[PATCH v4.16-rc5 1/1] x86/vdso: VDSO should handle clock_gettime(CLOCK_MONOTONIC_RAW) without syscall

[PATCH v4.16-rc5 1/1] x86/vdso: VDSO should handle clock_gettime(CLOCK_MONOTONIC_RAW) without syscall

[jason.vas.dias]

Resent to address reviewer comments.

  Currently, the VDSO does not handle
     clock_gettime( CLOCK_MONOTONIC_RAW, &ts )
  on Intel / AMD - it calls
     vdso_fallback_gettime()
  for this clock, which issues a syscall, having an unacceptably high
  latency (minimum measurable time or time between measurements)
  of 300-700ns on 2 2.8-3.9ghz Haswell x86_64 Family'_'Model : 06_3C
  machines under various versions of Linux.

  Sometimes, particularly when correlating elapsed time to performance
  counter values, user-space  code needs to know elapsed time from the
  perspective of the CPU no matter how "hot" / fast or "cold" / slow it
  might be running wrt NTP / PTP "real" time; when code needs this,
  the latencies associated with a syscall are often unacceptably high.

  I reported this as Bug #198161 :
    'https://bugzilla.kernel.org/show_bug.cgi?id=198961'
  and in previous posts with subjects matching 'CLOCK_MONOTONIC_RAW' .

  This patch handles CLOCK_MONOTONIC_RAW clock_gettime() in the VDSO ,
  by exporting the raw clock calibration, last cycles, last xtime_nsec,
  and last raw_sec value in the vsyscall_gtod_data during vsyscall_update() .

  Now the new do_monotonic_raw() function in the vDSO has a latency of @ 20ns
  on average, and the test program:
   tools/testing/selftest/timers/inconsistency-check.c
  succeeds with arguments: '-c 4 -t 120' or any arbitrary -t value.

  The patch is against Linus' latest 4.16-rc5 tree,
  current HEAD of :
    git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
  .

  This patch affects only files:

   arch/x86/include/asm/vgtod.h
   arch/x86/entry/vdso/vclock_gettime.c
   arch/x86/entry/vsyscall/vsyscall_gtod.c

  Patches for kernels 3.10.0-21 and 4.9.65-rt23 (ARM) are attached to bug #198161,
  as is the test program, timer_latency.c, to demonstrate the problem.

  Before the patch a latency of 200-1000ns was measured for
    clock_gettime(CLOCK_MONOTONIC_RAW,&ts)
  calls - after the patch, the same call on the same machine
  has a latency of @ 20ns.


Thanks & Best Regards,
Jason Vas Dias

[PATCH v4.16-rc5 1/1] x86/vdso: VDSO should handle clock_gettime(CLOCK_MONOTONIC_RAW) without syscall

[jason.vas.dias]

diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index f19856d..8b9b9cf 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -182,27 +182,49 @@ notrace static u64 vread_tsc(void)
 	return last;
 }
 
-notrace static inline u64 vgetsns(int *mode)
+notrace static inline __always_inline u64 vgetcycles(int *mode)
 {
-	u64 v;
-	cycles_t cycles;
-
-	if (gtod->vclock_mode == VCLOCK_TSC)
-		cycles = vread_tsc();
+	switch (gtod->vclock_mode) {
+	case VCLOCK_TSC:
+		return vread_tsc();
 #ifdef CONFIG_PARAVIRT_CLOCK
-	else if (gtod->vclock_mode == VCLOCK_PVCLOCK)
-		cycles = vread_pvclock(mode);
+	case VCLOCK_PVCLOCK:
+		return vread_pvclock(mode);
 #endif
 #ifdef CONFIG_HYPERV_TSCPAGE
-	else if (gtod->vclock_mode == VCLOCK_HVCLOCK)
-		cycles = vread_hvclock(mode);
+	case VCLOCK_HVCLOCK:
+		return vread_hvclock(mode);
 #endif
-	else
+	default:
+		break;
+	}
+	return 0;
+}
+
+notrace static inline u64 vgetsns(int *mode)
+{
+	u64 v;
+	cycles_t cycles = vgetcycles(mode);
+
+	if (cycles == 0)
 		return 0;
+
 	v = (cycles - gtod->cycle_last) & gtod->mask;
 	return v * gtod->mult;
 }
 
+notrace static inline u64 vgetsns_raw(int *mode)
+{
+	u64 v;
+	cycles_t cycles = vgetcycles(mode);
+
+	if (cycles == 0)
+		return 0;
+
+	v = (cycles - gtod->cycle_last) & gtod->raw_mask;
+	return v * gtod->raw_mult;
+}
+
 /* Code size doesn't matter (vdso is 4k anyway) and this is faster. */
 notrace static int __always_inline do_realtime(struct timespec *ts)
 {
@@ -246,6 +268,27 @@ notrace static int __always_inline do_monotonic(struct timespec *ts)
 	return mode;
 }
 
+notrace static __always_inline int do_monotonic_raw(struct timespec *ts)
+{
+	unsigned long seq;
+	u64 ns;
+	int mode;
+
+	do {
+		seq = gtod_read_begin(gtod);
+		mode = gtod->vclock_mode;
+		ts->tv_sec = gtod->monotonic_time_raw_sec;
+		ns = gtod->monotonic_time_raw_nsec;
+		ns += vgetsns_raw(&mode);
+		ns >>= gtod->raw_shift;
+	} while (unlikely(gtod_read_retry(gtod, seq)));
+
+	ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
+	ts->tv_nsec = ns;
+
+	return mode;
+}
+
 notrace static void do_realtime_coarse(struct timespec *ts)
 {
 	unsigned long seq;
@@ -277,6 +320,10 @@ notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
 		if (do_monotonic(ts) == VCLOCK_NONE)
 			goto fallback;
 		break;
+	case CLOCK_MONOTONIC_RAW:
+		if (do_monotonic_raw(ts) == VCLOCK_NONE)
+			goto fallback;
+		break;
 	case CLOCK_REALTIME_COARSE:
 		do_realtime_coarse(ts);
 		break;
diff --git a/arch/x86/entry/vsyscall/vsyscall_gtod.c b/arch/x86/entry/vsyscall/vsyscall_gtod.c
index e1216dd..83f5c21 100644
--- a/arch/x86/entry/vsyscall/vsyscall_gtod.c
+++ b/arch/x86/entry/vsyscall/vsyscall_gtod.c
@@ -44,6 +44,9 @@ void update_vsyscall(struct timekeeper *tk)
 	vdata->mask		= tk->tkr_mono.mask;
 	vdata->mult		= tk->tkr_mono.mult;
 	vdata->shift		= tk->tkr_mono.shift;
+	vdata->raw_mask		= tk->tkr_raw.mask;
+	vdata->raw_mult		= tk->tkr_raw.mult;
+	vdata->raw_shift	= tk->tkr_raw.shift;
 
 	vdata->wall_time_sec		= tk->xtime_sec;
 	vdata->wall_time_snsec		= tk->tkr_mono.xtime_nsec;
@@ -74,5 +77,8 @@ void update_vsyscall(struct timekeeper *tk)
 		vdata->monotonic_time_coarse_sec++;
 	}
 
+	vdata->monotonic_time_raw_sec  = tk->raw_sec;
+	vdata->monotonic_time_raw_nsec = tk->tkr_raw.xtime_nsec;
+
 	gtod_write_end(vdata);
 }
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index fb856c9..941e9d6 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -22,7 +22,9 @@ struct vsyscall_gtod_data {
 	u64	mask;
 	u32	mult;
 	u32	shift;
-
+	u32	raw_mask;
+	u32	raw_mult;
+	u32	raw_shift;
 	/* open coded 'struct timespec' */
 	u64		wall_time_snsec;
 	gtod_long_t	wall_time_sec;
@@ -32,6 +34,8 @@ struct vsyscall_gtod_data {
 	gtod_long_t	wall_time_coarse_nsec;
 	gtod_long_t	monotonic_time_coarse_sec;
 	gtod_long_t	monotonic_time_coarse_nsec;
+	gtod_long_t	monotonic_time_raw_sec;
+	gtod_long_t	monotonic_time_raw_nsec;
 
 	int		tz_minuteswest;
 	int		tz_dsttime;

Re: [PATCH v4.16-rc5 1/1] x86/vdso: VDSO should handle clock_gettime(CLOCK_MONOTONIC_RAW) without syscall

[kbuild test robot]

[-- Attachment #1: Type: text/plain, Size: 1814 bytes --]

Hi,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on v4.16-rc4]
[also build test ERROR on next-20180316]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/jason-vas-dias-gmail-com/x86-vdso-VDSO-should-handle-clock_gettime-CLOCK_MONOTONIC_RAW-without-syscall/20180317-101131
config: x86_64-kexec (attached as .config)
compiler: gcc-7 (Debian 7.3.0-1) 7.3.0
reproduce:
        # save the attached .config to linux build tree
        make ARCH=x86_64 

All errors (new ones prefixed by >>):

   arch/x86//entry/vdso/vclock_gettime.o: In function `__vdso_clock_gettime':
   vclock_gettime.c:(.text+0xe6): undefined reference to `__x86_indirect_thunk_rax'
   /usr/bin/ld: arch/x86//entry/vdso/vclock_gettime.o: relocation R_X86_64_PC32 against undefined symbol `__x86_indirect_thunk_rax' can not be used when making a shared object; recompile with -fPIC
   /usr/bin/ld: final link failed: Bad value
>> collect2: error: ld returned 1 exit status
--
>> objcopy: 'arch/x86//entry/vdso/vdso64.so.dbg': No such file
--
>> arch/x86//entry/vdso/vdso32.so.dbg: undefined symbols found
--
   arch/x86/entry/vdso/vclock_gettime.o: In function `__vdso_clock_gettime':
   vclock_gettime.c:(.text+0xe6): undefined reference to `__x86_indirect_thunk_rax'
   /usr/bin/ld: arch/x86/entry/vdso/vclock_gettime.o: relocation R_X86_64_PC32 against undefined symbol `__x86_indirect_thunk_rax' can not be used when making a shared object; recompile with -fPIC
   /usr/bin/ld: final link failed: Bad value
>> collect2: error: ld returned 1 exit status

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation

[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 26628 bytes --]