From 24f1e32c60c45c89a997c73395b69c8af6f0a84e Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 9 Sep 2009 19:22:48 +0200 Subject: hw-breakpoints: Rewrite the hw-breakpoints layer on top of perf events This patch rebase the implementation of the breakpoints API on top of perf events instances. Each breakpoints are now perf events that handle the register scheduling, thread/cpu attachment, etc.. The new layering is now made as follows: ptrace kgdb ftrace perf syscall \ | / / \ | / / / Core breakpoint API / / | / | / Breakpoints perf events | | Breakpoints PMU ---- Debug Register constraints handling (Part of core breakpoint API) | | Hardware debug registers Reasons of this rewrite: - Use the centralized/optimized pmu registers scheduling, implying an easier arch integration - More powerful register handling: perf attributes (pinned/flexible events, exclusive/non-exclusive, tunable period, etc...) Impact: - New perf ABI: the hardware breakpoints counters - Ptrace breakpoints setting remains tricky and still needs some per thread breakpoints references. Todo (in the order): - Support breakpoints perf counter events for perf tools (ie: implement perf_bpcounter_event()) - Support from perf tools Changes in v2: - Follow the perf "event " rename - The ptrace regression have been fixed (ptrace breakpoint perf events weren't released when a task ended) - Drop the struct hw_breakpoint and store generic fields in perf_event_attr. - Separate core and arch specific headers, drop asm-generic/hw_breakpoint.h and create linux/hw_breakpoint.h - Use new generic len/type for breakpoint - Handle off case: when breakpoints api is not supported by an arch Changes in v3: - Fix broken CONFIG_KVM, we need to propagate the breakpoint api changes to kvm when we exit the guest and restore the bp registers to the host. Changes in v4: - Drop the hw_breakpoint_restore() stub as it is only used by KVM - EXPORT_SYMBOL_GPL hw_breakpoint_restore() as KVM can be built as a module - Restore the breakpoints unconditionally on kvm guest exit: TIF_DEBUG_THREAD doesn't anymore cover every cases of running breakpoints and vcpu->arch.switch_db_regs might not always be set when the guest used debug registers. (Waiting for a reliable optimization) Changes in v5: - Split-up the asm-generic/hw-breakpoint.h moving to linux/hw_breakpoint.h into a separate patch - Optimize the breakpoints restoring while switching from kvm guest to host. We only want to restore the state if we have active breakpoints to the host, otherwise we don't care about messed-up address registers. - Add asm/hw_breakpoint.h to Kbuild - Fix bad breakpoint type in trace_selftest.c Changes in v6: - Fix wrong header inclusion in trace.h (triggered a build error with CONFIG_FTRACE_SELFTEST Signed-off-by: Frederic Weisbecker Cc: Prasad Cc: Alan Stern Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Steven Rostedt Cc: Ingo Molnar Cc: Jan Kiszka Cc: Jiri Slaby Cc: Li Zefan Cc: Avi Kivity Cc: Paul Mackerras Cc: Mike Galbraith Cc: Masami Hiramatsu Cc: Paul Mundt --- kernel/exit.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index e61891f80123..266f8920628a 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -49,6 +49,7 @@ #include #include #include +#include #include #include @@ -979,6 +980,10 @@ NORET_TYPE void do_exit(long code) proc_exit_connector(tsk); + /* + * FIXME: do that only when needed, using sched_exit tracepoint + */ + flush_ptrace_hw_breakpoint(tsk); /* * Flush inherited counters to the parent - before the parent * gets woken up by child-exit notifications. -- cgit v1.2.3 From d180c5bccec02612256fd8076ff3c1fac3429553 Mon Sep 17 00:00:00 2001 From: Hidetoshi Seto Date: Thu, 26 Nov 2009 14:48:30 +0900 Subject: sched: Introduce task_times() to replace task_{u,s}time() pair Functions task_{u,s}time() are called in pair in almost all cases. However task_stime() is implemented to call task_utime() from its inside, so such paired calls run task_utime() twice. It means we do heavy divisions (div_u64 + do_div) twice to get utime and stime which can be obtained at same time by one set of divisions. This patch introduces a function task_times(*tsk, *utime, *stime) to retrieve utime and stime at once in better, optimized way. Signed-off-by: Hidetoshi Seto Acked-by: Peter Zijlstra Cc: Stanislaw Gruszka Cc: Spencer Candland Cc: Oleg Nesterov Cc: Balbir Singh Cc: Americo Wang LKML-Reference: <4B0E16AE.906@jp.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/exit.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index f7864ac2ecc1..29068ab2670a 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -91,6 +91,8 @@ static void __exit_signal(struct task_struct *tsk) if (atomic_dec_and_test(&sig->count)) posix_cpu_timers_exit_group(tsk); else { + cputime_t utime, stime; + /* * If there is any task waiting for the group exit * then notify it: @@ -110,8 +112,9 @@ static void __exit_signal(struct task_struct *tsk) * We won't ever get here for the group leader, since it * will have been the last reference on the signal_struct. */ - sig->utime = cputime_add(sig->utime, task_utime(tsk)); - sig->stime = cputime_add(sig->stime, task_stime(tsk)); + task_times(tsk, &utime, &stime); + sig->utime = cputime_add(sig->utime, utime); + sig->stime = cputime_add(sig->stime, stime); sig->gtime = cputime_add(sig->gtime, task_gtime(tsk)); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; -- cgit v1.2.3 From d5b7c78e975302a1bab28263266c39ecb71acad4 Mon Sep 17 00:00:00 2001 From: Hidetoshi Seto Date: Thu, 26 Nov 2009 14:49:05 +0900 Subject: sched: Remove task_{u,s,g}time() Now all task_{u,s}time() pairs are replaced by task_times(). And task_gtime() is too simple to be an inline function. Cleanup them all. Signed-off-by: Hidetoshi Seto Acked-by: Peter Zijlstra Cc: Stanislaw Gruszka Cc: Spencer Candland Cc: Oleg Nesterov Cc: Balbir Singh Cc: Americo Wang LKML-Reference: <4B0E16D1.70902@jp.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/exit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 29068ab2670a..2eaf68b634e3 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -115,7 +115,7 @@ static void __exit_signal(struct task_struct *tsk) task_times(tsk, &utime, &stime); sig->utime = cputime_add(sig->utime, utime); sig->stime = cputime_add(sig->stime, stime); - sig->gtime = cputime_add(sig->gtime, task_gtime(tsk)); + sig->gtime = cputime_add(sig->gtime, tsk->gtime); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; sig->nvcsw += tsk->nvcsw; -- cgit v1.2.3 From 0cf55e1ec08bb5a22e068309e2d8ba1180ab4239 Mon Sep 17 00:00:00 2001 From: Hidetoshi Seto Date: Wed, 2 Dec 2009 17:28:07 +0900 Subject: sched, cputime: Introduce thread_group_times() This is a real fix for problem of utime/stime values decreasing described in the thread: http://lkml.org/lkml/2009/11/3/522 Now cputime is accounted in the following way: - {u,s}time in task_struct are increased every time when the thread is interrupted by a tick (timer interrupt). - When a thread exits, its {u,s}time are added to signal->{u,s}time, after adjusted by task_times(). - When all threads in a thread_group exits, accumulated {u,s}time (and also c{u,s}time) in signal struct are added to c{u,s}time in signal struct of the group's parent. So {u,s}time in task struct are "raw" tick count, while {u,s}time and c{u,s}time in signal struct are "adjusted" values. And accounted values are used by: - task_times(), to get cputime of a thread: This function returns adjusted values that originates from raw {u,s}time and scaled by sum_exec_runtime that accounted by CFS. - thread_group_cputime(), to get cputime of a thread group: This function returns sum of all {u,s}time of living threads in the group, plus {u,s}time in the signal struct that is sum of adjusted cputimes of all exited threads belonged to the group. The problem is the return value of thread_group_cputime(), because it is mixed sum of "raw" value and "adjusted" value: group's {u,s}time = foreach(thread){{u,s}time} + exited({u,s}time) This misbehavior can break {u,s}time monotonicity. Assume that if there is a thread that have raw values greater than adjusted values (e.g. interrupted by 1000Hz ticks 50 times but only runs 45ms) and if it exits, cputime will decrease (e.g. -5ms). To fix this, we could do: group's {u,s}time = foreach(t){task_times(t)} + exited({u,s}time) But task_times() contains hard divisions, so applying it for every thread should be avoided. This patch fixes the above problem in the following way: - Modify thread's exit (= __exit_signal()) not to use task_times(). It means {u,s}time in signal struct accumulates raw values instead of adjusted values. As the result it makes thread_group_cputime() to return pure sum of "raw" values. - Introduce a new function thread_group_times(*task, *utime, *stime) that converts "raw" values of thread_group_cputime() to "adjusted" values, in same calculation procedure as task_times(). - Modify group's exit (= wait_task_zombie()) to use this introduced thread_group_times(). It make c{u,s}time in signal struct to have adjusted values like before this patch. - Replace some thread_group_cputime() by thread_group_times(). This replacements are only applied where conveys the "adjusted" cputime to users, and where already uses task_times() near by it. (i.e. sys_times(), getrusage(), and /proc//stat.) This patch have a positive side effect: - Before this patch, if a group contains many short-life threads (e.g. runs 0.9ms and not interrupted by ticks), the group's cputime could be invisible since thread's cputime was accumulated after adjusted: imagine adjustment function as adj(ticks, runtime), {adj(0, 0.9) + adj(0, 0.9) + ....} = {0 + 0 + ....} = 0. After this patch it will not happen because the adjustment is applied after accumulated. v2: - remove if()s, put new variables into signal_struct. Signed-off-by: Hidetoshi Seto Acked-by: Peter Zijlstra Cc: Spencer Candland Cc: Americo Wang Cc: Oleg Nesterov Cc: Balbir Singh Cc: Stanislaw Gruszka LKML-Reference: <4B162517.8040909@jp.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/exit.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 2eaf68b634e3..b221ad65fd20 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -91,8 +91,6 @@ static void __exit_signal(struct task_struct *tsk) if (atomic_dec_and_test(&sig->count)) posix_cpu_timers_exit_group(tsk); else { - cputime_t utime, stime; - /* * If there is any task waiting for the group exit * then notify it: @@ -112,9 +110,8 @@ static void __exit_signal(struct task_struct *tsk) * We won't ever get here for the group leader, since it * will have been the last reference on the signal_struct. */ - task_times(tsk, &utime, &stime); - sig->utime = cputime_add(sig->utime, utime); - sig->stime = cputime_add(sig->stime, stime); + sig->utime = cputime_add(sig->utime, tsk->utime); + sig->stime = cputime_add(sig->stime, tsk->stime); sig->gtime = cputime_add(sig->gtime, tsk->gtime); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; @@ -1208,6 +1205,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) struct signal_struct *psig; struct signal_struct *sig; unsigned long maxrss; + cputime_t tgutime, tgstime; /* * The resource counters for the group leader are in its @@ -1223,20 +1221,23 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) * need to protect the access to parent->signal fields, * as other threads in the parent group can be right * here reaping other children at the same time. + * + * We use thread_group_times() to get times for the thread + * group, which consolidates times for all threads in the + * group including the group leader. */ + thread_group_times(p, &tgutime, &tgstime); spin_lock_irq(&p->real_parent->sighand->siglock); psig = p->real_parent->signal; sig = p->signal; psig->cutime = cputime_add(psig->cutime, - cputime_add(p->utime, - cputime_add(sig->utime, - sig->cutime))); + cputime_add(tgutime, + sig->cutime)); psig->cstime = cputime_add(psig->cstime, - cputime_add(p->stime, - cputime_add(sig->stime, - sig->cstime))); + cputime_add(tgstime, + sig->cstime)); psig->cgtime = cputime_add(psig->cgtime, cputime_add(p->gtime, -- cgit v1.2.3 From b69f2292063d2caf37ca9aec7d63ded203701bf3 Mon Sep 17 00:00:00 2001 From: Louis Rilling Date: Fri, 4 Dec 2009 14:52:42 +0100 Subject: block: Fix io_context leak after failure of clone with CLONE_IO With CLONE_IO, parent's io_context->nr_tasks is incremented, but never decremented whenever copy_process() fails afterwards, which prevents exit_io_context() from calling IO schedulers exit functions. Give a task_struct to exit_io_context(), and call exit_io_context() instead of put_io_context() in copy_process() cleanup path. Signed-off-by: Louis Rilling Signed-off-by: Jens Axboe --- kernel/exit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index f7864ac2ecc1..2544000125d9 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1004,7 +1004,7 @@ NORET_TYPE void do_exit(long code) tsk->flags |= PF_EXITPIDONE; if (tsk->io_context) - exit_io_context(); + exit_io_context(tsk); if (tsk->splice_pipe) __free_pipe_info(tsk->splice_pipe); -- cgit v1.2.3