Hyper-V: paravirtualized remote TLB flushing and hypercall improvements

index 2b58c8c1eeaa..94937a357b3e 100644
@@ -173,7 +173,12 @@ 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 94937a357b3e..01b9c0fb3aab 100644
@@ -28,6 +28,8 @@ 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 70e717fccdd6..b3bf024fc4e0 100644
@@ -184,9 +184,15 @@ 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_debug("Hyper-V: max %u virtual processors, %u logical processors\n",
+		 ms_hyperv.max_vp_index, ms_hyperv.max_lp_index);
+
 	/*
 	 * Extract host information.
 	 */

@@ -219,7 +225,7 @@ 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);
 	}
 

@@ -253,7 +259,7 @@ 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 5b882cc0c0e9..691603ee9179 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;

index 01b9c0fb3aab..5f708804b00b 100644
@@ -170,6 +170,45 @@ void hv_remove_crash_handler(void);
 
 #if IS_ENABLED(CONFIG_HYPERV)
 extern struct clocksource *hyperv_cs;
+extern void *hv_hypercall_pg;
+
+static inline 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;
+	u64 hv_status;
+	register void *__sp asm(_ASM_SP);
+
+#ifdef CONFIG_X86_64
+	if (!hv_hypercall_pg)
+		return U64_MAX;
+
+	__asm__ __volatile__("mov %4, %%r8\n"
+			     "call *%5"
+			     : "=a" (hv_status), "+r" (__sp),
+			       "+c" (control), "+d" (input_address)
+			     :  "r" (output_address), "m" (hv_hypercall_pg)
+			     : "cc", "memory", "r8", "r9", "r10", "r11");
+#else
+	u32 input_address_hi = upper_32_bits(input_address);
+	u32 input_address_lo = lower_32_bits(input_address);
+	u32 output_address_hi = upper_32_bits(output_address);
+	u32 output_address_lo = lower_32_bits(output_address);
+
+	if (!hv_hypercall_pg)
+		return U64_MAX;
+
+	__asm__ __volatile__("call *%7"
+			     : "=A" (hv_status),
+			       "+c" (input_address_lo), "+r" (__sp)
+			     : "A" (control),
+			       "b" (input_address_hi),
+			       "D"(output_address_hi), "S"(output_address_lo),
+			       "m" (hv_hypercall_pg)
+			     : "cc", "memory");
+#endif /* !x86_64 */
+	return hv_status;
+}
 
 void hyperv_init(void);
 void hyperv_report_panic(struct pt_regs *regs);

index 59c11ff90d12..45e806e3112f 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 b7d7bbec74e0..6608a71e7d79 100644
@@ -1187,7 +1187,6 @@ 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 5f708804b00b..91c404a4c020 100644
@@ -210,6 +210,40 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 	return hv_status;
 }
 
+#define HV_HYPERCALL_FAST_BIT		BIT(16)
+
+/* Fast hypercall with 8 bytes of input and no output */
+static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
+{
+	u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT;
+	register void *__sp asm(_ASM_SP);
+
+#ifdef CONFIG_X86_64
+	{
+		__asm__ __volatile__("call *%4"
+				     : "=a" (hv_status), "+r" (__sp),
+				       "+c" (control), "+d" (input1)
+				     : "m" (hv_hypercall_pg)
+				     : "cc", "r8", "r9", "r10", "r11");
+	}
+#else
+	{
+		u32 input1_hi = upper_32_bits(input1);
+		u32 input1_lo = lower_32_bits(input1);
+
+		__asm__ __volatile__ ("call *%5"
+				      : "=A"(hv_status),
+					"+c"(input1_lo),
+					"+r"(__sp)
+				      :	"A" (control),
+					"b" (input1_hi),
+					"m" (hv_hypercall_pg)
+				      : "cc", "edi", "esi");
+	}
+#endif
+		return hv_status;
+}
+
 void hyperv_init(void);
 void hyperv_report_panic(struct pt_regs *regs);
 bool hv_is_hypercall_page_setup(void);

index 4bbb8dea4727..fd2b6c67f781 100644
@@ -805,21 +805,12 @@ 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 = VMBUS_EVENT_CONNECTION_ID;
 
 	if (vmbus_proto_version != VERSION_WS2008) {
 		newchannel->is_dedicated_interrupt =
 				(offer->is_dedicated_interrupt != 0);
-		newchannel->sig_event->connectionid.u.id =
-				offer->connection_id;
+		newchannel->sig_event = offer->connection_id;
 	}
 
 	memcpy(&newchannel->offermsg, offer,

index 45e806e3112f..37ecf514189e 100644
@@ -408,6 +408,6 @@ 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);
 }
 EXPORT_SYMBOL_GPL(vmbus_set_event);

index 6608a71e7d79..c472bd43bdd7 100644
@@ -677,18 +677,6 @@ union hv_connection_id {
 	} u;
 };
 
-/* 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;
-};
-
 enum hv_numa_policy {
 	HV_BALANCED = 0,
 	HV_LOCALIZED,

@@ -770,8 +758,7 @@ struct vmbus_channel {
 	} callback_mode;
 
 	bool is_dedicated_interrupt;
-	struct hv_input_signal_event_buffer sig_buf;
-	struct hv_input_signal_event *sig_event;
+	u64 sig_event;
 
 	/*
 	 * Starting with win8, this field will be used to specify

index 91c404a4c020..47cec5b3f3d9 100644
@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <linux/atomic.h>
+#include <linux/nmi.h>
 #include <asm/hyperv.h>
 
 /*

@@ -210,7 +211,13 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 	return hv_status;
 }
 
+#define HV_HYPERCALL_RESULT_MASK	GENMASK_ULL(15, 0)
 #define HV_HYPERCALL_FAST_BIT		BIT(16)
+#define HV_HYPERCALL_VARHEAD_OFFSET	17
+#define HV_HYPERCALL_REP_COMP_OFFSET	32
+#define HV_HYPERCALL_REP_COMP_MASK	GENMASK_ULL(43, 32)
+#define HV_HYPERCALL_REP_START_OFFSET	48
+#define HV_HYPERCALL_REP_START_MASK	GENMASK_ULL(59, 48)
 
 /* Fast hypercall with 8 bytes of input and no output */
 static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)

@@ -244,6 +251,38 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
 		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;
+}
+
 void hyperv_init(void);
 void hyperv_report_panic(struct pt_regs *regs);
 bool hv_is_hypercall_page_setup(void);

index 691603ee9179..e93b9a0b1b10 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()] = 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 = kmalloc_array(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 47cec5b3f3d9..574cfc438ee8 100644
@@ -283,6 +283,30 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size,
 	return status;
 }
 
+/*
+ * Hypervisor's notion of virtual processor ID is different from
+ * Linux' notion of CPU ID. This information can only be retrieved
+ * in the context of the calling CPU. Setup a map for easy access
+ * to this information.
+ */
+extern u32 *hv_vp_index;
+
+/**
+ * hv_cpu_number_to_vp_number() - Map CPU to VP.
+ * @cpu_number: CPU number in Linux terms
+ *
+ * This function returns the mapping between the Linux processor
+ * number and the hypervisor's virtual processor number, useful
+ * in making hypercalls and such that talk about specific
+ * processors.
+ *
+ * Return: Virtual processor number in Hyper-V terms
+ */
+static inline int hv_cpu_number_to_vp_number(int cpu_number)
+{
+	return hv_vp_index[cpu_number];
+}
+
 void hyperv_init(void);
 void hyperv_report_panic(struct pt_regs *regs);
 bool hv_is_hypercall_page_setup(void);

index fd2b6c67f781..dc590195a74e 100644
@@ -599,7 +599,7 @@ 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;
 	}
 

@@ -683,7 +683,7 @@ 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)

@@ -1219,8 +1219,7 @@ 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 37ecf514189e..f41901f80b64 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 2ea12207caa0..8267439dd1ee 100644
@@ -234,7 +234,6 @@ 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);

@@ -276,14 +275,6 @@ 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 1b6a5e0dfa75..49569f8fe038 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 ed84e96715a0..c7e7d6db2d21 100644
@@ -1451,23 +1451,6 @@ 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;

84 lines not on this page · raw message

index c472bd43bdd7..e2a4fa57f110 100644
@@ -1173,7 +1173,6 @@ 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 e93b9a0b1b10..1a8eb550c40f 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.
 	 */

135 lines not on this page · raw message

index 574cfc438ee8..b53d9a955be6 100644
@@ -308,6 +308,8 @@ 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);

@@ -315,6 +317,7 @@ void hyperv_cleanup(void);
 static inline void hyperv_init(void) {}
 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 127ddadee1a5..a6fdd3b82b4a 100644
@@ -242,6 +242,8 @@
 		(~((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

@@ -259,6 +261,11 @@
 #define HV_PROCESSOR_POWER_STATE_C2		2
 #define HV_PROCESSOR_POWER_STATE_C3		3
 
+#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)
+
 /* hypercall status code */
 #define HV_STATUS_SUCCESS			0
 #define HV_STATUS_INVALID_HYPERCALL_CODE	2

index b3bf024fc4e0..42664f944cbc 100644
@@ -255,6 +255,7 @@ 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 6964f4a3ccde..6fb84c4c3ee7 100644
@@ -16,11 +16,25 @@ 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[];
+};
+
 /* Each gva in gva_list encodes up to 4096 pages to flush */
 #define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE)
 
 static struct hv_flush_pcpu __percpu *pcpu_flush;
 
+static struct hv_flush_pcpu_ex __percpu *pcpu_flush_ex;
+
 /*
  * Fills in gva_list starting from offset. Returns the number of items added.
  */

@@ -50,6 +64,35 @@ static inline int fill_gva_list(u64 gva_list[], int offset,
 
 	return gva_n - offset;
 }
+
+/* Return the number of banks in the resulting vp_set */
+static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush,
+				    const struct cpumask *cpus)
+{
+	int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1;
+
+	/*
+	 * Some banks may end up being empty but this is acceptable.
+	 */
+	for_each_cpu(cpu, cpus) {
+		vcpu = hv_cpu_number_to_vp_number(cpu);
+		vcpu_bank = vcpu / 64;
+		vcpu_offset = vcpu % 64;
+
+		/* valid_bank_mask can represent up to 64 banks */
+		if (vcpu_bank >= 64)
+			return 0;
+
+		__set_bit(vcpu_offset, (unsigned long *)
+			  &flush->hv_vp_set.bank_contents[vcpu_bank]);
+		if (vcpu_bank >= nr_bank)
+			nr_bank = vcpu_bank + 1;
+	}
+	flush->hv_vp_set.valid_bank_mask = GENMASK_ULL(nr_bank - 1, 0);
+
+	return nr_bank;
+}
+
 static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 				    const struct flush_tlb_info *info)
 {

@@ -119,17 +162,102 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 	native_flush_tlb_others(cpus, info);
 }
 
+static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
+				       const struct flush_tlb_info *info)
+{
+	int nr_bank = 0, max_gvas, gva_n;
+	struct hv_flush_pcpu_ex *flush;
+	u64 status = U64_MAX;
+	unsigned long flags;
+
+	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 (info->mm) {
+		flush->address_space = virt_to_phys(info->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_SPARCE_4K;
+		nr_bank = cpumask_to_vp_set(flush, cpus);
+	}
+
+	if (!nr_bank) {
+		flush->hv_vp_set.format = HV_GENERIC_SET_ALL;
+		flush->flags |= HV_FLUSH_ALL_PROCESSORS;
+	}
+
+	/*
+	 * 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 *
+		 sizeof(flush->hv_vp_set.bank_contents[0])) /
+		sizeof(flush->gva_list[0]);
+
+	if (info->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 if (info->end &&
+		   ((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) {
+		status = hv_do_rep_hypercall(
+			HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX,
+			0, nr_bank + 2, flush, NULL);
+	} else {
+		gva_n = fill_gva_list(flush->gva_list, nr_bank,
+				      info->start, info->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 & HV_HYPERCALL_RESULT_MASK))
+		return;
+do_native:
+	native_flush_tlb_others(cpus, info);
+}
+
 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;
+
+	setup_clear_cpu_cap(X86_FEATURE_PCID);
+
+	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;
-		setup_clear_cpu_cap(X86_FEATURE_PCID);
+	} 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 a6fdd3b82b4a..7032f4d8dff3 100644
@@ -149,6 +149,9 @@
  */
 #define HV_X64_DEPRECATING_AEOI_RECOMMENDED	(1 << 9)
 
+/* Recommend using the newer ExProcessorMasks interface */
+#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED	(1 << 11)
+
 /*
  * HV_VP_SET available
  */

@@ -245,6 +248,8 @@
 #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
 

@@ -266,6 +271,11 @@
 #define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY	BIT(2)
 #define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT	BIT(3)
 
+enum HV_GENERIC_SET_FORMAT {
+	HV_GENERIC_SET_SPARCE_4K,
+	HV_GENERIC_SET_ALL,
+};
+
 /* hypercall status code */
 #define HV_STATUS_SUCCESS			0
 #define HV_STATUS_INVALID_HYPERCALL_CODE	2

index 6fb84c4c3ee7..41bff87fb055 100644
@@ -8,6 +8,9 @@
 #include <asm/msr.h>
 #include <asm/tlbflush.h>
 
+#define CREATE_TRACE_POINTS
+#include <asm/trace/hyperv.h>
+
 /* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */
 struct hv_flush_pcpu {
 	u64 address_space;

@@ -101,6 +104,8 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 	u64 status = U64_MAX;
 	unsigned long flags;
 
+	trace_hyperv_mmu_flush_tlb_others(cpus, info);
+
 	if (!pcpu_flush || !hv_hypercall_pg)
 		goto do_native;
 

@@ -170,6 +175,8 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 	u64 status = U64_MAX;
 	unsigned long flags;
 
+	trace_hyperv_mmu_flush_tlb_others(cpus, info);
+
 	if (!pcpu_flush_ex || !hv_hypercall_pg)
 		goto do_native;
 

new file mode 100644
index 000000000000..4253bca99989
@@ -0,0 +1,40 @@
+#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,
+		     const struct flush_tlb_info *info),
+	    TP_ARGS(cpus, info),
+	    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 = info->mm;
+			   __entry->addr = info->start;
+			   __entry->end = info->end;
+		    ),
+	    TP_printk("ncpus %d mm %p addr %lx, end %lx",
+		      __entry->ncpus, __entry->mm,
+		      __entry->addr, __entry->end)
+	);
+
+#endif /* CONFIG_HYPERV */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH asm/trace/
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE hyperv
+#endif /* _TRACE_HYPERV_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>