powerpc: Improve resolution of VDSO clock_gettime
Currently the clock_gettime implementation in the VDSO produces a
result with microsecond resolution for the cases that are handled
without a system call, i.e. CLOCK_REALTIME and CLOCK_MONOTONIC. The
nanoseconds field of the result is obtained by computing a
microseconds value and multiplying by 1000.
This changes the code in the VDSO to do the computation for
clock_gettime with nanosecond resolution. That means that the
resolution of the result will ultimately depend on the timebase
frequency.
Because the timestamp in the VDSO datapage (stamp_xsec, the real time
corresponding to the timebase count in tb_orig_stamp) is in units of
2^-20 seconds, it doesn't have sufficient resolution for computing a
result with nanosecond resolution. Therefore this adds a copy of
xtime to the VDSO datapage and updates it in update_gtod() along with
the other time-related fields.
Signed-off-by: Paul Mackerras <paulus@samba.org>
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index 72ca26d..ee038d4 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -16,6 +16,13 @@
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
+/* Offset for the low 32-bit part of a field of long type */
+#ifdef CONFIG_PPC64
+#define LOPART 4
+#else
+#define LOPART 0
+#endif
+
.text
/*
* Exact prototype of gettimeofday
@@ -90,101 +97,53 @@
mflr r12 /* r12 saves lr */
.cfi_register lr,r12
- mr r10,r3 /* r10 saves id */
mr r11,r4 /* r11 saves tp */
bl __get_datapage@local /* get data page */
mr r9,r3 /* datapage ptr in r9 */
- beq cr1,50f /* if monotonic -> jump there */
- /*
- * CLOCK_REALTIME
- */
-
- bl __do_get_xsec@local /* get xsec from tb & kernel */
- bne- 98f /* out of line -> do syscall */
-
- /* seconds are xsec >> 20 */
- rlwinm r5,r4,12,20,31
- rlwimi r5,r3,12,0,19
- stw r5,TSPC32_TV_SEC(r11)
-
- /* get remaining xsec and convert to nsec. we scale
- * up remaining xsec by 12 bits and get the top 32 bits
- * of the multiplication, then we multiply by 1000
- */
- rlwinm r5,r4,12,0,19
- lis r6,1000000@h
- ori r6,r6,1000000@l
- mulhwu r5,r5,r6
- mulli r5,r5,1000
- stw r5,TSPC32_TV_NSEC(r11)
- mtlr r12
- crclr cr0*4+so
- li r3,0
- blr
+50: bl __do_get_tspec@local /* get sec/nsec from tb & kernel */
+ bne cr1,80f /* not monotonic -> all done */
/*
* CLOCK_MONOTONIC
*/
-50: bl __do_get_xsec@local /* get xsec from tb & kernel */
- bne- 98f /* out of line -> do syscall */
-
- /* seconds are xsec >> 20 */
- rlwinm r6,r4,12,20,31
- rlwimi r6,r3,12,0,19
-
- /* get remaining xsec and convert to nsec. we scale
- * up remaining xsec by 12 bits and get the top 32 bits
- * of the multiplication, then we multiply by 1000
- */
- rlwinm r7,r4,12,0,19
- lis r5,1000000@h
- ori r5,r5,1000000@l
- mulhwu r7,r7,r5
- mulli r7,r7,1000
-
/* now we must fixup using wall to monotonic. We need to snapshot
* that value and do the counter trick again. Fortunately, we still
* have the counter value in r8 that was returned by __do_get_xsec.
- * At this point, r6,r7 contain our sec/nsec values, r3,r4 and r5
- * can be used
+ * At this point, r3,r4 contain our sec/nsec values, r5 and r6
+ * can be used, r7 contains NSEC_PER_SEC.
*/
- lwz r3,WTOM_CLOCK_SEC(r9)
- lwz r4,WTOM_CLOCK_NSEC(r9)
+ lwz r5,WTOM_CLOCK_SEC(r9)
+ lwz r6,WTOM_CLOCK_NSEC(r9)
- /* We now have our result in r3,r4. We create a fake dependency
- * on that result and re-check the counter
+ /* We now have our offset in r5,r6. We create a fake dependency
+ * on that value and re-check the counter
*/
- or r5,r4,r3
- xor r0,r5,r5
+ or r0,r6,r5
+ xor r0,r0,r0
add r9,r9,r0
-#ifdef CONFIG_PPC64
- lwz r0,(CFG_TB_UPDATE_COUNT+4)(r9)
-#else
- lwz r0,(CFG_TB_UPDATE_COUNT)(r9)
-#endif
+ lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
cmpl cr0,r8,r0 /* check if updated */
bne- 50b
- /* Calculate and store result. Note that this mimmics the C code,
+ /* 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 ?
*/
- add r3,r3,r6
- add r4,r4,r7
- lis r5,NSEC_PER_SEC@h
- ori r5,r5,NSEC_PER_SEC@l
- cmpl cr0,r4,r5
- cmpli cr1,r4,0
+ add r3,r3,r5
+ add r4,r4,r6
+ cmpw cr0,r4,r7
+ cmpwi cr1,r4,0
blt 1f
- subf r4,r5,r4
+ subf r4,r7,r4
addi r3,r3,1
-1: bge cr1,1f
+1: bge cr1,80f
addi r3,r3,-1
- add r4,r4,r5
-1: stw r3,TSPC32_TV_SEC(r11)
+ add r4,r4,r7
+
+80: stw r3,TSPC32_TV_SEC(r11)
stw r4,TSPC32_TV_NSEC(r11)
mtlr r12
@@ -195,10 +154,6 @@
/*
* syscall fallback
*/
-98:
- mtlr r12
- mr r3,r10
- mr r4,r11
99:
li r0,__NR_clock_gettime
sc
@@ -254,11 +209,7 @@
/* Check for update count & load values. We use the low
* order 32 bits of the update count
*/
-#ifdef CONFIG_PPC64
-1: lwz r8,(CFG_TB_UPDATE_COUNT+4)(r9)
-#else
-1: lwz r8,(CFG_TB_UPDATE_COUNT)(r9)
-#endif
+1: lwz r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
andi. r0,r8,1 /* pending update ? loop */
bne- 1b
xor r0,r8,r8 /* create dependency */
@@ -305,11 +256,7 @@
or r6,r4,r3
xor r0,r6,r6
add r9,r9,r0
-#ifdef CONFIG_PPC64
- lwz r0,(CFG_TB_UPDATE_COUNT+4)(r9)
-#else
- lwz r0,(CFG_TB_UPDATE_COUNT)(r9)
-#endif
+ lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
cmpl cr0,r8,r0 /* check if updated */
bne- 1b
@@ -322,3 +269,98 @@
*/
3: blr
.cfi_endproc
+
+/*
+ * This is the core of clock_gettime(), it returns the current
+ * time in seconds and nanoseconds in r3 and r4.
+ * It expects the datapage ptr in r9 and doesn't clobber it.
+ * It clobbers r0, r5, r6, r10 and returns NSEC_PER_SEC in r7.
+ * On return, r8 contains the counter value that can be reused.
+ * This clobbers cr0 but not any other cr field.
+ */
+__do_get_tspec:
+ .cfi_startproc
+ /* Check for update count & load values. We use the low
+ * order 32 bits of the update count
+ */
+1: lwz r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
+ andi. r0,r8,1 /* pending update ? loop */
+ bne- 1b
+ xor r0,r8,r8 /* create dependency */
+ add r9,r9,r0
+
+ /* Load orig stamp (offset to TB) */
+ lwz r5,CFG_TB_ORIG_STAMP(r9)
+ lwz r6,(CFG_TB_ORIG_STAMP+4)(r9)
+
+ /* Get a stable TB value */
+2: mftbu r3
+ mftbl r4
+ mftbu r0
+ cmpl cr0,r3,r0
+ bne- 2b
+
+ /* Subtract tb orig stamp and shift left 12 bits.
+ */
+ subfc r7,r6,r4
+ subfe r0,r5,r3
+ slwi r0,r0,12
+ rlwimi. r0,r7,12,20,31
+ slwi r7,r7,12
+
+ /* Load scale factor & do multiplication */
+ lwz r5,CFG_TB_TO_XS(r9) /* load values */
+ lwz r6,(CFG_TB_TO_XS+4)(r9)
+ mulhwu r3,r7,r6
+ mullw r10,r7,r5
+ mulhwu r4,r7,r5
+ addc r10,r3,r10
+ li r3,0
+
+ beq+ 4f /* skip high part computation if 0 */
+ mulhwu r3,r0,r5
+ mullw r7,r0,r5
+ mulhwu r5,r0,r6
+ mullw r6,r0,r6
+ adde r4,r4,r7
+ addze r3,r3
+ addc r4,r4,r5
+ addze r3,r3
+ addc r10,r10,r6
+
+4: addze r4,r4 /* add in carry */
+ lis r7,NSEC_PER_SEC@h
+ ori r7,r7,NSEC_PER_SEC@l
+ mulhwu r4,r4,r7 /* convert to nanoseconds */
+
+ /* At this point, we have seconds & nanoseconds since the xtime
+ * stamp in r3+CA and r4. Load & add the xtime stamp.
+ */
+#ifdef CONFIG_PPC64
+ lwz r5,STAMP_XTIME+TSPC64_TV_SEC+LOPART(r9)
+ lwz r6,STAMP_XTIME+TSPC64_TV_NSEC+LOPART(r9)
+#else
+ lwz r5,STAMP_XTIME+TSPC32_TV_SEC(r9)
+ lwz r6,STAMP_XTIME+TSPC32_TV_NSEC(r9)
+#endif
+ add r4,r4,r6
+ adde r3,r3,r5
+
+ /* We now have our result in r3,r4. We create a fake dependency
+ * on that result and re-check the counter
+ */
+ or r6,r4,r3
+ xor r0,r6,r6
+ add r9,r9,r0
+ lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
+ cmpl cr0,r8,r0 /* check if updated */
+ bne- 1b
+
+ /* check for nanosecond overflow and adjust if necessary */
+ cmpw r4,r7
+ bltlr /* all done if no overflow */
+ subf r4,r7,r4 /* adjust if overflow */
+ addi r3,r3,1
+
+ blr
+ .cfi_endproc