From 8b05a3a7503c2a982c9c462eae96cfbd59506783 Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Fri, 11 Jan 2019 07:01:13 +0100 Subject: tracing/kprobes: Fix NULL pointer dereference in trace_kprobe_create() It is possible to trigger a NULL pointer dereference by writing an incorrectly formatted string to krpobe_events (trying to create a kretprobe omitting the symbol). Example: echo "r:event_1 " >> /sys/kernel/debug/tracing/kprobe_events That triggers this: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 6 PID: 1757 Comm: bash Not tainted 5.0.0-rc1+ #125 Hardware name: Dell Inc. XPS 13 9370/0F6P3V, BIOS 1.5.1 08/09/2018 RIP: 0010:kstrtoull+0x2/0x20 Code: 28 00 00 00 75 17 48 83 c4 18 5b 41 5c 5d c3 b8 ea ff ff ff eb e1 b8 de ff ff ff eb da e8 d6 36 bb ff 66 0f 1f 44 00 00 31 c0 <80> 3f 2b 55 48 89 e5 0f 94 c0 48 01 c7 e8 5c ff ff ff 5d c3 66 2e RSP: 0018:ffffb5d482e57cb8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000001 RCX: ffffffff82b12720 RDX: ffffb5d482e57cf8 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffffb5d482e57d70 R08: ffffa0c05e5a7080 R09: ffffa0c05e003980 R10: 0000000000000000 R11: 0000000040000000 R12: ffffa0c04fe87b08 R13: 0000000000000001 R14: 000000000000000b R15: ffffa0c058d749e1 FS: 00007f137c7f7740(0000) GS:ffffa0c05e580000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000497d46004 CR4: 00000000003606e0 Call Trace: ? trace_kprobe_create+0xb6/0x840 ? _cond_resched+0x19/0x40 ? _cond_resched+0x19/0x40 ? __kmalloc+0x62/0x210 ? argv_split+0x8f/0x140 ? trace_kprobe_create+0x840/0x840 ? trace_kprobe_create+0x840/0x840 create_or_delete_trace_kprobe+0x11/0x30 trace_run_command+0x50/0x90 trace_parse_run_command+0xc1/0x160 probes_write+0x10/0x20 __vfs_write+0x3a/0x1b0 ? apparmor_file_permission+0x1a/0x20 ? security_file_permission+0x31/0xf0 ? _cond_resched+0x19/0x40 vfs_write+0xb1/0x1a0 ksys_write+0x55/0xc0 __x64_sys_write+0x1a/0x20 do_syscall_64+0x5a/0x120 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fix by doing the proper argument checks in trace_kprobe_create(). Cc: Ingo Molnar Link: https://lore.kernel.org/lkml/20190111095108.b79a2ee026185cbd62365977@kernel.org Link: http://lkml.kernel.org/r/20190111060113.GA22841@xps-13 Fixes: 6212dd29683e ("tracing/kprobes: Use dyn_event framework for kprobe events") Acked-by: Masami Hiramatsu Signed-off-by: Andrea Righi Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_kprobe.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 5c19b8c41c7e..d5fb09ebba8b 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -607,11 +607,17 @@ static int trace_kprobe_create(int argc, const char *argv[]) char buf[MAX_EVENT_NAME_LEN]; unsigned int flags = TPARG_FL_KERNEL; - /* argc must be >= 1 */ - if (argv[0][0] == 'r') { + switch (argv[0][0]) { + case 'r': is_return = true; flags |= TPARG_FL_RETURN; - } else if (argv[0][0] != 'p' || argc < 2) + break; + case 'p': + break; + default: + return -ECANCELED; + } + if (argc < 2) return -ECANCELED; event = strchr(&argv[0][1], ':'); -- cgit v1.2.3 From ea6eb5e7d15e1838de335609994b4546e2abcaaf Mon Sep 17 00:00:00 2001 From: Andreas Ziegler Date: Thu, 17 Jan 2019 14:30:23 +0100 Subject: tracing: uprobes: Fix typo in pr_fmt string The subsystem-specific message prefix for uprobes was also "trace_kprobe: " instead of "trace_uprobe: " as described in the original commit message. Link: http://lkml.kernel.org/r/20190117133023.19292-1-andreas.ziegler@fau.de Cc: Ingo Molnar Cc: stable@vger.kernel.org Acked-by: Masami Hiramatsu Fixes: 7257634135c24 ("tracing/probe: Show subsystem name in messages") Signed-off-by: Andreas Ziegler Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_uprobe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index e335576b9411..19a1a8e19062 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -5,7 +5,7 @@ * Copyright (C) IBM Corporation, 2010-2012 * Author: Srikar Dronamraju */ -#define pr_fmt(fmt) "trace_kprobe: " fmt +#define pr_fmt(fmt) "trace_uprobe: " fmt #include #include -- cgit v1.2.3 From 0722069a5374b904ec1a67f91249f90e1cfae259 Mon Sep 17 00:00:00 2001 From: Andreas Ziegler Date: Wed, 16 Jan 2019 15:16:29 +0100 Subject: tracing/uprobes: Fix output for multiple string arguments When printing multiple uprobe arguments as strings the output for the earlier arguments would also include all later string arguments. This is best explained in an example: Consider adding a uprobe to a function receiving two strings as parameters which is at offset 0xa0 in strlib.so and we want to print both parameters when the uprobe is hit (on x86_64): $ echo 'p:func /lib/strlib.so:0xa0 +0(%di):string +0(%si):string' > \ /sys/kernel/debug/tracing/uprobe_events When the function is called as func("foo", "bar") and we hit the probe, the trace file shows a line like the following: [...] func: (0x7f7e683706a0) arg1="foobar" arg2="bar" Note the extra "bar" printed as part of arg1. This behaviour stacks up for additional string arguments. The strings are stored in a dynamically growing part of the uprobe buffer by fetch_store_string() after copying them from userspace via strncpy_from_user(). The return value of strncpy_from_user() is then directly used as the required size for the string. However, this does not take the terminating null byte into account as the documentation for strncpy_from_user() cleary states that it "[...] returns the length of the string (not including the trailing NUL)" even though the null byte will be copied to the destination. Therefore, subsequent calls to fetch_store_string() will overwrite the terminating null byte of the most recently fetched string with the first character of the current string, leading to the "accumulation" of strings in earlier arguments in the output. Fix this by incrementing the return value of strncpy_from_user() by one if we did not hit the maximum buffer size. Link: http://lkml.kernel.org/r/20190116141629.5752-1-andreas.ziegler@fau.de Cc: Ingo Molnar Cc: stable@vger.kernel.org Fixes: 5baaa59ef09e ("tracing/probes: Implement 'memory' fetch method for uprobes") Acked-by: Masami Hiramatsu Signed-off-by: Andreas Ziegler Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_uprobe.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 19a1a8e19062..9bde07c06362 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -160,6 +160,13 @@ fetch_store_string(unsigned long addr, void *dest, void *base) if (ret >= 0) { if (ret == maxlen) dst[ret - 1] = '\0'; + else + /* + * Include the terminating null byte. In this case it + * was copied by strncpy_from_user but not accounted + * for in ret. + */ + ret++; *(u32 *)dest = make_data_loc(ret, (void *)dst - base); } -- cgit v1.2.3 From e16ec34039c701594d55d08a5aa49ee3e1abc821 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 30 Jan 2019 18:12:44 -0800 Subject: bpf: fix potential deadlock in bpf_prog_register Lockdep found a potential deadlock between cpu_hotplug_lock, bpf_event_mutex, and cpuctx_mutex: [ 13.007000] WARNING: possible circular locking dependency detected [ 13.007587] 5.0.0-rc3-00018-g2fa53f892422-dirty #477 Not tainted [ 13.008124] ------------------------------------------------------ [ 13.008624] test_progs/246 is trying to acquire lock: [ 13.009030] 0000000094160d1d (tracepoints_mutex){+.+.}, at: tracepoint_probe_register_prio+0x2d/0x300 [ 13.009770] [ 13.009770] but task is already holding lock: [ 13.010239] 00000000d663ef86 (bpf_event_mutex){+.+.}, at: bpf_probe_register+0x1d/0x60 [ 13.010877] [ 13.010877] which lock already depends on the new lock. [ 13.010877] [ 13.011532] [ 13.011532] the existing dependency chain (in reverse order) is: [ 13.012129] [ 13.012129] -> #4 (bpf_event_mutex){+.+.}: [ 13.012582] perf_event_query_prog_array+0x9b/0x130 [ 13.013016] _perf_ioctl+0x3aa/0x830 [ 13.013354] perf_ioctl+0x2e/0x50 [ 13.013668] do_vfs_ioctl+0x8f/0x6a0 [ 13.014003] ksys_ioctl+0x70/0x80 [ 13.014320] __x64_sys_ioctl+0x16/0x20 [ 13.014668] do_syscall_64+0x4a/0x180 [ 13.015007] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 13.015469] [ 13.015469] -> #3 (&cpuctx_mutex){+.+.}: [ 13.015910] perf_event_init_cpu+0x5a/0x90 [ 13.016291] perf_event_init+0x1b2/0x1de [ 13.016654] start_kernel+0x2b8/0x42a [ 13.016995] secondary_startup_64+0xa4/0xb0 [ 13.017382] [ 13.017382] -> #2 (pmus_lock){+.+.}: [ 13.017794] perf_event_init_cpu+0x21/0x90 [ 13.018172] cpuhp_invoke_callback+0xb3/0x960 [ 13.018573] _cpu_up+0xa7/0x140 [ 13.018871] do_cpu_up+0xa4/0xc0 [ 13.019178] smp_init+0xcd/0xd2 [ 13.019483] kernel_init_freeable+0x123/0x24f [ 13.019878] kernel_init+0xa/0x110 [ 13.020201] ret_from_fork+0x24/0x30 [ 13.020541] [ 13.020541] -> #1 (cpu_hotplug_lock.rw_sem){++++}: [ 13.021051] static_key_slow_inc+0xe/0x20 [ 13.021424] tracepoint_probe_register_prio+0x28c/0x300 [ 13.021891] perf_trace_event_init+0x11f/0x250 [ 13.022297] perf_trace_init+0x6b/0xa0 [ 13.022644] perf_tp_event_init+0x25/0x40 [ 13.023011] perf_try_init_event+0x6b/0x90 [ 13.023386] perf_event_alloc+0x9a8/0xc40 [ 13.023754] __do_sys_perf_event_open+0x1dd/0xd30 [ 13.024173] do_syscall_64+0x4a/0x180 [ 13.024519] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 13.024968] [ 13.024968] -> #0 (tracepoints_mutex){+.+.}: [ 13.025434] __mutex_lock+0x86/0x970 [ 13.025764] tracepoint_probe_register_prio+0x2d/0x300 [ 13.026215] bpf_probe_register+0x40/0x60 [ 13.026584] bpf_raw_tracepoint_open.isra.34+0xa4/0x130 [ 13.027042] __do_sys_bpf+0x94f/0x1a90 [ 13.027389] do_syscall_64+0x4a/0x180 [ 13.027727] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 13.028171] [ 13.028171] other info that might help us debug this: [ 13.028171] [ 13.028807] Chain exists of: [ 13.028807] tracepoints_mutex --> &cpuctx_mutex --> bpf_event_mutex [ 13.028807] [ 13.029666] Possible unsafe locking scenario: [ 13.029666] [ 13.030140] CPU0 CPU1 [ 13.030510] ---- ---- [ 13.030875] lock(bpf_event_mutex); [ 13.031166] lock(&cpuctx_mutex); [ 13.031645] lock(bpf_event_mutex); [ 13.032135] lock(tracepoints_mutex); [ 13.032441] [ 13.032441] *** DEADLOCK *** [ 13.032441] [ 13.032911] 1 lock held by test_progs/246: [ 13.033239] #0: 00000000d663ef86 (bpf_event_mutex){+.+.}, at: bpf_probe_register+0x1d/0x60 [ 13.033909] [ 13.033909] stack backtrace: [ 13.034258] CPU: 1 PID: 246 Comm: test_progs Not tainted 5.0.0-rc3-00018-g2fa53f892422-dirty #477 [ 13.034964] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014 [ 13.035657] Call Trace: [ 13.035859] dump_stack+0x5f/0x8b [ 13.036130] print_circular_bug.isra.37+0x1ce/0x1db [ 13.036526] __lock_acquire+0x1158/0x1350 [ 13.036852] ? lock_acquire+0x98/0x190 [ 13.037154] lock_acquire+0x98/0x190 [ 13.037447] ? tracepoint_probe_register_prio+0x2d/0x300 [ 13.037876] __mutex_lock+0x86/0x970 [ 13.038167] ? tracepoint_probe_register_prio+0x2d/0x300 [ 13.038600] ? tracepoint_probe_register_prio+0x2d/0x300 [ 13.039028] ? __mutex_lock+0x86/0x970 [ 13.039337] ? __mutex_lock+0x24a/0x970 [ 13.039649] ? bpf_probe_register+0x1d/0x60 [ 13.039992] ? __bpf_trace_sched_wake_idle_without_ipi+0x10/0x10 [ 13.040478] ? tracepoint_probe_register_prio+0x2d/0x300 [ 13.040906] tracepoint_probe_register_prio+0x2d/0x300 [ 13.041325] bpf_probe_register+0x40/0x60 [ 13.041649] bpf_raw_tracepoint_open.isra.34+0xa4/0x130 [ 13.042068] ? __might_fault+0x3e/0x90 [ 13.042374] __do_sys_bpf+0x94f/0x1a90 [ 13.042678] do_syscall_64+0x4a/0x180 [ 13.042975] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 13.043382] RIP: 0033:0x7f23b10a07f9 [ 13.045155] RSP: 002b:00007ffdef42fdd8 EFLAGS: 00000202 ORIG_RAX: 0000000000000141 [ 13.045759] RAX: ffffffffffffffda RBX: 00007ffdef42ff70 RCX: 00007f23b10a07f9 [ 13.046326] RDX: 0000000000000070 RSI: 00007ffdef42fe10 RDI: 0000000000000011 [ 13.046893] RBP: 00007ffdef42fdf0 R08: 0000000000000038 R09: 00007ffdef42fe10 [ 13.047462] R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000000000 [ 13.048029] R13: 0000000000000016 R14: 00007f23b1db4690 R15: 0000000000000000 Since tracepoints_mutex will be taken in tracepoint_probe_register/unregister() there is no need to take bpf_event_mutex too. bpf_event_mutex is protecting modifications to prog array used in kprobe/perf bpf progs. bpf_raw_tracepoints don't need to take this mutex. Fixes: c4f6699dfcb8 ("bpf: introduce BPF_RAW_TRACEPOINT") Acked-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/trace/bpf_trace.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 8b068adb9da1..f1a86a0d881d 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1204,22 +1204,12 @@ static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog * int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog) { - int err; - - mutex_lock(&bpf_event_mutex); - err = __bpf_probe_register(btp, prog); - mutex_unlock(&bpf_event_mutex); - return err; + return __bpf_probe_register(btp, prog); } int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog) { - int err; - - mutex_lock(&bpf_event_mutex); - err = tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog); - mutex_unlock(&bpf_event_mutex); - return err; + return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog); } int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, -- cgit v1.2.3 From f6675872db57305fa957021efc788f9983ed3b67 Mon Sep 17 00:00:00 2001 From: Andreas Ziegler Date: Wed, 6 Feb 2019 20:00:13 +0100 Subject: tracing: probeevent: Correctly update remaining space in dynamic area Commit 9178412ddf5a ("tracing: probeevent: Return consumed bytes of dynamic area") improved the string fetching mechanism by returning the number of required bytes after copying the argument to the dynamic area. However, this return value is now only used to increment the pointer inside the dynamic area but misses updating the 'maxlen' variable which indicates the remaining space in the dynamic area. This means that fetch_store_string() always reads the *total* size of the dynamic area from the data_loc pointer instead of the *remaining* size (and passes it along to strncpy_from_{user,unsafe}) even if we're already about to copy data into the middle of the dynamic area. Link: http://lkml.kernel.org/r/20190206190013.16405-1-andreas.ziegler@fau.de Cc: Ingo Molnar Cc: stable@vger.kernel.org Fixes: 9178412ddf5a ("tracing: probeevent: Return consumed bytes of dynamic area") Acked-by: Masami Hiramatsu Signed-off-by: Andreas Ziegler Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_probe_tmpl.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h index 5c56afc17cf8..4737bb8c07a3 100644 --- a/kernel/trace/trace_probe_tmpl.h +++ b/kernel/trace/trace_probe_tmpl.h @@ -180,10 +180,12 @@ store_trace_args(void *data, struct trace_probe *tp, struct pt_regs *regs, if (unlikely(arg->dynamic)) *dl = make_data_loc(maxlen, dyndata - base); ret = process_fetch_insn(arg->code, regs, dl, base); - if (unlikely(ret < 0 && arg->dynamic)) + if (unlikely(ret < 0 && arg->dynamic)) { *dl = make_data_loc(0, dyndata - base); - else + } else { dyndata += ret; + maxlen -= ret; + } } } -- cgit v1.2.3