perf_counter: add an mmap method to allow userspace to read hardware counters

Impact: new feature giving performance improvement

This adds the ability for userspace to do an mmap on a hardware counter
fd and get access to a read-only page that contains the information
needed to translate a hardware counter value to the full 64-bit
counter value that would be returned by a read on the fd.  This is
useful on architectures that allow user programs to read the hardware
counters, such as PowerPC.

The mmap will only succeed if the counter is a hardware counter
monitoring the current process.

On my quad 2.5GHz PowerPC 970MP machine, userspace can read a counter
and translate it to the full 64-bit value in about 30ns using the
mmapped page, compared to about 830ns for the read syscall on the
counter, so this does give a significant performance improvement.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Orig-LKML-Reference: <20090323172417.297057964@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/arch/powerpc/kernel/perf_counter.c b/arch/powerpc/kernel/perf_counter.c
index d056515..e434928 100644 (file)
--- a/arch/powerpc/kernel/perf_counter.c
+++ b/arch/powerpc/kernel/perf_counter.c
@@ -417,6 +417,8 @@ void hw_perf_restore(u64 disable)
                atomic64_set(&counter->hw.prev_count, val);
                counter->hw.idx = hwc_index[i] + 1;
                write_pmc(counter->hw.idx, val);
+               if (counter->user_page)
+                       perf_counter_update_userpage(counter);
        }
        mb();
        cpuhw->mmcr[0] |= MMCR0_PMXE | MMCR0_FCECE;
@@ -572,6 +574,8 @@ static void power_perf_disable(struct perf_counter *counter)
                        ppmu->disable_pmc(counter->hw.idx - 1, cpuhw->mmcr);
                        write_pmc(counter->hw.idx, 0);
                        counter->hw.idx = 0;
+                       if (counter->user_page)
+                               perf_counter_update_userpage(counter);
                        break;
                }
        }
@@ -698,6 +702,8 @@ static void record_and_restart(struct perf_counter *counter, long val,
        write_pmc(counter->hw.idx, val);
        atomic64_set(&counter->hw.prev_count, val);
        atomic64_set(&counter->hw.period_left, left);
+       if (counter->user_page)
+               perf_counter_update_userpage(counter);
 
        /*
         * Finally record data if requested.

diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index 18dc17d..40b324e 100644 (file)
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -143,6 +143,17 @@ struct perf_counter_hw_event {
 #define PERF_COUNTER_IOC_ENABLE                _IO('$', 0)
 #define PERF_COUNTER_IOC_DISABLE       _IO('$', 1)
 
+/*
+ * Structure of the page that can be mapped via mmap
+ */
+struct perf_counter_mmap_page {
+       __u32   version;                /* version number of this structure */
+       __u32   compat_version;         /* lowest version this is compat with */
+       __u32   lock;                   /* seqlock for synchronization */
+       __u32   index;                  /* hardware counter identifier */
+       __s64   offset;                 /* add to hardware counter value */
+};
+
 #ifdef __KERNEL__
 /*
  * Kernel-internal data types and definitions:
@@ -278,6 +289,9 @@ struct perf_counter {
        int                             oncpu;
        int                             cpu;
 
+       /* pointer to page shared with userspace via mmap */
+       unsigned long                   user_page;
+
        /* read() / irq related data */
        wait_queue_head_t               waitq;
        /* optional: for NMIs */
@@ -361,6 +375,7 @@ extern int perf_counter_task_enable(void);
 extern int hw_perf_group_sched_in(struct perf_counter *group_leader,
               struct perf_cpu_context *cpuctx,
               struct perf_counter_context *ctx, int cpu);
+extern void perf_counter_update_userpage(struct perf_counter *counter);
 
 extern void perf_counter_output(struct perf_counter *counter,
                                int nmi, struct pt_regs *regs);

diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index ce34bff..d9cfd90 100644 (file)
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -1177,6 +1177,7 @@ static int perf_release(struct inode *inode, struct file *file)
        mutex_unlock(&counter->mutex);
        mutex_unlock(&ctx->mutex);
 
+       free_page(counter->user_page);
        free_counter(counter);
        put_context(ctx);
 
@@ -1346,12 +1347,87 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
        return err;
 }
 
+void perf_counter_update_userpage(struct perf_counter *counter)
+{
+       struct perf_counter_mmap_page *userpg;
+
+       if (!counter->user_page)
+               return;
+       userpg = (struct perf_counter_mmap_page *) counter->user_page;
+
+       ++userpg->lock;
+       smp_wmb();
+       userpg->index = counter->hw.idx;
+       userpg->offset = atomic64_read(&counter->count);
+       if (counter->state == PERF_COUNTER_STATE_ACTIVE)
+               userpg->offset -= atomic64_read(&counter->hw.prev_count);
+       smp_wmb();
+       ++userpg->lock;
+}
+
+static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+       struct perf_counter *counter = vma->vm_file->private_data;
+
+       if (!counter->user_page)
+               return VM_FAULT_SIGBUS;
+
+       vmf->page = virt_to_page(counter->user_page);
+       get_page(vmf->page);
+       return 0;
+}
+
+static struct vm_operations_struct perf_mmap_vmops = {
+       .fault = perf_mmap_fault,
+};
+
+static int perf_mmap(struct file *file, struct vm_area_struct *vma)
+{
+       struct perf_counter *counter = file->private_data;
+       unsigned long userpg;
+
+       if (!(vma->vm_flags & VM_SHARED) || (vma->vm_flags & VM_WRITE))
+               return -EINVAL;
+       if (vma->vm_end - vma->vm_start != PAGE_SIZE)
+               return -EINVAL;
+
+       /*
+        * For now, restrict to the case of a hardware counter
+        * on the current task.
+        */
+       if (is_software_counter(counter) || counter->task != current)
+               return -EINVAL;
+
+       userpg = counter->user_page;
+       if (!userpg) {
+               userpg = get_zeroed_page(GFP_KERNEL);
+               mutex_lock(&counter->mutex);
+               if (counter->user_page) {
+                       free_page(userpg);
+                       userpg = counter->user_page;
+               } else {
+                       counter->user_page = userpg;
+               }
+               mutex_unlock(&counter->mutex);
+               if (!userpg)
+                       return -ENOMEM;
+       }
+
+       perf_counter_update_userpage(counter);
+
+       vma->vm_flags &= ~VM_MAYWRITE;
+       vma->vm_flags |= VM_RESERVED;
+       vma->vm_ops = &perf_mmap_vmops;
+       return 0;
+}
+
 static const struct file_operations perf_fops = {
        .release                = perf_release,
        .read                   = perf_read,
        .poll                   = perf_poll,
        .unlocked_ioctl         = perf_ioctl,
        .compat_ioctl           = perf_ioctl,
+       .mmap                   = perf_mmap,
 };
 
 /*