From 62277de758b155dc04b78f195a1cb5208c37b2df Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Fri, 17 Jun 2016 17:33:59 +0000 Subject: ring-buffer: Fix return value check in test_ringbuffer() In case of error, the function kthread_run() returns ERR_PTR() and never returns NULL. The NULL test in the return value check should be replaced with IS_ERR(). Link: http://lkml.kernel.org/r/1466184839-14927-1-git-send-email-weiyj_lk@163.com Cc: stable@vger.kernel.org Fixes: 6c43e554a ("ring-buffer: Add ring buffer startup selftest") Signed-off-by: Wei Yongjun Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 96fc3c043ad6..54e7a90db848 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -4826,9 +4826,9 @@ static __init int test_ringbuffer(void) rb_data[cpu].cnt = cpu; rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu], "rbtester/%d", cpu); - if (WARN_ON(!rb_threads[cpu])) { + if (WARN_ON(IS_ERR(rb_threads[cpu]))) { pr_cont("FAILED\n"); - ret = -1; + ret = PTR_ERR(rb_threads[cpu]); goto out_free; } @@ -4838,9 +4838,9 @@ static __init int test_ringbuffer(void) /* Now create the rb hammer! */ rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer"); - if (WARN_ON(!rb_hammer)) { + if (WARN_ON(IS_ERR(rb_hammer))) { pr_cont("FAILED\n"); - ret = -1; + ret = PTR_ERR(rb_hammer); goto out_free; } -- cgit v1.2.3 From 82cc4fc2e70ec5baeff8f776f2773abc8b2cc0ae Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 14 Apr 2017 17:45:45 -0400 Subject: ftrace: Fix removing of second function probe When two function probes are added to set_ftrace_filter, and then one of them is removed, the update to the function locations is not performed, and the record keeping of the function states are corrupted, and causes an ftrace_bug() to occur. This is easily reproducable by adding two probes, removing one, and then adding it back again. # cd /sys/kernel/debug/tracing # echo schedule:traceoff > set_ftrace_filter # echo do_IRQ:traceoff > set_ftrace_filter # echo \!do_IRQ:traceoff > /debug/tracing/set_ftrace_filter # echo do_IRQ:traceoff > set_ftrace_filter Causes: ------------[ cut here ]------------ WARNING: CPU: 2 PID: 1098 at kernel/trace/ftrace.c:2369 ftrace_get_addr_curr+0x143/0x220 Modules linked in: [...] CPU: 2 PID: 1098 Comm: bash Not tainted 4.10.0-test+ #405 Hardware name: Hewlett-Packard HP Compaq Pro 6300 SFF/339A, BIOS K01 v02.05 05/07/2012 Call Trace: dump_stack+0x68/0x9f __warn+0x111/0x130 ? trace_irq_work_interrupt+0xa0/0xa0 warn_slowpath_null+0x1d/0x20 ftrace_get_addr_curr+0x143/0x220 ? __fentry__+0x10/0x10 ftrace_replace_code+0xe3/0x4f0 ? ftrace_int3_handler+0x90/0x90 ? printk+0x99/0xb5 ? 0xffffffff81000000 ftrace_modify_all_code+0x97/0x110 arch_ftrace_update_code+0x10/0x20 ftrace_run_update_code+0x1c/0x60 ftrace_run_modify_code.isra.48.constprop.62+0x8e/0xd0 register_ftrace_function_probe+0x4b6/0x590 ? ftrace_startup+0x310/0x310 ? debug_lockdep_rcu_enabled.part.4+0x1a/0x30 ? update_stack_state+0x88/0x110 ? ftrace_regex_write.isra.43.part.44+0x1d3/0x320 ? preempt_count_sub+0x18/0xd0 ? mutex_lock_nested+0x104/0x800 ? ftrace_regex_write.isra.43.part.44+0x1d3/0x320 ? __unwind_start+0x1c0/0x1c0 ? _mutex_lock_nest_lock+0x800/0x800 ftrace_trace_probe_callback.isra.3+0xc0/0x130 ? func_set_flag+0xe0/0xe0 ? __lock_acquire+0x642/0x1790 ? __might_fault+0x1e/0x20 ? trace_get_user+0x398/0x470 ? strcmp+0x35/0x60 ftrace_trace_onoff_callback+0x48/0x70 ftrace_regex_write.isra.43.part.44+0x251/0x320 ? match_records+0x420/0x420 ftrace_filter_write+0x2b/0x30 __vfs_write+0xd7/0x330 ? do_loop_readv_writev+0x120/0x120 ? locks_remove_posix+0x90/0x2f0 ? do_lock_file_wait+0x160/0x160 ? __lock_is_held+0x93/0x100 ? rcu_read_lock_sched_held+0x5c/0xb0 ? preempt_count_sub+0x18/0xd0 ? __sb_start_write+0x10a/0x230 ? vfs_write+0x222/0x240 vfs_write+0xef/0x240 SyS_write+0xab/0x130 ? SyS_read+0x130/0x130 ? trace_hardirqs_on_caller+0x182/0x280 ? trace_hardirqs_on_thunk+0x1a/0x1c entry_SYSCALL_64_fastpath+0x18/0xad RIP: 0033:0x7fe61c157c30 RSP: 002b:00007ffe87890258 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: ffffffff8114a410 RCX: 00007fe61c157c30 RDX: 0000000000000010 RSI: 000055814798f5e0 RDI: 0000000000000001 RBP: ffff8800c9027f98 R08: 00007fe61c422740 R09: 00007fe61ca53700 R10: 0000000000000073 R11: 0000000000000246 R12: 0000558147a36400 R13: 00007ffe8788f160 R14: 0000000000000024 R15: 00007ffe8788f15c ? trace_hardirqs_off_caller+0xc0/0x110 ---[ end trace 99fa09b3d9869c2c ]--- Bad trampoline accounting at: ffffffff81cc3b00 (do_IRQ+0x0/0x150) Cc: stable@vger.kernel.org Fixes: 59df055f1991 ("ftrace: trace different functions with a different tracer") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index b9691ee8f6c1..27bb2e61276e 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3755,23 +3755,24 @@ static void __enable_ftrace_function_probe(struct ftrace_ops_hash *old_hash) ftrace_probe_registered = 1; } -static void __disable_ftrace_function_probe(void) +static bool __disable_ftrace_function_probe(void) { int i; if (!ftrace_probe_registered) - return; + return false; for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) { struct hlist_head *hhd = &ftrace_func_hash[i]; if (hhd->first) - return; + return false; } /* no more funcs left */ ftrace_shutdown(&trace_probe_ops, 0); ftrace_probe_registered = 0; + return true; } @@ -3901,6 +3902,7 @@ static void __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, void *data, int flags) { + struct ftrace_ops_hash old_hash_ops; struct ftrace_func_entry *rec_entry; struct ftrace_func_probe *entry; struct ftrace_func_probe *p; @@ -3912,6 +3914,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, struct hlist_node *tmp; char str[KSYM_SYMBOL_LEN]; int i, ret; + bool disabled; if (glob && (strcmp(glob, "*") == 0 || !strlen(glob))) func_g.search = NULL; @@ -3930,6 +3933,10 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, mutex_lock(&trace_probe_ops.func_hash->regex_lock); + old_hash_ops.filter_hash = old_hash; + /* Probes only have filters */ + old_hash_ops.notrace_hash = NULL; + hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash); if (!hash) /* Hmm, should report this somehow */ @@ -3967,12 +3974,17 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, } } mutex_lock(&ftrace_lock); - __disable_ftrace_function_probe(); + disabled = __disable_ftrace_function_probe(); /* * Remove after the disable is called. Otherwise, if the last * probe is removed, a null hash means *all enabled*. */ ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash); + + /* still need to update the function call sites */ + if (ftrace_enabled && !disabled) + ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS, + &old_hash_ops); synchronize_sched(); if (!ret) free_ftrace_hash_rcu(old_hash); -- cgit v1.2.3 From d879d0b8c183aabeb9a65eba91f3f9e3c7e7b905 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 17 Apr 2017 11:44:27 +0900 Subject: ftrace: Fix function pid filter on instances When function tracer has a pid filter, it adds a probe to sched_switch to track if current task can be ignored. The probe checks the ftrace_ignore_pid from current tr to filter tasks. But it misses to delete the probe when removing an instance so that it can cause a crash due to the invalid tr pointer (use-after-free). This is easily reproducible with the following: # cd /sys/kernel/debug/tracing # mkdir instances/buggy # echo $$ > instances/buggy/set_ftrace_pid # rmdir instances/buggy ============================================================================ BUG: KASAN: use-after-free in ftrace_filter_pid_sched_switch_probe+0x3d/0x90 Read of size 8 by task kworker/0:1/17 CPU: 0 PID: 17 Comm: kworker/0:1 Tainted: G B 4.11.0-rc3 #198 Call Trace: dump_stack+0x68/0x9f kasan_object_err+0x21/0x70 kasan_report.part.1+0x22b/0x500 ? ftrace_filter_pid_sched_switch_probe+0x3d/0x90 kasan_report+0x25/0x30 __asan_load8+0x5e/0x70 ftrace_filter_pid_sched_switch_probe+0x3d/0x90 ? fpid_start+0x130/0x130 __schedule+0x571/0xce0 ... To fix it, use ftrace_clear_pids() to unregister the probe. As instance_rmdir() already updated ftrace codes, it can just free the filter safely. Link: http://lkml.kernel.org/r/20170417024430.21194-2-namhyung@kernel.org Fixes: 0c8916c34203 ("tracing: Add rmdir to remove multibuffer instances") Cc: Ingo Molnar Cc: stable@vger.kernel.org Reviewed-by: Masami Hiramatsu Signed-off-by: Namhyung Kim Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 9 +++++++++ kernel/trace/trace.c | 1 + kernel/trace/trace.h | 2 ++ 3 files changed, 12 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 27bb2e61276e..dd3e91d68dc7 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5566,6 +5566,15 @@ static void clear_ftrace_pids(struct trace_array *tr) trace_free_pid_list(pid_list); } +void ftrace_clear_pids(struct trace_array *tr) +{ + mutex_lock(&ftrace_lock); + + clear_ftrace_pids(tr); + + mutex_unlock(&ftrace_lock); +} + static void ftrace_pid_reset(struct trace_array *tr) { mutex_lock(&ftrace_lock); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f35109514a01..d484452ae648 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7402,6 +7402,7 @@ static int instance_rmdir(const char *name) tracing_set_nop(tr); event_trace_del_tracer(tr); + ftrace_clear_pids(tr); ftrace_destroy_function_files(tr); tracefs_remove_recursive(tr->dir); free_trace_buffers(tr); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index ae1cce91fead..d19d52d600d6 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -896,6 +896,7 @@ int using_ftrace_ops_list_func(void); void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer); void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d_tracer); +void ftrace_clear_pids(struct trace_array *tr); #else static inline int ftrace_trace_task(struct trace_array *tr) { @@ -914,6 +915,7 @@ ftrace_init_global_array_ops(struct trace_array *tr) { } static inline void ftrace_reset_array_ops(struct trace_array *tr) { } static inline void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d) { } static inline void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d) { } +static inline void ftrace_clear_pids(struct trace_array *tr) { } /* ftace_func_t type is not defined, use macro instead of static inline */ #define ftrace_init_array_ops(tr, func) do { } while (0) #endif /* CONFIG_FUNCTION_TRACER */ -- cgit v1.2.3 From df62db5be2e5f070ecd1a5ece5945b590ee112e0 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 19 Apr 2017 12:07:08 -0400 Subject: tracing: Allocate the snapshot buffer before enabling probe Currently the snapshot trigger enables the probe and then allocates the snapshot. If the probe triggers before the allocation, it could cause the snapshot to fail and turn tracing off. It's best to allocate the snapshot buffer first, and then enable the trigger. If something goes wrong in the enabling of the trigger, the snapshot buffer is still allocated, but it can also be freed by the user by writting zero into the snapshot buffer file. Also add a check of the return status of alloc_snapshot(). Cc: stable@vger.kernel.org Fixes: 77fd5c15e3 ("tracing: Add snapshot trigger to function probes") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d484452ae648..0ad75e9698f6 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6733,11 +6733,13 @@ ftrace_trace_snapshot_callback(struct ftrace_hash *hash, return ret; out_reg: - ret = register_ftrace_function_probe(glob, ops, count); + ret = alloc_snapshot(&global_trace); + if (ret < 0) + goto out; - if (ret >= 0) - alloc_snapshot(&global_trace); + ret = register_ftrace_function_probe(glob, ops, count); + out: return ret < 0 ? ret : 0; } -- cgit v1.2.3 From 78f7a45dac2a2d2002f98a3a95f7979867868d73 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 19 Apr 2017 14:29:46 -0400 Subject: ring-buffer: Have ring_buffer_iter_empty() return true when empty I noticed that reading the snapshot file when it is empty no longer gives a status. It suppose to show the status of the snapshot buffer as well as how to allocate and use it. For example: ># cat snapshot # tracer: nop # # # * Snapshot is allocated * # # Snapshot commands: # echo 0 > snapshot : Clears and frees snapshot buffer # echo 1 > snapshot : Allocates snapshot buffer, if not already allocated. # Takes a snapshot of the main buffer. # echo 2 > snapshot : Clears snapshot buffer (but does not allocate or free) # (Doesn't have to be '2' works with any number that # is not a '0' or '1') But instead it just showed an empty buffer: ># cat snapshot # tracer: nop # # entries-in-buffer/entries-written: 0/0 #P:4 # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / delay # TASK-PID CPU# |||| TIMESTAMP FUNCTION # | | | |||| | | What happened was that it was using the ring_buffer_iter_empty() function to see if it was empty, and if it was, it showed the status. But that function was returning false when it was empty. The reason was that the iter header page was on the reader page, and the reader page was empty, but so was the buffer itself. The check only tested to see if the iter was on the commit page, but the commit page was no longer pointing to the reader page, but as all pages were empty, the buffer is also. Cc: stable@vger.kernel.org Fixes: 651e22f2701b ("ring-buffer: Always reset iterator to reader page") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 54e7a90db848..ca47a4fa2986 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3405,11 +3405,23 @@ EXPORT_SYMBOL_GPL(ring_buffer_iter_reset); int ring_buffer_iter_empty(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer; + struct buffer_page *reader; + struct buffer_page *head_page; + struct buffer_page *commit_page; + unsigned commit; cpu_buffer = iter->cpu_buffer; - return iter->head_page == cpu_buffer->commit_page && - iter->head == rb_commit_index(cpu_buffer); + /* Remember, trace recording is off when iterator is in use */ + reader = cpu_buffer->reader_page; + head_page = cpu_buffer->head_page; + commit_page = cpu_buffer->commit_page; + commit = rb_page_commit(commit_page); + + return ((iter->head_page == commit_page && iter->head == commit) || + (iter->head_page == reader && commit_page == head_page && + head_page->read == commit && + iter->head == rb_page_commit(cpu_buffer->reader_page))); } EXPORT_SYMBOL_GPL(ring_buffer_iter_empty); -- cgit v1.2.3