From a670468f5e0b5fad4db6e4d195f15915dc2a35c1 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 21 Aug 2018 21:53:06 -0700 Subject: mm: zero out the vma in vma_init() Rather than in vm_area_alloc(). To ensure that the various oddball stack-based vmas are in a good state. Some of the callers were zeroing them out, others were not. Acked-by: Kirill A. Shutemov Cc: Russell King Cc: Dmitry Vyukov Cc: Oleg Nesterov Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 5ee74c113381..8c760effa42e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -310,8 +310,9 @@ static struct kmem_cache *mm_cachep; struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) { - struct vm_area_struct *vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + struct vm_area_struct *vma; + vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (vma) vma_init(vma, mm); return vma; -- cgit v1.2.3 From a2e514453861dd39b53b7a50b6771bd3f9852078 Mon Sep 17 00:00:00 2001 From: Dmitry Vyukov Date: Tue, 21 Aug 2018 21:55:52 -0700 Subject: kernel/hung_task.c: allow to set checking interval separately from timeout Currently task hung checking interval is equal to timeout, as the result hung is detected anywhere between timeout and 2*timeout. This is fine for most interactive environments, but this hurts automated testing setups (syzbot). In an automated setup we need to strictly order CPU lockup < RCU stall < workqueue lockup < task hung < silent loss, so that RCU stall is not detected as task hung and task hung is not detected as silent machine loss. The large variance in task hung detection timeout requires setting silent machine loss timeout to a very large value (e.g. if task hung is 3 mins, then silent loss need to be set to ~7 mins). The additional 3 minutes significantly reduce testing efficiency because usually we crash kernel within a minute, and this can add hours to bug localization process as it needs to do dozens of tests. Allow setting checking interval separately from timeout. This allows to set timeout to, say, 3 minutes, but checking interval to 10 secs. The interval is controlled via a new hung_task_check_interval_secs sysctl, similar to the existing hung_task_timeout_secs sysctl. The default value of 0 results in the current behavior: checking interval is equal to timeout. [akpm@linux-foundation.org: update hung_task_timeout_max's comment] Link: http://lkml.kernel.org/r/20180611111004.203513-1-dvyukov@google.com Signed-off-by: Dmitry Vyukov Cc: Paul E. McKenney Cc: Tetsuo Handa Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/kernel.txt | 15 ++++++++++++++- include/linux/sched.h | 1 + include/linux/sched/sysctl.h | 1 + kernel/fork.c | 1 + kernel/hung_task.c | 15 ++++++++++++++- kernel/sysctl.c | 13 ++++++++++++- 6 files changed, 43 insertions(+), 3 deletions(-) (limited to 'kernel/fork.c') diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 59585030cbaf..9d38e75b19a0 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -38,6 +38,7 @@ show up in /proc/sys/kernel: - hung_task_panic - hung_task_check_count - hung_task_timeout_secs +- hung_task_check_interval_secs - hung_task_warnings - hyperv_record_panic_msg - kexec_load_disabled @@ -355,7 +356,7 @@ This file shows up if CONFIG_DETECT_HUNG_TASK is enabled. hung_task_timeout_secs: -Check interval. When a task in D state did not get scheduled +When a task in D state did not get scheduled for more than this value report a warning. This file shows up if CONFIG_DETECT_HUNG_TASK is enabled. @@ -364,6 +365,18 @@ Possible values to set are in range {0..LONG_MAX/HZ}. ============================================================== +hung_task_check_interval_secs: + +Hung task check interval. If hung task checking is enabled +(see hung_task_timeout_secs), the check is done every +hung_task_check_interval_secs seconds. +This file shows up if CONFIG_DETECT_HUNG_TASK is enabled. + +0 (default): means use hung_task_timeout_secs as checking interval. +Possible values to set are in range {0..LONG_MAX/HZ}. + +============================================================== + hung_task_warnings: The maximum number of warnings to report. During a check interval diff --git a/include/linux/sched.h b/include/linux/sched.h index 789923fbee3a..58eb3a2bc695 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -853,6 +853,7 @@ struct task_struct { #endif #ifdef CONFIG_DETECT_HUNG_TASK unsigned long last_switch_count; + unsigned long last_switch_time; #endif /* Filesystem information: */ struct fs_struct *fs; diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 913488d828cb..a9c32daeb9d8 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -10,6 +10,7 @@ struct ctl_table; extern int sysctl_hung_task_check_count; extern unsigned int sysctl_hung_task_panic; extern unsigned long sysctl_hung_task_timeout_secs; +extern unsigned long sysctl_hung_task_check_interval_secs; extern int sysctl_hung_task_warnings; extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, void __user *buffer, diff --git a/kernel/fork.c b/kernel/fork.c index 8c760effa42e..8bcef2413f1b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1302,6 +1302,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) tsk->nvcsw = tsk->nivcsw = 0; #ifdef CONFIG_DETECT_HUNG_TASK tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw; + tsk->last_switch_time = 0; #endif tsk->mm = NULL; diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 32b479468e4d..b9132d1269ef 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -40,6 +40,11 @@ int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT; */ unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_TASK_TIMEOUT; +/* + * Zero (default value) means use sysctl_hung_task_timeout_secs: + */ +unsigned long __read_mostly sysctl_hung_task_check_interval_secs; + int __read_mostly sysctl_hung_task_warnings = 10; static int __read_mostly did_panic; @@ -98,8 +103,11 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) if (switch_count != t->last_switch_count) { t->last_switch_count = switch_count; + t->last_switch_time = jiffies; return; } + if (time_is_after_jiffies(t->last_switch_time + timeout * HZ)) + return; trace_sched_process_hang(t); @@ -245,8 +253,13 @@ static int watchdog(void *dummy) for ( ; ; ) { unsigned long timeout = sysctl_hung_task_timeout_secs; - long t = hung_timeout_jiffies(hung_last_checked, timeout); + unsigned long interval = sysctl_hung_task_check_interval_secs; + long t; + if (interval == 0) + interval = timeout; + interval = min_t(unsigned long, interval, timeout); + t = hung_timeout_jiffies(hung_last_checked, interval); if (t <= 0) { if (!atomic_xchg(&reset_hung_task, 0)) check_hung_uninterruptible_tasks(timeout); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index f22f76b7a138..dbdcb6673b27 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -145,7 +145,10 @@ static int minolduid; static int ngroups_max = NGROUPS_MAX; static const int cap_last_cap = CAP_LAST_CAP; -/*this is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs */ +/* + * This is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs + * and hung_task_check_interval_secs + */ #ifdef CONFIG_DETECT_HUNG_TASK static unsigned long hung_task_timeout_max = (LONG_MAX/HZ); #endif @@ -1090,6 +1093,14 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dohung_task_timeout_secs, .extra2 = &hung_task_timeout_max, }, + { + .procname = "hung_task_check_interval_secs", + .data = &sysctl_hung_task_check_interval_secs, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_dohung_task_timeout_secs, + .extra2 = &hung_task_timeout_max, + }, { .procname = "hung_task_warnings", .data = &sysctl_hung_task_warnings, -- cgit v1.2.3 From 06e62a46bbba20aa5286102016a04214bb446141 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Tue, 21 Aug 2018 22:00:58 -0700 Subject: fork: don't copy inconsistent signal handler state to child Before this change, if a multithreaded process forks while one of its threads is changing a signal handler using sigaction(), the memcpy() in copy_sighand() can race with the struct assignment in do_sigaction(). It isn't clear whether this can cause corruption of the userspace signal handler pointer, but it definitely can cause inconsistency between different fields of struct sigaction. Take the appropriate spinlock to avoid this. I have tested that this patch prevents inconsistency between sa_sigaction and sa_flags, which is possible before this patch. Link: http://lkml.kernel.org/r/20180702145108.73189-1-jannh@google.com Signed-off-by: Jann Horn Acked-by: Michal Hocko Reviewed-by: Andrew Morton Cc: Rik van Riel Cc: "Peter Zijlstra (Intel)" Cc: Kees Cook Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 8bcef2413f1b..23eb960c701d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1427,7 +1427,9 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) return -ENOMEM; atomic_set(&sig->count, 1); + spin_lock_irq(¤t->sighand->siglock); memcpy(sig->action, current->sighand->action, sizeof(sig->action)); + spin_unlock_irq(¤t->sighand->siglock); return 0; } -- cgit v1.2.3