3 files changed, 118 insertions, 13 deletions

diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index 5c056b8aebef..40e0e322161d 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -194,10 +194,20 @@ do_ex_hypercall:
 
 static bool __send_ipi_one(int cpu, int vector)
 {
-	struct cpumask mask = CPU_MASK_NONE;
+	int vp = hv_cpu_number_to_vp_number(cpu);
 
-	cpumask_set_cpu(cpu, &mask);
-	return __send_ipi_mask(&mask, vector);
+	trace_hyperv_send_ipi_one(cpu, vector);
+
+	if (!hv_hypercall_pg || (vp == VP_INVAL))
+		return false;
+
+	if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
+		return false;
+
+	if (vp >= 64)
+		return __send_ipi_mask_ex(cpumask_of(cpu), vector);
+
+	return !hv_do_fast_hypercall16(HVCALL_SEND_IPI, vector, BIT_ULL(vp));
 }
 
 static void hv_send_ipi(int cpu, int vector)
@@ -260,11 +270,21 @@ void __init hv_apic_init(void)
 	}
 
 	if (ms_hyperv.hints & HV_X64_APIC_ACCESS_RECOMMENDED) {
-		pr_info("Hyper-V: Using MSR based APIC access\n");
+		pr_info("Hyper-V: Using enlightened APIC (%s mode)",
+			x2apic_enabled() ? "x2apic" : "xapic");
+		/*
+		 * With x2apic, architectural x2apic MSRs are equivalent to the
+		 * respective synthetic MSRs, so there's no need to override
+		 * the apic accessors.  The only exception is
+		 * hv_apic_eoi_write, because it benefits from lazy EOI when
+		 * available, but it works for both xapic and x2apic modes.
+		 */
 		apic_set_eoi_write(hv_apic_eoi_write);
-		apic->read      = hv_apic_read;
-		apic->write     = hv_apic_write;
-		apic->icr_write = hv_apic_icr_write;
-		apic->icr_read  = hv_apic_icr_read;
+		if (!x2apic_enabled()) {
+			apic->read      = hv_apic_read;
+			apic->write     = hv_apic_write;
+			apic->icr_write = hv_apic_icr_write;
+			apic->icr_read  = hv_apic_icr_read;
+		}
 	}
 }
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 0d258688c8cf..b0da5320bcff 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -7,6 +7,7 @@
  * Author : K. Y. Srinivasan <kys@microsoft.com>
  */
 
+#include <linux/acpi.h>
 #include <linux/efi.h>
 #include <linux/types.h>
 #include <asm/apic.h>
@@ -20,11 +21,15 @@
 #include <linux/hyperv.h>
 #include <linux/slab.h>
 #include <linux/cpuhotplug.h>
+#include <linux/syscore_ops.h>
 #include <clocksource/hyperv_timer.h>
 
 void *hv_hypercall_pg;
 EXPORT_SYMBOL_GPL(hv_hypercall_pg);
 
+/* Storage to save the hypercall page temporarily for hibernation */
+static void *hv_hypercall_pg_saved;
+
 u32 *hv_vp_index;
 EXPORT_SYMBOL_GPL(hv_vp_index);
 
@@ -37,6 +42,28 @@ EXPORT_SYMBOL_GPL(hyperv_pcpu_input_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;
@@ -223,6 +250,48 @@ static int __init hv_pci_init(void)
 	return 1;
 }
 
+static int hv_suspend(void)
+{
+	union hv_x64_msr_hypercall_contents hypercall_msr;
+
+	/*
+	 * Reset the hypercall page as it is going to be invalidated
+	 * accross hibernation. Setting hv_hypercall_pg to NULL ensures
+	 * that any subsequent hypercall operation fails safely instead of
+	 * crashing due to an access of an invalid page. The hypercall page
+	 * pointer is restored on resume.
+	 */
+	hv_hypercall_pg_saved = hv_hypercall_pg;
+	hv_hypercall_pg = NULL;
+
+	/* Disable the hypercall page in the hypervisor */
+	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+	hypercall_msr.enable = 0;
+	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+
+	return 0;
+}
+
+static void hv_resume(void)
+{
+	union hv_x64_msr_hypercall_contents hypercall_msr;
+
+	/* Re-enable the hypercall page */
+	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+	hypercall_msr.enable = 1;
+	hypercall_msr.guest_physical_address =
+		vmalloc_to_pfn(hv_hypercall_pg_saved);
+	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+
+	hv_hypercall_pg = hv_hypercall_pg_saved;
+	hv_hypercall_pg_saved = NULL;
+}
+
+static struct syscore_ops hv_syscore_ops = {
+	.suspend	= hv_suspend,
+	.resume		= hv_resume,
+};
+
 /*
  * This function is to be invoked early in the boot sequence after the
  * hypervisor has been detected.
@@ -297,12 +366,18 @@ void __init hyperv_init(void)
 	hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
 	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 
+	/*
+	 * Ignore any errors in setting up stimer clockevents
+	 * as we can run with the LAPIC timer as a fallback.
+	 */
+	(void)hv_stimer_alloc();
+
 	hv_apic_init();
 
 	x86_init.pci.arch_init = hv_pci_init;
 
-	/* Register Hyper-V specific clocksource */
-	hv_init_clocksource();
+	register_syscore_ops(&hv_syscore_ops);
+
 	return;
 
 remove_cpuhp_state:
@@ -322,6 +397,8 @@ void hyperv_cleanup(void)
 {
 	union hv_x64_msr_hypercall_contents hypercall_msr;
 
+	unregister_syscore_ops(&hv_syscore_ops);
+
 	/* Reset our OS id */
 	wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
 
@@ -419,3 +496,9 @@ bool hv_is_hyperv_initialized(void)
 	return hypercall_msr.enable;
 }
 EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized);
+
+bool hv_is_hibernation_supported(void)
+{
+	return acpi_sleep_state_supported(ACPI_STATE_S4);
+}
+EXPORT_SYMBOL_GPL(hv_is_hibernation_supported);
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index e65d7fe6489f..5208ba49c89a 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -37,12 +37,14 @@ static inline int fill_gva_list(u64 gva_list[], int offset,
 		 * Lower 12 bits encode the number of additional
 		 * pages to flush (in addition to the 'cur' page).
 		 */
-		if (diff >= HV_TLB_FLUSH_UNIT)
+		if (diff >= HV_TLB_FLUSH_UNIT) {
 			gva_list[gva_n] |= ~PAGE_MASK;
-		else if (diff)
+			cur += HV_TLB_FLUSH_UNIT;
+		}  else if (diff) {
 			gva_list[gva_n] |= (diff - 1) >> PAGE_SHIFT;
+			cur = end;
+		}
 
-		cur += HV_TLB_FLUSH_UNIT;
 		gva_n++;
 
 	} while (cur < end);