[PATCH v5 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>
Acked-by: K. Y. Srinivasan <kys@xxxxxxxxxxxxx>
---
Changes since v4:
- Use __set_bit(), minor code style changes [Andy Shevchenko]
---
 arch/x86/hyperv/mmu.c              | 150 ++++++++++++++++++++++++++++++++++++-
 arch/x86/include/uapi/asm/hyperv.h |  10 +++
 2 files changed, 158 insertions(+), 2 deletions(-)

diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index 8ccd680..b08e7ca 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -15,11 +15,60 @@ 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 (PAGE_SIZE * PAGE_SIZE)
 
 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 cpu, vcpu, vcpu_bank, vcpu_offset, cur_bank, 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);
+			vcpu_bank = vcpu / 64;
+			vcpu_offset = vcpu % 64;
+
+			if (vcpu_bank != cur_bank)
+				continue;
+			__set_bit(vcpu_offset, (unsigned long *)
+				  &flush->hv_vp_set.bank_contents[nr_bank]);
+			if (!has_cpus) {
+				__set_bit(vcpu_bank, (unsigned long *)
+					  &flush->hv_vp_set.valid_bank_mask);
+				has_cpus = true;
+			}
+		}
+		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)
@@ -106,16 +155,113 @@ 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 = U64_MAX;
+	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) {
+		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 {
+		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 + HV_TLB_FLUSH_UNIT)
+				flush->gva_list[gva_n] |= ~PAGE_MASK;
+			else if (end > cur)
+				flush->gva_list[gva_n] |=
+					(end - cur - 1) >> PAGE_SHIFT;
+
+			cur += HV_TLB_FLUSH_UNIT;
+			++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);
 }
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index 38808f1..a177517 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	0x00000004
 #define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT	0x00000008
 
+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