[PATCH v2 08/10] 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. These areas are of fixes size, limit them with an arbitrary number
of 16 (16 gvas are able to specify 16 * 4096 pages).

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>
---
Changes since v1:
- Use local_irq_save/restore instead of spinlock [Jork Loeser].
- Make sure struct hv_flush_pcpu doesn't cross page boundary [Jork Loeser].
- mm can be NULL, account for that [Simon Xiao]
---
 arch/x86/hyperv/Makefile           |   2 +-
 arch/x86/hyperv/hv_init.c          |   2 +
 arch/x86/hyperv/mmu.c              | 117 +++++++++++++++++++++++++++++++++++++
 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, 131 insertions(+), 1 deletion(-)
 create mode 100644 arch/x86/hyperv/mmu.c

diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile
index 171ae09..367a820 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 1c14088..2cf8a98 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -163,6 +163,8 @@ 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 0000000..e3ab9b9
--- /dev/null
+++ b/arch/x86/hyperv/mmu.c
@@ -0,0 +1,117 @@
+#include <linux/types.h>
+#include <linux/hyperv.h>
+#include <linux/slab.h>
+#include <linux/log2.h>
+#include <asm/mshyperv.h>
+#include <asm/tlbflush.h>
+#include <asm/msr.h>
+#include <asm/fpu/api.h>
+
+/* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */
+struct hv_flush_pcpu {
+	__u64 address_space;
+	__u64 flags;
+	__u64 processor_mask;
+	__u64 gva_list[];
+};
+
+static struct hv_flush_pcpu __percpu *pcpu_flush;
+
+static void hyperv_flush_tlb_others(const struct cpumask *cpus,
+				    struct mm_struct *mm, unsigned long start,
+				    unsigned long end)
+{
+	struct hv_flush_pcpu *flush;
+	unsigned long cur, flags;
+	u64 status = -1ULL;
+	int cpu, vcpu, gva_n, max_gvas;
+
+	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 (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->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 != -1 && vcpu < 64)
+				flush->processor_mask |= 1 << vcpu;
+			else
+				goto do_native;
+		}
+	}
+
+	/*
+	 * 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)) / 8;
+
+	if (end == TLB_FLUSH_ALL ||
+	    (end && ((end - start)/(PAGE_SIZE*PAGE_SIZE)) > max_gvas)) {
+		if (end == TLB_FLUSH_ALL)
+			flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY;
+		status = hv_do_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE,
+					 flush, NULL);
+	} else {
+		cur = start;
+		gva_n = 0;
+		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 + PAGE_SIZE * PAGE_SIZE)
+				flush->gva_list[gva_n] |= ~PAGE_MASK;
+			else if (end > cur)
+				flush->gva_list[gva_n] |=
+					(end - cur - 1) >> PAGE_SHIFT;
+
+			cur += PAGE_SIZE * PAGE_SIZE;
+			++gva_n;
+
+		} while (cur < end);
+
+		status = hv_do_rep_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST,
+					     gva_n, 0, 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) {
+		pr_info("Hyper-V: Using hypercall for remote TLB flush\n");
+		pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;
+	}
+}
+
+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 fd1f101..bb65f53 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -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);
@@ -318,5 +320,6 @@ 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 */
 #endif
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index c87e900..3d44036 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -239,6 +239,8 @@
 		(~((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
@@ -256,6 +258,11 @@
 #define HV_PROCESSOR_POWER_STATE_C2		2
 #define HV_PROCESSOR_POWER_STATE_C3		3
 
+#define HV_FLUSH_ALL_PROCESSORS			0x00000001
+#define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES	0x00000002
+#define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY	0x00000004
+#define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT	0x00000008
+
 /* Hypercall interface */
 union hv_hypercall_input {
 	u64 as_uint64;
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index a8b4765..16a9221 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -240,6 +240,7 @@ 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
 }
 
-- 
2.9.3