Hyper-V: praravirtualized remote TLB flushing and hypercall improvements

index fba1007..91acec7 100644
@@ -175,7 +175,15 @@ void hyperv_init(void);
 void hyperv_report_panic(struct pt_regs *regs);
 bool hv_is_hypercall_page_setup(void);
 void hyperv_cleanup(void);
-#endif
+#else /* CONFIG_HYPERV */
+static inline void hyperv_init(void) {}
+static inline bool hv_is_hypercall_page_setup(void)
+{
+	return false;
+}
+static inline hyperv_cleanup(void) {}
+#endif /* CONFIG_HYPERV */
+
 #ifdef CONFIG_HYPERV_TSCPAGE
 struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
 static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)

index 91acec7..d42b6eb 100644
@@ -29,6 +29,8 @@ struct ms_hyperv_info {
 	u32 features;
 	u32 misc_features;
 	u32 hints;
+	u32 max_vp_index;
+	u32 max_lp_index;
 };
 
 extern struct ms_hyperv_info ms_hyperv;

index 04cb8d3..a8b4765 100644
@@ -175,9 +175,16 @@ static void __init ms_hyperv_init_platform(void)
 	ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES);
 	ms_hyperv.hints    = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
 
-	pr_info("HyperV: features 0x%x, hints 0x%x\n",
+	pr_info("Hyper-V: features 0x%x, hints 0x%x\n",
 		ms_hyperv.features, ms_hyperv.hints);
 
+	ms_hyperv.max_vp_index = cpuid_eax(HVCPUID_IMPLEMENTATION_LIMITS);
+	ms_hyperv.max_lp_index = cpuid_ebx(HVCPUID_IMPLEMENTATION_LIMITS);
+
+	pr_info("Hyper-V: max %d virtual processors, %d logical processors\n",
+		ms_hyperv.max_vp_index, ms_hyperv.max_lp_index);
+
+
 	/*
 	 * Extract host information.
 	 */

@@ -203,7 +210,7 @@ static void __init ms_hyperv_init_platform(void)
 		rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency);
 		hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ);
 		lapic_timer_frequency = hv_lapic_frequency;
-		pr_info("HyperV: LAPIC Timer Frequency: %#x\n",
+		pr_info("Hyper-V: LAPIC Timer Frequency: %#x\n",
 			lapic_timer_frequency);
 	}
 

@@ -237,7 +244,7 @@ static void __init ms_hyperv_init_platform(void)
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
-	.name			= "Microsoft HyperV",
+	.name			= "Microsoft Hyper-V",
 	.detect			= ms_hyperv_platform,
 	.init_platform		= ms_hyperv_init_platform,
 };

index 5b882cc..691603e 100644
@@ -75,7 +75,8 @@ static struct clocksource hyperv_cs_msr = {
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static void *hypercall_pg;
+void *hv_hypercall_pg;
+EXPORT_SYMBOL_GPL(hv_hypercall_pg);
 struct clocksource *hyperv_cs;
 EXPORT_SYMBOL_GPL(hyperv_cs);
 

@@ -102,15 +103,15 @@ void hyperv_init(void)
 	guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0);
 	wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id);
 
-	hypercall_pg  = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_RX);
-	if (hypercall_pg == NULL) {
+	hv_hypercall_pg  = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_RX);
+	if (hv_hypercall_pg == NULL) {
 		wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
 		return;
 	}
 
 	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 	hypercall_msr.enable = 1;
-	hypercall_msr.guest_physical_address = vmalloc_to_pfn(hypercall_pg);
+	hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
 	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 
 	/*

@@ -170,51 +171,6 @@ void hyperv_cleanup(void)
 }
 EXPORT_SYMBOL_GPL(hyperv_cleanup);
 
-/*
- * hv_do_hypercall- Invoke the specified hypercall
- */
-u64 hv_do_hypercall(u64 control, void *input, void *output)
-{
-	u64 input_address = (input) ? virt_to_phys(input) : 0;
-	u64 output_address = (output) ? virt_to_phys(output) : 0;
-#ifdef CONFIG_X86_64
-	u64 hv_status = 0;
-
-	if (!hypercall_pg)
-		return (u64)ULLONG_MAX;
-
-	__asm__ __volatile__("mov %0, %%r8" : : "r" (output_address) : "r8");
-	__asm__ __volatile__("call *%3" : "=a" (hv_status) :
-			     "c" (control), "d" (input_address),
-			     "m" (hypercall_pg));
-
-	return hv_status;
-
-#else
-
-	u32 control_hi = control >> 32;
-	u32 control_lo = control & 0xFFFFFFFF;
-	u32 hv_status_hi = 1;
-	u32 hv_status_lo = 1;
-	u32 input_address_hi = input_address >> 32;
-	u32 input_address_lo = input_address & 0xFFFFFFFF;
-	u32 output_address_hi = output_address >> 32;
-	u32 output_address_lo = output_address & 0xFFFFFFFF;
-
-	if (!hypercall_pg)
-		return (u64)ULLONG_MAX;
-
-	__asm__ __volatile__ ("call *%8" : "=d"(hv_status_hi),
-			      "=a"(hv_status_lo) : "d" (control_hi),
-			      "a" (control_lo), "b" (input_address_hi),
-			      "c" (input_address_lo), "D"(output_address_hi),
-			      "S"(output_address_lo), "m" (hypercall_pg));
-
-	return hv_status_lo | ((u64)hv_status_hi << 32);
-#endif /* !x86_64 */
-}
-EXPORT_SYMBOL_GPL(hv_do_hypercall);
-
 void hyperv_report_panic(struct pt_regs *regs)
 {
 	static bool panic_reported;

50 lines not on this page · raw message

index c2d74ee..4a0a9f6 100644
@@ -32,6 +32,8 @@
 #include <linux/hyperv.h>
 #include <linux/export.h>
 #include <asm/hyperv.h>
+#include <asm/mshyperv.h>
+
 #include "hyperv_vmbus.h"
 
 

index e09fc82..d1ae02d 100644
@@ -1188,7 +1188,6 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj,
 			bool fb_overlap_ok);
 void vmbus_free_mmio(resource_size_t start, resource_size_t size);
 int vmbus_cpu_number_to_vp_number(int cpu_number);
-u64 hv_do_hypercall(u64 control, void *input, void *output);
 
 /*
  * GUID definitions of various offer types - services offered to the guest.

index cbbf7db..52b3611 100644
@@ -217,6 +217,47 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 #endif /* !x86_64 */
 }
 
+/* Fast hypercall with 8 bytes of input and no output */
+static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
+{
+	union hv_hypercall_input control = {0};
+	register void *__sp asm(_ASM_SP);
+
+	control.code = code;
+	control.fast = 1;
+#ifdef CONFIG_X86_64
+	{
+		u64 hv_status;
+
+		__asm__ __volatile__("call *%4"
+				     : "=a" (hv_status), "+r" (__sp),
+				       "+c" (control.as_uint64), "+d" (input1)
+				     : "m" (hv_hypercall_pg)
+				     : "cc", "r8", "r9", "r10", "r11");
+		return hv_status;
+	}
+#else
+	{
+		u32 hv_status_hi, hv_status_lo;
+		u32 input1_hi = (u32)(input1 >> 32);
+		u32 input1_lo = (u32)input1;
+
+		__asm__ __volatile__ ("call *%7"
+				      : "=d"(hv_status_hi),
+					"=a"(hv_status_lo),
+					"+c"(input1_lo),
+					"+r"(__sp)
+				      :	"d" (control.as_uint32_hi),
+					"a" (control.as_uint32_lo),
+					"b" (input1_hi),
+					"m" (hv_hypercall_pg)
+				      : "cc", "edi", "esi");
+
+		return hv_status_lo | ((u64)hv_status_hi << 32);
+	}
+#endif
+}
+
 void hyperv_init(void);
 void hyperv_report_panic(struct pt_regs *regs);
 bool hv_is_hypercall_page_setup(void);

index 432df4b..c87e900 100644
@@ -256,6 +256,25 @@
 #define HV_PROCESSOR_POWER_STATE_C2		2
 #define HV_PROCESSOR_POWER_STATE_C3		3
 
+/* Hypercall interface */
+union hv_hypercall_input {
+	u64 as_uint64;
+	struct {
+		__u32 as_uint32_lo;
+		__u32 as_uint32_hi;
+	};
+	struct {
+		__u64 code:16;
+		__u64 fast:1;
+		__u64 varhead_size:10;
+		__u64 reserved1:5;
+		__u64 rep_count:12;
+		__u64 reserved2:4;
+		__u64 rep_start:12;
+		__u64 reserved3:4;
+	};
+};
+
 /* hypercall status code */
 #define HV_STATUS_SUCCESS			0
 #define HV_STATUS_INVALID_HYPERCALL_CODE	2

index 0fabd41..ee2a8dd 100644
@@ -806,20 +806,15 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
 	/*
 	 * Setup state for signalling the host.
 	 */
-	newchannel->sig_event = (struct hv_input_signal_event *)
-				(ALIGN((unsigned long)
-				&newchannel->sig_buf,
-				HV_HYPERCALL_PARAM_ALIGN));
-
-	newchannel->sig_event->connectionid.asu32 = 0;
-	newchannel->sig_event->connectionid.u.id = VMBUS_EVENT_CONNECTION_ID;
-	newchannel->sig_event->flag_number = 0;
-	newchannel->sig_event->rsvdz = 0;
+	newchannel->sig_event.connectionid.asu32 = 0;
+	newchannel->sig_event.connectionid.u.id = VMBUS_EVENT_CONNECTION_ID;
+	newchannel->sig_event.flag_number = 0;
+	newchannel->sig_event.rsvdz = 0;
 
 	if (vmbus_proto_version != VERSION_WS2008) {
 		newchannel->is_dedicated_interrupt =
 				(offer->is_dedicated_interrupt != 0);
-		newchannel->sig_event->connectionid.u.id =
+		newchannel->sig_event.connectionid.u.id =
 				offer->connection_id;
 	}
 

index 4a0a9f6..51f8cb2 100644
@@ -408,6 +408,7 @@ void vmbus_set_event(struct vmbus_channel *channel)
 	if (!channel->is_dedicated_interrupt)
 		vmbus_send_interrupt(child_relid);
 
-	hv_do_hypercall(HVCALL_SIGNAL_EVENT, channel->sig_event, NULL);
+	hv_do_fast_hypercall8(HVCALL_SIGNAL_EVENT,
+			      channel->sig_event.as_uint64);
 }
 EXPORT_SYMBOL_GPL(vmbus_set_event);

index d1ae02d..68a5772 100644
@@ -678,15 +678,13 @@ union hv_connection_id {
 };
 
 /* Definition of the hv_signal_event hypercall input structure. */
-struct hv_input_signal_event {
-	union hv_connection_id connectionid;
-	u16 flag_number;
-	u16 rsvdz;
-};
-
-struct hv_input_signal_event_buffer {
-	u64 align8;
-	struct hv_input_signal_event event;
+union hv_input_signal_event {
+	u64 as_uint64;
+	struct {
+		union hv_connection_id connectionid;
+		u16 flag_number;
+		u16 rsvdz;
+	};
 };
 
 enum hv_numa_policy {

@@ -771,8 +769,7 @@ struct vmbus_channel {
 	} callback_mode;
 
 	bool is_dedicated_interrupt;
-	struct hv_input_signal_event_buffer sig_buf;
-	struct hv_input_signal_event *sig_event;
+	union hv_input_signal_event sig_event;
 
 	/*
 	 * Starting with win8, this field will be used to specify

index 52b3611..e0b4c70 100644
@@ -4,6 +4,7 @@
 #include <linux/types.h>
 #include <linux/interrupt.h>
 #include <linux/clocksource.h>
+#include <linux/nmi.h>
 #include <asm/hyperv.h>
 
 /*

@@ -258,6 +259,31 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
 #endif
 }
 
+/*
+ * Rep hypercalls. Callers of this functions are supposed to ensure that
+ * rep_count and vahead_size comply with union hv_hypercall_input definition.
+ */
+static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size,
+				      void *input, void *output)
+{
+	union hv_hypercall_input hc_input = { .code = code,
+					      .varhead_size = varhead_size,
+					      .rep_count = rep_count};
+	u64 status;
+
+	do {
+		status = hv_do_hypercall(hc_input.as_uint64, input, output);
+		if ((status & 0xffff) != HV_STATUS_SUCCESS)
+			return status;
+
+		hc_input.rep_start = (status >> 32) & 0xfff;
+
+		touch_nmi_watchdog();
+	} while (hc_input.rep_start < hc_input.rep_count);
+
+	return status;
+}
+
 void hyperv_init(void);
 void hyperv_report_panic(struct pt_regs *regs);
 bool hv_is_hypercall_page_setup(void);

index 691603e..7fd9cd3 100644
@@ -26,6 +26,8 @@
 #include <linux/mm.h>
 #include <linux/clockchips.h>
 #include <linux/hyperv.h>
+#include <linux/slab.h>
+#include <linux/cpuhotplug.h>
 
 #ifdef CONFIG_HYPERV_TSCPAGE
 

@@ -80,6 +82,20 @@ EXPORT_SYMBOL_GPL(hv_hypercall_pg);
 struct clocksource *hyperv_cs;
 EXPORT_SYMBOL_GPL(hyperv_cs);
 
+u32 *hv_vp_index;
+EXPORT_SYMBOL_GPL(hv_vp_index);
+
+static int hv_cpu_init(unsigned int cpu)
+{
+	u64 msr_vp_index;
+
+	hv_get_vp_index(msr_vp_index);
+
+	hv_vp_index[smp_processor_id()] = (u32)msr_vp_index;
+
+	return 0;
+}
+
 /*
  * This function is to be invoked early in the boot sequence after the
  * hypervisor has been detected.

@@ -95,6 +111,16 @@ void hyperv_init(void)
 	if (x86_hyper != &x86_hyper_ms_hyperv)
 		return;
 
+	/* Allocate percpu VP index */
+	hv_vp_index = kcalloc(num_possible_cpus(), sizeof(*hv_vp_index),
+			      GFP_KERNEL);
+	if (!hv_vp_index)
+		return;
+
+	if (cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online",
+			      hv_cpu_init, NULL) < 0)
+		goto free_vp_index;
+
 	/*
 	 * Setup the hypercall page and enable hypercalls.
 	 * 1. Register the guest ID

@@ -106,7 +132,7 @@ void hyperv_init(void)
 	hv_hypercall_pg  = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_RX);
 	if (hv_hypercall_pg == NULL) {
 		wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
-		return;
+		goto free_vp_index;
 	}
 
 	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);

@@ -149,6 +175,12 @@ void hyperv_init(void)
 	hyperv_cs = &hyperv_cs_msr;
 	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
 		clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
+
+	return;
+
+free_vp_index:
+	kfree(hv_vp_index);
+	hv_vp_index = NULL;
 }
 
 /*

index e0b4c70..cdf2391 100644
@@ -284,6 +284,32 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size,
 	return status;
 }
 
+/*
+ * Hypervisor's notion of virtual processor ID is different from
+ * Linux' notion of CPU ID. This information can only be retrieved
+ * in the context of the calling CPU. Setup a map for easy access
+ * to this information.
+ */
+extern u32 __percpu *hv_vp_index;
+
+/**
+ * hv_cpu_number_to_vp_number() - Map CPU to VP.
+ * @cpu_number: CPU number in Linux terms
+ *
+ * This function returns the mapping between the Linux processor
+ * number and the hypervisor's virtual processor number, useful
+ * in making hypercalls and such that talk about specific
+ * processors.
+ *
+ * Return: Virtual processor number in Hyper-V terms
+ */
+static inline int hv_cpu_number_to_vp_number(int cpu_number)
+{
+	WARN_ON(hv_vp_index[cpu_number] == -1);
+
+	return hv_vp_index[cpu_number];
+}
+
 void hyperv_init(void);
 void hyperv_report_panic(struct pt_regs *regs);
 bool hv_is_hypercall_page_setup(void);

index ee2a8dd..a3e4dba 100644
@@ -600,7 +600,7 @@ static void init_vp_index(struct vmbus_channel *channel, u16 dev_type)
 		 */
 		channel->numa_node = 0;
 		channel->target_cpu = 0;
-		channel->target_vp = hv_context.vp_index[0];
+		channel->target_vp = hv_cpu_number_to_vp_number(0);
 		return;
 	}
 

@@ -684,7 +684,7 @@ static void init_vp_index(struct vmbus_channel *channel, u16 dev_type)
 	}
 
 	channel->target_cpu = cur_cpu;
-	channel->target_vp = hv_context.vp_index[cur_cpu];
+	channel->target_vp = hv_cpu_number_to_vp_number(cur_cpu);
 }
 
 static void vmbus_wait_for_unload(void)

@@ -1224,8 +1224,7 @@ struct vmbus_channel *vmbus_get_outgoing_channel(struct vmbus_channel *primary)
 		return outgoing_channel;
 	}
 
-	cur_cpu = hv_context.vp_index[get_cpu()];
-	put_cpu();
+	cur_cpu = hv_cpu_number_to_vp_number(smp_processor_id());
 	list_for_each_safe(cur, tmp, &primary->sc_list) {
 		cur_channel = list_entry(cur, struct vmbus_channel, sc_list);
 		if (cur_channel->state != CHANNEL_OPENED_STATE)

index 51f8cb2..34b7d55 100644
@@ -96,7 +96,8 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
 	 * the CPU attempting to connect may not be CPU 0.
 	 */
 	if (version >= VERSION_WIN8_1) {
-		msg->target_vcpu = hv_context.vp_index[smp_processor_id()];
+		msg->target_vcpu =
+			hv_cpu_number_to_vp_number(smp_processor_id());
 		vmbus_connection.connect_cpu = smp_processor_id();
 	} else {
 		msg->target_vcpu = 0;

index 12e7bae..7e67ef4 100644
@@ -229,7 +229,6 @@ int hv_synic_init(unsigned int cpu)
 	union hv_synic_siefp siefp;
 	union hv_synic_sint shared_sint;
 	union hv_synic_scontrol sctrl;
-	u64 vp_index;
 
 	/* Setup the Synic's message page */
 	hv_get_simp(simp.as_uint64);

@@ -271,14 +270,6 @@ int hv_synic_init(unsigned int cpu)
 	hv_context.synic_initialized = true;
 
 	/*
-	 * Setup the mapping between Hyper-V's notion
-	 * of cpuid and Linux' notion of cpuid.
-	 * This array will be indexed using Linux cpuid.
-	 */
-	hv_get_vp_index(vp_index);
-	hv_context.vp_index[cpu] = (u32)vp_index;
-
-	/*
 	 * Register the per-cpu clockevent source.
 	 */
 	if (ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE)

index 1b6a5e0..49569f8 100644
@@ -229,17 +229,6 @@ struct hv_context {
 	struct hv_per_cpu_context __percpu *cpu_context;
 
 	/*
-	 * Hypervisor's notion of virtual processor ID is different from
-	 * Linux' notion of CPU ID. This information can only be retrieved
-	 * in the context of the calling CPU. Setup a map for easy access
-	 * to this information:
-	 *
-	 * vp_index[a] is the Hyper-V's processor ID corresponding to
-	 * Linux cpuid 'a'.
-	 */
-	u32 vp_index[NR_CPUS];
-
-	/*
 	 * To manage allocations in a NUMA node.
 	 * Array indexed by numa node ID.
 	 */

index 59bb3ef..b37f4bb 100644
@@ -1482,23 +1482,6 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size)
 }
 EXPORT_SYMBOL_GPL(vmbus_free_mmio);
 
-/**
- * vmbus_cpu_number_to_vp_number() - Map CPU to VP.
- * @cpu_number: CPU number in Linux terms
- *
- * This function returns the mapping between the Linux processor
- * number and the hypervisor's virtual processor number, useful
- * in making hypercalls and such that talk about specific
- * processors.
- *
- * Return: Virtual processor number in Hyper-V terms
- */
-int vmbus_cpu_number_to_vp_number(int cpu_number)
-{
-	return hv_context.vp_index[cpu_number];
-}
-EXPORT_SYMBOL_GPL(vmbus_cpu_number_to_vp_number);
-
 static int vmbus_acpi_add(struct acpi_device *device)
 {
 	acpi_status result;

index 8493638..786ae41 100644
@@ -810,7 +810,7 @@ static void hv_irq_unmask(struct irq_data *data)
 	params->vector = cfg->vector;
 
 	for_each_cpu_and(cpu, dest, cpu_online_mask)
-		params->vp_mask |= (1ULL << vmbus_cpu_number_to_vp_number(cpu));
+		params->vp_mask |= (1ULL << hv_cpu_number_to_vp_number(cpu));
 
 	hv_do_hypercall(HVCALL_RETARGET_INTERRUPT, params, NULL);
 

@@ -905,7 +905,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 	} else {
 		for_each_cpu_and(cpu, affinity, cpu_online_mask) {
 			int_pkt->int_desc.cpu_mask |=
-				(1ULL << vmbus_cpu_number_to_vp_number(cpu));
+				(1ULL << hv_cpu_number_to_vp_number(cpu));
 		}
 	}
 

index 68a5772..08824f5 100644
@@ -1184,7 +1184,6 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj,
 			resource_size_t size, resource_size_t align,
 			bool fb_overlap_ok);
 void vmbus_free_mmio(resource_size_t start, resource_size_t size);
-int vmbus_cpu_number_to_vp_number(int cpu_number);
 
 /*
  * GUID definitions of various offer types - services offered to the guest.

index 7fd9cd3..df3252f 100644
@@ -140,6 +140,8 @@ void hyperv_init(void)
 	hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
 	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 
+	hyper_alloc_mmu();
+
 	/*
 	 * Register Hyper-V specific clocksource.
 	 */

117 lines not on this page · raw message

index cdf2391..783a8f6 100644
@@ -311,6 +311,8 @@ static inline int hv_cpu_number_to_vp_number(int cpu_number)
 }
 
 void hyperv_init(void);
+void hyperv_setup_mmu_ops(void);
+void hyper_alloc_mmu(void);
 void hyperv_report_panic(struct pt_regs *regs);
 bool hv_is_hypercall_page_setup(void);
 void hyperv_cleanup(void);

@@ -321,6 +323,7 @@ static inline bool hv_is_hypercall_page_setup(void)
 	return false;
 }
 static inline hyperv_cleanup(void) {}
+static inline void hyperv_setup_mmu_ops(void) {}
 #endif /* CONFIG_HYPERV */
 
 #ifdef CONFIG_HYPERV_TSCPAGE

index c87e900..3d44036 100644
@@ -239,6 +239,8 @@
 		(~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1))
 
 /* Declare the various hypercall operations. */
+#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE	0x0002
+#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST	0x0003
 #define HVCALL_NOTIFY_LONG_SPIN_WAIT		0x0008
 #define HVCALL_POST_MESSAGE			0x005c
 #define HVCALL_SIGNAL_EVENT			0x005d

@@ -256,6 +258,11 @@
 #define HV_PROCESSOR_POWER_STATE_C2		2
 #define HV_PROCESSOR_POWER_STATE_C3		3
 
+#define HV_FLUSH_ALL_PROCESSORS			0x00000001
+#define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES	0x00000002
+#define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY	0x00000004
+#define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT	0x00000008
+
 /* Hypercall interface */
 union hv_hypercall_input {
 	u64 as_uint64;

index a8b4765..16a9221 100644
@@ -240,6 +240,7 @@ static void __init ms_hyperv_init_platform(void)
 	 * Setup the hook to get control post apic initialization.
 	 */
 	x86_platform.apic_post_init = hyperv_init;
+	hyperv_setup_mmu_ops();
 #endif
 }
 

index e3ab9b9..c9cecb3 100644
@@ -15,8 +15,57 @@ struct hv_flush_pcpu {
 	__u64 gva_list[];
 };
 
+/* HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressListEx hypercalls */
+struct hv_flush_pcpu_ex {
+	__u64 address_space;
+	__u64 flags;
+	struct {
+		__u64 format;
+		__u64 valid_bank_mask;
+		__u64 bank_contents[];
+	} hv_vp_set;
+	__u64 gva_list[];
+};
+
 static struct hv_flush_pcpu __percpu *pcpu_flush;
 
+static struct hv_flush_pcpu_ex __percpu *pcpu_flush_ex;
+
+static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush,
+				    const struct cpumask *cpus)
+{
+	int cur_bank, cpu, vcpu, nr_bank = 0;
+	bool has_cpus;
+
+	/*
+	 * We can't be sure that translated vcpu numbers will always be
+	 * in ascending order, so iterate over all possible banks and
+	 * check all vcpus in it instead.
+	 */
+	for (cur_bank = 0; cur_bank < ms_hyperv.max_vp_index/64; cur_bank++) {
+		has_cpus = false;
+		for_each_cpu(cpu, cpus) {
+			vcpu = hv_cpu_number_to_vp_number(cpu);
+			if (vcpu/64 != cur_bank)
+				continue;
+			if (!has_cpus) {
+				flush->hv_vp_set.valid_bank_mask |=
+					1 << vcpu / 64;
+				flush->hv_vp_set.bank_contents[nr_bank] =
+					1 << vcpu % 64;
+				has_cpus = true;
+			} else {
+				flush->hv_vp_set.bank_contents[nr_bank] |=
+					1 << vcpu % 64;
+			}
+		}
+		if (has_cpus)
+			nr_bank++;
+	}
+
+	return nr_bank;
+}
+
 static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 				    struct mm_struct *mm, unsigned long start,
 				    unsigned long end)

@@ -102,16 +151,112 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 	native_flush_tlb_others(cpus, mm, start, end);
 }
 
+static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
+				       struct mm_struct *mm,
+				       unsigned long start,
+				       unsigned long end)
+{
+	struct hv_flush_pcpu_ex *flush;
+	unsigned long cur, flags;
+	u64 status = -1ULL;
+	int nr_bank = 0, max_gvas, gva_n;
+
+	if (!pcpu_flush_ex || !hv_hypercall_pg)
+		goto do_native;
+
+	if (cpumask_empty(cpus))
+		return;
+
+	local_irq_save(flags);
+
+	flush = this_cpu_ptr(pcpu_flush_ex);
+
+	if (mm) {
+		flush->address_space = virt_to_phys(mm->pgd);
+		flush->flags = 0;
+	} else {
+		flush->address_space = 0;
+		flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES;
+	}
+
+	flush->hv_vp_set.valid_bank_mask = 0;
+
+	if (cpumask_equal(cpus, cpu_present_mask)) {
+		flush->hv_vp_set.format = HV_GENERIC_SET_ALL;
+		flush->flags |= HV_FLUSH_ALL_PROCESSORS;
+	} else {
+		flush->hv_vp_set.format = HV_GENERIC_SET_SPARCE_4K;
+		nr_bank = cpumask_to_vp_set(flush, cpus);
+	}
+
+	/*
+	 * We can flush not more than max_gvas with one hypercall. Flush the
+	 * whole address space if we were asked to do more.
+	 */
+	max_gvas = (PAGE_SIZE - sizeof(*flush) - nr_bank*8) / 8;
+
+	if (end == TLB_FLUSH_ALL ||
+	    (end && ((end - start)/(PAGE_SIZE*PAGE_SIZE)) > max_gvas)) {
+		if (end == TLB_FLUSH_ALL)
+			flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY;
+
+		status = hv_do_rep_hypercall(
+			HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX,
+			0, nr_bank + 2, flush, NULL);
+	} else {
+		cur = start;
+		gva_n = nr_bank;
+		do {
+			flush->gva_list[gva_n] = cur & PAGE_MASK;
+			/*
+			 * Lower 12 bits encode the number of additional
+			 * pages to flush (in addition to the 'cur' page).
+			 */
+			if (end >= cur + PAGE_SIZE * PAGE_SIZE)
+				flush->gva_list[gva_n] |= ~PAGE_MASK;
+			else if (end > cur)
+				flush->gva_list[gva_n] |=
+					(end - cur - 1) >> PAGE_SHIFT;
+
+			cur += PAGE_SIZE * PAGE_SIZE;
+			++gva_n;
+
+		} while (cur < end);
+
+		status = hv_do_rep_hypercall(
+			HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX,
+			gva_n, nr_bank + 2, flush, NULL);
+	}
+
+	local_irq_restore(flags);
+
+	if (!(status & 0xffff))
+		return;
+do_native:
+	native_flush_tlb_others(cpus, mm, start, end);
+}
+
 void hyperv_setup_mmu_ops(void)
 {
-	if (ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED) {
+	if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED))
+		return;
+
+	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) {
 		pr_info("Hyper-V: Using hypercall for remote TLB flush\n");
 		pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;
+	} else {
+		pr_info("Hyper-V: Using ext hypercall for remote TLB flush\n");
+		pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others_ex;
 	}
 }
 
 void hyper_alloc_mmu(void)
 {
-	if (ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED)
+	if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED))
+		return;
+
+	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
 		pcpu_flush = __alloc_percpu(PAGE_SIZE, PAGE_SIZE);
+	else
+		pcpu_flush_ex = __alloc_percpu(PAGE_SIZE, PAGE_SIZE);
 }

index 3d44036..c697e20 100644
@@ -152,6 +152,9 @@
  */
 #define HV_X64_DEPRECATING_AEOI_RECOMMENDED	(1 << 9)
 
+/* Recommend using the newer ExProcessorMasks interface */
+#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED	(1 << 11)
+
 /*
  * Crash notification flag.
  */

@@ -242,6 +245,8 @@
 #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE	0x0002
 #define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST	0x0003
 #define HVCALL_NOTIFY_LONG_SPIN_WAIT		0x0008
+#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX  0x0013
+#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX   0x0014
 #define HVCALL_POST_MESSAGE			0x005c
 #define HVCALL_SIGNAL_EVENT			0x005d
 

@@ -263,6 +268,11 @@
 #define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY	0x00000004
 #define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT	0x00000008
 
+enum HV_GENERIC_SET_FORMAT {
+	HV_GENERIC_SET_SPARCE_4K,
+	HV_GENERIC_SET_ALL,
+};
+
 /* Hypercall interface */
 union hv_hypercall_input {
 	u64 as_uint64;

index c9cecb3..f6b5211 100644
@@ -6,6 +6,10 @@
 #include <asm/tlbflush.h>
 #include <asm/msr.h>
 #include <asm/fpu/api.h>
+#include <asm/trace/hyperv.h>
+
+#define CREATE_TRACE_POINTS
+DEFINE_TRACE(hyperv_mmu_flush_tlb_others);
 
 /* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */
 struct hv_flush_pcpu {

@@ -75,6 +79,8 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 	u64 status = -1ULL;
 	int cpu, vcpu, gva_n, max_gvas;
 
+	trace_hyperv_mmu_flush_tlb_others(cpus, mm, start, end);
+
 	if (!pcpu_flush || !hv_hypercall_pg)
 		goto do_native;
 

@@ -161,6 +167,8 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 	u64 status = -1ULL;
 	int nr_bank = 0, max_gvas, gva_n;
 
+	trace_hyperv_mmu_flush_tlb_others(cpus, mm, start, end);
+
 	if (!pcpu_flush_ex || !hv_hypercall_pg)
 		goto do_native;
 

new file mode 100644
index 0000000..e46a351
@@ -0,0 +1,34 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM hyperv
+
+#if !defined(_TRACE_HYPERV_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_HYPERV_H
+
+#include <linux/tracepoint.h>
+
+#if IS_ENABLED(CONFIG_HYPERV)
+
+TRACE_EVENT(hyperv_mmu_flush_tlb_others,
+	    TP_PROTO(const struct cpumask *cpus, struct mm_struct *mm,
+		     unsigned long addr, unsigned long end),
+	    TP_ARGS(cpus, mm, addr, end),
+	    TP_STRUCT__entry(
+		    __field(unsigned int, ncpus)
+		    __field(struct mm_struct *, mm)
+		    __field(unsigned long, addr)
+		    __field(unsigned long, end)
+		    ),
+	    TP_fast_assign(__entry->ncpus = cpumask_weight(cpus);
+			   __entry->mm = mm;
+			   __entry->addr = addr,
+			   __entry->end = end),
+	    TP_printk("ncpus %d mm %p addr %lx, end %lx",
+		      __entry->ncpus, __entry->mm, __entry->addr, __entry->end)
+	);
+
+#endif /* CONFIG_HYPERV */
+
+#endif /* _TRACE_HYPERV_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>