x86/vdso: Switch to generic vDSO implementation

The x86 vDSO library requires some adaptations to take advantage of the
newly introduced generic vDSO library.

Introduce the following changes:
 - Modification of vdso.c to be compliant with the common vdso datapage
 - Use of lib/vdso for gettimeofday

[ tglx: Massaged changelog and cleaned up the function signature formatting ]

Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-mips@vger.kernel.org
Cc: linux-kselftest@vger.kernel.org
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Burton <paul.burton@mips.com>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Mark Salyzyn <salyzyn@android.com>
Cc: Peter Collingbourne <pcc@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Dmitry Safonov <0x7f454c46@gmail.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Huw Davies <huw@codeweavers.com>
Cc: Shijith Thotton <sthotton@marvell.com>
Cc: Andre Przywara <andre.przywara@arm.com>
Link: https://lkml.kernel.org/r/20190621095252.32307-23-vincenzo.frascino@arm.com

5 files changed, 243 insertions, 76 deletions

diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index b6033680d458..19b695ff2c68 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_PVCLOCK_H
 #define _ASM_X86_PVCLOCK_H
 
-#include <linux/clocksource.h>
+#include <asm/clocksource.h>
 #include <asm/pvclock-abi.h>
 
 /* some helper functions for xen and kvm pv clock sources */
diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
new file mode 100644
index 000000000000..0e2650fc191b
--- /dev/null
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -0,0 +1,191 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Fast user context implementation of clock_gettime, gettimeofday, and time.
+ *
+ * Copyright (C) 2019 ARM Limited.
+ * Copyright 2006 Andi Kleen, SUSE Labs.
+ * 32 Bit compat layer by Stefani Seibold <stefani@seibold.net>
+ *  sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
+ */
+#ifndef __ASM_VDSO_GETTIMEOFDAY_H
+#define __ASM_VDSO_GETTIMEOFDAY_H
+
+#ifndef __ASSEMBLY__
+
+#include <uapi/linux/time.h>
+#include <asm/vgtod.h>
+#include <asm/vvar.h>
+#include <asm/unistd.h>
+#include <asm/msr.h>
+#include <asm/pvclock.h>
+#include <asm/mshyperv.h>
+
+#define __vdso_data (VVAR(_vdso_data))
+
+#define VDSO_HAS_TIME 1
+
+#ifdef CONFIG_PARAVIRT_CLOCK
+extern u8 pvclock_page[PAGE_SIZE]
+	__attribute__((visibility("hidden")));
+#endif
+
+#ifdef CONFIG_HYPERV_TSCPAGE
+extern u8 hvclock_page[PAGE_SIZE]
+	__attribute__((visibility("hidden")));
+#endif
+
+#ifndef BUILD_VDSO32
+
+static __always_inline
+long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	long ret;
+
+	asm ("syscall" : "=a" (ret), "=m" (*_ts) :
+	     "0" (__NR_clock_gettime), "D" (_clkid), "S" (_ts) :
+	     "rcx", "r11");
+
+	return ret;
+}
+
+static __always_inline
+long gettimeofday_fallback(struct __kernel_old_timeval *_tv,
+			   struct timezone *_tz)
+{
+	long ret;
+
+	asm("syscall" : "=a" (ret) :
+	    "0" (__NR_gettimeofday), "D" (_tv), "S" (_tz) : "memory");
+
+	return ret;
+}
+
+#else
+
+static __always_inline
+long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	long ret;
+
+	asm (
+		"mov %%ebx, %%edx \n"
+		"mov %[clock], %%ebx \n"
+		"call __kernel_vsyscall \n"
+		"mov %%edx, %%ebx \n"
+		: "=a" (ret), "=m" (*_ts)
+		: "0" (__NR_clock_gettime64), [clock] "g" (_clkid), "c" (_ts)
+		: "edx");
+
+	return ret;
+}
+
+static __always_inline
+long gettimeofday_fallback(struct __kernel_old_timeval *_tv,
+			   struct timezone *_tz)
+{
+	long ret;
+
+	asm(
+		"mov %%ebx, %%edx \n"
+		"mov %2, %%ebx \n"
+		"call __kernel_vsyscall \n"
+		"mov %%edx, %%ebx \n"
+		: "=a" (ret)
+		: "0" (__NR_gettimeofday), "g" (_tv), "c" (_tz)
+		: "memory", "edx");
+
+	return ret;
+}
+
+#endif
+
+#ifdef CONFIG_PARAVIRT_CLOCK
+static const struct pvclock_vsyscall_time_info *get_pvti0(void)
+{
+	return (const struct pvclock_vsyscall_time_info *)&pvclock_page;
+}
+
+static u64 vread_pvclock(void)
+{
+	const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti;
+	u32 version;
+	u64 ret;
+
+	/*
+	 * Note: The kernel and hypervisor must guarantee that cpu ID
+	 * number maps 1:1 to per-CPU pvclock time info.
+	 *
+	 * Because the hypervisor is entirely unaware of guest userspace
+	 * preemption, it cannot guarantee that per-CPU pvclock time
+	 * info is updated if the underlying CPU changes or that that
+	 * version is increased whenever underlying CPU changes.
+	 *
+	 * On KVM, we are guaranteed that pvti updates for any vCPU are
+	 * atomic as seen by *all* vCPUs.  This is an even stronger
+	 * guarantee than we get with a normal seqlock.
+	 *
+	 * On Xen, we don't appear to have that guarantee, but Xen still
+	 * supplies a valid seqlock using the version field.
+	 *
+	 * We only do pvclock vdso timing at all if
+	 * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to
+	 * mean that all vCPUs have matching pvti and that the TSC is
+	 * synced, so we can just look at vCPU 0's pvti.
+	 */
+
+	do {
+		version = pvclock_read_begin(pvti);
+
+		if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT)))
+			return U64_MAX;
+
+		ret = __pvclock_read_cycles(pvti, rdtsc_ordered());
+	} while (pvclock_read_retry(pvti, version));
+
+	return ret;
+}
+#endif
+
+#ifdef CONFIG_HYPERV_TSCPAGE
+static u64 vread_hvclock(void)
+{
+	const struct ms_hyperv_tsc_page *tsc_pg =
+		(const struct ms_hyperv_tsc_page *)&hvclock_page;
+
+	return hv_read_tsc_page(tsc_pg);
+}
+#endif
+
+static inline u64 __arch_get_hw_counter(s32 clock_mode)
+{
+	if (clock_mode == VCLOCK_TSC)
+		return (u64)rdtsc_ordered();
+	/*
+	 * For any memory-mapped vclock type, we need to make sure that gcc
+	 * doesn't cleverly hoist a load before the mode check.  Otherwise we
+	 * might end up touching the memory-mapped page even if the vclock in
+	 * question isn't enabled, which will segfault.  Hence the barriers.
+	 */
+#ifdef CONFIG_PARAVIRT_CLOCK
+	if (clock_mode == VCLOCK_PVCLOCK) {
+		barrier();
+		return vread_pvclock();
+	}
+#endif
+#ifdef CONFIG_HYPERV_TSCPAGE
+	if (clock_mode == VCLOCK_HVCLOCK) {
+		barrier();
+		return vread_hvclock();
+	}
+#endif
+	return U64_MAX;
+}
+
+static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
+{
+	return __vdso_data;
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/x86/include/asm/vdso/vsyscall.h b/arch/x86/include/asm/vdso/vsyscall.h
new file mode 100644
index 000000000000..0026ab2123ce
--- /dev/null
+++ b/arch/x86/include/asm/vdso/vsyscall.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSO_VSYSCALL_H
+#define __ASM_VDSO_VSYSCALL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/hrtimer.h>
+#include <linux/timekeeper_internal.h>
+#include <vdso/datapage.h>
+#include <asm/vgtod.h>
+#include <asm/vvar.h>
+
+int vclocks_used __read_mostly;
+
+DEFINE_VVAR(struct vdso_data, _vdso_data);
+/*
+ * Update the vDSO data page to keep in sync with kernel timekeeping.
+ */
+static __always_inline
+struct vdso_data *__x86_get_k_vdso_data(void)
+{
+	return _vdso_data;
+}
+#define __arch_get_k_vdso_data __x86_get_k_vdso_data
+
+static __always_inline
+int __x86_get_clock_mode(struct timekeeper *tk)
+{
+	int vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode;
+
+	/* Mark the new vclock used. */
+	BUILD_BUG_ON(VCLOCK_MAX >= 32);
+	WRITE_ONCE(vclocks_used, READ_ONCE(vclocks_used) | (1 << vclock_mode));
+
+	return vclock_mode;
+}
+#define __arch_get_clock_mode __x86_get_clock_mode
+
+/* The asm-generic header needs to be included after the definitions above */
+#include <asm-generic/vdso/vsyscall.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_VSYSCALL_H */
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 913a133f8e6f..a2638c6124ed 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -3,7 +3,9 @@
 #define _ASM_X86_VGTOD_H
 
 #include <linux/compiler.h>
-#include <linux/clocksource.h>
+#include <asm/clocksource.h>
+#include <vdso/datapage.h>
+#include <vdso/helpers.h>
 
 #include <uapi/linux/time.h>
 
@@ -13,81 +15,10 @@ typedef u64 gtod_long_t;
 typedef unsigned long gtod_long_t;
 #endif
 
-/*
- * There is one of these objects in the vvar page for each
- * vDSO-accelerated clockid.  For high-resolution clocks, this encodes
- * the time corresponding to vsyscall_gtod_data.cycle_last.  For coarse
- * clocks, this encodes the actual time.
- *
- * To confuse the reader, for high-resolution clocks, nsec is left-shifted
- * by vsyscall_gtod_data.shift.
- */
-struct vgtod_ts {
-	u64		sec;
-	u64		nsec;
-};
-
-#define VGTOD_BASES	(CLOCK_TAI + 1)
-#define VGTOD_HRES	(BIT(CLOCK_REALTIME) | BIT(CLOCK_MONOTONIC) | BIT(CLOCK_TAI))
-#define VGTOD_COARSE	(BIT(CLOCK_REALTIME_COARSE) | BIT(CLOCK_MONOTONIC_COARSE))
-
-/*
- * vsyscall_gtod_data will be accessed by 32 and 64 bit code at the same time
- * so be carefull by modifying this structure.
- */
-struct vsyscall_gtod_data {
-	unsigned int	seq;
-
-	int		vclock_mode;
-	u64		cycle_last;
-	u64		mask;
-	u32		mult;
-	u32		shift;
-
-	struct vgtod_ts	basetime[VGTOD_BASES];
-
-	int		tz_minuteswest;
-	int		tz_dsttime;
-};
-extern struct vsyscall_gtod_data vsyscall_gtod_data;
-
 extern int vclocks_used;
 static inline bool vclock_was_used(int vclock)
 {
 	return READ_ONCE(vclocks_used) & (1 << vclock);
 }
 
-static inline unsigned int gtod_read_begin(const struct vsyscall_gtod_data *s)
-{
-	unsigned int ret;
-
-repeat:
-	ret = READ_ONCE(s->seq);
-	if (unlikely(ret & 1)) {
-		cpu_relax();
-		goto repeat;
-	}
-	smp_rmb();
-	return ret;
-}
-
-static inline int gtod_read_retry(const struct vsyscall_gtod_data *s,
-				  unsigned int start)
-{
-	smp_rmb();
-	return unlikely(s->seq != start);
-}
-
-static inline void gtod_write_begin(struct vsyscall_gtod_data *s)
-{
-	++s->seq;
-	smp_wmb();
-}
-
-static inline void gtod_write_end(struct vsyscall_gtod_data *s)
-{
-	smp_wmb();
-	++s->seq;
-}
-
 #endif /* _ASM_X86_VGTOD_H */
diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h
index e474f5c6e387..32f5d9a0b90e 100644
--- a/arch/x86/include/asm/vvar.h
+++ b/arch/x86/include/asm/vvar.h
@@ -32,19 +32,20 @@
 extern char __vvar_page;
 
 #define DECLARE_VVAR(offset, type, name)				\
-	extern type vvar_ ## name __attribute__((visibility("hidden")));
+	extern type vvar_ ## name[CS_BASES]				\
+	__attribute__((visibility("hidden")));
 
 #define VVAR(name) (vvar_ ## name)
 
 #define DEFINE_VVAR(type, name)						\
-	type name							\
+	type name[CS_BASES]						\
 	__attribute__((section(".vvar_" #name), aligned(16))) __visible
 
 #endif
 
 /* DECLARE_VVAR(offset, type, name) */
 
-DECLARE_VVAR(128, struct vsyscall_gtod_data, vsyscall_gtod_data)
+DECLARE_VVAR(128, struct vdso_data, _vdso_data)
 
 #undef DECLARE_VVAR