From cba77f03f2c7b6cc0b0a44a3c679e0abade7da62 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Sat, 11 Jul 2015 21:19:19 -0400 Subject: locking/pvqspinlock: Fix kernel panic in locking-selftest Enabling locking-selftest in a VM guest may cause the following kernel panic: kernel BUG at .../kernel/locking/qspinlock_paravirt.h:137! This is due to the fact that the pvqspinlock unlock function is expecting either a _Q_LOCKED_VAL or _Q_SLOW_VAL in the lock byte. This patch prevents that bug report by ignoring it when debug_locks_silent is set. Otherwise, a warning will be printed if it contains an unexpected value. With this patch applied, the kernel locking-selftest completed without any noise. Tested-by: Masami Hiramatsu Signed-off-by: Waiman Long Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1436663959-53092-1-git-send-email-Waiman.Long@hp.com Signed-off-by: Ingo Molnar --- kernel/locking/qspinlock_paravirt.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index 04ab18151cc8..df19ae4debd0 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -4,6 +4,7 @@ #include #include +#include /* * Implement paravirt qspinlocks; the general idea is to halt the vcpus instead @@ -286,15 +287,23 @@ __visible void __pv_queued_spin_unlock(struct qspinlock *lock) { struct __qspinlock *l = (void *)lock; struct pv_node *node; + u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0); /* * We must not unlock if SLOW, because in that case we must first * unhash. Otherwise it would be possible to have multiple @lock * entries, which would be BAD. */ - if (likely(cmpxchg(&l->locked, _Q_LOCKED_VAL, 0) == _Q_LOCKED_VAL)) + if (likely(lockval == _Q_LOCKED_VAL)) return; + if (unlikely(lockval != _Q_SLOW_VAL)) { + if (debug_locks_silent) + return; + WARN(1, "pvqspinlock: lock %p has corrupted value 0x%x!\n", lock, atomic_read(&lock->val)); + return; + } + /* * Since the above failed to release, this must be the SLOW path. * Therefore start by looking up the blocked node and unhashing it. -- cgit v1.2.3-70-g09d2 From 00a2916f7f82c348a2a94dbb572874173bc308a3 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 27 Jul 2015 10:35:07 +0200 Subject: perf: Fix running time accounting A recent fix to the shadow timestamp inadvertly broke the running time accounting. We must not update the running timestamp if we fail to schedule the event, the event will not have ran. This can (and did) result in negative total runtime because the stopped timestamp was before the running timestamp (we 'started' but never stopped the event -- because it never really started we didn't have to stop it either). Reported-and-Tested-by: Vince Weaver Fixes: 72f669c0086f ("perf: Update shadow timestamp before add event") Signed-off-by: Peter Zijlstra (Intel) Cc: stable@vger.kernel.org # 4.1 Cc: Shaohua Li Signed-off-by: Thomas Gleixner --- kernel/events/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index d3dae3419b99..10d076b2572c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1868,8 +1868,6 @@ event_sched_in(struct perf_event *event, perf_pmu_disable(event->pmu); - event->tstamp_running += tstamp - event->tstamp_stopped; - perf_set_shadow_time(event, ctx, tstamp); perf_log_itrace_start(event); @@ -1881,6 +1879,8 @@ event_sched_in(struct perf_event *event, goto out; } + event->tstamp_running += tstamp - event->tstamp_stopped; + if (!is_software_event(event)) cpuctx->active_oncpu++; if (!ctx->nr_active++) -- cgit v1.2.3-70-g09d2 From fe0d34d242fa1e0dec059e774d146a705420bc9a Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 29 Jul 2015 05:52:14 +0930 Subject: module: weaken locking assertion for oops path. We don't actually hold the module_mutex when calling find_module_all from module_kallsyms_lookup_name: that's because it's used by the oops code and we don't want to deadlock. However, access to the list read-only is safe if preempt is disabled, so we can weaken the assertion. Keep a strong version for external callers though. Fixes: 0be964be0d45 ("module: Sanitize RCU usage and locking") Reported-by: He Kuang Cc: stable@kernel.org Acked-by: Peter Zijlstra (Intel) Signed-off-by: Rusty Russell --- kernel/module.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/module.c b/kernel/module.c index 4d2b82e610e2..b86b7bf1be38 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -602,13 +602,16 @@ const struct kernel_symbol *find_symbol(const char *name, } EXPORT_SYMBOL_GPL(find_symbol); -/* Search for module by name: must hold module_mutex. */ +/* + * Search for module by name: must hold module_mutex (or preempt disabled + * for read-only access). + */ static struct module *find_module_all(const char *name, size_t len, bool even_unformed) { struct module *mod; - module_assert_mutex(); + module_assert_mutex_or_preempt(); list_for_each_entry(mod, &modules, list) { if (!even_unformed && mod->state == MODULE_STATE_UNFORMED) @@ -621,6 +624,7 @@ static struct module *find_module_all(const char *name, size_t len, struct module *find_module(const char *name) { + module_assert_mutex(); return find_module_all(name, strlen(name), false); } EXPORT_SYMBOL_GPL(find_module); -- cgit v1.2.3-70-g09d2 From fed66e2cdd4f127a43fd11b8d92a99bdd429528c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 11 Jun 2015 10:32:01 +0200 Subject: perf: Fix fasync handling on inherited events Vince reported that the fasync signal stuff doesn't work proper for inherited events. So fix that. Installing fasync allocates memory and sets filp->f_flags |= FASYNC, which upon the demise of the file descriptor ensures the allocation is freed and state is updated. Now for perf, we can have the events stick around for a while after the original FD is dead because of references from child events. So we cannot copy the fasync pointer around. We can however consistently use the parent's fasync, as that will be updated. Reported-and-Tested-by: Vince Weaver Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Arnaldo Carvalho deMelo Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: eranian@google.com Link: http://lkml.kernel.org/r/1434011521.1495.71.camel@twins Signed-off-by: Ingo Molnar --- kernel/events/core.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 10d076b2572c..072b8a686517 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4740,12 +4740,20 @@ static const struct file_operations perf_fops = { * to user-space before waking everybody up. */ +static inline struct fasync_struct **perf_event_fasync(struct perf_event *event) +{ + /* only the parent has fasync state */ + if (event->parent) + event = event->parent; + return &event->fasync; +} + void perf_event_wakeup(struct perf_event *event) { ring_buffer_wakeup(event); if (event->pending_kill) { - kill_fasync(&event->fasync, SIGIO, event->pending_kill); + kill_fasync(perf_event_fasync(event), SIGIO, event->pending_kill); event->pending_kill = 0; } } @@ -6124,7 +6132,7 @@ static int __perf_event_overflow(struct perf_event *event, else perf_event_output(event, data, regs); - if (event->fasync && event->pending_kill) { + if (*perf_event_fasync(event) && event->pending_kill) { event->pending_wakeup = 1; irq_work_queue(&event->pending); } -- cgit v1.2.3-70-g09d2 From 3c00cb5e68dc719f2fc73a33b1b230aadfcb1309 Mon Sep 17 00:00:00 2001 From: Amanieu d'Antras Date: Thu, 6 Aug 2015 15:46:26 -0700 Subject: signal: fix information leak in copy_siginfo_from_user32 This function can leak kernel stack data when the user siginfo_t has a positive si_code value. The top 16 bits of si_code descibe which fields in the siginfo_t union are active, but they are treated inconsistently between copy_siginfo_from_user32, copy_siginfo_to_user32 and copy_siginfo_to_user. copy_siginfo_from_user32 is called from rt_sigqueueinfo and rt_tgsigqueueinfo in which the user has full control overthe top 16 bits of si_code. This fixes the following information leaks: x86: 8 bytes leaked when sending a signal from a 32-bit process to itself. This leak grows to 16 bytes if the process uses x32. (si_code = __SI_CHLD) x86: 100 bytes leaked when sending a signal from a 32-bit process to a 64-bit process. (si_code = -1) sparc: 4 bytes leaked when sending a signal from a 32-bit process to a 64-bit process. (si_code = any) parsic and s390 have similar bugs, but they are not vulnerable because rt_[tg]sigqueueinfo have checks that prevent sending a positive si_code to a different process. These bugs are also fixed for consistency. Signed-off-by: Amanieu d'Antras Cc: Oleg Nesterov Cc: Ingo Molnar Cc: Russell King Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Chris Metcalf Cc: Paul Mackerras Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/kernel/signal32.c | 2 -- arch/mips/kernel/signal32.c | 2 -- arch/powerpc/kernel/signal_32.c | 2 -- arch/tile/kernel/compat_signal.c | 2 -- kernel/signal.c | 4 ++-- 5 files changed, 2 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index 1670f15ef69e..81fd38f4fbaa 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -201,8 +201,6 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) { - memset(to, 0, sizeof *to); - if (copy_from_user(to, from, __ARCH_SI_PREAMBLE_SIZE) || copy_from_user(to->_sifields._pad, from->_sifields._pad, SI_PAD_SIZE)) diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c index 19a7705f2a01..5d7f2634996f 100644 --- a/arch/mips/kernel/signal32.c +++ b/arch/mips/kernel/signal32.c @@ -409,8 +409,6 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) { - memset(to, 0, sizeof *to); - if (copy_from_user(to, from, 3*sizeof(int)) || copy_from_user(to->_sifields._pad, from->_sifields._pad, SI_PAD_SIZE32)) diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index d3a831ac0f92..da50e0c9c57e 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -966,8 +966,6 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *d, const siginfo_t *s) int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from) { - memset(to, 0, sizeof *to); - if (copy_from_user(to, from, 3*sizeof(int)) || copy_from_user(to->_sifields._pad, from->_sifields._pad, SI_PAD_SIZE32)) diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c index e8c2c04143cd..c667e104a0c2 100644 --- a/arch/tile/kernel/compat_signal.c +++ b/arch/tile/kernel/compat_signal.c @@ -113,8 +113,6 @@ int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from) if (!access_ok(VERIFY_READ, from, sizeof(struct compat_siginfo))) return -EFAULT; - memset(to, 0, sizeof(*to)); - err = __get_user(to->si_signo, &from->si_signo); err |= __get_user(to->si_errno, &from->si_errno); err |= __get_user(to->si_code, &from->si_code); diff --git a/kernel/signal.c b/kernel/signal.c index 836df8dac6cc..00524cf6c412 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3017,7 +3017,7 @@ COMPAT_SYSCALL_DEFINE3(rt_sigqueueinfo, int, sig, struct compat_siginfo __user *, uinfo) { - siginfo_t info; + siginfo_t info = {}; int ret = copy_siginfo_from_user32(&info, uinfo); if (unlikely(ret)) return ret; @@ -3061,7 +3061,7 @@ COMPAT_SYSCALL_DEFINE4(rt_tgsigqueueinfo, int, sig, struct compat_siginfo __user *, uinfo) { - siginfo_t info; + siginfo_t info = {}; if (copy_siginfo_from_user32(&info, uinfo)) return -EFAULT; -- cgit v1.2.3-70-g09d2 From 26135022f85105ad725cda103fa069e29e83bd16 Mon Sep 17 00:00:00 2001 From: Amanieu d'Antras Date: Thu, 6 Aug 2015 15:46:29 -0700 Subject: signal: fix information leak in copy_siginfo_to_user This function may copy the si_addr_lsb, si_lower and si_upper fields to user mode when they haven't been initialized, which can leak kernel stack data to user mode. Just checking the value of si_code is insufficient because the same si_code value is shared between multiple signals. This is solved by checking the value of si_signo in addition to si_code. Signed-off-by: Amanieu d'Antras Cc: Oleg Nesterov Cc: Ingo Molnar Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/kernel/signal32.c | 3 ++- kernel/signal.c | 9 ++++++--- 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index 81fd38f4fbaa..948f0ad2de23 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -168,7 +168,8 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) * Other callers might not initialize the si_lsb field, * so check explicitely for the right codes here. */ - if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO) + if (from->si_signo == SIGBUS && + (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)) err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb); #endif break; diff --git a/kernel/signal.c b/kernel/signal.c index 00524cf6c412..0f6bbbe77b46 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2748,12 +2748,15 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from) * Other callers might not initialize the si_lsb field, * so check explicitly for the right codes here. */ - if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO) + if (from->si_signo == SIGBUS && + (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)) err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb); #endif #ifdef SEGV_BNDERR - err |= __put_user(from->si_lower, &to->si_lower); - err |= __put_user(from->si_upper, &to->si_upper); + if (from->si_signo == SIGSEGV && from->si_code == SEGV_BNDERR) { + err |= __put_user(from->si_lower, &to->si_lower); + err |= __put_user(from->si_upper, &to->si_upper); + } #endif break; case __SI_CHLD: -- cgit v1.2.3-70-g09d2 From 18896451eaeee497ef5c397d76902c6376a8787d Mon Sep 17 00:00:00 2001 From: David Kershner Date: Thu, 6 Aug 2015 15:46:45 -0700 Subject: kthread: export kthread functions The s-Par visornic driver, currently in staging, processes a queue being serviced by the an s-Par service partition. We can get a message that something has happened with the Service Partition, when that happens, we must not access the channel until we get a message that the service partition is back again. The visornic driver has a thread for processing the channel, when we get the message, we need to be able to park the thread and then resume it when the problem clears. We can do this with kthread_park and unpark but they are not exported from the kernel, this patch exports the needed functions. Signed-off-by: David Kershner Acked-by: Ingo Molnar Acked-by: Neil Horman Acked-by: Thomas Gleixner Cc: Richard Weinberger Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kthread.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel') diff --git a/kernel/kthread.c b/kernel/kthread.c index 10e489c448fe..fdea0bee7b5a 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -97,6 +97,7 @@ bool kthread_should_park(void) { return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(current)->flags); } +EXPORT_SYMBOL_GPL(kthread_should_park); /** * kthread_freezable_should_stop - should this freezable kthread return now? @@ -171,6 +172,7 @@ void kthread_parkme(void) { __kthread_parkme(to_kthread(current)); } +EXPORT_SYMBOL_GPL(kthread_parkme); static int kthread(void *_create) { @@ -411,6 +413,7 @@ void kthread_unpark(struct task_struct *k) if (kthread) __kthread_unpark(k, kthread); } +EXPORT_SYMBOL_GPL(kthread_unpark); /** * kthread_park - park a thread created by kthread_create(). @@ -441,6 +444,7 @@ int kthread_park(struct task_struct *k) } return ret; } +EXPORT_SYMBOL_GPL(kthread_park); /** * kthread_stop - stop a thread created by kthread_create(). -- cgit v1.2.3-70-g09d2 From ee9397a6fb9bc4e52677f5e33eed4abee0f515e6 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 27 Jul 2015 00:31:08 +0100 Subject: perf: Fix double-free of the AUX buffer If rb->aux_refcount is decremented to zero before rb->refcount, __rb_free_aux() may be called twice resulting in a double free of rb->aux_pages. Fix this by adding a check to __rb_free_aux(). Signed-off-by: Ben Hutchings Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: stable@vger.kernel.org Fixes: 57ffc5ca679f ("perf: Fix AUX buffer refcounting") Link: http://lkml.kernel.org/r/1437953468.12842.17.camel@decadent.org.uk Signed-off-by: Ingo Molnar --- kernel/events/ring_buffer.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index b2be01b1aa9d..c8aa3f75bc4d 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -559,11 +559,13 @@ static void __rb_free_aux(struct ring_buffer *rb) rb->aux_priv = NULL; } - for (pg = 0; pg < rb->aux_nr_pages; pg++) - rb_free_aux_page(rb, pg); + if (rb->aux_nr_pages) { + for (pg = 0; pg < rb->aux_nr_pages; pg++) + rb_free_aux_page(rb, pg); - kfree(rb->aux_pages); - rb->aux_nr_pages = 0; + kfree(rb->aux_pages); + rb->aux_nr_pages = 0; + } } void rb_free_aux(struct ring_buffer *rb) -- cgit v1.2.3-70-g09d2 From c7999c6f3fed9e383d3131474588f282ae6d56b9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 4 Aug 2015 19:22:49 +0200 Subject: perf: Fix PERF_EVENT_IOC_PERIOD migration race I ran the perf fuzzer, which triggered some WARN()s which are due to trying to stop/restart an event on the wrong CPU. Use the normal IPI pattern to ensure we run the code on the correct CPU. Signed-off-by: Peter Zijlstra (Intel) Cc: Vince Weaver Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: bad7192b842c ("perf: Fix PERF_EVENT_IOC_PERIOD to force-reset the period") Signed-off-by: Ingo Molnar --- kernel/events/core.c | 75 ++++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 55 insertions(+), 20 deletions(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 072b8a686517..e6feb5114134 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3958,28 +3958,21 @@ static void perf_event_for_each(struct perf_event *event, perf_event_for_each_child(sibling, func); } -static int perf_event_period(struct perf_event *event, u64 __user *arg) -{ - struct perf_event_context *ctx = event->ctx; - int ret = 0, active; +struct period_event { + struct perf_event *event; u64 value; +}; - if (!is_sampling_event(event)) - return -EINVAL; - - if (copy_from_user(&value, arg, sizeof(value))) - return -EFAULT; - - if (!value) - return -EINVAL; +static int __perf_event_period(void *info) +{ + struct period_event *pe = info; + struct perf_event *event = pe->event; + struct perf_event_context *ctx = event->ctx; + u64 value = pe->value; + bool active; - raw_spin_lock_irq(&ctx->lock); + raw_spin_lock(&ctx->lock); if (event->attr.freq) { - if (value > sysctl_perf_event_sample_rate) { - ret = -EINVAL; - goto unlock; - } - event->attr.sample_freq = value; } else { event->attr.sample_period = value; @@ -3998,11 +3991,53 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg) event->pmu->start(event, PERF_EF_RELOAD); perf_pmu_enable(ctx->pmu); } + raw_spin_unlock(&ctx->lock); -unlock: + return 0; +} + +static int perf_event_period(struct perf_event *event, u64 __user *arg) +{ + struct period_event pe = { .event = event, }; + struct perf_event_context *ctx = event->ctx; + struct task_struct *task; + u64 value; + + if (!is_sampling_event(event)) + return -EINVAL; + + if (copy_from_user(&value, arg, sizeof(value))) + return -EFAULT; + + if (!value) + return -EINVAL; + + if (event->attr.freq && value > sysctl_perf_event_sample_rate) + return -EINVAL; + + task = ctx->task; + pe.value = value; + + if (!task) { + cpu_function_call(event->cpu, __perf_event_period, &pe); + return 0; + } + +retry: + if (!task_function_call(task, __perf_event_period, &pe)) + return 0; + + raw_spin_lock_irq(&ctx->lock); + if (ctx->is_active) { + raw_spin_unlock_irq(&ctx->lock); + task = ctx->task; + goto retry; + } + + __perf_event_period(&pe); raw_spin_unlock_irq(&ctx->lock); - return ret; + return 0; } static const struct file_operations perf_fops; -- cgit v1.2.3-70-g09d2