From c7fd239a647ead1c336a051012d6bb96465ea8c6 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Sun, 29 Aug 2010 14:52:00 -0400 Subject: ARM: oprofile: fix and simplify init/exit functions Now that oprofile_arch_exit is only called when the OProfile module is unloaded, it can assume that init completed successfully and not have to worry about double frees or releasing NULL perf events. This patch ensures that oprofile_arch_init fails gracefully on ARM and simplifies the exit code based on the above. Cc: Robert Richter Cc: Matt Fleming Cc: Peter Zijlstra Cc: Ingo Molnar Signed-off-by: Will Deacon Signed-off-by: Robert Richter --- arch/arm/oprofile/common.c | 47 ++++++++++++++++++++++++---------------------- 1 file changed, 25 insertions(+), 22 deletions(-) (limited to 'arch/arm/oprofile/common.c') diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c index 0691176899f..c3652f73fed 100644 --- a/arch/arm/oprofile/common.c +++ b/arch/arm/oprofile/common.c @@ -275,7 +275,7 @@ out: return ret; } -static void exit_driverfs(void) +static void __exit exit_driverfs(void) { platform_device_unregister(oprofile_pdev); platform_driver_unregister(&oprofile_driver); @@ -359,14 +359,13 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) if (!counter_config) { pr_info("oprofile: failed to allocate %d " "counters\n", perf_num_counters); - return -ENOMEM; + ret = -ENOMEM; + goto out; } ret = init_driverfs(); - if (ret) { - kfree(counter_config); - return ret; - } + if (ret) + goto out; for_each_possible_cpu(cpu) { perf_events[cpu] = kcalloc(perf_num_counters, @@ -374,9 +373,8 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) if (!perf_events[cpu]) { pr_info("oprofile: failed to allocate %d perf events " "for cpu %d\n", perf_num_counters, cpu); - while (--cpu >= 0) - kfree(perf_events[cpu]); - return -ENOMEM; + ret = -ENOMEM; + goto out; } } @@ -393,28 +391,33 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) else pr_info("oprofile: using %s\n", ops->cpu_type); +out: + if (ret) { + for_each_possible_cpu(cpu) + kfree(perf_events[cpu]); + kfree(counter_config); + } + return ret; } -void oprofile_arch_exit(void) +void __exit oprofile_arch_exit(void) { int cpu, id; struct perf_event *event; - if (*perf_events) { - exit_driverfs(); - for_each_possible_cpu(cpu) { - for (id = 0; id < perf_num_counters; ++id) { - event = perf_events[cpu][id]; - if (event != NULL) - perf_event_release_kernel(event); - } - kfree(perf_events[cpu]); + for_each_possible_cpu(cpu) { + for (id = 0; id < perf_num_counters; ++id) { + event = perf_events[cpu][id]; + if (event) + perf_event_release_kernel(event); } + + kfree(perf_events[cpu]); } - if (counter_config) - kfree(counter_config); + kfree(counter_config); + exit_driverfs(); } #else int __init oprofile_arch_init(struct oprofile_operations *ops) @@ -422,5 +425,5 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) pr_info("oprofile: hardware counters not available\n"); return -ENODEV; } -void oprofile_arch_exit(void) {} +void __exit oprofile_arch_exit(void) {} #endif /* CONFIG_HW_PERF_EVENTS */ -- cgit v1.2.3-70-g09d2 From 4cbe75be5c6ae86bdc7daec864eeb2dfd66f48bb Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Mon, 30 Aug 2010 18:21:55 +0200 Subject: oprofile, arm: initialize perf_event pointers with NULL The pointers must be NULL'ed to avoid double-freeing the pointers in rare cases during reinitialization. Signed-off-by: Robert Richter --- arch/arm/oprofile/common.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/arm/oprofile/common.c') diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c index c3652f73fed..d660cb8dab3 100644 --- a/arch/arm/oprofile/common.c +++ b/arch/arm/oprofile/common.c @@ -351,6 +351,8 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) { int cpu, ret = 0; + memset(&perf_events, 0, sizeof(perf_events)); + perf_num_counters = armpmu_get_max_events(); counter_config = kcalloc(perf_num_counters, -- cgit v1.2.3-70-g09d2 From 3bf101ba42a1c89b5afbc7492e7647dae5e18735 Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Mon, 27 Sep 2010 20:22:24 +0100 Subject: perf: Add helper function to return number of counters The number of counters for the registered pmu is needed in a few places so provide a helper function that returns this number. Signed-off-by: Matt Fleming Tested-by: Will Deacon Acked-by: Paul Mundt Acked-by: Peter Zijlstra Signed-off-by: Robert Richter --- arch/arm/kernel/perf_event.c | 6 ++++++ arch/arm/oprofile/common.c | 31 ++++++++++++++++++------------- arch/sh/kernel/perf_event.c | 9 +++++++++ include/linux/perf_event.h | 1 + 4 files changed, 34 insertions(+), 13 deletions(-) (limited to 'arch/arm/oprofile/common.c') diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 417c392ddf1..3b0aedfb96e 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -123,6 +123,12 @@ armpmu_get_max_events(void) } EXPORT_SYMBOL_GPL(armpmu_get_max_events); +int perf_num_counters(void) +{ + return armpmu_get_max_events(); +} +EXPORT_SYMBOL_GPL(perf_num_counters); + #define HW_OP_UNSUPPORTED 0xFFFF #define C(_x) \ diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c index d660cb8dab3..1e971a7fcf8 100644 --- a/arch/arm/oprofile/common.c +++ b/arch/arm/oprofile/common.c @@ -43,7 +43,7 @@ static DEFINE_MUTEX(op_arm_mutex); static struct op_counter_config *counter_config; static struct perf_event **perf_events[nr_cpumask_bits]; -static int perf_num_counters; +static int num_counters; /* * Overflow callback for oprofile. @@ -54,11 +54,11 @@ static void op_overflow_handler(struct perf_event *event, int unused, int id; u32 cpu = smp_processor_id(); - for (id = 0; id < perf_num_counters; ++id) + for (id = 0; id < num_counters; ++id) if (perf_events[cpu][id] == event) break; - if (id != perf_num_counters) + if (id != num_counters) oprofile_add_sample(regs, id); else pr_warning("oprofile: ignoring spurious overflow " @@ -76,7 +76,7 @@ static void op_perf_setup(void) u32 size = sizeof(struct perf_event_attr); struct perf_event_attr *attr; - for (i = 0; i < perf_num_counters; ++i) { + for (i = 0; i < num_counters; ++i) { attr = &counter_config[i].attr; memset(attr, 0, size); attr->type = PERF_TYPE_RAW; @@ -131,7 +131,7 @@ static int op_perf_start(void) int cpu, event, ret = 0; for_each_online_cpu(cpu) { - for (event = 0; event < perf_num_counters; ++event) { + for (event = 0; event < num_counters; ++event) { ret = op_create_counter(cpu, event); if (ret) goto out; @@ -150,7 +150,7 @@ static void op_perf_stop(void) int cpu, event; for_each_online_cpu(cpu) - for (event = 0; event < perf_num_counters; ++event) + for (event = 0; event < num_counters; ++event) op_destroy_counter(cpu, event); } @@ -179,7 +179,7 @@ static int op_arm_create_files(struct super_block *sb, struct dentry *root) { unsigned int i; - for (i = 0; i < perf_num_counters; i++) { + for (i = 0; i < num_counters; i++) { struct dentry *dir; char buf[4]; @@ -353,14 +353,19 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) memset(&perf_events, 0, sizeof(perf_events)); - perf_num_counters = armpmu_get_max_events(); + num_counters = perf_num_counters(); + if (num_counters <= 0) { + pr_info("oprofile: no performance counters\n"); + ret = -ENODEV; + goto out; + } - counter_config = kcalloc(perf_num_counters, + counter_config = kcalloc(num_counters, sizeof(struct op_counter_config), GFP_KERNEL); if (!counter_config) { pr_info("oprofile: failed to allocate %d " - "counters\n", perf_num_counters); + "counters\n", num_counters); ret = -ENOMEM; goto out; } @@ -370,11 +375,11 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) goto out; for_each_possible_cpu(cpu) { - perf_events[cpu] = kcalloc(perf_num_counters, + perf_events[cpu] = kcalloc(num_counters, sizeof(struct perf_event *), GFP_KERNEL); if (!perf_events[cpu]) { pr_info("oprofile: failed to allocate %d perf events " - "for cpu %d\n", perf_num_counters, cpu); + "for cpu %d\n", num_counters, cpu); ret = -ENOMEM; goto out; } @@ -409,7 +414,7 @@ void __exit oprofile_arch_exit(void) struct perf_event *event; for_each_possible_cpu(cpu) { - for (id = 0; id < perf_num_counters; ++id) { + for (id = 0; id < num_counters; ++id) { event = perf_events[cpu][id]; if (event) perf_event_release_kernel(event); diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c index 7a3dc356725..2cb9ad59d4b 100644 --- a/arch/sh/kernel/perf_event.c +++ b/arch/sh/kernel/perf_event.c @@ -59,6 +59,15 @@ static inline int sh_pmu_initialized(void) return !!sh_pmu; } +int perf_num_counters(void) +{ + if (!sh_pmu) + return 0; + + return sh_pmu->num_events; +} +EXPORT_SYMBOL_GPL(perf_num_counters); + /* * Release the PMU if this is the last perf_event. */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 716f99b682c..1a021924718 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -849,6 +849,7 @@ extern int perf_max_events; extern const struct pmu *hw_perf_event_init(struct perf_event *event); +extern int perf_num_counters(void); extern void perf_event_task_sched_in(struct task_struct *task); extern void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next); extern void perf_event_task_tick(struct task_struct *task); -- cgit v1.2.3-70-g09d2 From 56946331b28d53232115a155ba662ab3dc598952 Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Fri, 8 Oct 2010 21:42:17 +0100 Subject: oprofile: Make op_name_from_perf_id() global Make op_name_from_perf_id() global so that we have a way for each architecture to construct an oprofile name for op->cpu_type. We need to remove the argument from the function prototype so that we can hide all implementation details inside the function. Signed-off-by: Matt Fleming Signed-off-by: Robert Richter --- arch/arm/oprofile/common.c | 6 ++++-- include/linux/oprofile.h | 4 ++++ 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'arch/arm/oprofile/common.c') diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c index 1e971a7fcf8..4f67cfab2c5 100644 --- a/arch/arm/oprofile/common.c +++ b/arch/arm/oprofile/common.c @@ -155,8 +155,10 @@ static void op_perf_stop(void) } -static char *op_name_from_perf_id(enum arm_perf_pmu_ids id) +char *op_name_from_perf_id(void) { + enum arm_perf_pmu_ids id = armpmu_get_pmu_id(); + switch (id) { case ARM_PERF_PMU_ID_XSCALE1: return "arm/xscale1"; @@ -391,7 +393,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) ops->start = op_arm_start; ops->stop = op_arm_stop; ops->shutdown = op_arm_stop; - ops->cpu_type = op_name_from_perf_id(armpmu_get_pmu_id()); + ops->cpu_type = op_name_from_perf_id(); if (!ops->cpu_type) ret = -ENODEV; diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h index 5171639ecf0..1574d4aca72 100644 --- a/include/linux/oprofile.h +++ b/include/linux/oprofile.h @@ -185,4 +185,8 @@ int oprofile_add_data(struct op_entry *entry, unsigned long val); int oprofile_add_data64(struct op_entry *entry, u64 val); int oprofile_write_commit(struct op_entry *entry); +#ifdef CONFIG_PERF_EVENTS +char *op_name_from_perf_id(void); +#endif /* CONFIG_PERF_EVENTS */ + #endif /* OPROFILE_H */ -- cgit v1.2.3-70-g09d2 From 80e96b11f6cd261e1e569f3931604d656388af33 Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Mon, 27 Sep 2010 20:29:58 +0100 Subject: ARM: oprofile: Rename op_arm to oprofile_perf In preparation for moving the generic functions out of this file, give the functions more general names (e.g. remove "arm" from the names). Signed-off-by: Matt Fleming Tested-by: Will Deacon Signed-off-by: Robert Richter --- arch/arm/oprofile/common.c | 68 +++++++++++++++++++++++----------------------- 1 file changed, 34 insertions(+), 34 deletions(-) (limited to 'arch/arm/oprofile/common.c') diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c index 4f67cfab2c5..d18c9f3fcff 100644 --- a/arch/arm/oprofile/common.c +++ b/arch/arm/oprofile/common.c @@ -38,8 +38,8 @@ struct op_counter_config { struct perf_event_attr attr; }; -static int op_arm_enabled; -static DEFINE_MUTEX(op_arm_mutex); +static int oprofile_perf_enabled; +static DEFINE_MUTEX(oprofile_perf_mutex); static struct op_counter_config *counter_config; static struct perf_event **perf_events[nr_cpumask_bits]; @@ -66,7 +66,7 @@ static void op_overflow_handler(struct perf_event *event, int unused, } /* - * Called by op_arm_setup to create perf attributes to mirror the oprofile + * Called by oprofile_perf_setup to create perf attributes to mirror the oprofile * settings in counter_config. Attributes are created as `pinned' events and * so are permanently scheduled on the PMU. */ @@ -123,7 +123,7 @@ static void op_destroy_counter(int cpu, int event) } /* - * Called by op_arm_start to create active perf events based on the + * Called by oprofile_perf_start to create active perf events based on the * perviously configured attributes. */ static int op_perf_start(void) @@ -143,7 +143,7 @@ out: } /* - * Called by op_arm_stop at the end of a profiling run. + * Called by oprofile_perf_stop at the end of a profiling run. */ static void op_perf_stop(void) { @@ -177,7 +177,7 @@ char *op_name_from_perf_id(void) } } -static int op_arm_create_files(struct super_block *sb, struct dentry *root) +static int oprofile_perf_create_files(struct super_block *sb, struct dentry *root) { unsigned int i; @@ -198,7 +198,7 @@ static int op_arm_create_files(struct super_block *sb, struct dentry *root) return 0; } -static int op_arm_setup(void) +static int oprofile_perf_setup(void) { spin_lock(&oprofilefs_lock); op_perf_setup(); @@ -206,54 +206,54 @@ static int op_arm_setup(void) return 0; } -static int op_arm_start(void) +static int oprofile_perf_start(void) { int ret = -EBUSY; - mutex_lock(&op_arm_mutex); - if (!op_arm_enabled) { + mutex_lock(&oprofile_perf_mutex); + if (!oprofile_perf_enabled) { ret = 0; op_perf_start(); - op_arm_enabled = 1; + oprofile_perf_enabled = 1; } - mutex_unlock(&op_arm_mutex); + mutex_unlock(&oprofile_perf_mutex); return ret; } -static void op_arm_stop(void) +static void oprofile_perf_stop(void) { - mutex_lock(&op_arm_mutex); - if (op_arm_enabled) + mutex_lock(&oprofile_perf_mutex); + if (oprofile_perf_enabled) op_perf_stop(); - op_arm_enabled = 0; - mutex_unlock(&op_arm_mutex); + oprofile_perf_enabled = 0; + mutex_unlock(&oprofile_perf_mutex); } #ifdef CONFIG_PM -static int op_arm_suspend(struct platform_device *dev, pm_message_t state) +static int oprofile_perf_suspend(struct platform_device *dev, pm_message_t state) { - mutex_lock(&op_arm_mutex); - if (op_arm_enabled) + mutex_lock(&oprofile_perf_mutex); + if (oprofile_perf_enabled) op_perf_stop(); - mutex_unlock(&op_arm_mutex); + mutex_unlock(&oprofile_perf_mutex); return 0; } -static int op_arm_resume(struct platform_device *dev) +static int oprofile_perf_resume(struct platform_device *dev) { - mutex_lock(&op_arm_mutex); - if (op_arm_enabled && op_perf_start()) - op_arm_enabled = 0; - mutex_unlock(&op_arm_mutex); + mutex_lock(&oprofile_perf_mutex); + if (oprofile_perf_enabled && op_perf_start()) + oprofile_perf_enabled = 0; + mutex_unlock(&oprofile_perf_mutex); return 0; } static struct platform_driver oprofile_driver = { .driver = { - .name = "arm-oprofile", + .name = "oprofile-perf", }, - .resume = op_arm_resume, - .suspend = op_arm_suspend, + .resume = oprofile_perf_resume, + .suspend = oprofile_perf_suspend, }; static struct platform_device *oprofile_pdev; @@ -388,11 +388,11 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) } ops->backtrace = arm_backtrace; - ops->create_files = op_arm_create_files; - ops->setup = op_arm_setup; - ops->start = op_arm_start; - ops->stop = op_arm_stop; - ops->shutdown = op_arm_stop; + ops->create_files = oprofile_perf_create_files; + ops->setup = oprofile_perf_setup; + ops->start = oprofile_perf_start; + ops->stop = oprofile_perf_stop; + ops->shutdown = oprofile_perf_stop; ops->cpu_type = op_name_from_perf_id(); if (!ops->cpu_type) -- cgit v1.2.3-70-g09d2 From 58850e210cd207399cf6461326e322541b2ec81c Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Mon, 27 Sep 2010 20:35:29 +0100 Subject: ARM: oprofile: Move non-ARM code into separate init/exit In preparation for moving the majority of this oprofile code into an architecture-neutral place separate the architecture-independent code into oprofile_perf_init() and oprofile_perf_exit(). Signed-off-by: Matt Fleming Tested-by: Will Deacon Signed-off-by: Robert Richter --- arch/arm/oprofile/common.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'arch/arm/oprofile/common.c') diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c index d18c9f3fcff..8718311cb53 100644 --- a/arch/arm/oprofile/common.c +++ b/arch/arm/oprofile/common.c @@ -349,7 +349,7 @@ static void arm_backtrace(struct pt_regs * const regs, unsigned int depth) tail = user_backtrace(tail); } -int __init oprofile_arch_init(struct oprofile_operations *ops) +int __init oprofile_perf_init(struct oprofile_operations *ops) { int cpu, ret = 0; @@ -387,7 +387,6 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) } } - ops->backtrace = arm_backtrace; ops->create_files = oprofile_perf_create_files; ops->setup = oprofile_perf_setup; ops->start = oprofile_perf_start; @@ -410,7 +409,14 @@ out: return ret; } -void __exit oprofile_arch_exit(void) +int __init oprofile_arch_init(struct oprofile_operations *ops) +{ + ops->backtrace = arm_backtrace; + + return oprofile_perf_init(ops); +} + +void __exit oprofile_perf_exit(void) { int cpu, id; struct perf_event *event; @@ -428,6 +434,11 @@ void __exit oprofile_arch_exit(void) kfree(counter_config); exit_driverfs(); } + +void __exit oprofile_arch_exit(void) +{ + oprofile_perf_exit(); +} #else int __init oprofile_arch_init(struct oprofile_operations *ops) { -- cgit v1.2.3-70-g09d2 From 3d90a00763b51e1db344a7430c966be723b67a29 Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Mon, 27 Sep 2010 20:45:08 +0100 Subject: oprofile: Abstract the perf-events backend Move the perf-events backend from arch/arm/oprofile into drivers/oprofile so that the code can be shared between architectures. This allows each architecture to maintain only a single copy of the PMU accessor functions instead of one for both perf and OProfile. It also becomes possible for other architectures to delete much of their OProfile code in favour of the common code now available in drivers/oprofile/oprofile_perf.c. Signed-off-by: Matt Fleming Tested-by: Will Deacon Signed-off-by: Robert Richter --- arch/arm/oprofile/Makefile | 4 + arch/arm/oprofile/common.c | 319 -------------------------------------- drivers/oprofile/oprofile_perf.c | 326 +++++++++++++++++++++++++++++++++++++++ include/linux/oprofile.h | 3 + 4 files changed, 333 insertions(+), 319 deletions(-) create mode 100644 drivers/oprofile/oprofile_perf.c (limited to 'arch/arm/oprofile/common.c') diff --git a/arch/arm/oprofile/Makefile b/arch/arm/oprofile/Makefile index e666eafed15..b2215c61cdf 100644 --- a/arch/arm/oprofile/Makefile +++ b/arch/arm/oprofile/Makefile @@ -6,4 +6,8 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \ oprofilefs.o oprofile_stats.o \ timer_int.o ) +ifeq ($(CONFIG_HW_PERF_EVENTS),y) +DRIVER_OBJS += $(addprefix ../../../drivers/oprofile/, oprofile_perf.o) +endif + oprofile-y := $(DRIVER_OBJS) common.o diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c index 8718311cb53..8aa974491df 100644 --- a/arch/arm/oprofile/common.c +++ b/arch/arm/oprofile/common.c @@ -25,136 +25,6 @@ #include #ifdef CONFIG_HW_PERF_EVENTS -/* - * Per performance monitor configuration as set via oprofilefs. - */ -struct op_counter_config { - unsigned long count; - unsigned long enabled; - unsigned long event; - unsigned long unit_mask; - unsigned long kernel; - unsigned long user; - struct perf_event_attr attr; -}; - -static int oprofile_perf_enabled; -static DEFINE_MUTEX(oprofile_perf_mutex); - -static struct op_counter_config *counter_config; -static struct perf_event **perf_events[nr_cpumask_bits]; -static int num_counters; - -/* - * Overflow callback for oprofile. - */ -static void op_overflow_handler(struct perf_event *event, int unused, - struct perf_sample_data *data, struct pt_regs *regs) -{ - int id; - u32 cpu = smp_processor_id(); - - for (id = 0; id < num_counters; ++id) - if (perf_events[cpu][id] == event) - break; - - if (id != num_counters) - oprofile_add_sample(regs, id); - else - pr_warning("oprofile: ignoring spurious overflow " - "on cpu %u\n", cpu); -} - -/* - * Called by oprofile_perf_setup to create perf attributes to mirror the oprofile - * settings in counter_config. Attributes are created as `pinned' events and - * so are permanently scheduled on the PMU. - */ -static void op_perf_setup(void) -{ - int i; - u32 size = sizeof(struct perf_event_attr); - struct perf_event_attr *attr; - - for (i = 0; i < num_counters; ++i) { - attr = &counter_config[i].attr; - memset(attr, 0, size); - attr->type = PERF_TYPE_RAW; - attr->size = size; - attr->config = counter_config[i].event; - attr->sample_period = counter_config[i].count; - attr->pinned = 1; - } -} - -static int op_create_counter(int cpu, int event) -{ - int ret = 0; - struct perf_event *pevent; - - if (!counter_config[event].enabled || (perf_events[cpu][event] != NULL)) - return ret; - - pevent = perf_event_create_kernel_counter(&counter_config[event].attr, - cpu, -1, - op_overflow_handler); - - if (IS_ERR(pevent)) { - ret = PTR_ERR(pevent); - } else if (pevent->state != PERF_EVENT_STATE_ACTIVE) { - pr_warning("oprofile: failed to enable event %d " - "on CPU %d\n", event, cpu); - ret = -EBUSY; - } else { - perf_events[cpu][event] = pevent; - } - - return ret; -} - -static void op_destroy_counter(int cpu, int event) -{ - struct perf_event *pevent = perf_events[cpu][event]; - - if (pevent) { - perf_event_release_kernel(pevent); - perf_events[cpu][event] = NULL; - } -} - -/* - * Called by oprofile_perf_start to create active perf events based on the - * perviously configured attributes. - */ -static int op_perf_start(void) -{ - int cpu, event, ret = 0; - - for_each_online_cpu(cpu) { - for (event = 0; event < num_counters; ++event) { - ret = op_create_counter(cpu, event); - if (ret) - goto out; - } - } - -out: - return ret; -} - -/* - * Called by oprofile_perf_stop at the end of a profiling run. - */ -static void op_perf_stop(void) -{ - int cpu, event; - - for_each_online_cpu(cpu) - for (event = 0; event < num_counters; ++event) - op_destroy_counter(cpu, event); -} - - char *op_name_from_perf_id(void) { enum arm_perf_pmu_ids id = armpmu_get_pmu_id(); @@ -177,116 +47,6 @@ char *op_name_from_perf_id(void) } } -static int oprofile_perf_create_files(struct super_block *sb, struct dentry *root) -{ - unsigned int i; - - for (i = 0; i < num_counters; i++) { - struct dentry *dir; - char buf[4]; - - snprintf(buf, sizeof buf, "%d", i); - dir = oprofilefs_mkdir(sb, root, buf); - oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled); - oprofilefs_create_ulong(sb, dir, "event", &counter_config[i].event); - oprofilefs_create_ulong(sb, dir, "count", &counter_config[i].count); - oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask); - oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel); - oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user); - } - - return 0; -} - -static int oprofile_perf_setup(void) -{ - spin_lock(&oprofilefs_lock); - op_perf_setup(); - spin_unlock(&oprofilefs_lock); - return 0; -} - -static int oprofile_perf_start(void) -{ - int ret = -EBUSY; - - mutex_lock(&oprofile_perf_mutex); - if (!oprofile_perf_enabled) { - ret = 0; - op_perf_start(); - oprofile_perf_enabled = 1; - } - mutex_unlock(&oprofile_perf_mutex); - return ret; -} - -static void oprofile_perf_stop(void) -{ - mutex_lock(&oprofile_perf_mutex); - if (oprofile_perf_enabled) - op_perf_stop(); - oprofile_perf_enabled = 0; - mutex_unlock(&oprofile_perf_mutex); -} - -#ifdef CONFIG_PM -static int oprofile_perf_suspend(struct platform_device *dev, pm_message_t state) -{ - mutex_lock(&oprofile_perf_mutex); - if (oprofile_perf_enabled) - op_perf_stop(); - mutex_unlock(&oprofile_perf_mutex); - return 0; -} - -static int oprofile_perf_resume(struct platform_device *dev) -{ - mutex_lock(&oprofile_perf_mutex); - if (oprofile_perf_enabled && op_perf_start()) - oprofile_perf_enabled = 0; - mutex_unlock(&oprofile_perf_mutex); - return 0; -} - -static struct platform_driver oprofile_driver = { - .driver = { - .name = "oprofile-perf", - }, - .resume = oprofile_perf_resume, - .suspend = oprofile_perf_suspend, -}; - -static struct platform_device *oprofile_pdev; - -static int __init init_driverfs(void) -{ - int ret; - - ret = platform_driver_register(&oprofile_driver); - if (ret) - goto out; - - oprofile_pdev = platform_device_register_simple( - oprofile_driver.driver.name, 0, NULL, 0); - if (IS_ERR(oprofile_pdev)) { - ret = PTR_ERR(oprofile_pdev); - platform_driver_unregister(&oprofile_driver); - } - -out: - return ret; -} - -static void __exit exit_driverfs(void) -{ - platform_device_unregister(oprofile_pdev); - platform_driver_unregister(&oprofile_driver); -} -#else -static int __init init_driverfs(void) { return 0; } -#define exit_driverfs() do { } while (0) -#endif /* CONFIG_PM */ - static int report_trace(struct stackframe *frame, void *d) { unsigned int *depth = d; @@ -349,66 +109,6 @@ static void arm_backtrace(struct pt_regs * const regs, unsigned int depth) tail = user_backtrace(tail); } -int __init oprofile_perf_init(struct oprofile_operations *ops) -{ - int cpu, ret = 0; - - memset(&perf_events, 0, sizeof(perf_events)); - - num_counters = perf_num_counters(); - if (num_counters <= 0) { - pr_info("oprofile: no performance counters\n"); - ret = -ENODEV; - goto out; - } - - counter_config = kcalloc(num_counters, - sizeof(struct op_counter_config), GFP_KERNEL); - - if (!counter_config) { - pr_info("oprofile: failed to allocate %d " - "counters\n", num_counters); - ret = -ENOMEM; - goto out; - } - - ret = init_driverfs(); - if (ret) - goto out; - - for_each_possible_cpu(cpu) { - perf_events[cpu] = kcalloc(num_counters, - sizeof(struct perf_event *), GFP_KERNEL); - if (!perf_events[cpu]) { - pr_info("oprofile: failed to allocate %d perf events " - "for cpu %d\n", num_counters, cpu); - ret = -ENOMEM; - goto out; - } - } - - ops->create_files = oprofile_perf_create_files; - ops->setup = oprofile_perf_setup; - ops->start = oprofile_perf_start; - ops->stop = oprofile_perf_stop; - ops->shutdown = oprofile_perf_stop; - ops->cpu_type = op_name_from_perf_id(); - - if (!ops->cpu_type) - ret = -ENODEV; - else - pr_info("oprofile: using %s\n", ops->cpu_type); - -out: - if (ret) { - for_each_possible_cpu(cpu) - kfree(perf_events[cpu]); - kfree(counter_config); - } - - return ret; -} - int __init oprofile_arch_init(struct oprofile_operations *ops) { ops->backtrace = arm_backtrace; @@ -416,25 +116,6 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) return oprofile_perf_init(ops); } -void __exit oprofile_perf_exit(void) -{ - int cpu, id; - struct perf_event *event; - - for_each_possible_cpu(cpu) { - for (id = 0; id < num_counters; ++id) { - event = perf_events[cpu][id]; - if (event) - perf_event_release_kernel(event); - } - - kfree(perf_events[cpu]); - } - - kfree(counter_config); - exit_driverfs(); -} - void __exit oprofile_arch_exit(void) { oprofile_perf_exit(); diff --git a/drivers/oprofile/oprofile_perf.c b/drivers/oprofile/oprofile_perf.c new file mode 100644 index 00000000000..ebb40cb8747 --- /dev/null +++ b/drivers/oprofile/oprofile_perf.c @@ -0,0 +1,326 @@ +/* + * Copyright 2010 ARM Ltd. + * + * Perf-events backend for OProfile. + */ +#include +#include +#include + +/* + * Per performance monitor configuration as set via oprofilefs. + */ +struct op_counter_config { + unsigned long count; + unsigned long enabled; + unsigned long event; + unsigned long unit_mask; + unsigned long kernel; + unsigned long user; + struct perf_event_attr attr; +}; + +static int oprofile_perf_enabled; +static DEFINE_MUTEX(oprofile_perf_mutex); + +static struct op_counter_config *counter_config; +static struct perf_event **perf_events[nr_cpumask_bits]; +static int num_counters; + +/* + * Overflow callback for oprofile. + */ +static void op_overflow_handler(struct perf_event *event, int unused, + struct perf_sample_data *data, struct pt_regs *regs) +{ + int id; + u32 cpu = smp_processor_id(); + + for (id = 0; id < num_counters; ++id) + if (perf_events[cpu][id] == event) + break; + + if (id != num_counters) + oprofile_add_sample(regs, id); + else + pr_warning("oprofile: ignoring spurious overflow " + "on cpu %u\n", cpu); +} + +/* + * Called by oprofile_perf_setup to create perf attributes to mirror the oprofile + * settings in counter_config. Attributes are created as `pinned' events and + * so are permanently scheduled on the PMU. + */ +static void op_perf_setup(void) +{ + int i; + u32 size = sizeof(struct perf_event_attr); + struct perf_event_attr *attr; + + for (i = 0; i < num_counters; ++i) { + attr = &counter_config[i].attr; + memset(attr, 0, size); + attr->type = PERF_TYPE_RAW; + attr->size = size; + attr->config = counter_config[i].event; + attr->sample_period = counter_config[i].count; + attr->pinned = 1; + } +} + +static int op_create_counter(int cpu, int event) +{ + int ret = 0; + struct perf_event *pevent; + + if (!counter_config[event].enabled || (perf_events[cpu][event] != NULL)) + return ret; + + pevent = perf_event_create_kernel_counter(&counter_config[event].attr, + cpu, -1, + op_overflow_handler); + + if (IS_ERR(pevent)) { + ret = PTR_ERR(pevent); + } else if (pevent->state != PERF_EVENT_STATE_ACTIVE) { + pr_warning("oprofile: failed to enable event %d " + "on CPU %d\n", event, cpu); + ret = -EBUSY; + } else { + perf_events[cpu][event] = pevent; + } + + return ret; +} + +static void op_destroy_counter(int cpu, int event) +{ + struct perf_event *pevent = perf_events[cpu][event]; + + if (pevent) { + perf_event_release_kernel(pevent); + perf_events[cpu][event] = NULL; + } +} + +/* + * Called by oprofile_perf_start to create active perf events based on the + * perviously configured attributes. + */ +static int op_perf_start(void) +{ + int cpu, event, ret = 0; + + for_each_online_cpu(cpu) { + for (event = 0; event < num_counters; ++event) { + ret = op_create_counter(cpu, event); + if (ret) + goto out; + } + } + +out: + return ret; +} + +/* + * Called by oprofile_perf_stop at the end of a profiling run. + */ +static void op_perf_stop(void) +{ + int cpu, event; + + for_each_online_cpu(cpu) + for (event = 0; event < num_counters; ++event) + op_destroy_counter(cpu, event); +} + +static int oprofile_perf_create_files(struct super_block *sb, struct dentry *root) +{ + unsigned int i; + + for (i = 0; i < num_counters; i++) { + struct dentry *dir; + char buf[4]; + + snprintf(buf, sizeof buf, "%d", i); + dir = oprofilefs_mkdir(sb, root, buf); + oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled); + oprofilefs_create_ulong(sb, dir, "event", &counter_config[i].event); + oprofilefs_create_ulong(sb, dir, "count", &counter_config[i].count); + oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask); + oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel); + oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user); + } + + return 0; +} + +static int oprofile_perf_setup(void) +{ + spin_lock(&oprofilefs_lock); + op_perf_setup(); + spin_unlock(&oprofilefs_lock); + return 0; +} + +static int oprofile_perf_start(void) +{ + int ret = -EBUSY; + + mutex_lock(&oprofile_perf_mutex); + if (!oprofile_perf_enabled) { + ret = 0; + op_perf_start(); + oprofile_perf_enabled = 1; + } + mutex_unlock(&oprofile_perf_mutex); + return ret; +} + +static void oprofile_perf_stop(void) +{ + mutex_lock(&oprofile_perf_mutex); + if (oprofile_perf_enabled) + op_perf_stop(); + oprofile_perf_enabled = 0; + mutex_unlock(&oprofile_perf_mutex); +} + +#ifdef CONFIG_PM +static int oprofile_perf_suspend(struct platform_device *dev, pm_message_t state) +{ + mutex_lock(&oprofile_perf_mutex); + if (oprofile_perf_enabled) + op_perf_stop(); + mutex_unlock(&oprofile_perf_mutex); + return 0; +} + +static int oprofile_perf_resume(struct platform_device *dev) +{ + mutex_lock(&oprofile_perf_mutex); + if (oprofile_perf_enabled && op_perf_start()) + oprofile_perf_enabled = 0; + mutex_unlock(&oprofile_perf_mutex); + return 0; +} + +static struct platform_driver oprofile_driver = { + .driver = { + .name = "oprofile-perf", + }, + .resume = oprofile_perf_resume, + .suspend = oprofile_perf_suspend, +}; + +static struct platform_device *oprofile_pdev; + +static int __init init_driverfs(void) +{ + int ret; + + ret = platform_driver_register(&oprofile_driver); + if (ret) + goto out; + + oprofile_pdev = platform_device_register_simple( + oprofile_driver.driver.name, 0, NULL, 0); + if (IS_ERR(oprofile_pdev)) { + ret = PTR_ERR(oprofile_pdev); + platform_driver_unregister(&oprofile_driver); + } + +out: + return ret; +} + +static void __exit exit_driverfs(void) +{ + platform_device_unregister(oprofile_pdev); + platform_driver_unregister(&oprofile_driver); +} +#else +static int __init init_driverfs(void) { return 0; } +#define exit_driverfs() do { } while (0) +#endif /* CONFIG_PM */ + +int __init oprofile_perf_init(struct oprofile_operations *ops) +{ + int cpu, ret = 0; + + memset(&perf_events, 0, sizeof(perf_events)); + + num_counters = perf_num_counters(); + if (num_counters <= 0) { + pr_info("oprofile: no performance counters\n"); + ret = -ENODEV; + goto out; + } + + counter_config = kcalloc(num_counters, + sizeof(struct op_counter_config), GFP_KERNEL); + + if (!counter_config) { + pr_info("oprofile: failed to allocate %d " + "counters\n", num_counters); + ret = -ENOMEM; + goto out; + } + + ret = init_driverfs(); + if (ret) + goto out; + + for_each_possible_cpu(cpu) { + perf_events[cpu] = kcalloc(num_counters, + sizeof(struct perf_event *), GFP_KERNEL); + if (!perf_events[cpu]) { + pr_info("oprofile: failed to allocate %d perf events " + "for cpu %d\n", num_counters, cpu); + ret = -ENOMEM; + goto out; + } + } + + ops->create_files = oprofile_perf_create_files; + ops->setup = oprofile_perf_setup; + ops->start = oprofile_perf_start; + ops->stop = oprofile_perf_stop; + ops->shutdown = oprofile_perf_stop; + ops->cpu_type = op_name_from_perf_id(); + + if (!ops->cpu_type) + ret = -ENODEV; + else + pr_info("oprofile: using %s\n", ops->cpu_type); + +out: + if (ret) { + for_each_possible_cpu(cpu) + kfree(perf_events[cpu]); + kfree(counter_config); + } + + return ret; +} + +void __exit oprofile_perf_exit(void) +{ + int cpu, id; + struct perf_event *event; + + for_each_possible_cpu(cpu) { + for (id = 0; id < num_counters; ++id) { + event = perf_events[cpu][id]; + if (event) + perf_event_release_kernel(event); + } + + kfree(perf_events[cpu]); + } + + kfree(counter_config); + exit_driverfs(); +} diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h index 1574d4aca72..d67a8330b41 100644 --- a/include/linux/oprofile.h +++ b/include/linux/oprofile.h @@ -15,6 +15,7 @@ #include #include +#include #include /* Each escaped entry is prefixed by ESCAPE_CODE @@ -186,6 +187,8 @@ int oprofile_add_data64(struct op_entry *entry, u64 val); int oprofile_write_commit(struct op_entry *entry); #ifdef CONFIG_PERF_EVENTS +int __init oprofile_perf_init(struct oprofile_operations *ops); +void __exit oprofile_perf_exit(void); char *op_name_from_perf_id(void); #endif /* CONFIG_PERF_EVENTS */ -- cgit v1.2.3-70-g09d2