sched_clock: Expose struct clock_read_data

In order to support perf_event_mmap_page::cap_time features, an
architecture needs, aside from a userspace readable counter register,
to expose the exact clock data so that userspace can convert the
counter register into a correct timestamp.

Provide struct clock_read_data and two (seqcount) helpers so that
architectures (arm64 in specific) can expose the numbers to userspace.

Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Leo Yan <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Will Deacon <[email protected]>

Author: Peter Zijlstra

include/linux/sched_clock.h

@@ -6,6 +6,34 @@
 #define LINUX_SCHED_CLOCK
 
 #ifdef CONFIG_GENERIC_SCHED_CLOCK
+/**
+ * struct clock_read_data - data required to read from sched_clock()
+ *
+ * @epoch_ns:		sched_clock() value at last update
+ * @epoch_cyc:		Clock cycle value at last update.
+ * @sched_clock_mask:   Bitmask for two's complement subtraction of non 64bit
+ *			clocks.
+ * @read_sched_clock:	Current clock source (or dummy source when suspended).
+ * @mult:		Multipler for scaled math conversion.
+ * @shift:		Shift value for scaled math conversion.
+ *
+ * Care must be taken when updating this structure; it is read by
+ * some very hot code paths. It occupies <=40 bytes and, when combined
+ * with the seqcount used to synchronize access, comfortably fits into
+ * a 64 byte cache line.
+ */
+struct clock_read_data {
+	u64 epoch_ns;
+	u64 epoch_cyc;
+	u64 sched_clock_mask;
+	u64 (*read_sched_clock)(void);
+	u32 mult;
+	u32 shift;
+};
+
+extern struct clock_read_data *sched_clock_read_begin(unsigned int *seq);
+extern int sched_clock_read_retry(unsigned int seq);
+
 extern void generic_sched_clock_init(void);
 
 extern void sched_clock_register(u64 (*read)(void), int bits,

kernel/time/sched_clock.c

@@ -19,31 +19,6 @@
 
 #include "timekeeping.h"
 
-/**
- * struct clock_read_data - data required to read from sched_clock()
- *
- * @epoch_ns:		sched_clock() value at last update
- * @epoch_cyc:		Clock cycle value at last update.
- * @sched_clock_mask:   Bitmask for two's complement subtraction of non 64bit
- *			clocks.
- * @read_sched_clock:	Current clock source (or dummy source when suspended).
- * @mult:		Multipler for scaled math conversion.
- * @shift:		Shift value for scaled math conversion.
- *
- * Care must be taken when updating this structure; it is read by
- * some very hot code paths. It occupies <=40 bytes and, when combined
- * with the seqcount used to synchronize access, comfortably fits into
- * a 64 byte cache line.
- */
-struct clock_read_data {
-	u64 epoch_ns;
-	u64 epoch_cyc;
-	u64 sched_clock_mask;
-	u64 (*read_sched_clock)(void);
-	u32 mult;
-	u32 shift;
-};
-
 /**
  * struct clock_data - all data needed for sched_clock() (including
  *                     registration of a new clock source)
@@ -93,20 +68,30 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 	return (cyc * mult) >> shift;
 }
 
+struct clock_read_data *sched_clock_read_begin(unsigned int *seq)
+{
+	*seq = raw_read_seqcount(&cd.seq);
+	return cd.read_data + (*seq & 1);
+}
+
+int sched_clock_read_retry(unsigned int seq)
+{
+	return read_seqcount_retry(&cd.seq, seq);
+}
+
 unsigned long long notrace sched_clock(void)
 {
 	u64 cyc, res;
 	unsigned int seq;
 	struct clock_read_data *rd;
 
 	do {
-		seq = raw_read_seqcount(&cd.seq);
-		rd = cd.read_data + (seq & 1);
+		rd = sched_clock_read_begin(&seq);
 
 		cyc = (rd->read_sched_clock() - rd->epoch_cyc) &
 		      rd->sched_clock_mask;
 		res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift);
-	} while (read_seqcount_retry(&cd.seq, seq));
+	} while (sched_clock_read_retry(seq));
 
 	return res;
 }