perf: Add perf_event_mmap_page::cap_user_time_short ABI

In order to support short clock counters, provide an ABI extension.

As a whole:

    u64 time, delta, cyc = read_cycle_counter();

+   if (cap_user_time_short)
+	cyc = time_cycle + ((cyc - time_cycle) & time_mask);

    delta = mul_u64_u32_shr(cyc, time_mult, time_shift);

    if (cap_user_time_zero)
	time = time_zero + delta;

    delta += time_offset;
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Leo Yan <leo.yan@linaro.org>
Link: https://lore.kernel.org/r/20200716051130.4359-6-leo.yan@linaro.orgSigned-off-by: Will Deacon <will@kernel.org>

include/uapi/linux/perf_event.h

@@ -532,9 +532,10 @@ struct perf_event_mmap_page {
 				cap_bit0_is_deprecated	: 1, /* Always 1, signals that bit 0 is zero */
 
 				cap_user_rdpmc		: 1, /* The RDPMC instruction can be used to read counts */
-				cap_user_time		: 1, /* The time_* fields are used */
+				cap_user_time		: 1, /* The time_{shift,mult,offset} fields are used */
 				cap_user_time_zero	: 1, /* The time_zero field is used */
-				cap_____res		: 59;
+				cap_user_time_short	: 1, /* the time_{cycle,mask} fields are used */
+				cap_____res		: 58;
 		};
 	};
 
@@ -593,13 +594,29 @@ struct perf_event_mmap_page {
 	 *               ((rem * time_mult) >> time_shift);
 	 */
 	__u64	time_zero;
+
 	__u32	size;			/* Header size up to __reserved[] fields. */
+	__u32	__reserved_1;
+
+	/*
+	 * If cap_usr_time_short, the hardware clock is less than 64bit wide
+	 * and we must compute the 'cyc' value, as used by cap_usr_time, as:
+	 *
+	 *   cyc = time_cycles + ((cyc - time_cycles) & time_mask)
+	 *
+	 * NOTE: this form is explicitly chosen such that cap_usr_time_short
+	 *       is a correction on top of cap_usr_time, and code that doesn't
+	 *       know about cap_usr_time_short still works under the assumption
+	 *       the counter doesn't wrap.
+	 */
+	__u64	time_cycles;
+	__u64	time_mask;
 
 		/*
 		 * Hole for extension of the self monitor capabilities
 		 */
 
-	__u8	__reserved[118*8+4];	/* align to 1k. */
+	__u8	__reserved[116*8];	/* align to 1k. */
 
 	/*
 	 * Control data for the mmap() data buffer.