Merge remote-tracking branch 'hyperv/hyperv-next'

17 files changed, 669 insertions, 476 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 48120de227b3..731b8879bce9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7333,6 +7333,7 @@ F:	arch/x86/include/asm/trace/hyperv.h
 F:	arch/x86/include/asm/hyperv-tlfs.h
 F:	arch/x86/kernel/cpu/mshyperv.c
 F:	arch/x86/hyperv
+F:	drivers/clocksource/hyperv_timer.c
 F:	drivers/hid/hid-hyperv.c
 F:	drivers/hv/
 F:	drivers/input/serio/hyperv-keyboard.c
@@ -7343,8 +7344,10 @@ F:	drivers/uio/uio_hv_generic.c
 F:	drivers/video/fbdev/hyperv_fb.c
 F:	drivers/iommu/hyperv_iommu.c
 F:	net/vmw_vsock/hyperv_transport.c
+F:	include/clocksource/hyperv_timer.h
 F:	include/linux/hyperv.h
 F:	include/uapi/linux/hyperv.h
+F:	include/asm-generic/mshyperv.h
 F:	tools/hv/
 F:	Documentation/ABI/stable/sysfs-bus-vmbus
 
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 0f82a70c7682..310e7bf59ad2 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -21,6 +21,7 @@
 #include <linux/math64.h>
 #include <linux/time.h>
 #include <linux/kernel.h>
+#include <clocksource/hyperv_timer.h>
 
 #define gtod (&VVAR(vsyscall_gtod_data))
 
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 8db1f594e8b1..349a61d8bf34 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -22,7 +22,7 @@
 #include <asm/page.h>
 #include <asm/desc.h>
 #include <asm/cpufeature.h>
-#include <asm/mshyperv.h>
+#include <clocksource/hyperv_timer.h>
 
 #if defined(CONFIG_X86_64)
 unsigned int __read_mostly vdso64_enabled = 1;
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 1608050e9df9..0e033ef11a9f 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -17,64 +17,13 @@
 #include <linux/version.h>
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
-#include <linux/clockchips.h>
 #include <linux/hyperv.h>
 #include <linux/slab.h>
 #include <linux/cpuhotplug.h>
-
-#ifdef CONFIG_HYPERV_TSCPAGE
-
-static struct ms_hyperv_tsc_page *tsc_pg;
-
-struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
-{
-	return tsc_pg;
-}
-EXPORT_SYMBOL_GPL(hv_get_tsc_page);
-
-static u64 read_hv_clock_tsc(struct clocksource *arg)
-{
-	u64 current_tick = hv_read_tsc_page(tsc_pg);
-
-	if (current_tick == U64_MAX)
-		rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
-
-	return current_tick;
-}
-
-static struct clocksource hyperv_cs_tsc = {
-		.name		= "hyperv_clocksource_tsc_page",
-		.rating		= 400,
-		.read		= read_hv_clock_tsc,
-		.mask		= CLOCKSOURCE_MASK(64),
-		.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
-};
-#endif
-
-static u64 read_hv_clock_msr(struct clocksource *arg)
-{
-	u64 current_tick;
-	/*
-	 * Read the partition counter to get the current tick count. This count
-	 * is set to 0 when the partition is created and is incremented in
-	 * 100 nanosecond units.
-	 */
-	rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
-	return current_tick;
-}
-
-static struct clocksource hyperv_cs_msr = {
-	.name		= "hyperv_clocksource_msr",
-	.rating		= 400,
-	.read		= read_hv_clock_msr,
-	.mask		= CLOCKSOURCE_MASK(64),
-	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
-};
+#include <clocksource/hyperv_timer.h>
 
 void *hv_hypercall_pg;
 EXPORT_SYMBOL_GPL(hv_hypercall_pg);
-struct clocksource *hyperv_cs;
-EXPORT_SYMBOL_GPL(hyperv_cs);
 
 u32 *hv_vp_index;
 EXPORT_SYMBOL_GPL(hv_vp_index);
@@ -343,42 +292,8 @@ void __init hyperv_init(void)
 
 	x86_init.pci.arch_init = hv_pci_init;
 
-	/*
-	 * Register Hyper-V specific clocksource.
-	 */
-#ifdef CONFIG_HYPERV_TSCPAGE
-	if (ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE) {
-		union hv_x64_msr_hypercall_contents tsc_msr;
-
-		tsc_pg = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL);
-		if (!tsc_pg)
-			goto register_msr_cs;
-
-		hyperv_cs = &hyperv_cs_tsc;
-
-		rdmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
-
-		tsc_msr.enable = 1;
-		tsc_msr.guest_physical_address = vmalloc_to_pfn(tsc_pg);
-
-		wrmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
-
-		hyperv_cs_tsc.archdata.vclock_mode = VCLOCK_HVCLOCK;
-
-		clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
-		return;
-	}
-register_msr_cs:
-#endif
-	/*
-	 * For 32 bit guests just use the MSR based mechanism for reading
-	 * the partition counter.
-	 */
-
-	hyperv_cs = &hyperv_cs_msr;
-	if (ms_hyperv.features & HV_MSR_TIME_REF_COUNT_AVAILABLE)
-		clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
-
+	/* Register Hyper-V specific clocksource */
+	hv_init_clocksource();
 	return;
 
 remove_cpuhp_state:
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index cdf44aa9a501..af78cd72b8f3 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -401,6 +401,12 @@ enum HV_GENERIC_SET_FORMAT {
 #define HV_STATUS_INVALID_CONNECTION_ID		18
 #define HV_STATUS_INSUFFICIENT_BUFFERS		19
 
+/*
+ * The Hyper-V TimeRefCount register and the TSC
+ * page provide a guest VM clock with 100ns tick rate
+ */
+#define HV_CLOCK_HZ (NSEC_PER_SEC/100)
+
 typedef struct _HV_REFERENCE_TSC_PAGE {
 	__u32 tsc_sequence;
 	__u32 res1;
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index cc60e617931c..2a793bf6ebb0 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -3,84 +3,15 @@
 #define _ASM_X86_MSHYPER_H
 
 #include <linux/types.h>
-#include <linux/atomic.h>
 #include <linux/nmi.h>
 #include <asm/io.h>
 #include <asm/hyperv-tlfs.h>
 #include <asm/nospec-branch.h>
 
-#define VP_INVAL	U32_MAX
-
-struct ms_hyperv_info {
-	u32 features;
-	u32 misc_features;
-	u32 hints;
-	u32 nested_features;
-	u32 max_vp_index;
-	u32 max_lp_index;
-};
-
-extern struct ms_hyperv_info ms_hyperv;
-
-
 typedef int (*hyperv_fill_flush_list_func)(
 		struct hv_guest_mapping_flush_list *flush,
 		void *data);
 
-/*
- * Generate the guest ID.
- */
-
-static inline  __u64 generate_guest_id(__u64 d_info1, __u64 kernel_version,
-				       __u64 d_info2)
-{
-	__u64 guest_id = 0;
-
-	guest_id = (((__u64)HV_LINUX_VENDOR_ID) << 48);
-	guest_id |= (d_info1 << 48);
-	guest_id |= (kernel_version << 16);
-	guest_id |= d_info2;
-
-	return guest_id;
-}
-
-
-/* Free the message slot and signal end-of-message if required */
-static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
-{
-	/*
-	 * On crash we're reading some other CPU's message page and we need
-	 * to be careful: this other CPU may already had cleared the header
-	 * and the host may already had delivered some other message there.
-	 * In case we blindly write msg->header.message_type we're going
-	 * to lose it. We can still lose a message of the same type but
-	 * we count on the fact that there can only be one
-	 * CHANNELMSG_UNLOAD_RESPONSE and we don't care about other messages
-	 * on crash.
-	 */
-	if (cmpxchg(&msg->header.message_type, old_msg_type,
-		    HVMSG_NONE) != old_msg_type)
-		return;
-
-	/*
-	 * Make sure the write to MessageType (ie set to
-	 * HVMSG_NONE) happens before we read the
-	 * MessagePending and EOMing. Otherwise, the EOMing
-	 * will not deliver any more messages since there is
-	 * no empty slot
-	 */
-	mb();
-
-	if (msg->header.message_flags.msg_pending) {
-		/*
-		 * This will cause message queue rescan to
-		 * possibly deliver another msg from the
-		 * hypervisor
-		 */
-		wrmsrl(HV_X64_MSR_EOM, 0);
-	}
-}
-
 #define hv_init_timer(timer, tick) \
 	wrmsrl(HV_X64_MSR_STIMER0_COUNT + (2*timer), tick)
 #define hv_init_timer_config(timer, val) \
@@ -97,6 +28,8 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
 
 #define hv_get_vp_index(index) rdmsrl(HV_X64_MSR_VP_INDEX, index)
 
+#define hv_signal_eom() wrmsrl(HV_X64_MSR_EOM, 0)
+
 #define hv_get_synint_state(int_num, val) \
 	rdmsrl(HV_X64_MSR_SINT0 + int_num, val)
 #define hv_set_synint_state(int_num, val) \
@@ -105,19 +38,23 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
 #define hv_get_crash_ctl(val) \
 	rdmsrl(HV_X64_MSR_CRASH_CTL, val)
 
+#define hv_get_time_ref_count(val) \
+	rdmsrl(HV_X64_MSR_TIME_REF_COUNT, val)
+
+#define hv_get_reference_tsc(val) \
+	rdmsrl(HV_X64_MSR_REFERENCE_TSC, val)
+#define hv_set_reference_tsc(val) \
+	wrmsrl(HV_X64_MSR_REFERENCE_TSC, val)
+#define hv_set_clocksource_vdso(val) \
+	((val).archdata.vclock_mode = VCLOCK_HVCLOCK)
+#define hv_get_raw_timer() rdtsc_ordered()
+
 void hyperv_callback_vector(void);
 void hyperv_reenlightenment_vector(void);
 #ifdef CONFIG_TRACING
 #define trace_hyperv_callback_vector hyperv_callback_vector
 #endif
 void hyperv_vector_handler(struct pt_regs *regs);
-void hv_setup_vmbus_irq(void (*handler)(void));
-void hv_remove_vmbus_irq(void);
-
-void hv_setup_kexec_handler(void (*handler)(void));
-void hv_remove_kexec_handler(void);
-void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs));
-void hv_remove_crash_handler(void);
 
 /*
  * Routines for stimer0 Direct Mode handling.
@@ -125,15 +62,12 @@ void hv_remove_crash_handler(void);
  */
 void hv_stimer0_vector_handler(struct pt_regs *regs);
 void hv_stimer0_callback_vector(void);
-int hv_setup_stimer0_irq(int *irq, int *vector, void (*handler)(void));
-void hv_remove_stimer0_irq(int irq);
 
 static inline void hv_enable_stimer0_percpu_irq(int irq) {}
 static inline void hv_disable_stimer0_percpu_irq(int irq) {}
 
 
 #if IS_ENABLED(CONFIG_HYPERV)
-extern struct clocksource *hyperv_cs;
 extern void *hv_hypercall_pg;
 extern void  __percpu  **hyperv_pcpu_input_arg;
 
@@ -272,14 +206,6 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size,
 	return status;
 }
 
-/*
- * Hypervisor's notion of virtual processor ID is different from
- * Linux' notion of CPU ID. This information can only be retrieved
- * in the context of the calling CPU. Setup a map for easy access
- * to this information.
- */
-extern u32 *hv_vp_index;
-extern u32 hv_max_vp_index;
 extern struct hv_vp_assist_page **hv_vp_assist_page;
 
 static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu)
@@ -290,63 +216,8 @@ static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu)
 	return hv_vp_assist_page[cpu];
 }
 
-/**
- * hv_cpu_number_to_vp_number() - Map CPU to VP.
- * @cpu_number: CPU number in Linux terms
- *
- * This function returns the mapping between the Linux processor
- * number and the hypervisor's virtual processor number, useful
- * in making hypercalls and such that talk about specific
- * processors.
- *
- * Return: Virtual processor number in Hyper-V terms
- */
-static inline int hv_cpu_number_to_vp_number(int cpu_number)
-{
-	return hv_vp_index[cpu_number];
-}
-
-static inline int cpumask_to_vpset(struct hv_vpset *vpset,
-				    const struct cpumask *cpus)
-{
-	int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1;
-
-	/* valid_bank_mask can represent up to 64 banks */
-	if (hv_max_vp_index / 64 >= 64)
-		return 0;
-
-	/*
-	 * Clear all banks up to the maximum possible bank as hv_tlb_flush_ex
-	 * structs are not cleared between calls, we risk flushing unneeded
-	 * vCPUs otherwise.
-	 */
-	for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++)
-		vpset->bank_contents[vcpu_bank] = 0;
-
-	/*
-	 * Some banks may end up being empty but this is acceptable.
-	 */
-	for_each_cpu(cpu, cpus) {
-		vcpu = hv_cpu_number_to_vp_number(cpu);
-		if (vcpu == VP_INVAL)
-			return -1;
-		vcpu_bank = vcpu / 64;
-		vcpu_offset = vcpu % 64;
-		__set_bit(vcpu_offset, (unsigned long *)
-			  &vpset->bank_contents[vcpu_bank]);
-		if (vcpu_bank >= nr_bank)
-			nr_bank = vcpu_bank + 1;
-	}
-	vpset->valid_bank_mask = GENMASK_ULL(nr_bank - 1, 0);
-	return nr_bank;
-}
-
 void __init hyperv_init(void);
 void hyperv_setup_mmu_ops(void);
-void hyperv_report_panic(struct pt_regs *regs, long err);
-void hyperv_report_panic_msg(phys_addr_t pa, size_t size);
-bool hv_is_hyperv_initialized(void);
-void hyperv_cleanup(void);
 
 void hyperv_reenlightenment_intr(struct pt_regs *regs);
 void set_hv_tscchange_cb(void (*cb)(void));
@@ -369,8 +240,6 @@ static inline void hv_apic_init(void) {}
 
 #else /* CONFIG_HYPERV */
 static inline void hyperv_init(void) {}
-static inline bool hv_is_hyperv_initialized(void) { return false; }
-static inline void hyperv_cleanup(void) {}
 static inline void hyperv_setup_mmu_ops(void) {}
 static inline void set_hv_tscchange_cb(void (*cb)(void)) {}
 static inline void clear_hv_tscchange_cb(void) {}
@@ -387,73 +256,6 @@ static inline int hyperv_flush_guest_mapping_range(u64 as,
 }
 #endif /* CONFIG_HYPERV */
 
-#ifdef CONFIG_HYPERV_TSCPAGE
-struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
-static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
-				       u64 *cur_tsc)
-{
-	u64 scale, offset;
-	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;
-}
+#include <asm-generic/mshyperv.h>
 
-static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
-{
-	u64 cur_tsc;
-
-	return hv_read_tsc_page_tsc(tsc_pg, &cur_tsc);
-}
-
-#else
-static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
-{
-	return NULL;
-}
-
-static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
-				       u64 *cur_tsc)
-{
-	BUG();
-	return U64_MAX;
-}
-#endif
 #endif
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 39490b46c9e2..e0d1440fdc2a 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -17,6 +17,7 @@
 #include <linux/irq.h>
 #include <linux/kexec.h>
 #include <linux/i8253.h>
+#include <linux/random.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
 #include <asm/hyperv-tlfs.h>
@@ -80,6 +81,7 @@ __visible void __irq_entry hv_stimer0_vector_handler(struct pt_regs *regs)
 	inc_irq_stat(hyperv_stimer0_count);
 	if (hv_stimer0_handler)
 		hv_stimer0_handler();
+	add_interrupt_randomness(HYPERV_STIMER0_VECTOR, 0);
 	ack_APIC_irq();
 
 	exiting_irq();
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 83aefd759846..5cb42f285666 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -70,6 +70,7 @@
 #include <asm/mshyperv.h>
 #include <asm/hypervisor.h>
 #include <asm/intel_pt.h>
+#include <clocksource/hyperv_timer.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 0939886b305f..8de3c71f7e42 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -85,3 +85,4 @@ obj-$(CONFIG_ATCPIT100_TIMER)		+= timer-atcpit100.o
 obj-$(CONFIG_RISCV_TIMER)		+= timer-riscv.o
 obj-$(CONFIG_CSKY_MP_TIMER)		+= timer-mp-csky.o
 obj-$(CONFIG_GX6605S_TIMER)		+= timer-gx6605s.o
+obj-$(CONFIG_HYPERV_TIMER)		+= hyperv_timer.o
diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
new file mode 100644
index 000000000000..274614dd9d41
--- /dev/null
+++ b/drivers/clocksource/hyperv_timer.c
@@ -0,0 +1,321 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Clocksource driver for the synthetic counter and timers
+ * provided by the Hyper-V hypervisor to guest VMs, as described
+ * in the Hyper-V Top Level Functional Spec (TLFS). This driver
+ * is instruction set architecture independent.
+ *
+ * Copyright (C) 2019, Microsoft, Inc.
+ *
+ * Author:  Michael Kelley <mikelley@microsoft.com>
+ */
+
+#include <linux/percpu.h>
+#include <linux/cpumask.h>
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/sched_clock.h>
+#include <linux/mm.h>
+#include <clocksource/hyperv_timer.h>
+#include <asm/hyperv-tlfs.h>
+#include <asm/mshyperv.h>
+
+static struct clock_event_device __percpu *hv_clock_event;
+
+/*
+ * If false, we're using the old mechanism for stimer0 interrupts
+ * where it sends a VMbus message when it expires. The old
+ * mechanism is used when running on older versions of Hyper-V
+ * that don't support Direct Mode. While Hyper-V provides
+ * four stimer's per CPU, Linux uses only stimer0.
+ */
+static bool direct_mode_enabled;
+
+static int stimer0_irq;
+static int stimer0_vector;
+static int stimer0_message_sint;
+
+/*
+ * ISR for when stimer0 is operating in Direct Mode.  Direct Mode
+ * does not use VMbus or any VMbus messages, so process here and not
+ * in the VMbus driver code.
+ */
+void hv_stimer0_isr(void)
+{
+	struct clock_event_device *ce;
+
+	ce = this_cpu_ptr(hv_clock_event);
+	ce->event_handler(ce);
+}
+EXPORT_SYMBOL_GPL(hv_stimer0_isr);
+
+static int hv_ce_set_next_event(unsigned long delta,
+				struct clock_event_device *evt)
+{
+	u64 current_tick;
+
+	WARN_ON(!clockevent_state_oneshot(evt));
+
+	current_tick = hyperv_cs->read(NULL);
+	current_tick += delta;
+	hv_init_timer(0, current_tick);
+	return 0;
+}
+
+static int hv_ce_shutdown(struct clock_event_device *evt)
+{
+	hv_init_timer(0, 0);
+	hv_init_timer_config(0, 0);
+	if (direct_mode_enabled)
+		hv_disable_stimer0_percpu_irq(stimer0_irq);
+
+	return 0;
+}
+
+static int hv_ce_set_oneshot(struct clock_event_device *evt)
+{
+	union hv_stimer_config timer_cfg;
+
+	timer_cfg.as_uint64 = 0;
+	timer_cfg.enable = 1;
+	timer_cfg.auto_enable = 1;
+	if (direct_mode_enabled) {
+		/*
+		 * When it expires, the timer will directly interrupt
+		 * on the specified hardware vector/IRQ.
+		 */
+		timer_cfg.direct_mode = 1;
+		timer_cfg.apic_vector = stimer0_vector;
+		hv_enable_stimer0_percpu_irq(stimer0_irq);
+	} else {
+		/*
+		 * When it expires, the timer will generate a VMbus message,
+		 * to be handled by the normal VMbus interrupt handler.
+		 */
+		timer_cfg.direct_mode = 0;
+		timer_cfg.sintx = stimer0_message_sint;
+	}
+	hv_init_timer_config(0, timer_cfg.as_uint64);
+	return 0;
+}
+
+/*
+ * hv_stimer_init - Per-cpu initialization of the clockevent
+ */
+int hv_stimer_init(unsigned int cpu)
+{
+	struct clock_event_device *ce;
+
+	if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) {
+		ce = per_cpu_ptr(hv_clock_event, cpu);
+		ce->name = "Hyper-V clockevent";
+		ce->features = CLOCK_EVT_FEAT_ONESHOT;
+		ce->cpumask = cpumask_of(cpu);
+		ce->rating = 1000;
+		ce->set_state_shutdown = hv_ce_shutdown;
+		ce->set_state_oneshot = hv_ce_set_oneshot;
+		ce->set_next_event = hv_ce_set_next_event;
+
+		clockevents_config_and_register(ce,
+						HV_CLOCK_HZ,
+						HV_MIN_DELTA_TICKS,
+						HV_MAX_MAX_DELTA_TICKS);
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(hv_stimer_init);
+
+/*
+ * hv_stimer_cleanup - Per-cpu cleanup of the clockevent
+ */
+int hv_stimer_cleanup(unsigned int cpu)
+{
+	struct clock_event_device *ce;
+
+	/* Turn off clockevent device */
+	if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) {
+		ce = per_cpu_ptr(hv_clock_event, cpu);
+		clockevents_unbind_device(ce, cpu);
+		hv_ce_shutdown(ce);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(hv_stimer_cleanup);
+
+/* hv_stimer_alloc - Global initialization of the clockevent and stimer0 */
+int hv_stimer_alloc(int sint)
+{
+	hv_clock_event = alloc_percpu(struct clock_event_device);
+	if (!hv_clock_event)
+		return -ENOMEM;
+
+	direct_mode_enabled = ms_hyperv.misc_features &
+			HV_STIMER_DIRECT_MODE_AVAILABLE;
+	if (direct_mode_enabled &&
+	    hv_setup_stimer0_irq(&stimer0_irq, &stimer0_vector,
+				hv_stimer0_isr)) {
+		free_percpu(hv_clock_event);
+		return -EINVAL;
+	}
+
+	stimer0_message_sint = sint;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(hv_stimer_alloc);
+
+/* hv_stimer_free - Free global resources allocated by hv_stimer_alloc() */
+void hv_stimer_free(void)
+{
+	if (direct_mode_enabled)
+		hv_remove_stimer0_irq(stimer0_irq);
+	free_percpu(hv_clock_event);
+}
+EXPORT_SYMBOL_GPL(hv_stimer_free);
+
+/*
+ * Do a global cleanup of clockevents for the cases of kexec and
+ * vmbus exit
+ */
+void hv_stimer_global_cleanup(void)
+{
+	int	cpu;
+	struct clock_event_device *ce;
+
+	if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE)
+		for_each_present_cpu(cpu) {
+			ce = per_cpu_ptr(hv_clock_event, cpu);
+			clockevents_unbind_device(ce, cpu);
+		}
+	hv_stimer_free();
+}
+EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup);
+
+/*
+ * Code and definitions for the Hyper-V clocksources.  Two
+ * clocksources are defined: one that reads the Hyper-V defined MSR, and
+ * the other that uses the TSC reference page feature as defined in the
+ * TLFS.  The MSR version is for compatibility with old versions of
+ * Hyper-V and 32-bit x86.  The TSC reference page version is preferred.
+ */
+
+struct clocksource *hyperv_cs;
+EXPORT_SYMBOL_GPL(hyperv_cs);
+
+#ifdef CONFIG_HYPERV_TSCPAGE
+
+static struct ms_hyperv_tsc_page *tsc_pg;
+
+struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
+{
+	return tsc_pg;
+}
+EXPORT_SYMBOL_GPL(hv_get_tsc_page);
+
+static u64 read_hv_sched_clock_tsc(void)
+{
+	u64 current_tick = hv_read_tsc_page(tsc_pg);
+
+	if (current_tick == U64_MAX)
+		hv_get_time_ref_count(current_tick);
+
+	return current_tick;
+}
+
+static u64 read_hv_clock_tsc(struct clocksource *arg)
+{
+	return read_hv_sched_clock_tsc();
+}
+
+static struct clocksource hyperv_cs_tsc = {
+		.name		= "hyperv_clocksource_tsc_page",
+		.rating		= 400,
+		.read		= read_hv_clock_tsc,
+		.mask		= CLOCKSOURCE_MASK(64),
+		.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
+};
+#endif
+
+static u64 read_hv_sched_clock_msr(void)
+{
+	u64 current_tick;
+	/*
+	 * Read the partition counter to get the current tick count. This count
+	 * is set to 0 when the partition is created and is incremented in
+	 * 100 nanosecond units.
+	 */
+	hv_get_time_ref_count(current_tick);
+	return current_tick;
+}
+
+static u64 read_hv_clock_msr(struct clocksource *arg)
+{
+	return read_hv_sched_clock_msr();
+}
+
+static struct clocksource hyperv_cs_msr = {
+	.name		= "hyperv_clocksource_msr",
+	.rating		= 400,
+	.read		= read_hv_clock_msr,
+	.mask		= CLOCKSOURCE_MASK(64),
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+void __init hv_init_clocksource(void)
+{
+#ifdef CONFIG_HYPERV_TSCPAGE
+	if (ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE) {
+
+		u64		tsc_msr;
+		phys_addr_t	phys_addr;
+
+		tsc_pg = vmalloc(PAGE_SIZE);
+		if (!tsc_pg)
+			goto register_msr_cs;
+
+		hyperv_cs = &hyperv_cs_tsc;
+		phys_addr = page_to_phys(vmalloc_to_page(tsc_pg));
+
+		/* The Hyper-V TLFS specifies to preserve the value of
+		 * reserved bits in registers.  So read the existing
+		 * value, preserve the low order 12 bits, and add in
+		 * the guest physical address (which already has at
+		 * least the low 12 bits set to zero since it is page
+		 * aligned). Also set the "enable" bit, which is bit 0.
+		 */
+		hv_get_reference_tsc(tsc_msr);
+		tsc_msr &= GENMASK_ULL(11, 0);
+		tsc_msr = tsc_msr | 0x1 | (u64)phys_addr;
+		hv_set_reference_tsc(tsc_msr);
+
+		hv_set_clocksource_vdso(hyperv_cs_tsc);
+		clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
+
+		/*
+		 * sched_clock_register is needed on ARM64 but
+		 * is a no-op on x86
+		 */
+		sched_clock_register(read_hv_sched_clock_tsc,
+						64, HV_CLOCK_HZ);
+		return;
+	}
+register_msr_cs:
+#endif
+	/*
+	 * For 32 bit guests just use the MSR based mechanism for reading
+	 * the partition counter.
+	 */
+	hyperv_cs = &hyperv_cs_msr;
+	if (ms_hyperv.features & HV_MSR_TIME_REF_COUNT_AVAILABLE) {
+		clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
+
+		/*
+		 * sched_clock_register is needed on ARM64 but
+		 * is a no-op on x86
+		 */
+		sched_clock_register(read_hv_sched_clock_msr,
+						64, HV_CLOCK_HZ);
+	}
+}
+EXPORT_SYMBOL_GPL(hv_init_clocksource);
diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig
index 1c1a2514d6f3..c423e57ae888 100644
--- a/drivers/hv/Kconfig
+++ b/drivers/hv/Kconfig
@@ -10,6 +10,9 @@ config HYPERV
 	  Select this option to run Linux as a Hyper-V client operating
 	  system.
 
+config HYPERV_TIMER
+	def_bool HYPERV
+
 config HYPERV_TSCPAGE
        def_bool HYPERV && X86_64
 
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index a1ea482183e8..6188fb7dda42 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -16,6 +16,7 @@
 #include <linux/version.h>
 #include <linux/random.h>
 #include <linux/clockchips.h>
+#include <clocksource/hyperv_timer.h>
 #include <asm/mshyperv.h>
 #include "hyperv_vmbus.h"
 
@@ -23,21 +24,6 @@
 struct hv_context hv_context;
 
 /*
- * If false, we're using the old mechanism for stimer0 interrupts
- * where it sends a VMbus message when it expires. The old
- * mechanism is used when running on older versions of Hyper-V
- * that don't support Direct Mode. While Hyper-V provides
- * four stimer's per CPU, Linux uses only stimer0.
- */
-static bool direct_mode_enabled;
-static int stimer0_irq;
-static int stimer0_vector;
-
-#define HV_TIMER_FREQUENCY (10 * 1000 * 1000) /* 100ns period */
-#define HV_MAX_MAX_DELTA_TICKS 0xffffffff
-#define HV_MIN_DELTA_TICKS 1
-
-/*
  * hv_init - Main initialization routine.
  *
  * This routine must be called before any other routines in here are called
@@ -47,9 +33,6 @@ int hv_init(void)
 	hv_context.cpu_context = alloc_percpu(struct hv_per_cpu_context);
 	if (!hv_context.cpu_context)
 		return -ENOMEM;
-
-	direct_mode_enabled = ms_hyperv.misc_features &
-			HV_STIMER_DIRECT_MODE_AVAILABLE;
 	return 0;
 }
 
@@ -88,89 +71,6 @@ int hv_post_message(union hv_connection_id connection_id,
 	return status & 0xFFFF;
 }
 
-/*
- * ISR for when stimer0 is operating in Direct Mode.  Direct Mode
- * does not use VMbus or any VMbus messages, so process here and not
- * in the VMbus driver code.
- */
-
-static void hv_stimer0_isr(void)
-{
-	struct hv_per_cpu_context *hv_cpu;
-
-	hv_cpu = this_cpu_ptr(hv_context.cpu_context);
-	hv_cpu->clk_evt->event_handler(hv_cpu->clk_evt);
-	add_interrupt_randomness(stimer0_vector, 0);
-}
-
-static int hv_ce_set_next_event(unsigned long delta,
-				struct clock_event_device *evt)
-{
-	u64 current_tick;
-
-	WARN_ON(!clockevent_state_oneshot(evt));
-
-	current_tick = hyperv_cs->read(NULL);
-	current_tick += delta;
-	hv_init_timer(0, current_tick);
-	return 0;
-}
-
-static int hv_ce_shutdown(struct clock_event_device *evt)
-{
-	hv_init_timer(0, 0);
-	hv_init_timer_config(0, 0);
-	if (direct_mode_enabled)
-		hv_disable_stimer0_percpu_irq(stimer0_irq);
-
-	return 0;
-}
-
-static int hv_ce_set_oneshot(struct clock_event_device *evt)
-{
-	union hv_stimer_config timer_cfg;
-
-	timer_cfg.as_uint64 = 0;
-	timer_cfg.enable = 1;
-	timer_cfg.auto_enable = 1;
-	if (direct_mode_enabled) {
-		/*
-		 * When it expires, the timer will directly interrupt
-		 * on the specified hardware vector/IRQ.
-		 */
-		timer_cfg.direct_mode = 1;
-		timer_cfg.apic_vector = stimer0_vector;
-		hv_enable_stimer0_percpu_irq(stimer0_irq);
-	} else {
-		/*
-		 * When it expires, the timer will generate a VMbus message,
-		 * to be handled by the normal VMbus interrupt handler.
-		 */
-		timer_cfg.direct_mode = 0;
-		timer_cfg.sintx = VMBUS_MESSAGE_SINT;
-	}
-	hv_init_timer_config(0, timer_cfg.as_uint64);
-	return 0;
-}
-
-static void hv_init_clockevent_device(struct clock_event_device *dev, int cpu)
-{
-	dev->name = "Hyper-V clockevent";
-	dev->features = CLOCK_EVT_FEAT_ONESHOT;
-	dev->cpumask = cpumask_of(cpu);
-	dev->rating = 1000;
-	/*
-	 * Avoid settint dev->owner = THIS_MODULE deliberately as doing so will
-	 * result in clockevents_config_and_register() taking additional
-	 * references to the hv_vmbus module making it impossible to unload.
-	 */
-
-	dev->set_state_shutdown = hv_ce_shutdown;
-	dev->set_state_oneshot = hv_ce_set_oneshot;
-	dev->set_next_event = hv_ce_set_next_event;
-}
-
-
 int hv_synic_alloc(void)
 {
 	int cpu;
@@ -199,14 +99,6 @@ int hv_synic_alloc(void)
 		tasklet_init(&hv_cpu->msg_dpc,
 			     vmbus_on_msg_dpc, (unsigned long) hv_cpu);
 
-		hv_cpu->clk_evt = kzalloc(sizeof(struct clock_event_device),
-					  GFP_KERNEL);
-		if (hv_cpu->clk_evt == NULL) {
-			pr_err("Unable to allocate clock event device\n");
-			goto err;
-		}
-		hv_init_clockevent_device(hv_cpu->clk_evt, cpu);
-
 		hv_cpu->synic_message_page =
 			(void *)get_zeroed_page(GFP_ATOMIC);
 		if (hv_cpu->synic_message_page == NULL) {
@@ -229,11 +121,6 @@ int hv_synic_alloc(void)
 		INIT_LIST_HEAD(&hv_cpu->chan_list);
 	}
 
-	if (direct_mode_enabled &&
-	    hv_setup_stimer0_irq(&stimer0_irq, &stimer0_vector,
-				hv_stimer0_isr))
-		goto err;
-
 	return 0;
 err:
 	/*
@@ -252,7 +139,6 @@ void hv_synic_free(void)
 		struct hv_per_cpu_context *hv_cpu
 			= per_cpu_ptr(hv_context.cpu_context, cpu);
 
-		kfree(hv_cpu->clk_evt);
 		free_page((unsigned long)hv_cpu->synic_event_page);
 		free_page((unsigned long)hv_cpu->synic_message_page);
 		free_page((unsigned long)hv_cpu->post_msg_page);
@@ -311,36 +197,9 @@ int hv_synic_init(unsigned int cpu)
 
 	hv_set_synic_state(sctrl.as_uint64);
 
-	/*
-	 * Register the per-cpu clockevent source.
-	 */
-	if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE)
-		clockevents_config_and_register(hv_cpu->clk_evt,
-						HV_TIMER_FREQUENCY,
-						HV_MIN_DELTA_TICKS,
-						HV_MAX_MAX_DELTA_TICKS);
-	return 0;
-}
-
-/*
- * hv_synic_clockevents_cleanup - Cleanup clockevent devices
- */
-void hv_synic_clockevents_cleanup(void)
-{
-	int cpu;
+	hv_stimer_init(cpu);
 
-	if (!(ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE))
-		return;
-
-	if (direct_mode_enabled)
-		hv_remove_stimer0_irq(stimer0_irq);
-
-	for_each_present_cpu(cpu) {
-		struct hv_per_cpu_context *hv_cpu
-			= per_cpu_ptr(hv_context.cpu_context, cpu);
-
-		clockevents_unbind_device(hv_cpu->clk_evt, cpu);
-	}
+	return 0;
 }
 
 /*
@@ -388,14 +247,7 @@ int hv_synic_cleanup(unsigned int cpu)
 	if (channel_found && vmbus_connection.conn_state == CONNECTED)
 		return -EBUSY;
 
-	/* Turn off clockevent device */
-	if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) {
-		struct hv_per_cpu_context *hv_cpu
-			= this_cpu_ptr(hv_context.cpu_context);
-
-		clockevents_unbind_device(hv_cpu->clk_evt, cpu);
-		hv_ce_shutdown(hv_cpu->clk_evt);
-	}
+	hv_stimer_cleanup(cpu);
 
 	hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
 
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 7d3d31f099ea..e32681ee7b9f 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -17,6 +17,7 @@
 #include <linux/hyperv.h>
 #include <linux/clockchips.h>
 #include <linux/ptp_clock_kernel.h>
+#include <clocksource/hyperv_timer.h>
 #include <asm/mshyperv.h>
 
 #include "hyperv_vmbus.h"
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index b8e1ff05f110..362e70e9d145 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -138,7 +138,6 @@ struct hv_per_cpu_context {
 	 * per-cpu list of the channels based on their CPU affinity.
 	 */
 	struct list_head chan_list;
-	struct clock_event_device *clk_evt;
 };
 
 struct hv_context {
@@ -176,8 +175,6 @@ extern int hv_synic_init(unsigned int cpu);
 
 extern int hv_synic_cleanup(unsigned int cpu);
 
-extern void hv_synic_clockevents_cleanup(void);
-
 /* Interface */
 
 void hv_ringbuffer_pre_init(struct vmbus_channel *channel);
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 92b1874b3eb3..894da5abdc55 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -30,6 +30,7 @@
 #include <linux/kdebug.h>
 #include <linux/efi.h>
 #include <linux/random.h>
+#include <clocksource/hyperv_timer.h>
 #include "hyperv_vmbus.h"
 
 struct vmbus_dynid {
@@ -955,17 +956,6 @@ static void vmbus_onmessage_work(struct work_struct *work)
 	kfree(ctx);
 }
 
-static void hv_process_timer_expiration(struct hv_message *msg,
-					struct hv_per_cpu_context *hv_cpu)
-{
-	struct clock_event_device *dev = hv_cpu->clk_evt;
-
-	if (dev->event_handler)
-		dev->event_handler(dev);
-
-	vmbus_signal_eom(msg, HVMSG_TIMER_EXPIRED);
-}
-
 void vmbus_on_msg_dpc(unsigned long data)
 {
 	struct hv_per_cpu_context *hv_cpu = (void *)data;
@@ -1159,9 +1149,10 @@ static void vmbus_isr(void)
 
 	/* Check if there are actual msgs to be processed */
 	if (msg->header.message_type != HVMSG_NONE) {
-		if (msg->header.message_type == HVMSG_TIMER_EXPIRED)
-			hv_process_timer_expiration(msg, hv_cpu);
-		else
+		if (msg->header.message_type == HVMSG_TIMER_EXPIRED) {
+			hv_stimer0_isr();
+			vmbus_signal_eom(msg, HVMSG_TIMER_EXPIRED);
+		} else
 			tasklet_schedule(&hv_cpu->msg_dpc);
 	}
 
@@ -1263,14 +1254,19 @@ static int vmbus_bus_init(void)
 	ret = hv_synic_alloc();
 	if (ret)
 		goto err_alloc;
+
+	ret = hv_stimer_alloc(VMBUS_MESSAGE_SINT);
+	if (ret < 0)
+		goto err_alloc;
+
 	/*
-	 * Initialize the per-cpu interrupt state and
-	 * connect to the host.
+	 * Initialize the per-cpu interrupt state and stimer state.
+	 * Then connect to the host.
 	 */
 	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "hyperv/vmbus:online",
 				hv_synic_init, hv_synic_cleanup);
 	if (ret < 0)
-		goto err_alloc;
+		goto err_cpuhp;
 	hyperv_cpuhp_online = ret;
 
 	ret = vmbus_connect();
@@ -1318,6 +1314,8 @@ static int vmbus_bus_init(void)
 
 err_connect:
 	cpuhp_remove_state(hyperv_cpuhp_online);
+err_cpuhp:
+	hv_stimer_free();
 err_alloc:
 	hv_synic_free();
 	hv_remove_vmbus_irq();
@@ -2064,7 +2062,7 @@ static struct acpi_driver vmbus_acpi_driver = {
 
 static void hv_kexec_handler(void)
 {
-	hv_synic_clockevents_cleanup();
+	hv_stimer_global_cleanup();
 	vmbus_initiate_unload(false);
 	vmbus_connection.conn_state = DISCONNECTED;
 	/* Make sure conn_state is set as hv_synic_cleanup checks for it */
@@ -2075,6 +2073,8 @@ static void hv_kexec_handler(void)
 
 static void hv_crash_handler(struct pt_regs *regs)
 {
+	int cpu;
+
 	vmbus_initiate_unload(true);
 	/*
 	 * In crash handler we can't schedule synic cleanup for all CPUs,
@@ -2082,7 +2082,9 @@ static void hv_crash_handler(struct pt_regs *regs)
 	 * for kdump.
 	 */
 	vmbus_connection.conn_state = DISCONNECTED;
-	hv_synic_cleanup(smp_processor_id());
+	cpu = smp_processor_id();
+	hv_stimer_cleanup(cpu);
+	hv_synic_cleanup(cpu);
 	hyperv_cleanup();
 };
 
@@ -2131,7 +2133,7 @@ static void __exit vmbus_exit(void)
 	hv_remove_kexec_handler();
 	hv_remove_crash_handler();
 	vmbus_connection.conn_state = DISCONNECTED;
-	hv_synic_clockevents_cleanup();
+	hv_stimer_global_cleanup();
 	vmbus_disconnect();
 	hv_remove_vmbus_irq();
 	for_each_online_cpu(cpu) {
@@ -2161,6 +2163,7 @@ static void __exit vmbus_exit(void)
 
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Microsoft Hyper-V VMBus Driver");
 
 subsys_initcall(hv_acpi_init);
 module_exit(vmbus_exit);
diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
new file mode 100644
index 000000000000..0becb7d9704d
--- /dev/null
+++ b/include/asm-generic/mshyperv.h
@@ -0,0 +1,180 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Linux-specific definitions for managing interactions with Microsoft's
+ * Hyper-V hypervisor. The definitions in this file are architecture
+ * independent. See arch/<arch>/include/asm/mshyperv.h for definitions
+ * that are specific to architecture <arch>.
+ *
+ * Definitions that are specified in the Hyper-V Top Level Functional
+ * Spec (TLFS) should not go in this file, but should instead go in
+ * hyperv-tlfs.h.
+ *
+ * Copyright (C) 2019, Microsoft, Inc.
+ *
+ * Author : Michael Kelley <mikelley@microsoft.com>
+ */
+
+#ifndef _ASM_GENERIC_MSHYPERV_H
+#define _ASM_GENERIC_MSHYPERV_H
+
+#include <linux/types.h>
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/cpumask.h>
+#include <asm/ptrace.h>
+#include <asm/hyperv-tlfs.h>
+
+struct ms_hyperv_info {
+	u32 features;
+	u32 misc_features;
+	u32 hints;
+	u32 nested_features;
+	u32 max_vp_index;
+	u32 max_lp_index;
+};
+extern struct ms_hyperv_info ms_hyperv;
+
+extern u64 hv_do_hypercall(u64 control, void *inputaddr, void *outputaddr);
+extern u64 hv_do_fast_hypercall8(u16 control, u64 input8);
+
+
+/* Generate the guest OS identifier as described in the Hyper-V TLFS */
+static inline  __u64 generate_guest_id(__u64 d_info1, __u64 kernel_version,
+				       __u64 d_info2)
+{
+	__u64 guest_id = 0;
+
+	guest_id = (((__u64)HV_LINUX_VENDOR_ID) << 48);
+	guest_id |= (d_info1 << 48);
+	guest_id |= (kernel_version << 16);
+	guest_id |= d_info2;
+
+	return guest_id;
+}
+
+
+/* Free the message slot and signal end-of-message if required */
+static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
+{
+	/*
+	 * On crash we're reading some other CPU's message page and we need
+	 * to be careful: this other CPU may already had cleared the header
+	 * and the host may already had delivered some other message there.
+	 * In case we blindly write msg->header.message_type we're going
+	 * to lose it. We can still lose a message of the same type but
+	 * we count on the fact that there can only be one
+	 * CHANNELMSG_UNLOAD_RESPONSE and we don't care about other messages
+	 * on crash.
+	 */
+	if (cmpxchg(&msg->header.message_type, old_msg_type,
+		    HVMSG_NONE) != old_msg_type)
+		return;
+
+	/*
+	 * The cmxchg() above does an implicit memory barrier to
+	 * ensure the write to MessageType (ie set to
+	 * HVMSG_NONE) happens before we read the
+	 * MessagePending and EOMing. Otherwise, the EOMing
+	 * will not deliver any more messages since there is
+	 * no empty slot
+	 */
+	if (msg->header.message_flags.msg_pending) {
+		/*
+		 * This will cause message queue rescan to
+		 * possibly deliver another msg from the
+		 * hypervisor
+		 */
+		hv_signal_eom();
+	}
+}
+
+void hv_setup_vmbus_irq(void (*handler)(void));
+void hv_remove_vmbus_irq(void);
+void hv_enable_vmbus_irq(void);
+void hv_disable_vmbus_irq(void);
+
+void hv_setup_kexec_handler(void (*handler)(void));
+void hv_remove_kexec_handler(void);
+void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs));
+void hv_remove_crash_handler(void);
+
+#if IS_ENABLED(CONFIG_HYPERV)
+/*
+ * Hypervisor's notion of virtual processor ID is different from
+ * Linux' notion of CPU ID. This information can only be retrieved
+ * in the context of the calling CPU. Setup a map for easy access
+ * to this information.
+ */
+extern u32 *hv_vp_index;
+extern u32 hv_max_vp_index;
+
+/* Sentinel value for an uninitialized entry in hv_vp_index array */
+#define VP_INVAL	U32_MAX
+
+/**
+ * hv_cpu_number_to_vp_number() - Map CPU to VP.
+ * @cpu_number: CPU number in Linux terms
+ *
+ * This function returns the mapping between the Linux processor
+ * number and the hypervisor's virtual processor number, useful
+ * in making hypercalls and such that talk about specific
+ * processors.
+ *
+ * Return: Virtual processor number in Hyper-V terms
+ */
+static inline int hv_cpu_number_to_vp_number(int cpu_number)
+{
+	return hv_vp_index[cpu_number];
+}
+
+static inline int cpumask_to_vpset(struct hv_vpset *vpset,
+				    const struct cpumask *cpus)
+{
+	int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1;
+
+	/* valid_bank_mask can represent up to 64 banks */
+	if (hv_max_vp_index / 64 >= 64)
+		return 0;
+
+	/*
+	 * Clear all banks up to the maximum possible bank as hv_tlb_flush_ex
+	 * structs are not cleared between calls, we risk flushing unneeded
+	 * vCPUs otherwise.
+	 */
+	for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++)
+		vpset->bank_contents[vcpu_bank] = 0;
+
+	/*
+	 * Some banks may end up being empty but this is acceptable.
+	 */
+	for_each_cpu(cpu, cpus) {
+		vcpu = hv_cpu_number_to_vp_number(cpu);
+		if (vcpu == VP_INVAL)
+			return -1;
+		vcpu_bank = vcpu / 64;
+		vcpu_offset = vcpu % 64;
+		__set_bit(vcpu_offset, (unsigned long *)
+			  &vpset->bank_contents[vcpu_bank]);
+		if (vcpu_bank >= nr_bank)
+			nr_bank = vcpu_bank + 1;
+	}
+	vpset->valid_bank_mask = GENMASK_ULL(nr_bank - 1, 0);
+	return nr_bank;
+}
+
+void hyperv_report_panic(struct pt_regs *regs, long err);
+void hyperv_report_panic_msg(phys_addr_t pa, size_t size);
+bool hv_is_hyperv_initialized(void);
+void hyperv_cleanup(void);
+#else /* CONFIG_HYPERV */
+static inline bool hv_is_hyperv_initialized(void) { return false; }
+static inline void hyperv_cleanup(void) {}
+#endif /* CONFIG_HYPERV */
+
+#if IS_ENABLED(CONFIG_HYPERV)
+extern int hv_setup_stimer0_irq(int *irq, int *vector, void (*handler)(void));
+extern void hv_remove_stimer0_irq(int irq);
+#endif
+
+#endif
diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h
new file mode 100644
index 000000000000..e17e8a26d612
--- /dev/null
+++ b/include/clocksource/hyperv_timer.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Definitions for the clocksource provided by the Hyper-V
+ * hypervisor to guest VMs, as described in the Hyper-V Top
+ * Level Functional Spec (TLFS).
+ *
+ * Copyright (C) 2019, Microsoft, Inc.
+ *
+ * Author:  Michael Kelley <mikelley@microsoft.com>
+ */
+
+#ifndef __CLKSOURCE_HYPERV_TIMER_H
+#define __CLKSOURCE_HYPERV_TIMER_H
+
+#include <linux/clocksource.h>
+#include <linux/math64.h>
+#include <asm/mshyperv.h>
+
+#define HV_MAX_MAX_DELTA_TICKS 0xffffffff
+#define HV_MIN_DELTA_TICKS 1
+
+/* Routines called by the VMbus driver */
+extern int hv_stimer_alloc(int sint);
+extern void hv_stimer_free(void);
+extern int hv_stimer_init(unsigned int cpu);
+extern int hv_stimer_cleanup(unsigned int cpu);
+extern void hv_stimer_global_cleanup(void);
+extern void hv_stimer0_isr(void);
+
+#if IS_ENABLED(CONFIG_HYPERV)
+extern struct clocksource *hyperv_cs;
+extern void hv_init_clocksource(void);
+#endif /* CONFIG_HYPERV */
+
+#ifdef CONFIG_HYPERV_TSCPAGE
+extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
+static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
+				       u64 *cur_tsc)
+{
+	u64 scale, offset;
+	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 = hv_get_raw_timer();
+
+		/*
+		 * 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;
+}
+
+static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
+{
+	u64 cur_tsc;
+
+	return hv_read_tsc_page_tsc(tsc_pg, &cur_tsc);
+}
+
+#else /* CONFIG_HYPERV_TSC_PAGE */
+static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
+{
+	return NULL;
+}
+
+static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
+				       u64 *cur_tsc)
+{
+	return U64_MAX;
+}
+#endif /* CONFIG_HYPERV_TSCPAGE */
+
+#endif