Merge tag 'hyperv-next-signed-20230424' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull hyperv updates from Wei Liu:

 - PCI passthrough for Hyper-V confidential VMs (Michael Kelley)

 - Hyper-V VTL mode support (Saurabh Sengar)

 - Move panic report initialization code earlier (Long Li)

 - Various improvements and bug fixes (Dexuan Cui and Michael Kelley)

* tag 'hyperv-next-signed-20230424' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux: (22 commits)
  PCI: hv: Replace retarget_msi_interrupt_params with hyperv_pcpu_input_arg
  Drivers: hv: move panic report code from vmbus to hv early init code
  x86/hyperv: VTL support for Hyper-V
  Drivers: hv: Kconfig: Add HYPERV_VTL_MODE
  x86/hyperv: Make hv_get_nmi_reason public
  x86/hyperv: Add VTL specific structs and hypercalls
  x86/init: Make get/set_rtc_noop() public
  x86/hyperv: Exclude lazy TLB mode CPUs from enlightened TLB flushes
  x86/hyperv: Add callback filter to cpumask_to_vpset()
  Drivers: hv: vmbus: Remove the per-CPU post_msg_page
  clocksource: hyper-v: make sure Invariant-TSC is used if it is available
  PCI: hv: Enable PCI pass-thru devices in Confidential VMs
  Drivers: hv: Don't remap addresses that are above shared_gpa_boundary
  hv_netvsc: Remove second mapping of send and recv buffers
  Drivers: hv: vmbus: Remove second way of mapping ring buffers
  Drivers: hv: vmbus: Remove second mapping of VMBus monitor pages
  swiotlb: Remove bounce buffer remapping for Hyper-V
  Driver: VMBus: Add Devicetree support
  dt-bindings: bus: Add Hyper-V VMBus
  Drivers: hv: vmbus: Convert acpi_device to more generic platform_device
  ...

12 files changed, 614 insertions, 583 deletions

diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
index c0cef92b12b8..bcd9042a0c9f 100644
--- a/drivers/clocksource/hyperv_timer.c
+++ b/drivers/clocksource/hyperv_timer.c
@@ -49,7 +49,7 @@ static bool direct_mode_enabled;
 
 static int stimer0_irq = -1;
 static int stimer0_message_sint;
-static DEFINE_PER_CPU(long, stimer0_evt);
+static __maybe_unused DEFINE_PER_CPU(long, stimer0_evt);
 
 /*
  * Common code for stimer0 interrupts coming via Direct Mode or
@@ -68,7 +68,7 @@ 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)
+static irqreturn_t __maybe_unused hv_stimer0_percpu_isr(int irq, void *dev_id)
 {
 	hv_stimer0_isr();
 	return IRQ_HANDLED;
@@ -196,6 +196,7 @@ void __weak hv_remove_stimer0_handler(void)
 {
 };
 
+#ifdef CONFIG_ACPI
 /* Called only on architectures with per-cpu IRQs (i.e., not x86/x64) */
 static int hv_setup_stimer0_irq(void)
 {
@@ -230,6 +231,16 @@ static void hv_remove_stimer0_irq(void)
 		stimer0_irq = -1;
 	}
 }
+#else
+static int hv_setup_stimer0_irq(void)
+{
+	return 0;
+}
+
+static void hv_remove_stimer0_irq(void)
+{
+}
+#endif
 
 /* hv_stimer_alloc - Global initialization of the clockevent and stimer0 */
 int hv_stimer_alloc(bool have_percpu_irqs)
@@ -506,9 +517,6 @@ static bool __init hv_init_tsc_clocksource(void)
 {
 	union hv_reference_tsc_msr tsc_msr;
 
-	if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE))
-		return false;
-
 	/*
 	 * If Hyper-V offers TSC_INVARIANT, then the virtualized TSC correctly
 	 * handles frequency and offset changes due to live migration,
@@ -525,6 +533,9 @@ static bool __init hv_init_tsc_clocksource(void)
 		hyperv_cs_msr.rating = 250;
 	}
 
+	if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE))
+		return false;
+
 	hv_read_reference_counter = read_hv_clock_tsc;
 
 	/*
diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig
index 0747a8f1fcee..00242107d62e 100644
--- a/drivers/hv/Kconfig
+++ b/drivers/hv/Kconfig
@@ -4,15 +4,39 @@ menu "Microsoft Hyper-V guest support"
 
 config HYPERV
 	tristate "Microsoft Hyper-V client drivers"
-	depends on ACPI && ((X86 && X86_LOCAL_APIC && HYPERVISOR_GUEST) \
-		|| (ARM64 && !CPU_BIG_ENDIAN))
+	depends on (X86 && X86_LOCAL_APIC && HYPERVISOR_GUEST) \
+		|| (ACPI && ARM64 && !CPU_BIG_ENDIAN)
 	select PARAVIRT
 	select X86_HV_CALLBACK_VECTOR if X86
-	select VMAP_PFN
+	select OF_EARLY_FLATTREE if OF
 	help
 	  Select this option to run Linux as a Hyper-V client operating
 	  system.
 
+config HYPERV_VTL_MODE
+	bool "Enable Linux to boot in VTL context"
+	depends on X86_64 && HYPERV
+	default n
+	help
+	  Virtual Secure Mode (VSM) is a set of hypervisor capabilities and
+	  enlightenments offered to host and guest partitions which enables
+	  the creation and management of new security boundaries within
+	  operating system software.
+
+	  VSM achieves and maintains isolation through Virtual Trust Levels
+	  (VTLs). Virtual Trust Levels are hierarchical, with higher levels
+	  being more privileged than lower levels. VTL0 is the least privileged
+	  level, and currently only other level supported is VTL2.
+
+	  Select this option to build a Linux kernel to run at a VTL other than
+	  the normal VTL0, which currently is only VTL2.  This option
+	  initializes the x86 platform for VTL2, and adds the ability to boot
+	  secondary CPUs directly into 64-bit context as required for VTLs other
+	  than 0.  A kernel built with this option must run at VTL2, and will
+	  not run as a normal guest.
+
+	  If unsure, say N
+
 config HYPERV_TIMER
 	def_bool HYPERV && X86
 
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index cc23b90cae02..007f26d5f1a4 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -67,7 +67,7 @@ const struct vmbus_device vmbus_devs[] = {
 	{ .dev_type = HV_PCIE,
 	  HV_PCIE_GUID,
 	  .perf_device = false,
-	  .allowed_in_isolated = false,
+	  .allowed_in_isolated = true,
 	},
 
 	/* Synthetic Frame Buffer */
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index da51b50787df..5978e9dbc286 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -104,8 +104,14 @@ int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version)
 		vmbus_connection.msg_conn_id = VMBUS_MESSAGE_CONNECTION_ID;
 	}
 
-	msg->monitor_page1 = vmbus_connection.monitor_pages_pa[0];
-	msg->monitor_page2 = vmbus_connection.monitor_pages_pa[1];
+	/*
+	 * shared_gpa_boundary is zero in non-SNP VMs, so it's safe to always
+	 * bitwise OR it
+	 */
+	msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]) |
+				ms_hyperv.shared_gpa_boundary;
+	msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]) |
+				ms_hyperv.shared_gpa_boundary;
 
 	msg->target_vcpu = hv_cpu_number_to_vp_number(VMBUS_CONNECT_CPU);
 
@@ -219,72 +225,27 @@ int vmbus_connect(void)
 	 * Setup the monitor notification facility. The 1st page for
 	 * parent->child and the 2nd page for child->parent
 	 */
-	vmbus_connection.monitor_pages[0] = (void *)hv_alloc_hyperv_zeroed_page();
-	vmbus_connection.monitor_pages[1] = (void *)hv_alloc_hyperv_zeroed_page();
+	vmbus_connection.monitor_pages[0] = (void *)hv_alloc_hyperv_page();
+	vmbus_connection.monitor_pages[1] = (void *)hv_alloc_hyperv_page();
 	if ((vmbus_connection.monitor_pages[0] == NULL) ||
 	    (vmbus_connection.monitor_pages[1] == NULL)) {
 		ret = -ENOMEM;
 		goto cleanup;
 	}
 
-	vmbus_connection.monitor_pages_original[0]
-		= vmbus_connection.monitor_pages[0];
-	vmbus_connection.monitor_pages_original[1]
-		= vmbus_connection.monitor_pages[1];
-	vmbus_connection.monitor_pages_pa[0]
-		= virt_to_phys(vmbus_connection.monitor_pages[0]);
-	vmbus_connection.monitor_pages_pa[1]
-		= virt_to_phys(vmbus_connection.monitor_pages[1]);
-
-	if (hv_is_isolation_supported()) {
-		ret = set_memory_decrypted((unsigned long)
-					   vmbus_connection.monitor_pages[0],
-					   1);
-		ret |= set_memory_decrypted((unsigned long)
-					    vmbus_connection.monitor_pages[1],
-					    1);
-		if (ret)
-			goto cleanup;
-
-		/*
-		 * Isolation VM with AMD SNP needs to access monitor page via
-		 * address space above shared gpa boundary.
-		 */
-		if (hv_isolation_type_snp()) {
-			vmbus_connection.monitor_pages_pa[0] +=
-				ms_hyperv.shared_gpa_boundary;
-			vmbus_connection.monitor_pages_pa[1] +=
-				ms_hyperv.shared_gpa_boundary;
-
-			vmbus_connection.monitor_pages[0]
-				= memremap(vmbus_connection.monitor_pages_pa[0],
-					   HV_HYP_PAGE_SIZE,
-					   MEMREMAP_WB);
-			if (!vmbus_connection.monitor_pages[0]) {
-				ret = -ENOMEM;
-				goto cleanup;
-			}
-
-			vmbus_connection.monitor_pages[1]
-				= memremap(vmbus_connection.monitor_pages_pa[1],
-					   HV_HYP_PAGE_SIZE,
-					   MEMREMAP_WB);
-			if (!vmbus_connection.monitor_pages[1]) {
-				ret = -ENOMEM;
-				goto cleanup;
-			}
-		}
-
-		/*
-		 * Set memory host visibility hvcall smears memory
-		 * and so zero monitor pages here.
-		 */
-		memset(vmbus_connection.monitor_pages[0], 0x00,
-		       HV_HYP_PAGE_SIZE);
-		memset(vmbus_connection.monitor_pages[1], 0x00,
-		       HV_HYP_PAGE_SIZE);
+	ret = set_memory_decrypted((unsigned long)
+				vmbus_connection.monitor_pages[0], 1);
+	ret |= set_memory_decrypted((unsigned long)
+				vmbus_connection.monitor_pages[1], 1);
+	if (ret)
+		goto cleanup;
 
-	}
+	/*
+	 * Set_memory_decrypted() will change the memory contents if
+	 * decryption occurs, so zero monitor pages here.
+	 */
+	memset(vmbus_connection.monitor_pages[0], 0x00, HV_HYP_PAGE_SIZE);
+	memset(vmbus_connection.monitor_pages[1], 0x00, HV_HYP_PAGE_SIZE);
 
 	msginfo = kzalloc(sizeof(*msginfo) +
 			  sizeof(struct vmbus_channel_initiate_contact),
@@ -376,31 +337,13 @@ void vmbus_disconnect(void)
 		vmbus_connection.int_page = NULL;
 	}
 
-	if (hv_is_isolation_supported()) {
-		/*
-		 * memunmap() checks input address is ioremap address or not
-		 * inside. It doesn't unmap any thing in the non-SNP CVM and
-		 * so not check CVM type here.
-		 */
-		memunmap(vmbus_connection.monitor_pages[0]);
-		memunmap(vmbus_connection.monitor_pages[1]);
-
-		set_memory_encrypted((unsigned long)
-			vmbus_connection.monitor_pages_original[0],
-			1);
-		set_memory_encrypted((unsigned long)
-			vmbus_connection.monitor_pages_original[1],
-			1);
-	}
+	set_memory_encrypted((unsigned long)vmbus_connection.monitor_pages[0], 1);
+	set_memory_encrypted((unsigned long)vmbus_connection.monitor_pages[1], 1);
 
-	hv_free_hyperv_page((unsigned long)
-		vmbus_connection.monitor_pages_original[0]);
-	hv_free_hyperv_page((unsigned long)
-		vmbus_connection.monitor_pages_original[1]);
-	vmbus_connection.monitor_pages_original[0] =
-		vmbus_connection.monitor_pages[0] = NULL;
-	vmbus_connection.monitor_pages_original[1] =
-		vmbus_connection.monitor_pages[1] = NULL;
+	hv_free_hyperv_page((unsigned long)vmbus_connection.monitor_pages[0]);
+	hv_free_hyperv_page((unsigned long)vmbus_connection.monitor_pages[1]);
+	vmbus_connection.monitor_pages[0] = NULL;
+	vmbus_connection.monitor_pages[1] = NULL;
 }
 
 /*
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 8b0dd8e5244d..de6708dbe0df 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -39,42 +39,6 @@ int hv_init(void)
 }
 
 /*
- * 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.
  *
  * This involves a hypercall.
@@ -84,14 +48,15 @@ int hv_post_message(union hv_connection_id connection_id,
 		  void *payload, size_t payload_size)
 {
 	struct hv_input_post_message *aligned_msg;
-	struct hv_per_cpu_context *hv_cpu;
+	unsigned long flags;
 	u64 status;
 
 	if (payload_size > HV_MESSAGE_PAYLOAD_BYTE_COUNT)
 		return -EMSGSIZE;
 
-	hv_cpu = get_cpu_ptr(hv_context.cpu_context);
-	aligned_msg = hv_cpu->post_msg_page;
+	local_irq_save(flags);
+
+	aligned_msg = *this_cpu_ptr(hyperv_pcpu_input_arg);
 	aligned_msg->connectionid = connection_id;
 	aligned_msg->reserved = 0;
 	aligned_msg->message_type = message_type;
@@ -106,11 +71,7 @@ int hv_post_message(union hv_connection_id connection_id,
 		status = hv_do_hypercall(HVCALL_POST_MESSAGE,
 				aligned_msg, NULL);
 
-	/* Preemption must remain disabled until after the hypercall
-	 * so some other thread can't get scheduled onto this cpu and
-	 * corrupt the per-cpu post_msg_page
-	 */
-	put_cpu_ptr(hv_cpu);
+	local_irq_restore(flags);
 
 	return hv_result(status);
 }
@@ -162,12 +123,6 @@ int hv_synic_alloc(void)
 				goto err;
 			}
 		}
-
-		hv_cpu->post_msg_page = (void *)get_zeroed_page(GFP_ATOMIC);
-		if (hv_cpu->post_msg_page == NULL) {
-			pr_err("Unable to allocate post msg page\n");
-			goto err;
-		}
 	}
 
 	return 0;
@@ -190,7 +145,6 @@ void hv_synic_free(void)
 
 		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);
 	}
 
 	kfree(hv_context.hv_numa_map);
@@ -217,11 +171,13 @@ void hv_synic_enable_regs(unsigned int cpu)
 	simp.simp_enabled = 1;
 
 	if (hv_isolation_type_snp() || hv_root_partition) {
+		/* Mask out vTOM bit. ioremap_cache() maps decrypted */
+		u64 base = (simp.base_simp_gpa << HV_HYP_PAGE_SHIFT) &
+				~ms_hyperv.shared_gpa_boundary;
 		hv_cpu->synic_message_page
-			= memremap(simp.base_simp_gpa << HV_HYP_PAGE_SHIFT,
-				   HV_HYP_PAGE_SIZE, MEMREMAP_WB);
+			= (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE);
 		if (!hv_cpu->synic_message_page)
-			pr_err("Fail to map syinc message page.\n");
+			pr_err("Fail to map synic message page.\n");
 	} else {
 		simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page)
 			>> HV_HYP_PAGE_SHIFT;
@@ -234,12 +190,13 @@ void hv_synic_enable_regs(unsigned int cpu)
 	siefp.siefp_enabled = 1;
 
 	if (hv_isolation_type_snp() || hv_root_partition) {
-		hv_cpu->synic_event_page =
-			memremap(siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT,
-				 HV_HYP_PAGE_SIZE, MEMREMAP_WB);
-
+		/* Mask out vTOM bit. ioremap_cache() maps decrypted */
+		u64 base = (siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT) &
+				~ms_hyperv.shared_gpa_boundary;
+		hv_cpu->synic_event_page
+			= (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE);
 		if (!hv_cpu->synic_event_page)
-			pr_err("Fail to map syinc event page.\n");
+			pr_err("Fail to map synic event page.\n");
 	} else {
 		siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page)
 			>> HV_HYP_PAGE_SHIFT;
@@ -316,7 +273,7 @@ void hv_synic_disable_regs(unsigned int cpu)
 	 */
 	simp.simp_enabled = 0;
 	if (hv_isolation_type_snp() || hv_root_partition) {
-		memunmap(hv_cpu->synic_message_page);
+		iounmap(hv_cpu->synic_message_page);
 		hv_cpu->synic_message_page = NULL;
 	} else {
 		simp.base_simp_gpa = 0;
@@ -328,7 +285,7 @@ void hv_synic_disable_regs(unsigned int cpu)
 	siefp.siefp_enabled = 0;
 
 	if (hv_isolation_type_snp() || hv_root_partition) {
-		memunmap(hv_cpu->synic_event_page);
+		iounmap(hv_cpu->synic_event_page);
 		hv_cpu->synic_event_page = NULL;
 	} else {
 		siefp.base_siefp_gpa = 0;
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index 52a6f89ccdbd..64f9ceca887b 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -17,8 +17,11 @@
 #include <linux/export.h>
 #include <linux/bitfield.h>
 #include <linux/cpumask.h>
+#include <linux/sched/task_stack.h>
 #include <linux/panic_notifier.h>
 #include <linux/ptrace.h>
+#include <linux/kdebug.h>
+#include <linux/kmsg_dump.h>
 #include <linux/slab.h>
 #include <linux/dma-map-ops.h>
 #include <asm/hyperv-tlfs.h>
@@ -54,6 +57,10 @@ EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg);
 void * __percpu *hyperv_pcpu_output_arg;
 EXPORT_SYMBOL_GPL(hyperv_pcpu_output_arg);
 
+static void hv_kmsg_dump_unregister(void);
+
+static struct ctl_table_header *hv_ctl_table_hdr;
+
 /*
  * Hyper-V specific initialization and shutdown code that is
  * common across all architectures.  Called from architecture
@@ -62,6 +69,12 @@ EXPORT_SYMBOL_GPL(hyperv_pcpu_output_arg);
 
 void __init hv_common_free(void)
 {
+	unregister_sysctl_table(hv_ctl_table_hdr);
+	hv_ctl_table_hdr = NULL;
+
+	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE)
+		hv_kmsg_dump_unregister();
+
 	kfree(hv_vp_index);
 	hv_vp_index = NULL;
 
@@ -72,10 +85,203 @@ void __init hv_common_free(void)
 	hyperv_pcpu_input_arg = NULL;
 }
 
+/*
+ * 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);
+}
+EXPORT_SYMBOL_GPL(hv_alloc_hyperv_page);
+
+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);
+}
+EXPORT_SYMBOL_GPL(hv_alloc_hyperv_zeroed_page);
+
+void hv_free_hyperv_page(unsigned long addr)
+{
+	if (PAGE_SIZE == HV_HYP_PAGE_SIZE)
+		free_page(addr);
+	else
+		kfree((void *)addr);
+}
+EXPORT_SYMBOL_GPL(hv_free_hyperv_page);
+
+static void *hv_panic_page;
+
+/*
+ * Boolean to control whether to report panic messages over Hyper-V.
+ *
+ * It can be set via /proc/sys/kernel/hyperv_record_panic_msg
+ */
+static int sysctl_record_panic_msg = 1;
+
+/*
+ * sysctl option to allow the user to control whether kmsg data should be
+ * reported to Hyper-V on panic.
+ */
+static struct ctl_table hv_ctl_table[] = {
+	{
+		.procname	= "hyperv_record_panic_msg",
+		.data		= &sysctl_record_panic_msg,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE
+	},
+	{}
+};
+
+static int hv_die_panic_notify_crash(struct notifier_block *self,
+				     unsigned long val, void *args);
+
+static struct notifier_block hyperv_die_report_block = {
+	.notifier_call = hv_die_panic_notify_crash,
+};
+
+static struct notifier_block hyperv_panic_report_block = {
+	.notifier_call = hv_die_panic_notify_crash,
+};
+
+/*
+ * The following callback works both as die and panic notifier; its
+ * goal is to provide panic information to the hypervisor unless the
+ * kmsg dumper is used [see hv_kmsg_dump()], which provides more
+ * information but isn't always available.
+ *
+ * Notice that both the panic/die report notifiers are registered only
+ * if we have the capability HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE set.
+ */
+static int hv_die_panic_notify_crash(struct notifier_block *self,
+				     unsigned long val, void *args)
+{
+	struct pt_regs *regs;
+	bool is_die;
+
+	/* Don't notify Hyper-V unless we have a die oops event or panic. */
+	if (self == &hyperv_panic_report_block) {
+		is_die = false;
+		regs = current_pt_regs();
+	} else { /* die event */
+		if (val != DIE_OOPS)
+			return NOTIFY_DONE;
+
+		is_die = true;
+		regs = ((struct die_args *)args)->regs;
+	}
+
+	/*
+	 * Hyper-V should be notified only once about a panic/die. If we will
+	 * be calling hv_kmsg_dump() later with kmsg data, don't do the
+	 * notification here.
+	 */
+	if (!sysctl_record_panic_msg || !hv_panic_page)
+		hyperv_report_panic(regs, val, is_die);
+
+	return NOTIFY_DONE;
+}
+
+/*
+ * Callback from kmsg_dump. Grab as much as possible from the end of the kmsg
+ * buffer and call into Hyper-V to transfer the data.
+ */
+static void hv_kmsg_dump(struct kmsg_dumper *dumper,
+			 enum kmsg_dump_reason reason)
+{
+	struct kmsg_dump_iter iter;
+	size_t bytes_written;
+
+	/* We are only interested in panics. */
+	if (reason != KMSG_DUMP_PANIC || !sysctl_record_panic_msg)
+		return;
+
+	/*
+	 * Write dump contents to the page. No need to synchronize; panic should
+	 * be single-threaded.
+	 */
+	kmsg_dump_rewind(&iter);
+	kmsg_dump_get_buffer(&iter, false, hv_panic_page, HV_HYP_PAGE_SIZE,
+			     &bytes_written);
+	if (!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 = {
+	.dump = hv_kmsg_dump,
+};
+
+static void hv_kmsg_dump_unregister(void)
+{
+	kmsg_dump_unregister(&hv_kmsg_dumper);
+	unregister_die_notifier(&hyperv_die_report_block);
+	atomic_notifier_chain_unregister(&panic_notifier_list,
+					 &hyperv_panic_report_block);
+
+	hv_free_hyperv_page((unsigned long)hv_panic_page);
+	hv_panic_page = NULL;
+}
+
+static void hv_kmsg_dump_register(void)
+{
+	int ret;
+
+	hv_panic_page = hv_alloc_hyperv_zeroed_page();
+	if (!hv_panic_page) {
+		pr_err("Hyper-V: panic message page memory allocation failed\n");
+		return;
+	}
+
+	ret = kmsg_dump_register(&hv_kmsg_dumper);
+	if (ret) {
+		pr_err("Hyper-V: kmsg dump register error 0x%x\n", ret);
+		hv_free_hyperv_page((unsigned long)hv_panic_page);
+		hv_panic_page = NULL;
+	}
+}
+
 int __init hv_common_init(void)
 {
 	int i;
 
+	if (hv_is_isolation_supported())
+		sysctl_record_panic_msg = 0;
+
 	/*
 	 * Hyper-V expects to get crash register data or kmsg when
 	 * crash enlightment is available and system crashes. Set
@@ -84,8 +290,33 @@ int __init hv_common_init(void)
 	 * kernel.
 	 */
 	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
+		u64 hyperv_crash_ctl;
+
 		crash_kexec_post_notifiers = true;
 		pr_info("Hyper-V: enabling crash_kexec_post_notifiers\n");
+
+		/*
+		 * Panic message recording (sysctl_record_panic_msg)
+		 * is enabled by default in non-isolated guests and
+		 * disabled by default in isolated guests; the panic
+		 * message recording won't be available in isolated
+		 * guests should the following registration fail.
+		 */
+		hv_ctl_table_hdr = register_sysctl("kernel", hv_ctl_table);
+		if (!hv_ctl_table_hdr)
+			pr_err("Hyper-V: sysctl table register error");
+
+		/*
+		 * Register for panic kmsg callback only if the right
+		 * capability is supported by the hypervisor.
+		 */
+		hyperv_crash_ctl = hv_get_register(HV_REGISTER_CRASH_CTL);
+		if (hyperv_crash_ctl & HV_CRASH_CTL_CRASH_NOTIFY_MSG)
+			hv_kmsg_dump_register();
+
+		register_die_notifier(&hyperv_die_report_block);
+		atomic_notifier_chain_register(&panic_notifier_list,
+					       &hyperv_panic_report_block);
 	}
 
 	/*
@@ -311,14 +542,3 @@ u64 __weak hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_s
 	return HV_STATUS_INVALID_PARAMETER;
 }
 EXPORT_SYMBOL_GPL(hv_ghcb_hypercall);
-
-void __weak *hv_map_memory(void *addr, unsigned long size)
-{
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(hv_map_memory);
-
-void __weak hv_unmap_memory(void *addr)
-{
-}
-EXPORT_SYMBOL_GPL(hv_unmap_memory);
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index dc673edf053c..55f2086841ae 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -122,10 +122,6 @@ enum {
 struct hv_per_cpu_context {
 	void *synic_message_page;
 	void *synic_event_page;
-	/*
-	 * buffer to post messages to the host.
-	 */
-	void *post_msg_page;
 
 	/*
 	 * Starting with win8, we can take channel interrupts on any CPU;
@@ -241,8 +237,6 @@ struct vmbus_connection {
 	 * is child->parent notification
 	 */
 	struct hv_monitor_page *monitor_pages[2];
-	void *monitor_pages_original[2];
-	phys_addr_t monitor_pages_pa[2];
 	struct list_head chn_msg_list;
 	spinlock_t channelmsg_lock;
 
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 2111e97c3b63..3c9b02471760 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -186,8 +186,6 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info,
 		       struct page *pages, u32 page_cnt, u32 max_pkt_size)
 {
 	struct page **pages_wraparound;
-	unsigned long *pfns_wraparound;
-	u64 pfn;
 	int i;
 
 	BUILD_BUG_ON((sizeof(struct hv_ring_buffer) != PAGE_SIZE));
@@ -196,50 +194,30 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info,
 	 * First page holds struct hv_ring_buffer, do wraparound mapping for
 	 * the rest.
 	 */
-	if (hv_isolation_type_snp()) {
-		pfn = page_to_pfn(pages) +
-			PFN_DOWN(ms_hyperv.shared_gpa_boundary);
+	pages_wraparound = kcalloc(page_cnt * 2 - 1,
+				   sizeof(struct page *),
+				   GFP_KERNEL);
+	if (!pages_wraparound)
+		return -ENOMEM;
 
-		pfns_wraparound = kcalloc(page_cnt * 2 - 1,
-			sizeof(unsigned long), GFP_KERNEL);
-		if (!pfns_wraparound)
-			return -ENOMEM;
-
-		pfns_wraparound[0] = pfn;
-		for (i = 0; i < 2 * (page_cnt - 1); i++)
-			pfns_wraparound[i + 1] = pfn + i % (page_cnt - 1) + 1;
-
-		ring_info->ring_buffer = (struct hv_ring_buffer *)
-			vmap_pfn(pfns_wraparound, page_cnt * 2 - 1,
-				 pgprot_decrypted(PAGE_KERNEL));
-		kfree(pfns_wraparound);
-
-		if (!ring_info->ring_buffer)
-			return -ENOMEM;
-
-		/* Zero ring buffer after setting memory host visibility. */
-		memset(ring_info->ring_buffer, 0x00, PAGE_SIZE * page_cnt);
-	} else {
-		pages_wraparound = kcalloc(page_cnt * 2 - 1,
-					   sizeof(struct page *),
-					   GFP_KERNEL);
-		if (!pages_wraparound)
-			return -ENOMEM;
-
-		pages_wraparound[0] = pages;
-		for (i = 0; i < 2 * (page_cnt - 1); i++)
-			pages_wraparound[i + 1] =
-				&pages[i % (page_cnt - 1) + 1];
+	pages_wraparound[0] = pages;
+	for (i = 0; i < 2 * (page_cnt - 1); i++)
+		pages_wraparound[i + 1] =
+			&pages[i % (page_cnt - 1) + 1];
 
-		ring_info->ring_buffer = (struct hv_ring_buffer *)
-			vmap(pages_wraparound, page_cnt * 2 - 1, VM_MAP,
-				PAGE_KERNEL);
+	ring_info->ring_buffer = (struct hv_ring_buffer *)
+		vmap(pages_wraparound, page_cnt * 2 - 1, VM_MAP,
+			pgprot_decrypted(PAGE_KERNEL));
 
-		kfree(pages_wraparound);
-		if (!ring_info->ring_buffer)
-			return -ENOMEM;
-	}
+	kfree(pages_wraparound);
+	if (!ring_info->ring_buffer)
+		return -ENOMEM;
 
+	/*
+	 * Ensure the header page is zero'ed since
+	 * encryption status may have changed.
+	 */
+	memset(ring_info->ring_buffer, 0, HV_HYP_PAGE_SIZE);
 
 	ring_info->ring_buffer->read_index =
 		ring_info->ring_buffer->write_index = 0;
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 734fff86c8dc..1c65a6dfb9fa 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/device.h>
+#include <linux/platform_device.h>
 #include <linux/interrupt.h>
 #include <linux/sysctl.h>
 #include <linux/slab.h>
@@ -19,6 +20,7 @@
 #include <linux/completion.h>
 #include <linux/hyperv.h>
 #include <linux/kernel_stat.h>
+#include <linux/of_address.h>
 #include <linux/clockchips.h>
 #include <linux/cpu.h>
 #include <linux/sched/isolation.h>
@@ -28,7 +30,6 @@
 #include <linux/panic_notifier.h>
 #include <linux/ptrace.h>
 #include <linux/screen_info.h>
-#include <linux/kdebug.h>
 #include <linux/efi.h>
 #include <linux/random.h>
 #include <linux/kernel.h>
@@ -44,12 +45,10 @@ struct vmbus_dynid {
 	struct hv_vmbus_device_id id;
 };
 
-static struct acpi_device  *hv_acpi_dev;
+static struct device  *hv_dev;
 
 static int hyperv_cpuhp_online;
 
-static void *hv_panic_page;
-
 static long __percpu *vmbus_evt;
 
 /* Values parsed from ACPI DSDT */
@@ -57,18 +56,6 @@ int vmbus_irq;
 int vmbus_interrupt;
 
 /*
- * Boolean to control whether to report panic messages over Hyper-V.
- *
- * It can be set via /proc/sys/kernel/hyperv_record_panic_msg
- */
-static int sysctl_record_panic_msg = 1;
-
-static int hyperv_report_reg(void)
-{
-	return !sysctl_record_panic_msg || !hv_panic_page;
-}
-
-/*
  * The panic notifier below is responsible solely for unloading the
  * vmbus connection, which is necessary in a panic event.
  *
@@ -88,54 +75,6 @@ static struct notifier_block hyperv_panic_vmbus_unload_block = {
 	.priority	= INT_MIN + 1, /* almost the latest one to execute */
 };
 
-static int hv_die_panic_notify_crash(struct notifier_block *self,
-				     unsigned long val, void *args);
-
-static struct notifier_block hyperv_die_report_block = {
-	.notifier_call = hv_die_panic_notify_crash,
-};
-static struct notifier_block hyperv_panic_report_block = {
-	.notifier_call = hv_die_panic_notify_crash,
-};
-
-/*
- * The following callback works both as die and panic notifier; its
- * goal is to provide panic information to the hypervisor unless the
- * kmsg dumper is used [see hv_kmsg_dump()], which provides more
- * information but isn't always available.
- *
- * Notice that both the panic/die report notifiers are registered only
- * if we have the capability HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE set.
- */
-static int hv_die_panic_notify_crash(struct notifier_block *self,
-				     unsigned long val, void *args)
-{
-	struct pt_regs *regs;
-	bool is_die;
-
-	/* Don't notify Hyper-V unless we have a die oops event or panic. */
-	if (self == &hyperv_panic_report_block) {
-		is_die = false;
-		regs = current_pt_regs();
-	} else { /* die event */
-		if (val != DIE_OOPS)
-			return NOTIFY_DONE;
-
-		is_die = true;
-		regs = ((struct die_args *)args)->regs;
-	}
-
-	/*