From fb0459d75c1d0a4ba3cafdd2c754e7486968a676 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Fri, 25 Sep 2009 12:25:56 +0200 Subject: perf/core: Provide a kernel-internal interface to get to performance counters There are reasons for kernel code to ask for, and use, performance counters. For example, in CPU freq governors this tends to be a good idea, but there are other examples possible as well of course. This patch adds the needed bits to do enable this functionality; they have been tested in an experimental cpufreq driver that I'm working on, and the changes are all that I needed to access counters properly. [fweisbec@gmail.com: added pid to perf_event_create_kernel_counter so that we can profile a particular task too TODO: Have a better error reporting, don't just return NULL in fail case.] v2: Remove the wrong comment about the fact perf_event_create_kernel_counter must be called from a kernel thread. Signed-off-by: Arjan van de Ven Acked-by: Peter Zijlstra Cc: "K.Prasad" Cc: Alan Stern 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 Cc: Jan Kiszka Cc: Avi Kivity LKML-Reference: <20090925122556.2f8bd939@infradead.org> Signed-off-by: Frederic Weisbecker --- kernel/perf_event.c | 75 ++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 74 insertions(+), 1 deletion(-) (limited to 'kernel/perf_event.c') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 12b5ec39bf9..02d4ff041b0 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -1725,6 +1725,26 @@ static int perf_release(struct inode *inode, struct file *file) return 0; } +int perf_event_release_kernel(struct perf_event *event) +{ + struct perf_event_context *ctx = event->ctx; + + WARN_ON_ONCE(ctx->parent_ctx); + mutex_lock(&ctx->mutex); + perf_event_remove_from_context(event); + mutex_unlock(&ctx->mutex); + + mutex_lock(&event->owner->perf_event_mutex); + list_del_init(&event->owner_entry); + mutex_unlock(&event->owner->perf_event_mutex); + put_task_struct(event->owner); + + free_event(event); + + return 0; +} +EXPORT_SYMBOL_GPL(perf_event_release_kernel); + static int perf_event_read_size(struct perf_event *event) { int entry = sizeof(u64); /* value */ @@ -1750,7 +1770,7 @@ static int perf_event_read_size(struct perf_event *event) return size; } -static u64 perf_event_read_value(struct perf_event *event) +u64 perf_event_read_value(struct perf_event *event) { struct perf_event *child; u64 total = 0; @@ -1761,6 +1781,7 @@ static u64 perf_event_read_value(struct perf_event *event) return total; } +EXPORT_SYMBOL_GPL(perf_event_read_value); static int perf_event_read_entry(struct perf_event *event, u64 read_format, char __user *buf) @@ -4638,6 +4659,58 @@ err_put_context: return err; } +/** + * perf_event_create_kernel_counter + * + * @attr: attributes of the counter to create + * @cpu: cpu in which the counter is bound + * @pid: task to profile + */ +struct perf_event * +perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, + pid_t pid) +{ + struct perf_event *event; + struct perf_event_context *ctx; + int err; + + /* + * Get the target context (task or percpu): + */ + + ctx = find_get_context(pid, cpu); + if (IS_ERR(ctx)) + return NULL ; + + event = perf_event_alloc(attr, cpu, ctx, NULL, + NULL, GFP_KERNEL); + err = PTR_ERR(event); + if (IS_ERR(event)) + goto err_put_context; + + event->filp = NULL; + WARN_ON_ONCE(ctx->parent_ctx); + mutex_lock(&ctx->mutex); + perf_install_in_context(ctx, event, cpu); + ++ctx->generation; + mutex_unlock(&ctx->mutex); + + event->owner = current; + get_task_struct(current); + mutex_lock(¤t->perf_event_mutex); + list_add_tail(&event->owner_entry, ¤t->perf_event_list); + mutex_unlock(¤t->perf_event_mutex); + + return event; + +err_put_context: + if (err < 0) + put_ctx(ctx); + + return NULL; +} +EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter); + /* * inherit a event from parent task to child task: */ -- cgit v1.2.3 From 97eaf5300b9d0cd99c310bf8c4a0f2f3296d88a3 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sun, 18 Oct 2009 15:33:50 +0200 Subject: perf/core: Add a callback to perf events A simple callback in a perf event can be used for multiple purposes. For example it is useful for triggered based events like hardware breakpoints that need a callback to dispatch a triggered breakpoint event. v2: Simplify a bit the callback attribution as suggested by Paul Mackerras Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: "K.Prasad" Cc: Alan Stern Cc: Arnaldo Carvalho de Melo Cc: Steven Rostedt Cc: Ingo Molnar Cc: Paul Mackerras Cc: Mike Galbraith Cc: Paul Mundt --- kernel/perf_event.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'kernel/perf_event.c') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 02d4ff041b0..5087125e2a0 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -4293,6 +4293,7 @@ perf_event_alloc(struct perf_event_attr *attr, struct perf_event_context *ctx, struct perf_event *group_leader, struct perf_event *parent_event, + perf_callback_t callback, gfp_t gfpflags) { const struct pmu *pmu; @@ -4335,6 +4336,11 @@ perf_event_alloc(struct perf_event_attr *attr, event->state = PERF_EVENT_STATE_INACTIVE; + if (!callback && parent_event) + callback = parent_event->callback; + + event->callback = callback; + if (attr->disabled) event->state = PERF_EVENT_STATE_OFF; @@ -4611,7 +4617,7 @@ SYSCALL_DEFINE5(perf_event_open, } event = perf_event_alloc(&attr, cpu, ctx, group_leader, - NULL, GFP_KERNEL); + NULL, NULL, GFP_KERNEL); err = PTR_ERR(event); if (IS_ERR(event)) goto err_put_context; @@ -4668,7 +4674,7 @@ err_put_context: */ struct perf_event * perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, - pid_t pid) + pid_t pid, perf_callback_t callback) { struct perf_event *event; struct perf_event_context *ctx; @@ -4683,7 +4689,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, return NULL ; event = perf_event_alloc(attr, cpu, ctx, NULL, - NULL, GFP_KERNEL); + NULL, callback, GFP_KERNEL); err = PTR_ERR(event); if (IS_ERR(event)) goto err_put_context; @@ -4736,7 +4742,7 @@ inherit_event(struct perf_event *parent_event, child_event = perf_event_alloc(&parent_event->attr, parent_event->cpu, child_ctx, group_leader, parent_event, - GFP_KERNEL); + NULL, GFP_KERNEL); if (IS_ERR(child_event)) return child_event; get_ctx(child_ctx); -- cgit v1.2.3 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/perf_event.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 52 insertions(+), 1 deletion(-) (limited to 'kernel/perf_event.c') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 5087125e2a0..98dc56b2ebe 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -29,6 +29,7 @@ #include #include #include +#include #include @@ -4229,6 +4230,51 @@ static void perf_event_free_filter(struct perf_event *event) #endif /* CONFIG_EVENT_PROFILE */ +#ifdef CONFIG_HAVE_HW_BREAKPOINT +static void bp_perf_event_destroy(struct perf_event *event) +{ + release_bp_slot(event); +} + +static const struct pmu *bp_perf_event_init(struct perf_event *bp) +{ + int err; + /* + * The breakpoint is already filled if we haven't created the counter + * through perf syscall + * FIXME: manage to get trigerred to NULL if it comes from syscalls + */ + if (!bp->callback) + err = register_perf_hw_breakpoint(bp); + else + err = __register_perf_hw_breakpoint(bp); + if (err) + return ERR_PTR(err); + + bp->destroy = bp_perf_event_destroy; + + return &perf_ops_bp; +} + +void perf_bp_event(struct perf_event *bp, void *regs) +{ + /* TODO */ +} +#else +static void bp_perf_event_destroy(struct perf_event *event) +{ +} + +static const struct pmu *bp_perf_event_init(struct perf_event *bp) +{ + return NULL; +} + +void perf_bp_event(struct perf_event *bp, void *regs) +{ +} +#endif + atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX]; static void sw_perf_event_destroy(struct perf_event *event) @@ -4375,6 +4421,11 @@ perf_event_alloc(struct perf_event_attr *attr, pmu = tp_perf_event_init(event); break; + case PERF_TYPE_BREAKPOINT: + pmu = bp_perf_event_init(event); + break; + + default: break; } @@ -4686,7 +4737,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, ctx = find_get_context(pid, cpu); if (IS_ERR(ctx)) - return NULL ; + return NULL; event = perf_event_alloc(attr, cpu, ctx, NULL, NULL, callback, GFP_KERNEL); -- cgit v1.2.3