FROMLIST: [PATCH v5 11/12] lib: vdso: Add support for CLOCK_BOOTTIME

(cherry pick from url https://patchwork.kernel.org/patch/10044503/)

Take an effort to recode the arm64 vdso code from assembler to C
previously submitted by Andrew Pinski <apinski@cavium.com>, rework
it for use in both arm and arm64, overlapping any optimizations
for each architecture. But instead of landing it in arm64, land the
result into lib/vdso and unify both implementations to simplify
future maintenance.

Add a case for CLOCK_BOOTTIME as it is popular for measuring
relative time on systems expected to suspend() or hibernate().

Android uses CLOCK_BOOTTIME for all relative time measurements
and timeouts. Switching to vdso reduced CPU utilization and improves
accuracy. There is also a desire by some partners to switch all
logging over to CLOCK_BOOTTIME, and thus this operation alone would
contribute to a near percentile CPU load.

Signed-off-by: Mark Salyzyn <salyzyn@android.com>
Cc: James Morse <james.morse@arm.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dmitry Safonov <dsafonov@virtuozzo.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Laura Abbott <labbott@redhat.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Andy Gross <andy.gross@linaro.org>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Andrew Pinski <apinski@cavium.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Bug: 63737556
Bug: 20045882
Change-Id: I76c26b054baf7f1100e03c65d6b16fe649b883b1

arch/arm/include/asm/vdso_datapage.h

@@ -64,6 +64,7 @@ struct vdso_data {
 	u32 tz_minuteswest;	/* timezone info for gettimeofday(2) */
 	u32 tz_dsttime;
 
+	u64 btm_nsec;		/* monotonic to boot time */
 	/* Raw clocksource multipler */
 	u32 cs_raw_mult;
 	/* Raw time */

arch/arm/kernel/vdso.c

@@ -329,6 +329,7 @@ void update_vsyscall(struct timekeeper *tk)
 		/* tkr_mono.shift == tkr_raw.shift */
 		vdso_data->cs_shift		= tk->tkr_mono.shift;
 		vdso_data->cs_mask		= tk->tkr_mono.mask;
+		vdso_data->btm_nsec		= ktime_to_ns(tk->offs_boot);
 	}
 
 	vdso_write_end(vdso_data);

arch/arm64/include/asm/vdso_datapage.h

@@ -45,6 +45,7 @@ struct vdso_data {
 	__u64 xtime_coarse_nsec;
 	__u64 wtm_clock_sec;	/* Wall to monotonic time */
 	vdso_wtm_clock_nsec_t wtm_clock_nsec;
+	__u64 btm_nsec;		/* monotonic to boot time */
 	__u32 tb_seq_count;	/* Timebase sequence counter */
 	/* cs_* members must be adjacent and in this order (ldp accesses) */
 	__u32 cs_mono_mult;	/* NTP-adjusted clocksource multiplier */

arch/arm64/kernel/vdso.c

@@ -266,6 +266,7 @@ void update_vsyscall(struct timekeeper *tk)
 		vdso_data->cs_raw_mult		= tk->tkr_raw.mult;
 		/* tkr_mono.shift == tkr_raw.shift */
 		vdso_data->cs_shift		= tk->tkr_mono.shift;
+		vdso_data->btm_nsec		= ktime_to_ns(tk->offs_boot);
 	}
 
 	smp_wmb();

lib/vdso/vgettimeofday.c

@@ -247,6 +247,50 @@ static notrace int do_monotonic_raw(const struct vdso_data *vd,
 	return 0;
 }
 
+static notrace int do_boottime(const struct vdso_data *vd, struct timespec *ts)
+{
+	u32 seq, mult, shift;
+	u64 nsec, cycle_last, wtm_nsec;
+#ifdef ARCH_CLOCK_FIXED_MASK
+	static const u64 mask = ARCH_CLOCK_FIXED_MASK;
+#else
+	u64 mask;
+#endif
+	__kernel_time_t sec;
+
+	do {
+		seq = vdso_read_begin(vd);
+
+		if (vd->use_syscall)
+			return -1;
+
+		cycle_last = vd->cs_cycle_last;
+
+		mult = vd->cs_mono_mult;
+		shift = vd->cs_shift;
+#ifndef ARCH_CLOCK_FIXED_MASK
+		mask = vd->cs_mask;
+#endif
+
+		sec = vd->xtime_clock_sec;
+		nsec = vd->xtime_clock_snsec;
+
+		sec += vd->wtm_clock_sec;
+		wtm_nsec = vd->wtm_clock_nsec + vd->btm_nsec;
+
+	} while (unlikely(vdso_read_retry(vd, seq)));
+
+	nsec += get_clock_shifted_nsec(cycle_last, mult, mask);
+	nsec >>= shift;
+	nsec += wtm_nsec;
+
+	/* open coding timespec_add_ns to save a ts->tv_nsec = 0 */
+	ts->tv_sec = sec + __iter_div_u64_rem(nsec, NSEC_PER_SEC, &nsec);
+	ts->tv_nsec = nsec;
+
+	return 0;
+}
+
 #else /* ARCH_PROVIDES_TIMER */
 
 static notrace int do_realtime(const struct vdso_data *vd, struct timespec *ts)
@@ -265,6 +309,12 @@ static notrace int do_monotonic_raw(const struct vdso_data *vd,
 	return -1;
 }
 
+static notrace int do_boottime(const struct vdso_data *vd,
+			       struct timespec *ts)
+{
+	return -1;
+}
+
 #endif /* ARCH_PROVIDES_TIMER */
 
 notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
@@ -290,6 +340,10 @@ notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
 		if (do_monotonic_raw(vd, ts))
 			goto fallback;
 		break;
+	case CLOCK_BOOTTIME:
+		if (do_boottime(vd, ts))
+			goto fallback;
+		break;
 	default:
 		goto fallback;
 	}
@@ -326,6 +380,7 @@ int __vdso_clock_getres(clockid_t clock, struct timespec *res)
 	long nsec;
 
 	if (clock == CLOCK_REALTIME ||
+	    clock == CLOCK_BOOTTIME ||
 	    clock == CLOCK_MONOTONIC ||
 	    clock == CLOCK_MONOTONIC_RAW)
 		nsec = MONOTONIC_RES_NSEC;