Merge branch 'x86-vdso-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 vdso updates from Ingo Molnar:
 "Add support for vDSO acceleration of the "Hyper-V TSC page", to speed
  up clock reading on Hyper-V guests"

* 'x86-vdso-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/vdso: Add VCLOCK_HVCLOCK vDSO clock read method
  x86/hyperv: Move TSC reading method to asm/mshyperv.h
  x86/hyperv: Implement hv_get_tsc_page()

3 files changed, 57 insertions, 1 deletions

diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h
index eae33c7170c8..47bea8cadbd0 100644
--- a/arch/x86/include/asm/clocksource.h
+++ b/arch/x86/include/asm/clocksource.h
@@ -6,7 +6,8 @@
 #define VCLOCK_NONE	0	/* No vDSO clock available.		*/
 #define VCLOCK_TSC	1	/* vDSO should use vread_tsc.		*/
 #define VCLOCK_PVCLOCK	2	/* vDSO should use vread_pvclock.	*/
-#define VCLOCK_MAX	2
+#define VCLOCK_HVCLOCK	3	/* vDSO should use vread_hvclock.	*/
+#define VCLOCK_MAX	3
 
 struct arch_clocksource_data {
 	int vclock_mode;
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 7c9c895432a9..fba100713924 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -176,4 +176,58 @@ void hyperv_report_panic(struct pt_regs *regs);
 bool hv_is_hypercall_page_setup(void);
 void hyperv_cleanup(void);
 #endif
+#ifdef CONFIG_HYPERV_TSCPAGE
+struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
+static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
+{
+	u64 scale, offset, cur_tsc;
+	u32 sequence;
+
+	/*
+	 * The protocol for reading Hyper-V TSC page is specified in Hypervisor
+	 * Top-Level Functional Specification ver. 3.0 and above. To get the
+	 * reference time we must do the following:
+	 * - READ ReferenceTscSequence
+	 *   A special '0' value indicates the time source is unreliable and we
+	 *   need to use something else. The currently published specification
+	 *   versions (up to 4.0b) contain a mistake and wrongly claim '-1'
+	 *   instead of '0' as the special value, see commit c35b82ef0294.
+	 * - ReferenceTime =
+	 *        ((RDTSC() * ReferenceTscScale) >> 64) + ReferenceTscOffset
+	 * - READ ReferenceTscSequence again. In case its value has changed
+	 *   since our first reading we need to discard ReferenceTime and repeat
+	 *   the whole sequence as the hypervisor was updating the page in
+	 *   between.
+	 */
+	do {
+		sequence = READ_ONCE(tsc_pg->tsc_sequence);
+		if (!sequence)
+			return U64_MAX;
+		/*
+		 * Make sure we read sequence before we read other values from
+		 * TSC page.
+		 */
+		smp_rmb();
+
+		scale = READ_ONCE(tsc_pg->tsc_scale);
+		offset = READ_ONCE(tsc_pg->tsc_offset);
+		cur_tsc = rdtsc_ordered();
+
+		/*
+		 * Make sure we read sequence after we read all other values
+		 * from TSC page.
+		 */
+		smp_rmb();
+
+	} while (READ_ONCE(tsc_pg->tsc_sequence) != sequence);
+
+	return mul_u64_u64_shr(cur_tsc, scale, 64) + offset;
+}
+
+#else
+static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
+{
+	return NULL;
+}
+#endif
 #endif
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index 2444189cbe28..bccdf4938ddf 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -20,6 +20,7 @@ struct vdso_image {
 	long sym_vvar_page;
 	long sym_hpet_page;
 	long sym_pvclock_page;
+	long sym_hvclock_page;
 	long sym_VDSO32_NOTE_MASK;
 	long sym___kernel_sigreturn;
 	long sym___kernel_rt_sigreturn;