diff options
Diffstat (limited to 'drivers/oprofile')
-rw-r--r-- | drivers/oprofile/buffer_sync.c | 27 | ||||
-rw-r--r-- | drivers/oprofile/cpu_buffer.c | 65 |
2 files changed, 27 insertions, 65 deletions
diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c index c9e2ae90f195..5c4df24eae4b 100644 --- a/drivers/oprofile/buffer_sync.c +++ b/drivers/oprofile/buffer_sync.c @@ -140,16 +140,6 @@ static struct notifier_block module_load_nb = { .notifier_call = module_load_notify, }; - -static void end_sync(void) -{ - end_cpu_work(); - /* make sure we don't leak task structs */ - process_task_mortuary(); - process_task_mortuary(); -} - - int sync_start(void) { int err; @@ -157,7 +147,7 @@ int sync_start(void) if (!zalloc_cpumask_var(&marked_cpus, GFP_KERNEL)) return -ENOMEM; - start_cpu_work(); + mutex_lock(&buffer_mutex); err = task_handoff_register(&task_free_nb); if (err) @@ -172,7 +162,10 @@ int sync_start(void) if (err) goto out4; + start_cpu_work(); + out: + mutex_unlock(&buffer_mutex); return err; out4: profile_event_unregister(PROFILE_MUNMAP, &munmap_nb); @@ -181,7 +174,6 @@ out3: out2: task_handoff_unregister(&task_free_nb); out1: - end_sync(); free_cpumask_var(marked_cpus); goto out; } @@ -189,11 +181,20 @@ out1: void sync_stop(void) { + /* flush buffers */ + mutex_lock(&buffer_mutex); + end_cpu_work(); unregister_module_notifier(&module_load_nb); profile_event_unregister(PROFILE_MUNMAP, &munmap_nb); profile_event_unregister(PROFILE_TASK_EXIT, &task_exit_nb); task_handoff_unregister(&task_free_nb); - end_sync(); + mutex_unlock(&buffer_mutex); + flush_scheduled_work(); + + /* make sure we don't leak task structs */ + process_task_mortuary(); + process_task_mortuary(); + free_cpumask_var(marked_cpus); } diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c index a7aae24f2889..5e2ac4aea949 100644 --- a/drivers/oprofile/cpu_buffer.c +++ b/drivers/oprofile/cpu_buffer.c @@ -30,23 +30,7 @@ #define OP_BUFFER_FLAGS 0 -/* - * Read and write access is using spin locking. Thus, writing to the - * buffer by NMI handler (x86) could occur also during critical - * sections when reading the buffer. To avoid this, there are 2 - * buffers for independent read and write access. Read access is in - * process context only, write access only in the NMI handler. If the - * read buffer runs empty, both buffers are swapped atomically. There - * is potentially a small window during swapping where the buffers are - * disabled and samples could be lost. - * - * Using 2 buffers is a little bit overhead, but the solution is clear - * and does not require changes in the ring buffer implementation. It - * can be changed to a single buffer solution when the ring buffer - * access is implemented as non-locking atomic code. - */ -static struct ring_buffer *op_ring_buffer_read; -static struct ring_buffer *op_ring_buffer_write; +static struct ring_buffer *op_ring_buffer; DEFINE_PER_CPU(struct oprofile_cpu_buffer, cpu_buffer); static void wq_sync_buffer(struct work_struct *work); @@ -69,12 +53,9 @@ void oprofile_cpu_buffer_inc_smpl_lost(void) void free_cpu_buffers(void) { - if (op_ring_buffer_read) - ring_buffer_free(op_ring_buffer_read); - op_ring_buffer_read = NULL; - if (op_ring_buffer_write) - ring_buffer_free(op_ring_buffer_write); - op_ring_buffer_write = NULL; + if (op_ring_buffer) + ring_buffer_free(op_ring_buffer); + op_ring_buffer = NULL; } #define RB_EVENT_HDR_SIZE 4 @@ -87,11 +68,8 @@ int alloc_cpu_buffers(void) unsigned long byte_size = buffer_size * (sizeof(struct op_sample) + RB_EVENT_HDR_SIZE); - op_ring_buffer_read = ring_buffer_alloc(byte_size, OP_BUFFER_FLAGS); - if (!op_ring_buffer_read) - goto fail; - op_ring_buffer_write = ring_buffer_alloc(byte_size, OP_BUFFER_FLAGS); - if (!op_ring_buffer_write) + op_ring_buffer = ring_buffer_alloc(byte_size, OP_BUFFER_FLAGS); + if (!op_ring_buffer) goto fail; for_each_possible_cpu(i) { @@ -143,8 +121,6 @@ void end_cpu_work(void) cancel_delayed_work(&b->work); } - - flush_scheduled_work(); } /* @@ -163,16 +139,11 @@ struct op_sample *op_cpu_buffer_write_reserve(struct op_entry *entry, unsigned long size) { entry->event = ring_buffer_lock_reserve - (op_ring_buffer_write, sizeof(struct op_sample) + + (op_ring_buffer, sizeof(struct op_sample) + size * sizeof(entry->sample->data[0])); - if (entry->event) - entry->sample = ring_buffer_event_data(entry->event); - else - entry->sample = NULL; - - if (!entry->sample) + if (!entry->event) return NULL; - + entry->sample = ring_buffer_event_data(entry->event); entry->size = size; entry->data = entry->sample->data; @@ -181,25 +152,16 @@ struct op_sample int op_cpu_buffer_write_commit(struct op_entry *entry) { - return ring_buffer_unlock_commit(op_ring_buffer_write, entry->event); + return ring_buffer_unlock_commit(op_ring_buffer, entry->event); } struct op_sample *op_cpu_buffer_read_entry(struct op_entry *entry, int cpu) { struct ring_buffer_event *e; - e = ring_buffer_consume(op_ring_buffer_read, cpu, NULL); - if (e) - goto event; - if (ring_buffer_swap_cpu(op_ring_buffer_read, - op_ring_buffer_write, - cpu)) + e = ring_buffer_consume(op_ring_buffer, cpu, NULL); + if (!e) return NULL; - e = ring_buffer_consume(op_ring_buffer_read, cpu, NULL); - if (e) - goto event; - return NULL; -event: entry->event = e; entry->sample = ring_buffer_event_data(e); entry->size = (ring_buffer_event_length(e) - sizeof(struct op_sample)) @@ -210,8 +172,7 @@ event: unsigned long op_cpu_buffer_entries(int cpu) { - return ring_buffer_entries_cpu(op_ring_buffer_read, cpu) - + ring_buffer_entries_cpu(op_ring_buffer_write, cpu); + return ring_buffer_entries_cpu(op_ring_buffer, cpu); } static int |