[PATCH v4 2/8] powerpc/vdso32: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

[Christophe Leroy]

This is copied and adapted from commit 5c929885f1bb ("powerpc/vdso64:
Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE")
from Santosh Sivaraj <santosh at fossix.org>

Benchmark from vdsotest-all:
clock-gettime-realtime: syscall: 3601 nsec/call
clock-gettime-realtime:    libc: 1072 nsec/call
clock-gettime-realtime:    vdso: 931 nsec/call
clock-gettime-monotonic: syscall: 4034 nsec/call
clock-gettime-monotonic:    libc: 1213 nsec/call
clock-gettime-monotonic:    vdso: 1076 nsec/call
clock-gettime-realtime-coarse: syscall: 2722 nsec/call
clock-gettime-realtime-coarse:    libc: 805 nsec/call
clock-gettime-realtime-coarse:    vdso: 668 nsec/call
clock-gettime-monotonic-coarse: syscall: 2949 nsec/call
clock-gettime-monotonic-coarse:    libc: 882 nsec/call
clock-gettime-monotonic-coarse:    vdso: 745 nsec/call

Additional test passed with:
	vdsotest -d 30 clock-gettime-monotonic-coarse verify

Signed-off-by: Christophe Leroy <christophe.leroy at c-s.fr>
Cc: Naveen N. Rao <naveen.n.rao at linux.vnet.ibm.com>
Cc: Santosh Sivaraj <santosh at fossix.org>
Link: https://github.com/linuxppc/issues/issues/41
---
v4: Using STAMP_XTIME_SEC and STAMP_XTIMER_NSEC instead of STAMP_XTIME following merge of latest 2038 fixing series.
---
 arch/powerpc/kernel/vdso32/gettimeofday.S | 64 +++++++++++++++++++++++++++----
 1 file changed, 57 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index c8e6902cb01b..7c1be86c1e90 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -69,7 +69,13 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	cmpli	cr0,r3,CLOCK_REALTIME
 	cmpli	cr1,r3,CLOCK_MONOTONIC
 	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
-	bne	cr0,99f
+
+	cmpli	cr5,r3,CLOCK_REALTIME_COARSE
+	cmpli	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, .Lgettime_fallback
 
 	mflr	r12			/* r12 saves lr */
   .cfi_register lr,r12
@@ -78,8 +84,10 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	mr	r9,r3			/* datapage ptr in r9 */
 	lis	r7,NSEC_PER_SEC at h	/* want nanoseconds */
 	ori	r7,r7,NSEC_PER_SEC at l
-50:	bl	__do_get_tspec at local	/* get sec/nsec from tb & kernel */
-	bne	cr1,80f			/* not monotonic -> all done */
+	beq	cr5, .Lcoarse_clocks
+.Lprecise_clocks:
+	bl	__do_get_tspec at local	/* get sec/nsec from tb & kernel */
+	bne	cr1, .Lfinish		/* not monotonic -> all done */
 
 	/*
 	 * CLOCK_MONOTONIC
@@ -103,12 +111,53 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	add	r9,r9,r0
 	lwz	r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
         cmpl    cr0,r8,r0		/* check if updated */
-	bne-	50b
+	bne-	.Lprecise_clocks
+	b	.Lfinish_monotonic
+
+	/*
+	 * 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.
+	 */
+.Lcoarse_clocks:
+	lwz	r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
+	andi.	r0,r8,1                 /* pending update ? loop */
+	bne-	.Lcoarse_clocks
+	add	r9,r9,r0		/* r0 is already 0 */
+
+	/*
+	 * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
+	 * too
+	 */
+	lwz	r3,STAMP_XTIME_SEC+LOPART(r9)
+	lwz	r4,STAMP_XTIME_NSEC+LOPART(r9)
+	bne	cr6,1f
+
+	/* CLOCK_MONOTONIC_COARSE */
+	lwz	r5,(WTOM_CLOCK_SEC+LOPART)(r9)
+	lwz	r6,WTOM_CLOCK_NSEC(r9)
+
+	/* check if counter has updated */
+	or	r0,r6,r5
+1:	or	r0,r0,r3
+	or	r0,r0,r4
+	xor	r0,r0,r0
+	add	r3,r3,r0
+	lwz	r0,CFG_TB_UPDATE_COUNT+LOPART(r9)
+	cmpl	cr0,r0,r8               /* check if updated */
+	bne-	.Lcoarse_clocks
+
+	/* 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, .Lfinish
 
 	/* Calculate and store result. Note that this mimics the C code,
 	 * which may cause funny results if nsec goes negative... is that
 	 * possible at all ?
 	 */
+.Lfinish_monotonic:
 	add	r3,r3,r5
 	add	r4,r4,r6
 	cmpw	cr0,r4,r7
@@ -116,11 +165,12 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	blt	1f
 	subf	r4,r7,r4
 	addi	r3,r3,1
-1:	bge	cr1,80f
+1:	bge	cr1, .Lfinish
 	addi	r3,r3,-1
 	add	r4,r4,r7
 
-80:	stw	r3,TSPC32_TV_SEC(r11)
+.Lfinish:
+	stw	r3,TSPC32_TV_SEC(r11)
 	stw	r4,TSPC32_TV_NSEC(r11)
 
 	mtlr	r12
@@ -131,7 +181,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	/*
 	 * syscall fallback
 	 */
-99:
+.Lgettime_fallback:
 	li	r0,__NR_clock_gettime
   .cfi_restore lr
 	sc
-- 
2.13.3