From a1ee1932aa6bea0bb074f5e3ced112664e4637ed Mon Sep 17 00:00:00 2001 From: Joshua Hunt Date: Thu, 17 Mar 2016 14:17:23 -0700 Subject: watchdog: don't run proc_watchdog_update if new value is same as old While working on a script to restore all sysctl params before a series of tests I found that writing any value into the /proc/sys/kernel/{nmi_watchdog,soft_watchdog,watchdog,watchdog_thresh} causes them to call proc_watchdog_update(). NMI watchdog: enabled on all CPUs, permanently consumes one hw-PMU counter. NMI watchdog: enabled on all CPUs, permanently consumes one hw-PMU counter. NMI watchdog: enabled on all CPUs, permanently consumes one hw-PMU counter. NMI watchdog: enabled on all CPUs, permanently consumes one hw-PMU counter. There doesn't appear to be a reason for doing this work every time a write occurs, so only do it when the values change. Signed-off-by: Josh Hunt Acked-by: Don Zickus Reviewed-by: Aaron Tomlin Cc: Ulrich Obergfell Cc: [4.1.x+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/watchdog.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/watchdog.c b/kernel/watchdog.c index b3ace6ebbba3..9acb29f280ec 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -923,6 +923,9 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write, * both lockup detectors are disabled if proc_watchdog_update() * returns an error. */ + if (old == new) + goto out; + err = proc_watchdog_update(); } out: @@ -967,7 +970,7 @@ int proc_soft_watchdog(struct ctl_table *table, int write, int proc_watchdog_thresh(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int err, old; + int err, old, new; get_online_cpus(); mutex_lock(&watchdog_proc_mutex); @@ -987,6 +990,10 @@ int proc_watchdog_thresh(struct ctl_table *table, int write, /* * Update the sample period. Restore on failure. */ + new = ACCESS_ONCE(watchdog_thresh); + if (old == new) + goto out; + set_sample_period(); err = proc_watchdog_update(); if (err) { -- cgit v1.2.3 From 12580e4b54ba8a1b22ec977c200be0174ca42348 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 17 Mar 2016 14:17:38 -0700 Subject: mm: memcontrol: report kernel stack usage in cgroup2 memory.stat Show how much memory is allocated to kernel stacks. Signed-off-by: Vladimir Davydov Acked-by: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroup-v2.txt | 4 ++++ include/linux/memcontrol.h | 3 ++- kernel/fork.c | 10 +++++++++- mm/memcontrol.c | 2 ++ 4 files changed, 17 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt index e4e0c1d78cee..e2f4e7948a66 100644 --- a/Documentation/cgroup-v2.txt +++ b/Documentation/cgroup-v2.txt @@ -843,6 +843,10 @@ PAGE_SIZE multiple when read back. Amount of memory used to cache filesystem data, including tmpfs and shared memory. + kernel_stack + + Amount of memory allocated to kernel stacks. + slab Amount of memory used for storing in-kernel data diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e7af4834ffea..d6300313b298 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -52,9 +52,10 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ MEM_CGROUP_STAT_NSTATS, /* default hierarchy stats */ - MEMCG_SOCK = MEM_CGROUP_STAT_NSTATS, + MEMCG_KERNEL_STACK = MEM_CGROUP_STAT_NSTATS, MEMCG_SLAB_RECLAIMABLE, MEMCG_SLAB_UNRECLAIMABLE, + MEMCG_SOCK, MEMCG_NR_STAT, }; diff --git a/kernel/fork.c b/kernel/fork.c index 2e391c754ae7..accb7221d547 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -164,12 +164,20 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); + if (page) + memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK, + 1 << THREAD_SIZE_ORDER); + return page ? page_address(page) : NULL; } static inline void free_thread_info(struct thread_info *ti) { - free_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER); + struct page *page = virt_to_page(ti); + + memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK, + -(1 << THREAD_SIZE_ORDER)); + __free_kmem_pages(page, THREAD_SIZE_ORDER); } # else static struct kmem_cache *thread_info_cache; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3ad64bf464fd..4b7dda7c2e74 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5106,6 +5106,8 @@ static int memory_stat_show(struct seq_file *m, void *v) (u64)stat[MEM_CGROUP_STAT_RSS] * PAGE_SIZE); seq_printf(m, "file %llu\n", (u64)stat[MEM_CGROUP_STAT_CACHE] * PAGE_SIZE); + seq_printf(m, "kernel_stack %llu\n", + (u64)stat[MEMCG_KERNEL_STACK] * PAGE_SIZE); seq_printf(m, "slab %llu\n", (u64)(stat[MEMCG_SLAB_RECLAIMABLE] + stat[MEMCG_SLAB_UNRECLAIMABLE]) * PAGE_SIZE); -- cgit v1.2.3 From 795ae7a0de6b834a0cc202aa55c190ef81496665 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 17 Mar 2016 14:19:14 -0700 Subject: mm: scale kswapd watermarks in proportion to memory In machines with 140G of memory and enterprise flash storage, we have seen read and write bursts routinely exceed the kswapd watermarks and cause thundering herds in direct reclaim. Unfortunately, the only way to tune kswapd aggressiveness is through adjusting min_free_kbytes - the system's emergency reserves - which is entirely unrelated to the system's latency requirements. In order to get kswapd to maintain a 250M buffer of free memory, the emergency reserves need to be set to 1G. That is a lot of memory wasted for no good reason. On the other hand, it's reasonable to assume that allocation bursts and overall allocation concurrency scale with memory capacity, so it makes sense to make kswapd aggressiveness a function of that as well. Change the kswapd watermark scale factor from the currently fixed 25% of the tunable emergency reserve to a tunable 0.1% of memory. Beyond 1G of memory, this will produce bigger watermark steps than the current formula in default settings. Ensure that the new formula never chooses steps smaller than that, i.e. 25% of the emergency reserve. On a 140G machine, this raises the default watermark steps - the distance between min and low, and low and high - from 16M to 143M. Signed-off-by: Johannes Weiner Acked-by: Mel Gorman Acked-by: Rik van Riel Acked-by: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 18 ++++++++++++++++++ include/linux/mm.h | 1 + include/linux/mmzone.h | 2 ++ kernel/sysctl.c | 10 ++++++++++ mm/page_alloc.c | 29 +++++++++++++++++++++++++++-- 5 files changed, 58 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 89a887c76629..cb0368459da3 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -803,6 +803,24 @@ performance impact. Reclaim code needs to take various locks to find freeable directory and inode objects. With vfs_cache_pressure=1000, it will look for ten times more freeable objects than there are. +============================================================= + +watermark_scale_factor: + +This factor controls the aggressiveness of kswapd. It defines the +amount of memory left in a node/system before kswapd is woken up and +how much memory needs to be free before kswapd goes back to sleep. + +The unit is in fractions of 10,000. The default value of 10 means the +distances between watermarks are 0.1% of the available memory in the +node/system. The maximum value is 1000, or 10% of memory. + +A high rate of threads entering direct reclaim (allocstall) or kswapd +going to sleep prematurely (kswapd_low_wmark_hit_quickly) can indicate +that the number of free pages kswapd maintains for latency reasons is +too small for the allocation bursts occurring in the system. This knob +can then be used to tune kswapd aggressiveness accordingly. + ============================================================== zone_reclaim_mode: diff --git a/include/linux/mm.h b/include/linux/mm.h index 75d1907b9009..f7fd64227d3a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1889,6 +1889,7 @@ extern void zone_pcp_reset(struct zone *zone); /* page_alloc.c */ extern int min_free_kbytes; +extern int watermark_scale_factor; /* nommu.c */ extern atomic_long_t mmap_pages_allocated; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index bdd9a270a813..c60df9257cc7 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -841,6 +841,8 @@ static inline int is_highmem(struct zone *zone) struct ctl_table; int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); +int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, + void __user *, size_t *, loff_t *); extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1]; int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index f5102fabef7f..725587f10667 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -126,6 +126,7 @@ static int __maybe_unused two = 2; static int __maybe_unused four = 4; static unsigned long one_ul = 1; static int one_hundred = 100; +static int one_thousand = 1000; #ifdef CONFIG_PRINTK static int ten_thousand = 10000; #endif @@ -1403,6 +1404,15 @@ static struct ctl_table vm_table[] = { .proc_handler = min_free_kbytes_sysctl_handler, .extra1 = &zero, }, + { + .procname = "watermark_scale_factor", + .data = &watermark_scale_factor, + .maxlen = sizeof(watermark_scale_factor), + .mode = 0644, + .proc_handler = watermark_scale_factor_sysctl_handler, + .extra1 = &one, + .extra2 = &one_thousand, + }, { .procname = "percpu_pagelist_fraction", .data = &percpu_pagelist_fraction, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 941b802e11ec..d156310aedeb 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -249,6 +249,7 @@ compound_page_dtor * const compound_page_dtors[] = { int min_free_kbytes = 1024; int user_min_free_kbytes = -1; +int watermark_scale_factor = 10; static unsigned long __meminitdata nr_kernel_pages; static unsigned long __meminitdata nr_all_pages; @@ -6347,8 +6348,17 @@ static void __setup_per_zone_wmarks(void) zone->watermark[WMARK_MIN] = tmp; } - zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2); - zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1); + /* + * Set the kswapd watermarks distance according to the + * scale factor in proportion to available memory, but + * ensure a minimum size on small systems. + */ + tmp = max_t(u64, tmp >> 2, + mult_frac(zone->managed_pages, + watermark_scale_factor, 10000)); + + zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp; + zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2; __mod_zone_page_state(zone, NR_ALLOC_BATCH, high_wmark_pages(zone) - low_wmark_pages(zone) - @@ -6489,6 +6499,21 @@ int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write, return 0; } +int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ + int rc; + + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (rc) + return rc; + + if (write) + setup_per_zone_wmarks(); + + return 0; +} + #ifdef CONFIG_NUMA int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) -- cgit v1.2.3 From da8b44d5a9f8bf26da637b7336508ca534d6b319 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 17 Mar 2016 14:20:51 -0700 Subject: timer: convert timer_slack_ns from unsigned long to u64 This patchset introduces a /proc//timerslack_ns interface which would allow controlling processes to be able to set the timerslack value on other processes in order to save power by avoiding wakeups (Something Android currently does via out-of-tree patches). The first patch tries to fix the internal timer_slack_ns usage which was defined as a long, which limits the slack range to ~4 seconds on 32bit systems. It converts it to a u64, which provides the same basically unlimited slack (500 years) on both 32bit and 64bit machines. The second patch introduces the /proc//timerslack_ns interface which allows the full 64bit slack range for a task to be read or set on both 32bit and 64bit machines. With these two patches, on a 32bit machine, after setting the slack on bash to 10 seconds: $ time sleep 1 real 0m10.747s user 0m0.001s sys 0m0.005s The first patch is a little ugly, since I had to chase the slack delta arguments through a number of functions converting them to u64s. Let me know if it makes sense to break that up more or not. Other than that things are fairly straightforward. This patch (of 2): The timer_slack_ns value in the task struct is currently a unsigned long. This means that on 32bit applications, the maximum slack is just over 4 seconds. However, on 64bit machines, its much much larger (~500 years). This disparity could make application development a little (as well as the default_slack) to a u64. This means both 32bit and 64bit systems have the same effective internal slack range. Now the existing ABI via PR_GET_TIMERSLACK and PR_SET_TIMERSLACK specify the interface as a unsigned long, so we preserve that limitation on 32bit systems, where SET_TIMERSLACK can only set the slack to a unsigned long value, and GET_TIMERSLACK will return ULONG_MAX if the slack is actually larger then what can be stored by an unsigned long. This patch also modifies hrtimer functions which specified the slack delta as a unsigned long. Signed-off-by: John Stultz Cc: Arjan van de Ven Cc: Thomas Gleixner Cc: Oren Laadan Cc: Ruchi Kandoi Cc: Rom Lemarchand Cc: Kees Cook Cc: Android Kernel Team Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/eventpoll.c | 2 +- fs/select.c | 8 ++++---- include/linux/freezer.h | 2 +- include/linux/hrtimer.h | 12 +++++++----- include/linux/poll.h | 2 +- include/linux/sched.h | 4 ++-- kernel/sys.c | 5 ++++- kernel/time/hrtimer.c | 8 ++++---- kernel/time/timer.c | 4 ++-- 9 files changed, 26 insertions(+), 21 deletions(-) (limited to 'kernel') diff --git a/fs/eventpoll.c b/fs/eventpoll.c index cde60741cad2..8a74a2a52e0f 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1616,7 +1616,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, { int res = 0, eavail, timed_out = 0; unsigned long flags; - long slack = 0; + u64 slack = 0; wait_queue_t wait; ktime_t expires, *to = NULL; diff --git a/fs/select.c b/fs/select.c index 79d0d4953cad..869293988c2a 100644 --- a/fs/select.c +++ b/fs/select.c @@ -70,9 +70,9 @@ static long __estimate_accuracy(struct timespec *tv) return slack; } -long select_estimate_accuracy(struct timespec *tv) +u64 select_estimate_accuracy(struct timespec *tv) { - unsigned long ret; + u64 ret; struct timespec now; /* @@ -402,7 +402,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) struct poll_wqueues table; poll_table *wait; int retval, i, timed_out = 0; - unsigned long slack = 0; + u64 slack = 0; unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; unsigned long busy_end = 0; @@ -784,7 +784,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait, poll_table* pt = &wait->pt; ktime_t expire, *to = NULL; int timed_out = 0, count = 0; - unsigned long slack = 0; + u64 slack = 0; unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; unsigned long busy_end = 0; diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 6b7fd9cf5ea2..dd03e837ebb7 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -231,7 +231,7 @@ static inline long freezable_schedule_timeout_killable_unsafe(long timeout) * call this with locks held. */ static inline int freezable_schedule_hrtimeout_range(ktime_t *expires, - unsigned long delta, const enum hrtimer_mode mode) + u64 delta, const enum hrtimer_mode mode) { int __retval; freezer_do_not_count(); diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 2ead22dd74a0..c98c6539e2c2 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -220,7 +220,7 @@ static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time timer->node.expires = ktime_add_safe(time, delta); } -static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, unsigned long delta) +static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, u64 delta) { timer->_softexpires = time; timer->node.expires = ktime_add_safe(time, ns_to_ktime(delta)); @@ -378,7 +378,7 @@ static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { } /* Basic timer operations: */ extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, - unsigned long range_ns, const enum hrtimer_mode mode); + u64 range_ns, const enum hrtimer_mode mode); /** * hrtimer_start - (re)start an hrtimer on the current CPU @@ -399,7 +399,7 @@ extern int hrtimer_try_to_cancel(struct hrtimer *timer); static inline void hrtimer_start_expires(struct hrtimer *timer, enum hrtimer_mode mode) { - unsigned long delta; + u64 delta; ktime_t soft, hard; soft = hrtimer_get_softexpires(timer); hard = hrtimer_get_expires(timer); @@ -477,10 +477,12 @@ extern long hrtimer_nanosleep_restart(struct restart_block *restart_block); extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *tsk); -extern int schedule_hrtimeout_range(ktime_t *expires, unsigned long delta, +extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta, const enum hrtimer_mode mode); extern int schedule_hrtimeout_range_clock(ktime_t *expires, - unsigned long delta, const enum hrtimer_mode mode, int clock); + u64 delta, + const enum hrtimer_mode mode, + int clock); extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode); /* Soft interrupt function to run the hrtimer queues: */ diff --git a/include/linux/poll.h b/include/linux/poll.h index c08386fb3e08..9fb4f40d9a26 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -96,7 +96,7 @@ extern void poll_initwait(struct poll_wqueues *pwq); extern void poll_freewait(struct poll_wqueues *pwq); extern int poll_schedule_timeout(struct poll_wqueues *pwq, int state, ktime_t *expires, unsigned long slack); -extern long select_estimate_accuracy(struct timespec *tv); +extern u64 select_estimate_accuracy(struct timespec *tv); static inline int poll_schedule(struct poll_wqueues *pwq, int state) diff --git a/include/linux/sched.h b/include/linux/sched.h index eb7f2f84009b..3284d07edec7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1792,8 +1792,8 @@ struct task_struct { * time slack values; these are used to round up poll() and * select() etc timeout values. These are in nanoseconds. */ - unsigned long timer_slack_ns; - unsigned long default_timer_slack_ns; + u64 timer_slack_ns; + u64 default_timer_slack_ns; #ifdef CONFIG_KASAN unsigned int kasan_depth; diff --git a/kernel/sys.c b/kernel/sys.c index 78947de6f969..cf8ba545c7d3 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2169,7 +2169,10 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = perf_event_task_enable(); break; case PR_GET_TIMERSLACK: - error = current->timer_slack_ns; + if (current->timer_slack_ns > ULONG_MAX) + error = ULONG_MAX; + else + error = current->timer_slack_ns; break; case PR_SET_TIMERSLACK: if (arg2 <= 0) diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index fa909f9fd559..58a321c34cfb 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -979,7 +979,7 @@ static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim, * relative (HRTIMER_MODE_REL) */ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, - unsigned long delta_ns, const enum hrtimer_mode mode) + u64 delta_ns, const enum hrtimer_mode mode) { struct hrtimer_clock_base *base, *new_base; unsigned long flags; @@ -1548,7 +1548,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, struct restart_block *restart; struct hrtimer_sleeper t; int ret = 0; - unsigned long slack; + u64 slack; slack = current->timer_slack_ns; if (dl_task(current) || rt_task(current)) @@ -1724,7 +1724,7 @@ void __init hrtimers_init(void) * @clock: timer clock, CLOCK_MONOTONIC or CLOCK_REALTIME */ int __sched -schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta, +schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, const enum hrtimer_mode mode, int clock) { struct hrtimer_sleeper t; @@ -1792,7 +1792,7 @@ schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta, * * Returns 0 when the timer has expired otherwise -EINTR */ -int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta, +int __sched schedule_hrtimeout_range(ktime_t *expires, u64 delta, const enum hrtimer_mode mode) { return schedule_hrtimeout_range_clock(expires, delta, mode, diff --git a/kernel/time/timer.c b/kernel/time/timer.c index bbc5d1114583..d1798fa0c743 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1698,10 +1698,10 @@ EXPORT_SYMBOL(msleep_interruptible); static void __sched do_usleep_range(unsigned long min, unsigned long max) { ktime_t kmin; - unsigned long delta; + u64 delta; kmin = ktime_set(0, min * NSEC_PER_USEC); - delta = (max - min) * NSEC_PER_USEC; + delta = (u64)(max - min) * NSEC_PER_USEC; schedule_hrtimeout_range(&kmin, delta, HRTIMER_MODE_REL); } -- cgit v1.2.3 From a8199371afc27946d72f0d53e938e78d2ea0bae3 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 17 Mar 2016 14:21:20 -0700 Subject: printk: move can_use_console() out of console_trylock_for_printk() console_unlock() allows to cond_resched() if its caller has set `console_may_schedule' to 1 (this functionality is present since 8d91f8b15361 ("printk: do cond_resched() between lines while outputting to consoles"). The rules are: -- console_lock() always sets `console_may_schedule' to 1 -- console_trylock() always sets `console_may_schedule' to 0 printk() calls console_unlock() with preemption desabled, which basically can lead to RCU stalls, watchdog soft lockups, etc. if something is simultaneously calling printk() frequent enough (IOW, console_sem owner always has new data to send to console divers and can't leave console_unlock() for a long time). printk()->console_trylock() callers do not necessarily execute in atomic contexts, and some of them can cond_resched() in console_unlock(). console_trylock() can set `console_may_schedule' to 1 (allow cond_resched() later in consoe_unlock()) when it's safe. This patch (of 3): vprintk_emit() disables preemption around console_trylock_for_printk() and console_unlock() calls for a strong reason -- can_use_console() check. The thing is that vprintl_emit() can be called on a CPU that is not fully brought up yet (!cpu_online()), which potentially can cause problems if console driver wants to access per-cpu data. A console driver can explicitly state that it's safe to call it from !online cpu by setting CON_ANYTIME bit in console ->flags. That's why for !cpu_online() can_use_console() iterates all the console to find out if there is a CON_ANYTIME console, otherwise console_unlock() must be avoided. can_use_console() ensures that console_unlock() call is safe in vprintk_emit() only; console_lock() and console_trylock() are not covered by this check. Even though call_console_drivers(), invoked from console_cont_flush() and console_unlock(), tests `!cpu_online() && CON_ANYTIME' for_each_console(), it may be too late, which can result in messages loss. Assume that we have 2 cpus -- CPU0 is online, CPU1 is !online, and no CON_ANYTIME consoles available. CPU0 online CPU1 !online console_trylock() ... console_unlock() console_cont_flush spin_lock logbuf_lock if (!cont.len) { spin_unlock logbuf_lock return } for (;;) { vprintk_emit spin_lock logbuf_lock log_store spin_unlock logbuf_lock spin_lock logbuf_lock !console_trylock_for_printk msg_print_text return console_idx = log_next() console_seq++ console_prev = msg->flags spin_unlock logbuf_lock call_console_drivers() for_each_console(con) { if (!cpu_online() && !(con->flags & CON_ANYTIME)) continue; } /* * no message printed, we lost it */ vprintk_emit spin_lock logbuf_lock log_store spin_unlock logbuf_lock !console_trylock_for_printk return /* * go to the beginning of the loop, * find out there are new messages, * lose it */ } console_trylock()/console_lock() call on CPU1 may come from cpu notifiers registered on that CPU. Since notifiers are not getting unregistered when CPU is going DOWN, all of the notifiers receive notifications during CPU UP. For example, on my x86_64, I see around 50 notification sent from offline CPU to itself [swapper/2] from cpu:2 to:2 action:CPU_STARTING hotplug_hrtick [swapper/2] from cpu:2 to:2 action:CPU_STARTING blk_mq_main_cpu_notify [swapper/2] from cpu:2 to:2 action:CPU_STARTING blk_mq_queue_reinit_notify [swapper/2] from cpu:2 to:2 action:CPU_STARTING console_cpu_notify while doing echo 0 > /sys/devices/system/cpu/cpu2/online echo 1 > /sys/devices/system/cpu/cpu2/online So grabbing the console_sem lock while CPU is !online is possible, in theory. This patch moves can_use_console() check out of console_trylock_for_printk(). Instead it calls it in console_unlock(), so now console_lock()/console_unlock() are also 'protected' by can_use_console(). This also means that console_trylock_for_printk() is not really needed anymore and can be removed. Signed-off-by: Sergey Senozhatsky Reviewed-by: Petr Mladek Cc: Jan Kara Cc: Tejun Heo Cc: Kyle McMartin Cc: Dave Jones Cc: Calvin Owens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/printk/printk.c | 97 ++++++++++++++++++++++---------------------------- 1 file changed, 42 insertions(+), 55 deletions(-) (limited to 'kernel') diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index c963ba534a78..2523332bd998 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1483,58 +1483,6 @@ static void zap_locks(void) sema_init(&console_sem, 1); } -/* - * Check if we have any console that is capable of printing while cpu is - * booting or shutting down. Requires console_sem. - */ -static int have_callable_console(void) -{ - struct console *con; - - for_each_console(con) - if (con->flags & CON_ANYTIME) - return 1; - - return 0; -} - -/* - * Can we actually use the console at this time on this cpu? - * - * Console drivers may assume that per-cpu resources have been allocated. So - * unless they're explicitly marked as being able to cope (CON_ANYTIME) don't - * call them until this CPU is officially up. - */ -static inline int can_use_console(unsigned int cpu) -{ - return cpu_online(cpu) || have_callable_console(); -} - -/* - * Try to get console ownership to actually show the kernel - * messages from a 'printk'. Return true (and with the - * console_lock held, and 'console_locked' set) if it - * is successful, false otherwise. - */ -static int console_trylock_for_printk(void) -{ - unsigned int cpu = smp_processor_id(); - - if (!console_trylock()) - return 0; - /* - * If we can't use the console, we need to release the console - * semaphore by hand to avoid flushing the buffer. We need to hold the - * console semaphore in order to do this test safely. - */ - if (!can_use_console(cpu)) { - console_locked = 0; - up_console_sem(); - return 0; - } - return 1; -} - int printk_delay_msec __read_mostly; static inline void printk_delay(void) @@ -1681,7 +1629,6 @@ asmlinkage int vprintk_emit(int facility, int level, boot_delay_msec(level); printk_delay(); - /* This stops the holder of console_sem just where we want him */ local_irq_save(flags); this_cpu = smp_processor_id(); @@ -1705,6 +1652,7 @@ asmlinkage int vprintk_emit(int facility, int level, } lockdep_off(); + /* This stops the holder of console_sem just where we want him */ raw_spin_lock(&logbuf_lock); logbuf_cpu = this_cpu; @@ -1821,7 +1769,7 @@ asmlinkage int vprintk_emit(int facility, int level, * semaphore. The release will print out buffers and wake up * /dev/kmsg and syslog() users. */ - if (console_trylock_for_printk()) + if (console_trylock()) console_unlock(); preempt_enable(); lockdep_on(); @@ -2184,6 +2132,33 @@ int is_console_locked(void) return console_locked; } +/* + * Check if we have any console that is capable of printing while cpu is + * booting or shutting down. Requires console_sem. + */ +static int have_callable_console(void) +{ + struct console *con; + + for_each_console(con) + if (con->flags & CON_ANYTIME) + return 1; + + return 0; +} + +/* + * Can we actually use the console at this time on this cpu? + * + * Console drivers may assume that per-cpu resources have been allocated. So + * unless they're explicitly marked as being able to cope (CON_ANYTIME) don't + * call them until this CPU is officially up. + */ +static inline int can_use_console(void) +{ + return cpu_online(raw_smp_processor_id()) || have_callable_console(); +} + static void console_cont_flush(char *text, size_t size) { unsigned long flags; @@ -2254,9 +2229,21 @@ void console_unlock(void) do_cond_resched = console_may_schedule; console_may_schedule = 0; +again: + /* + * We released the console_sem lock, so we need to recheck if + * cpu is online and (if not) is there at least one CON_ANYTIME + * console. + */ + if (!can_use_console()) { + console_locked = 0; + up_console_sem(); + return; + } + /* flush buffered message fragment immediately to console */ console_cont_flush(text, sizeof(text)); -again: + for (;;) { struct printk_log *msg; size_t ext_len = 0; -- cgit v1.2.3 From 6b97a20d3a7909daa06625d4440c2c52d7bf08d7 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 17 Mar 2016 14:21:23 -0700 Subject: printk: set may_schedule for some of console_trylock() callers console_unlock() allows to cond_resched() if its caller has set `console_may_schedule' to 1, since 8d91f8b15361 ("printk: do cond_resched() between lines while outputting to consoles"). The rules are: -- console_lock() always sets `console_may_schedule' to 1 -- console_trylock() always sets `console_may_schedule' to 0 However, console_trylock() callers (among them is printk()) do not always call printk() from atomic contexts, and some of them can cond_resched() in console_unlock(), so console_trylock() can set `console_may_schedule' to 1 for such processes. For !CONFIG_PREEMPT_COUNT kernels, however, console_trylock() always sets `console_may_schedule' to 0. It's possible to drop explicit preempt_disable()/preempt_enable() in vprintk_emit(), because console_unlock() and console_trylock() are now smart enough: a) console_unlock() does not cond_resched() when it's unsafe (console_trylock() takes care of that) b) console_unlock() does can_use_console() check. Signed-off-by: Sergey Senozhatsky Reviewed-by: Petr Mladek Cc: Jan Kara Cc: Tejun Heo Cc: Kyle McMartin Cc: Dave Jones Cc: Calvin Owens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/printk/printk.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 2523332bd998..a6d023c3b852 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1757,13 +1757,6 @@ asmlinkage int vprintk_emit(int facility, int level, /* If called from the scheduler, we can not call up(). */ if (!in_sched) { lockdep_off(); - /* - * Disable preemption to avoid being preempted while holding - * console_sem which would prevent anyone from printing to - * console - */ - preempt_disable(); - /* * Try to acquire and then immediately release the console * semaphore. The release will print out buffers and wake up @@ -1771,7 +1764,6 @@ asmlinkage int vprintk_emit(int facility, int level, */ if (console_trylock()) console_unlock(); - preempt_enable(); lockdep_on(); } @@ -2122,7 +2114,20 @@ int console_trylock(void) return 0; } console_locked = 1; - console_may_schedule = 0; + /* + * When PREEMPT_COUNT disabled we can't reliably detect if it's + * safe to schedule (e.g. calling printk while holding a spin_lock), + * because preempt_disable()/preempt_enable() are just barriers there + * and preempt_count() is always 0. + * + * RCU read sections have a separate preemption counter when + * PREEMPT_RCU enabled thus we must take extra care and check + * rcu_preempt_depth(), otherwise RCU read sections modify + * preempt_count(). + */ + console_may_schedule = !oops_in_progress && + preemptible() && + !rcu_preempt_depth(); return 1; } EXPORT_SYMBOL(console_trylock); -- cgit v1.2.3 From adaf6590ee7db23c3a124fb9f213c90c15cecf96 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 17 Mar 2016 14:21:27 -0700 Subject: printk: check CON_ENABLED in have_callable_console() have_callable_console() must also test CON_ENABLED bit, not just CON_ANYTIME. We may have disabled CON_ANYTIME console so printk can wrongly assume that it's safe to call_console_drivers(). Signed-off-by: Sergey Senozhatsky Reviewed-by: Petr Mladek Cc: Jan Kara Cc: Tejun Heo Cc: Kyle McMartin Cc: Dave Jones Cc: Calvin Owens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/printk/printk.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index a6d023c3b852..d5fd844e5b08 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2146,7 +2146,8 @@ static int have_callable_console(void) struct console *con; for_each_console(con) - if (con->flags & CON_ANYTIME) + if ((con->flags & CON_ENABLED) && + (con->flags & CON_ANYTIME)) return 1; return 0; -- cgit v1.2.3 From f468908bb55a0b01d9424c74f8ec8eb906835150 Mon Sep 17 00:00:00 2001 From: Ivan Delalande Date: Thu, 17 Mar 2016 14:21:30 -0700 Subject: printk: add clear_idx symbol to vmcoreinfo This allows us to extract from the vmcore only the messages emitted since the last time the ring buffer was cleared. We just have to make sure its value is always up-to-date, when old messages are discarded to free space in log_make_free_space() for example. Signed-off-by: Zeyu Zhao Signed-off-by: Ivan Delalande Cc: Kay Sievers Cc: Neil Horman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/printk/printk.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index d5fd844e5b08..bfbf284e4218 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -367,16 +367,20 @@ static int logbuf_has_space(u32 msg_size, bool empty) static int log_make_free_space(u32 msg_size) { - while (log_first_seq < log_next_seq) { - if (logbuf_has_space(msg_size, false)) - return 0; + while (log_first_seq < log_next_seq && + !logbuf_has_space(msg_size, false)) { /* drop old messages until we have enough contiguous space */ log_first_idx = log_next(log_first_idx); log_first_seq++; } + if (clear_seq < log_first_seq) { + clear_seq = log_first_seq; + clear_idx = log_first_idx; + } + /* sequence numbers are equal, so the log buffer is empty */ - if (logbuf_has_space(msg_size, true)) + if (logbuf_has_space(msg_size, log_first_seq == log_next_seq)) return 0; return -ENOMEM; @@ -854,6 +858,7 @@ void log_buf_kexec_setup(void) VMCOREINFO_SYMBOL(log_buf); VMCOREINFO_SYMBOL(log_buf_len); VMCOREINFO_SYMBOL(log_first_idx); + VMCOREINFO_SYMBOL(clear_idx); VMCOREINFO_SYMBOL(log_next_idx); /* * Export struct printk_log size and field offsets. User space tools can @@ -1216,12 +1221,6 @@ static int syslog_print_all(char __user *buf, int size, bool clear) u32 idx; enum log_flags prev; - if (clear_seq < log_first_seq) { - /* messages are gone, move to first available one */ - clear_seq = log_first_seq; - clear_idx = log_first_idx; - } - /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. -- cgit v1.2.3 From 4cc7ecb7f2a60e8deb783b8fbf7c1ae467acb920 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 17 Mar 2016 14:23:00 -0700 Subject: param: convert some "on"/"off" users to strtobool This changes several users of manual "on"/"off" parsing to use strtobool. Some side-effects: - these uses will now parse y/n/1/0 meaningfully too - the early_param uses will now bubble up parse errors Signed-off-by: Kees Cook Acked-by: Heiko Carstens Acked-by: Michael Ellerman Cc: Amitkumar Karwar Cc: Andy Shevchenko Cc: Daniel Borkmann Cc: Joe Perches Cc: Kalle Valo Cc: Martin Schwidefsky Cc: Nishant Sarmukadam Cc: Rasmus Villemoes Cc: Steve French Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/kernel/rtasd.c | 9 ++------- arch/powerpc/platforms/pseries/hotplug-cpu.c | 10 ++-------- arch/s390/kernel/time.c | 8 ++------ arch/s390/kernel/topology.c | 7 ++----- arch/x86/kernel/aperture_64.c | 12 ++---------- include/linux/tick.h | 2 +- kernel/time/hrtimer.c | 10 ++-------- kernel/time/tick-sched.c | 10 ++-------- 8 files changed, 15 insertions(+), 53 deletions(-) (limited to 'kernel') diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 5a2c049c1c61..aa610ce8742f 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -49,7 +49,7 @@ static unsigned int rtas_error_log_buffer_max; static unsigned int event_scan; static unsigned int rtas_event_scan_rate; -static int full_rtas_msgs = 0; +static bool full_rtas_msgs; /* Stop logging to nvram after first fatal error */ static int logging_enabled; /* Until we initialize everything, @@ -592,11 +592,6 @@ __setup("surveillance=", surveillance_setup); static int __init rtasmsgs_setup(char *str) { - if (strcmp(str, "on") == 0) - full_rtas_msgs = 1; - else if (strcmp(str, "off") == 0) - full_rtas_msgs = 0; - - return 1; + return (kstrtobool(str, &full_rtas_msgs) == 0); } __setup("rtasmsgs=", rtasmsgs_setup); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 32274f72fe3f..282837a1d74b 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -47,20 +47,14 @@ static DEFINE_PER_CPU(enum cpu_state_vals, current_state) = CPU_STATE_OFFLINE; static enum cpu_state_vals default_offline_state = CPU_STATE_OFFLINE; -static int cede_offline_enabled __read_mostly = 1; +static bool cede_offline_enabled __read_mostly = true; /* * Enable/disable cede_offline when available. */ static int __init setup_cede_offline(char *str) { - if (!strcmp(str, "off")) - cede_offline_enabled = 0; - else if (!strcmp(str, "on")) - cede_offline_enabled = 1; - else - return 0; - return 1; + return (kstrtobool(str, &cede_offline_enabled) == 0); } __setup("cede_offline=", setup_cede_offline); diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index c4e5f183f225..9409d32f285e 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -1432,7 +1432,7 @@ device_initcall(etr_init_sysfs); /* * Server Time Protocol (STP) code. */ -static int stp_online; +static bool stp_online; static struct stp_sstpi stp_info; static void *stp_page; @@ -1443,11 +1443,7 @@ static struct timer_list stp_timer; static int __init early_parse_stp(char *p) { - if (strncmp(p, "off", 3) == 0) - stp_online = 0; - else if (strncmp(p, "on", 2) == 0) - stp_online = 1; - return 0; + return kstrtobool(p, &stp_online); } early_param("stp", early_parse_stp); diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 40b8102fdadb..64298a867589 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -37,7 +37,7 @@ static void set_topology_timer(void); static void topology_work_fn(struct work_struct *work); static struct sysinfo_15_1_x *tl_info; -static int topology_enabled = 1; +static bool topology_enabled = true; static DECLARE_WORK(topology_work, topology_work_fn); /* @@ -444,10 +444,7 @@ static const struct cpumask *cpu_book_mask(int cpu) static int __init early_parse_topology(char *p) { - if (strncmp(p, "off", 3)) - return 0; - topology_enabled = 0; - return 0; + return kstrtobool(p, &topology_enabled); } early_param("topology", early_parse_topology); diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 6e85f713641d..0a2bb1f62e72 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -227,19 +227,11 @@ static u32 __init search_agp_bridge(u32 *order, int *valid_agp) return 0; } -static int gart_fix_e820 __initdata = 1; +static bool gart_fix_e820 __initdata = true; static int __init parse_gart_mem(char *p) { - if (!p) - return -EINVAL; - - if (!strncmp(p, "off", 3)) - gart_fix_e820 = 0; - else if (!strncmp(p, "on", 2)) - gart_fix_e820 = 1; - - return 0; + return kstrtobool(p, &gart_fix_e820); } early_param("gart_fix_e820", parse_gart_mem); diff --git a/include/linux/tick.h b/include/linux/tick.h index 21f73649a4dc..62be0786d6d0 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -111,7 +111,7 @@ enum tick_dep_bits { #define TICK_DEP_MASK_CLOCK_UNSTABLE (1 << TICK_DEP_BIT_CLOCK_UNSTABLE) #ifdef CONFIG_NO_HZ_COMMON -extern int tick_nohz_enabled; +extern bool tick_nohz_enabled; extern int tick_nohz_tick_stopped(void); extern void tick_nohz_idle_enter(void); extern void tick_nohz_idle_exit(void); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 58a321c34cfb..fa0b983290cf 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -515,7 +515,7 @@ static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) /* * High resolution timer enabled ? */ -static int hrtimer_hres_enabled __read_mostly = 1; +static bool hrtimer_hres_enabled __read_mostly = true; unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC; EXPORT_SYMBOL_GPL(hrtimer_resolution); @@ -524,13 +524,7 @@ EXPORT_SYMBOL_GPL(hrtimer_resolution); */ static int __init setup_hrtimer_hres(char *str) { - if (!strcmp(str, "off")) - hrtimer_hres_enabled = 0; - else if (!strcmp(str, "on")) - hrtimer_hres_enabled = 1; - else - return 0; - return 1; + return (kstrtobool(str, &hrtimer_hres_enabled) == 0); } __setup("highres=", setup_hrtimer_hres); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 969e6704c3c9..195fe7d2caad 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -486,20 +486,14 @@ void __init tick_nohz_init(void) /* * NO HZ enabled ? */ -int tick_nohz_enabled __read_mostly = 1; +bool tick_nohz_enabled __read_mostly = true; unsigned long tick_nohz_active __read_mostly; /* * Enable / Disable tickless mode */ static int __init setup_tick_nohz(char *str) { - if (!strcmp(str, "off")) - tick_nohz_enabled = 0; - else if (!strcmp(str, "on")) - tick_nohz_enabled = 1; - else - return 0; - return 1; + return (kstrtobool(str, &tick_nohz_enabled) == 0); } __setup("nohz=", setup_tick_nohz); -- cgit v1.2.3 From 2553b67a1fbe7bf202e4e8070ab0b00d3d3a06a2 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 17 Mar 2016 14:23:04 -0700 Subject: lib/bug.c: use common WARN helper The traceoff_on_warning option doesn't have any effect on s390, powerpc, arm64, parisc, and sh because there are two different types of WARN implementations: 1) The above mentioned architectures treat WARN() as a special case of a BUG() exception. They handle warnings in report_bug() in lib/bug.c. 2) All other architectures just call warn_slowpath_*() directly. Their warnings are handled in warn_slowpath_common() in kernel/panic.c. Support traceoff_on_warning on all architectures and prevent any future divergence by using a single common function to emit the warning. Also remove the '()' from '%pS()', because the parentheses look funky: [ 45.607629] WARNING: at /root/warn_mod/warn_mod.c:17 .init_dummy+0x20/0x40 [warn_mod]() Reported-by: Chunyu Hu Signed-off-by: Josh Poimboeuf Acked-by: Heiko Carstens Tested-by: Prarit Bhargava Acked-by: Prarit Bhargava Acked-by: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/bug.h | 6 ++++++ kernel/panic.c | 41 ++++++++++++++++++++++++++--------------- lib/bug.c | 26 ++------------------------ 3 files changed, 34 insertions(+), 39 deletions(-) (limited to 'kernel') diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index fdf6fa078422..f90588abbfd4 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -81,6 +81,12 @@ extern void warn_slowpath_null(const char *file, const int line); do { printk(arg); __WARN_TAINT(taint); } while (0) #endif +/* used internally by panic.c */ +struct warn_args; + +void __warn(const char *file, int line, void *caller, unsigned taint, + struct pt_regs *regs, struct warn_args *args); + #ifndef WARN_ON #define WARN_ON(condition) ({ \ int __ret_warn_on = !!(condition); \ diff --git a/kernel/panic.c b/kernel/panic.c index d96469de72dc..fa400852bf6c 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -24,6 +24,7 @@ #include #include #include +#include #define PANIC_TIMER_STEP 100 #define PANIC_BLINK_SPD 18 @@ -449,20 +450,25 @@ void oops_exit(void) kmsg_dump(KMSG_DUMP_OOPS); } -#ifdef WANT_WARN_ON_SLOWPATH -struct slowpath_args { +struct warn_args { const char *fmt; va_list args; }; -static void warn_slowpath_common(const char *file, int line, void *caller, - unsigned taint, struct slowpath_args *args) +void __warn(const char *file, int line, void *caller, unsigned taint, + struct pt_regs *regs, struct warn_args *args) { disable_trace_on_warning(); pr_warn("------------[ cut here ]------------\n"); - pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS()\n", - raw_smp_processor_id(), current->pid, file, line, caller); + + if (file) + pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n", + raw_smp_processor_id(), current->pid, file, line, + caller); + else + pr_warn("WARNING: CPU: %d PID: %d at %pS\n", + raw_smp_processor_id(), current->pid, caller); if (args) vprintk(args->fmt, args->args); @@ -479,20 +485,27 @@ static void warn_slowpath_common(const char *file, int line, void *caller, } print_modules(); - dump_stack(); + + if (regs) + show_regs(regs); + else + dump_stack(); + print_oops_end_marker(); + /* Just a warning, don't kill lockdep. */ add_taint(taint, LOCKDEP_STILL_OK); } +#ifdef WANT_WARN_ON_SLOWPATH void warn_slowpath_fmt(const char *file, int line, const char *fmt, ...) { - struct slowpath_args args; + struct warn_args args; args.fmt = fmt; va_start(args.args, fmt); - warn_slowpath_common(file, line, __builtin_return_address(0), - TAINT_WARN, &args); + __warn(file, line, __builtin_return_address(0), TAINT_WARN, NULL, + &args); va_end(args.args); } EXPORT_SYMBOL(warn_slowpath_fmt); @@ -500,20 +513,18 @@ EXPORT_SYMBOL(warn_slowpath_fmt); void warn_slowpath_fmt_taint(const char *file, int line, unsigned taint, const char *fmt, ...) { - struct slowpath_args args; + struct warn_args args; args.fmt = fmt; va_start(args.args, fmt); - warn_slowpath_common(file, line, __builtin_return_address(0), - taint, &args); + __warn(file, line, __builtin_return_address(0), taint, NULL, &args); va_end(args.args); } EXPORT_SYMBOL(warn_slowpath_fmt_taint); void warn_slowpath_null(const char *file, int line) { - warn_slowpath_common(file, line, __builtin_return_address(0), - TAINT_WARN, NULL); + __warn(file, line, __builtin_return_address(0), TAINT_WARN, NULL, NULL); } EXPORT_SYMBOL(warn_slowpath_null); #endif diff --git a/lib/bug.c b/lib/bug.c index 6cde380f09de..bc3656e944d2 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -167,30 +167,8 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) if (warning) { /* this is a WARN_ON rather than BUG/BUG_ON */ - pr_warn("------------[ cut here ]------------\n"); - - if (file) - pr_warn("WARNING: at %s:%u\n", file, line); - else - pr_warn("WARNING: at %p [verbose debug info unavailable]\n", - (void *)bugaddr); - - if (panic_on_warn) { - /* - * This thread may hit another WARN() in the panic path. - * Resetting this prevents additional WARN() from - * panicking the system on this thread. Other threads - * are blocked by the panic_mutex in panic(). - */ - panic_on_warn = 0; - panic("panic_on_warn set ...\n"); - } - - print_modules(); - show_regs(regs); - print_oops_end_marker(); - /* Just a warning, don't kill lockdep. */ - add_taint(BUG_GET_TAINT(bug), LOCKDEP_STILL_OK); + __warn(file, line, (void *)bugaddr, BUG_GET_TAINT(bug), regs, + NULL); return BUG_TRAP_TYPE_WARN; } -- cgit v1.2.3