[PATCH v10 7/9] x86/hyper-v: use hypercall for remote TLB flush

[Vitaly Kuznetsov]

Hyper-V host can suggest us to use hypercall for doing remote TLB flush,
this is supposed to work faster than IPIs.

Implementation details: to do HvFlushVirtualAddress{Space,List} hypercalls
we need to put the input somewhere in memory and we don't really want to
have memory allocation on each call so we pre-allocate per cpu memory areas
on boot.

pv_ops patching is happening very early so we need to separate
hyperv_setup_mmu_ops() and hyper_alloc_mmu().

It is possible and easy to implement local TLB flushing too and there is
even a hint for that. However, I don't see a room for optimization on the
host side as both hypercall and native tlb flush will result in vmexit. The
hint is also not set on modern Hyper-V versions.

Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
Reviewed-by: Andy Shevchenko <andy.shevchenko@xxxxxxxxx>
Reviewed-by: Stephen Hemminger <sthemmin@xxxxxxxxxxxxx>
---
 arch/x86/hyperv/Makefile           |   2 +-
 arch/x86/hyperv/hv_init.c          |   2 +
 arch/x86/hyperv/mmu.c              | 138 +++++++++++++++++++++++++++++++++++++
 arch/x86/include/asm/mshyperv.h    |   3 +
 arch/x86/include/uapi/asm/hyperv.h |   7 ++
 arch/x86/kernel/cpu/mshyperv.c     |   1 +
 6 files changed, 152 insertions(+), 1 deletion(-)
 create mode 100644 arch/x86/hyperv/mmu.c

diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile
index 171ae09864d7..367a8203cfcf 100644
--- a/arch/x86/hyperv/Makefile
+++ b/arch/x86/hyperv/Makefile
@@ -1 +1 @@
-obj-y		:= hv_init.o
+obj-y		:= hv_init.o mmu.o
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index e93b9a0b1b10..1a8eb550c40f 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -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.
 	 */
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
new file mode 100644
index 000000000000..9419a20b1d75
--- /dev/null
+++ b/arch/x86/hyperv/mmu.c
@@ -0,0 +1,138 @@
+#define pr_fmt(fmt)  "Hyper-V: " fmt
+
+#include <linux/hyperv.h>
+#include <linux/log2.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include <asm/fpu/api.h>
+#include <asm/mshyperv.h>
+#include <asm/msr.h>
+#include <asm/tlbflush.h>
+
+/* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */
+struct hv_flush_pcpu {
+	u64 address_space;
+	u64 flags;
+	u64 processor_mask;
+	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;
+
+/*
+ * Fills in gva_list starting from offset. Returns the number of items added.
+ */
+static inline int fill_gva_list(u64 gva_list[], int offset,
+				unsigned long start, unsigned long end)
+{
+	int gva_n = offset;
+	unsigned long cur = start, diff;
+
+	do {
+		diff = end > cur ? end - cur : 0;
+
+		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 (diff >= HV_TLB_FLUSH_UNIT)
+			gva_list[gva_n] |= ~PAGE_MASK;
+		else if (diff)
+			gva_list[gva_n] |= (diff - 1) >> PAGE_SHIFT;
+
+		cur += HV_TLB_FLUSH_UNIT;
+		gva_n++;
+
+	} while (cur < end);
+
+	return gva_n - offset;
+}
+
+static void hyperv_flush_tlb_others(const struct cpumask *cpus,
+				    const struct flush_tlb_info *info)
+{
+	int cpu, vcpu, gva_n, max_gvas;
+	struct hv_flush_pcpu *flush;
+	u64 status = U64_MAX;
+	unsigned long flags;
+
+	if (!pcpu_flush || !hv_hypercall_pg)
+		goto do_native;
+
+	if (cpumask_empty(cpus))
+		return;
+
+	local_irq_save(flags);
+
+	flush = this_cpu_ptr(pcpu_flush);
+
+	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->processor_mask = 0;
+	if (cpumask_equal(cpus, cpu_present_mask)) {
+		flush->flags |= HV_FLUSH_ALL_PROCESSORS;
+	} else {
+		for_each_cpu(cpu, cpus) {
+			vcpu = hv_cpu_number_to_vp_number(cpu);
+			if (vcpu >= 64)
+				goto do_native;
+
+			__set_bit(vcpu, (unsigned long *)
+				  &flush->processor_mask);
+		}
+	}
+
+	/*
+	 * 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)) / sizeof(flush->gva_list[0]);
+
+	if (info->end == TLB_FLUSH_ALL) {
+		flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY;
+		status = hv_do_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE,
+					 flush, NULL);
+	} else if (info->end &&
+		   ((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) {
+		status = hv_do_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE,
+					 flush, NULL);
+	} else {
+		gva_n = fill_gva_list(flush->gva_list, 0,
+				      info->start, info->end);
+		status = hv_do_rep_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST,
+					     gva_n, 0, 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) {
+		pr_info("Using hypercall for remote TLB flush\n");
+		pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;
+		setup_clear_cpu_cap(X86_FEATURE_PCID);
+	}
+}
+
+void hyper_alloc_mmu(void)
+{
+	if (ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED)
+		pcpu_flush = __alloc_percpu(PAGE_SIZE, PAGE_SIZE);
+}
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index efd2f80d3353..0d4b01c5e438 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -307,6 +307,8 @@ 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);
@@ -314,6 +316,7 @@ void hyperv_cleanup(void);
 static inline void hyperv_init(void) {}
 static inline bool hv_is_hypercall_page_setup(void) { return false; }
 static inline void hyperv_cleanup(void) {}
+static inline void hyperv_setup_mmu_ops(void) {}
 #endif /* CONFIG_HYPERV */
 
 #ifdef CONFIG_HYPERV_TSCPAGE
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index 127ddadee1a5..a6fdd3b82b4a 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -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
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 70e717fccdd6..daefd67a66c7 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -249,6 +249,7 @@ 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
 }
 
-- 
2.13.3