perf_counter: new output ABI - part 1

Impact: Rework the perfcounter output ABI

use sys_read() only for instant data and provide mmap() output for all
async overflow data.

The first mmap() determines the size of the output buffer. The mmap()
size must be a PAGE_SIZE multiple of 1+pages, where pages must be a
power of 2 or 0. Further mmap()s of the same fd must have the same
size. Once all maps are gone, you can again mmap() with a new size.

In case of 0 extra pages there is no data output and the first page
only contains meta data.

When there are data pages, a poll() event will be generated for each
full page of data. Furthermore, the output is circular. This means
that although 1 page is a valid configuration, its useless, since
we'll start overwriting it the instant we report a full page.

Future work will focus on the output format (currently maintained)
where we'll likey want each entry denoted by a header which includes a
type and length.

Further future work will allow to splice() the fd, also containing the
async overflow data -- splice() would be mutually exclusive with
mmap() of the data.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Orig-LKML-Reference: <20090323172417.470536358@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/powerpc/kernel/perf_counter.c

@@ -417,8 +417,7 @@ 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);
+		perf_counter_update_userpage(counter);
 	}
 	mb();
 	cpuhw->mmcr[0] |= MMCR0_PMXE | MMCR0_FCECE;
@@ -574,8 +573,7 @@ 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);
+			perf_counter_update_userpage(counter);
 			break;
 		}
 	}
@@ -702,8 +700,7 @@ 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);
+	perf_counter_update_userpage(counter);
 
 	/*
 	 * Finally record data if requested.

include/linux/perf_counter.h

@@ -152,6 +152,8 @@ struct perf_counter_mmap_page {
 	__u32	lock;			/* seqlock for synchronization */
 	__u32	index;			/* hardware counter identifier */
 	__s64	offset;			/* add to hardware counter value */
+
+	__u32   data_head;		/* head in the data section */
 };
 
 #ifdef __KERNEL__
@@ -218,21 +220,6 @@ struct hw_perf_counter {
 #endif
 };
 
-/*
- * Hardcoded buffer length limit for now, for IRQ-fed events:
- */
-#define PERF_DATA_BUFLEN		2048
-
-/**
- * struct perf_data - performance counter IRQ data sampling ...
- */
-struct perf_data {
-	int				len;
-	int				rd_idx;
-	int				overrun;
-	u8				data[PERF_DATA_BUFLEN];
-};
-
 struct perf_counter;
 
 /**
@@ -256,6 +243,14 @@ enum perf_counter_active_state {
 
 struct file;
 
+struct perf_mmap_data {
+	struct rcu_head			rcu_head;
+	int				nr_pages;
+	atomic_t			head;
+	struct perf_counter_mmap_page   *user_page;
+	void 				*data_pages[0];
+};
+
 /**
  * struct perf_counter - performance counter kernel representation:
  */
@@ -289,16 +284,15 @@ struct perf_counter {
 	int				oncpu;
 	int				cpu;
 
-	/* pointer to page shared with userspace via mmap */
-	unsigned long			user_page;
+	/* mmap bits */
+	struct mutex			mmap_mutex;
+	atomic_t			mmap_count;
+	struct perf_mmap_data		*data;
 
-	/* read() / irq related data */
+	/* poll related */
 	wait_queue_head_t		waitq;
 	/* optional: for NMIs */
 	int				wakeup_pending;
-	struct perf_data		*irqdata;
-	struct perf_data		*usrdata;
-	struct perf_data		data[2];
 
 	void (*destroy)(struct perf_counter *);
 	struct rcu_head			rcu_head;