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

3 files changed, 37 insertions, 218 deletions

diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 42fe42e82baf..39106111be86 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -3,6 +3,12 @@
 # Building vDSO images for x86.
 #
 
+# Absolute relocation type $(ARCH_REL_TYPE_ABS) needs to be defined before
+# the inclusion of generic Makefile.
+ARCH_REL_TYPE_ABS := R_X86_64_JUMP_SLOT|R_X86_64_GLOB_DAT|R_X86_64_RELATIVE|
+ARCH_REL_TYPE_ABS += R_386_GLOB_DAT|R_386_JMP_SLOT|R_386_RELATIVE
+include $(srctree)/lib/vdso/Makefile
+
 KBUILD_CFLAGS += $(DISABLE_LTO)
 KASAN_SANITIZE			:= n
 UBSAN_SANITIZE			:= n
@@ -51,6 +57,7 @@ VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -soname linux-vdso.so.1 --no-undefined \
 
 $(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE
 	$(call if_changed,vdso)
+	$(call if_changed,vdso_check)
 
 HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/$(SUBARCH)/include/uapi
 hostprogs-y			+= vdso2c
@@ -121,6 +128,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 
 $(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE
 	$(call if_changed,vdso)
+	$(call if_changed,vdso_check)
 
 CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
 VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -soname linux-gate.so.1
@@ -160,6 +168,7 @@ $(obj)/vdso32.so.dbg: FORCE \
 		      $(obj)/vdso32/system_call.o \
 		      $(obj)/vdso32/sigreturn.o
 	$(call if_changed,vdso)
+	$(call if_changed,vdso_check)
 
 #
 # The DSO images are built using a special linker script.
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 4aed41f638bb..f01a3f0787ca 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -1,251 +1,60 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright 2006 Andi Kleen, SUSE Labs.
- *
  * Fast user context implementation of clock_gettime, gettimeofday, and time.
  *
+ * Copyright 2006 Andi Kleen, SUSE Labs.
+ * Copyright 2019 ARM Limited
+ *
  * 32 Bit compat layer by Stefani Seibold <stefani@seibold.net>
  *  sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
- *
- * The code should have no internal unresolved relocations.
- * Check with readelf after changing.
  */
-
-#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>
-#include <linux/math64.h>
 #include <linux/time.h>
 #include <linux/kernel.h>
+#include <linux/types.h>
 
-#define gtod (&VVAR(vsyscall_gtod_data))
+#include "../../../../lib/vdso/gettimeofday.c"
 
-extern int __vdso_clock_gettime(clockid_t clock, struct timespec *ts);
-extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz);
+extern int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
 extern time_t __vdso_time(time_t *t);
 
-#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
-
-notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
-{
-	long ret;
-	asm ("syscall" : "=a" (ret), "=m" (*ts) :
-	     "0" (__NR_clock_gettime), "D" (clock), "S" (ts) :
-	     "rcx", "r11");
-	return ret;
-}
-
-#else
-
-notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 {
-	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_gettime), [clock] "g" (clock), "c" (ts)
-		: "edx");
-	return ret;
+	return __cvdso_gettimeofday(tv, tz);
 }
 
-#endif
-
-#ifdef CONFIG_PARAVIRT_CLOCK
-static notrace const struct pvclock_vsyscall_time_info *get_pvti0(void)
-{
-	return (const struct pvclock_vsyscall_time_info *)&pvclock_page;
-}
+int gettimeofday(struct __kernel_old_timeval *, struct timezone *)
+	__attribute__((weak, alias("__vdso_gettimeofday")));
 
-static notrace u64 vread_pvclock(void)
+time_t __vdso_time(time_t *t)
 {
-	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;
+	return __cvdso_time(t);
 }
-#endif
-#ifdef CONFIG_HYPERV_TSCPAGE
-static notrace 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
+time_t time(time_t *t)	__attribute__((weak, alias("__vdso_time")));
 
-notrace static inline u64 vgetcyc(int mode)
-{
-	if (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 (mode == VCLOCK_PVCLOCK) {
-		barrier();
-		return vread_pvclock();
-	}
-#endif
-#ifdef CONFIG_HYPERV_TSCPAGE
-	if (mode == VCLOCK_HVCLOCK) {
-		barrier();
-		return vread_hvclock();
-	}
-#endif
-	return U64_MAX;
-}
+#if defined(CONFIG_X86_64) && !defined(BUILD_VDSO32_64)
+/* both 64-bit and x32 use these */
+extern int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
 
-notrace static int do_hres(clockid_t clk, struct timespec *ts)
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
 {
-	struct vgtod_ts *base = &gtod->basetime[clk];
-	u64 cycles, last, sec, ns;
-	unsigned int seq;
-
-	do {
-		seq = gtod_read_begin(gtod);
-		cycles = vgetcyc(gtod->vclock_mode);
-		ns = base->nsec;
-		last = gtod->cycle_last;
-		if (unlikely((s64)cycles < 0))
-			return vdso_fallback_gettime(clk, ts);
-		if (cycles > last)
-			ns += (cycles - last) * gtod->mult;
-		ns >>= gtod->shift;
-		sec = base->sec;
-	} while (unlikely(gtod_read_retry(gtod, seq)));
-
-	/*
-	 * Do this outside the loop: a race inside the loop could result
-	 * in __iter_div_u64_rem() being extremely slow.
-	 */
-	ts->tv_sec = sec + __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
-	ts->tv_nsec = ns;
-
-	return 0;
+	return __cvdso_clock_gettime(clock, ts);
 }
 
-notrace static void do_coarse(clockid_t clk, struct timespec *ts)
-{
-	struct vgtod_ts *base = &gtod->basetime[clk];
-	unsigned int seq;
+int clock_gettime(clockid_t, struct __kernel_timespec *)
+	__attribute__((weak, alias("__vdso_clock_gettime")));
 
-	do {
-		seq = gtod_read_begin(gtod);
-		ts->tv_sec = base->sec;
-		ts->tv_nsec = base->nsec;
-	} while (unlikely(gtod_read_retry(gtod, seq)));
-}
+#else
+/* i386 only */
+extern int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts);
 
-notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
+int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts)
 {
-	unsigned int msk;
-
-	/* Sort out negative (CPU/FD) and invalid clocks */
-	if (unlikely((unsigned int) clock >= MAX_CLOCKS))
-		return vdso_fallback_gettime(clock, ts);
-
-	/*
-	 * Convert the clockid to a bitmask and use it to check which
-	 * clocks are handled in the VDSO directly.
-	 */
-	msk = 1U << clock;
-	if (likely(msk & VGTOD_HRES)) {
-		return do_hres(clock, ts);
-	} else if (msk & VGTOD_COARSE) {
-		do_coarse(clock, ts);
-		return 0;
-	}
-	return vdso_fallback_gettime(clock, ts);
+	return __cvdso_clock_gettime32(clock, ts);
 }
 
-int clock_gettime(clockid_t, struct timespec *)
+int clock_gettime(clockid_t, struct old_timespec32 *)
 	__attribute__((weak, alias("__vdso_clock_gettime")));
 
-notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
-{
-	if (likely(tv != NULL)) {
-		struct timespec *ts = (struct timespec *) tv;
-
-		do_hres(CLOCK_REALTIME, ts);
-		tv->tv_usec /= 1000;
-	}
-	if (unlikely(tz != NULL)) {
-		tz->tz_minuteswest = gtod->tz_minuteswest;
-		tz->tz_dsttime = gtod->tz_dsttime;
-	}
-
-	return 0;
-}
-int gettimeofday(struct timeval *, struct timezone *)
-	__attribute__((weak, alias("__vdso_gettimeofday")));
-
-/*
- * This will break when the xtime seconds get inaccurate, but that is
- * unlikely
- */
-notrace time_t __vdso_time(time_t *t)
-{
-	/* This is atomic on x86 so we don't need any locks. */
-	time_t result = READ_ONCE(gtod->basetime[CLOCK_REALTIME].sec);
-
-	if (t)
-		*t = result;
-	return result;
-}
-time_t time(time_t *t)
-	__attribute__((weak, alias("__vdso_time")));
+#endif
diff --git a/arch/x86/entry/vdso/vdsox32.lds.S b/arch/x86/entry/vdso/vdsox32.lds.S
index 05cd1c5c4a15..16a8050a4fb6 100644
--- a/arch/x86/entry/vdso/vdsox32.lds.S
+++ b/arch/x86/entry/vdso/vdsox32.lds.S
@@ -21,6 +21,7 @@ VERSION {
 		__vdso_gettimeofday;
 		__vdso_getcpu;
 		__vdso_time;
+		__vdso_clock_getres;
 	local: *;
 	};
 }