5 files changed, 120 insertions, 60 deletions

diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile
index bef0bc9..5d17950 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/vdso/Makefile
@@ -26,6 +26,7 @@ targets += vdso.so vdso.so.dbg vdso.lds $(vobjs-y)
 export CPPFLAGS_vdso.lds += -P -C
 
 VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
+			-Wl,--no-undefined \
 		      	-Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
 
 $(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index a724905..6bc0e72 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -6,7 +6,6 @@
  *
  * The code should have no internal unresolved relocations.
  * Check with readelf after changing.
- * Also alternative() doesn't work.
  */
 
 /* Disable profiling for userspace code: */
@@ -17,6 +16,7 @@
 #include <linux/time.h>
 #include <linux/string.h>
 #include <asm/vsyscall.h>
+#include <asm/fixmap.h>
 #include <asm/vgtod.h>
 #include <asm/timex.h>
 #include <asm/hpet.h>
@@ -25,6 +25,43 @@
 
 #define gtod (&VVAR(vsyscall_gtod_data))
 
+notrace static cycle_t vread_tsc(void)
+{
+	cycle_t ret;
+	u64 last;
+
+	/*
+	 * Empirically, a fence (of type that depends on the CPU)
+	 * before rdtsc is enough to ensure that rdtsc is ordered
+	 * with respect to loads.  The various CPU manuals are unclear
+	 * as to whether rdtsc can be reordered with later loads,
+	 * but no one has ever seen it happen.
+	 */
+	rdtsc_barrier();
+	ret = (cycle_t)vget_cycles();
+
+	last = VVAR(vsyscall_gtod_data).clock.cycle_last;
+
+	if (likely(ret >= last))
+		return ret;
+
+	/*
+	 * GCC likes to generate cmov here, but this branch is extremely
+	 * predictable (it's just a funciton of time and the likely is
+	 * very likely) and there's a data dependence, so force GCC
+	 * to generate a branch instead.  I don't barrier() because
+	 * we don't actually need a barrier, and if this function
+	 * ever gets inlined it will generate worse code.
+	 */
+	asm volatile ("");
+	return last;
+}
+
+static notrace cycle_t vread_hpet(void)
+{
+	return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0);
+}
+
 notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 {
 	long ret;
@@ -36,9 +73,12 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 notrace static inline long vgetns(void)
 {
 	long v;
-	cycles_t (*vread)(void);
-	vread = gtod->clock.vread;
-	v = (vread() - gtod->clock.cycle_last) & gtod->clock.mask;
+	cycles_t cycles;
+	if (gtod->clock.vclock_mode == VCLOCK_TSC)
+		cycles = vread_tsc();
+	else
+		cycles = vread_hpet();
+	v = (cycles - gtod->clock.cycle_last) & gtod->clock.mask;
 	return (v * gtod->clock.mult) >> gtod->clock.shift;
 }
 
@@ -116,21 +156,21 @@ notrace static noinline int do_monotonic_coarse(struct timespec *ts)
 
 notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
 {
-	if (likely(gtod->sysctl_enabled))
-		switch (clock) {
-		case CLOCK_REALTIME:
-			if (likely(gtod->clock.vread))
-				return do_realtime(ts);
-			break;
-		case CLOCK_MONOTONIC:
-			if (likely(gtod->clock.vread))
-				return do_monotonic(ts);
-			break;
-		case CLOCK_REALTIME_COARSE:
-			return do_realtime_coarse(ts);
-		case CLOCK_MONOTONIC_COARSE:
-			return do_monotonic_coarse(ts);
-		}
+	switch (clock) {
+	case CLOCK_REALTIME:
+		if (likely(gtod->clock.vclock_mode != VCLOCK_NONE))
+			return do_realtime(ts);
+		break;
+	case CLOCK_MONOTONIC:
+		if (likely(gtod->clock.vclock_mode != VCLOCK_NONE))
+			return do_monotonic(ts);
+		break;
+	case CLOCK_REALTIME_COARSE:
+		return do_realtime_coarse(ts);
+	case CLOCK_MONOTONIC_COARSE:
+		return do_monotonic_coarse(ts);
+	}
+
 	return vdso_fallback_gettime(clock, ts);
 }
 int clock_gettime(clockid_t, struct timespec *)
@@ -139,7 +179,7 @@ int clock_gettime(clockid_t, struct timespec *)
 notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
 {
 	long ret;
-	if (likely(gtod->sysctl_enabled && gtod->clock.vread)) {
+	if (likely(gtod->clock.vclock_mode != VCLOCK_NONE)) {
 		if (likely(tv != NULL)) {
 			BUILD_BUG_ON(offsetof(struct timeval, tv_usec) !=
 				     offsetof(struct timespec, tv_nsec) ||
@@ -161,27 +201,14 @@ notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
 int gettimeofday(struct timeval *, struct timezone *)
 	__attribute__((weak, alias("__vdso_gettimeofday")));
 
-/* This will break when the xtime seconds get inaccurate, but that is
- * unlikely */
-
-static __always_inline long time_syscall(long *t)
-{
-	long secs;
-	asm volatile("syscall"
-		     : "=a" (secs)
-		     : "0" (__NR_time), "D" (t) : "cc", "r11", "cx", "memory");
-	return secs;
-}
-
+/*
+ * This will break when the xtime seconds get inaccurate, but that is
+ * unlikely
+ */
 notrace time_t __vdso_time(time_t *t)
 {
-	time_t result;
-
-	if (unlikely(!VVAR(vsyscall_gtod_data).sysctl_enabled))
-		return time_syscall(t);
-
 	/* This is atomic on x86_64 so we don't need any locks. */
-	result = ACCESS_ONCE(VVAR(vsyscall_gtod_data).wall_time_sec);
+	time_t result = ACCESS_ONCE(VVAR(vsyscall_gtod_data).wall_time_sec);
 
 	if (t)
 		*t = result;
diff --git a/arch/x86/vdso/vdso.S b/arch/x86/vdso/vdso.S
index 1d3aa6b..01f5e3b 100644
--- a/arch/x86/vdso/vdso.S
+++ b/arch/x86/vdso/vdso.S
@@ -1,10 +1,22 @@
+#include <asm/page_types.h>
+#include <linux/linkage.h>
 #include <linux/init.h>
 
-__INITDATA
+__PAGE_ALIGNED_DATA
 
 	.globl vdso_start, vdso_end
+	.align PAGE_SIZE
 vdso_start:
 	.incbin "arch/x86/vdso/vdso.so"
 vdso_end:
+	.align PAGE_SIZE /* extra data here leaks to userspace. */
 
-__FINIT
+.previous
+
+	.globl vdso_pages
+	.bss
+	.align 8
+	.type vdso_pages, @object
+vdso_pages:
+	.zero (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE * 8
+	.size vdso_pages, .-vdso_pages
diff --git a/arch/x86/vdso/vdso32/sysenter.S b/arch/x86/vdso/vdso32/sysenter.S
index e2800af..e354bce 100644
--- a/arch/x86/vdso/vdso32/sysenter.S
+++ b/arch/x86/vdso/vdso32/sysenter.S
@@ -43,7 +43,7 @@ __kernel_vsyscall:
 	.space 7,0x90
 
 	/* 14: System call restart point is here! (SYSENTER_RETURN-2) */
-	jmp .Lenter_kernel
+	int $0x80
 	/* 16: System call normal return point is here! */
 VDSO32_SYSENTER_RETURN:	/* Symbol used by sysenter.c via vdso32-syms.h */
 	pop %ebp
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index caa42ce..153407c 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -14,41 +14,61 @@
 #include <asm/vgtod.h>
 #include <asm/proto.h>
 #include <asm/vdso.h>
+#include <asm/page.h>
 
 unsigned int __read_mostly vdso_enabled = 1;
 
 extern char vdso_start[], vdso_end[];
 extern unsigned short vdso_sync_cpuid;
 
-static struct page **vdso_pages;
+extern struct page *vdso_pages[];
 static unsigned vdso_size;
 
-static int __init init_vdso_vars(void)
+static void __init patch_vdso(void *vdso, size_t len)
+{
+	Elf64_Ehdr *hdr = vdso;
+	Elf64_Shdr *sechdrs, *alt_sec = 0;
+	char *secstrings;
+	void *alt_data;
+	int i;
+
+	BUG_ON(len < sizeof(Elf64_Ehdr));
+	BUG_ON(memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0);
+
+	sechdrs = (void *)hdr + hdr->e_shoff;
+	secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+
+	for (i = 1; i < hdr->e_shnum; i++) {
+		Elf64_Shdr *shdr = &sechdrs[i];
+		if (!strcmp(secstrings + shdr->sh_name, ".altinstructions")) {
+			alt_sec = shdr;
+			goto found;
+		}
+	}
+
+	/* If we get here, it's probably a bug. */
+	pr_warning("patch_vdso: .altinstructions not found\n");
+	return;  /* nothing to patch */
+
+found:
+	alt_data = (void *)hdr + alt_sec->sh_offset;
+	apply_alternatives(alt_data, alt_data + alt_sec->sh_size);
+}
+
+static int __init init_vdso(void)
 {
 	int npages = (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE;
 	int i;
 
+	patch_vdso(vdso_start, vdso_end - vdso_start);
+
 	vdso_size = npages << PAGE_SHIFT;
-	vdso_pages = kmalloc(sizeof(struct page *) * npages, GFP_KERNEL);
-	if (!vdso_pages)
-		goto oom;
-	for (i = 0; i < npages; i++) {
-		struct page *p;
-		p = alloc_page(GFP_KERNEL);
-		if (!p)
-			goto oom;
-		vdso_pages[i] = p;
-		copy_page(page_address(p), vdso_start + i*PAGE_SIZE);
-	}
+	for (i = 0; i < npages; i++)
+		vdso_pages[i] = virt_to_page(vdso_start + i*PAGE_SIZE);
 
 	return 0;
-
- oom:
-	printk("Cannot allocate vdso\n");
-	vdso_enabled = 0;
-	return -ENOMEM;
 }
-subsys_initcall(init_vdso_vars);
+subsys_initcall(init_vdso);
 
 struct linux_binprm;