x86/vdso: Get pvclock data from the vvar VMA instead of the fixmap

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/9d37826fdc7e2d2809efe31d5345f97186859284.1449702533.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/entry/vdso/vclock_gettime.c

@@ -36,6 +36,11 @@ static notrace cycle_t vread_hpet(void)
 }
 #endif
 
+#ifdef CONFIG_PARAVIRT_CLOCK
+extern u8 pvclock_page
+	__attribute__((visibility("hidden")));
+#endif
+
 #ifndef BUILD_VDSO32
 
 #include <linux/kernel.h>
@@ -62,23 +67,14 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
 
 #ifdef CONFIG_PARAVIRT_CLOCK
 
-static notrace const struct pvclock_vsyscall_time_info *get_pvti(int cpu)
+static notrace const struct pvclock_vsyscall_time_info *get_pvti0(void)
 {
-	const struct pvclock_vsyscall_time_info *pvti_base;
+	return (const struct pvclock_vsyscall_time_info *)&pvclock_page;
-	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_vcpu_time_info *pvti = &get_pvti(0)->pvti;
+	const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti;
 	cycle_t ret;
 	u64 tsc, pvti_tsc;
 	u64 last, delta, pvti_system_time;

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

@@ -73,6 +73,7 @@ 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,
 };
@@ -80,6 +81,7 @@ enum {
 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

@@ -100,6 +100,7 @@ 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 +170,18 @@ 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;

arch/x86/include/asm/pvclock.h

@@ -4,6 +4,15 @@
 #include <linux/clocksource.h>
 #include <asm/pvclock-abi.h>
 
+#ifdef CONFIG_PARAVIRT_CLOCK
+extern struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void);
+#else
+static inline struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
+{
+	return NULL;
+}
+#endif
+
 /* some helper functions for xen and kvm pv clock sources */
 cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
 u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src);

arch/x86/include/asm/vdso.h

@@ -22,6 +22,7 @@ struct vdso_image {
 
 	long sym_vvar_page;
 	long sym_hpet_page;
+	long sym_pvclock_page;
 	long sym_VDSO32_NOTE_MASK;
 	long sym___kernel_sigreturn;
 	long sym___kernel_rt_sigreturn;

arch/x86/kernel/kvmclock.c

@@ -45,6 +45,11 @@ early_param("no-kvmclock", parse_no_kvmclock);
 static struct pvclock_vsyscall_time_info *hv_clock;
 static struct pvclock_wall_clock wall_clock;
 
+struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
+{
+	return hv_clock;
+}
+
 /*
  * The wallclock is the time of day when we booted. Since then, some time may
  * have elapsed since the hypervisor wrote the data. So we try to account for