From 9c0dee54eb91d48cca048bd7bd2c1f4a166e0252 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 25 Feb 2021 17:19:44 -0800 Subject: tracing: add error_report_end trace point Patch series "Add error_report_end tracepoint to KFENCE and KASAN", v3. This patchset adds a tracepoint, error_repor_end, that is to be used by KFENCE, KASAN, and potentially other bug detection tools, when they print an error report. One of the possible use cases is userspace collection of kernel error reports: interested parties can subscribe to the tracing event via tracefs, and get notified when an error report occurs. This patch (of 3): Introduce error_report_end tracepoint. It can be used in debugging tools like KASAN, KFENCE, etc. to provide extensions to the error reporting mechanisms (e.g. allow tests hook into error reporting, ease error report collection from production kernels). Another benefit would be making use of ftrace for debugging or benchmarking the tools themselves. Should we need it, the tracepoint name leaves us with the possibility to introduce a complementary error_report_start tracepoint in the future. Link: https://lkml.kernel.org/r/20210121131915.1331302-1-glider@google.com Link: https://lkml.kernel.org/r/20210121131915.1331302-2-glider@google.com Signed-off-by: Alexander Potapenko Suggested-by: Marco Elver Cc: Andrey Konovalov Cc: Dmitry Vyukov Cc: Ingo Molnar Cc: Petr Mladek Cc: Steven Rostedt Cc: Sergey Senozhatsky Cc: Greg Kroah-Hartman Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/trace/Makefile | 1 + kernel/trace/error_report-traces.c | 11 +++++++++++ 2 files changed, 12 insertions(+) create mode 100644 kernel/trace/error_report-traces.c (limited to 'kernel') diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 7e44cea89fdc..b28d3e5013cd 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -81,6 +81,7 @@ obj-$(CONFIG_SYNTH_EVENTS) += trace_events_synth.o obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o +obj-$(CONFIG_TRACEPOINTS) += error_report-traces.o obj-$(CONFIG_TRACEPOINTS) += power-traces.o ifeq ($(CONFIG_PM),y) obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o diff --git a/kernel/trace/error_report-traces.c b/kernel/trace/error_report-traces.c new file mode 100644 index 000000000000..f89792c25b11 --- /dev/null +++ b/kernel/trace/error_report-traces.c @@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Error reporting trace points. + * + * Copyright (C) 2021, Google LLC. + */ + +#define CREATE_TRACE_POINTS +#include + +EXPORT_TRACEPOINT_SYMBOL_GPL(error_report_end); -- cgit v1.2.3 From 3b3376f222e3ab58367d9dd405cafd09d5e37b7c Mon Sep 17 00:00:00 2001 From: Lin Feng Date: Thu, 25 Feb 2021 17:20:53 -0800 Subject: sysctl.c: fix underflow value setting risk in vm_table Apart from subsystem specific .proc_handler handler, all ctl_tables with extra1 and extra2 members set should use proc_dointvec_minmax instead of proc_dointvec, or the limit set in extra* never work and potentially echo underflow values(negative numbers) is likely make system unstable. Especially vfs_cache_pressure and zone_reclaim_mode, -1 is apparently not a valid value, but we can set to them. And then kernel may crash. # echo -1 > /proc/sys/vm/vfs_cache_pressure Link: https://lkml.kernel.org/r/20201223105535.2875-1-linf@wangsu.com Signed-off-by: Lin Feng Cc: Alexey Dobriyan Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c9fbdd848138..62fbd09b5dc1 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2962,7 +2962,7 @@ static struct ctl_table vm_table[] = { .data = &block_dump, .maxlen = sizeof(block_dump), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, { @@ -2970,7 +2970,7 @@ static struct ctl_table vm_table[] = { .data = &sysctl_vfs_cache_pressure, .maxlen = sizeof(sysctl_vfs_cache_pressure), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, #if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \ @@ -2980,7 +2980,7 @@ static struct ctl_table vm_table[] = { .data = &sysctl_legacy_va_layout, .maxlen = sizeof(sysctl_legacy_va_layout), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, #endif @@ -2990,7 +2990,7 @@ static struct ctl_table vm_table[] = { .data = &node_reclaim_mode, .maxlen = sizeof(node_reclaim_mode), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, { -- cgit v1.2.3 From e1e014115dfd48ab3e3691ce46f9484ce12e67d4 Mon Sep 17 00:00:00 2001 From: Hubert Jasudowicz Date: Thu, 25 Feb 2021 17:21:07 -0800 Subject: groups: simplify struct group_info allocation Combine kmalloc and vmalloc into a single call. Use struct_size macro instead of direct size calculation. Link: https://lkml.kernel.org/r/ba9ba5beea9a44b7196c41a0d9528abd5f20dd2e.1611620846.git.hubert.jasudowicz@gmail.com Signed-off-by: Hubert Jasudowicz Cc: Gao Xiang Cc: Micah Morton Cc: Michael Kelley Cc: "Peter Zijlstra (Intel)" Cc: Thomas Cedeno Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/groups.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/groups.c b/kernel/groups.c index fe7e6385530e..787b381c7c00 100644 --- a/kernel/groups.c +++ b/kernel/groups.c @@ -15,12 +15,7 @@ struct group_info *groups_alloc(int gidsetsize) { struct group_info *gi; - unsigned int len; - - len = sizeof(struct group_info) + sizeof(kgid_t) * gidsetsize; - gi = kmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_NOWARN|__GFP_NORETRY); - if (!gi) - gi = __vmalloc(len, GFP_KERNEL_ACCOUNT); + gi = kvmalloc(struct_size(gi, gid, gidsetsize), GFP_KERNEL_ACCOUNT); if (!gi) return NULL; -- cgit v1.2.3 From c034f48e99907d5be147ac8f0f3e630a9307c2be Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 25 Feb 2021 17:21:10 -0800 Subject: kernel: delete repeated words in comments Drop repeated words in kernel/events/. {if, the, that, with, time} Drop repeated words in kernel/locking/. {it, no, the} Drop repeated words in kernel/sched/. {in, not} Link: https://lkml.kernel.org/r/20210127023412.26292-1-rdunlap@infradead.org Signed-off-by: Randy Dunlap Acked-by: Will Deacon [kernel/locking/] Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Will Deacon Cc: Mathieu Desnoyers Cc: "Paul E. McKenney" Cc: Juri Lelli Cc: Vincent Guittot Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/events/core.c | 8 ++++---- kernel/events/uprobes.c | 2 +- kernel/locking/rtmutex.c | 4 ++-- kernel/locking/rwsem.c | 2 +- kernel/locking/semaphore.c | 2 +- kernel/sched/fair.c | 2 +- kernel/sched/membarrier.c | 2 +- 7 files changed, 11 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 129dee540a8b..0aeca5f3c0ac 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -269,7 +269,7 @@ static void event_function_call(struct perf_event *event, event_f func, void *da if (!event->parent) { /* * If this is a !child event, we must hold ctx::mutex to - * stabilize the the event->ctx relation. See + * stabilize the event->ctx relation. See * perf_event_ctx_lock(). */ lockdep_assert_held(&ctx->mutex); @@ -1303,7 +1303,7 @@ static void put_ctx(struct perf_event_context *ctx) * life-time rules separate them. That is an exiting task cannot fork, and a * spawning task cannot (yet) exit. * - * But remember that that these are parent<->child context relations, and + * But remember that these are parent<->child context relations, and * migration does not affect children, therefore these two orderings should not * interact. * @@ -1442,7 +1442,7 @@ static u64 primary_event_id(struct perf_event *event) /* * Get the perf_event_context for a task and lock it. * - * This has to cope with with the fact that until it is locked, + * This has to cope with the fact that until it is locked, * the context could get moved to another task. */ static struct perf_event_context * @@ -2486,7 +2486,7 @@ static void perf_set_shadow_time(struct perf_event *event, * But this is a bit hairy. * * So instead, we have an explicit cgroup call to remain - * within the time time source all along. We believe it + * within the time source all along. We believe it * is cleaner and simpler to understand. */ if (is_cgroup_event(event)) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 3ea7f8f92f1d..6addc9780319 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1733,7 +1733,7 @@ void uprobe_free_utask(struct task_struct *t) } /* - * Allocate a uprobe_task object for the task if if necessary. + * Allocate a uprobe_task object for the task if necessary. * Called when the thread hits a breakpoint. * * Returns: diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 03b21135313c..48fff6437901 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1420,7 +1420,7 @@ rt_mutex_fasttrylock(struct rt_mutex *lock, } /* - * Performs the wakeup of the the top-waiter and re-enables preemption. + * Performs the wakeup of the top-waiter and re-enables preemption. */ void rt_mutex_postunlock(struct wake_q_head *wake_q) { @@ -1819,7 +1819,7 @@ struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock) * been started. * @waiter: the pre-initialized rt_mutex_waiter * - * Wait for the the lock acquisition started on our behalf by + * Wait for the lock acquisition started on our behalf by * rt_mutex_start_proxy_lock(). Upon failure, the caller must call * rt_mutex_cleanup_proxy_lock(). * diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index ba67600c7b2c..abba5df50006 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -1048,7 +1048,7 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) /* * If there were already threads queued before us and: - * 1) there are no no active locks, wake the front + * 1) there are no active locks, wake the front * queued process(es) as the handoff bit might be set. * 2) there are no active writers and some readers, the lock * must be read owned; so we try to wake any read lock diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c index d9dd94defc0a..9aa855a96c4a 100644 --- a/kernel/locking/semaphore.c +++ b/kernel/locking/semaphore.c @@ -119,7 +119,7 @@ EXPORT_SYMBOL(down_killable); * @sem: the semaphore to be acquired * * Try to acquire the semaphore atomically. Returns 0 if the semaphore has - * been acquired successfully or 1 if it it cannot be acquired. + * been acquired successfully or 1 if it cannot be acquired. * * NOTE: This return value is inverted from both spin_trylock and * mutex_trylock! Be careful about this when converting code. diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 8a8bd7b13634..794c2cb945f8 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5126,7 +5126,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) /* * When a group wakes up we want to make sure that its quota is not already * expired/exceeded, otherwise it may be allowed to steal additional ticks of - * runtime as update_curr() throttling can not not trigger until it's on-rq. + * runtime as update_curr() throttling can not trigger until it's on-rq. */ static void check_enqueue_throttle(struct cfs_rq *cfs_rq) { diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 08ae45ad9261..acdae625c636 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -454,7 +454,7 @@ static int sync_runqueues_membarrier_state(struct mm_struct *mm) /* * For each cpu runqueue, if the task's mm match @mm, ensure that all - * @mm's membarrier state set bits are also set in in the runqueue's + * @mm's membarrier state set bits are also set in the runqueue's * membarrier state. This ensures that a runqueue scheduling * between threads which are users of @mm has its membarrier state * updated. -- cgit v1.2.3 From d54ce6158e354f5358a547b96299ecd7f3725393 Mon Sep 17 00:00:00 2001 From: Sumit Garg Date: Thu, 25 Feb 2021 17:22:38 -0800 Subject: kgdb: fix to kill breakpoints on initmem after boot Currently breakpoints in kernel .init.text section are not handled correctly while allowing to remove them even after corresponding pages have been freed. Fix it via killing .init.text section breakpoints just prior to initmem pages being freed. Doug: "HW breakpoints aren't handled by this patch but it's probably not such a big deal". Link: https://lkml.kernel.org/r/20210224081652.587785-1-sumit.garg@linaro.org Signed-off-by: Sumit Garg Suggested-by: Doug Anderson Acked-by: Doug Anderson Acked-by: Daniel Thompson Tested-by: Daniel Thompson Cc: Masami Hiramatsu Cc: Steven Rostedt (VMware) Cc: Jason Wessel Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kgdb.h | 2 ++ init/main.c | 1 + kernel/debug/debug_core.c | 11 +++++++++++ 3 files changed, 14 insertions(+) (limited to 'kernel') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 0444b44bd156..392a3670944c 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -359,9 +359,11 @@ extern atomic_t kgdb_active; extern bool dbg_is_early; extern void __init dbg_late_init(void); extern void kgdb_panic(const char *msg); +extern void kgdb_free_init_mem(void); #else /* ! CONFIG_KGDB */ #define in_dbg_master() (0) #define dbg_late_init() static inline void kgdb_panic(const char *msg) {} +static inline void kgdb_free_init_mem(void) { } #endif /* ! CONFIG_KGDB */ #endif /* _KGDB_H_ */ diff --git a/init/main.c b/init/main.c index 3648c9f94882..53b278845b88 100644 --- a/init/main.c +++ b/init/main.c @@ -1426,6 +1426,7 @@ static int __ref kernel_init(void *unused) async_synchronize_full(); kprobe_free_init_mem(); ftrace_free_init_mem(); + kgdb_free_init_mem(); free_initmem(); mark_readonly(); diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index b636d517c02c..4708aec492df 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -455,6 +455,17 @@ setundefined: return 0; } +void kgdb_free_init_mem(void) +{ + int i; + + /* Clear init memory breakpoints. */ + for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) { + if (init_section_contains((void *)kgdb_break[i].bpt_addr, 0)) + kgdb_break[i].state = BP_UNDEFINED; + } +} + #ifdef CONFIG_KGDB_KDB void kdb_dump_stack_on_cpu(int cpu) { -- cgit v1.2.3