hyperv-next for 5.13

-----BEGIN PGP SIGNATURE-----
 
 iQFHBAABCAAxFiEEIbPD0id6easf0xsudhRwX5BBoF4FAmCG9+oTHHdlaS5saXVA
 a2VybmVsLm9yZwAKCRB2FHBfkEGgXqo5CACQrfupoIeawVUMZQOGPOKW56zcmo+l
 kwgEYdukleYebJzES3zxdAod2k45WnAJ3aMQJaL2DxZ5SZdTJG1zIK08wlP87ui8
 m80Htq/8c3fBM90gjUSjShxHw9SaWwwSQUVBKrm0doS7o0iUq0PPHHE6gvJHMX/w
 IcHug294c6ArCz0qNR5aiBxPNGixXBX7S7/5ubdjxszU2BVAzrfFLWYOWU4HzHyN
 g68BDY6F2K9+F3XOVO0zhcCdhzvIzb5Bh0V06VBKl9HRWnk28h0/Y7fBq9HVzCZu
 k7k5+o6lJUyyFkXR8MlcBKRlWnFXSHc5wIdJ/gcXTzEMsqrJlQ1vrGog
 =pGet
 -----END PGP SIGNATURE-----

Merge tag 'hyperv-next-signed-20210426' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull Hyper-V updates from Wei Liu:

 - VMBus enhancement

 - Free page reporting support for Hyper-V balloon driver

 - Some patches for running Linux as Arm64 Hyper-V guest

 - A few misc clean-up patches

* tag 'hyperv-next-signed-20210426' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux: (30 commits)
  drivers: hv: Create a consistent pattern for checking Hyper-V hypercall status
  x86/hyperv: Move hv_do_rep_hypercall to asm-generic
  video: hyperv_fb: Add ratelimit on error message
  Drivers: hv: vmbus: Increase wait time for VMbus unload
  Drivers: hv: vmbus: Initialize unload_event statically
  Drivers: hv: vmbus: Check for pending channel interrupts before taking a CPU offline
  Drivers: hv: vmbus: Drivers: hv: vmbus: Introduce CHANNELMSG_MODIFYCHANNEL_RESPONSE
  Drivers: hv: vmbus: Introduce and negotiate VMBus protocol version 5.3
  Drivers: hv: vmbus: Use after free in __vmbus_open()
  Drivers: hv: vmbus: remove unused function
  Drivers: hv: vmbus: Remove unused linux/version.h header
  x86/hyperv: remove unused linux/version.h header
  x86/Hyper-V: Support for free page reporting
  x86/hyperv: Fix unused variable 'hi' warning in hv_apic_read
  x86/hyperv: Fix unused variable 'msr_val' warning in hv_qlock_wait
  hv: hyperv.h: a few mundane typo fixes
  drivers: hv: Fix EXPORT_SYMBOL and tab spaces issue
  Drivers: hv: vmbus: Drop error message when 'No request id available'
  asm-generic/hyperv: Add missing function prototypes per -W1 warnings
  clocksource/drivers/hyper-v: Move handling of STIMER0 interrupts
  ...

arch/x86/hyperv/hv_apic.c

@@ -60,9 +60,11 @@ static u32 hv_apic_read(u32 reg)
 	switch (reg) {
 	case APIC_EOI:
 		rdmsr(HV_X64_MSR_EOI, reg_val, hi);
+		(void)hi;
 		return reg_val;
 	case APIC_TASKPRI:
 		rdmsr(HV_X64_MSR_TPR, reg_val, hi);
+		(void)hi;
 		return reg_val;
 
 	default:
@@ -103,7 +105,7 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
 	struct hv_send_ipi_ex *ipi_arg;
 	unsigned long flags;
 	int nr_bank = 0;
-	int ret = 1;
+	u64 status = HV_STATUS_INVALID_PARAMETER;
 
 	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
 		return false;
@@ -128,19 +130,19 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
 	if (!nr_bank)
 		ipi_arg->vp_set.format = HV_GENERIC_SET_ALL;
 
-	ret = hv_do_rep_hypercall(HVCALL_SEND_IPI_EX, 0, nr_bank,
+	status = hv_do_rep_hypercall(HVCALL_SEND_IPI_EX, 0, nr_bank,
 			      ipi_arg, NULL);
 
 ipi_mask_ex_done:
 	local_irq_restore(flags);
-	return ((ret == 0) ? true : false);
+	return hv_result_success(status);
 }
 
 static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 {
 	int cur_cpu, vcpu;
 	struct hv_send_ipi ipi_arg;
-	int ret = 1;
+	u64 status;
 
 	trace_hyperv_send_ipi_mask(mask, vector);
 
@@ -184,9 +186,9 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 		__set_bit(vcpu, (unsigned long *)&ipi_arg.cpu_mask);
 	}
 
-	ret = hv_do_fast_hypercall16(HVCALL_SEND_IPI, ipi_arg.vector,
+	status = hv_do_fast_hypercall16(HVCALL_SEND_IPI, ipi_arg.vector,
 				     ipi_arg.cpu_mask);
-	return ((ret == 0) ? true : false);
+	return hv_result_success(status);
 
 do_ex_hypercall:
 	return __send_ipi_mask_ex(mask, vector);
@@ -195,6 +197,7 @@ do_ex_hypercall:
 static bool __send_ipi_one(int cpu, int vector)
 {
 	int vp = hv_cpu_number_to_vp_number(cpu);
+	u64 status;
 
 	trace_hyperv_send_ipi_one(cpu, vector);
 
@@ -207,7 +210,8 @@ static bool __send_ipi_one(int cpu, int vector)
 	if (vp >= 64)
 		return __send_ipi_mask_ex(cpumask_of(cpu), vector);
 
-	return !hv_do_fast_hypercall16(HVCALL_SEND_IPI, vector, BIT_ULL(vp));
+	status = hv_do_fast_hypercall16(HVCALL_SEND_IPI, vector, BIT_ULL(vp));
+	return hv_result_success(status);
 }
 
 static void hv_send_ipi(int cpu, int vector)

arch/x86/hyperv/hv_init.c

@@ -54,28 +54,6 @@ EXPORT_SYMBOL_GPL(hyperv_pcpu_output_arg);
 u32 hv_max_vp_index;
 EXPORT_SYMBOL_GPL(hv_max_vp_index);
 
-void *hv_alloc_hyperv_page(void)
-{
-	BUILD_BUG_ON(PAGE_SIZE != HV_HYP_PAGE_SIZE);
-
-	return (void *)__get_free_page(GFP_KERNEL);
-}
-EXPORT_SYMBOL_GPL(hv_alloc_hyperv_page);
-
-void *hv_alloc_hyperv_zeroed_page(void)
-{
-        BUILD_BUG_ON(PAGE_SIZE != HV_HYP_PAGE_SIZE);
-
-        return (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
-}
-EXPORT_SYMBOL_GPL(hv_alloc_hyperv_zeroed_page);
-
-void hv_free_hyperv_page(unsigned long addr)
-{
-	free_page(addr);
-}
-EXPORT_SYMBOL_GPL(hv_free_hyperv_page);
-
 static int hv_cpu_init(unsigned int cpu)
 {
 	u64 msr_vp_index;
@@ -97,7 +75,7 @@ static int hv_cpu_init(unsigned int cpu)
 		*output_arg = page_address(pg + 1);
 	}
 
-	hv_get_vp_index(msr_vp_index);
+	msr_vp_index = hv_get_register(HV_REGISTER_VP_INDEX);
 
 	hv_vp_index[smp_processor_id()] = msr_vp_index;
 
@@ -349,7 +327,7 @@ static void __init hv_stimer_setup_percpu_clockev(void)
 	 * Ignore any errors in setting up stimer clockevents
 	 * as we can run with the LAPIC timer as a fallback.
 	 */
-	(void)hv_stimer_alloc();
+	(void)hv_stimer_alloc(false);
 
 	/*
 	 * Still register the LAPIC timer, because the direct-mode STIMER is
@@ -369,7 +347,7 @@ static void __init hv_get_partition_id(void)
 	local_irq_save(flags);
 	output_page = *this_cpu_ptr(hyperv_pcpu_output_arg);
 	status = hv_do_hypercall(HVCALL_GET_PARTITION_ID, NULL, output_page);
-	if ((status & HV_HYPERCALL_RESULT_MASK) != HV_STATUS_SUCCESS) {
+	if (!hv_result_success(status)) {
 		/* No point in proceeding if this failed */
 		pr_err("Failed to get partition ID: %lld\n", status);
 		BUG();
@@ -520,6 +498,8 @@ void __init hyperv_init(void)
 		x86_init.irqs.create_pci_msi_domain = hv_create_pci_msi_domain;
 #endif
 
+	/* Query the VMs extended capability once, so that it can be cached. */
+	hv_query_ext_cap(0);
 	return;
 
 remove_cpuhp_state:
@@ -593,33 +573,6 @@ void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die)
 }
 EXPORT_SYMBOL_GPL(hyperv_report_panic);
 
-/**
- * hyperv_report_panic_msg - report panic message to Hyper-V
- * @pa: physical address of the panic page containing the message
- * @size: size of the message in the page
- */
-void hyperv_report_panic_msg(phys_addr_t pa, size_t size)
-{
-	/*
-	 * P3 to contain the physical address of the panic page & P4 to
-	 * contain the size of the panic data in that page. Rest of the
-	 * registers are no-op when the NOTIFY_MSG flag is set.
-	 */
-	wrmsrl(HV_X64_MSR_CRASH_P0, 0);
-	wrmsrl(HV_X64_MSR_CRASH_P1, 0);
-	wrmsrl(HV_X64_MSR_CRASH_P2, 0);
-	wrmsrl(HV_X64_MSR_CRASH_P3, pa);
-	wrmsrl(HV_X64_MSR_CRASH_P4, size);
-
-	/*
-	 * Let Hyper-V know there is crash data available along with
-	 * the panic message.
-	 */
-	wrmsrl(HV_X64_MSR_CRASH_CTL,
-	       (HV_CRASH_CTL_CRASH_NOTIFY | HV_CRASH_CTL_CRASH_NOTIFY_MSG));
-}
-EXPORT_SYMBOL_GPL(hyperv_report_panic_msg);
-
 bool hv_is_hyperv_initialized(void)
 {
 	union hv_x64_msr_hypercall_contents hypercall_msr;
@@ -650,7 +603,7 @@ EXPORT_SYMBOL_GPL(hv_is_hibernation_supported);
 
 enum hv_isolation_type hv_get_isolation_type(void)
 {
-	if (!(ms_hyperv.features_b & HV_ISOLATION))
+	if (!(ms_hyperv.priv_high & HV_ISOLATION))
 		return HV_ISOLATION_TYPE_NONE;
 	return FIELD_GET(HV_ISOLATION_TYPE, ms_hyperv.isolation_config_b);
 }
@@ -661,3 +614,50 @@ bool hv_is_isolation_supported(void)
 	return hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE;
 }
 EXPORT_SYMBOL_GPL(hv_is_isolation_supported);
+
+/* Bit mask of the extended capability to query: see HV_EXT_CAPABILITY_xxx */
+bool hv_query_ext_cap(u64 cap_query)
+{
+	/*
+	 * The address of the 'hv_extended_cap' variable will be used as an
+	 * output parameter to the hypercall below and so it should be
+	 * compatible with 'virt_to_phys'. Which means, it's address should be
+	 * directly mapped. Use 'static' to keep it compatible; stack variables
+	 * can be virtually mapped, making them imcompatible with
+	 * 'virt_to_phys'.
+	 * Hypercall input/output addresses should also be 8-byte aligned.
+	 */
+	static u64 hv_extended_cap __aligned(8);
+	static bool hv_extended_cap_queried;
+	u64 status;
+
+	/*
+	 * Querying extended capabilities is an extended hypercall. Check if the
+	 * partition supports extended hypercall, first.
+	 */
+	if (!(ms_hyperv.priv_high & HV_ENABLE_EXTENDED_HYPERCALLS))
+		return false;
+
+	/* Extended capabilities do not change at runtime. */
+	if (hv_extended_cap_queried)
+		return hv_extended_cap & cap_query;
+
+	status = hv_do_hypercall(HV_EXT_CALL_QUERY_CAPABILITIES, NULL,
+				 &hv_extended_cap);
+
+	/*
+	 * The query extended capabilities hypercall should not fail under
+	 * any normal circumstances. Avoid repeatedly making the hypercall, on
+	 * error.
+	 */
+	hv_extended_cap_queried = true;
+	status &= HV_HYPERCALL_RESULT_MASK;
+	if (status != HV_STATUS_SUCCESS) {
+		pr_err("Hyper-V: Extended query capabilities hypercall failed 0x%llx\n",
+		       status);
+		return false;
+	}
+
+	return hv_extended_cap & cap_query;
+}
+EXPORT_SYMBOL_GPL(hv_query_ext_cap);

arch/x86/hyperv/hv_proc.c

@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
-#include <linux/version.h>
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
 #include <linux/clockchips.h>
@@ -93,10 +92,9 @@ int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages)
 	status = hv_do_rep_hypercall(HVCALL_DEPOSIT_MEMORY,
 				     page_count, 0, input_page, NULL);
 	local_irq_restore(flags);
-
+	if (!hv_result_success(status)) {
-	if ((status & HV_HYPERCALL_RESULT_MASK) != HV_STATUS_SUCCESS) {
 		pr_err("Failed to deposit pages: %lld\n", status);
-		ret = status;
+		ret = hv_result(status);
 		goto err_free_allocations;
 	}
 
@@ -122,7 +120,7 @@ int hv_call_add_logical_proc(int node, u32 lp_index, u32 apic_id)
 	struct hv_add_logical_processor_out *output;
 	u64 status;
 	unsigned long flags;
-	int ret = 0;
+	int ret = HV_STATUS_SUCCESS;
 	int pxm = node_to_pxm(node);
 
 	/*
@@ -148,13 +146,11 @@ int hv_call_add_logical_proc(int node, u32 lp_index, u32 apic_id)
 					 input, output);
 		local_irq_restore(flags);
 
-		status &= HV_HYPERCALL_RESULT_MASK;
+		if (hv_result(status) != HV_STATUS_INSUFFICIENT_MEMORY) {
-
+			if (!hv_result_success(status)) {
-		if (status != HV_STATUS_INSUFFICIENT_MEMORY) {
-			if (status != HV_STATUS_SUCCESS) {
 				pr_err("%s: cpu %u apic ID %u, %lld\n", __func__,
 				       lp_index, apic_id, status);
-				ret = status;
+				ret = hv_result(status);
 			}
 			break;
 		}
@@ -169,7 +165,7 @@ int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags)
 	struct hv_create_vp *input;
 	u64 status;
 	unsigned long irq_flags;
-	int ret = 0;
+	int ret = HV_STATUS_SUCCESS;
 	int pxm = node_to_pxm(node);
 
 	/* Root VPs don't seem to need pages deposited */
@@ -200,13 +196,11 @@ int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags)
 		status = hv_do_hypercall(HVCALL_CREATE_VP, input, NULL);
 		local_irq_restore(irq_flags);
 
-		status &= HV_HYPERCALL_RESULT_MASK;
+		if (hv_result(status) != HV_STATUS_INSUFFICIENT_MEMORY) {
-
+			if (!hv_result_success(status)) {
-		if (status != HV_STATUS_INSUFFICIENT_MEMORY) {
-			if (status != HV_STATUS_SUCCESS) {
 				pr_err("%s: vcpu %u, lp %u, %lld\n", __func__,
 				       vp_index, flags, status);
-				ret = status;
+				ret = hv_result(status);
 			}
 			break;
 		}

arch/x86/hyperv/hv_spinlock.c

@@ -25,7 +25,6 @@ static void hv_qlock_kick(int cpu)
 
 static void hv_qlock_wait(u8 *byte, u8 val)
 {
-	unsigned long msr_val;
 	unsigned long flags;
 
 	if (in_nmi())
@@ -48,8 +47,13 @@ static void hv_qlock_wait(u8 *byte, u8 val)
 	/*
 	 * Only issue the rdmsrl() when the lock state has not changed.
 	 */
-	if (READ_ONCE(*byte) == val)
+	if (READ_ONCE(*byte) == val) {
+		unsigned long msr_val;
+
 		rdmsrl(HV_X64_MSR_GUEST_IDLE, msr_val);
+
+		(void)msr_val;
+	}
 	local_irq_restore(flags);
 }
 

arch/x86/hyperv/irqdomain.c

@@ -63,10 +63,10 @@ static int hv_map_interrupt(union hv_device_id device_id, bool level,
 
 	local_irq_restore(flags);
 
-	if ((status & HV_HYPERCALL_RESULT_MASK) != HV_STATUS_SUCCESS)
+	if (!hv_result_success(status))
 		pr_err("%s: hypercall failed, status %lld\n", __func__, status);
 
-	return status & HV_HYPERCALL_RESULT_MASK;
+	return hv_result(status);
 }
 
 static int hv_unmap_interrupt(u64 id, struct hv_interrupt_entry *old_entry)
@@ -88,7 +88,7 @@ static int hv_unmap_interrupt(u64 id, struct hv_interrupt_entry *old_entry)
 	status = hv_do_hypercall(HVCALL_UNMAP_DEVICE_INTERRUPT, input, NULL);
 	local_irq_restore(flags);
 
-	return status & HV_HYPERCALL_RESULT_MASK;
+	return hv_result(status);
 }
 
 #ifdef CONFIG_PCI_MSI

arch/x86/hyperv/mmu.c

@@ -58,7 +58,7 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 	int cpu, vcpu, gva_n, max_gvas;
 	struct hv_tlb_flush **flush_pcpu;
 	struct hv_tlb_flush *flush;
-	u64 status = U64_MAX;
+	u64 status;
 	unsigned long flags;
 
 	trace_hyperv_mmu_flush_tlb_others(cpus, info);
@@ -161,7 +161,7 @@ do_ex_hypercall:
 check_status:
 	local_irq_restore(flags);
 
-	if (!(status & HV_HYPERCALL_RESULT_MASK))
+	if (hv_result_success(status))
 		return;
 do_native:
 	native_flush_tlb_others(cpus, info);
@@ -176,7 +176,7 @@ static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 	u64 status;
 
 	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
-		return U64_MAX;
+		return HV_STATUS_INVALID_PARAMETER;
 
 	flush_pcpu = (struct hv_tlb_flush_ex **)
 		     this_cpu_ptr(hyperv_pcpu_input_arg);
@@ -201,7 +201,7 @@ static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 	flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
 	nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus);
 	if (nr_bank < 0)
-		return U64_MAX;
+		return HV_STATUS_INVALID_PARAMETER;
 
 	/*
 	 * We can flush not more than max_gvas with one hypercall. Flush the

arch/x86/hyperv/nested.c

@@ -47,7 +47,7 @@ int hyperv_flush_guest_mapping(u64 as)
 				 flush, NULL);
 	local_irq_restore(flags);
 
-	if (!(status & HV_HYPERCALL_RESULT_MASK))
+	if (hv_result_success(status))
 		ret = 0;
 
 fault:
@@ -92,7 +92,7 @@ int hyperv_flush_guest_mapping_range(u64 as,
 {
 	struct hv_guest_mapping_flush_list **flush_pcpu;
 	struct hv_guest_mapping_flush_list *flush;
-	u64 status = 0;
+	u64 status;
 	unsigned long flags;
 	int ret = -ENOTSUPP;
 	int gpa_n = 0;
@@ -125,10 +125,10 @@ int hyperv_flush_guest_mapping_range(u64 as,
 
 	local_irq_restore(flags);
 
-	if (!(status & HV_HYPERCALL_RESULT_MASK))
+	if (hv_result_success(status))
 		ret = 0;
 	else
-		ret = status;
+		ret = hv_result(status);
 fault:
 	trace_hyperv_nested_flush_guest_mapping_range(as, ret);
 	return ret;

arch/x86/include/asm/hyperv-tlfs.h

@@ -156,7 +156,7 @@ enum hv_isolation_type {
 #define HV_X64_MSR_HYPERCALL			0x40000001
 
 /* MSR used to provide vcpu index */
-#define HV_X64_MSR_VP_INDEX			0x40000002
+#define HV_REGISTER_VP_INDEX			0x40000002
 
 /* MSR used to reset the guest OS. */
 #define HV_X64_MSR_RESET			0x40000003
@@ -165,10 +165,10 @@ enum hv_isolation_type {
 #define HV_X64_MSR_VP_RUNTIME			0x40000010
 
 /* MSR used to read the per-partition time reference counter */
-#define HV_X64_MSR_TIME_REF_COUNT		0x40000020
+#define HV_REGISTER_TIME_REF_COUNT		0x40000020
 
 /* A partition's reference time stamp counter (TSC) page */
-#define HV_X64_MSR_REFERENCE_TSC		0x40000021
+#define HV_REGISTER_REFERENCE_TSC		0x40000021
 
 /* MSR used to retrieve the TSC frequency */
 #define HV_X64_MSR_TSC_FREQUENCY		0x40000022
@@ -183,50 +183,50 @@ enum hv_isolation_type {
 #define HV_X64_MSR_VP_ASSIST_PAGE		0x40000073
 
 /* Define synthetic interrupt controller model specific registers. */
-#define HV_X64_MSR_SCONTROL			0x40000080
+#define HV_REGISTER_SCONTROL			0x40000080
-#define HV_X64_MSR_SVERSION			0x40000081
+#define HV_REGISTER_SVERSION			0x40000081
-#define HV_X64_MSR_SIEFP			0x40000082
+#define HV_REGISTER_SIEFP			0x40000082
-#define HV_X64_MSR_SIMP				0x40000083
+#define HV_REGISTER_SIMP			0x40000083
-#define HV_X64_MSR_EOM				0x40000084
+#define HV_REGISTER_EOM				0x40000084
-#define HV_X64_MSR_SINT0			0x40000090
+#define HV_REGISTER_SINT0			0x40000090
-#define HV_X64_MSR_SINT1			0x40000091
+#define HV_REGISTER_SINT1			0x40000091
-#define HV_X64_MSR_SINT2			0x40000092
+#define HV_REGISTER_SINT2			0x40000092
-#define HV_X64_MSR_SINT3			0x40000093
+#define HV_REGISTER_SINT3			0x40000093
-#define HV_X64_MSR_SINT4			0x40000094
+#define HV_REGISTER_SINT4			0x40000094
-#define HV_X64_MSR_SINT5			0x40000095
+#define HV_REGISTER_SINT5			0x40000095
-#define HV_X64_MSR_SINT6			0x40000096
+#define HV_REGISTER_SINT6			0x40000096
-#define HV_X64_MSR_SINT7			0x40000097
+#define HV_REGISTER_SINT7			0x40000097
-#define HV_X64_MSR_SINT8			0x40000098
+#define HV_REGISTER_SINT8			0x40000098
-#define HV_X64_MSR_SINT9			0x40000099
+#define HV_REGISTER_SINT9			0x40000099
-#define HV_X64_MSR_SINT10			0x4000009A
+#define HV_REGISTER_SINT10			0x4000009A
-#define HV_X64_MSR_SINT11			0x4000009B
+#define HV_REGISTER_SINT11			0x4000009B
-#define HV_X64_MSR_SINT12			0x4000009C
+#define HV_REGISTER_SINT12			0x4000009C
-#define HV_X64_MSR_SINT13			0x4000009D
+#define HV_REGISTER_SINT13			0x4000009D
-#define HV_X64_MSR_SINT14			0x4000009E
+#define HV_REGISTER_SINT14			0x4000009E
-#define HV_X64_MSR_SINT15			0x4000009F
+#define HV_REGISTER_SINT15			0x4000009F
 
 /*
  * Synthetic Timer MSRs. Four timers per vcpu.
  */
-#define HV_X64_MSR_STIMER0_CONFIG		0x400000B0
+#define HV_REGISTER_STIMER0_CONFIG		0x400000B0
-#define HV_X64_MSR_STIMER0_COUNT		0x400000B1
+#define HV_REGISTER_STIMER0_COUNT		0x400000B1
-#define HV_X64_MSR_STIMER1_CONFIG		0x400000B2
+#define HV_REGISTER_STIMER1_CONFIG		0x400000B2
-#define HV_X64_MSR_STIMER1_COUNT		0x400000B3
+#define HV_REGISTER_STIMER1_COUNT		0x400000B3
-#define HV_X64_MSR_STIMER2_CONFIG		0x400000B4
+#define HV_REGISTER_STIMER2_CONFIG		0x400000B4
-#define HV_X64_MSR_STIMER2_COUNT		0x400000B5
+#define HV_REGISTER_STIMER2_COUNT		0x400000B5
-#define HV_X64_MSR_STIMER3_CONFIG		0x400000B6
+#define HV_REGISTER_STIMER3_CONFIG		0x400000B6
-#define HV_X64_MSR_STIMER3_COUNT		0x400000B7
+#define HV_REGISTER_STIMER3_COUNT		0x400000B7
 
 /* Hyper-V guest idle MSR */
 #define HV_X64_MSR_GUEST_IDLE			0x400000F0
 
 /* Hyper-V guest crash notification MSR's */
-#define HV_X64_MSR_CRASH_P0			0x40000100
+#define HV_REGISTER_CRASH_P0			0x40000100
-#define HV_X64_MSR_CRASH_P1			0x40000101
+#define HV_REGISTER_CRASH_P1			0x40000101
-#define HV_X64_MSR_CRASH_P2			0x40000102
+#define HV_REGISTER_CRASH_P2			0x40000102
-#define HV_X64_MSR_CRASH_P3			0x40000103
+#define HV_REGISTER_CRASH_P3			0x40000103
-#define HV_X64_MSR_CRASH_P4			0x40000104
+#define HV_REGISTER_CRASH_P4			0x40000104
-#define HV_X64_MSR_CRASH_CTL			0x40000105
+#define HV_REGISTER_CRASH_CTL			0x40000105
 
 /* TSC emulation after migration */
 #define HV_X64_MSR_REENLIGHTENMENT_CONTROL	0x40000106
@@ -236,6 +236,32 @@ enum hv_isolation_type {
 /* TSC invariant control */
 #define HV_X64_MSR_TSC_INVARIANT_CONTROL	0x40000118
 
+/* Register name aliases for temporary compatibility */
+#define HV_X64_MSR_STIMER0_COUNT	HV_REGISTER_STIMER0_COUNT
+#define HV_X64_MSR_STIMER0_CONFIG	HV_REGISTER_STIMER0_CONFIG
+#define HV_X64_MSR_STIMER1_COUNT	HV_REGISTER_STIMER1_COUNT
+#define HV_X64_MSR_STIMER1_CONFIG	HV_REGISTER_STIMER1_CONFIG
+#define HV_X64_MSR_STIMER2_COUNT	HV_REGISTER_STIMER2_COUNT
+#define HV_X64_MSR_STIMER2_CONFIG	HV_REGISTER_STIMER2_CONFIG
+#define HV_X64_MSR_STIMER3_COUNT	HV_REGISTER_STIMER3_COUNT
+#define HV_X64_MSR_STIMER3_CONFIG	HV_REGISTER_STIMER3_CONFIG
+#define HV_X64_MSR_SCONTROL		HV_REGISTER_SCONTROL
+#define HV_X64_MSR_SVERSION		HV_REGISTER_SVERSION
+#define HV_X64_MSR_SIMP			HV_REGISTER_SIMP
+#define HV_X64_MSR_SIEFP		HV_REGISTER_SIEFP
+#define HV_X64_MSR_VP_INDEX		HV_REGISTER_VP_INDEX
+#define HV_X64_MSR_EOM			HV_REGISTER_EOM
+#define HV_X64_MSR_SINT0		HV_REGISTER_SINT0
+#define HV_X64_MSR_SINT15		HV_REGISTER_SINT15
+#define HV_X64_MSR_CRASH_P0		HV_REGISTER_CRASH_P0
+#define HV_X64_MSR_CRASH_P1		HV_REGISTER_CRASH_P1
+#define HV_X64_MSR_CRASH_P2		HV_REGISTER_CRASH_P2
+#define HV_X64_MSR_CRASH_P3		HV_REGISTER_CRASH_P3
+#define HV_X64_MSR_CRASH_P4		HV_REGISTER_CRASH_P4
+#define HV_X64_MSR_CRASH_CTL		HV_REGISTER_CRASH_CTL
+#define HV_X64_MSR_TIME_REF_COUNT	HV_REGISTER_TIME_REF_COUNT
+#define HV_X64_MSR_REFERENCE_TSC	HV_REGISTER_REFERENCE_TSC
+
 /*
  * Declare the MSR used to setup pages used to communicate with the hypervisor.
  */
@@ -288,35 +314,6 @@ struct hv_tsc_emulation_status {
 #define HV_X64_MSR_TSC_REFERENCE_ENABLE		0x00000001
 #define HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT	12
 
-
-/* Define hypervisor message types. */
-enum hv_message_type {
-	HVMSG_NONE			= 0x00000000,
-
-	/* Memory access messages. */
-	HVMSG_UNMAPPED_GPA		= 0x80000000,
-	HVMSG_GPA_INTERCEPT		= 0x80000001,
-
-	/* Timer notification messages. */
-	HVMSG_TIMER_EXPIRED		= 0x80000010,
-
-	/* Error messages. */
-	HVMSG_INVALID_VP_REGISTER_VALUE	= 0x80000020,
-	HVMSG_UNRECOVERABLE_EXCEPTION	= 0x80000021,
-	HVMSG_UNSUPPORTED_FEATURE	= 0x80000022,
-
-	/* Trace buffer complete messages. */
-	HVMSG_EVENTLOG_BUFFERCOMPLETE	= 0x80000040,
-
-	/* Platform-specific processor intercept messages. */
-	HVMSG_X64_IOPORT_INTERCEPT	= 0x80010000,
-	HVMSG_X64_MSR_INTERCEPT		= 0x80010001,
-	HVMSG_X64_CPUID_INTERCEPT	= 0x80010002,
-	HVMSG_X64_EXCEPTION_INTERCEPT	= 0x80010003,
-	HVMSG_X64_APIC_EOI		= 0x80010004,
-	HVMSG_X64_LEGACY_FP_ERROR	= 0x80010005
-};
-
 struct hv_nested_enlightenments_control {
 	struct {
 		__u32 directhypercall:1;

arch/x86/include/asm/mshyperv.h

@@ -9,70 +9,29 @@
 #include <asm/hyperv-tlfs.h>
 #include <asm/nospec-branch.h>
 #include <asm/paravirt.h>
+#include <asm/mshyperv.h>
 
 typedef int (*hyperv_fill_flush_list_func)(
 		struct hv_guest_mapping_flush_list *flush,
 		void *data);
 
-#define hv_init_timer(timer, tick) \
+static inline void hv_set_register(unsigned int reg, u64 value)
-	wrmsrl(HV_X64_MSR_STIMER0_COUNT + (2*timer), tick)
-#define hv_init_timer_config(timer, val) \
-	wrmsrl(HV_X64_MSR_STIMER0_CONFIG + (2*timer), val)
-
-#define hv_get_simp(val) rdmsrl(HV_X64_MSR_SIMP, val)
-#define hv_set_simp(val) wrmsrl(HV_X64_MSR_SIMP, val)
-
-#define hv_get_siefp(val) rdmsrl(HV_X64_MSR_SIEFP, val)
-#define hv_set_siefp(val) wrmsrl(HV_X64_MSR_SIEFP, val)
-
-#define hv_get_synic_state(val) rdmsrl(HV_X64_MSR_SCONTROL, val)
-#define hv_set_synic_state(val) wrmsrl(HV_X64_MSR_SCONTROL, val)
-
-#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) \
-	wrmsrl(HV_X64_MSR_SINT0 + int_num, val)
-#define hv_recommend_using_aeoi() \
-	(!(ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED))
-
-#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).vdso_clock_mode = VDSO_CLOCKMODE_HVCLOCK)
-#define hv_enable_vdso_clocksource() \
-	vclocks_set_used(VDSO_CLOCKMODE_HVCLOCK);
-#define hv_get_raw_timer() rdtsc_ordered()
-#define hv_get_vector() HYPERVISOR_CALLBACK_VECTOR
-
-/*
- * Reference to pv_ops must be inline so objtool
- * detection of noinstr violations can work correctly.
- */
-static __always_inline void hv_setup_sched_clock(void *sched_clock)
 {
-#ifdef CONFIG_PARAVIRT
+	wrmsrl(reg, value);
-	paravirt_set_sched_clock(sched_clock);
-#endif
 }
 
+static inline u64 hv_get_register(unsigned int reg)
+{
+	u64 value;
+
+	rdmsrl(reg, value);
+	return value;
+}
+
+#define hv_get_raw_timer() rdtsc_ordered()
+
 void hyperv_vector_handler(struct pt_regs *regs);
 
-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 int hyperv_init_cpuhp;
 
@@ -189,38 +148,6 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
 	return hv_status;
 }
 
-/*
- * Rep hypercalls. Callers of this functions are supposed to ensure that
- * rep_count and varhead_size comply with Hyper-V hypercall definition.
- */
-static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size,
-				      void *input, void *output)
-{
-	u64 control = code;
-	u64 status;
-	u16 rep_comp;
-
-	control |= (u64)varhead_size << HV_HYPERCALL_VARHEAD_OFFSET;
-	control |= (u64)rep_count << HV_HYPERCALL_REP_COMP_OFFSET;
-
-	do {
-		status = hv_do_hypercall(control, input, output);
-		if ((status & HV_HYPERCALL_RESULT_MASK) != HV_STATUS_SUCCESS)
-			return status;
-
-		/* Bits 32-43 of status have 'Reps completed' data. */
-		rep_comp = (status & HV_HYPERCALL_REP_COMP_MASK) >>
-			HV_HYPERCALL_REP_COMP_OFFSET;
-
-		control &= ~HV_HYPERCALL_REP_START_MASK;
-		control |= (u64)rep_comp << HV_HYPERCALL_REP_START_OFFSET;
-
-		touch_nmi_watchdog();
-	} while (rep_comp < rep_count);
-
-	return status;
-}
-
 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)
@@ -233,9 +160,6 @@ static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu)
 
 void __init hyperv_init(void);
 void hyperv_setup_mmu_ops(void);
-void *hv_alloc_hyperv_page(void);
-void *hv_alloc_hyperv_zeroed_page(void);
-void hv_free_hyperv_page(unsigned long addr);
 void set_hv_tscchange_cb(void (*cb)(void));
 void clear_hv_tscchange_cb(void);
 void hyperv_stop_tsc_emulation(void);
@@ -272,8 +196,6 @@ int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);
 #else /* CONFIG_HYPERV */
 static inline void hyperv_init(void) {}
 static inline void hyperv_setup_mmu_ops(void) {}
-static inline void *hv_alloc_hyperv_page(void) { return NULL; }
-static inline void hv_free_hyperv_page(unsigned long addr) {}
 static inline void set_hv_tscchange_cb(void (*cb)(void)) {}
 static inline void clear_hv_tscchange_cb(void) {}
 static inline void hyperv_stop_tsc_emulation(void) {};

arch/x86/kernel/cpu/mshyperv.c

@@ -60,23 +60,18 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback)
 	set_irq_regs(old_regs);
 }
 
-int hv_setup_vmbus_irq(int irq, void (*handler)(void))
+void hv_setup_vmbus_handler(void (*handler)(void))
 {
-	/*
-	 * The 'irq' argument is ignored on x86/x64 because a hard-coded
-	 * interrupt vector is used for Hyper-V interrupts.
-	 */
 	vmbus_handler = handler;
-	return 0;
 }
+EXPORT_SYMBOL_GPL(hv_setup_vmbus_handler);
 
-void hv_remove_vmbus_irq(void)
+void hv_remove_vmbus_handler(void)
 {
 	/* We have no way to deallocate the interrupt gate */
 	vmbus_handler = NULL;
 }
-EXPORT_SYMBOL_GPL(hv_setup_vmbus_irq);
+EXPORT_SYMBOL_GPL(hv_remove_vmbus_handler);
-EXPORT_SYMBOL_GPL(hv_remove_vmbus_irq);
 
 /*
  * Routines to do per-architecture handling of stimer0
@@ -95,21 +90,17 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_stimer0)
 	set_irq_regs(old_regs);
 }
 
-int hv_setup_stimer0_irq(int *irq, int *vector, void (*handler)(void))
+/* For x86/x64, override weak placeholders in hyperv_timer.c */
+void hv_setup_stimer0_handler(void (*handler)(void))
 {
-	*vector = HYPERV_STIMER0_VECTOR;
-	*irq = -1;   /* Unused on x86/x64 */
 	hv_stimer0_handler = handler;
-	return 0;
 }
-EXPORT_SYMBOL_GPL(hv_setup_stimer0_irq);
 
-void hv_remove_stimer0_irq(int irq)
+void hv_remove_stimer0_handler(void)
 {
 	/* We have no way to deallocate the interrupt gate */
 	hv_stimer0_handler = NULL;
 }
-EXPORT_SYMBOL_GPL(hv_remove_stimer0_irq);
 
 void hv_setup_kexec_handler(void (*handler)(void))
 {
@@ -274,12 +265,13 @@ static void __init ms_hyperv_init_platform(void)
 	 * Extract the features and hints
 	 */
 	ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES);
-	ms_hyperv.features_b = cpuid_ebx(HYPERV_CPUID_FEATURES);
+	ms_hyperv.priv_high = cpuid_ebx(HYPERV_CPUID_FEATURES);
 	ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES);
 	ms_hyperv.hints    = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
 
-	pr_info("Hyper-V: features 0x%x, hints 0x%x, misc 0x%x\n",
+	pr_info("Hyper-V: privilege flags low 0x%x, high 0x%x, hints 0x%x, misc 0x%x\n",
-		ms_hyperv.features, ms_hyperv.hints, ms_hyperv.misc_features);
+		ms_hyperv.features, ms_hyperv.priv_high, ms_hyperv.hints,
+		ms_hyperv.misc_features);
 
 	ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS);
 	ms_hyperv.max_lp_index = cpuid_ebx(HYPERV_CPUID_IMPLEMENT_LIMITS);
@@ -325,7 +317,7 @@ static void __init ms_hyperv_init_platform(void)
 		x86_platform.calibrate_cpu = hv_get_tsc_khz;
 	}
 
-	if (ms_hyperv.features_b & HV_ISOLATION) {
+	if (ms_hyperv.priv_high & HV_ISOLATION) {
 		ms_hyperv.isolation_config_a = cpuid_eax(HYPERV_CPUID_ISOLATION_CONFIG);
 		ms_hyperv.isolation_config_b = cpuid_ebx(HYPERV_CPUID_ISOLATION_CONFIG);
 

drivers/clocksource/hyperv_timer.c

@@ -18,6 +18,9 @@
 #include <linux/sched_clock.h>
 #include <linux/mm.h>
 #include <linux/cpuhotplug.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/acpi.h>
 #include <clocksource/hyperv_timer.h>
 #include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
@@ -43,14 +46,13 @@ static u64 hv_sched_clock_offset __ro_after_init;
  */
 static bool direct_mode_enabled;
 
-static int stimer0_irq;
+static int stimer0_irq = -1;
-static int stimer0_vector;
 static int stimer0_message_sint;
+static DEFINE_PER_CPU(long, stimer0_evt);
 
 /*
- * ISR for when stimer0 is operating in Direct Mode.  Direct Mode
+ * Common code for stimer0 interrupts coming via Direct Mode or
- * does not use VMbus or any VMbus messages, so process here and not
+ * as a VMbus message.
- * in the VMbus driver code.
  */
 void hv_stimer0_isr(void)
 {
@@ -61,6 +63,16 @@ void hv_stimer0_isr(void)
 }
 EXPORT_SYMBOL_GPL(hv_stimer0_isr);
 
+/*
+ * stimer0 interrupt handler for architectures that support
+ * per-cpu interrupts, which also implies Direct Mode.
+ */
+static irqreturn_t hv_stimer0_percpu_isr(int irq, void *dev_id)
+{
+	hv_stimer0_isr();
+	return IRQ_HANDLED;
+}
+
 static int hv_ce_set_next_event(unsigned long delta,
 				struct clock_event_device *evt)
 {
@@ -68,16 +80,16 @@ static int hv_ce_set_next_event(unsigned long delta,
 
 	current_tick = hv_read_reference_counter();
 	current_tick += delta;
-	hv_init_timer(0, current_tick);
+	hv_set_register(HV_REGISTER_STIMER0_COUNT, current_tick);
 	return 0;
 }
 
 static int hv_ce_shutdown(struct clock_event_device *evt)
 {
-	hv_init_timer(0, 0);
+	hv_set_register(HV_REGISTER_STIMER0_COUNT, 0);
-	hv_init_timer_config(0, 0);
+	hv_set_register(HV_REGISTER_STIMER0_CONFIG, 0);
-	if (direct_mode_enabled)
+	if (direct_mode_enabled && stimer0_irq >= 0)
-		hv_disable_stimer0_percpu_irq(stimer0_irq);
+		disable_percpu_irq(stimer0_irq);
 
 	return 0;
 }
@@ -95,8 +107,9 @@ static int hv_ce_set_oneshot(struct clock_event_device *evt)
 		 * on the specified hardware vector/IRQ.
 		 */
 		timer_cfg.direct_mode = 1;
-		timer_cfg.apic_vector = stimer0_vector;
+		timer_cfg.apic_vector = HYPERV_STIMER0_VECTOR;
-		hv_enable_stimer0_percpu_irq(stimer0_irq);
+		if (stimer0_irq >= 0)
+			enable_percpu_irq(stimer0_irq, IRQ_TYPE_NONE);
 	} else {
 		/*
 		 * When it expires, the timer will generate a VMbus message,
@@ -105,7 +118,7 @@ static int hv_ce_set_oneshot(struct clock_event_device *evt)
 		timer_cfg.direct_mode = 0;
 		timer_cfg.sintx = stimer0_message_sint;
 	}
-	hv_init_timer_config(0, timer_cfg.as_uint64);
+	hv_set_register(HV_REGISTER_STIMER0_CONFIG, timer_cfg.as_uint64);
 	return 0;
 }
 
@@ -169,10 +182,58 @@ int hv_stimer_cleanup(unsigned int cpu)
 }
 EXPORT_SYMBOL_GPL(hv_stimer_cleanup);
 
-/* hv_stimer_alloc - Global initialization of the clockevent and stimer0 */
+/*
-int hv_stimer_alloc(void)
+ * These placeholders are overridden by arch specific code on
+ * architectures that need special setup of the stimer0 IRQ because
+ * they don't support per-cpu IRQs (such as x86/x64).
+ */
+void __weak hv_setup_stimer0_handler(void (*handler)(void))
 {
-	int ret = 0;
+};
+
+void __weak hv_remove_stimer0_handler(void)
+{
+};
+
+/* Called only on architectures with per-cpu IRQs (i.e., not x86/x64) */
+static int hv_setup_stimer0_irq(void)
+{
+	int ret;
+
+	ret = acpi_register_gsi(NULL, HYPERV_STIMER0_VECTOR,
+			ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_HIGH);
+	if (ret < 0) {
+		pr_err("Can't register Hyper-V stimer0 GSI. Error %d", ret);
+		return ret;
+	}
+	stimer0_irq = ret;
+
+	ret = request_percpu_irq(stimer0_irq, hv_stimer0_percpu_isr,
+		"Hyper-V stimer0", &stimer0_evt);
+	if (ret) {
+		pr_err("Can't request Hyper-V stimer0 IRQ %d. Error %d",
+			stimer0_irq, ret);
+		acpi_unregister_gsi(stimer0_irq);
+		stimer0_irq = -1;
+	}
+	return ret;
+}
+
+static void hv_remove_stimer0_irq(void)
+{
+	if (stimer0_irq == -1) {
+		hv_remove_stimer0_handler();
+	} else {
+		free_percpu_irq(stimer0_irq, &stimer0_evt);
+		acpi_unregister_gsi(stimer0_irq);
+		stimer0_irq = -1;
+	}
+}
+
+/* hv_stimer_alloc - Global initialization of the clockevent and stimer0 */
+int hv_stimer_alloc(bool have_percpu_irqs)
+{
+	int ret;
 
 	/*
 	 * Synthetic timers are always available except on old versions of
@@ -188,29 +249,37 @@ int hv_stimer_alloc(void)
 
 	direct_mode_enabled = ms_hyperv.misc_features &
 			HV_STIMER_DIRECT_MODE_AVAILABLE;
-	if (direct_mode_enabled) {
-		ret = hv_setup_stimer0_irq(&stimer0_irq, &stimer0_vector,
-				hv_stimer0_isr);
-		if (ret)
-			goto free_percpu;
 
-		/*
+	/*
-		 * Since we are in Direct Mode, stimer initialization
+	 * If Direct Mode isn't enabled, the remainder of the initialization
-		 * can be done now with a CPUHP value in the same range
+	 * is done later by hv_stimer_legacy_init()
-		 * as other clockevent devices.
+	 */
-		 */
+	if (!direct_mode_enabled)
-		ret = cpuhp_setup_state(CPUHP_AP_HYPERV_TIMER_STARTING,
+		return 0;
-				"clockevents/hyperv/stimer:starting",
+
-				hv_stimer_init, hv_stimer_cleanup);
+	if (have_percpu_irqs) {
-		if (ret < 0)
+		ret = hv_setup_stimer0_irq();
-			goto free_stimer0_irq;
+		if (ret)
+			goto free_clock_event;
+	} else {
+		hv_setup_stimer0_handler(hv_stimer0_isr);
+	}
+
+	/*
+	 * Since we are in Direct Mode, stimer initialization
+	 * can be done now with a CPUHP value in the same range
+	 * as other clockevent devices.
+	 */
+	ret = cpuhp_setup_state(CPUHP_AP_HYPERV_TIMER_STARTING,
+			"clockevents/hyperv/stimer:starting",
+			hv_stimer_init, hv_stimer_cleanup);
+	if (ret < 0) {
+		hv_remove_stimer0_irq();
+		goto free_clock_event;
 	}
 	return ret;
 
-free_stimer0_irq:
+free_clock_event:
-	hv_remove_stimer0_irq(stimer0_irq);
-	stimer0_irq = 0;
-free_percpu:
 	free_percpu(hv_clock_event);
 	hv_clock_event = NULL;
 	return ret;
@@ -254,23 +323,6 @@ void hv_stimer_legacy_cleanup(unsigned int cpu)
 }
 EXPORT_SYMBOL_GPL(hv_stimer_legacy_cleanup);
 
-
-/* hv_stimer_free - Free global resources allocated by hv_stimer_alloc() */
-void hv_stimer_free(void)
-{
-	if (!hv_clock_event)
-		return;
-
-	if (direct_mode_enabled) {
-		cpuhp_remove_state(CPUHP_AP_HYPERV_TIMER_STARTING);
-		hv_remove_stimer0_irq(stimer0_irq);
-		stimer0_irq = 0;
-	}
-	free_percpu(hv_clock_event);
-	hv_clock_event = NULL;
-}
-EXPORT_SYMBOL_GPL(hv_stimer_free);
-
 /*
  * Do a global cleanup of clockevents for the cases of kexec and
  * vmbus exit
@@ -287,12 +339,17 @@ void hv_stimer_global_cleanup(void)
 		hv_stimer_legacy_cleanup(cpu);
 	}
 
-	/*
+	if (!hv_clock_event)
-	 * If Direct Mode is enabled, the cpuhp teardown callback
+		return;
-	 * (hv_stimer_cleanup) will be run on all CPUs to stop the
+
-	 * stimers.
+	if (direct_mode_enabled) {
-	 */
+		cpuhp_remove_state(CPUHP_AP_HYPERV_TIMER_STARTING);
-	hv_stimer_free();
+		hv_remove_stimer0_irq();
+		stimer0_irq = -1;
+	}
+	free_percpu(hv_clock_event);
+	hv_clock_event = NULL;
+
 }
 EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup);
 
@@ -302,14 +359,6 @@ EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup);
  * 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.
- *
- * The Hyper-V clocksource ratings of 250 are chosen to be below the
- * TSC clocksource rating of 300.  In configurations where Hyper-V offers
- * an InvariantTSC, the TSC is not marked "unstable", so the TSC clocksource
- * is available and preferred.  With the higher rating, it will be the
- * default.  On older hardware and Hyper-V versions, the TSC is marked
- * "unstable", so no TSC clocksource is created and the selected Hyper-V
- * clocksource will be the default.
  */
 
 u64 (*hv_read_reference_counter)(void);
@@ -331,7 +380,7 @@ static u64 notrace read_hv_clock_tsc(void)
 	u64 current_tick = hv_read_tsc_page(hv_get_tsc_page());
 
 	if (current_tick == U64_MAX)
-		hv_get_time_ref_count(current_tick);
+		current_tick = hv_get_register(HV_REGISTER_TIME_REF_COUNT);
 
 	return current_tick;
 }
@@ -352,9 +401,9 @@ static void suspend_hv_clock_tsc(struct clocksource *arg)
 	u64 tsc_msr;
 
 	/* Disable the TSC page */
-	hv_get_reference_tsc(tsc_msr);
+	tsc_msr = hv_get_register(HV_REGISTER_REFERENCE_TSC);
 	tsc_msr &= ~BIT_ULL(0);
-	hv_set_reference_tsc(tsc_msr);
+	hv_set_register(HV_REGISTER_REFERENCE_TSC, tsc_msr);
 }
 
 
@@ -364,39 +413,44 @@ static void resume_hv_clock_tsc(struct clocksource *arg)
 	u64 tsc_msr;
 
 	/* Re-enable the TSC page */
-	hv_get_reference_tsc(tsc_msr);
+	tsc_msr = hv_get_register(HV_REGISTER_REFERENCE_TSC);
 	tsc_msr &= GENMASK_ULL(11, 0);
 	tsc_msr |= BIT_ULL(0) | (u64)phys_addr;
-	hv_set_reference_tsc(tsc_msr);
+	hv_set_register(HV_REGISTER_REFERENCE_TSC, tsc_msr);
 }
 
+#ifdef VDSO_CLOCKMODE_HVCLOCK
 static int hv_cs_enable(struct clocksource *cs)
 {
-	hv_enable_vdso_clocksource();
+	vclocks_set_used(VDSO_CLOCKMODE_HVCLOCK);
 	return 0;
 }
+#endif
 
 static struct clocksource hyperv_cs_tsc = {
 	.name	= "hyperv_clocksource_tsc_page",
-	.rating	= 250,
+	.rating	= 500,
 	.read	= read_hv_clock_tsc_cs,
 	.mask	= CLOCKSOURCE_MASK(64),
 	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
 	.suspend= suspend_hv_clock_tsc,
 	.resume	= resume_hv_clock_tsc,
+#ifdef VDSO_CLOCKMODE_HVCLOCK
 	.enable = hv_cs_enable,
+	.vdso_clock_mode = VDSO_CLOCKMODE_HVCLOCK,
+#else
+	.vdso_clock_mode = VDSO_CLOCKMODE_NONE,
+#endif
 };
 
 static u64 notrace read_hv_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 hv_get_register(HV_REGISTER_TIME_REF_COUNT);
-	return current_tick;
 }
 
 static u64 notrace read_hv_clock_msr_cs(struct clocksource *arg)
@@ -412,12 +466,36 @@ static u64 notrace read_hv_sched_clock_msr(void)
 
 static struct clocksource hyperv_cs_msr = {
 	.name	= "hyperv_clocksource_msr",
-	.rating	= 250,
+	.rating	= 500,
 	.read	= read_hv_clock_msr_cs,
 	.mask	= CLOCKSOURCE_MASK(64),
 	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
+/*
+ * Reference to pv_ops must be inline so objtool
+ * detection of noinstr violations can work correctly.
+ */
+#ifdef CONFIG_GENERIC_SCHED_CLOCK
+static __always_inline void hv_setup_sched_clock(void *sched_clock)
+{
+	/*
+	 * We're on an architecture with generic sched clock (not x86/x64).
+	 * The Hyper-V sched clock read function returns nanoseconds, not
+	 * the normal 100ns units of the Hyper-V synthetic clock.
+	 */
+	sched_clock_register(sched_clock, 64, NSEC_PER_SEC);
+}
+#elif defined CONFIG_PARAVIRT
+static __always_inline void hv_setup_sched_clock(void *sched_clock)
+{
+	/* We're on x86/x64 *and* using PV ops */
+	paravirt_set_sched_clock(sched_clock);
+}
+#else /* !CONFIG_GENERIC_SCHED_CLOCK && !CONFIG_PARAVIRT */
+static __always_inline void hv_setup_sched_clock(void *sched_clock) {}
+#endif /* CONFIG_GENERIC_SCHED_CLOCK */
+
 static bool __init hv_init_tsc_clocksource(void)
 {
 	u64		tsc_msr;
@@ -429,6 +507,22 @@ static bool __init hv_init_tsc_clocksource(void)
 	if (hv_root_partition)
 		return false;
 
+	/*
+	 * If Hyper-V offers TSC_INVARIANT, then the virtualized TSC correctly
+	 * handles frequency and offset changes due to live migration,
+	 * pause/resume, and other VM management operations.  So lower the
+	 * Hyper-V Reference TSC rating, causing the generic TSC to be used.
+	 * TSC_INVARIANT is not offered on ARM64, so the Hyper-V Reference
+	 * TSC will be preferred over the virtualized ARM64 arch counter.
+	 * While the Hyper-V MSR clocksource won't be used since the
+	 * Reference TSC clocksource is present, change its rating as
+	 * well for consistency.
+	 */
+	if (ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) {
+		hyperv_cs_tsc.rating = 250;
+		hyperv_cs_msr.rating = 250;
+	}
+
 	hv_read_reference_counter = read_hv_clock_tsc;
 	phys_addr = virt_to_phys(hv_get_tsc_page());
 
@@ -439,12 +533,11 @@ static bool __init hv_init_tsc_clocksource(void)
 	 * (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 = hv_get_register(HV_REGISTER_REFERENCE_TSC);
 	tsc_msr &= GENMASK_ULL(11, 0);
 	tsc_msr = tsc_msr | 0x1 | (u64)phys_addr;
-	hv_set_reference_tsc(tsc_msr);
+	hv_set_register(HV_REGISTER_REFERENCE_TSC, tsc_msr);
 
-	hv_set_clocksource_vdso(hyperv_cs_tsc);
 	clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
 
 	hv_sched_clock_offset = hv_read_reference_counter();

drivers/hv/Kconfig

@@ -23,6 +23,7 @@ config HYPERV_UTILS
 config HYPERV_BALLOON
 	tristate "Microsoft Hyper-V Balloon driver"
 	depends on HYPERV
+	select PAGE_REPORTING
 	help
 	  Select this option to enable Hyper-V Balloon driver.
 

drivers/hv/channel.c

@@ -209,31 +209,96 @@ int vmbus_send_tl_connect_request(const guid_t *shv_guest_servie_id,
 }
 EXPORT_SYMBOL_GPL(vmbus_send_tl_connect_request);
 
+static int send_modifychannel_without_ack(struct vmbus_channel *channel, u32 target_vp)
+{
+	struct vmbus_channel_modifychannel msg;
+	int ret;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.header.msgtype = CHANNELMSG_MODIFYCHANNEL;
+	msg.child_relid = channel->offermsg.child_relid;
+	msg.target_vp = target_vp;
+
+	ret = vmbus_post_msg(&msg, sizeof(msg), true);
+	trace_vmbus_send_modifychannel(&msg, ret);
+
+	return ret;
+}
+
+static int send_modifychannel_with_ack(struct vmbus_channel *channel, u32 target_vp)
+{
+	struct vmbus_channel_modifychannel *msg;
+	struct vmbus_channel_msginfo *info;
+	unsigned long flags;
+	int ret;
+
+	info = kzalloc(sizeof(struct vmbus_channel_msginfo) +
+				sizeof(struct vmbus_channel_modifychannel),
+		       GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	init_completion(&info->waitevent);
+	info->waiting_channel = channel;
+
+	msg = (struct vmbus_channel_modifychannel *)info->msg;
+	msg->header.msgtype = CHANNELMSG_MODIFYCHANNEL;
+	msg->child_relid = channel->offermsg.child_relid;
+	msg->target_vp = target_vp;
+
+	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
+	list_add_tail(&info->msglistentry, &vmbus_connection.chn_msg_list);
+	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
+
+	ret = vmbus_post_msg(msg, sizeof(*msg), true);
+	trace_vmbus_send_modifychannel(msg, ret);
+	if (ret != 0) {
+		spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
+		list_del(&info->msglistentry);
+		spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
+		goto free_info;
+	}
+
+	/*
+	 * Release channel_mutex; otherwise, vmbus_onoffer_rescind() could block on
+	 * the mutex and be unable to signal the completion.
+	 *
+	 * See the caller target_cpu_store() for information about the usage of the
+	 * mutex.
+	 */
+	mutex_unlock(&vmbus_connection.channel_mutex);
+	wait_for_completion(&info->waitevent);
+	mutex_lock(&vmbus_connection.channel_mutex);
+
+	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
+	list_del(&info->msglistentry);
+	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
+
+	if (info->response.modify_response.status)
+		ret = -EAGAIN;
+
+free_info:
+	kfree(info);
+	return ret;
+}
+
 /*
  * Set/change the vCPU (@target_vp) the channel (@child_relid) will interrupt.
  *
- * CHANNELMSG_MODIFYCHANNEL messages are aynchronous.  Also, Hyper-V does not
+ * CHANNELMSG_MODIFYCHANNEL messages are aynchronous.  When VMbus version 5.3
- * ACK such messages.  IOW we can't know when the host will stop interrupting
+ * or later is negotiated, Hyper-V always sends an ACK in response to such a
- * the "old" vCPU and start interrupting the "new" vCPU for the given channel.
+ * message.  For VMbus version 5.2 and earlier, it never sends an ACK.  With-
+ * out an ACK, we can not know when the host will stop interrupting the "old"
+ * vCPU and start interrupting the "new" vCPU for the given channel.
  *
  * The CHANNELMSG_MODIFYCHANNEL message type is supported since VMBus version
  * VERSION_WIN10_V4_1.
  */
-int vmbus_send_modifychannel(u32 child_relid, u32 target_vp)
+int vmbus_send_modifychannel(struct vmbus_channel *channel, u32 target_vp)
 {
-	struct vmbus_channel_modifychannel conn_msg;
+	if (vmbus_proto_version >= VERSION_WIN10_V5_3)
-	int ret;
+		return send_modifychannel_with_ack(channel, target_vp);
-
+	return send_modifychannel_without_ack(channel, target_vp);
-	memset(&conn_msg, 0, sizeof(conn_msg));
-	conn_msg.header.msgtype = CHANNELMSG_MODIFYCHANNEL;
-	conn_msg.child_relid = child_relid;
-	conn_msg.target_vp = target_vp;
-
-	ret = vmbus_post_msg(&conn_msg, sizeof(conn_msg), true);
-
-	trace_vmbus_send_modifychannel(&conn_msg, ret);
-
-	return ret;
 }
 EXPORT_SYMBOL_GPL(vmbus_send_modifychannel);
 
@@ -385,7 +450,7 @@ nomem:
  * @kbuffer: from kmalloc or vmalloc
  * @size: page-size multiple
  * @send_offset: the offset (in bytes) where the send ring buffer starts,
- * 		 should be 0 for BUFFER type gpadl
+ *              should be 0 for BUFFER type gpadl
  * @gpadl_handle: some funky thing
  */
 static int __vmbus_establish_gpadl(struct vmbus_channel *channel,
@@ -653,7 +718,7 @@ static int __vmbus_open(struct vmbus_channel *newchannel,
 
 	if (newchannel->rescind) {
 		err = -ENODEV;
-		goto error_free_info;
+		goto error_clean_msglist;
 	}
 
 	err = vmbus_post_msg(open_msg,

drivers/hv/channel_mgmt.c

@@ -333,7 +333,6 @@ fw_error:
 	negop->icversion_data[1].minor = icmsg_minor;
 	return found_match;
 }
-
 EXPORT_SYMBOL_GPL(vmbus_prep_negotiate_resp);
 
 /*
@@ -593,10 +592,10 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
 	 * CPUS_READ_UNLOCK		CPUS_WRITE_UNLOCK
 	 *
 	 * Forbids: CPU1's LOAD from *not* seing CPU2's STORE &&
-	 * 		CPU2's SEARCH from *not* seeing CPU1's INSERT
+	 *              CPU2's SEARCH from *not* seeing CPU1's INSERT
 	 *
 	 * Forbids: CPU2's SEARCH from seeing CPU1's INSERT &&
-	 * 		CPU2's LOAD from *not* seing CPU1's STORE
+	 *              CPU2's LOAD from *not* seing CPU1's STORE
 	 */
 	cpus_read_lock();
 
@@ -756,6 +755,12 @@ static void init_vp_index(struct vmbus_channel *channel)
 	free_cpumask_var(available_mask);
 }
 
+#define UNLOAD_DELAY_UNIT_MS	10		/* 10 milliseconds */
+#define UNLOAD_WAIT_MS		(100*1000)	/* 100 seconds */
+#define UNLOAD_WAIT_LOOPS	(UNLOAD_WAIT_MS/UNLOAD_DELAY_UNIT_MS)
+#define UNLOAD_MSG_MS		(5*1000)	/* Every 5 seconds */
+#define UNLOAD_MSG_LOOPS	(UNLOAD_MSG_MS/UNLOAD_DELAY_UNIT_MS)
+
 static void vmbus_wait_for_unload(void)
 {
 	int cpu;
@@ -773,12 +778,17 @@ static void vmbus_wait_for_unload(void)
 	 * vmbus_connection.unload_event. If not, the last thing we can do is
 	 * read message pages for all CPUs directly.
 	 *
-	 * Wait no more than 10 seconds so that the panic path can't get
+	 * Wait up to 100 seconds since an Azure host must writeback any dirty
-	 * hung forever in case the response message isn't seen.
+	 * data in its disk cache before the VMbus UNLOAD request will
+	 * complete. This flushing has been empirically observed to take up
+	 * to 50 seconds in cases with a lot of dirty data, so allow additional
+	 * leeway and for inaccuracies in mdelay(). But eventually time out so
+	 * that the panic path can't get hung forever in case the response
+	 * message isn't seen.
 	 */
-	for (i = 0; i < 1000; i++) {
+	for (i = 1; i <= UNLOAD_WAIT_LOOPS; i++) {
 		if (completion_done(&vmbus_connection.unload_event))
-			break;
+			goto completed;
 
 		for_each_online_cpu(cpu) {
 			struct hv_per_cpu_context *hv_cpu
@@ -801,9 +811,18 @@ static void vmbus_wait_for_unload(void)
 			vmbus_signal_eom(msg, message_type);
 		}
 
-		mdelay(10);
+		/*
-	}
+		 * Give a notice periodically so someone watching the
+		 * serial output won't think it is completely hung.
+		 */
+		if (!(i % UNLOAD_MSG_LOOPS))
+			pr_notice("Waiting for VMBus UNLOAD to complete\n");
 
+		mdelay(UNLOAD_DELAY_UNIT_MS);
+	}
+	pr_err("Continuing even though VMBus UNLOAD did not complete\n");
+
+completed:
 	/*
 	 * We're crashing and already got the UNLOAD_RESPONSE, cleanup all
 	 * maybe-pending messages on all CPUs to be able to receive new
@@ -827,6 +846,11 @@ static void vmbus_unload_response(struct vmbus_channel_message_header *hdr)
 	/*
 	 * This is a global event; just wakeup the waiting thread.
 	 * Once we successfully unload, we can cleanup the monitor state.
+	 *
+	 * NB.  A malicious or compromised Hyper-V could send a spurious
+	 * message of type CHANNELMSG_UNLOAD_RESPONSE, and trigger a call
+	 * of the complete() below.  Make sure that unload_event has been
+	 * initialized by the time this complete() is executed.
 	 */
 	complete(&vmbus_connection.unload_event);
 }
@@ -842,7 +866,7 @@ void vmbus_initiate_unload(bool crash)
 	if (vmbus_proto_version < VERSION_WIN8_1)
 		return;
 
-	init_completion(&vmbus_connection.unload_event);
+	reinit_completion(&vmbus_connection.unload_event);
 	memset(&hdr, 0, sizeof(struct vmbus_channel_message_header));
 	hdr.msgtype = CHANNELMSG_UNLOAD;
 	vmbus_post_msg(&hdr, sizeof(struct vmbus_channel_message_header),
@@ -980,7 +1004,7 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
 		 *					UNLOCK channel_mutex
 		 *
 		 * Forbids: r1 == valid_relid &&
-		 * 		channels[valid_relid] == channel
+		 *              channels[valid_relid] == channel
 		 *
 		 * Note.  r1 can be INVALID_RELID only for an hv_sock channel.
 		 * None of the hv_sock channels which were present before the
@@ -1312,6 +1336,46 @@ static void vmbus_ongpadl_created(struct vmbus_channel_message_header *hdr)
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
 }
 
+/*
+ * vmbus_onmodifychannel_response - Modify Channel response handler.
+ *
+ * This is invoked when we received a response to our channel modify request.
+ * Find the matching request, copy the response and signal the requesting thread.
+ */
+static void vmbus_onmodifychannel_response(struct vmbus_channel_message_header *hdr)
+{
+	struct vmbus_channel_modifychannel_response *response;
+	struct vmbus_channel_msginfo *msginfo;
+	unsigned long flags;
+
+	response = (struct vmbus_channel_modifychannel_response *)hdr;
+
+	trace_vmbus_onmodifychannel_response(response);
+
+	/*
+	 * Find the modify msg, copy the response and signal/unblock the wait event.
+	 */
+	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
+
+	list_for_each_entry(msginfo, &vmbus_connection.chn_msg_list, msglistentry) {
+		struct vmbus_channel_message_header *responseheader =
+				(struct vmbus_channel_message_header *)msginfo->msg;
+
+		if (responseheader->msgtype == CHANNELMSG_MODIFYCHANNEL) {
+			struct vmbus_channel_modifychannel *modifymsg;
+
+			modifymsg = (struct vmbus_channel_modifychannel *)msginfo->msg;
+			if (modifymsg->child_relid == response->child_relid) {
+				memcpy(&msginfo->response.modify_response, response,
+				       sizeof(*response));
+				complete(&msginfo->waitevent);
+				break;
+			}
+		}
+	}
+	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
+}
+
 /*
  * vmbus_ongpadl_torndown - GPADL torndown handler.
  *
@@ -1429,6 +1493,8 @@ channel_message_table[CHANNELMSG_COUNT] = {
 	{ CHANNELMSG_TL_CONNECT_REQUEST,	0, NULL, 0},
 	{ CHANNELMSG_MODIFYCHANNEL,		0, NULL, 0},
 	{ CHANNELMSG_TL_CONNECT_RESULT,		0, NULL, 0},
+	{ CHANNELMSG_MODIFYCHANNEL_RESPONSE,	1, vmbus_onmodifychannel_response,
+		sizeof(struct vmbus_channel_modifychannel_response)},
 };
 
 /*

drivers/hv/connection.c

@@ -26,9 +26,11 @@
 
 struct vmbus_connection vmbus_connection = {
 	.conn_state		= DISCONNECTED,
+	.unload_event		= COMPLETION_INITIALIZER(
+				  vmbus_connection.unload_event),
 	.next_gpadl_handle	= ATOMIC_INIT(0xE1E10),
 
-	.ready_for_suspend_event= COMPLETION_INITIALIZER(
+	.ready_for_suspend_event = COMPLETION_INITIALIZER(
 				  vmbus_connection.ready_for_suspend_event),
 	.ready_for_resume_event	= COMPLETION_INITIALIZER(
 				  vmbus_connection.ready_for_resume_event),
@@ -45,6 +47,7 @@ EXPORT_SYMBOL_GPL(vmbus_proto_version);
  * Table of VMBus versions listed from newest to oldest.
  */
 static __u32 vmbus_versions[] = {
+	VERSION_WIN10_V5_3,
 	VERSION_WIN10_V5_2,
 	VERSION_WIN10_V5_1,
 	VERSION_WIN10_V5,
@@ -60,7 +63,7 @@ static __u32 vmbus_versions[] = {
  * Maximal VMBus protocol version guests can negotiate.  Useful to cap the
  * VMBus version for testing and debugging purpose.
  */
-static uint max_version = VERSION_WIN10_V5_2;
+static uint max_version = VERSION_WIN10_V5_3;
 
 module_param(max_version, uint, S_IRUGO);
 MODULE_PARM_DESC(max_version,

drivers/hv/hv.c

@@ -13,9 +13,10 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/hyperv.h>
-#include <linux/version.h>
 #include <linux/random.h>
 #include <linux/clockchips.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
 #include <clocksource/hyperv_timer.h>
 #include <asm/mshyperv.h>
 #include "hyperv_vmbus.h"
@@ -36,6 +37,42 @@ int hv_init(void)
 	return 0;
 }
 
+/*
+ * Functions for allocating and freeing memory with size and
+ * alignment HV_HYP_PAGE_SIZE. These functions are needed because
+ * the guest page size may not be the same as the Hyper-V page
+ * size. We depend upon kmalloc() aligning power-of-two size
+ * allocations to the allocation size boundary, so that the
+ * allocated memory appears to Hyper-V as a page of the size
+ * it expects.
+ */
+
+void *hv_alloc_hyperv_page(void)
+{
+	BUILD_BUG_ON(PAGE_SIZE <  HV_HYP_PAGE_SIZE);
+
+	if (PAGE_SIZE == HV_HYP_PAGE_SIZE)
+		return (void *)__get_free_page(GFP_KERNEL);
+	else
+		return kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
+}
+
+void *hv_alloc_hyperv_zeroed_page(void)
+{
+	if (PAGE_SIZE == HV_HYP_PAGE_SIZE)
+		return (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+	else
+		return kzalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
+}
+
+void hv_free_hyperv_page(unsigned long addr)
+{
+	if (PAGE_SIZE == HV_HYP_PAGE_SIZE)
+		free_page(addr);
+	else
+		kfree((void *)addr);
+}
+
 /*
  * hv_post_message - Post a message using the hypervisor message IPC.
  *
@@ -68,7 +105,7 @@ int hv_post_message(union hv_connection_id connection_id,
 	 */
 	put_cpu_ptr(hv_cpu);
 
-	return status & 0xFFFF;
+	return hv_result(status);
 }
 
 int hv_synic_alloc(void)
@@ -162,34 +199,48 @@ void hv_synic_enable_regs(unsigned int cpu)
 	union hv_synic_scontrol sctrl;
 
 	/* Setup the Synic's message page */
-	hv_get_simp(simp.as_uint64);
+	simp.as_uint64 = hv_get_register(HV_REGISTER_SIMP);
 	simp.simp_enabled = 1;
 	simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page)
 		>> HV_HYP_PAGE_SHIFT;
 
-	hv_set_simp(simp.as_uint64);
+	hv_set_register(HV_REGISTER_SIMP, simp.as_uint64);
 
 	/* Setup the Synic's event page */
-	hv_get_siefp(siefp.as_uint64);
+	siefp.as_uint64 = hv_get_register(HV_REGISTER_SIEFP);
 	siefp.siefp_enabled = 1;
 	siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page)
 		>> HV_HYP_PAGE_SHIFT;
 
-	hv_set_siefp(siefp.as_uint64);
+	hv_set_register(HV_REGISTER_SIEFP, siefp.as_uint64);
 
 	/* Setup the shared SINT. */
-	hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+	if (vmbus_irq != -1)
+		enable_percpu_irq(vmbus_irq, 0);
+	shared_sint.as_uint64 = hv_get_register(HV_REGISTER_SINT0 +
+					VMBUS_MESSAGE_SINT);
 
-	shared_sint.vector = hv_get_vector();
+	shared_sint.vector = vmbus_interrupt;
 	shared_sint.masked = false;
-	shared_sint.auto_eoi = hv_recommend_using_aeoi();
+
-	hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+	/*
+	 * On architectures where Hyper-V doesn't support AEOI (e.g., ARM64),
+	 * it doesn't provide a recommendation flag and AEOI must be disabled.
+	 */
+#ifdef HV_DEPRECATING_AEOI_RECOMMENDED
+	shared_sint.auto_eoi =
+			!(ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED);
+#else
+	shared_sint.auto_eoi = 0;
+#endif
+	hv_set_register(HV_REGISTER_SINT0 + VMBUS_MESSAGE_SINT,
+				shared_sint.as_uint64);
 
 	/* Enable the global synic bit */
-	hv_get_synic_state(sctrl.as_uint64);
+	sctrl.as_uint64 = hv_get_register(HV_REGISTER_SCONTROL);
 	sctrl.enable = 1;
 
-	hv_set_synic_state(sctrl.as_uint64);
+	hv_set_register(HV_REGISTER_SCONTROL, sctrl.as_uint64);
 }
 
 int hv_synic_init(unsigned int cpu)
@@ -211,30 +262,71 @@ void hv_synic_disable_regs(unsigned int cpu)
 	union hv_synic_siefp siefp;
 	union hv_synic_scontrol sctrl;
 
-	hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+	shared_sint.as_uint64 = hv_get_register(HV_REGISTER_SINT0 +
+					VMBUS_MESSAGE_SINT);
 
 	shared_sint.masked = 1;
 
 	/* Need to correctly cleanup in the case of SMP!!! */
 	/* Disable the interrupt */
-	hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+	hv_set_register(HV_REGISTER_SINT0 + VMBUS_MESSAGE_SINT,
+				shared_sint.as_uint64);
 
-	hv_get_simp(simp.as_uint64);
+	simp.as_uint64 = hv_get_register(HV_REGISTER_SIMP);
 	simp.simp_enabled = 0;
 	simp.base_simp_gpa = 0;
 
-	hv_set_simp(simp.as_uint64);
+	hv_set_register(HV_REGISTER_SIMP, simp.as_uint64);
 
-	hv_get_siefp(siefp.as_uint64);
+	siefp.as_uint64 = hv_get_register(HV_REGISTER_SIEFP);
 	siefp.siefp_enabled = 0;
 	siefp.base_siefp_gpa = 0;
 
-	hv_set_siefp(siefp.as_uint64);
+	hv_set_register(HV_REGISTER_SIEFP, siefp.as_uint64);
 
 	/* Disable the global synic bit */
-	hv_get_synic_state(sctrl.as_uint64);
+	sctrl.as_uint64 = hv_get_register(HV_REGISTER_SCONTROL);
 	sctrl.enable = 0;
-	hv_set_synic_state(sctrl.as_uint64);
+	hv_set_register(HV_REGISTER_SCONTROL, sctrl.as_uint64);
+
+	if (vmbus_irq != -1)
+		disable_percpu_irq(vmbus_irq);
+}
+
+#define HV_MAX_TRIES 3
+/*
+ * Scan the event flags page of 'this' CPU looking for any bit that is set.  If we find one
+ * bit set, then wait for a few milliseconds.  Repeat these steps for a maximum of 3 times.
+ * Return 'true', if there is still any set bit after this operation; 'false', otherwise.
+ *
+ * If a bit is set, that means there is a pending channel interrupt.  The expectation is
+ * that the normal interrupt handling mechanism will find and process the channel interrupt
+ * "very soon", and in the process clear the bit.
+ */
+static bool hv_synic_event_pending(void)
+{
+	struct hv_per_cpu_context *hv_cpu = this_cpu_ptr(hv_context.cpu_context);
+	union hv_synic_event_flags *event =
+		(union hv_synic_event_flags *)hv_cpu->synic_event_page + VMBUS_MESSAGE_SINT;
+	unsigned long *recv_int_page = event->flags; /* assumes VMBus version >= VERSION_WIN8 */
+	bool pending;
+	u32 relid;
+	int tries = 0;
+
+retry:
+	pending = false;
+	for_each_set_bit(relid, recv_int_page, HV_EVENT_FLAGS_COUNT) {
+		/* Special case - VMBus channel protocol messages */
+		if (relid == 0)
+			continue;
+		pending = true;
+		break;
+	}
+	if (pending && tries++ < HV_MAX_TRIES) {
+		usleep_range(10000, 20000);
+		goto retry;
+	}
+	return pending;
 }
 
 int hv_synic_cleanup(unsigned int cpu)
@@ -242,6 +334,9 @@ int hv_synic_cleanup(unsigned int cpu)
 	struct vmbus_channel *channel, *sc;
 	bool channel_found = false;
 
+	if (vmbus_connection.conn_state != CONNECTED)
+		goto always_cleanup;
+
 	/*
 	 * Hyper-V does not provide a way to change the connect CPU once
 	 * it is set; we must prevent the connect CPU from going offline
@@ -249,8 +344,7 @@ int hv_synic_cleanup(unsigned int cpu)
 	 * path where the vmbus is already disconnected, the CPU must be
 	 * allowed to shut down.
 	 */
-	if (cpu == VMBUS_CONNECT_CPU &&
+	if (cpu == VMBUS_CONNECT_CPU)
-	    vmbus_connection.conn_state == CONNECTED)
 		return -EBUSY;
 
 	/*
@@ -277,9 +371,21 @@ int hv_synic_cleanup(unsigned int cpu)
 	}
 	mutex_unlock(&vmbus_connection.channel_mutex);
 
-	if (channel_found && vmbus_connection.conn_state == CONNECTED)
+	if (channel_found)
 		return -EBUSY;
 
+	/*
+	 * channel_found == false means that any channels that were previously
+	 * assigned to the CPU have been reassigned elsewhere with a call of
+	 * vmbus_send_modifychannel().  Scan the event flags page looking for
+	 * bits that are set and waiting with a timeout for vmbus_chan_sched()
+	 * to process such bits.  If bits are still set after this operation
+	 * and VMBus is connected, fail the CPU offlining operation.
+	 */
+	if (vmbus_proto_version >= VERSION_WIN10_V4_1 && hv_synic_event_pending())
+		return -EBUSY;
+
+always_cleanup:
 	hv_stimer_legacy_cleanup(cpu);
 
 	hv_synic_disable_regs(cpu);

drivers/hv/hv_balloon.c

@@ -21,6 +21,7 @@
 #include <linux/memory.h>
 #include <linux/notifier.h>
 #include <linux/percpu_counter.h>
+#include <linux/page_reporting.h>
 
 #include <linux/hyperv.h>
 #include <asm/hyperv-tlfs.h>
@@ -563,6 +564,8 @@ struct hv_dynmem_device {
 	 * The negotiated version agreed by host.
 	 */
 	__u32 version;
+
+	struct page_reporting_dev_info pr_dev_info;
 };
 
 static struct hv_dynmem_device dm_device;
@@ -1568,6 +1571,89 @@ static void balloon_onchannelcallback(void *context)
 
 }
 
+/* Hyper-V only supports reporting 2MB pages or higher */
+#define HV_MIN_PAGE_REPORTING_ORDER	9
+#define HV_MIN_PAGE_REPORTING_LEN (HV_HYP_PAGE_SIZE << HV_MIN_PAGE_REPORTING_ORDER)
+static int hv_free_page_report(struct page_reporting_dev_info *pr_dev_info,
+		    struct scatterlist *sgl, unsigned int nents)
+{
+	unsigned long flags;
+	struct hv_memory_hint *hint;
+	int i;
+	u64 status;
+	struct scatterlist *sg;
+
+	WARN_ON_ONCE(nents > HV_MEMORY_HINT_MAX_GPA_PAGE_RANGES);
+	WARN_ON_ONCE(sgl->length < HV_MIN_PAGE_REPORTING_LEN);
+	local_irq_save(flags);
+	hint = *(struct hv_memory_hint **)this_cpu_ptr(hyperv_pcpu_input_arg);
+	if (!hint) {
+		local_irq_restore(flags);
+		return -ENOSPC;
+	}
+
+	hint->type = HV_EXT_MEMORY_HEAT_HINT_TYPE_COLD_DISCARD;
+	hint->reserved = 0;
+	for_each_sg(sgl, sg, nents, i) {
+		union hv_gpa_page_range *range;
+
+		range = &hint->ranges[i];
+		range->address_space = 0;
+		/* page reporting only reports 2MB pages or higher */
+		range->page.largepage = 1;
+		range->page.additional_pages =
+			(sg->length / HV_MIN_PAGE_REPORTING_LEN) - 1;
+		range->page_size = HV_GPA_PAGE_RANGE_PAGE_SIZE_2MB;
+		range->base_large_pfn =
+			page_to_hvpfn(sg_page(sg)) >> HV_MIN_PAGE_REPORTING_ORDER;
+	}
+
+	status = hv_do_rep_hypercall(HV_EXT_CALL_MEMORY_HEAT_HINT, nents, 0,
+				     hint, NULL);
+	local_irq_restore(flags);
+	if ((status & HV_HYPERCALL_RESULT_MASK) != HV_STATUS_SUCCESS) {
+		pr_err("Cold memory discard hypercall failed with status %llx\n",
+			status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void enable_page_reporting(void)
+{
+	int ret;
+
+	/* Essentially, validating 'PAGE_REPORTING_MIN_ORDER' is big enough. */
+	if (pageblock_order < HV_MIN_PAGE_REPORTING_ORDER) {
+		pr_debug("Cold memory discard is only supported on 2MB pages and above\n");
+		return;
+	}
+
+	if (!hv_query_ext_cap(HV_EXT_CAPABILITY_MEMORY_COLD_DISCARD_HINT)) {
+		pr_debug("Cold memory discard hint not supported by Hyper-V\n");
+		return;
+	}
+
+	BUILD_BUG_ON(PAGE_REPORTING_CAPACITY > HV_MEMORY_HINT_MAX_GPA_PAGE_RANGES);
+	dm_device.pr_dev_info.report = hv_free_page_report;
+	ret = page_reporting_register(&dm_device.pr_dev_info);
+	if (ret < 0) {
+		dm_device.pr_dev_info.report = NULL;
+		pr_err("Failed to enable cold memory discard: %d\n", ret);
+	} else {
+		pr_info("Cold memory discard hint enabled\n");
+	}
+}
+
+static void disable_page_reporting(void)
+{
+	if (dm_device.pr_dev_info.report) {
+		page_reporting_unregister(&dm_device.pr_dev_info);
+		dm_device.pr_dev_info.report = NULL;
+	}
+}
+
 static int balloon_connect_vsp(struct hv_device *dev)
 {
 	struct dm_version_request version_req;
@@ -1713,6 +1799,7 @@ static int balloon_probe(struct hv_device *dev,
 	if (ret != 0)
 		return ret;
 
+	enable_page_reporting();
 	dm_device.state = DM_INITIALIZED;
 
 	dm_device.thread =
@@ -1727,6 +1814,7 @@ static int balloon_probe(struct hv_device *dev,
 probe_error:
 	dm_device.state = DM_INIT_ERROR;
 	dm_device.thread  = NULL;
+	disable_page_reporting();
 	vmbus_close(dev->channel);
 #ifdef CONFIG_MEMORY_HOTPLUG
 	unregister_memory_notifier(&hv_memory_nb);
@@ -1749,6 +1837,7 @@ static int balloon_remove(struct hv_device *dev)
 	cancel_work_sync(&dm->ha_wrk.wrk);
 
 	kthread_stop(dm->thread);
+	disable_page_reporting();
 	vmbus_close(dev->channel);
 #ifdef CONFIG_MEMORY_HOTPLUG
 	unregister_memory_notifier(&hv_memory_nb);

drivers/hv/hv_trace.h

@@ -103,6 +103,21 @@ TRACE_EVENT(vmbus_ongpadl_created,
 		    )
 	);
 
+TRACE_EVENT(vmbus_onmodifychannel_response,
+	    TP_PROTO(const struct vmbus_channel_modifychannel_response *response),
+	    TP_ARGS(response),
+	    TP_STRUCT__entry(
+		    __field(u32, child_relid)
+		    __field(u32, status)
+		    ),
+	    TP_fast_assign(__entry->child_relid = response->child_relid;
+			   __entry->status = response->status;
+		    ),
+	    TP_printk("child_relid 0x%x, status %d",
+		      __entry->child_relid,  __entry->status
+		    )
+	);
+
 TRACE_EVENT(vmbus_ongpadl_torndown,
 	    TP_PROTO(const struct vmbus_channel_gpadl_torndown *gpadltorndown),
 	    TP_ARGS(gpadltorndown),

drivers/hv/ring_buffer.c

@@ -84,15 +84,6 @@ hv_set_next_write_location(struct hv_ring_buffer_info *ring_info,
 	ring_info->ring_buffer->write_index = next_write_location;
 }
 
-/* Set the next read location for the specified ring buffer. */
-static inline void
-hv_set_next_read_location(struct hv_ring_buffer_info *ring_info,
-		    u32 next_read_location)
-{
-	ring_info->ring_buffer->read_index = next_read_location;
-	ring_info->priv_read_index = next_read_location;
-}
-
 /* Get the size of the ring buffer. */
 static inline u32
 hv_get_ring_buffersize(const struct hv_ring_buffer_info *ring_info)
@@ -313,7 +304,6 @@ int hv_ringbuffer_write(struct vmbus_channel *channel,
 		rqst_id = vmbus_next_request_id(&channel->requestor, requestid);
 		if (rqst_id == VMBUS_RQST_ERROR) {
 			spin_unlock_irqrestore(&outring_info->ring_lock, flags);
-			pr_err("No request id available\n");
 			return -EAGAIN;
 		}
 	}

drivers/hv/vmbus_drv.c

@@ -48,8 +48,10 @@ static int hyperv_cpuhp_online;
 
 static void *hv_panic_page;
 
+static long __percpu *vmbus_evt;
+
 /* Values parsed from ACPI DSDT */
-static int vmbus_irq;
+int vmbus_irq;
 int vmbus_interrupt;
 
 /*
@@ -1381,7 +1383,13 @@ static void vmbus_isr(void)
 			tasklet_schedule(&hv_cpu->msg_dpc);
 	}
 
-	add_interrupt_randomness(hv_get_vector(), 0);
+	add_interrupt_randomness(vmbus_interrupt, 0);
+}
+
+static irqreturn_t vmbus_percpu_isr(int irq, void *dev_id)
+{
+	vmbus_isr();
+	return IRQ_HANDLED;
 }
 
 /*
@@ -1392,22 +1400,36 @@ static void hv_kmsg_dump(struct kmsg_dumper *dumper,
 			 enum kmsg_dump_reason reason)
 {
 	size_t bytes_written;
-	phys_addr_t panic_pa;
 
 	/* We are only interested in panics. */
 	if ((reason != KMSG_DUMP_PANIC) || (!sysctl_record_panic_msg))
 		return;
 
-	panic_pa = virt_to_phys(hv_panic_page);
-
 	/*
 	 * Write dump contents to the page. No need to synchronize; panic should
 	 * be single-threaded.
 	 */
 	kmsg_dump_get_buffer(dumper, false, hv_panic_page, HV_HYP_PAGE_SIZE,
 			     &bytes_written);
-	if (bytes_written)
+	if (!bytes_written)
-		hyperv_report_panic_msg(panic_pa, bytes_written);
+		return;
+	/*
+	 * P3 to contain the physical address of the panic page & P4 to
+	 * contain the size of the panic data in that page. Rest of the
+	 * registers are no-op when the NOTIFY_MSG flag is set.
+	 */
+	hv_set_register(HV_REGISTER_CRASH_P0, 0);
+	hv_set_register(HV_REGISTER_CRASH_P1, 0);
+	hv_set_register(HV_REGISTER_CRASH_P2, 0);
+	hv_set_register(HV_REGISTER_CRASH_P3, virt_to_phys(hv_panic_page));
+	hv_set_register(HV_REGISTER_CRASH_P4, bytes_written);
+
+	/*
+	 * Let Hyper-V know there is crash data available along with
+	 * the panic message.
+	 */
+	hv_set_register(HV_REGISTER_CRASH_CTL,
+	       (HV_CRASH_CTL_CRASH_NOTIFY | HV_CRASH_CTL_CRASH_NOTIFY_MSG));
 }
 
 static struct kmsg_dumper hv_kmsg_dumper = {
@@ -1482,9 +1504,28 @@ static int vmbus_bus_init(void)
 	if (ret)
 		return ret;
 
-	ret = hv_setup_vmbus_irq(vmbus_irq, vmbus_isr);
+	/*
-	if (ret)
+	 * VMbus interrupts are best modeled as per-cpu interrupts. If
-		goto err_setup;
+	 * on an architecture with support for per-cpu IRQs (e.g. ARM64),
+	 * allocate a per-cpu IRQ using standard Linux kernel functionality.
+	 * If not on such an architecture (e.g., x86/x64), then rely on
+	 * code in the arch-specific portion of the code tree to connect
+	 * the VMbus interrupt handler.
+	 */
+
+	if (vmbus_irq == -1) {
+		hv_setup_vmbus_handler(vmbus_isr);
+	} else {
+		vmbus_evt = alloc_percpu(long);
+		ret = request_percpu_irq(vmbus_irq, vmbus_percpu_isr,
+				"Hyper-V VMbus", vmbus_evt);
+		if (ret) {
+			pr_err("Can't request Hyper-V VMbus IRQ %d, Err %d",
+					vmbus_irq, ret);
+			free_percpu(vmbus_evt);
+			goto err_setup;
+		}
+	}
 
 	ret = hv_synic_alloc();
 	if (ret)
@@ -1521,7 +1562,7 @@ static int vmbus_bus_init(void)
 		 * Register for panic kmsg callback only if the right
 		 * capability is supported by the hypervisor.
 		 */
-		hv_get_crash_ctl(hyperv_crash_ctl);
+		hyperv_crash_ctl = hv_get_register(HV_REGISTER_CRASH_CTL);
 		if (hyperv_crash_ctl & HV_CRASH_CTL_CRASH_NOTIFY_MSG)
 			hv_kmsg_dump_register();
 
@@ -1545,7 +1586,12 @@ err_connect:
 err_cpuhp:
 	hv_synic_free();
 err_alloc:
-	hv_remove_vmbus_irq();
+	if (vmbus_irq == -1) {
+		hv_remove_vmbus_handler();
+	} else {
+		free_percpu_irq(vmbus_irq, vmbus_evt);
+		free_percpu(vmbus_evt);
+	}
 err_setup:
 	bus_unregister(&hv_bus);
 	unregister_sysctl_table(hv_ctl_table_hdr);
@@ -1802,13 +1848,15 @@ static ssize_t target_cpu_store(struct vmbus_channel *channel,
 	if (target_cpu == origin_cpu)
 		goto cpu_store_unlock;
 
-	if (vmbus_send_modifychannel(channel->offermsg.child_relid,
+	if (vmbus_send_modifychannel(channel,
 				     hv_cpu_number_to_vp_number(target_cpu))) {
 		ret = -EIO;
 		goto cpu_store_unlock;
 	}
 
 	/*
+	 * For version before VERSION_WIN10_V5_3, the following warning holds:
+	 *
 	 * Warning.  At this point, there is *no* guarantee that the host will
 	 * have successfully processed the vmbus_send_modifychannel() request.
 	 * See the header comment of vmbus_send_modifychannel() for more info.
@@ -2663,6 +2711,18 @@ static int __init hv_acpi_init(void)
 		ret = -ETIMEDOUT;
 		goto cleanup;
 	}
+
+	/*
+	 * If we're on an architecture with a hardcoded hypervisor
+	 * vector (i.e. x86/x64), override the VMbus interrupt found
+	 * in the ACPI tables. Ensure vmbus_irq is not set since the
+	 * normal Linux IRQ mechanism is not used in this case.
+	 */
+#ifdef HYPERVISOR_CALLBACK_VECTOR
+	vmbus_interrupt = HYPERVISOR_CALLBACK_VECTOR;
+	vmbus_irq = -1;
+#endif
+
 	hv_debug_init();
 
 	ret = vmbus_bus_init();
@@ -2693,7 +2753,12 @@ static void __exit vmbus_exit(void)
 	vmbus_connection.conn_state = DISCONNECTED;
 	hv_stimer_global_cleanup();
 	vmbus_disconnect();
-	hv_remove_vmbus_irq();
+	if (vmbus_irq == -1) {
+		hv_remove_vmbus_handler();
+	} else {
+		free_percpu_irq(vmbus_irq, vmbus_evt);
+		free_percpu(vmbus_evt);
+	}
 	for_each_online_cpu(cpu) {
 		struct hv_per_cpu_context *hv_cpu
 			= per_cpu_ptr(hv_context.cpu_context, cpu);

drivers/pci/controller/pci-hyperv.c

@@ -1292,7 +1292,7 @@ exit_unlock:
 	 * resumes, hv_pci_restore_msi_state() is able to correctly restore
 	 * the interrupt with the correct affinity.
 	 */
-	if (res && hbus->state != hv_pcibus_removing)
+	if (!hv_result_success(res) && hbus->state != hv_pcibus_removing)
 		dev_err(&hbus->hdev->device,
 			"%s() failed: %#llx", __func__, res);
 

drivers/video/fbdev/hyperv_fb.c

@@ -308,7 +308,7 @@ static inline int synthvid_send(struct hv_device *hdev,
 			       VM_PKT_DATA_INBAND, 0);
 
 	if (ret)
-		pr_err("Unable to send packet via vmbus\n");
+		pr_err_ratelimited("Unable to send packet via vmbus; error %d\n", ret);
 
 	return ret;
 }

include/asm-generic/hyperv-tlfs.h

@@ -89,9 +89,9 @@
 #define HV_ACCESS_STATS				BIT(8)
 #define HV_DEBUGGING				BIT(11)
 #define HV_CPU_MANAGEMENT			BIT(12)
+#define HV_ENABLE_EXTENDED_HYPERCALLS		BIT(20)
 #define HV_ISOLATION				BIT(22)
 
-
 /*
  * TSC page layout.
  */
@@ -159,11 +159,18 @@ struct ms_hyperv_tsc_page {
 #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af
 #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0
 
+/* Extended hypercalls */
+#define HV_EXT_CALL_QUERY_CAPABILITIES		0x8001
+#define HV_EXT_CALL_MEMORY_HEAT_HINT		0x8003
+
 #define HV_FLUSH_ALL_PROCESSORS			BIT(0)
 #define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES	BIT(1)
 #define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY	BIT(2)
 #define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT	BIT(3)
 
+/* Extended capability bits */
+#define HV_EXT_CAPABILITY_MEMORY_COLD_DISCARD_HINT BIT(8)
+
 enum HV_GENERIC_SET_FORMAT {
 	HV_GENERIC_SET_SPARSE_4K,
 	HV_GENERIC_SET_ALL,
@@ -220,6 +227,41 @@ enum HV_GENERIC_SET_FORMAT {
 #define HV_MESSAGE_PAYLOAD_BYTE_COUNT	(240)
 #define HV_MESSAGE_PAYLOAD_QWORD_COUNT	(30)
 
+/*
+ * Define hypervisor message types. Some of the message types
+ * are x86/x64 specific, but there's no good way to separate
+ * them out into the arch-specific version of hyperv-tlfs.h
+ * because C doesn't provide a way to extend enum types.
+ * Keeping them all in the arch neutral hyperv-tlfs.h seems
+ * the least messy compromise.
+ */
+enum hv_message_type {
+	HVMSG_NONE			= 0x00000000,
+
+	/* Memory access messages. */
+	HVMSG_UNMAPPED_GPA		= 0x80000000,
+	HVMSG_GPA_INTERCEPT		= 0x80000001,
+
+	/* Timer notification messages. */
+	HVMSG_TIMER_EXPIRED		= 0x80000010,
+
+	/* Error messages. */
+	HVMSG_INVALID_VP_REGISTER_VALUE	= 0x80000020,
+	HVMSG_UNRECOVERABLE_EXCEPTION	= 0x80000021,
+	HVMSG_UNSUPPORTED_FEATURE	= 0x80000022,
+
+	/* Trace buffer complete messages. */
+	HVMSG_EVENTLOG_BUFFERCOMPLETE	= 0x80000040,
+
+	/* Platform-specific processor intercept messages. */
+	HVMSG_X64_IOPORT_INTERCEPT	= 0x80010000,
+	HVMSG_X64_MSR_INTERCEPT		= 0x80010001,
+	HVMSG_X64_CPUID_INTERCEPT	= 0x80010002,
+	HVMSG_X64_EXCEPTION_INTERCEPT	= 0x80010003,
+	HVMSG_X64_APIC_EOI		= 0x80010004,
+	HVMSG_X64_LEGACY_FP_ERROR	= 0x80010005
+};
+
 /* Define synthetic interrupt controller message flags. */
 union hv_message_flags {
 	__u8 asu8;
@@ -373,8 +415,10 @@ struct hv_guest_mapping_flush {
  *  by the bitwidth of "additional_pages" in union hv_gpa_page_range.
  */
 #define HV_MAX_FLUSH_PAGES (2048)
+#define HV_GPA_PAGE_RANGE_PAGE_SIZE_2MB		0
+#define HV_GPA_PAGE_RANGE_PAGE_SIZE_1GB		1
 
-/* HvFlushGuestPhysicalAddressList hypercall */
+/* HvFlushGuestPhysicalAddressList, HvExtCallMemoryHeatHint hypercall */
 union hv_gpa_page_range {
 	u64 address_space;
 	struct {
@@ -382,6 +426,12 @@ union hv_gpa_page_range {
 		u64 largepage:1;
 		u64 basepfn:52;
 	} page;
+	struct {
+		u64 reserved:12;
+		u64 page_size:1;
+		u64 reserved1:8;
+		u64 base_large_pfn:43;
+	};
 };
 
 /*
@@ -739,4 +789,20 @@ struct hv_input_unmap_device_interrupt {
 #define HV_SOURCE_SHADOW_NONE               0x0
 #define HV_SOURCE_SHADOW_BRIDGE_BUS_RANGE   0x1
 
+/*
+ * The whole argument should fit in a page to be able to pass to the hypervisor
+ * in one hypercall.
+ */
+#define HV_MEMORY_HINT_MAX_GPA_PAGE_RANGES  \
+	((HV_HYP_PAGE_SIZE - sizeof(struct hv_memory_hint)) / \
+		sizeof(union hv_gpa_page_range))
+
+/* HvExtCallMemoryHeatHint hypercall */
+#define HV_EXT_MEMORY_HEAT_HINT_TYPE_COLD_DISCARD	2
+struct hv_memory_hint {
+	u64 type:2;
+	u64 reserved:62;
+	union hv_gpa_page_range ranges[];
+} __packed;
+
 #endif

include/asm-generic/mshyperv.h

@@ -27,7 +27,7 @@
 
 struct ms_hyperv_info {
 	u32 features;
-	u32 features_b;
+	u32 priv_high;
 	u32 misc_features;
 	u32 hints;
 	u32 nested_features;
@@ -41,6 +41,53 @@ 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);
 
+/* Helper functions that provide a consistent pattern for checking Hyper-V hypercall status. */
+static inline int hv_result(u64 status)
+{
+	return status & HV_HYPERCALL_RESULT_MASK;
+}
+
+static inline bool hv_result_success(u64 status)
+{
+	return hv_result(status) == HV_STATUS_SUCCESS;
+}
+
+static inline unsigned int hv_repcomp(u64 status)
+{
+	/* Bits [43:32] of status have 'Reps completed' data. */
+	return (status & HV_HYPERCALL_REP_COMP_MASK) >>
+			 HV_HYPERCALL_REP_COMP_OFFSET;
+}
+
+/*
+ * Rep hypercalls. Callers of this functions are supposed to ensure that
+ * rep_count and varhead_size comply with Hyper-V hypercall definition.
+ */
+static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size,
+				      void *input, void *output)
+{
+	u64 control = code;
+	u64 status;
+	u16 rep_comp;
+
+	control |= (u64)varhead_size << HV_HYPERCALL_VARHEAD_OFFSET;
+	control |= (u64)rep_count << HV_HYPERCALL_REP_COMP_OFFSET;
+
+	do {
+		status = hv_do_hypercall(control, input, output);
+		if (!hv_result_success(status))
+			return status;
+
+		rep_comp = hv_repcomp(status);
+
+		control &= ~HV_HYPERCALL_REP_START_MASK;
+		control |= (u64)rep_comp << HV_HYPERCALL_REP_START_OFFSET;
+
+		touch_nmi_watchdog();
+	} while (rep_comp < rep_count);
+
+	return status;
+}
 
 /* Generate the guest OS identifier as described in the Hyper-V TLFS */
 static inline  __u64 generate_guest_id(__u64 d_info1, __u64 kernel_version,
@@ -56,7 +103,6 @@ static inline  __u64 generate_guest_id(__u64 d_info1, __u64 kernel_version,
 	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)
 {
@@ -88,14 +134,14 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
 		 * possibly deliver another msg from the
 		 * hypervisor
 		 */
-		hv_signal_eom();
+		hv_set_register(HV_REGISTER_EOM, 0);
 	}
 }
 
-int hv_setup_vmbus_irq(int irq, void (*handler)(void));
+void hv_setup_vmbus_handler(void (*handler)(void));
-void hv_remove_vmbus_irq(void);
+void hv_remove_vmbus_handler(void);
-void hv_enable_vmbus_irq(void);
+void hv_setup_stimer0_handler(void (*handler)(void));
-void hv_disable_vmbus_irq(void);
+void hv_remove_stimer0_handler(void);
 
 void hv_setup_kexec_handler(void (*handler)(void));
 void hv_remove_kexec_handler(void);
@@ -103,6 +149,7 @@ void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs));
 void hv_remove_crash_handler(void);
 
 extern int vmbus_interrupt;
+extern int vmbus_irq;
 
 #if IS_ENABLED(CONFIG_HYPERV)
 /*
@@ -117,6 +164,10 @@ extern u32 hv_max_vp_index;
 /* Sentinel value for an uninitialized entry in hv_vp_index array */
 #define VP_INVAL	U32_MAX
 
+void *hv_alloc_hyperv_page(void);
+void *hv_alloc_hyperv_zeroed_page(void);
+void hv_free_hyperv_page(unsigned long addr);
+
 /**
  * hv_cpu_number_to_vp_number() - Map CPU to VP.
  * @cpu_number: CPU number in Linux terms
@@ -169,21 +220,16 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset,
 }
 
 void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die);
-void hyperv_report_panic_msg(phys_addr_t pa, size_t size);
 bool hv_is_hyperv_initialized(void);
 bool hv_is_hibernation_supported(void);
 enum hv_isolation_type hv_get_isolation_type(void);
 bool hv_is_isolation_supported(void);
 void hyperv_cleanup(void);
+bool hv_query_ext_cap(u64 cap_query);
 #else /* CONFIG_HYPERV */
 static inline bool hv_is_hyperv_initialized(void) { return false; }
 static inline bool hv_is_hibernation_supported(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

include/clocksource/hyperv_timer.h

@@ -21,8 +21,7 @@
 #define HV_MIN_DELTA_TICKS 1
 
 /* Routines called by the VMbus driver */
-extern int hv_stimer_alloc(void);
+extern int hv_stimer_alloc(bool have_percpu_irqs);
-extern void hv_stimer_free(void);
 extern int hv_stimer_cleanup(unsigned int cpu);
 extern void hv_stimer_legacy_init(unsigned int cpu, int sint);
 extern void hv_stimer_legacy_cleanup(unsigned int cpu);

include/linux/hyperv.h

@@ -234,6 +234,7 @@ static inline u32 hv_get_avail_to_write_percent(
  * 5 . 0  (Newer Windows 10)
  * 5 . 1  (Windows 10 RS4)
  * 5 . 2  (Windows Server 2019, RS5)
+ * 5 . 3  (Windows Server 2022)
  */
 
 #define VERSION_WS2008  ((0 << 16) | (13))
@@ -245,6 +246,7 @@ static inline u32 hv_get_avail_to_write_percent(
 #define VERSION_WIN10_V5 ((5 << 16) | (0))
 #define VERSION_WIN10_V5_1 ((5 << 16) | (1))
 #define VERSION_WIN10_V5_2 ((5 << 16) | (2))
+#define VERSION_WIN10_V5_3 ((5 << 16) | (3))
 
 /* Make maximum size of pipe payload of 16K */
 #define MAX_PIPE_DATA_PAYLOAD		(sizeof(u8) * 16384)
@@ -284,7 +286,7 @@ struct vmbus_channel_offer {
 
 		/*
 		 * Pipes:
-		 * The following sructure is an integrated pipe protocol, which
+		 * The following structure is an integrated pipe protocol, which
 		 * is implemented on top of standard user-defined data. Pipe
 		 * clients have MAX_PIPE_USER_DEFINED_BYTES left for their own
 		 * use.
@@ -475,6 +477,7 @@ enum vmbus_channel_message_type {
 	CHANNELMSG_TL_CONNECT_REQUEST		= 21,
 	CHANNELMSG_MODIFYCHANNEL		= 22,
 	CHANNELMSG_TL_CONNECT_RESULT		= 23,
+	CHANNELMSG_MODIFYCHANNEL_RESPONSE	= 24,
 	CHANNELMSG_COUNT
 };
 
@@ -588,6 +591,13 @@ struct vmbus_channel_open_result {
 	u32 status;
 } __packed;
 
+/* Modify Channel Result parameters */
+struct vmbus_channel_modifychannel_response {
+	struct vmbus_channel_message_header header;
+	u32 child_relid;
+	u32 status;
+} __packed;
+
 /* Close channel parameters; */
 struct vmbus_channel_close_channel {
 	struct vmbus_channel_message_header header;
@@ -720,6 +730,7 @@ struct vmbus_channel_msginfo {
 		struct vmbus_channel_gpadl_torndown gpadl_torndown;
 		struct vmbus_channel_gpadl_created gpadl_created;
 		struct vmbus_channel_version_response version_response;
+		struct vmbus_channel_modifychannel_response modify_response;
 	} response;
 
 	u32 msgsize;
@@ -883,11 +894,11 @@ struct vmbus_channel {
 	 * Support for sub-channels. For high performance devices,
 	 * it will be useful to have multiple sub-channels to support
 	 * a scalable communication infrastructure with the host.
-	 * The support for sub-channels is implemented as an extention
+	 * The support for sub-channels is implemented as an extension
 	 * to the current infrastructure.
 	 * The initial offer is considered the primary channel and this
 	 * offer message will indicate if the host supports sub-channels.
-	 * The guest is free to ask for sub-channels to be offerred and can
+	 * The guest is free to ask for sub-channels to be offered and can
 	 * open these sub-channels as a normal "primary" channel. However,
 	 * all sub-channels will have the same type and instance guids as the
 	 * primary channel. Requests sent on a given channel will result in a
@@ -951,7 +962,7 @@ struct vmbus_channel {
 	 * Clearly, these optimizations improve throughput at the expense of
 	 * latency. Furthermore, since the channel is shared for both
 	 * control and data messages, control messages currently suffer
-	 * unnecessary latency adversley impacting performance and boot
+	 * unnecessary latency adversely impacting performance and boot
 	 * time. To fix this issue, permit tagging the channel as being
 	 * in "low latency" mode. In this mode, we will bypass the monitor
 	 * mechanism.
@@ -1594,7 +1605,7 @@ extern __u32 vmbus_proto_version;
 
 int vmbus_send_tl_connect_request(const guid_t *shv_guest_servie_id,
 				  const guid_t *shv_host_servie_id);
-int vmbus_send_modifychannel(u32 child_relid, u32 target_vp);
+int vmbus_send_modifychannel(struct vmbus_channel *channel, u32 target_vp);
 void vmbus_set_event(struct vmbus_channel *channel);
 
 /* Get the start of the ring buffer. */