From patchwork Mon Sep 13 06:07:35 2010 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Matt Fleming X-Patchwork-Id: 173802 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by demeter1.kernel.org (8.14.4/8.14.3) with ESMTP id o8D67iSH013346 for ; Mon, 13 Sep 2010 06:07:48 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752637Ab0IMGHq (ORCPT ); Mon, 13 Sep 2010 02:07:46 -0400 Received: from arkanian.console-pimps.org ([212.110.184.194]:39323 "EHLO arkanian.console-pimps.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752772Ab0IMGHn (ORCPT ); Mon, 13 Sep 2010 02:07:43 -0400 Received: by arkanian.console-pimps.org (Postfix, from userid 1002) id 2B27244341; Mon, 13 Sep 2010 07:07:42 +0100 (BST) X-Spam-Checker-Version: SpamAssassin 3.2.5 (2008-06-10) on arkanian.vm.bytemark.co.uk X-Spam-Level: X-Spam-Status: No, score=-4.2 required=5.0 tests=ALL_TRUSTED,AWL,BAYES_00 autolearn=ham version=3.2.5 Received: from localhost (cpc5-brad6-0-0-cust25.barn.cable.virginmedia.com [82.38.64.26]) by arkanian.console-pimps.org (Postfix) with ESMTPSA id 353B64432F; Mon, 13 Sep 2010 07:07:40 +0100 (BST) From: Matt Fleming To: Robert Richter Cc: Will Deacon , Paul Mundt , Russell King , linux-arm-kernel@lists.infradead.org, linux-sh@vger.kernel.org, Peter Zijlstra , Ingo Molnar , Frederic Weisbecker , Arnaldo Carvalho de Melo , linux-arch@vger.kernel.org Subject: [PATCH 4/6] oprofile: Abstract the perf-events backend Date: Mon, 13 Sep 2010 07:07:35 +0100 Message-Id: <490b61c044891ab1c85761143a3b093b15986bbb.1284357372.git.matt@console-pimps.org> X-Mailer: git-send-email 1.7.1 In-Reply-To: References: In-Reply-To: References: Sender: linux-sh-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-sh@vger.kernel.org X-Greylist: IP, sender and recipient auto-whitelisted, not delayed by milter-greylist-4.2.3 (demeter1.kernel.org [140.211.167.41]); Mon, 13 Sep 2010 06:07:48 +0000 (UTC) diff --git a/arch/arm/oprofile/Makefile b/arch/arm/oprofile/Makefile index e666eaf..07c93f6 100644 --- a/arch/arm/oprofile/Makefile +++ b/arch/arm/oprofile/Makefile @@ -4,6 +4,6 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \ oprof.o cpu_buffer.o buffer_sync.o \ event_buffer.o oprofile_files.o \ oprofilefs.o oprofile_stats.o \ - timer_int.o ) + timer_int.o oprofile_perf.o ) oprofile-y := $(DRIVER_OBJS) common.o diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c index 4d814c3..9a3ed26 100644 --- a/arch/arm/oprofile/common.c +++ b/arch/arm/oprofile/common.c @@ -25,135 +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]; - -/* - * 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 < perf_num_counters(); ++id) - if (perf_events[cpu][id] == event) - break; - - if (id != perf_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 < perf_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 < perf_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 < perf_num_counters(); ++event) - op_destroy_counter(cpu, event); -} - - static char *op_name_from_perf_id(enum arm_perf_pmu_ids id) { switch (id) { @@ -174,116 +45,6 @@ static char *op_name_from_perf_id(enum arm_perf_pmu_ids id) } } -static int oprofile_perf_create_files(struct super_block *sb, struct dentry *root) -{ - unsigned int i; - - for (i = 0; i < perf_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 = "perf-oprofile", - }, - .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; @@ -346,63 +107,6 @@ 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)); - - counter_config = kcalloc(perf_num_counters(), - sizeof(struct op_counter_config), GFP_KERNEL); - - if (!counter_config) { - pr_info("oprofile: failed to allocate %d " - "counters\n", perf_num_counters()); - ret = -ENOMEM; - goto out; - } - - ret = init_driverfs(); - if (ret) - goto out; - - for_each_possible_cpu(cpu) { - perf_events[cpu] = kcalloc(perf_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); - ret = -ENOMEM; - goto out; - } - } - - if (!ops->create_files) - ops->create_files = oprofile_perf_create_files; - if (!ops->setup) - ops->setup = oprofile_perf_setup; - if (!ops->start) - ops->start = oprofile_perf_start; - if (!ops->stop) - ops->stop = oprofile_perf_stop; - if (!ops->shutdown) - ops->shutdown = oprofile_perf_stop; - - 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; @@ -411,25 +115,6 @@ 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 < perf_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 0000000..46d7b76 --- /dev/null +++ b/drivers/oprofile/oprofile_perf.c @@ -0,0 +1,322 @@ +/* + * 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]; + +/* + * 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 < perf_num_counters(); ++id) + if (perf_events[cpu][id] == event) + break; + + if (id != perf_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 < perf_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 < perf_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 < perf_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 < perf_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 = "perf-oprofile", + }, + .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)); + + counter_config = kcalloc(perf_num_counters(), + sizeof(struct op_counter_config), GFP_KERNEL); + + if (!counter_config) { + pr_info("oprofile: failed to allocate %d " + "counters\n", perf_num_counters()); + ret = -ENOMEM; + goto out; + } + + ret = init_driverfs(); + if (ret) + goto out; + + for_each_possible_cpu(cpu) { + perf_events[cpu] = kcalloc(perf_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); + ret = -ENOMEM; + goto out; + } + } + + if (!ops->create_files) + ops->create_files = oprofile_perf_create_files; + if (!ops->setup) + ops->setup = oprofile_perf_setup; + if (!ops->start) + ops->start = oprofile_perf_start; + if (!ops->stop) + ops->stop = oprofile_perf_stop; + if (!ops->shutdown) + ops->shutdown = oprofile_perf_stop; + + 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 < perf_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 5171639..a53bfc0 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 @@ -185,4 +186,9 @@ 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 +int __init oprofile_perf_init(struct oprofile_operations *ops); +void __exit oprofile_perf_exit(void); +#endif /* CONFIG_PERF_EVENTS */ + #endif /* OPROFILE_H */