From 3e08a9f9760f4a70d633c328a76408e62d6f80a3 Mon Sep 17 00:00:00 2001 From: Liangyan Date: Mon, 7 Jun 2021 20:57:34 +0800 Subject: tracing: Correct the length check which causes memory corruption We've suffered from severe kernel crashes due to memory corruption on our production environment, like, Call Trace: [1640542.554277] general protection fault: 0000 [#1] SMP PTI [1640542.554856] CPU: 17 PID: 26996 Comm: python Kdump: loaded Tainted:G [1640542.556629] RIP: 0010:kmem_cache_alloc+0x90/0x190 [1640542.559074] RSP: 0018:ffffb16faa597df8 EFLAGS: 00010286 [1640542.559587] RAX: 0000000000000000 RBX: 0000000000400200 RCX: 0000000006e931bf [1640542.560323] RDX: 0000000006e931be RSI: 0000000000400200 RDI: ffff9a45ff004300 [1640542.560996] RBP: 0000000000400200 R08: 0000000000023420 R09: 0000000000000000 [1640542.561670] R10: 0000000000000000 R11: 0000000000000000 R12: ffffffff9a20608d [1640542.562366] R13: ffff9a45ff004300 R14: ffff9a45ff004300 R15: 696c662f65636976 [1640542.563128] FS: 00007f45d7c6f740(0000) GS:ffff9a45ff840000(0000) knlGS:0000000000000000 [1640542.563937] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [1640542.564557] CR2: 00007f45d71311a0 CR3: 000000189d63e004 CR4: 00000000003606e0 [1640542.565279] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [1640542.566069] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [1640542.566742] Call Trace: [1640542.567009] anon_vma_clone+0x5d/0x170 [1640542.567417] __split_vma+0x91/0x1a0 [1640542.567777] do_munmap+0x2c6/0x320 [1640542.568128] vm_munmap+0x54/0x70 [1640542.569990] __x64_sys_munmap+0x22/0x30 [1640542.572005] do_syscall_64+0x5b/0x1b0 [1640542.573724] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [1640542.575642] RIP: 0033:0x7f45d6e61e27 James Wang has reproduced it stably on the latest 4.19 LTS. After some debugging, we finally proved that it's due to ftrace buffer out-of-bound access using a debug tool as follows: [ 86.775200] BUG: Out-of-bounds write at addr 0xffff88aefe8b7000 [ 86.780806] no_context+0xdf/0x3c0 [ 86.784327] __do_page_fault+0x252/0x470 [ 86.788367] do_page_fault+0x32/0x140 [ 86.792145] page_fault+0x1e/0x30 [ 86.795576] strncpy_from_unsafe+0x66/0xb0 [ 86.799789] fetch_memory_string+0x25/0x40 [ 86.804002] fetch_deref_string+0x51/0x60 [ 86.808134] kprobe_trace_func+0x32d/0x3a0 [ 86.812347] kprobe_dispatcher+0x45/0x50 [ 86.816385] kprobe_ftrace_handler+0x90/0xf0 [ 86.820779] ftrace_ops_assist_func+0xa1/0x140 [ 86.825340] 0xffffffffc00750bf [ 86.828603] do_sys_open+0x5/0x1f0 [ 86.832124] do_syscall_64+0x5b/0x1b0 [ 86.835900] entry_SYSCALL_64_after_hwframe+0x44/0xa9 commit b220c049d519 ("tracing: Check length before giving out the filter buffer") adds length check to protect trace data overflow introduced in 0fc1b09ff1ff, seems that this fix can't prevent overflow entirely, the length check should also take the sizeof entry->array[0] into account, since this array[0] is filled the length of trace data and occupy addtional space and risk overflow. Link: https://lkml.kernel.org/r/20210607125734.1770447-1-liangyan.peng@linux.alibaba.com Cc: stable@vger.kernel.org Cc: Ingo Molnar Cc: Xunlei Pang Cc: Greg Kroah-Hartman Fixes: b220c049d519 ("tracing: Check length before giving out the filter buffer") Reviewed-by: Xunlei Pang Reviewed-by: yinbinbin Reviewed-by: Wetp Zhang Tested-by: James Wang Signed-off-by: Liangyan Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a21ef9cd2aae..9299057feb56 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2736,7 +2736,7 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb, (entry = this_cpu_read(trace_buffered_event))) { /* Try to use the per cpu buffer first */ val = this_cpu_inc_return(trace_buffered_event_cnt); - if ((len < (PAGE_SIZE - sizeof(*entry))) && val == 1) { + if ((len < (PAGE_SIZE - sizeof(*entry) - sizeof(entry->array[0]))) && val == 1) { trace_event_setup(entry, type, trace_ctx); entry->array[0] = len; return entry; -- cgit v1.2.3 From 85550c83da421fb12dc1816c45012e1e638d2b38 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 17 Jun 2021 13:47:25 -0400 Subject: tracing: Do not stop recording cmdlines when tracing is off The saved_cmdlines is used to map pids to the task name, such that the output of the tracing does not just show pids, but also gives a human readable name for the task. If the name is not mapped, the output looks like this: <...>-1316 [005] ...2 132.044039: ... Instead of this: gnome-shell-1316 [005] ...2 132.044039: ... The names are updated when tracing is running, but are skipped if tracing is stopped. Unfortunately, this stops the recording of the names if the top level tracer is stopped, and not if there's other tracers active. The recording of a name only happens when a new event is written into a ring buffer, so there is no need to test if tracing is on or not. If tracing is off, then no event is written and no need to test if tracing is off or not. Remove the check, as it hides the names of tasks for events in the instance buffers. Cc: stable@vger.kernel.org Fixes: 7ffbd48d5cab2 ("tracing: Cache comms only after an event occurred") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 9299057feb56..e220b37e29c6 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2486,8 +2486,6 @@ static bool tracing_record_taskinfo_skip(int flags) { if (unlikely(!(flags & (TRACE_RECORD_CMDLINE | TRACE_RECORD_TGID)))) return true; - if (atomic_read(&trace_record_taskinfo_disabled) || !tracing_is_on()) - return true; if (!__this_cpu_read(trace_taskinfo_save)) return true; return false; -- cgit v1.2.3 From 4fdd595e4f9a1ff6d93ec702eaecae451cfc6591 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 17 Jun 2021 14:32:34 -0400 Subject: tracing: Do not stop recording comms if the trace file is being read A while ago, when the "trace" file was opened, tracing was stopped, and code was added to stop recording the comms to saved_cmdlines, for mapping of the pids to the task name. Code has been added that only records the comm if a trace event occurred, and there's no reason to not trace it if the trace file is opened. Cc: stable@vger.kernel.org Fixes: 7ffbd48d5cab2 ("tracing: Cache comms only after an event occurred") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 9 --------- 1 file changed, 9 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index e220b37e29c6..d23a09d3eb37 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2198,9 +2198,6 @@ struct saved_cmdlines_buffer { }; static struct saved_cmdlines_buffer *savedcmd; -/* temporary disable recording */ -static atomic_t trace_record_taskinfo_disabled __read_mostly; - static inline char *get_saved_cmdlines(int idx) { return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN]; @@ -3996,9 +3993,6 @@ static void *s_start(struct seq_file *m, loff_t *pos) return ERR_PTR(-EBUSY); #endif - if (!iter->snapshot) - atomic_inc(&trace_record_taskinfo_disabled); - if (*pos != iter->pos) { iter->ent = NULL; iter->cpu = 0; @@ -4041,9 +4035,6 @@ static void s_stop(struct seq_file *m, void *p) return; #endif - if (!iter->snapshot) - atomic_dec(&trace_record_taskinfo_disabled); - trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); } -- cgit v1.2.3