[PATCH v5] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

[Santosh Sivaraj]

Current vDSO64 implementation does not have support for coarse clocks
(CLOCK_MONOTONIC_COARSE, CLOCK_REALTIME_COARSE), for which it falls back
to system call, increasing the response time, vDSO implementation reduces
the cycle time. Below is a benchmark of the difference in execution times.

(Non-coarse clocks are also included just for completion)

clock-gettime-realtime: syscall: 172 nsec/call
clock-gettime-realtime:    libc: 28 nsec/call
clock-gettime-realtime:    vdso: 22 nsec/call
clock-gettime-monotonic: syscall: 171 nsec/call
clock-gettime-monotonic:    libc: 30 nsec/call
clock-gettime-monotonic:    vdso: 25 nsec/call
clock-gettime-realtime-coarse: syscall: 153 nsec/call
clock-gettime-realtime-coarse:    libc: 16 nsec/call
clock-gettime-realtime-coarse:    vdso: 10 nsec/call
clock-gettime-monotonic-coarse: syscall: 167 nsec/call
clock-gettime-monotonic-coarse:    libc: 17 nsec/call
clock-gettime-monotonic-coarse:    vdso: 11 nsec/call

CC: Benjamin Herrenschmidt <benh at kernel.crashing.org>
Signed-off-by: Santosh Sivaraj <santosh at fossix.org>
---
Changelog:
v1:
- gettimeofday was moved from asm to C
- Coarse timer support addition
v2:
- Moved Syscall fallback from inline assembly back to its original place in
  __kernel_clock_gettime
v3:
- Based on Ben's input, coarse timer support was added in assembly itself
- Dropped idea of conversion to C due to the vdso update_count variable
  being optimized out in C
v4:
- Based on Naveen's comments restructured code to avoid a duplicate code
  block
v5:
- Skip creating dependency for registers that are not used for
  CLOCK_REALTIME_COARSE (Naveen)
- Reorder instructions to get proper dependency setup (Naveen)

 arch/powerpc/kernel/asm-offsets.c         |  2 +
 arch/powerpc/kernel/vdso64/gettimeofday.S | 68 ++++++++++++++++++++++++++-----
 2 files changed, 59 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 8cfb20e38cfe..b55c68c54dc1 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -396,6 +396,8 @@ int main(void)
 	/* Other bits used by the vdso */
 	DEFINE(CLOCK_REALTIME, CLOCK_REALTIME);
 	DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
+	DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
+	DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
 	DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
 	DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
 
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index 382021324883..058e7c24f670 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -64,6 +64,12 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	cmpwi	cr0,r3,CLOCK_REALTIME
 	cmpwi	cr1,r3,CLOCK_MONOTONIC
 	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
+
+	cmpwi	cr5,r3,CLOCK_REALTIME_COARSE
+	cmpwi	cr6,r3,CLOCK_MONOTONIC_COARSE
+	cror	cr5*4+eq,cr5*4+eq,cr6*4+eq
+
+	cror	cr0*4+eq,cr0*4+eq,cr5*4+eq
 	bne	cr0,99f
 
 	mflr	r12			/* r12 saves lr */
@@ -72,6 +78,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	bl	V_LOCAL_FUNC(__get_datapage)	/* get data page */
 	lis	r7,NSEC_PER_SEC at h	/* want nanoseconds */
 	ori	r7,r7,NSEC_PER_SEC at l
+	beq	cr5,70f
 50:	bl	V_LOCAL_FUNC(__do_get_tspec)	/* get time from tb & kernel */
 	bne	cr1,80f			/* if not monotonic, all done */
 
@@ -97,19 +104,58 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	ld	r0,CFG_TB_UPDATE_COUNT(r3)
         cmpld   cr0,r0,r8		/* check if updated */
 	bne-	50b
+	b	78f
 
-	/* Add wall->monotonic offset and check for overflow or underflow.
+	/*
+	 * For coarse clocks we get data directly from the vdso data page, so
+	 * we don't need to call __do_get_tspec, but we still need to do the
+	 * counter trick.
 	 */
-	add	r4,r4,r6
-	add	r5,r5,r9
-	cmpd	cr0,r5,r7
-	cmpdi	cr1,r5,0
-	blt	1f
-	subf	r5,r7,r5
-	addi	r4,r4,1
-1:	bge	cr1,80f
-	addi	r4,r4,-1
-	add	r5,r5,r7
+70:	ld      r8,CFG_TB_UPDATE_COUNT(r3)
+	andi.   r0,r8,1                 /* pending update ? loop */
+	bne-    70b
+	xor     r0,r8,r8                /* create dependency */
+	add     r3,r3,r0
+
+	/*
+	 * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
+	 * too
+	 */
+	ld      r4,STAMP_XTIME+TSPC64_TV_SEC(r3)
+	ld      r5,STAMP_XTIME+TSPC64_TV_NSEC(r3)
+	bne     cr6,75f
+
+	/* CLOCK_MONOTONIC_COARSE */
+	lwa     r6,WTOM_CLOCK_SEC(r3)
+	lwa     r9,WTOM_CLOCK_NSEC(r3)
+
+	/* check if counter has updated */
+	or      r0,r6,r9
+75:	or	r0,r0,r4
+	or	r0,r0,r5
+	xor     r0,r0,r0
+	add     r3,r3,r0
+	ld      r0,CFG_TB_UPDATE_COUNT(r3)
+	cmpld   cr0,r0,r8               /* check if updated */
+	bne-    70b
+
+	/* Counter has not updated, so continue calculating proper values for
+	 * sec and nsec if monotonic coarse, or just return with the proper
+	 * values for realtime.
+	 */
+	bne     cr6,80f
+
+	/* Add wall->monotonic offset and check for overflow or underflow */
+78:	add     r4,r4,r6
+	add     r5,r5,r9
+	cmpd    cr0,r5,r7
+	cmpdi   cr1,r5,0
+	blt     79f
+	subf    r5,r7,r5
+	addi    r4,r4,1
+79:	bge     cr1,80f
+	addi    r4,r4,-1
+	add     r5,r5,r7
 
 80:	std	r4,TSPC64_TV_SEC(r11)
 	std	r5,TSPC64_TV_NSEC(r11)
-- 
2.13.6