From 3a38bb98d9abdc3856f26b5ed4332803065cd7cf Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 10 Apr 2018 09:37:32 -0700 Subject: bpf/tracing: fix a deadlock in perf_event_detach_bpf_prog syzbot reported a possible deadlock in perf_event_detach_bpf_prog. The error details: ====================================================== WARNING: possible circular locking dependency detected 4.16.0-rc7+ #3 Not tainted ------------------------------------------------------ syz-executor7/24531 is trying to acquire lock: (bpf_event_mutex){+.+.}, at: [<000000008a849b07>] perf_event_detach_bpf_prog+0x92/0x3d0 kernel/trace/bpf_trace.c:854 but task is already holding lock: (&mm->mmap_sem){++++}, at: [<0000000038768f87>] vm_mmap_pgoff+0x198/0x280 mm/util.c:353 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++}: __might_fault+0x13a/0x1d0 mm/memory.c:4571 _copy_to_user+0x2c/0xc0 lib/usercopy.c:25 copy_to_user include/linux/uaccess.h:155 [inline] bpf_prog_array_copy_info+0xf2/0x1c0 kernel/bpf/core.c:1694 perf_event_query_prog_array+0x1c7/0x2c0 kernel/trace/bpf_trace.c:891 _perf_ioctl kernel/events/core.c:4750 [inline] perf_ioctl+0x3e1/0x1480 kernel/events/core.c:4770 vfs_ioctl fs/ioctl.c:46 [inline] do_vfs_ioctl+0x1b1/0x1520 fs/ioctl.c:686 SYSC_ioctl fs/ioctl.c:701 [inline] SyS_ioctl+0x8f/0xc0 fs/ioctl.c:692 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x42/0xb7 -> #0 (bpf_event_mutex){+.+.}: lock_acquire+0x1d5/0x580 kernel/locking/lockdep.c:3920 __mutex_lock_common kernel/locking/mutex.c:756 [inline] __mutex_lock+0x16f/0x1a80 kernel/locking/mutex.c:893 mutex_lock_nested+0x16/0x20 kernel/locking/mutex.c:908 perf_event_detach_bpf_prog+0x92/0x3d0 kernel/trace/bpf_trace.c:854 perf_event_free_bpf_prog kernel/events/core.c:8147 [inline] _free_event+0xbdb/0x10f0 kernel/events/core.c:4116 put_event+0x24/0x30 kernel/events/core.c:4204 perf_mmap_close+0x60d/0x1010 kernel/events/core.c:5172 remove_vma+0xb4/0x1b0 mm/mmap.c:172 remove_vma_list mm/mmap.c:2490 [inline] do_munmap+0x82a/0xdf0 mm/mmap.c:2731 mmap_region+0x59e/0x15a0 mm/mmap.c:1646 do_mmap+0x6c0/0xe00 mm/mmap.c:1483 do_mmap_pgoff include/linux/mm.h:2223 [inline] vm_mmap_pgoff+0x1de/0x280 mm/util.c:355 SYSC_mmap_pgoff mm/mmap.c:1533 [inline] SyS_mmap_pgoff+0x462/0x5f0 mm/mmap.c:1491 SYSC_mmap arch/x86/kernel/sys_x86_64.c:100 [inline] SyS_mmap+0x16/0x20 arch/x86/kernel/sys_x86_64.c:91 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x42/0xb7 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&mm->mmap_sem); lock(bpf_event_mutex); lock(&mm->mmap_sem); lock(bpf_event_mutex); *** DEADLOCK *** ====================================================== The bug is introduced by Commit f371b304f12e ("bpf/tracing: allow user space to query prog array on the same tp") where copy_to_user, which requires mm->mmap_sem, is called inside bpf_event_mutex lock. At the same time, during perf_event file descriptor close, mm->mmap_sem is held first and then subsequent perf_event_detach_bpf_prog needs bpf_event_mutex lock. Such a senario caused a deadlock. As suggested by Daniel, moving copy_to_user out of the bpf_event_mutex lock should fix the problem. Fixes: f371b304f12e ("bpf/tracing: allow user space to query prog array on the same tp") Reported-by: syzbot+dc5ca0e4c9bfafaf2bae@syzkaller.appspotmail.com Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann --- kernel/trace/bpf_trace.c | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index d88e96d4e12c..56ba0f2a01db 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -977,6 +977,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info) { struct perf_event_query_bpf __user *uquery = info; struct perf_event_query_bpf query = {}; + u32 *ids, prog_cnt, ids_len; int ret; if (!capable(CAP_SYS_ADMIN)) @@ -985,16 +986,32 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info) return -EINVAL; if (copy_from_user(&query, uquery, sizeof(query))) return -EFAULT; - if (query.ids_len > BPF_TRACE_MAX_PROGS) + + ids_len = query.ids_len; + if (ids_len > BPF_TRACE_MAX_PROGS) return -E2BIG; + ids = kcalloc(ids_len, sizeof(u32), GFP_USER | __GFP_NOWARN); + if (!ids) + return -ENOMEM; + /* + * The above kcalloc returns ZERO_SIZE_PTR when ids_len = 0, which + * is required when user only wants to check for uquery->prog_cnt. + * There is no need to check for it since the case is handled + * gracefully in bpf_prog_array_copy_info. + */ mutex_lock(&bpf_event_mutex); ret = bpf_prog_array_copy_info(event->tp_event->prog_array, - uquery->ids, - query.ids_len, - &uquery->prog_cnt); + ids, + ids_len, + &prog_cnt); mutex_unlock(&bpf_event_mutex); + if (copy_to_user(&uquery->prog_cnt, &prog_cnt, sizeof(prog_cnt)) || + copy_to_user(uquery->ids, ids, ids_len * sizeof(u32))) + ret = -EFAULT; + + kfree(ids); return ret; } -- cgit v1.3-14-g43fede From 5c8dad48e4f53d6fd0a7e4f95d7c1c983374de88 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 13 Apr 2018 11:55:13 -0700 Subject: trace_kprobe: Remove warning message "Could not insert probe at..." This warning message is not very helpful, as the return value should already show information about the error. Also, this message will spam dmesg if the user space does testing in a loop, like: for x in {0..5} do echo p:xx xx+$x >> /sys/kernel/debug/tracing/kprobe_events done Reported-by: Vince Weaver Signed-off-by: Song Liu Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: kernel-team@fb.com Link: http://lkml.kernel.org/r/20180413185513.3626052-1-songliubraving@fb.com Signed-off-by: Ingo Molnar --- kernel/trace/trace_kprobe.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 1cd3fb4d70f8..02aed76e0978 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -512,8 +512,6 @@ static int __register_trace_kprobe(struct trace_kprobe *tk) if (ret == 0) tk->tp.flags |= TP_FLAG_REGISTERED; else { - pr_warn("Could not insert probe at %s+%lu: %d\n", - trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret); if (ret == -ENOENT && trace_kprobe_is_on_module(tk)) { pr_warn("This probe might be able to register after target module is loaded. Continue.\n"); ret = 0; -- cgit v1.3-14-g43fede From ba16293dad626d3e3827cfe0a1a743c1d93e76b7 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Fri, 20 Apr 2018 20:37:58 +0530 Subject: tracing: Fix kernel crash while using empty filter with perf Kernel is crashing when user tries to record 'ftrace:function' event with empty filter: # perf record -e ftrace:function --filter="" ls # dmesg BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 Oops: 0000 [#1] SMP PTI ... RIP: 0010:ftrace_profile_set_filter+0x14b/0x2d0 RSP: 0018:ffffa4a7c0da7d20 EFLAGS: 00010246 RAX: ffffa4a7c0da7d64 RBX: 0000000000000000 RCX: 0000000000000006 RDX: 0000000000000000 RSI: 0000000000000092 RDI: ffff8c48ffc968f0 ... Call Trace: _perf_ioctl+0x54a/0x6b0 ? rcu_all_qs+0x5/0x30 ... After patch: # perf record -e ftrace:function --filter="" ls failed to set filter "" on event ftrace:function with 22 (Invalid argument) Also, if user tries to echo "" > filter, it used to throw an error. This behavior got changed by commit 80765597bc58 ("tracing: Rewrite filter logic to be simpler and faster"). This patch restores the behavior as a side effect: Before patch: # echo "" > filter # After patch: # echo "" > filter bash: echo: write error: Invalid argument # Link: http://lkml.kernel.org/r/20180420150758.19787-1-ravi.bangoria@linux.ibm.com Fixes: 80765597bc58 ("tracing: Rewrite filter logic to be simpler and faster") Signed-off-by: Ravi Bangoria Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_filter.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 9b4716bb8bb0..1f951b3df60c 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1499,14 +1499,14 @@ static int process_preds(struct trace_event_call *call, return ret; } - if (!nr_preds) { - prog = NULL; - } else { - prog = predicate_parse(filter_string, nr_parens, nr_preds, + if (!nr_preds) + return -EINVAL; + + prog = predicate_parse(filter_string, nr_parens, nr_preds, parse_pred, call, pe); - if (IS_ERR(prog)) - return PTR_ERR(prog); - } + if (IS_ERR(prog)) + return PTR_ERR(prog); + rcu_assign_pointer(filter->prog, prog); return 0; } -- cgit v1.3-14-g43fede From 9a0fd675304d410f3a9586e1b333e16f4658d56c Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 15 Mar 2018 14:06:39 +0800 Subject: tracing: Fix missing tab for hwlat_detector print format It's been missing for a while but no one is touching that up. Fix it. Link: http://lkml.kernel.org/r/20180315060639.9578-1-peterx@redhat.com CC: Ingo Molnar Cc:stable@vger.kernel.org Fixes: 7b2c86250122d ("tracing: Add NMI tracing in hwlat detector") Signed-off-by: Peter Xu Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_entries.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index e954ae3d82c0..e3a658bac10f 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -356,7 +356,7 @@ FTRACE_ENTRY(hwlat, hwlat_entry, __field( unsigned int, seqnum ) ), - F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llunmi-ts:%llu\tnmi-count:%u\n", + F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llu\tnmi-ts:%llu\tnmi-count:%u\n", __entry->seqnum, __entry->tv_sec, __entry->tv_nsec, -- cgit v1.3-14-g43fede From a3ed0e4393d6885b4af7ce84b437dc696490a530 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 25 Apr 2018 15:33:38 +0200 Subject: Revert: Unify CLOCK_MONOTONIC and CLOCK_BOOTTIME Revert commits 92af4dcb4e1c ("tracing: Unify the "boot" and "mono" tracing clocks") 127bfa5f4342 ("hrtimer: Unify MONOTONIC and BOOTTIME clock behavior") 7250a4047aa6 ("posix-timers: Unify MONOTONIC and BOOTTIME clock behavior") d6c7270e913d ("timekeeping: Remove boot time specific code") f2d6fdbfd238 ("Input: Evdev - unify MONOTONIC and BOOTTIME clock behavior") d6ed449afdb3 ("timekeeping: Make the MONOTONIC clock behave like the BOOTTIME clock") 72199320d49d ("timekeeping: Add the new CLOCK_MONOTONIC_ACTIVE clock") As stated in the pull request for the unification of CLOCK_MONOTONIC and CLOCK_BOOTTIME, it was clear that we might have to revert the change. As reported by several folks systemd and other applications rely on the documented behaviour of CLOCK_MONOTONIC on Linux and break with the above changes. After resume daemons time out and other timeout related issues are observed. Rafael compiled this list: * systemd kills daemons on resume, after >WatchdogSec seconds of suspending (Genki Sky). [Verified that that's because systemd uses CLOCK_MONOTONIC and expects it to not include the suspend time.] * systemd-journald misbehaves after resume: systemd-journald[7266]: File /var/log/journal/016627c3c4784cd4812d4b7e96a34226/system.journal corrupted or uncleanly shut down, renaming and replacing. (Mike Galbraith). * NetworkManager reports "networking disabled" and networking is broken after resume 50% of the time (Pavel). [May be because of systemd.] * MATE desktop dims the display and starts the screensaver right after system resume (Pavel). * Full system hang during resume (me). [May be due to systemd or NM or both.] That happens on debian and open suse systems. It's sad, that these problems were neither catched in -next nor by those folks who expressed interest in this change. Reported-by: Rafael J. Wysocki Reported-by: Genki Sky , Reported-by: Pavel Machek Signed-off-by: Thomas Gleixner Cc: Dmitry Torokhov Cc: John Stultz Cc: Jonathan Corbet Cc: Kevin Easton Cc: Linus Torvalds Cc: Mark Salyzyn Cc: Michael Kerrisk Cc: Peter Zijlstra Cc: Petr Mladek Cc: Prarit Bhargava Cc: Sergey Senozhatsky Cc: Steven Rostedt --- Documentation/trace/ftrace.rst | 14 +++++-- drivers/input/evdev.c | 7 +++- include/linux/hrtimer.h | 2 + include/linux/timekeeper_internal.h | 2 - include/linux/timekeeping.h | 37 ++++++++++++------ include/uapi/linux/time.h | 1 - kernel/time/hrtimer.c | 16 +++++++- kernel/time/posix-stubs.c | 2 - kernel/time/posix-timers.c | 26 ++++++++----- kernel/time/tick-common.c | 15 ------- kernel/time/tick-internal.h | 6 --- kernel/time/tick-sched.c | 9 ----- kernel/time/timekeeping.c | 78 ++++++++++++++++++------------------- kernel/time/timekeeping.h | 1 + kernel/trace/trace.c | 2 +- 15 files changed, 114 insertions(+), 104 deletions(-) (limited to 'kernel/trace') diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst index e45f0786f3f9..67d9c38e95eb 100644 --- a/Documentation/trace/ftrace.rst +++ b/Documentation/trace/ftrace.rst @@ -461,9 +461,17 @@ of ftrace. Here is a list of some of the key files: and ticks at the same rate as the hardware clocksource. boot: - Same as mono. Used to be a separate clock which accounted - for the time spent in suspend while CLOCK_MONOTONIC did - not. + This is the boot clock (CLOCK_BOOTTIME) and is based on the + fast monotonic clock, but also accounts for time spent in + suspend. Since the clock access is designed for use in + tracing in the suspend path, some side effects are possible + if clock is accessed after the suspend time is accounted before + the fast mono clock is updated. In this case, the clock update + appears to happen slightly sooner than it normally would have. + Also on 32-bit systems, it's possible that the 64-bit boot offset + sees a partial update. These effects are rare and post + processing should be able to handle them. See comments in the + ktime_get_boot_fast_ns() function for more information. To set a clock, simply echo the clock name into this file:: diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index 46115a392098..c81c79d01d93 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -31,6 +31,7 @@ enum evdev_clock_type { EV_CLK_REAL = 0, EV_CLK_MONO, + EV_CLK_BOOT, EV_CLK_MAX }; @@ -197,10 +198,12 @@ static int evdev_set_clk_type(struct evdev_client *client, unsigned int clkid) case CLOCK_REALTIME: clk_type = EV_CLK_REAL; break; - case CLOCK_BOOTTIME: case CLOCK_MONOTONIC: clk_type = EV_CLK_MONO; break; + case CLOCK_BOOTTIME: + clk_type = EV_CLK_BOOT; + break; default: return -EINVAL; } @@ -311,6 +314,8 @@ static void evdev_events(struct input_handle *handle, ev_time[EV_CLK_MONO] = ktime_get(); ev_time[EV_CLK_REAL] = ktime_mono_to_real(ev_time[EV_CLK_MONO]); + ev_time[EV_CLK_BOOT] = ktime_mono_to_any(ev_time[EV_CLK_MONO], + TK_OFFS_BOOT); rcu_read_lock(); diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index a2656c3ebe81..3892e9c8b2de 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -161,9 +161,11 @@ struct hrtimer_clock_base { enum hrtimer_base_type { HRTIMER_BASE_MONOTONIC, HRTIMER_BASE_REALTIME, + HRTIMER_BASE_BOOTTIME, HRTIMER_BASE_TAI, HRTIMER_BASE_MONOTONIC_SOFT, HRTIMER_BASE_REALTIME_SOFT, + HRTIMER_BASE_BOOTTIME_SOFT, HRTIMER_BASE_TAI_SOFT, HRTIMER_MAX_CLOCK_BASES, }; diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 4b3dca173e89..7acb953298a7 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -52,7 +52,6 @@ struct tk_read_base { * @offs_real: Offset clock monotonic -> clock realtime * @offs_boot: Offset clock monotonic -> clock boottime * @offs_tai: Offset clock monotonic -> clock tai - * @time_suspended: Accumulated suspend time * @tai_offset: The current UTC to TAI offset in seconds * @clock_was_set_seq: The sequence number of clock was set events * @cs_was_changed_seq: The sequence number of clocksource change events @@ -95,7 +94,6 @@ struct timekeeper { ktime_t offs_real; ktime_t offs_boot; ktime_t offs_tai; - ktime_t time_suspended; s32 tai_offset; unsigned int clock_was_set_seq; u8 cs_was_changed_seq; diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 9737fbec7019..588a0e4b1ab9 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -33,25 +33,20 @@ extern void ktime_get_ts64(struct timespec64 *ts); extern time64_t ktime_get_seconds(void); extern time64_t __ktime_get_real_seconds(void); extern time64_t ktime_get_real_seconds(void); -extern void ktime_get_active_ts64(struct timespec64 *ts); extern int __getnstimeofday64(struct timespec64 *tv); extern void getnstimeofday64(struct timespec64 *tv); extern void getboottime64(struct timespec64 *ts); -#define ktime_get_real_ts64(ts) getnstimeofday64(ts) - -/* Clock BOOTTIME compatibility wrappers */ -static inline void get_monotonic_boottime64(struct timespec64 *ts) -{ - ktime_get_ts64(ts); -} +#define ktime_get_real_ts64(ts) getnstimeofday64(ts) /* * ktime_t based interfaces */ + enum tk_offsets { TK_OFFS_REAL, + TK_OFFS_BOOT, TK_OFFS_TAI, TK_OFFS_MAX, }; @@ -62,10 +57,6 @@ extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); extern ktime_t ktime_get_raw(void); extern u32 ktime_get_resolution_ns(void); -/* Clock BOOTTIME compatibility wrappers */ -static inline ktime_t ktime_get_boottime(void) { return ktime_get(); } -static inline u64 ktime_get_boot_ns(void) { return ktime_get(); } - /** * ktime_get_real - get the real (wall-) time in ktime_t format */ @@ -74,6 +65,17 @@ static inline ktime_t ktime_get_real(void) return ktime_get_with_offset(TK_OFFS_REAL); } +/** + * ktime_get_boottime - Returns monotonic time since boot in ktime_t format + * + * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the + * time spent in suspend. + */ +static inline ktime_t ktime_get_boottime(void) +{ + return ktime_get_with_offset(TK_OFFS_BOOT); +} + /** * ktime_get_clocktai - Returns the TAI time of day in ktime_t format */ @@ -100,6 +102,11 @@ static inline u64 ktime_get_real_ns(void) return ktime_to_ns(ktime_get_real()); } +static inline u64 ktime_get_boot_ns(void) +{ + return ktime_to_ns(ktime_get_boottime()); +} + static inline u64 ktime_get_tai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); @@ -112,11 +119,17 @@ static inline u64 ktime_get_raw_ns(void) extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); +extern u64 ktime_get_boot_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* * timespec64 interfaces utilizing the ktime based ones */ +static inline void get_monotonic_boottime64(struct timespec64 *ts) +{ + *ts = ktime_to_timespec64(ktime_get_boottime()); +} + static inline void timekeeping_clocktai64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_clocktai()); diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h index 16a296612ba4..4c0338ea308a 100644 --- a/include/uapi/linux/time.h +++ b/include/uapi/linux/time.h @@ -73,7 +73,6 @@ struct __kernel_old_timeval { */ #define CLOCK_SGI_CYCLE 10 #define CLOCK_TAI 11 -#define CLOCK_MONOTONIC_ACTIVE 12 #define MAX_CLOCKS 16 #define CLOCKS_MASK (CLOCK_REALTIME | CLOCK_MONOTONIC) diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index eda1210ce50f..14e858753d76 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -90,6 +90,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, + { + .index = HRTIMER_BASE_BOOTTIME, + .clockid = CLOCK_BOOTTIME, + .get_time = &ktime_get_boottime, + }, { .index = HRTIMER_BASE_TAI, .clockid = CLOCK_TAI, @@ -105,6 +110,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, + { + .index = HRTIMER_BASE_BOOTTIME_SOFT, + .clockid = CLOCK_BOOTTIME, + .get_time = &ktime_get_boottime, + }, { .index = HRTIMER_BASE_TAI_SOFT, .clockid = CLOCK_TAI, @@ -119,7 +129,7 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { [CLOCK_REALTIME] = HRTIMER_BASE_REALTIME, [CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC, - [CLOCK_BOOTTIME] = HRTIMER_BASE_MONOTONIC, + [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME, [CLOCK_TAI] = HRTIMER_BASE_TAI, }; @@ -571,12 +581,14 @@ __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_ static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) { ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; + ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset; ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq, - offs_real, offs_tai); + offs_real, offs_boot, offs_tai); base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real; + base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot; base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai; return now; diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index e0dbae98db9d..69a937c3cd81 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -83,8 +83,6 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp) case CLOCK_BOOTTIME: get_monotonic_boottime64(tp); break; - case CLOCK_MONOTONIC_ACTIVE: - ktime_get_active_ts64(tp); default: return -EINVAL; } diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index b6899b5060bd..10b7186d0638 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -252,16 +252,15 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 * return 0; } -static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp) +static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp) { - timekeeping_clocktai64(tp); + get_monotonic_boottime64(tp); return 0; } -static int posix_get_monotonic_active(clockid_t which_clock, - struct timespec64 *tp) +static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp) { - ktime_get_active_ts64(tp); + timekeeping_clocktai64(tp); return 0; } @@ -1317,9 +1316,19 @@ static const struct k_clock clock_tai = { .timer_arm = common_hrtimer_arm, }; -static const struct k_clock clock_monotonic_active = { +static const struct k_clock clock_boottime = { .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_get_monotonic_active, + .clock_get = posix_get_boottime, + .nsleep = common_nsleep, + .timer_create = common_timer_create, + .timer_set = common_timer_set, + .timer_get = common_timer_get, + .timer_del = common_timer_del, + .timer_rearm = common_hrtimer_rearm, + .timer_forward = common_hrtimer_forward, + .timer_remaining = common_hrtimer_remaining, + .timer_try_to_cancel = common_hrtimer_try_to_cancel, + .timer_arm = common_hrtimer_arm, }; static const struct k_clock * const posix_clocks[] = { @@ -1330,11 +1339,10 @@ static const struct k_clock * const posix_clocks[] = { [CLOCK_MONOTONIC_RAW] = &clock_monotonic_raw, [CLOCK_REALTIME_COARSE] = &clock_realtime_coarse, [CLOCK_MONOTONIC_COARSE] = &clock_monotonic_coarse, - [CLOCK_BOOTTIME] = &clock_monotonic, + [CLOCK_BOOTTIME] = &clock_boottime, [CLOCK_REALTIME_ALARM] = &alarm_clock, [CLOCK_BOOTTIME_ALARM] = &alarm_clock, [CLOCK_TAI] = &clock_tai, - [CLOCK_MONOTONIC_ACTIVE] = &clock_monotonic_active, }; static const struct k_clock *clockid_to_kclock(const clockid_t id) diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 099572ca4a8f..49edc1c4f3e6 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -419,19 +419,6 @@ void tick_suspend_local(void) clockevents_shutdown(td->evtdev); } -static void tick_forward_next_period(void) -{ - ktime_t delta, now = ktime_get(); - u64 n; - - delta = ktime_sub(now, tick_next_period); - n = ktime_divns(delta, tick_period); - tick_next_period += n * tick_period; - if (tick_next_period < now) - tick_next_period += tick_period; - tick_sched_forward_next_period(); -} - /** * tick_resume_local - Resume the local tick device * @@ -444,8 +431,6 @@ void tick_resume_local(void) struct tick_device *td = this_cpu_ptr(&tick_cpu_device); bool broadcast = tick_resume_check_broadcast(); - tick_forward_next_period(); - clockevents_tick_resume(td->evtdev); if (!broadcast) { if (td->mode == TICKDEV_MODE_PERIODIC) diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 21efab7485ca..e277284c2831 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -141,12 +141,6 @@ static inline void tick_check_oneshot_broadcast_this_cpu(void) { } static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); } #endif /* !(BROADCAST && ONESHOT) */ -#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS) -extern void tick_sched_forward_next_period(void); -#else -static inline void tick_sched_forward_next_period(void) { } -#endif - /* NO_HZ_FULL internal */ #ifdef CONFIG_NO_HZ_FULL extern void tick_nohz_init(void); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index d31bec177fa5..da9455a6b42b 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -51,15 +51,6 @@ struct tick_sched *tick_get_tick_sched(int cpu) */ static ktime_t last_jiffies_update; -/* - * Called after resume. Make sure that jiffies are not fast forwarded due to - * clock monotonic being forwarded by the suspended time. - */ -void tick_sched_forward_next_period(void) -{ - last_jiffies_update = tick_next_period; -} - /* * Must be called with interrupts disabled ! */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index dcf7f20fcd12..49cbceef5deb 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -138,12 +138,7 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { - /* Update both bases so mono and raw stay coupled. */ - tk->tkr_mono.base += delta; - tk->tkr_raw.base += delta; - - /* Accumulate time spent in suspend */ - tk->time_suspended += delta; + tk->offs_boot = ktime_add(tk->offs_boot, delta); } /* @@ -473,6 +468,36 @@ u64 ktime_get_raw_fast_ns(void) } EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); +/** + * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock. + * + * To keep it NMI safe since we're accessing from tracing, we're not using a + * separate timekeeper with updates to monotonic clock and boot offset + * protected with seqlocks. This has the following minor side effects: + * + * (1) Its possible that a timestamp be taken after the boot offset is updated + * but before the timekeeper is updated. If this happens, the new boot offset + * is added to the old timekeeping making the clock appear to update slightly + * earlier: + * CPU 0 CPU 1 + * timekeeping_inject_sleeptime64() + * __timekeeping_inject_sleeptime(tk, delta); + * timestamp(); + * timekeeping_update(tk, TK_CLEAR_NTP...); + * + * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be + * partially updated. Since the tk->offs_boot update is a rare event, this + * should be a rare occurrence which postprocessing should be able to handle. + */ +u64 notrace ktime_get_boot_fast_ns(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + + return (ktime_get_mono_fast_ns() + ktime_to_ns(tk->offs_boot)); +} +EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); + + /* * See comment for __ktime_get_fast_ns() vs. timestamp ordering */ @@ -764,6 +789,7 @@ EXPORT_SYMBOL_GPL(ktime_get_resolution_ns); static ktime_t *offsets[TK_OFFS_MAX] = { [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, + [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, }; @@ -860,39 +886,6 @@ void ktime_get_ts64(struct timespec64 *ts) } EXPORT_SYMBOL_GPL(ktime_get_ts64); -/** - * ktime_get_active_ts64 - Get the active non-suspended monotonic clock - * @ts: pointer to timespec variable - * - * The function calculates the monotonic clock from the realtime clock and - * the wall_to_monotonic offset, subtracts the accumulated suspend time and - * stores the result in normalized timespec64 format in the variable - * pointed to by @ts. - */ -void ktime_get_active_ts64(struct timespec64 *ts) -{ - struct timekeeper *tk = &tk_core.timekeeper; - struct timespec64 tomono, tsusp; - u64 nsec, nssusp; - unsigned int seq; - - WARN_ON(timekeeping_suspended); - - do { - seq = read_seqcount_begin(&tk_core.seq); - ts->tv_sec = tk->xtime_sec; - nsec = timekeeping_get_ns(&tk->tkr_mono); - tomono = tk->wall_to_monotonic; - nssusp = tk->time_suspended; - } while (read_seqcount_retry(&tk_core.seq, seq)); - - ts->tv_sec += tomono.tv_sec; - ts->tv_nsec = 0; - timespec64_add_ns(ts, nsec + tomono.tv_nsec); - tsusp = ns_to_timespec64(nssusp); - *ts = timespec64_sub(*ts, tsusp); -} - /** * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC * @@ -1593,6 +1586,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, return; } tk_xtime_add(tk, delta); + tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); tk_debug_account_sleep_time(delta); } @@ -2125,7 +2119,7 @@ out: void getboottime64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; - ktime_t t = ktime_sub(tk->offs_real, tk->time_suspended); + ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); *ts = ktime_to_timespec64(t); } @@ -2188,6 +2182,7 @@ void do_timer(unsigned long ticks) * ktime_get_update_offsets_now - hrtimer helper * @cwsseq: pointer to check and store the clock was set sequence number * @offs_real: pointer to storage for monotonic -> realtime offset + * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset * * Returns current monotonic time and updates the offsets if the @@ -2197,7 +2192,7 @@ void do_timer(unsigned long ticks) * Called from hrtimer_interrupt() or retrigger_next_event() */ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, - ktime_t *offs_tai) + ktime_t *offs_boot, ktime_t *offs_tai) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; @@ -2214,6 +2209,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, if (*cwsseq != tk->clock_was_set_seq) { *cwsseq = tk->clock_was_set_seq; *offs_real = tk->offs_real; + *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; } diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index 79b67f5e0343..7a9b4eb7a1d5 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -6,6 +6,7 @@ */ extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, + ktime_t *offs_boot, ktime_t *offs_tai); extern int timekeeping_valid_for_hres(void); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index dfbcf9ee1447..414d7210b2ec 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1165,7 +1165,7 @@ static struct { { trace_clock, "perf", 1 }, { ktime_get_mono_fast_ns, "mono", 1 }, { ktime_get_raw_fast_ns, "mono_raw", 1 }, - { ktime_get_mono_fast_ns, "boot", 1 }, + { ktime_get_boot_fast_ns, "boot", 1 }, ARCH_TRACE_CLOCKS }; -- cgit v1.3-14-g43fede From 0c92c7a3c5d416f47b32c5f20a611dfeca5d5f2e Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 23 Apr 2018 10:21:34 -0700 Subject: tracing: Fix bad use of igrab in trace_uprobe.c As Miklos reported and suggested: This pattern repeats two times in trace_uprobe.c and in kernel/events/core.c as well: ret = kern_path(filename, LOOKUP_FOLLOW, &path); if (ret) goto fail_address_parse; inode = igrab(d_inode(path.dentry)); path_put(&path); And it's wrong. You can only hold a reference to the inode if you have an active ref to the superblock as well (which is normally through path.mnt) or holding s_umount. This way unmounting the containing filesystem while the tracepoint is active will give you the "VFS: Busy inodes after unmount..." message and a crash when the inode is finally put. Solution: store path instead of inode. This patch fixes two instances in trace_uprobe.c. struct path is added to struct trace_uprobe to keep the inode and containing mount point referenced. Link: http://lkml.kernel.org/r/20180423172135.4050588-1-songliubraving@fb.com Fixes: f3f096cfedf8 ("tracing: Provide trace events interface for uprobes") Fixes: 33ea4b24277b ("perf/core: Implement the 'perf_uprobe' PMU") Cc: stable@vger.kernel.org Cc: Ingo Molnar Cc: Howard McLauchlan Cc: Josef Bacik Cc: Srikar Dronamraju Acked-by: Miklos Szeredi Reported-by: Miklos Szeredi Signed-off-by: Song Liu Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_uprobe.c | 35 ++++++++++++++--------------------- 1 file changed, 14 insertions(+), 21 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 34fd0e0ec51d..ac892878dbe6 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -55,6 +55,7 @@ struct trace_uprobe { struct list_head list; struct trace_uprobe_filter filter; struct uprobe_consumer consumer; + struct path path; struct inode *inode; char *filename; unsigned long offset; @@ -289,7 +290,7 @@ static void free_trace_uprobe(struct trace_uprobe *tu) for (i = 0; i < tu->tp.nr_args; i++) traceprobe_free_probe_arg(&tu->tp.args[i]); - iput(tu->inode); + path_put(&tu->path); kfree(tu->tp.call.class->system); kfree(tu->tp.call.name); kfree(tu->filename); @@ -363,7 +364,6 @@ end: static int create_trace_uprobe(int argc, char **argv) { struct trace_uprobe *tu; - struct inode *inode; char *arg, *event, *group, *filename; char buf[MAX_EVENT_NAME_LEN]; struct path path; @@ -371,7 +371,6 @@ static int create_trace_uprobe(int argc, char **argv) bool is_delete, is_return; int i, ret; - inode = NULL; ret = 0; is_delete = false; is_return = false; @@ -437,21 +436,16 @@ static int create_trace_uprobe(int argc, char **argv) } /* Find the last occurrence, in case the path contains ':' too. */ arg = strrchr(argv[1], ':'); - if (!arg) { - ret = -EINVAL; - goto fail_address_parse; - } + if (!arg) + return -EINVAL; *arg++ = '\0'; filename = argv[1]; ret = kern_path(filename, LOOKUP_FOLLOW, &path); if (ret) - goto fail_address_parse; - - inode = igrab(d_real_inode(path.dentry)); - path_put(&path); + return ret; - if (!inode || !S_ISREG(inode->i_mode)) { + if (!d_is_reg(path.dentry)) { ret = -EINVAL; goto fail_address_parse; } @@ -490,7 +484,7 @@ static int create_trace_uprobe(int argc, char **argv) goto fail_address_parse; } tu->offset = offset; - tu->inode = inode; + tu->path = path; tu->filename = kstrdup(filename, GFP_KERNEL); if (!tu->filename) { @@ -558,7 +552,7 @@ error: return ret; fail_address_parse: - iput(inode); + path_put(&path); pr_info("Failed to parse address or file.\n"); @@ -922,6 +916,7 @@ probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file, goto err_flags; tu->consumer.filter = filter; + tu->inode = d_real_inode(tu->path.dentry); ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); if (ret) goto err_buffer; @@ -967,6 +962,7 @@ probe_event_disable(struct trace_uprobe *tu, struct trace_event_file *file) WARN_ON(!uprobe_filter_is_empty(&tu->filter)); uprobe_unregister(tu->inode, tu->offset, &tu->consumer); + tu->inode = NULL; tu->tp.flags &= file ? ~TP_FLAG_TRACE : ~TP_FLAG_PROFILE; uprobe_buffer_disable(); @@ -1337,7 +1333,6 @@ struct trace_event_call * create_local_trace_uprobe(char *name, unsigned long offs, bool is_return) { struct trace_uprobe *tu; - struct inode *inode; struct path path; int ret; @@ -1345,11 +1340,8 @@ create_local_trace_uprobe(char *name, unsigned long offs, bool is_return) if (ret) return ERR_PTR(ret); - inode = igrab(d_inode(path.dentry)); - path_put(&path); - - if (!inode || !S_ISREG(inode->i_mode)) { - iput(inode); + if (!d_is_reg(path.dentry)) { + path_put(&path); return ERR_PTR(-EINVAL); } @@ -1364,11 +1356,12 @@ create_local_trace_uprobe(char *name, unsigned long offs, bool is_return) if (IS_ERR(tu)) { pr_info("Failed to allocate trace_uprobe.(%d)\n", (int)PTR_ERR(tu)); + path_put(&path); return ERR_CAST(tu); } tu->offset = offs; - tu->inode = inode; + tu->path = path; tu->filename = kstrdup(name, GFP_KERNEL); init_trace_event_call(tu, &tu->tp.call); -- cgit v1.3-14-g43fede From 608940dabe1bd2ce4c97524004ec86637cf80f2c Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 26 Apr 2018 20:04:47 -0500 Subject: tracing: Restore proper field flag printing when displaying triggers The flag-printing code used when displaying hist triggers somehow got dropped during refactoring of the inter-event patchset. This restores it. Below are a couple examples - in the first case, .usecs wasn't being displayed properly for common_timestamps and the second illustrates the same for other flags such as .execname. Before: # echo 'hist:key=common_pid.execname:val=count:sort=count' > /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger hist:keys=common_pid:vals=hitcount,count:sort=count:size=2048 [active] # echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="cyclictest"' >> /sys/kernel/debug/tracing/events/sched/sched_wakeup/trigger # cat /sys/kernel/debug/tracing/events/sched/sched_wakeup/trigger hist:keys=pid:vals=hitcount:ts0=common_timestamp:sort=hitcount:size=2048:clock=global if comm=="cyclictest" [active] After: # echo 'hist:key=common_pid.execname:val=count:sort=count' > /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger hist:keys=common_pid.execname:vals=hitcount,count:sort=count:size=2048 [active] # echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="cyclictest"' >> /sys/kernel/debug/tracing/events/sched/sched_wakeup/trigger # cat /sys/kernel/debug/tracing/events/sched/sched_wakeup/trigger hist:keys=pid:vals=hitcount:ts0=common_timestamp.usecs:sort=hitcount:size=2048:clock=global if comm=="cyclictest" [active] Link: http://lkml.kernel.org/r/492bab42ff21806600af98a8ea901af10efbee0c.1524790601.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_hist.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 0d7b3ffbecc2..66c87be4ebb2 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -4913,6 +4913,16 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field) seq_printf(m, "%s", field_name); } else if (hist_field->flags & HIST_FIELD_FL_TIMESTAMP) seq_puts(m, "common_timestamp"); + + if (hist_field->flags) { + if (!(hist_field->flags & HIST_FIELD_FL_VAR_REF) && + !(hist_field->flags & HIST_FIELD_FL_EXPR)) { + const char *flags = get_hist_field_flags(hist_field); + + if (flags) + seq_printf(m, ".%s", flags); + } + } } static int event_hist_trigger_print(struct seq_file *m, -- cgit v1.3-14-g43fede From 5ec432d7bf9dd3b4a2b84f8974e3adb71f45fb1d Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 26 Apr 2018 20:04:48 -0500 Subject: tracing: Add field parsing hist error for hist triggers If the user specifies a nonexistent field for a hist trigger, the current code correctly flags that as an error, but doesn't tell the user what happened. Fix this by invoking hist_err() with an appropriate message when nonexistent fields are specified. Before: # echo 'hist:keys=pid:ts0=common_timestamp.usecs' >> /sys/kernel/debug/tracing/events/sched/sched_switch/trigger -su: echo: write error: Invalid argument # cat /sys/kernel/debug/tracing/events/sched/sched_switch/hist After: # echo 'hist:keys=pid:ts0=common_timestamp.usecs' >> /sys/kernel/debug/tracing/events/sched/sched_switch/trigger -su: echo: write error: Invalid argument # cat /sys/kernel/debug/tracing/events/sched/sched_switch/hist ERROR: Couldn't find field: pid Last command: keys=pid:ts0=common_timestamp.usecs Link: http://lkml.kernel.org/r/fdc8746969d16906120f162b99dd71c741e0b62c.1524790601.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi Reported-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_hist.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 66c87be4ebb2..f231fa2a3dcd 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2481,6 +2481,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, else { field = trace_find_event_field(file->event_call, field_name); if (!field || !field->size) { + hist_err("Couldn't find field: ", field_name); field = ERR_PTR(-EINVAL); goto out; } -- cgit v1.3-14-g43fede From dcf234577cd31fa16874e828b90659166ad6b80d Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 26 Apr 2018 20:04:49 -0500 Subject: tracing: Add field modifier parsing hist error for hist triggers If the user specifies an invalid field modifier for a hist trigger, the current code correctly flags that as an error, but doesn't tell the user what happened. Fix this by invoking hist_err() with an appropriate message when invalid modifiers are specified. Before: # echo 'hist:keys=pid:ts0=common_timestamp.junkusecs' >> /sys/kernel/debug/tracing/events/sched/sched_wakeup/trigger -su: echo: write error: Invalid argument # cat /sys/kernel/debug/tracing/events/sched/sched_wakeup/hist After: # echo 'hist:keys=pid:ts0=common_timestamp.junkusecs' >> /sys/kernel/debug/tracing/events/sched/sched_wakeup/trigger -su: echo: write error: Invalid argument # cat /sys/kernel/debug/tracing/events/sched/sched_wakeup/hist ERROR: Invalid field modifier: junkusecs Last command: keys=pid:ts0=common_timestamp.junkusecs Link: http://lkml.kernel.org/r/b043c59fa79acd06a5f14a1d44dee9e5a3cd1248.1524790601.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_hist.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index f231fa2a3dcd..b9061ed59bbd 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2466,6 +2466,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, else if (strcmp(modifier, "usecs") == 0) *flags |= HIST_FIELD_FL_TIMESTAMP_USECS; else { + hist_err("Invalid field modifier: ", modifier); field = ERR_PTR(-EINVAL); goto out; } -- cgit v1.3-14-g43fede From 1ce0500d234f8ef880c399d55a886af646beec9a Mon Sep 17 00:00:00 2001 From: Chen LinX Date: Wed, 3 Sep 2014 14:31:09 +0800 Subject: ftrace: Have set_graph_* files have normal file modes The set_graph_function and set_graph_notrace file mode should be 0644 instead of 0444 as they are writeable. Note, the mode appears to be ignored regardless, but they should at least look sane. Link: http://lkml.kernel.org/r/1409725869-4501-1-git-send-email-linx.z.chen@intel.com Acked-by: Namhyung Kim Signed-off-by: Chen LinX Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 16bbf062018f..8d83bcf9ef69 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5514,10 +5514,10 @@ static __init int ftrace_init_dyn_tracefs(struct dentry *d_tracer) ftrace_create_filter_files(&global_ops, d_tracer); #ifdef CONFIG_FUNCTION_GRAPH_TRACER - trace_create_file("set_graph_function", 0444, d_tracer, + trace_create_file("set_graph_function", 0644, d_tracer, NULL, &ftrace_graph_fops); - trace_create_file("set_graph_notrace", 0444, d_tracer, + trace_create_file("set_graph_notrace", 0644, d_tracer, NULL, &ftrace_graph_notrace_fops); #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -- cgit v1.3-14-g43fede From 0c5a9acc8b4e878e761f735e144d4a7e4477d4e6 Mon Sep 17 00:00:00 2001 From: Zhengyuan Liu Date: Thu, 8 Feb 2018 09:41:53 +0800 Subject: tracing: Fix the file mode of stack tracer It looks weird that the stack_trace_filter file can be written by root but shows that it does not have write permission by ll command. Link: http://lkml.kernel.org/r/1518054113-28096-1-git-send-email-liuzhengyuan@kylinos.cn Signed-off-by: Zhengyuan Liu Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_stack.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 3c7bfc4bf5e9..4237eba4ef20 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -472,7 +472,7 @@ static __init int stack_trace_init(void) NULL, &stack_trace_fops); #ifdef CONFIG_DYNAMIC_FTRACE - trace_create_file("stack_trace_filter", 0444, d_tracer, + trace_create_file("stack_trace_filter", 0644, d_tracer, &trace_ops, &stack_trace_filter_fops); #endif -- cgit v1.3-14-g43fede