device_del.part.2) from [<804a3420>] (platform_device_unregister+0x28/0x34) r5:9f563400 r4:9efa8800 [<804a33f8>] (platform_device_unregister) from [<8055dce0>] (ci_hdrc_remove_device+0x1c/0x30) r5:9f563400 r4:00000001 [<8055dcc4>] (ci_hdrc_remove_device) from [<805652ac>] (ci_hdrc_imx_remove+0x38/0x118) r7:81c78320 r6:9f563454 r5:9f563410 r4:9f541010 [<8056538c>] (ci_hdrc_imx_shutdown) from [<804a2970>] (platform_drv_shutdown+0x2c/0x30) [<804a2944>] (platform_drv_shutdown) from [<8049e4fc>] (device_shutdown+0x158/0x1f0) [<8049e3a4>] (device_shutdown) from [<8013ac80>] (kernel_restart_prepare+0x44/0x48) r10:00000058 r9:9f4d8000 r8:fee1dead r7:379ce700 r6:81c0b280 r5:81c03048 r4:00000000 [<8013ac3c>] (kernel_restart_prepare) from [<8013ad14>] (kernel_restart+0x1c/0x60) [<8013acf8>] (kernel_restart) from [<8013af84>] (__do_sys_reboot+0xe0/0x1d8) r5:81c03048 r4:00000000 [<8013aea4>] (__do_sys_reboot) from [<8013b0ec>] (sys_reboot+0x18/0x1c) r8:80101204 r7:00000058 r6:00000000 r5:00000000 r4:00000000 [<8013b0d4>] (sys_reboot) from [<80101000>] (ret_fast_syscall+0x0/0x54) Exception stack(0x9f4d9fa8 to 0x9f4d9ff0) 9fa0: 00000000 00000000 fee1dead 28121969 01234567 379ce700 9fc0: 00000000 00000000 00000000 00000058 00000000 00000000 00000000 00016d04 9fe0: 00028e0c 7ec87c64 000135ec 76c1f410 Restore original invalid input check in dma_common_free_remap() to avoid this problem. Fixes: 5cf4537975bb ("dma-mapping: introduce a dma_common_find_pages helper") Signed-off-by: Andrey Smirnov [hch: just revert the offending hunk instead of creating a new helper] Signed-off-by: Christoph Hellwig --- kernel/dma/remap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index ca4e5d44b571..c00b9258fa6a 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -87,9 +87,9 @@ void *dma_common_contiguous_remap(struct page *page, size_t size, */ void dma_common_free_remap(void *cpu_addr, size_t size) { - struct page **pages = dma_common_find_pages(cpu_addr); + struct vm_struct *area = find_vm_area(cpu_addr); - if (!pages) { + if (!area || area->flags != VM_DMA_COHERENT) { WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr); return; } -- cgit v1.2.3 From 0e48f51cbbfbdb79149806de14dcb8bf0f01ca94 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Fri, 4 Oct 2019 13:00:25 +0300 Subject: Revert "libata, freezer: avoid block device removal while system is frozen" This reverts commit 85fbd722ad0f5d64d1ad15888cd1eb2188bfb557. The commit was added as a quick band-aid for a hang that happened when a block device was removed during system suspend. Now that bdi_wq is not freezable anymore the hang should not be possible and we can get rid of this hack by reverting it. Acked-by: Rafael J. Wysocki Signed-off-by: Mika Westerberg Signed-off-by: Jens Axboe --- kernel/freezer.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'kernel') diff --git a/kernel/freezer.c b/kernel/freezer.c index c0738424bb43..dc520f01f99d 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -22,12 +22,6 @@ EXPORT_SYMBOL(system_freezing_cnt); bool pm_freezing; bool pm_nosig_freezing; -/* - * Temporary export for the deadlock workaround in ata_scsi_hotplug(). - * Remove once the hack becomes unnecessary. - */ -EXPORT_SYMBOL_GPL(pm_freezing); - /* protects freezing and frozen transitions */ static DEFINE_SPINLOCK(freezer_lock); -- cgit v1.2.3 From f733c6b508bcaa3441ba1eacf16efb9abd47489f Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 4 Oct 2019 15:57:29 +0300 Subject: perf/core: Fix inheritance of aux_output groups Commit: ab43762ef010 ("perf: Allow normal events to output AUX data") forgets to configure aux_output relation in the inherited groups, which results in child PEBS events forever failing to schedule. Fix this by setting up the AUX output link in the inheritance path. Signed-off-by: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191004125729.32397-1-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 3f0cb82e4fbc..f953dd16a5e2 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -11862,6 +11862,10 @@ static int inherit_group(struct perf_event *parent_event, child, leader, child_ctx); if (IS_ERR(child_ctr)) return PTR_ERR(child_ctr); + + if (sub->aux_event == parent_event && + !perf_get_aux_event(child_ctr, leader)) + return -EINVAL; } return 0; } -- cgit v1.2.3 From 20bb759a66be52cf4a9ddd17fddaf509e11490cd Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Sun, 6 Oct 2019 17:58:00 -0700 Subject: panic: ensure preemption is disabled during panic() Calling 'panic()' on a kernel with CONFIG_PREEMPT=y can leave the calling CPU in an infinite loop, but with interrupts and preemption enabled. From this state, userspace can continue to be scheduled, despite the system being "dead" as far as the kernel is concerned. This is easily reproducible on arm64 when booting with "nosmp" on the command line; a couple of shell scripts print out a periodic "Ping" message whilst another triggers a crash by writing to /proc/sysrq-trigger: | sysrq: Trigger a crash | Kernel panic - not syncing: sysrq triggered crash | CPU: 0 PID: 1 Comm: init Not tainted 5.2.15 #1 | Hardware name: linux,dummy-virt (DT) | Call trace: | dump_backtrace+0x0/0x148 | show_stack+0x14/0x20 | dump_stack+0xa0/0xc4 | panic+0x140/0x32c | sysrq_handle_reboot+0x0/0x20 | __handle_sysrq+0x124/0x190 | write_sysrq_trigger+0x64/0x88 | proc_reg_write+0x60/0xa8 | __vfs_write+0x18/0x40 | vfs_write+0xa4/0x1b8 | ksys_write+0x64/0xf0 | __arm64_sys_write+0x14/0x20 | el0_svc_common.constprop.0+0xb0/0x168 | el0_svc_handler+0x28/0x78 | el0_svc+0x8/0xc | Kernel Offset: disabled | CPU features: 0x0002,24002004 | Memory Limit: none | ---[ end Kernel panic - not syncing: sysrq triggered crash ]--- | Ping 2! | Ping 1! | Ping 1! | Ping 2! The issue can also be triggered on x86 kernels if CONFIG_SMP=n, otherwise local interrupts are disabled in 'smp_send_stop()'. Disable preemption in 'panic()' before re-enabling interrupts. Link: http://lkml.kernel.org/r/20191002123538.22609-1-will@kernel.org Link: https://lore.kernel.org/r/BX1W47JXPMR8.58IYW53H6M5N@dragonstone Signed-off-by: Will Deacon Reported-by: Xogium Reviewed-by: Kees Cook Cc: Russell King Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: Petr Mladek Cc: Feng Tang Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/panic.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/panic.c b/kernel/panic.c index 47e8ebccc22b..f470a038b05b 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -180,6 +180,7 @@ void panic(const char *fmt, ...) * after setting panic_cpu) from invoking panic() again. */ local_irq_disable(); + preempt_disable_notrace(); /* * It's possible to come here directly from a panic-assertion and -- cgit v1.2.3 From b0f53dbc4bc4c371f38b14c391095a3bb8a0bb40 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Sun, 6 Oct 2019 17:58:19 -0700 Subject: kernel/sysctl.c: do not override max_threads provided by userspace Partially revert 16db3d3f1170 ("kernel/sysctl.c: threads-max observe limits") because the patch is causing a regression to any workload which needs to override the auto-tuning of the limit provided by kernel. set_max_threads is implementing a boot time guesstimate to provide a sensible limit of the concurrently running threads so that runaways will not deplete all the memory. This is a good thing in general but there are workloads which might need to increase this limit for an application to run (reportedly WebSpher MQ is affected) and that is simply not possible after the mentioned change. It is also very dubious to override an admin decision by an estimation that doesn't have any direct relation to correctness of the kernel operation. Fix this by dropping set_max_threads from sysctl_max_threads so any value is accepted as long as it fits into MAX_THREADS which is important to check because allowing more threads could break internal robust futex restriction. While at it, do not use MIN_THREADS as the lower boundary because it is also only a heuristic for automatic estimation and admin might have a good reason to stop new threads to be created even when below this limit. This became more severe when we switched x86 from 4k to 8k kernel stacks. Starting since 6538b8ea886e ("x86_64: expand kernel stack to 16K") (3.16) we use THREAD_SIZE_ORDER = 2 and that halved the auto-tuned value. In the particular case 3.12 kernel.threads-max = 515561 4.4 kernel.threads-max = 200000 Neither of the two values is really insane on 32GB machine. I am not sure we want/need to tune the max_thread value further. If anything the tuning should be removed altogether if proven not useful in general. But we definitely need a way to override this auto-tuning. Link: http://lkml.kernel.org/r/20190922065801.GB18814@dhcp22.suse.cz Fixes: 16db3d3f1170 ("kernel/sysctl.c: threads-max observe limits") Signed-off-by: Michal Hocko Reviewed-by: "Eric W. Biederman" Cc: Heinrich Schuchardt Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 1f6c45f6a734..bcdf53125210 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2925,7 +2925,7 @@ int sysctl_max_threads(struct ctl_table *table, int write, struct ctl_table t; int ret; int threads = max_threads; - int min = MIN_THREADS; + int min = 1; int max = MAX_THREADS; t = *table; @@ -2937,7 +2937,7 @@ int sysctl_max_threads(struct ctl_table *table, int write, if (ret || !write) return ret; - set_max_threads(threads); + max_threads = threads; return 0; } -- cgit v1.2.3 From 4929a4e6faa0f13289a67cae98139e727f0d4a97 Mon Sep 17 00:00:00 2001 From: Xuewei Zhang Date: Thu, 3 Oct 2019 17:12:43 -0700 Subject: sched/fair: Scale bandwidth quota and period without losing quota/period ratio precision The quota/period ratio is used to ensure a child task group won't get more bandwidth than the parent task group, and is calculated as: normalized_cfs_quota() = [(quota_us << 20) / period_us] If the quota/period ratio was changed during this scaling due to precision loss, it will cause inconsistency between parent and child task groups. See below example: A userspace container manager (kubelet) does three operations: 1) Create a parent cgroup, set quota to 1,000us and period to 10,000us. 2) Create a few children cgroups. 3) Set quota to 1,000us and period to 10,000us on a child cgroup. These operations are expected to succeed. However, if the scaling of 147/128 happens before step 3, quota and period of the parent cgroup will be changed: new_quota: 1148437ns, 1148us new_period: 11484375ns, 11484us And when step 3 comes in, the ratio of the child cgroup will be 104857, which will be larger than the parent cgroup ratio (104821), and will fail. Scaling them by a factor of 2 will fix the problem. Tested-by: Phil Auld Signed-off-by: Xuewei Zhang Signed-off-by: Peter Zijlstra (Intel) Acked-by: Phil Auld Cc: Anton Blanchard Cc: Ben Segall Cc: Dietmar Eggemann Cc: Juri Lelli Cc: Linus Torvalds Cc: Mel Gorman Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vincent Guittot Fixes: 2e8e19226398 ("sched/fair: Limit sched_cfs_period_timer() loop to avoid hard lockup") Link: https://lkml.kernel.org/r/20191004001243.140897-1-xueweiz@google.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 36 ++++++++++++++++++++++-------------- 1 file changed, 22 insertions(+), 14 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 83ab35e2374f..682a754ea3e1 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4926,20 +4926,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) if (++count > 3) { u64 new, old = ktime_to_ns(cfs_b->period); - new = (old * 147) / 128; /* ~115% */ - new = min(new, max_cfs_quota_period); - - cfs_b->period = ns_to_ktime(new); - - /* since max is 1s, this is limited to 1e9^2, which fits in u64 */ - cfs_b->quota *= new; - cfs_b->quota = div64_u64(cfs_b->quota, old); - - pr_warn_ratelimited( - "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n", - smp_processor_id(), - div_u64(new, NSEC_PER_USEC), - div_u64(cfs_b->quota, NSEC_PER_USEC)); + /* + * Grow period by a factor of 2 to avoid losing precision. + * Precision loss in the quota/period ratio can cause __cfs_schedulable + * to fail. + */ + new = old * 2; + if (new < max_cfs_quota_period) { + cfs_b->period = ns_to_ktime(new); + cfs_b->quota *= 2; + + pr_warn_ratelimited( + "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us = %lld, cfs_quota_us = %lld)\n", + smp_processor_id(), + div_u64(new, NSEC_PER_USEC), + div_u64(cfs_b->quota, NSEC_PER_USEC)); + } else { + pr_warn_ratelimited( + "cfs_period_timer[cpu%d]: period too short, but cannot scale up without losing precision (cfs_period_us = %lld, cfs_quota_us = %lld)\n", + smp_processor_id(), + div_u64(old, NSEC_PER_USEC), + div_u64(cfs_b->quota, NSEC_PER_USEC)); + } /* reset count so we don't come right back in here */ count = 0; -- cgit v1.2.3 From 68e7a4d66b0ce04bf18ff2ffded5596ab3618585 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 25 Sep 2019 23:42:42 +0200 Subject: sched/vtime: Fix guest/system mis-accounting on task switch vtime_account_system() assumes that the target task to account cputime to is always the current task. This is most often true indeed except on task switch where we call: vtime_common_task_switch(prev) vtime_account_system(prev) Here prev is the scheduling-out task where we account the cputime to. It doesn't match current that is already the scheduling-in task at this stage of the context switch. So we end up checking the wrong task flags to determine if we are accounting guest or system time to the previous task. As a result the wrong task is used to check if the target is running in guest mode. We may then spuriously account or leak either system or guest time on task switch. Fix this assumption and also turn vtime_guest_enter/exit() to use the task passed in parameter as well to avoid future similar issues. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Wanpeng Li Fixes: 2a42eb9594a1 ("sched/cputime: Accumulate vtime on top of nsec clocksource") Link: https://lkml.kernel.org/r/20190925214242.21873-1-frederic@kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/cputime.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 2305ce89a26c..46ed4e1383e2 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -740,7 +740,7 @@ void vtime_account_system(struct task_struct *tsk) write_seqcount_begin(&vtime->seqcount); /* We might have scheduled out from guest path */ - if (current->flags & PF_VCPU) + if (tsk->flags & PF_VCPU) vtime_account_guest(tsk, vtime); else __vtime_account_system(tsk, vtime); @@ -783,7 +783,7 @@ void vtime_guest_enter(struct task_struct *tsk) */ write_seqcount_begin(&vtime->seqcount); __vtime_account_system(tsk, vtime); - current->flags |= PF_VCPU; + tsk->flags |= PF_VCPU; write_seqcount_end(&vtime->seqcount); } EXPORT_SYMBOL_GPL(vtime_guest_enter); @@ -794,7 +794,7 @@ void vtime_guest_exit(struct task_struct *tsk) write_seqcount_begin(&vtime->seqcount); vtime_account_guest(tsk, vtime); - current->flags &= ~PF_VCPU; + tsk->flags &= ~PF_VCPU; write_seqcount_end(&vtime->seqcount); } EXPORT_SYMBOL_GPL(vtime_guest_exit); -- cgit v1.2.3 From d44248a41337731a111374822d7d4451b64e73e4 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Wed, 4 Sep 2019 14:46:18 -0700 Subject: perf/core: Rework memory accounting in perf_mmap() perf_mmap() always increases user->locked_vm. As a result, "extra" could grow bigger than "user_extra", which doesn't make sense. Here is an example case: (Note: Assume "user_lock_limit" is very small.) | # of perf_mmap calls |vma->vm_mm->pinned_vm|user->locked_vm| | 0 | 0 | 0 | | 1 | user_extra | user_extra | | 2 | 3 * user_extra | 2 * user_extra| | 3 | 6 * user_extra | 3 * user_extra| | 4 | 10 * user_extra | 4 * user_extra| Fix this by maintaining proper user_extra and extra. Reviewed-By: Hechao Li Reported-by: Hechao Li Signed-off-by: Song Liu Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Jie Meng Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20190904214618.3795672-1-songliubraving@fb.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index f953dd16a5e2..2b8265ad7bf5 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5668,7 +5668,8 @@ again: * undo the VM accounting. */ - atomic_long_sub((size >> PAGE_SHIFT) + 1, &mmap_user->locked_vm); + atomic_long_sub((size >> PAGE_SHIFT) + 1 - mmap_locked, + &mmap_user->locked_vm); atomic64_sub(mmap_locked, &vma->vm_mm->pinned_vm); free_uid(mmap_user); @@ -5812,8 +5813,20 @@ accounting: user_locked = atomic_long_read(&user->locked_vm) + user_extra; - if (user_locked > user_lock_limit) + if (user_locked <= user_lock_limit) { + /* charge all to locked_vm */ + } else if (atomic_long_read(&user->locked_vm) >= user_lock_limit) { + /* charge all to pinned_vm */ + extra = user_extra; + user_extra = 0; + } else { + /* + * charge locked_vm until it hits user_lock_limit; + * charge the rest from pinned_vm + */ extra = user_locked - user_lock_limit; + user_extra -= extra; + } lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; -- cgit v1.2.3 From 7fa343b7fdc4f351de4e3f28d5c285937dd1f42f Mon Sep 17 00:00:00 2001 From: Song Liu Date: Tue, 8 Oct 2019 09:59:49 -0700 Subject: perf/core: Fix corner case in perf_rotate_context() In perf_rotate_context(), when the first cpu flexible event fail to schedule, cpu_rotate is 1, while cpu_event is NULL. Since cpu_event is NULL, perf_rotate_context will _NOT_ call cpu_ctx_sched_out(), thus cpuctx->ctx.is_active will have EVENT_FLEXIBLE set. Then, the next perf_event_sched_in() will skip all cpu flexible events because of the EVENT_FLEXIBLE bit. In the next call of perf_rotate_context(), cpu_rotate stays 1, and cpu_event stays NULL, so this process repeats. The end result is, flexible events on this cpu will not be scheduled (until another event being added to the cpuctx). Here is an easy repro of this issue. On Intel CPUs, where ref-cycles could only use one counter, run one pinned event for ref-cycles, one flexible event for ref-cycles, and one flexible event for cycles. The flexible ref-cycles is never scheduled, which is expected. However, because of this issue, the cycles event is never scheduled either. $ perf stat -e ref-cycles:D,ref-cycles,cycles -C 5 -I 1000 time counts unit events 1.000152973 15,412,480 ref-cycles:D 1.000152973 ref-cycles (0.00%) 1.000152973 cycles (0.00%) 2.000486957 18,263,120 ref-cycles:D 2.000486957 ref-cycles (0.00%) 2.000486957 cycles (0.00%) To fix this, when the flexible_active list is empty, try rotate the first event in the flexible_groups. Also, rename ctx_first_active() to ctx_event_to_rotate(), which is more accurate. Signed-off-by: Song Liu Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Sasha Levin Cc: Thomas Gleixner Fixes: 8d5bce0c37fa ("perf/core: Optimize perf_rotate_context() event scheduling") Link: https://lkml.kernel.org/r/20191008165949.920548-1-songliubraving@fb.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 2b8265ad7bf5..9ec0b0bfddbd 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3779,11 +3779,23 @@ static void rotate_ctx(struct perf_event_context *ctx, struct perf_event *event) perf_event_groups_insert(&ctx->flexible_groups, event); } +/* pick an event from the flexible_groups to rotate */ static inline struct perf_event * -ctx_first_active(struct perf_event_context *ctx) +ctx_event_to_rotate(struct perf_event_context *ctx) { - return list_first_entry_or_null(&ctx->flexible_active, - struct perf_event, active_list); + struct perf_event *event; + + /* pick the first active flexible event */ + event = list_first_entry_or_null(&ctx->flexible_active, + struct perf_event, active_list); + + /* if no active flexible event, pick the first event */ + if (!event) { + event = rb_entry_safe(rb_first(&ctx->flexible_groups.tree), + typeof(*event), group_node); + } + + return event; } static bool perf_rotate_context(struct perf_cpu_context *cpuctx) @@ -3808,9 +3820,9 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx) perf_pmu_disable(cpuctx->ctx.pmu); if (task_rotate) - task_event = ctx_first_active(task_ctx); + task_event = ctx_event_to_rotate(task_ctx); if (cpu_rotate) - cpu_event = ctx_first_active(&cpuctx->ctx); + cpu_event = ctx_event_to_rotate(&cpuctx->ctx); /* * As per the order given at ctx_resched() first 'pop' task flexible -- cgit v1.2.3 From f49249d58abdc12067d69f15d509487171148b30 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Tue, 8 Oct 2019 11:46:46 +0100 Subject: PM: sleep: include for pm_wq Include the for the definition of pm_wq to avoid the following warning: kernel/power/main.c:890:25: warning: symbol 'pm_wq' was not declared. Should it be static? Signed-off-by: Ben Dooks Signed-off-by: Rafael J. Wysocki --- kernel/power/main.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/power/main.c b/kernel/power/main.c index e8710d179b35..e26de7af520b 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -15,6 +15,7 @@ #include #include #include +#include #include "power.h" -- cgit v1.2.3 From 9ef16693aff8137faa21d16ffe65bb9832d24d71 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 11 Oct 2019 17:56:57 -0400 Subject: ftrace: Get a reference counter for the trace_array on filter files The ftrace set_ftrace_filter and set_ftrace_notrace files are specific for an instance now. They need to take a reference to the instance otherwise there could be a race between accessing the files and deleting the instance. It wasn't until the :mod: caching where these file operations started referencing the trace_array directly. Cc: stable@vger.kernel.org Fixes: 673feb9d76ab3 ("ftrace: Add :mod: caching infrastructure to trace_array") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 62a50bf399d6..32c2eb167de0 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3540,21 +3540,22 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, struct ftrace_hash *hash; struct list_head *mod_head; struct trace_array *tr = ops->private; - int ret = 0; + int ret = -ENOMEM; ftrace_ops_init(ops); if (unlikely(ftrace_disabled)) return -ENODEV; + if (tr && trace_array_get(tr) < 0) + return -ENODEV; + iter = kzalloc(sizeof(*iter), GFP_KERNEL); if (!iter) - return -ENOMEM; + goto out; - if (trace_parser_get_init(&iter->parser, FTRACE_BUFF_MAX)) { - kfree(iter); - return -ENOMEM; - } + if (trace_parser_get_init(&iter->parser, FTRACE_BUFF_MAX)) + goto out; iter->ops = ops; iter->flags = flag; @@ -3584,13 +3585,13 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, if (!iter->hash) { trace_parser_put(&iter->parser); - kfree(iter); - ret = -ENOMEM; goto out_unlock; } } else iter->hash = hash; + ret = 0; + if (file->f_mode & FMODE_READ) { iter->pg = ftrace_pages_start; @@ -3602,7 +3603,6 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, /* Failed */ free_ftrace_hash(iter->hash); trace_parser_put(&iter->parser); - kfree(iter); } } else file->private_data = iter; @@ -3610,6 +3610,13 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, out_unlock: mutex_unlock(&ops->func_hash->regex_lock); + out: + if (ret) { + kfree(iter); + if (tr) + trace_array_put(tr); + } + return ret; } @@ -5037,6 +5044,8 @@ int ftrace_regex_release(struct inode *inode, struct file *file) mutex_unlock(&iter->ops->func_hash->regex_lock); free_ftrace_hash(iter->hash); + if (iter->tr) + trace_array_put(iter->tr); kfree(iter); return 0; -- cgit v1.2.3 From 194c2c74f5532e62c218adeb8e2b683119503907 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 11 Oct 2019 18:19:17 -0400 Subject: tracing: Get trace_array reference for available_tracers files As instances may have different tracers available, we need to look at the trace_array descriptor that shows the list of the available tracers for the instance. But there's a race between opening the file and an admin deleting the instance. The trace_array_get() needs to be called before accessing the trace_array. Cc: stable@vger.kernel.org Fixes: 607e2ea167e56 ("tracing: Set up infrastructure to allow tracers for instances") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 252f79c435f8..fa7d813b04c6 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4355,9 +4355,14 @@ static int show_traces_open(struct inode *inode, struct file *file) if (tracing_disabled) return -ENODEV; + if (trace_array_get(tr) < 0) + return -ENODEV; + ret = seq_open(file, &show_traces_seq_ops); - if (ret) + if (ret) { + trace_array_put(tr); return ret; + } m = file->private_data; m->private = tr; @@ -4365,6 +4370,14 @@ static int show_traces_open(struct inode *inode, struct file *file) return 0; } +static int show_traces_release(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + + trace_array_put(tr); + return seq_release(inode, file); +} + static ssize_t tracing_write_stub(struct file *filp, const char __user *ubuf, size_t count, loff_t *ppos) @@ -4395,8 +4408,8 @@ static const struct file_operations tracing_fops = { static const struct file_operations show_traces_fops = { .open = show_traces_open, .read = seq_read, - .release = seq_release, .llseek = seq_lseek, + .release = show_traces_release, }; static ssize_t -- cgit v1.2.3 From aa07d71f1bc7ea20e442e812b5de9d632b7f84c6 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 11 Oct 2019 19:12:21 -0400 Subject: tracing: Have trace events system open call tracing_open_generic_tr() Instead of having the trace events system open call open code the taking of the trace_array descriptor (with trace_array_get()) and then calling trace_open_generic(), have it use the tracing_open_generic_tr() that does the combination of the two. This requires making tracing_open_generic_tr() global. Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 2 +- kernel/trace/trace.h | 1 + kernel/trace/trace_events.c | 17 +++-------------- 3 files changed, 5 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index fa7d813b04c6..94f1b9124939 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4156,7 +4156,7 @@ bool tracing_is_disabled(void) * Open and update trace_array ref count. * Must have the current trace_array passed to it. */ -static int tracing_open_generic_tr(struct inode *inode, struct file *filp) +int tracing_open_generic_tr(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index f801d154ff6a..854dbf4050f8 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -681,6 +681,7 @@ void tracing_reset_online_cpus(struct trace_buffer *buf); void tracing_reset_current(int cpu); void tracing_reset_all_online_cpus(void); int tracing_open_generic(struct inode *inode, struct file *filp); +int tracing_open_generic_tr(struct inode *inode, struct file *filp); bool tracing_is_disabled(void); bool tracer_tracing_is_on(struct trace_array *tr); void tracer_tracing_on(struct trace_array *tr); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index b89cdfe20bc1..9613a757c902 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1440,28 +1440,17 @@ static int system_tr_open(struct inode *inode, struct file *filp) struct trace_array *tr = inode->i_private; int ret; - if (tracing_is_disabled()) - return -ENODEV; - - if (trace_array_get(tr) < 0) - return -ENODEV; - /* Make a temporary dir that has no system but points to tr */ dir = kzalloc(sizeof(*dir), GFP_KERNEL); - if (!dir) { - trace_array_put(tr); + if (!dir) return -ENOMEM; - } - - dir->tr = tr; - ret = tracing_open_generic(inode, filp); + ret = tracing_open_generic_tr(inode, filp); if (ret < 0) { - trace_array_put(tr); kfree(dir); return ret; } - + dir->tr = tr; filp->private_data = dir; return 0; -- cgit v1.2.3 From 8530dec63e7b486e3761cc3d74a22de301845ff5 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 11 Oct 2019 17:39:57 -0400 Subject: tracing: Add tracing_check_open_get_tr() Currently, most files in the tracefs directory test if tracing_disabled is set. If so, it should return -ENODEV. The tracing_disabled is called when tracing is found to be broken. Originally it was done in case the ring buffer was found to be corrupted, and we wanted to prevent reading it from crashing the kernel. But it's also called if a tracing selftest fails on boot. It's a one way switch. That is, once it is triggered, tracing is disabled until reboot. As most tracefs files can also be used by instances in the tracefs directory, they need to be carefully done. Each instance has a trace_array associated to it, and when the instance is removed, the trace_array is freed. But if an instance is opened with a reference to the trace_array, then it requires looking up the trace_array to get its ref counter (as there could be a race with it being deleted and the open itself). Once it is found, a reference is added to prevent the instance from being removed (and the trace_array associated with it freed). Combine the two checks (tracing_disabled and trace_array_get()) into a single helper function. This will also make it easier to add lockdown to tracefs later. Link: http://lkml.kernel.org/r/20191011135458.7399da44@gandalf.local.home Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 7 ++- kernel/trace/trace.c | 117 ++++++++++++++++++++++----------------- kernel/trace/trace.h | 1 + kernel/trace/trace_dynevent.c | 4 ++ kernel/trace/trace_events.c | 10 ++-- kernel/trace/trace_events_hist.c | 2 +- 6 files changed, 81 insertions(+), 60 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 32c2eb167de0..8b765a55e01c 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3547,7 +3547,7 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, if (unlikely(ftrace_disabled)) return -ENODEV; - if (tr && trace_array_get(tr) < 0) + if (tracing_check_open_get_tr(tr)) return -ENODEV; iter = kzalloc(sizeof(*iter), GFP_KERNEL); @@ -6546,8 +6546,9 @@ ftrace_pid_open(struct inode *inode, struct file *file) struct seq_file *m; int ret = 0; - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 94f1b9124939..26ee280f852b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -304,6 +304,17 @@ void trace_array_put(struct trace_array *this_tr) mutex_unlock(&trace_types_lock); } +int tracing_check_open_get_tr(struct trace_array *tr) +{ + if (tracing_disabled) + return -ENODEV; + + if (tr && trace_array_get(tr) < 0) + return -ENODEV; + + return 0; +} + int call_filter_check_discard(struct trace_event_call *call, void *rec, struct ring_buffer *buffer, struct ring_buffer_event *event) @@ -4140,8 +4151,11 @@ release: int tracing_open_generic(struct inode *inode, struct file *filp) { - if (tracing_disabled) - return -ENODEV; + int ret; + + ret = tracing_check_open_get_tr(NULL); + if (ret) + return ret; filp->private_data = inode->i_private; return 0; @@ -4159,12 +4173,11 @@ bool tracing_is_disabled(void) int tracing_open_generic_tr(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; + int ret; - if (tracing_disabled) - return -ENODEV; - - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; filp->private_data = inode->i_private; @@ -4233,10 +4246,11 @@ static int tracing_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; struct trace_iterator *iter; - int ret = 0; + int ret; - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; /* If this file was open for write, then erase contents */ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { @@ -4352,11 +4366,9 @@ static int show_traces_open(struct inode *inode, struct file *file) struct seq_file *m; int ret; - if (tracing_disabled) - return -ENODEV; - - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; ret = seq_open(file, &show_traces_seq_ops); if (ret) { @@ -4710,11 +4722,9 @@ static int tracing_trace_options_open(struct inode *inode, struct file *file) struct trace_array *tr = inode->i_private; int ret; - if (tracing_disabled) - return -ENODEV; - - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; ret = single_open(file, tracing_trace_options_show, inode->i_private); if (ret < 0) @@ -5051,8 +5061,11 @@ static const struct seq_operations tracing_saved_tgids_seq_ops = { static int tracing_saved_tgids_open(struct inode *inode, struct file *filp) { - if (tracing_disabled) - return -ENODEV; + int ret; + + ret = tracing_check_open_get_tr(NULL); + if (ret) + return ret; return seq_open(filp, &tracing_saved_tgids_seq_ops); } @@ -5128,8 +5141,11 @@ static const struct seq_operations tracing_saved_cmdlines_seq_ops = { static int tracing_saved_cmdlines_open(struct inode *inode, struct file *filp) { - if (tracing_disabled) - return -ENODEV; + int ret; + + ret = tracing_check_open_get_tr(NULL); + if (ret) + return ret; return seq_open(filp, &tracing_saved_cmdlines_seq_ops); } @@ -5293,8 +5309,11 @@ static const struct seq_operations tracing_eval_map_seq_ops = { static int tracing_eval_map_open(struct inode *inode, struct file *filp) { - if (tracing_disabled) - return -ENODEV; + int ret; + + ret = tracing_check_open_get_tr(NULL); + if (ret) + return ret; return seq_open(filp, &tracing_eval_map_seq_ops); } @@ -5817,13 +5836,11 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; struct trace_iterator *iter; - int ret = 0; - - if (tracing_disabled) - return -ENODEV; + int ret; - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; mutex_lock(&trace_types_lock); @@ -6560,11 +6577,9 @@ static int tracing_clock_open(struct inode *inode, struct file *file) struct trace_array *tr = inode->i_private; int ret; - if (tracing_disabled) - return -ENODEV; - - if (trace_array_get(tr)) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; ret = single_open(file, tracing_clock_show, inode->i_private); if (ret < 0) @@ -6594,11 +6609,9 @@ static int tracing_time_stamp_mode_open(struct inode *inode, struct file *file) struct trace_array *tr = inode->i_private; int ret; - if (tracing_disabled) - return -ENODEV; - - if (trace_array_get(tr)) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; ret = single_open(file, tracing_time_stamp_mode_show, inode->i_private); if (ret < 0) @@ -6651,10 +6664,11 @@ static int tracing_snapshot_open(struct inode *inode, struct file *file) struct trace_array *tr = inode->i_private; struct trace_iterator *iter; struct seq_file *m; - int ret = 0; + int ret; - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; if (file->f_mode & FMODE_READ) { iter = __tracing_open(inode, file, true); @@ -7118,8 +7132,9 @@ static int tracing_err_log_open(struct inode *inode, struct file *file) struct trace_array *tr = inode->i_private; int ret = 0; - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; /* If this file was opened for write, then erase contents */ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) @@ -7170,11 +7185,9 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp) struct ftrace_buffer_info *info; int ret; - if (tracing_disabled) - return -ENODEV; - - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) { diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 854dbf4050f8..d685c61085c0 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -338,6 +338,7 @@ extern struct mutex trace_types_lock; extern int trace_array_get(struct trace_array *tr); extern void trace_array_put(struct trace_array *tr); +extern int tracing_check_open_get_tr(struct trace_array *tr); extern int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs); extern int tracing_set_clock(struct trace_array *tr, const char *clockstr); diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c index a41fed46c285..89779eb84a07 100644 --- a/kernel/trace/trace_dynevent.c +++ b/kernel/trace/trace_dynevent.c @@ -174,6 +174,10 @@ static int dyn_event_open(struct inode *inode, struct file *file) { int ret; + ret = tracing_check_open_get_tr(NULL); + if (ret) + return ret; + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { ret = dyn_events_release_all(NULL); if (ret < 0) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 9613a757c902..71ab0a3660f4 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1794,8 +1794,9 @@ ftrace_event_set_open(struct inode *inode, struct file *file) struct trace_array *tr = inode->i_private; int ret; - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) @@ -1814,8 +1815,9 @@ ftrace_event_set_pid_open(struct inode *inode, struct file *file) struct trace_array *tr = inode->i_private; int ret; - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 9468bd8d44a2..dd18d76bf1bd 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1680,7 +1680,7 @@ static int save_hist_vars(struct hist_trigger_data *hist_data) if (var_data) return 0; - if (trace_array_get(tr) < 0) + if (tracing_check_open_get_tr(tr)) return -ENODEV; var_data = kzalloc(sizeof(*var_data), GFP_KERNEL); -- cgit v1.2.3 From 17911ff38aa58d3c95c07589dbf5d3564c4cf3c5 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 11 Oct 2019 17:22:50 -0400 Subject: tracing: Add locked_down checks to the open calls of files created for tracefs Added various checks on open tracefs calls to see if tracefs is in lockdown mode, and if so, to return -EPERM. Note, the event format files (which are basically standard on all machines) as well as the enabled_functions file (which shows what is currently being traced) are not lockde down. Perhaps they should be, but it seems counter intuitive to lockdown information to help you know if the system has been modified. Link: http://lkml.kernel.org/r/CAHk-=wj7fGPKUspr579Cii-w_y60PtRaiDgKuxVtBAMK0VNNkA@mail.gmail.com Suggested-by: Linus Torvalds Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 23 ++++++++++++++++++++++- kernel/trace/trace.c | 8 ++++++++ kernel/trace/trace_events.c | 8 ++++++++ kernel/trace/trace_events_hist.c | 11 +++++++++++ kernel/trace/trace_events_trigger.c | 8 +++++++- kernel/trace/trace_kprobe.c | 12 +++++++++++- kernel/trace/trace_printk.c | 7 +++++++ kernel/trace/trace_stack.c | 8 ++++++++ kernel/trace/trace_stat.c | 6 +++++- kernel/trace/trace_uprobe.c | 11 +++++++++++ 10 files changed, 98 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 8b765a55e01c..f296d89be757 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -3486,6 +3487,11 @@ static int ftrace_avail_open(struct inode *inode, struct file *file) { struct ftrace_iterator *iter; + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; if (unlikely(ftrace_disabled)) return -ENODEV; @@ -3505,6 +3511,15 @@ ftrace_enabled_open(struct inode *inode, struct file *file) { struct ftrace_iterator *iter; + /* + * This shows us what functions are currently being + * traced and by what. Not sure if we want lockdown + * to hide such critical information for an admin. + * Although, perhaps it can show information we don't + * want people to see, but if something is tracing + * something, we probably want to know about it. + */ + iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter)); if (!iter) return -ENOMEM; @@ -3625,6 +3640,7 @@ ftrace_filter_open(struct inode *inode, struct file *file) { struct ftrace_ops *ops = inode->i_private; + /* Checks for tracefs lockdown */ return ftrace_regex_open(ops, FTRACE_ITER_FILTER | FTRACE_ITER_DO_PROBES, inode, file); @@ -3635,6 +3651,7 @@ ftrace_notrace_open(struct inode *inode, struct file *file) { struct ftrace_ops *ops = inode->i_private; + /* Checks for tracefs lockdown */ return ftrace_regex_open(ops, FTRACE_ITER_NOTRACE, inode, file); } @@ -5203,9 +5220,13 @@ static int __ftrace_graph_open(struct inode *inode, struct file *file, struct ftrace_graph_data *fgd) { - int ret = 0; + int ret; struct ftrace_hash *new_hash = NULL; + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + if (file->f_mode & FMODE_WRITE) { const int size_bits = FTRACE_HASH_DEFAULT_BITS; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 26ee280f852b..2b4eff383505 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -306,6 +307,12 @@ void trace_array_put(struct trace_array *this_tr) int tracing_check_open_get_tr(struct trace_array *tr) { + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + if (tracing_disabled) return -ENODEV; @@ -6813,6 +6820,7 @@ static int snapshot_raw_open(struct inode *inode, struct file *filp) struct ftrace_buffer_info *info; int ret; + /* The following checks for tracefs lockdown */ ret = tracing_buffers_open(inode, filp); if (ret < 0) return ret; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 71ab0a3660f4..fba87d10f0c1 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -12,6 +12,7 @@ #define pr_fmt(fmt) fmt #include +#include #include #include #include @@ -1294,6 +1295,8 @@ static int trace_format_open(struct inode *inode, struct file *file) struct seq_file *m; int ret; + /* Do we want to hide event format files on tracefs lockdown? */ + ret = seq_open(file, &trace_format_seq_ops); if (ret < 0) return ret; @@ -1760,6 +1763,10 @@ ftrace_event_open(struct inode *inode, struct file *file, struct seq_file *m; int ret; + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + ret = seq_open(file, seq_ops); if (ret < 0) return ret; @@ -1784,6 +1791,7 @@ ftrace_event_avail_open(struct inode *inode, struct file *file) { const struct seq_operations *seq_ops = &show_event_seq_ops; + /* Checks for tracefs lockdown */ return ftrace_event_open(inode, file, seq_ops); } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index dd18d76bf1bd..57648c5aa679 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -7,6 +7,7 @@ #include #include +#include #include #include #include @@ -1448,6 +1449,10 @@ static int synth_events_open(struct inode *inode, struct file *file) { int ret; + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { ret = dyn_events_release_all(&synth_event_ops); if (ret < 0) @@ -5515,6 +5520,12 @@ static int hist_show(struct seq_file *m, void *v) static int event_hist_open(struct inode *inode, struct file *file) { + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + return single_open(file, hist_show, file); } diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 2a2912cb4533..2cd53ca21b51 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -5,6 +5,7 @@ * Copyright (C) 2013 Tom Zanussi */ +#include #include #include #include @@ -173,7 +174,11 @@ static const struct seq_operations event_triggers_seq_ops = { static int event_trigger_regex_open(struct inode *inode, struct file *file) { - int ret = 0; + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; mutex_lock(&event_mutex); @@ -292,6 +297,7 @@ event_trigger_write(struct file *filp, const char __user *ubuf, static int event_trigger_open(struct inode *inode, struct file *filp) { + /* Checks for tracefs lockdown */ return event_trigger_regex_open(inode, filp); } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 324ffbea3556..1552a95c743b 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -7,11 +7,11 @@ */ #define pr_fmt(fmt) "trace_kprobe: " fmt +#include #include #include #include #include -#include #include /* for COMMAND_LINE_SIZE */ @@ -936,6 +936,10 @@ static int probes_open(struct inode *inode, struct file *file) { int ret; + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { ret = dyn_events_release_all(&trace_kprobe_ops); if (ret < 0) @@ -988,6 +992,12 @@ static const struct seq_operations profile_seq_op = { static int profile_open(struct inode *inode, struct file *file) { + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + return seq_open(file, &profile_seq_op); } diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index c3fd849d4a8f..d4e31e969206 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -6,6 +6,7 @@ * */ #include +#include #include #include #include @@ -348,6 +349,12 @@ static const struct seq_operations show_format_seq_ops = { static int ftrace_formats_open(struct inode *inode, struct file *file) { + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + return seq_open(file, &show_format_seq_ops); } diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index ec9a34a97129..4df9a209f7ca 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -5,6 +5,7 @@ */ #include #include +#include #include #include #include @@ -470,6 +471,12 @@ static const struct seq_operations stack_trace_seq_ops = { static int stack_trace_open(struct inode *inode, struct file *file) { + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + return seq_open(file, &stack_trace_seq_ops); } @@ -487,6 +494,7 @@ stack_trace_filter_open(struct inode *inode, struct file *file) { struct ftrace_ops *ops = inode->i_private; + /* Checks for tracefs lockdown */ return ftrace_regex_open(ops, FTRACE_ITER_FILTER, inode, file); } diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index 75bf1bcb4a8a..9ab0a1a7ad5e 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -9,7 +9,7 @@ * */ - +#include #include #include #include @@ -238,6 +238,10 @@ static int tracing_stat_open(struct inode *inode, struct file *file) struct seq_file *m; struct stat_session *session = inode->i_private; + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + ret = stat_seq_init(session); if (ret) return ret; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index dd884341f5c5..352073d36585 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -7,6 +7,7 @@ */ #define pr_fmt(fmt) "trace_uprobe: " fmt +#include #include #include #include @@ -769,6 +770,10 @@ static int probes_open(struct inode *inode, struct file *file) { int ret; + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { ret = dyn_events_release_all(&trace_uprobe_ops); if (ret) @@ -818,6 +823,12 @@ static const struct seq_operations profile_seq_op = { static int profile_open(struct inode *inode, struct file *file) { + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + return seq_open(file, &profile_seq_op); } -- cgit v1.2.3 From 98dc19c11470ee6048aba723d77079ad2cda8a52 Mon Sep 17 00:00:00 2001 From: "Srivatsa S. Bhat (VMware)" Date: Thu, 10 Oct 2019 11:50:46 -0700 Subject: tracing/hwlat: Report total time spent in all NMIs during the sample nmi_total_ts is supposed to record the total time spent in *all* NMIs that occur on the given CPU during the (active portion of the) sampling window. However, the code seems to be overwriting this variable for each NMI, thereby only recording the time spent in the most recent NMI. Fix it by accumulating the duration instead. Link: http://lkml.kernel.org/r/157073343544.17189.13911783866738671133.stgit@srivatsa-ubuntu Fixes: 7b2c86250122 ("tracing: Add NMI tracing in hwlat detector") Cc: stable@vger.kernel.org Signed-off-by: Srivatsa S. Bhat (VMware) Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_hwlat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index fa95139445b2..a0251a78807d 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -150,7 +150,7 @@ void trace_hwlat_callback(bool enter) if (enter) nmi_ts_start = time_get(); else - nmi_total_ts = time_get() - nmi_ts_start; + nmi_total_ts += time_get() - nmi_ts_start; } if (enter) -- cgit v1.2.3 From fc64e4ad80d4b72efce116f87b3174f0b7196f8e Mon Sep 17 00:00:00 2001 From: "Srivatsa S. Bhat (VMware)" Date: Thu, 10 Oct 2019 11:51:01 -0700 Subject: tracing/hwlat: Don't ignore outer-loop duration when calculating max_latency max_latency is intended to record the maximum ever observed hardware latency, which may occur in either part of the loop (inner/outer). So we need to also consider the outer-loop sample when updating max_latency. Link: http://lkml.kernel.org/r/157073345463.17189.18124025522664682811.stgit@srivatsa-ubuntu Fixes: e7c15cd8a113 ("tracing: Added hardware latency tracer") Cc: stable@vger.kernel.org Signed-off-by: Srivatsa S. Bhat (VMware) Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_hwlat.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index a0251a78807d..862f4b0139fc 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -256,6 +256,8 @@ static int get_sample(void) /* Keep a running maximum ever recorded hardware latency */ if (sample > tr->max_latency) tr->max_latency = sample; + if (outer_sample > tr->max_latency) + tr->max_latency = outer_sample; } out: -- cgit v1.2.3 From d303de1fcf344ff7c15ed64c3f48a991c9958775 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Fri, 11 Oct 2019 16:21:34 +0200 Subject: tracing: Initialize iter->seq after zeroing in tracing_read_pipe() A customer reported the following softlockup: [899688.160002] NMI watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [test.sh:16464] [899688.160002] CPU: 0 PID: 16464 Comm: test.sh Not tainted 4.12.14-6.23-azure #1 SLE12-SP4 [899688.160002] RIP: 0010:up_write+0x1a/0x30 [899688.160002] Kernel panic - not syncing: softlockup: hung tasks [899688.160002] RIP: 0010:up_write+0x1a/0x30 [899688.160002] RSP: 0018:ffffa86784d4fde8 EFLAGS: 00000257 ORIG_RAX: ffffffffffffff12 [899688.160002] RAX: ffffffff970fea00 RBX: 0000000000000001 RCX: 0000000000000000 [899688.160002] RDX: ffffffff00000001 RSI: 0000000000000080 RDI: ffffffff970fea00 [899688.160002] RBP: ffffffffffffffff R08: ffffffffffffffff R09: 0000000000000000 [899688.160002] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8b59014720d8 [899688.160002] R13: ffff8b59014720c0 R14: ffff8b5901471090 R15: ffff8b5901470000 [899688.160002] tracing_read_pipe+0x336/0x3c0 [899688.160002] __vfs_read+0x26/0x140 [899688.160002] vfs_read+0x87/0x130 [899688.160002] SyS_read+0x42/0x90 [899688.160002] do_syscall_64+0x74/0x160 It caught the process in the middle of trace_access_unlock(). There is no loop. So, it must be looping in the caller tracing_read_pipe() via the "waitagain" label. Crashdump analyze uncovered that iter->seq was completely zeroed at this point, including iter->seq.seq.size. It means that print_trace_line() was never able to print anything and there was no forward progress. The culprit seems to be in the code: /* reset all but tr, trace, and overruns */ memset(&iter->seq, 0, sizeof(struct trace_iterator) - offsetof(struct trace_iterator, seq)); It was added by the commit 53d0aa773053ab182877 ("ftrace: add logic to record overruns"). It was v2.6.27-rc1. It was the time when iter->seq looked like: struct trace_seq { unsigned char buffer[PAGE_SIZE]; unsigned int len; }; There was no "size" variable and zeroing was perfectly fine. The solution is to reinitialize the structure after or without zeroing. Link: http://lkml.kernel.org/r/20191011142134.11997-1-pmladek@suse.com Signed-off-by: Petr Mladek Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 2b4eff383505..6a0ee9178365 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6036,6 +6036,7 @@ waitagain: sizeof(struct trace_iterator) - offsetof(struct trace_iterator, seq)); cpumask_clear(iter->started); + trace_seq_init(&iter->seq); iter->pos = -1; trace_event_read_lock(); -- cgit v1.2.3 From ff229eee3d897f52bd001c841f2d3cce8853ecdc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 8 Oct 2019 10:32:04 -0700 Subject: hrtimer: Annotate lockless access to timer->base Followup to commit dd2261ed45aa ("hrtimer: Protect lockless access to timer->base") lock_hrtimer_base() fetches timer->base without lock exclusion. Compiler is allowed to read timer->base twice (even if considered dumb) which could end up trying to lock migration_base and return &migration_base. base = timer->base; if (likely(base != &migration_base)) { /* compiler reads timer->base again, and now (base == &migration_base) raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); if (likely(base == timer->base)) return base; /* == &migration_base ! */ Similarly the write sides must use WRITE_ONCE() to avoid store tearing. Signed-off-by: Eric Dumazet Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20191008173204.180879-1-edumazet@google.com --- kernel/time/hrtimer.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 0d4dc241c0fb..65605530ee34 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -164,7 +164,7 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, struct hrtimer_clock_base *base; for (;;) { - base = timer->base; + base = READ_ONCE(timer->base); if (likely(base != &migration_base)) { raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); if (likely(base == timer->base)) @@ -244,7 +244,7 @@ again: return base; /* See the comment in lock_hrtimer_base() */ - timer->base = &migration_base; + WRITE_ONCE(timer->base, &migration_base); raw_spin_unlock(&base->cpu_base->lock); raw_spin_lock(&new_base->cpu_base->lock); @@ -253,10 +253,10 @@ again: raw_spin_unlock(&new_base->cpu_base->lock); raw_spin_lock(&base->cpu_base->lock); new_cpu_base = this_cpu_base; - timer->base = base; + WRITE_ONCE(timer->base, base); goto again; } - timer->base = new_base; + WRITE_ONCE(timer->base, new_base); } else { if (new_cpu_base != this_cpu_base && hrtimer_check_target(timer, new_base)) { -- cgit v1.2.3 From b67114db64adcb0aaff0fe0bb2a84ede0a99aaf2 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 4 Oct 2019 13:10:09 +0200 Subject: parisc: sysctl.c: Use CONFIG_PARISC instead of __hppa_ define Signed-off-by: Helge Deller --- kernel/sysctl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 00fcea236eba..b6f2f35d0bcf 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -163,7 +163,7 @@ static unsigned long hung_task_timeout_max = (LONG_MAX/HZ); #ifdef CONFIG_SPARC #endif -#ifdef __hppa__ +#ifdef CONFIG_PARISC extern int pwrsw_enabled; #endif @@ -620,7 +620,7 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif -#ifdef __hppa__ +#ifdef CONFIG_PARISC { .procname = "soft-power", .data = &pwrsw_enabled, -- cgit v1.2.3 From bc88f85c6c09306bd21917e1ae28205e9cd775a7 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Wed, 16 Oct 2019 12:24:58 +0100 Subject: kthread: make __kthread_queue_delayed_work static The __kthread_queue_delayed_work is not exported so make it static, to avoid the following sparse warning: kernel/kthread.c:869:6: warning: symbol '__kthread_queue_delayed_work' was not declared. Should it be static? Signed-off-by: Ben Dooks Signed-off-by: Linus Torvalds --- kernel/kthread.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/kthread.c b/kernel/kthread.c index 621467c33fef..b262f47046ca 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -866,9 +866,9 @@ void kthread_delayed_work_timer_fn(struct timer_list *t) } EXPORT_SYMBOL(kthread_delayed_work_timer_fn); -void __kthread_queue_delayed_work(struct kthread_worker *worker, - struct kthread_delayed_work *dwork, - unsigned long delay) +static void __kthread_queue_delayed_work(struct kthread_worker *worker, + struct kthread_delayed_work *dwork, + unsigned long delay) { struct timer_list *timer = &dwork->timer; struct kthread_work *work = &dwork->work; -- cgit v1.2.3 From 700dea5a0bea9f64eba89fae7cb2540326fdfdc1 Mon Sep 17 00:00:00 2001 From: Dmitry Goldin Date: Wed, 9 Oct 2019 13:42:14 +0000 Subject: kheaders: substituting --sort in archive creation The option --sort=ORDER was only introduced in tar 1.28 (2014), which is rather new and might not be available in some setups. This patch tries to replicate the previous behaviour as closely as possible to fix the kheaders build for older environments. It does not produce identical archives compared to the previous version due to minor sorting differences but produces reproducible results itself in my tests. Reported-by: Andreas Schwab Signed-off-by: Dmitry Goldin Tested-by: Andreas Schwab Tested-by: Quentin Perret Signed-off-by: Masahiro Yamada --- kernel/gen_kheaders.sh | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index aff79e461fc9..5a0fc0b0403a 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -71,10 +71,13 @@ done | cpio --quiet -pd $cpio_dir >/dev/null 2>&1 find $cpio_dir -type f -print0 | xargs -0 -P8 -n1 perl -pi -e 'BEGIN {undef $/;}; s/\/\*((?!SPDX).)*?\*\///smg;' -# Create archive and try to normalize metadata for reproducibility -tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \ - --owner=0 --group=0 --sort=name --numeric-owner \ - -Jcf $tarfile -C $cpio_dir/ . > /dev/null +# Create archive and try to normalize metadata for reproducibility. +# For compatibility with older versions of tar, files are fed to tar +# pre-sorted, as --sort=name might not be available. +find $cpio_dir -printf "./%P\n" | LC_ALL=C sort | \ + tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \ + --owner=0 --group=0 --numeric-owner --no-recursion \ + -Jcf $tarfile -C $cpio_dir/ -T - > /dev/null echo "$src_files_md5" > kernel/kheaders.md5 echo "$obj_files_md5" >> kernel/kheaders.md5 -- cgit v1.2.3 From b1fc5833357524d5d342737913dbe32ff3557bc5 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 7 Oct 2019 11:45:36 +0100 Subject: stop_machine: Avoid potential race behaviour Both multi_cpu_stop() and set_state() access multi_stop_data::state racily using plain accesses. These are subject to compiler transformations which could break the intended behaviour of the code, and this situation is detected by KCSAN on both arm64 and x86 (splats below). Improve matters by using READ_ONCE() and WRITE_ONCE() to ensure that the compiler cannot elide, replay, or tear loads and stores. In multi_cpu_stop() the two loads of multi_stop_data::state are expected to be a consistent value, so snapshot the value into a temporary variable to ensure this. The state transitions are serialized by atomic manipulation of multi_stop_data::num_threads, and other fields in multi_stop_data are not modified while subject to concurrent reads. KCSAN splat on arm64: | BUG: KCSAN: data-race in multi_cpu_stop+0xa8/0x198 and set_state+0x80/0xb0 | | write to 0xffff00001003bd00 of 4 bytes by task 24 on cpu 3: | set_state+0x80/0xb0 | multi_cpu_stop+0x16c/0x198 | cpu_stopper_thread+0x170/0x298 | smpboot_thread_fn+0x40c/0x560 | kthread+0x1a8/0x1b0 | ret_from_fork+0x10/0x18 | | read to 0xffff00001003bd00 of 4 bytes by task 14 on cpu 1: | multi_cpu_stop+0xa8/0x198 | cpu_stopper_thread+0x170/0x298 | smpboot_thread_fn+0x40c/0x560 | kthread+0x1a8/0x1b0 | ret_from_fork+0x10/0x18 | | Reported by Kernel Concurrency Sanitizer on: | CPU: 1 PID: 14 Comm: migration/1 Not tainted 5.3.0-00007-g67ab35a199f4-dirty #3 | Hardware name: linux,dummy-virt (DT) KCSAN splat on x86: | write to 0xffffb0bac0013e18 of 4 bytes by task 19 on cpu 2: | set_state kernel/stop_machine.c:170 [inline] | ack_state kernel/stop_machine.c:177 [inline] | multi_cpu_stop+0x1a4/0x220 kernel/stop_machine.c:227 | cpu_stopper_thread+0x19e/0x280 kernel/stop_machine.c:516 | smpboot_thread_fn+0x1a8/0x300 kernel/smpboot.c:165 | kthread+0x1b5/0x200 kernel/kthread.c:255 | ret_from_fork+0x35/0x40 arch/x86/entry/entry_64.S:352 | | read to 0xffffb0bac0013e18 of 4 bytes by task 44 on cpu 7: | multi_cpu_stop+0xb4/0x220 kernel/stop_machine.c:213 | cpu_stopper_thread+0x19e/0x280 kernel/stop_machine.c:516 | smpboot_thread_fn+0x1a8/0x300 kernel/smpboot.c:165 | kthread+0x1b5/0x200 kernel/kthread.c:255 | ret_from_fork+0x35/0x40 arch/x86/entry/entry_64.S:352 | | Reported by Kernel Concurrency Sanitizer on: | CPU: 7 PID: 44 Comm: migration/7 Not tainted 5.3.0+ #1 | Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 Signed-off-by: Mark Rutland Signed-off-by: Thomas Gleixner Acked-by: Marco Elver Link: https://lkml.kernel.org/r/20191007104536.27276-1-mark.rutland@arm.com --- kernel/stop_machine.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index c7031a22aa7b..998d50ee2d9b 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -7,6 +7,7 @@ * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo */ +#include #include #include #include @@ -167,7 +168,7 @@ static void set_state(struct multi_stop_data *msdata, /* Reset ack counter. */ atomic_set(&msdata->thread_ack, msdata->num_threads); smp_wmb(); - msdata->state = newstate; + WRITE_ONCE(msdata->state, newstate); } /* Last one to ack a state moves to the next state. */ @@ -186,7 +187,7 @@ void __weak stop_machine_yield(const struct cpumask *cpumask) static int multi_cpu_stop(void *data) { struct multi_stop_data *msdata = data; - enum multi_stop_state curstate = MULTI_STOP_NONE; + enum multi_stop_state newstate, curstate = MULTI_STOP_NONE; int cpu = smp_processor_id(), err = 0; const struct cpumask *cpumask; unsigned long flags; @@ -210,8 +211,9 @@ static int multi_cpu_stop(void *data) do { /* Chill out and ensure we re-read multi_stop_state. */ stop_machine_yield(cpumask); - if (msdata->state != curstate) { - curstate = msdata->state; + newstate = READ_ONCE(msdata->state); + if (newstate != curstate) { + curstate = newstate; switch (curstate) { case MULTI_STOP_DISABLE_IRQ: local_irq_disable(); -- cgit v1.2.3 From aa5de305c90c995321df452f274fe75b52bd8fcc Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 18 Oct 2019 20:20:40 -0700 Subject: kernel/events/uprobes.c: only do FOLL_SPLIT_PMD for uprobe register Attaching uprobe to text section in THP splits the PMD mapped page table into PTE mapped entries. On uprobe detach, we would like to regroup PMD mapped page table entry to regain performance benefit of THP. However, the regroup is broken For perf_event based trace_uprobe. This is because perf_event based trace_uprobe calls uprobe_unregister twice on close: first in TRACE_REG_PERF_CLOSE, then in TRACE_REG_PERF_UNREGISTER. The second call will split the PMD mapped page table entry, which is not the desired behavior. Fix this by only use FOLL_SPLIT_PMD for uprobe register case. Add a WARN() to confirm uprobe unregister never work on huge pages, and abort the operation when this WARN() triggers. Link: http://lkml.kernel.org/r/20191017164223.2762148-6-songliubraving@fb.com Fixes: 5a52c9df62b4 ("uprobe: use FOLL_SPLIT_PMD instead of FOLL_SPLIT") Signed-off-by: Song Liu Reviewed-by: Srikar Dronamraju Cc: Kirill A. Shutemov Cc: Oleg Nesterov Cc: Matthew Wilcox (Oracle) Cc: William Kucharski Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/events/uprobes.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 94d38a39d72e..c74761004ee5 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -474,14 +474,17 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, struct vm_area_struct *vma; int ret, is_register, ref_ctr_updated = 0; bool orig_page_huge = false; + unsigned int gup_flags = FOLL_FORCE; is_register = is_swbp_insn(&opcode); uprobe = container_of(auprobe, struct uprobe, arch); retry: + if (is_register) + gup_flags |= FOLL_SPLIT_PMD; /* Read the page with vaddr into memory */ - ret = get_user_pages_remote(NULL, mm, vaddr, 1, - FOLL_FORCE | FOLL_SPLIT_PMD, &old_page, &vma, NULL); + ret = get_user_pages_remote(NULL, mm, vaddr, 1, gup_flags, + &old_page, &vma, NULL); if (ret <= 0) return ret; @@ -489,6 +492,12 @@ retry: if (ret <= 0) goto put_old; + if (WARN(!is_register && PageCompound(old_page), + "uprobe unregister should never work on compound page\n")) { + ret = -EINVAL; + goto put_old; + } + /* We are going to replace instruction, update ref_ctr. */ if (!ref_ctr_updated && uprobe->ref_ctr_offset) { ret = update_ref_ctr(uprobe, mm, is_register ? 1 : -1); -- cgit v1.2.3