Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linu…

…x/kernel/git/tip/tip

Pull x86 asm updates from Ingo Molnar:
 "The main changes in this cycle were:

   - vDSO and asm entry improvements (Andy Lutomirski)

   - Xen paravirt entry enhancements (Boris Ostrovsky)

   - asm entry labels enhancement (Borislav Petkov)

   - and other misc changes (Thomas Gleixner, me)"

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/vsdo: Fix build on PARAVIRT_CLOCK=y, KVM_GUEST=n
  Revert "x86/kvm: On KVM re-enable (e.g. after suspend), update clocks"
  x86/entry/64_compat: Make labels local
  x86/platform/uv: Include clocksource.h for clocksource_touch_watchdog()
  x86/vdso: Enable vdso pvclock access on all vdso variants
  x86/vdso: Remove pvclock fixmap machinery
  x86/vdso: Get pvclock data from the vvar VMA instead of the fixmap
  x86, vdso, pvclock: Simplify and speed up the vdso pvclock reader
  x86/kvm: On KVM re-enable (e.g. after suspend), update clocks
  x86/entry/64: Bypass enter_from_user_mode on non-context-tracking boots
  x86/asm: Add asm macros for static keys/jump labels
  x86/asm: Error out if asm/jump_label.h is included inappropriately
  context_tracking: Switch to new static_branch API
  x86/entry, x86/paravirt: Remove the unused usergs_sysret32 PV op
  x86/paravirt: Remove the unused irq_enable_sysexit pv op
  x86/xen: Avoid fast syscall path for Xen PV guests

arch/x86/entry/calling.h

@@ -1,3 +1,5 @@
+#include <linux/jump_label.h>
+
 /*
 
  x86 function call convention, 64-bit:
@@ -232,3 +234,16 @@ For 32-bit we have the following conventions - kernel is built with
 
 #endif /* CONFIG_X86_64 */
 
+/*
+ * This does 'call enter_from_user_mode' unless we can avoid it based on
+ * kernel config or using the static jump infrastructure.
+ */
+.macro CALL_enter_from_user_mode
+#ifdef CONFIG_CONTEXT_TRACKING
+#ifdef HAVE_JUMP_LABEL
+	STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0
+#endif
+	call enter_from_user_mode
+.Lafter_call_\@:
+#endif
+.endm

arch/x86/entry/entry_32.S

@@ -329,7 +329,8 @@ sysenter_past_esp:
 	 * Return back to the vDSO, which will pop ecx and edx.
 	 * Don't bother with DS and ES (they already contain __USER_DS).
 	 */
-	ENABLE_INTERRUPTS_SYSEXIT
+	sti
+	sysexit
 
 .pushsection .fixup, "ax"
 2:	movl	$0, PT_FS(%esp)
@@ -552,11 +553,6 @@ ENTRY(native_iret)
 	iret
 	_ASM_EXTABLE(native_iret, iret_exc)
 END(native_iret)
-
-ENTRY(native_irq_enable_sysexit)
-	sti
-	sysexit
-END(native_irq_enable_sysexit)
 #endif
 
 ENTRY(overflow)

arch/x86/entry/entry_64.S

@@ -520,9 +520,7 @@ END(irq_entries_start)
 	 */
 	TRACE_IRQS_OFF
 
-#ifdef CONFIG_CONTEXT_TRACKING
-	call enter_from_user_mode
-#endif
+	CALL_enter_from_user_mode
 
 1:
 	/*
@@ -1066,9 +1064,7 @@ ENTRY(error_entry)
 	 * (which can take locks).
 	 */
 	TRACE_IRQS_OFF
-#ifdef CONFIG_CONTEXT_TRACKING
-	call enter_from_user_mode
-#endif
+	CALL_enter_from_user_mode
 	ret
 
 .Lerror_entry_done:

arch/x86/entry/entry_64_compat.S

@@ -18,13 +18,6 @@
 
 	.section .entry.text, "ax"
 
-#ifdef CONFIG_PARAVIRT
-ENTRY(native_usergs_sysret32)
-	swapgs
-	sysretl
-ENDPROC(native_usergs_sysret32)
-#endif
-
 /*
  * 32-bit SYSENTER instruction entry.
  *
@@ -103,15 +96,15 @@ ENTRY(entry_SYSENTER_compat)
 	 * This needs to happen before enabling interrupts so that
 	 * we don't get preempted with NT set.
 	 *
-	 * NB.: sysenter_fix_flags is a label with the code under it moved
+	 * NB.: .Lsysenter_fix_flags is a label with the code under it moved
 	 * out-of-line as an optimization: NT is unlikely to be set in the
 	 * majority of the cases and instead of polluting the I$ unnecessarily,
 	 * we're keeping that code behind a branch which will predict as
 	 * not-taken and therefore its instructions won't be fetched.
 	 */
 	testl	$X86_EFLAGS_NT, EFLAGS(%rsp)
-	jnz	sysenter_fix_flags
-sysenter_flags_fixed:
+	jnz	.Lsysenter_fix_flags
+.Lsysenter_flags_fixed:
 
 	/*
 	 * User mode is traced as though IRQs are on, and SYSENTER
@@ -126,10 +119,10 @@ sysenter_flags_fixed:
 		    "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
 	jmp	sysret32_from_system_call
 
-sysenter_fix_flags:
+.Lsysenter_fix_flags:
 	pushq	$X86_EFLAGS_FIXED
 	popfq
-	jmp	sysenter_flags_fixed
+	jmp	.Lsysenter_flags_fixed
 ENDPROC(entry_SYSENTER_compat)
 
 /*
@@ -238,7 +231,8 @@ sysret32_from_system_call:
 	xorq	%r9, %r9
 	xorq	%r10, %r10
 	movq	RSP-ORIG_RAX(%rsp), %rsp
-        USERGS_SYSRET32
+	swapgs
+	sysretl
 END(entry_SYSCALL_compat)
 
 /*

arch/x86/entry/vdso/vclock_gettime.c

@@ -17,8 +17,10 @@
 #include <asm/vvar.h>
 #include <asm/unistd.h>
 #include <asm/msr.h>
+#include <asm/pvclock.h>
 #include <linux/math64.h>
 #include <linux/time.h>
+#include <linux/kernel.h>
 
 #define gtod (&VVAR(vsyscall_gtod_data))
 
@@ -36,12 +38,12 @@ static notrace cycle_t vread_hpet(void)
 }
 #endif
 
-#ifndef BUILD_VDSO32
+#ifdef CONFIG_PARAVIRT_CLOCK
+extern u8 pvclock_page
+	__attribute__((visibility("hidden")));
+#endif
 
-#include <linux/kernel.h>
-#include <asm/vsyscall.h>
-#include <asm/fixmap.h>
-#include <asm/pvclock.h>
+#ifndef BUILD_VDSO32
 
 notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 {
@@ -60,75 +62,6 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
 	return ret;
 }
 
-#ifdef CONFIG_PARAVIRT_CLOCK
-
-static notrace const struct pvclock_vsyscall_time_info *get_pvti(int cpu)
-{
-	const struct pvclock_vsyscall_time_info *pvti_base;
-	int idx = cpu / (PAGE_SIZE/PVTI_SIZE);
-	int offset = cpu % (PAGE_SIZE/PVTI_SIZE);
-
-	BUG_ON(PVCLOCK_FIXMAP_BEGIN + idx > PVCLOCK_FIXMAP_END);
-
-	pvti_base = (struct pvclock_vsyscall_time_info *)
-		    __fix_to_virt(PVCLOCK_FIXMAP_BEGIN+idx);
-
-	return &pvti_base[offset];
-}
-
-static notrace cycle_t vread_pvclock(int *mode)
-{
-	const struct pvclock_vsyscall_time_info *pvti;
-	cycle_t ret;
-	u64 last;
-	u32 version;
-	u8 flags;
-	unsigned cpu, cpu1;
-
-
-	/*
-	 * Note: hypervisor must guarantee that:
-	 * 1. cpu ID number maps 1:1 to per-CPU pvclock time info.
-	 * 2. that per-CPU pvclock time info is updated if the
-	 *    underlying CPU changes.
-	 * 3. that version is increased whenever underlying CPU
-	 *    changes.
-	 *
-	 */
-	do {
-		cpu = __getcpu() & VGETCPU_CPU_MASK;
-		/* TODO: We can put vcpu id into higher bits of pvti.version.
-		 * This will save a couple of cycles by getting rid of
-		 * __getcpu() calls (Gleb).
-		 */
-
-		pvti = get_pvti(cpu);
-
-		version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
-
-		/*
-		 * Test we're still on the cpu as well as the version.
-		 * We could have been migrated just after the first
-		 * vgetcpu but before fetching the version, so we
-		 * wouldn't notice a version change.
-		 */
-		cpu1 = __getcpu() & VGETCPU_CPU_MASK;
-	} while (unlikely(cpu != cpu1 ||
-			  (pvti->pvti.version & 1) ||
-			  pvti->pvti.version != version));
-
-	if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT)))
-		*mode = VCLOCK_NONE;
-
-	/* refer to tsc.c read_tsc() comment for rationale */
-	last = gtod->cycle_last;
-
-	if (likely(ret >= last))
-		return ret;
-
-	return last;
-}
-#endif
 
 #else
 
@@ -162,15 +95,77 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
 	return ret;
 }
 
+#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;
+}
 
 static notrace cycle_t vread_pvclock(int *mode)
 {
-	*mode = VCLOCK_NONE;
-	return 0;
-}
-#endif
+	const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti;
+	cycle_t ret;
+	u64 tsc, pvti_tsc;
+	u64 last, delta, pvti_system_time;
+	u32 version, pvti_tsc_to_system_mul, pvti_tsc_shift;
+
+	/*
+	 * 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.
+	 */
 
+	if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) {
+		*mode = VCLOCK_NONE;
+		return 0;
+	}
+
+	do {
+		version = pvti->version;
+
+		smp_rmb();
+
+		tsc = rdtsc_ordered();
+		pvti_tsc_to_system_mul = pvti->tsc_to_system_mul;
+		pvti_tsc_shift = pvti->tsc_shift;
+		pvti_system_time = pvti->system_time;
+		pvti_tsc = pvti->tsc_timestamp;
+
+		/* Make sure that the version double-check is last. */
+		smp_rmb();
+	} while (unlikely((version & 1) || version != pvti->version));
+
+	delta = tsc - pvti_tsc;
+	ret = pvti_system_time +
+		pvclock_scale_delta(delta, pvti_tsc_to_system_mul,
+				    pvti_tsc_shift);
+
+	/* refer to vread_tsc() comment for rationale */
+	last = gtod->cycle_last;
+
+	if (likely(ret >= last))
+		return ret;
+
+	return last;
+}
 #endif
 
 notrace static cycle_t vread_tsc(void)

arch/x86/entry/vdso/vdso-layout.lds.S

@@ -25,7 +25,7 @@ SECTIONS
 	 * segment.
 	 */
 
-	vvar_start = . - 2 * PAGE_SIZE;
+	vvar_start = . - 3 * PAGE_SIZE;
 	vvar_page = vvar_start;
 
 	/* Place all vvars at the offsets in asm/vvar.h. */
@@ -36,6 +36,7 @@ SECTIONS
 #undef EMIT_VVAR
 
 	hpet_page = vvar_start + PAGE_SIZE;
+	pvclock_page = vvar_start + 2 * PAGE_SIZE;
 
 	. = SIZEOF_HEADERS;
 

arch/x86/entry/vdso/vdso2c.c

@@ -73,13 +73,15 @@ enum {
 	sym_vvar_start,
 	sym_vvar_page,
 	sym_hpet_page,
+	sym_pvclock_page,
 	sym_VDSO_FAKE_SECTION_TABLE_START,
 	sym_VDSO_FAKE_SECTION_TABLE_END,
 };
 
 const int special_pages[] = {
 	sym_vvar_page,
 	sym_hpet_page,
+	sym_pvclock_page,
 };
 
 struct vdso_sym {
@@ -91,6 +93,7 @@ struct vdso_sym required_syms[] = {
 	[sym_vvar_start] = {"vvar_start", true},
 	[sym_vvar_page] = {"vvar_page", true},
 	[sym_hpet_page] = {"hpet_page", true},
+	[sym_pvclock_page] = {"pvclock_page", true},
 	[sym_VDSO_FAKE_SECTION_TABLE_START] = {
 		"VDSO_FAKE_SECTION_TABLE_START", false
 	},

arch/x86/entry/vdso/vma.c

@@ -12,6 +12,7 @@
 #include <linux/random.h>
 #include <linux/elf.h>
 #include <linux/cpu.h>
+#include <asm/pvclock.h>
 #include <asm/vgtod.h>
 #include <asm/proto.h>
 #include <asm/vdso.h>
@@ -100,6 +101,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 		.name = "[vvar]",
 		.pages = no_pages,
 	};
+	struct pvclock_vsyscall_time_info *pvti;
 
 	if (calculate_addr) {
 		addr = vdso_addr(current->mm->start_stack,
@@ -169,6 +171,18 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 	}
 #endif
 
+	pvti = pvclock_pvti_cpu0_va();
+	if (pvti && image->sym_pvclock_page) {
+		ret = remap_pfn_range(vma,
+				      text_start + image->sym_pvclock_page,
+				      __pa(pvti) >> PAGE_SHIFT,
+				      PAGE_SIZE,
+				      PAGE_READONLY);
+
+		if (ret)
+			goto up_fail;
+	}
+
 up_fail:
 	if (ret)
 		current->mm->context.vdso = NULL;