[PATCH v6 09/10] x86/hyper-v: support extended CPU ranges for TLB flush hypercalls

[Vitaly Kuznetsov]

Hyper-V hosts may support more than 64 vCPUs, we need to use
HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX/LIST_EX hypercalls in this
case.

Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
---
Changes since v5:
- Do single pass in cpumask_to_vp_set() as it turns our that empty banks
  are valid [Jork Loeser]
- Use fill_gva_list() for _EX hypercalls [Andy Shevchenko]
- Use HV_HYPERCALL_RESULT_MASK [Andy Shevchenko]
- __u64 -> u64, minor code tweaks [Andy Shevchenko]
---
 arch/x86/hyperv/mmu.c              | 126 ++++++++++++++++++++++++++++++++++++-
 arch/x86/include/uapi/asm/hyperv.h |  10 +++
 2 files changed, 133 insertions(+), 3 deletions(-)

diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index fe87ffe..9f11442 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -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 filled
  * in gva_list (including offset)
@@ -52,6 +66,31 @@ static inline int fill_gva_list(u64 gva_list[], int offset,
 	return gva_n;
 }
 
+/* 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 = 0;
+
+	/*
+	 * 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;
+
+		__set_bit(vcpu_offset, (unsigned long *)
+			  &flush->hv_vp_set.bank_contents[nr_bank]);
+		__set_bit(vcpu_bank, (unsigned long *)
+			  &flush->hv_vp_set.valid_bank_mask);
+		if (vcpu_bank > nr_bank)
+			nr_bank = vcpu_bank;
+	}
+
+	return nr_bank + 1;
+}
+
 static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 				    struct mm_struct *mm, unsigned long start,
 				    unsigned long end)
@@ -72,7 +111,7 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 	flush = this_cpu_ptr(pcpu_flush);
 
 	if (mm) {
-		flush->address_space = virt_to_phys(mm->pgd);
+		flush->address_space = (u64)virt_to_phys(mm->pgd);
 		flush->flags = 0;
 	} else {
 		flush->address_space = 0;
@@ -120,16 +159,97 @@ 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)
+{
+	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 (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 * sizeof(flush->hv_vp_set.bank_contents[0])) /
+		sizeof(flush->gva_list[0]);
+
+	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 if (end && ((end - 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, start, 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, 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);
 }
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index cc0e70c..9a19272 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -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	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
-- 
2.9.4