4 files changed, 102 insertions, 66 deletions

diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c
index 7581dbe456da..219f79e2210a 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, op_cpu_buffer);
 
 static void wq_sync_buffer(struct work_struct *work);
@@ -68,12 +52,9 @@ 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
@@ -86,11 +67,8 @@ 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) {
@@ -162,16 +140,11 @@ 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;
 
@@ -180,25 +153,16 @@ 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, 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, NULL);
+        if (!e)
                 return NULL;
-        e = ring_buffer_consume(op_ring_buffer_read, cpu, NULL, 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))
@@ -209,8 +173,7 @@ 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
@@ -356,8 +319,16 @@ void oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
 
 void oprofile_add_sample(struct pt_regs * const regs, unsigned long event)
 {
-        int is_kernel = !user_mode(regs);
-        unsigned long pc = profile_pc(regs);
+        int is_kernel;
+        unsigned long pc;
+
+        if (likely(regs)) {
+                is_kernel = !user_mode(regs);
+                pc = profile_pc(regs);
+        } else {
+                is_kernel = 0;    /* This value will not be used */
+                pc = ESCAPE_CODE; /* as this causes an early return. */
+        }
 
         __oprofile_add_ext_sample(pc, regs, event, is_kernel);
 }
diff --git a/drivers/oprofile/oprof.c b/drivers/oprofile/oprof.c
index dc8a0428260d..b336cd9ee7a1 100644
--- a/drivers/oprofile/oprof.c
+++ b/drivers/oprofile/oprof.c
@@ -253,22 +253,26 @@ static int __init oprofile_init(void)
         int err;
 
         err = oprofile_arch_init(&oprofile_ops);
-
         if (err < 0 || timer) {
                 printk(KERN_INFO "oprofile: using timer interrupt.\n");
-                oprofile_timer_init(&oprofile_ops);
+                err = oprofile_timer_init(&oprofile_ops);
+                if (err)
+                        goto out_arch;
         }
-
         err = oprofilefs_register();
         if (err)
-                oprofile_arch_exit();
+                goto out_arch;
+        return 0;
 
+out_arch:
+        oprofile_arch_exit();
         return err;
 }
 
 
 static void __exit oprofile_exit(void)
 {
+        oprofile_timer_exit();
         oprofilefs_unregister();
         oprofile_arch_exit();
 }
diff --git a/drivers/oprofile/oprof.h b/drivers/oprofile/oprof.h
index cb92f5c98c1a..47e12cb4ee8b 100644
--- a/drivers/oprofile/oprof.h
+++ b/drivers/oprofile/oprof.h
@@ -34,7 +34,8 @@ struct super_block;
 struct dentry;
 
 void oprofile_create_files(struct super_block *sb, struct dentry *root);
-void oprofile_timer_init(struct oprofile_operations *ops);
+int oprofile_timer_init(struct oprofile_operations *ops);
+void oprofile_timer_exit(void);
 
 int oprofile_set_backtrace(unsigned long depth);
 int oprofile_set_timeout(unsigned long time);
diff --git a/drivers/oprofile/timer_int.c b/drivers/oprofile/timer_int.c
index 333f915568c7..dc0ae4d14dff 100644
--- a/drivers/oprofile/timer_int.c
+++ b/drivers/oprofile/timer_int.c
@@ -13,34 +13,94 @@
 #include <linux/oprofile.h>
 #include <linux/profile.h>
 #include <linux/init.h>
+#include <linux/cpu.h>
+#include <linux/hrtimer.h>
+#include <asm/irq_regs.h>
 #include <asm/ptrace.h>
 
 #include "oprof.h"
 
-static int timer_notify(struct pt_regs *regs)
+static DEFINE_PER_CPU(struct hrtimer, oprofile_hrtimer);
+
+static enum hrtimer_restart oprofile_hrtimer_notify(struct hrtimer *hrtimer)
+{
+        oprofile_add_sample(get_irq_regs(), 0);
+        hrtimer_forward_now(hrtimer, ns_to_ktime(TICK_NSEC));
+        return HRTIMER_RESTART;
+}
+
+static void __oprofile_hrtimer_start(void *unused)
+{
+        struct hrtimer *hrtimer = &__get_cpu_var(oprofile_hrtimer);
+
+        hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+        hrtimer->function = oprofile_hrtimer_notify;
+
+        hrtimer_start(hrtimer, ns_to_ktime(TICK_NSEC),
+                      HRTIMER_MODE_REL_PINNED);
+}
+
+static int oprofile_hrtimer_start(void)
 {
-        oprofile_add_sample(regs, 0);
+        on_each_cpu(__oprofile_hrtimer_start, NULL, 1);
         return 0;
 }
 
-static int timer_start(void)
+static void __oprofile_hrtimer_stop(int cpu)
 {
-        return register_timer_hook(timer_notify);
+        struct hrtimer *hrtimer = &per_cpu(oprofile_hrtimer, cpu);
+
+        hrtimer_cancel(hrtimer);
 }
 
+static void oprofile_hrtimer_stop(void)
+{
+        int cpu;
+
+        for_each_online_cpu(cpu)
+                __oprofile_hrtimer_stop(cpu);
+}
 
-static void timer_stop(void)
+static int __cpuinit oprofile_cpu_notify(struct notifier_block *self,
+                                         unsigned long action, void *hcpu)
 {
-        unregister_timer_hook(timer_notify);
+        long cpu = (long) hcpu;
+
+        switch (action) {
+        case CPU_ONLINE:
+        case CPU_ONLINE_FROZEN:
+                smp_call_function_single(cpu, __oprofile_hrtimer_start,
+                                         NULL, 1);
+                break;
+        case CPU_DEAD:
+        case CPU_DEAD_FROZEN:
+                __oprofile_hrtimer_stop(cpu);
+                break;
+        }
+        return NOTIFY_OK;
 }
 
+static struct notifier_block __refdata oprofile_cpu_notifier = {
+        .notifier_call = oprofile_cpu_notify,
+};
 
-void __init oprofile_timer_init(struct oprofile_operations *ops)
+int __init oprofile_timer_init(struct oprofile_operations *ops)
 {
+        int rc;
+
+        rc = register_hotcpu_notifier(&oprofile_cpu_notifier);
+        if (rc)
+                return rc;
         ops->create_files = NULL;
         ops->setup = NULL;
         ops->shutdown = NULL;
-        ops->start = timer_start;
-        ops->stop = timer_stop;
+        ops->start = oprofile_hrtimer_start;
+        ops->stop = oprofile_hrtimer_stop;
         ops->cpu_type = "timer";
+        return 0;
+}
+
+void __exit oprofile_timer_exit(void)
+{
+        unregister_hotcpu_notifier(&oprofile_cpu_notifier);
 }