From f06febc96ba8e0af80bcc3eaec0a109e88275fac Mon Sep 17 00:00:00 2001 From: Frank Mayhar Date: Fri, 12 Sep 2008 09:54:39 -0700 Subject: timers: fix itimer/many thread hang Overview This patch reworks the handling of POSIX CPU timers, including the ITIMER_PROF, ITIMER_VIRT timers and rlimit handling. It was put together with the help of Roland McGrath, the owner and original writer of this code. The problem we ran into, and the reason for this rework, has to do with using a profiling timer in a process with a large number of threads. It appears that the performance of the old implementation of run_posix_cpu_timers() was at least O(n*3) (where "n" is the number of threads in a process) or worse. Everything is fine with an increasing number of threads until the time taken for that routine to run becomes the same as or greater than the tick time, at which point things degrade rather quickly. This patch fixes bug 9906, "Weird hang with NPTL and SIGPROF." Code Changes This rework corrects the implementation of run_posix_cpu_timers() to make it run in constant time for a particular machine. (Performance may vary between one machine and another depending upon whether the kernel is built as single- or multiprocessor and, in the latter case, depending upon the number of running processors.) To do this, at each tick we now update fields in signal_struct as well as task_struct. The run_posix_cpu_timers() function uses those fields to make its decisions. We define a new structure, "task_cputime," to contain user, system and scheduler times and use these in appropriate places: struct task_cputime { cputime_t utime; cputime_t stime; unsigned long long sum_exec_runtime; }; This is included in the structure "thread_group_cputime," which is a new substructure of signal_struct and which varies for uniprocessor versus multiprocessor kernels. For uniprocessor kernels, it uses "task_cputime" as a simple substructure, while for multiprocessor kernels it is a pointer: struct thread_group_cputime { struct task_cputime totals; }; struct thread_group_cputime { struct task_cputime *totals; }; We also add a new task_cputime substructure directly to signal_struct, to cache the earliest expiration of process-wide timers, and task_cputime also replaces the it_*_expires fields of task_struct (used for earliest expiration of thread timers). The "thread_group_cputime" structure contains process-wide timers that are updated via account_user_time() and friends. In the non-SMP case the structure is a simple aggregator; unfortunately in the SMP case that simplicity was not achievable due to cache-line contention between CPUs (in one measured case performance was actually _worse_ on a 16-cpu system than the same test on a 4-cpu system, due to this contention). For SMP, the thread_group_cputime counters are maintained as a per-cpu structure allocated using alloc_percpu(). The timer functions update only the timer field in the structure corresponding to the running CPU, obtained using per_cpu_ptr(). We define a set of inline functions in sched.h that we use to maintain the thread_group_cputime structure and hide the differences between UP and SMP implementations from the rest of the kernel. The thread_group_cputime_init() function initializes the thread_group_cputime structure for the given task. The thread_group_cputime_alloc() is a no-op for UP; for SMP it calls the out-of-line function thread_group_cputime_alloc_smp() to allocate and fill in the per-cpu structures and fields. The thread_group_cputime_free() function, also a no-op for UP, in SMP frees the per-cpu structures. The thread_group_cputime_clone_thread() function (also a UP no-op) for SMP calls thread_group_cputime_alloc() if the per-cpu structures haven't yet been allocated. The thread_group_cputime() function fills the task_cputime structure it is passed with the contents of the thread_group_cputime fields; in UP it's that simple but in SMP it must also safely check that tsk->signal is non-NULL (if it is it just uses the appropriate fields of task_struct) and, if so, sums the per-cpu values for each online CPU. Finally, the three functions account_group_user_time(), account_group_system_time() and account_group_exec_runtime() are used by timer functions to update the respective fields of the thread_group_cputime structure. Non-SMP operation is trivial and will not be mentioned further. The per-cpu structure is always allocated when a task creates its first new thread, via a call to thread_group_cputime_clone_thread() from copy_signal(). It is freed at process exit via a call to thread_group_cputime_free() from cleanup_signal(). All functions that formerly summed utime/stime/sum_sched_runtime values from from all threads in the thread group now use thread_group_cputime() to snapshot the values in the thread_group_cputime structure or the values in the task structure itself if the per-cpu structure hasn't been allocated. Finally, the code in kernel/posix-cpu-timers.c has changed quite a bit. The run_posix_cpu_timers() function has been split into a fast path and a slow path; the former safely checks whether there are any expired thread timers and, if not, just returns, while the slow path does the heavy lifting. With the dedicated thread group fields, timers are no longer "rebalanced" and the process_timer_rebalance() function and related code has gone away. All summing loops are gone and all code that used them now uses the thread_group_cputime() inline. When process-wide timers are set, the new task_cputime structure in signal_struct is used to cache the earliest expiration; this is checked in the fast path. Performance The fix appears not to add significant overhead to existing operations. It generally performs the same as the current code except in two cases, one in which it performs slightly worse (Case 5 below) and one in which it performs very significantly better (Case 2 below). Overall it's a wash except in those two cases. I've since done somewhat more involved testing on a dual-core Opteron system. Case 1: With no itimer running, for a test with 100,000 threads, the fixed kernel took 1428.5 seconds, 513 seconds more than the unfixed system, all of which was spent in the system. There were twice as many voluntary context switches with the fix as without it. Case 2: With an itimer running at .01 second ticks and 4000 threads (the most an unmodified kernel can handle), the fixed kernel ran the test in eight percent of the time (5.8 seconds as opposed to 70 seconds) and had better tick accuracy (.012 seconds per tick as opposed to .023 seconds per tick). Case 3: A 4000-thread test with an initial timer tick of .01 second and an interval of 10,000 seconds (i.e. a timer that ticks only once) had very nearly the same performance in both cases: 6.3 seconds elapsed for the fixed kernel versus 5.5 seconds for the unfixed kernel. With fewer threads (eight in these tests), the Case 1 test ran in essentially the same time on both the modified and unmodified kernels (5.2 seconds versus 5.8 seconds). The Case 2 test ran in about the same time as well, 5.9 seconds versus 5.4 seconds but again with much better tick accuracy, .013 seconds per tick versus .025 seconds per tick for the unmodified kernel. Since the fix affected the rlimit code, I also tested soft and hard CPU limits. Case 4: With a hard CPU limit of 20 seconds and eight threads (and an itimer running), the modified kernel was very slightly favored in that while it killed the process in 19.997 seconds of CPU time (5.002 seconds of wall time), only .003 seconds of that was system time, the rest was user time. The unmodified kernel killed the process in 20.001 seconds of CPU (5.014 seconds of wall time) of which .016 seconds was system time. Really, though, the results were too close to call. The results were essentially the same with no itimer running. Case 5: With a soft limit of 20 seconds and a hard limit of 2000 seconds (where the hard limit would never be reached) and an itimer running, the modified kernel exhibited worse tick accuracy than the unmodified kernel: .050 seconds/tick versus .028 seconds/tick. Otherwise, performance was almost indistinguishable. With no itimer running this test exhibited virtually identical behavior and times in both cases. In times past I did some limited performance testing. those results are below. On a four-cpu Opteron system without this fix, a sixteen-thread test executed in 3569.991 seconds, of which user was 3568.435s and system was 1.556s. On the same system with the fix, user and elapsed time were about the same, but system time dropped to 0.007 seconds. Performance with eight, four and one thread were comparable. Interestingly, the timer ticks with the fix seemed more accurate: The sixteen-thread test with the fix received 149543 ticks for 0.024 seconds per tick, while the same test without the fix received 58720 for 0.061 seconds per tick. Both cases were configured for an interval of 0.01 seconds. Again, the other tests were comparable. Each thread in this test computed the primes up to 25,000,000. I also did a test with a large number of threads, 100,000 threads, which is impossible without the fix. In this case each thread computed the primes only up to 10,000 (to make the runtime manageable). System time dominated, at 1546.968 seconds out of a total 2176.906 seconds (giving a user time of 629.938s). It received 147651 ticks for 0.015 seconds per tick, still quite accurate. There is obviously no comparable test without the fix. Signed-off-by: Frank Mayhar Cc: Roland McGrath Cc: Alexey Dobriyan Cc: Andrew Morton Signed-off-by: Ingo Molnar --- include/linux/sched.h | 257 +++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 244 insertions(+), 13 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 3d9120c5ad1..26d7a5f2d0b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -425,6 +425,45 @@ struct pacct_struct { unsigned long ac_minflt, ac_majflt; }; +/** + * struct task_cputime - collected CPU time counts + * @utime: time spent in user mode, in &cputime_t units + * @stime: time spent in kernel mode, in &cputime_t units + * @sum_exec_runtime: total time spent on the CPU, in nanoseconds + * + * This structure groups together three kinds of CPU time that are + * tracked for threads and thread groups. Most things considering + * CPU time want to group these counts together and treat all three + * of them in parallel. + */ +struct task_cputime { + cputime_t utime; + cputime_t stime; + unsigned long long sum_exec_runtime; +}; +/* Alternate field names when used to cache expirations. */ +#define prof_exp stime +#define virt_exp utime +#define sched_exp sum_exec_runtime + +/** + * struct thread_group_cputime - thread group interval timer counts + * @totals: thread group interval timers; substructure for + * uniprocessor kernel, per-cpu for SMP kernel. + * + * This structure contains the version of task_cputime, above, that is + * used for thread group CPU clock calculations. + */ +#ifdef CONFIG_SMP +struct thread_group_cputime { + struct task_cputime *totals; +}; +#else +struct thread_group_cputime { + struct task_cputime totals; +}; +#endif + /* * NOTE! "signal_struct" does not have it's own * locking, because a shared signal_struct always @@ -470,6 +509,17 @@ struct signal_struct { cputime_t it_prof_expires, it_virt_expires; cputime_t it_prof_incr, it_virt_incr; + /* + * Thread group totals for process CPU clocks. + * See thread_group_cputime(), et al, for details. + */ + struct thread_group_cputime cputime; + + /* Earliest-expiration cache. */ + struct task_cputime cputime_expires; + + struct list_head cpu_timers[3]; + /* job control IDs */ /* @@ -500,7 +550,7 @@ struct signal_struct { * Live threads maintain their own counters and add to these * in __exit_signal, except for the group leader. */ - cputime_t utime, stime, cutime, cstime; + cputime_t cutime, cstime; cputime_t gtime; cputime_t cgtime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; @@ -508,14 +558,6 @@ struct signal_struct { unsigned long inblock, oublock, cinblock, coublock; struct task_io_accounting ioac; - /* - * Cumulative ns of scheduled CPU time for dead threads in the - * group, not including a zombie group leader. (This only differs - * from jiffies_to_ns(utime + stime) if sched_clock uses something - * other than jiffies.) - */ - unsigned long long sum_sched_runtime; - /* * We don't bother to synchronize most readers of this at all, * because there is no reader checking a limit that actually needs @@ -527,8 +569,6 @@ struct signal_struct { */ struct rlimit rlim[RLIM_NLIMITS]; - struct list_head cpu_timers[3]; - /* keep the process-shared keyrings here so that they do the right * thing in threads created with CLONE_THREAD */ #ifdef CONFIG_KEYS @@ -1134,8 +1174,7 @@ struct task_struct { /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */ unsigned long min_flt, maj_flt; - cputime_t it_prof_expires, it_virt_expires; - unsigned long long it_sched_expires; + struct task_cputime cputime_expires; struct list_head cpu_timers[3]; /* process credentials */ @@ -1585,6 +1624,7 @@ extern unsigned long long cpu_clock(int cpu); extern unsigned long long task_sched_runtime(struct task_struct *task); +extern unsigned long long thread_group_sched_runtime(struct task_struct *task); /* sched_exec is called by processes performing an exec */ #ifdef CONFIG_SMP @@ -2081,6 +2121,197 @@ static inline int spin_needbreak(spinlock_t *lock) #endif } +/* + * Thread group CPU time accounting. + */ +#ifdef CONFIG_SMP + +extern int thread_group_cputime_alloc_smp(struct task_struct *); +extern void thread_group_cputime_smp(struct task_struct *, struct task_cputime *); + +static inline void thread_group_cputime_init(struct signal_struct *sig) +{ + sig->cputime.totals = NULL; +} + +static inline int thread_group_cputime_clone_thread(struct task_struct *curr, + struct task_struct *new) +{ + if (curr->signal->cputime.totals) + return 0; + return thread_group_cputime_alloc_smp(curr); +} + +static inline void thread_group_cputime_free(struct signal_struct *sig) +{ + free_percpu(sig->cputime.totals); +} + +/** + * thread_group_cputime - Sum the thread group time fields across all CPUs. + * + * This is a wrapper for the real routine, thread_group_cputime_smp(). See + * that routine for details. + */ +static inline void thread_group_cputime( + struct task_struct *tsk, + struct task_cputime *times) +{ + thread_group_cputime_smp(tsk, times); +} + +/** + * thread_group_cputime_account_user - Maintain utime for a thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @cputime: Time value by which to increment the utime field of that + * structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the utime field there. + */ +static inline void thread_group_cputime_account_user( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->utime = cputime_add(times->utime, cputime); + put_cpu_no_resched(); + } +} + +/** + * thread_group_cputime_account_system - Maintain stime for a thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @cputime: Time value by which to increment the stime field of that + * structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the stime field there. + */ +static inline void thread_group_cputime_account_system( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->stime = cputime_add(times->stime, cputime); + put_cpu_no_resched(); + } +} + +/** + * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a + * thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @ns: Time value by which to increment the sum_exec_runtime field + * of that structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the sum_exec_runtime field there. + */ +static inline void thread_group_cputime_account_exec_runtime( + struct thread_group_cputime *tgtimes, + unsigned long long ns) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->sum_exec_runtime += ns; + put_cpu_no_resched(); + } +} + +#else /* CONFIG_SMP */ + +static inline void thread_group_cputime_init(struct signal_struct *sig) +{ + sig->cputime.totals.utime = cputime_zero; + sig->cputime.totals.stime = cputime_zero; + sig->cputime.totals.sum_exec_runtime = 0; +} + +static inline int thread_group_cputime_alloc(struct task_struct *tsk) +{ + return 0; +} + +static inline void thread_group_cputime_free(struct signal_struct *sig) +{ +} + +static inline int thread_group_cputime_clone_thread(struct task_struct *curr, + struct task_struct *tsk) +{ +} + +static inline void thread_group_cputime(struct task_struct *tsk, + struct task_cputime *cputime) +{ + *cputime = tsk->signal->cputime.totals; +} + +static inline void thread_group_cputime_account_user( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + tgtimes->totals->utime = cputime_add(tgtimes->totals->utime, cputime); +} + +static inline void thread_group_cputime_account_system( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + tgtimes->totals->stime = cputime_add(tgtimes->totals->stime, cputime); +} + +static inline void thread_group_cputime_account_exec_runtime( + struct thread_group_cputime *tgtimes, + unsigned long long ns) +{ + tgtimes->totals->sum_exec_runtime += ns; +} + +#endif /* CONFIG_SMP */ + +static inline void account_group_user_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_user(&sig->cputime, cputime); +} + +static inline void account_group_system_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_system(&sig->cputime, cputime); +} + +static inline void account_group_exec_runtime(struct task_struct *tsk, + unsigned long long ns) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_exec_runtime(&sig->cputime, ns); +} + /* * Reevaluate whether the task has signals pending delivery. * Wake the task if so. -- cgit v1.2.3-70-g09d2 From 0a8eaa4f9b58759595a1bfe13a1295fdc25ba026 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 14 Sep 2008 17:03:52 +0200 Subject: timers: fix itimer/many thread hang, fix #2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit fix the UP build: In file included from arch/x86/kernel/asm-offsets_32.c:9, from arch/x86/kernel/asm-offsets.c:3: include/linux/sched.h: In function ‘thread_group_cputime_clone_thread’: include/linux/sched.h:2272: warning: no return statement in function returning non-void include/linux/sched.h: In function ‘thread_group_cputime_account_user’: include/linux/sched.h:2284: error: invalid type argument of ‘->’ (have ‘struct task_cputime’) include/linux/sched.h:2284: error: invalid type argument of ‘->’ (have ‘struct task_cputime’) include/linux/sched.h: In function ‘thread_group_cputime_account_system’: include/linux/sched.h:2291: error: invalid type argument of ‘->’ (have ‘struct task_cputime’) include/linux/sched.h:2291: error: invalid type argument of ‘->’ (have ‘struct task_cputime’) include/linux/sched.h: In function ‘thread_group_cputime_account_exec_runtime’: include/linux/sched.h:2298: error: invalid type argument of ‘->’ (have ‘struct task_cputime’) distcc[14501] ERROR: compile arch/x86/kernel/asm-offsets.c on a/30 failed make[1]: *** [arch/x86/kernel/asm-offsets.s] Error 1 Signed-off-by: Ingo Molnar --- include/linux/sched.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 26d7a5f2d0b..ed355f02d32 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2251,6 +2251,7 @@ static inline void thread_group_cputime_free(struct signal_struct *sig) static inline int thread_group_cputime_clone_thread(struct task_struct *curr, struct task_struct *tsk) { + return 0; } static inline void thread_group_cputime(struct task_struct *tsk, @@ -2263,21 +2264,21 @@ static inline void thread_group_cputime_account_user( struct thread_group_cputime *tgtimes, cputime_t cputime) { - tgtimes->totals->utime = cputime_add(tgtimes->totals->utime, cputime); + tgtimes->totals.utime = cputime_add(tgtimes->totals.utime, cputime); } static inline void thread_group_cputime_account_system( struct thread_group_cputime *tgtimes, cputime_t cputime) { - tgtimes->totals->stime = cputime_add(tgtimes->totals->stime, cputime); + tgtimes->totals.stime = cputime_add(tgtimes->totals.stime, cputime); } static inline void thread_group_cputime_account_exec_runtime( struct thread_group_cputime *tgtimes, unsigned long long ns) { - tgtimes->totals->sum_exec_runtime += ns; + tgtimes->totals.sum_exec_runtime += ns; } #endif /* CONFIG_SMP */ -- cgit v1.2.3-70-g09d2 From 5ce73a4a5a4893a1aa4cdeed1b1a5a6de42c43b6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 14 Sep 2008 17:11:46 +0200 Subject: timers: fix itimer/many thread hang, cleanups Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 +- kernel/posix-cpu-timers.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index ed355f02d32..7ce8d4e5356 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -430,7 +430,7 @@ struct pacct_struct { * @utime: time spent in user mode, in &cputime_t units * @stime: time spent in kernel mode, in &cputime_t units * @sum_exec_runtime: total time spent on the CPU, in nanoseconds - * + * * This structure groups together three kinds of CPU time that are * tracked for threads and thread groups. Most things considering * CPU time want to group these counts together and treat all three diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index dba1c334c3e..9a7ea049fcd 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -94,7 +94,7 @@ void update_rlimit_cpu(unsigned long rlim_new) cputime = secs_to_cputime(rlim_new); if (cputime_eq(current->signal->it_prof_expires, cputime_zero) || - cputime_lt(current->signal->it_prof_expires, cputime)) { + cputime_lt(current->signal->it_prof_expires, cputime)) { spin_lock_irq(¤t->sighand->siglock); set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL); spin_unlock_irq(¤t->sighand->siglock); @@ -1372,9 +1372,9 @@ void run_posix_cpu_timers(struct task_struct *tsk) * tsk->signal is non-NULL; this probably can't happen but cover the * possibility anyway. */ - if (unlikely(!sig) || !fastpath_timer_check(tsk, sig)) { + if (unlikely(!sig) || !fastpath_timer_check(tsk, sig)) return; - } + sighand = lock_task_sighand(tsk, &flags); if (likely(sighand)) { /* -- cgit v1.2.3-70-g09d2 From bb34d92f643086d546b49cef680f6f305ed84414 Mon Sep 17 00:00:00 2001 From: Frank Mayhar Date: Fri, 12 Sep 2008 09:54:39 -0700 Subject: timers: fix itimer/many thread hang, v2 This is the second resubmission of the posix timer rework patch, posted a few days ago. This includes the changes from the previous resubmittion, which addressed Oleg Nesterov's comments, removing the RCU stuff from the patch and un-inlining the thread_group_cputime() function for SMP. In addition, per Ingo Molnar it simplifies the UP code, consolidating much of it with the SMP version and depending on lower-level SMP/UP handling to take care of the differences. It also cleans up some UP compile errors, moves the scheduler stats-related macros into kernel/sched_stats.h, cleans up a merge error in kernel/fork.c and has a few other minor fixes and cleanups as suggested by Oleg and Ingo. Thanks for the review, guys. Signed-off-by: Frank Mayhar Cc: Roland McGrath Cc: Alexey Dobriyan Cc: Andrew Morton Signed-off-by: Ingo Molnar --- include/linux/kernel_stat.h | 1 + include/linux/sched.h | 183 ++------------------------------------------ kernel/fork.c | 5 +- kernel/posix-cpu-timers.c | 153 ++++++++++++++++-------------------- kernel/sched.c | 47 ++---------- kernel/sched_stats.h | 136 ++++++++++++++++++++++++++++++++ 6 files changed, 214 insertions(+), 311 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index cf9f40a91c9..cac3750cd65 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -52,6 +52,7 @@ static inline int kstat_irqs(int irq) return sum; } +extern unsigned long long task_delta_exec(struct task_struct *); extern void account_user_time(struct task_struct *, cputime_t); extern void account_user_time_scaled(struct task_struct *, cputime_t); extern void account_system_time(struct task_struct *, int, cputime_t); diff --git a/include/linux/sched.h b/include/linux/sched.h index 7ce8d4e5356..b982fb48c8f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -454,15 +454,9 @@ struct task_cputime { * This structure contains the version of task_cputime, above, that is * used for thread group CPU clock calculations. */ -#ifdef CONFIG_SMP struct thread_group_cputime { struct task_cputime *totals; }; -#else -struct thread_group_cputime { - struct task_cputime totals; -}; -#endif /* * NOTE! "signal_struct" does not have it's own @@ -2124,193 +2118,26 @@ static inline int spin_needbreak(spinlock_t *lock) /* * Thread group CPU time accounting. */ -#ifdef CONFIG_SMP -extern int thread_group_cputime_alloc_smp(struct task_struct *); -extern void thread_group_cputime_smp(struct task_struct *, struct task_cputime *); +extern int thread_group_cputime_alloc(struct task_struct *); +extern void thread_group_cputime(struct task_struct *, struct task_cputime *); static inline void thread_group_cputime_init(struct signal_struct *sig) { sig->cputime.totals = NULL; } -static inline int thread_group_cputime_clone_thread(struct task_struct *curr, - struct task_struct *new) +static inline int thread_group_cputime_clone_thread(struct task_struct *curr) { if (curr->signal->cputime.totals) return 0; - return thread_group_cputime_alloc_smp(curr); + return thread_group_cputime_alloc(curr); } -static inline void thread_group_cputime_free(struct signal_struct *sig) -{ - free_percpu(sig->cputime.totals); -} - -/** - * thread_group_cputime - Sum the thread group time fields across all CPUs. - * - * This is a wrapper for the real routine, thread_group_cputime_smp(). See - * that routine for details. - */ -static inline void thread_group_cputime( - struct task_struct *tsk, - struct task_cputime *times) -{ - thread_group_cputime_smp(tsk, times); -} - -/** - * thread_group_cputime_account_user - Maintain utime for a thread group. - * - * @tgtimes: Pointer to thread_group_cputime structure. - * @cputime: Time value by which to increment the utime field of that - * structure. - * - * If thread group time is being maintained, get the structure for the - * running CPU and update the utime field there. - */ -static inline void thread_group_cputime_account_user( - struct thread_group_cputime *tgtimes, - cputime_t cputime) -{ - if (tgtimes->totals) { - struct task_cputime *times; - - times = per_cpu_ptr(tgtimes->totals, get_cpu()); - times->utime = cputime_add(times->utime, cputime); - put_cpu_no_resched(); - } -} - -/** - * thread_group_cputime_account_system - Maintain stime for a thread group. - * - * @tgtimes: Pointer to thread_group_cputime structure. - * @cputime: Time value by which to increment the stime field of that - * structure. - * - * If thread group time is being maintained, get the structure for the - * running CPU and update the stime field there. - */ -static inline void thread_group_cputime_account_system( - struct thread_group_cputime *tgtimes, - cputime_t cputime) -{ - if (tgtimes->totals) { - struct task_cputime *times; - - times = per_cpu_ptr(tgtimes->totals, get_cpu()); - times->stime = cputime_add(times->stime, cputime); - put_cpu_no_resched(); - } -} - -/** - * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a - * thread group. - * - * @tgtimes: Pointer to thread_group_cputime structure. - * @ns: Time value by which to increment the sum_exec_runtime field - * of that structure. - * - * If thread group time is being maintained, get the structure for the - * running CPU and update the sum_exec_runtime field there. - */ -static inline void thread_group_cputime_account_exec_runtime( - struct thread_group_cputime *tgtimes, - unsigned long long ns) -{ - if (tgtimes->totals) { - struct task_cputime *times; - - times = per_cpu_ptr(tgtimes->totals, get_cpu()); - times->sum_exec_runtime += ns; - put_cpu_no_resched(); - } -} - -#else /* CONFIG_SMP */ - -static inline void thread_group_cputime_init(struct signal_struct *sig) -{ - sig->cputime.totals.utime = cputime_zero; - sig->cputime.totals.stime = cputime_zero; - sig->cputime.totals.sum_exec_runtime = 0; -} - -static inline int thread_group_cputime_alloc(struct task_struct *tsk) -{ - return 0; -} static inline void thread_group_cputime_free(struct signal_struct *sig) { -} - -static inline int thread_group_cputime_clone_thread(struct task_struct *curr, - struct task_struct *tsk) -{ - return 0; -} - -static inline void thread_group_cputime(struct task_struct *tsk, - struct task_cputime *cputime) -{ - *cputime = tsk->signal->cputime.totals; -} - -static inline void thread_group_cputime_account_user( - struct thread_group_cputime *tgtimes, - cputime_t cputime) -{ - tgtimes->totals.utime = cputime_add(tgtimes->totals.utime, cputime); -} - -static inline void thread_group_cputime_account_system( - struct thread_group_cputime *tgtimes, - cputime_t cputime) -{ - tgtimes->totals.stime = cputime_add(tgtimes->totals.stime, cputime); -} - -static inline void thread_group_cputime_account_exec_runtime( - struct thread_group_cputime *tgtimes, - unsigned long long ns) -{ - tgtimes->totals.sum_exec_runtime += ns; -} - -#endif /* CONFIG_SMP */ - -static inline void account_group_user_time(struct task_struct *tsk, - cputime_t cputime) -{ - struct signal_struct *sig; - - sig = tsk->signal; - if (likely(sig)) - thread_group_cputime_account_user(&sig->cputime, cputime); -} - -static inline void account_group_system_time(struct task_struct *tsk, - cputime_t cputime) -{ - struct signal_struct *sig; - - sig = tsk->signal; - if (likely(sig)) - thread_group_cputime_account_system(&sig->cputime, cputime); -} - -static inline void account_group_exec_runtime(struct task_struct *tsk, - unsigned long long ns) -{ - struct signal_struct *sig; - - sig = tsk->signal; - if (likely(sig)) - thread_group_cputime_account_exec_runtime(&sig->cputime, ns); + free_percpu(sig->cputime.totals); } /* diff --git a/kernel/fork.c b/kernel/fork.c index 1181b9aac48..021ae012cc7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -791,7 +791,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) int ret; if (clone_flags & CLONE_THREAD) { - ret = thread_group_cputime_clone_thread(current, tsk); + ret = thread_group_cputime_clone_thread(current); if (likely(!ret)) { atomic_inc(¤t->signal->count); atomic_inc(¤t->signal->live); @@ -834,9 +834,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0; sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0; task_io_accounting_init(&sig->ioac); - INIT_LIST_HEAD(&sig->cpu_timers[0]); - INIT_LIST_HEAD(&sig->cpu_timers[1]); - INIT_LIST_HEAD(&sig->cpu_timers[2]); taskstats_tgid_init(sig); task_lock(current->group_leader); diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 9a7ea049fcd..153dcb2639c 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -7,50 +7,46 @@ #include #include #include +#include -#ifdef CONFIG_SMP /* - * Allocate the thread_group_cputime structure appropriately for SMP kernels - * and fill in the current values of the fields. Called from copy_signal() - * via thread_group_cputime_clone_thread() when adding a second or subsequent + * Allocate the thread_group_cputime structure appropriately and fill in the + * current values of the fields. Called from copy_signal() via + * thread_group_cputime_clone_thread() when adding a second or subsequent * thread to a thread group. Assumes interrupts are enabled when called. */ -int thread_group_cputime_alloc_smp(struct task_struct *tsk) +int thread_group_cputime_alloc(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; struct task_cputime *cputime; /* * If we have multiple threads and we don't already have a - * per-CPU task_cputime struct, allocate one and fill it in with - * the times accumulated so far. + * per-CPU task_cputime struct (checked in the caller), allocate + * one and fill it in with the times accumulated so far. We may + * race with another thread so recheck after we pick up the sighand + * lock. */ - if (sig->cputime.totals) - return 0; cputime = alloc_percpu(struct task_cputime); if (cputime == NULL) return -ENOMEM; - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); if (sig->cputime.totals) { spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); free_percpu(cputime); return 0; } sig->cputime.totals = cputime; - cputime = per_cpu_ptr(sig->cputime.totals, get_cpu()); + cputime = per_cpu_ptr(sig->cputime.totals, smp_processor_id()); cputime->utime = tsk->utime; cputime->stime = tsk->stime; cputime->sum_exec_runtime = tsk->se.sum_exec_runtime; - put_cpu_no_resched(); spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); return 0; } /** - * thread_group_cputime_smp - Sum the thread group time fields across all CPUs. + * thread_group_cputime - Sum the thread group time fields across all CPUs. * * @tsk: The task we use to identify the thread group. * @times: task_cputime structure in which we return the summed fields. @@ -58,7 +54,7 @@ int thread_group_cputime_alloc_smp(struct task_struct *tsk) * Walk the list of CPUs to sum the per-CPU time fields in the thread group * time structure. */ -void thread_group_cputime_smp( +void thread_group_cputime( struct task_struct *tsk, struct task_cputime *times) { @@ -83,8 +79,6 @@ void thread_group_cputime_smp( } } -#endif /* CONFIG_SMP */ - /* * Called after updating RLIMIT_CPU to set timer expiration if necessary. */ @@ -300,7 +294,7 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, cpu->cpu = virt_ticks(p); break; case CPUCLOCK_SCHED: - cpu->sched = task_sched_runtime(p); + cpu->sched = p->se.sum_exec_runtime + task_delta_exec(p); break; } return 0; @@ -309,16 +303,15 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, /* * Sample a process (thread group) clock for the given group_leader task. * Must be called with tasklist_lock held for reading. - * Must be called with tasklist_lock held for reading, and p->sighand->siglock. */ -static int cpu_clock_sample_group_locked(unsigned int clock_idx, - struct task_struct *p, - union cpu_time_count *cpu) +static int cpu_clock_sample_group(const clockid_t which_clock, + struct task_struct *p, + union cpu_time_count *cpu) { struct task_cputime cputime; thread_group_cputime(p, &cputime); - switch (clock_idx) { + switch (which_clock) { default: return -EINVAL; case CPUCLOCK_PROF: @@ -328,29 +321,12 @@ static int cpu_clock_sample_group_locked(unsigned int clock_idx, cpu->cpu = cputime.utime; break; case CPUCLOCK_SCHED: - cpu->sched = thread_group_sched_runtime(p); + cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p); break; } return 0; } -/* - * Sample a process (thread group) clock for the given group_leader task. - * Must be called with tasklist_lock held for reading. - */ -static int cpu_clock_sample_group(const clockid_t which_clock, - struct task_struct *p, - union cpu_time_count *cpu) -{ - int ret; - unsigned long flags; - spin_lock_irqsave(&p->sighand->siglock, flags); - ret = cpu_clock_sample_group_locked(CPUCLOCK_WHICH(which_clock), p, - cpu); - spin_unlock_irqrestore(&p->sighand->siglock, flags); - return ret; -} - int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp) { @@ -1324,29 +1300,37 @@ static inline int task_cputime_expired(const struct task_cputime *sample, * fastpath_timer_check - POSIX CPU timers fast path. * * @tsk: The task (thread) being checked. - * @sig: The signal pointer for that task. * - * If there are no timers set return false. Otherwise snapshot the task and - * thread group timers, then compare them with the corresponding expiration - # times. Returns true if a timer has expired, else returns false. + * Check the task and thread group timers. If both are zero (there are no + * timers set) return false. Otherwise snapshot the task and thread group + * timers and compare them with the corresponding expiration times. Return + * true if a timer has expired, else return false. */ -static inline int fastpath_timer_check(struct task_struct *tsk, - struct signal_struct *sig) +static inline int fastpath_timer_check(struct task_struct *tsk) { - struct task_cputime task_sample = { - .utime = tsk->utime, - .stime = tsk->stime, - .sum_exec_runtime = tsk->se.sum_exec_runtime - }; - struct task_cputime group_sample; + struct signal_struct *sig = tsk->signal; - if (task_cputime_zero(&tsk->cputime_expires) && - task_cputime_zero(&sig->cputime_expires)) + if (unlikely(!sig)) return 0; - if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) - return 1; - thread_group_cputime(tsk, &group_sample); - return task_cputime_expired(&group_sample, &sig->cputime_expires); + + if (!task_cputime_zero(&tsk->cputime_expires)) { + struct task_cputime task_sample = { + .utime = tsk->utime, + .stime = tsk->stime, + .sum_exec_runtime = tsk->se.sum_exec_runtime + }; + + if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) + return 1; + } + if (!task_cputime_zero(&sig->cputime_expires)) { + struct task_cputime group_sample; + + thread_group_cputime(tsk, &group_sample); + if (task_cputime_expired(&group_sample, &sig->cputime_expires)) + return 1; + } + return 0; } /* @@ -1358,43 +1342,34 @@ void run_posix_cpu_timers(struct task_struct *tsk) { LIST_HEAD(firing); struct k_itimer *timer, *next; - struct signal_struct *sig; - struct sighand_struct *sighand; - unsigned long flags; BUG_ON(!irqs_disabled()); - /* Pick up tsk->signal and make sure it's valid. */ - sig = tsk->signal; /* * The fast path checks that there are no expired thread or thread - * group timers. If that's so, just return. Also check that - * tsk->signal is non-NULL; this probably can't happen but cover the - * possibility anyway. + * group timers. If that's so, just return. */ - if (unlikely(!sig) || !fastpath_timer_check(tsk, sig)) + if (!fastpath_timer_check(tsk)) return; - sighand = lock_task_sighand(tsk, &flags); - if (likely(sighand)) { - /* - * Here we take off tsk->signal->cpu_timers[N] and - * tsk->cpu_timers[N] all the timers that are firing, and - * put them on the firing list. - */ - check_thread_timers(tsk, &firing); - check_process_timers(tsk, &firing); + spin_lock(&tsk->sighand->siglock); + /* + * Here we take off tsk->signal->cpu_timers[N] and + * tsk->cpu_timers[N] all the timers that are firing, and + * put them on the firing list. + */ + check_thread_timers(tsk, &firing); + check_process_timers(tsk, &firing); - /* - * We must release these locks before taking any timer's lock. - * There is a potential race with timer deletion here, as the - * siglock now protects our private firing list. We have set - * the firing flag in each timer, so that a deletion attempt - * that gets the timer lock before we do will give it up and - * spin until we've taken care of that timer below. - */ - } - unlock_task_sighand(tsk, &flags); + /* + * We must release these locks before taking any timer's lock. + * There is a potential race with timer deletion here, as the + * siglock now protects our private firing list. We have set + * the firing flag in each timer, so that a deletion attempt + * that gets the timer lock before we do will give it up and + * spin until we've taken care of that timer below. + */ + spin_unlock(&tsk->sighand->siglock); /* * Now that all the timers on our list have the firing flag, @@ -1433,7 +1408,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, struct list_head *head; BUG_ON(clock_idx == CPUCLOCK_SCHED); - cpu_clock_sample_group_locked(clock_idx, tsk, &now); + cpu_clock_sample_group(clock_idx, tsk, &now); if (oldval) { if (!cputime_eq(*oldval, cputime_zero)) { diff --git a/kernel/sched.c b/kernel/sched.c index c51b5d27666..260c22cc530 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4039,55 +4039,22 @@ EXPORT_PER_CPU_SYMBOL(kstat); /* * Return any ns on the sched_clock that have not yet been banked in * @p in case that task is currently running. - * - * Called with task_rq_lock() held on @rq. */ -static unsigned long long task_delta_exec(struct task_struct *p, struct rq *rq) +unsigned long long task_delta_exec(struct task_struct *p) { + struct rq *rq; + unsigned long flags; + u64 ns = 0; + + rq = task_rq_lock(p, &flags); if (task_current(rq, p)) { u64 delta_exec; update_rq_clock(rq); delta_exec = rq->clock - p->se.exec_start; if ((s64)delta_exec > 0) - return delta_exec; + ns = delta_exec; } - return 0; -} - -/* - * Return p->sum_exec_runtime plus any more ns on the sched_clock - * that have not yet been banked in case the task is currently running. - */ -unsigned long long task_sched_runtime(struct task_struct *p) -{ - unsigned long flags; - u64 ns; - struct rq *rq; - - rq = task_rq_lock(p, &flags); - ns = p->se.sum_exec_runtime + task_delta_exec(p, rq); - task_rq_unlock(rq, &flags); - - return ns; -} - -/* - * Return sum_exec_runtime for the thread group plus any more ns on the - * sched_clock that have not yet been banked in case the task is currently - * running. - */ -unsigned long long thread_group_sched_runtime(struct task_struct *p) -{ - unsigned long flags; - u64 ns; - struct rq *rq; - struct task_cputime totals; - - rq = task_rq_lock(p, &flags); - thread_group_cputime(p, &totals); - ns = totals.sum_exec_runtime + task_delta_exec(p, rq); - task_rq_unlock(rq, &flags); return ns; } diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index 8385d43987e..d6903bd0c7a 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -270,3 +270,139 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next) #define sched_info_switch(t, next) do { } while (0) #endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */ +/* + * The following are functions that support scheduler-internal time accounting. + * These functions are generally called at the timer tick. None of this depends + * on CONFIG_SCHEDSTATS. + */ + +#ifdef CONFIG_SMP + +/** + * thread_group_cputime_account_user - Maintain utime for a thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @cputime: Time value by which to increment the utime field of that + * structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the utime field there. + */ +static inline void thread_group_cputime_account_user( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->utime = cputime_add(times->utime, cputime); + put_cpu_no_resched(); + } +} + +/** + * thread_group_cputime_account_system - Maintain stime for a thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @cputime: Time value by which to increment the stime field of that + * structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the stime field there. + */ +static inline void thread_group_cputime_account_system( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->stime = cputime_add(times->stime, cputime); + put_cpu_no_resched(); + } +} + +/** + * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a + * thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @ns: Time value by which to increment the sum_exec_runtime field + * of that structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the sum_exec_runtime field there. + */ +static inline void thread_group_cputime_account_exec_runtime( + struct thread_group_cputime *tgtimes, + unsigned long long ns) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->sum_exec_runtime += ns; + put_cpu_no_resched(); + } +} + +#else /* CONFIG_SMP */ + +static inline void thread_group_cputime_account_user( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + tgtimes->totals->utime = cputime_add(tgtimes->totals->utime, cputime); +} + +static inline void thread_group_cputime_account_system( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + tgtimes->totals->stime = cputime_add(tgtimes->totals->stime, cputime); +} + +static inline void thread_group_cputime_account_exec_runtime( + struct thread_group_cputime *tgtimes, + unsigned long long ns) +{ + tgtimes->totals->sum_exec_runtime += ns; +} + +#endif /* CONFIG_SMP */ + +/* + * These are the generic time-accounting routines that use the above + * functions. They are the functions actually called by the scheduler. + */ +static inline void account_group_user_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_user(&sig->cputime, cputime); +} + +static inline void account_group_system_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_system(&sig->cputime, cputime); +} + +static inline void account_group_exec_runtime(struct task_struct *tsk, + unsigned long long ns) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_exec_runtime(&sig->cputime, ns); +} -- cgit v1.2.3-70-g09d2 From 7086efe1c1536f6bc160e7d60a9bfd645b91f279 Mon Sep 17 00:00:00 2001 From: Frank Mayhar Date: Fri, 12 Sep 2008 09:54:39 -0700 Subject: timers: fix itimer/many thread hang, v3 - fix UP lockup - another set of UP/SMP cleanups and simplifications Signed-off-by: Frank Mayhar Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 - kernel/sched.c | 1 - kernel/sched_stats.h | 126 +++++++++++++++----------------------------------- 3 files changed, 38 insertions(+), 90 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index b982fb48c8f..23d9d546454 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2134,7 +2134,6 @@ static inline int thread_group_cputime_clone_thread(struct task_struct *curr) return thread_group_cputime_alloc(curr); } - static inline void thread_group_cputime_free(struct signal_struct *sig) { free_percpu(sig->cputime.totals); diff --git a/kernel/sched.c b/kernel/sched.c index 260c22cc530..29a3152c45d 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4046,7 +4046,6 @@ unsigned long long task_delta_exec(struct task_struct *p) unsigned long flags; u64 ns = 0; - rq = task_rq_lock(p, &flags); if (task_current(rq, p)) { u64 delta_exec; diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index d6903bd0c7a..b8c156979cf 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -276,133 +276,83 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next) * on CONFIG_SCHEDSTATS. */ -#ifdef CONFIG_SMP - /** - * thread_group_cputime_account_user - Maintain utime for a thread group. + * account_group_user_time - Maintain utime for a thread group. * - * @tgtimes: Pointer to thread_group_cputime structure. - * @cputime: Time value by which to increment the utime field of that - * structure. + * @tsk: Pointer to task structure. + * @cputime: Time value by which to increment the utime field of the + * thread_group_cputime structure. * * If thread group time is being maintained, get the structure for the * running CPU and update the utime field there. */ -static inline void thread_group_cputime_account_user( - struct thread_group_cputime *tgtimes, - cputime_t cputime) +static inline void account_group_user_time(struct task_struct *tsk, + cputime_t cputime) { - if (tgtimes->totals) { + struct signal_struct *sig; + + sig = tsk->signal; + if (unlikely(!sig)) + return; + if (sig->cputime.totals) { struct task_cputime *times; - times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times = per_cpu_ptr(sig->cputime.totals, get_cpu()); times->utime = cputime_add(times->utime, cputime); put_cpu_no_resched(); } } /** - * thread_group_cputime_account_system - Maintain stime for a thread group. + * account_group_system_time - Maintain stime for a thread group. * - * @tgtimes: Pointer to thread_group_cputime structure. - * @cputime: Time value by which to increment the stime field of that - * structure. + * @tsk: Pointer to task structure. + * @cputime: Time value by which to increment the stime field of the + * thread_group_cputime structure. * * If thread group time is being maintained, get the structure for the * running CPU and update the stime field there. */ -static inline void thread_group_cputime_account_system( - struct thread_group_cputime *tgtimes, - cputime_t cputime) +static inline void account_group_system_time(struct task_struct *tsk, + cputime_t cputime) { - if (tgtimes->totals) { + struct signal_struct *sig; + + sig = tsk->signal; + if (unlikely(!sig)) + return; + if (sig->cputime.totals) { struct task_cputime *times; - times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times = per_cpu_ptr(sig->cputime.totals, get_cpu()); times->stime = cputime_add(times->stime, cputime); put_cpu_no_resched(); } } /** - * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a - * thread group. + * account_group_exec_runtime - Maintain exec runtime for a thread group. * - * @tgtimes: Pointer to thread_group_cputime structure. + * @tsk: Pointer to task structure. * @ns: Time value by which to increment the sum_exec_runtime field - * of that structure. + * of the thread_group_cputime structure. * * If thread group time is being maintained, get the structure for the * running CPU and update the sum_exec_runtime field there. */ -static inline void thread_group_cputime_account_exec_runtime( - struct thread_group_cputime *tgtimes, - unsigned long long ns) +static inline void account_group_exec_runtime(struct task_struct *tsk, + unsigned long long ns) { - if (tgtimes->totals) { + struct signal_struct *sig; + + sig = tsk->signal; + if (unlikely(!sig)) + return; + if (sig->cputime.totals) { struct task_cputime *times; - times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times = per_cpu_ptr(sig->cputime.totals, get_cpu()); times->sum_exec_runtime += ns; put_cpu_no_resched(); } } - -#else /* CONFIG_SMP */ - -static inline void thread_group_cputime_account_user( - struct thread_group_cputime *tgtimes, - cputime_t cputime) -{ - tgtimes->totals->utime = cputime_add(tgtimes->totals->utime, cputime); -} - -static inline void thread_group_cputime_account_system( - struct thread_group_cputime *tgtimes, - cputime_t cputime) -{ - tgtimes->totals->stime = cputime_add(tgtimes->totals->stime, cputime); -} - -static inline void thread_group_cputime_account_exec_runtime( - struct thread_group_cputime *tgtimes, - unsigned long long ns) -{ - tgtimes->totals->sum_exec_runtime += ns; -} - -#endif /* CONFIG_SMP */ - -/* - * These are the generic time-accounting routines that use the above - * functions. They are the functions actually called by the scheduler. - */ -static inline void account_group_user_time(struct task_struct *tsk, - cputime_t cputime) -{ - struct signal_struct *sig; - - sig = tsk->signal; - if (likely(sig)) - thread_group_cputime_account_user(&sig->cputime, cputime); -} - -static inline void account_group_system_time(struct task_struct *tsk, - cputime_t cputime) -{ - struct signal_struct *sig; - - sig = tsk->signal; - if (likely(sig)) - thread_group_cputime_account_system(&sig->cputime, cputime); -} - -static inline void account_group_exec_runtime(struct task_struct *tsk, - unsigned long long ns) -{ - struct signal_struct *sig; - - sig = tsk->signal; - if (likely(sig)) - thread_group_cputime_account_exec_runtime(&sig->cputime, ns); -} -- cgit v1.2.3-70-g09d2 From e575f111dc0f27044e170580e7de50985ab3e011 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Sat, 18 Oct 2008 20:27:08 -0700 Subject: coredump_filter: add hugepage dumping Presently hugepage's vma has a VM_RESERVED flag in order not to be swapped. But a VM_RESERVED vma isn't core dumped because this flag is often used for some kernel vmas (e.g. vmalloc, sound related). Thus hugepages are never dumped and it can't be debugged easily. Many developers want hugepages to be included into core-dump. However, We can't read generic VM_RESERVED area because this area is often IO mapping area. then these area reading may change device state. it is definitly undesiable side-effect. So adding a hugepage specific bit to the coredump filter is better. It will be able to hugepage core dumping and doesn't cause any side-effect to any i/o devices. In additional, libhugetlb use hugetlb private mapping pages as anonymous page. Then, hugepage private mapping pages should be core dumped by default. Then, /proc/[pid]/core_dump_filter has two new bits. - bit 5 mean hugetlb private mapping pages are dumped or not. (default: yes) - bit 6 mean hugetlb shared mapping pages are dumped or not. (default: no) I tested by following method. % ulimit -c unlimited % ./crash_hugepage 50 % ./crash_hugepage 50 -p % ls -lh % gdb ./crash_hugepage core % % echo 0x43 > /proc/self/coredump_filter % ./crash_hugepage 50 % ./crash_hugepage 50 -p % ls -lh % gdb ./crash_hugepage core #include #include #include #include #include #include "hugetlbfs.h" int main(int argc, char** argv){ char* p; int ch; int mmap_flags = MAP_SHARED; int fd; int nr_pages; while((ch = getopt(argc, argv, "p")) != -1) { switch (ch) { case 'p': mmap_flags &= ~MAP_SHARED; mmap_flags |= MAP_PRIVATE; break; default: /* nothing*/ break; } } argc -= optind; argv += optind; if (argc == 0){ printf("need # of pages\n"); exit(1); } nr_pages = atoi(argv[0]); if (nr_pages < 2) { printf("nr_pages must >2\n"); exit(1); } fd = hugetlbfs_unlinked_fd(); p = mmap(NULL, nr_pages * gethugepagesize(), PROT_READ|PROT_WRITE, mmap_flags, fd, 0); sleep(2); *(p + gethugepagesize()) = 1; /* COW */ sleep(2); /* crash! */ *(int*)0 = 1; return 0; } Signed-off-by: KOSAKI Motohiro Reviewed-by: Kawai Hidehiro Cc: Hugh Dickins Cc: William Irwin Cc: Adam Litke Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.txt | 15 ++++++++++----- fs/binfmt_elf.c | 12 ++++++++++-- include/linux/sched.h | 7 +++++-- 3 files changed, 25 insertions(+), 9 deletions(-) (limited to 'include/linux/sched.h') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index c032bf39e8b..02cb7faeed6 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -2412,24 +2412,29 @@ will be dumped when the process is dumped. coredump_filter is a bitmask of memory types. If a bit of the bitmask is set, memory segments of the corresponding memory type are dumped, otherwise they are not dumped. -The following 4 memory types are supported: +The following 7 memory types are supported: - (bit 0) anonymous private memory - (bit 1) anonymous shared memory - (bit 2) file-backed private memory - (bit 3) file-backed shared memory - (bit 4) ELF header pages in file-backed private memory areas (it is effective only if the bit 2 is cleared) + - (bit 5) hugetlb private memory + - (bit 6) hugetlb shared memory Note that MMIO pages such as frame buffer are never dumped and vDSO pages are always dumped regardless of the bitmask status. -Default value of coredump_filter is 0x3; this means all anonymous memory -segments are dumped. + Note bit 0-4 doesn't effect any hugetlb memory. hugetlb memory are only + effected by bit 5-6. + +Default value of coredump_filter is 0x23; this means all anonymous memory +segments and hugetlb private memory are dumped. If you don't want to dump all shared memory segments attached to pid 1234, -write 1 to the process's proc file. +write 0x21 to the process's proc file. - $ echo 0x1 > /proc/1234/coredump_filter + $ echo 0x21 > /proc/1234/coredump_filter When a new process is created, the process inherits the bitmask status from its parent. It is useful to set up coredump_filter before the program runs. diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index c76afa26edf..e2159063198 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1156,16 +1156,24 @@ static int dump_seek(struct file *file, loff_t off) static unsigned long vma_dump_size(struct vm_area_struct *vma, unsigned long mm_flags) { +#define FILTER(type) (mm_flags & (1UL << MMF_DUMP_##type)) + /* The vma can be set up to tell us the answer directly. */ if (vma->vm_flags & VM_ALWAYSDUMP) goto whole; + /* Hugetlb memory check */ + if (vma->vm_flags & VM_HUGETLB) { + if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED)) + goto whole; + if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE)) + goto whole; + } + /* Do not dump I/O mapped devices or special mappings */ if (vma->vm_flags & (VM_IO | VM_RESERVED)) return 0; -#define FILTER(type) (mm_flags & (1UL << MMF_DUMP_##type)) - /* By default, dump shared memory if mapped from an anonymous file. */ if (vma->vm_flags & VM_SHARED) { if (vma->vm_file->f_path.dentry->d_inode->i_nlink == 0 ? diff --git a/include/linux/sched.h b/include/linux/sched.h index c226c7b8294..017cc914ef1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -403,12 +403,15 @@ extern int get_dumpable(struct mm_struct *mm); #define MMF_DUMP_MAPPED_PRIVATE 4 #define MMF_DUMP_MAPPED_SHARED 5 #define MMF_DUMP_ELF_HEADERS 6 +#define MMF_DUMP_HUGETLB_PRIVATE 7 +#define MMF_DUMP_HUGETLB_SHARED 8 #define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS -#define MMF_DUMP_FILTER_BITS 5 +#define MMF_DUMP_FILTER_BITS 7 #define MMF_DUMP_FILTER_MASK \ (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) #define MMF_DUMP_FILTER_DEFAULT \ - ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED)) + ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\ + (1 << MMF_DUMP_HUGETLB_PRIVATE)) struct sighand_struct { atomic_t count; -- cgit v1.2.3-70-g09d2 From 656eb2cd5da153762f2e8419ca117ce12ef522c3 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Sat, 18 Oct 2008 20:28:23 -0700 Subject: add CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS This adds a kconfig option to change the /proc/PID/coredump_filter default. Fedora has been carrying a trivial patch to change the hard-wired value for this default, since Fedora 8. The default default can't change safely because there are old GDB versions out there (all before 6.7) that are confused by the core dump files created by the MMF_DUMP_ELF_HEADERS setting. Signed-off-by: Roland McGrath Cc: Michael Kerrisk Cc: Oleg Nesterov Cc: Alan Cox Cc: Andi Kleen Cc: KOSAKI Motohiro Cc: Kawai Hidehiro Cc: Ingo Molnar Cc: David Jones Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/Kconfig.binfmt | 22 ++++++++++++++++++++++ include/linux/sched.h | 8 +++++++- 2 files changed, 29 insertions(+), 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 801db134181..ce9fb3fbfae 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -40,6 +40,28 @@ config BINFMT_ELF_FDPIC It is also possible to run FDPIC ELF binaries on MMU linux also. +config CORE_DUMP_DEFAULT_ELF_HEADERS + bool "Write ELF core dumps with partial segments" + default n + depends on BINFMT_ELF + help + ELF core dump files describe each memory mapping of the crashed + process, and can contain or omit the memory contents of each one. + The contents of an unmodified text mapping are omitted by default. + + For an unmodified text mapping of an ELF object, including just + the first page of the file in a core dump makes it possible to + identify the build ID bits in the file, without paying the i/o + cost and disk space to dump all the text. However, versions of + GDB before 6.7 are confused by ELF core dump files in this format. + + The core dump behavior can be controlled per process using + the /proc/PID/coredump_filter pseudo-file; this setting is + inherited. See Documentation/filesystems/proc.txt for details. + + This config option changes the default setting of coredump_filter + seen at boot time. If unsure, say N. + config BINFMT_FLAT bool "Kernel support for flat binaries" depends on !MMU && (!FRV || BROKEN) diff --git a/include/linux/sched.h b/include/linux/sched.h index 017cc914ef1..f52dbd3587a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -411,7 +411,13 @@ extern int get_dumpable(struct mm_struct *mm); (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) #define MMF_DUMP_FILTER_DEFAULT \ ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\ - (1 << MMF_DUMP_HUGETLB_PRIVATE)) + (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF) + +#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS +# define MMF_DUMP_MASK_DEFAULT_ELF (1 << MMF_DUMP_ELF_HEADERS) +#else +# define MMF_DUMP_MASK_DEFAULT_ELF 0 +#endif struct sighand_struct { atomic_t count; -- cgit v1.2.3-70-g09d2