Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1674263 > unrolled thread

[PATCH 00/10] Hyper-V: paravirtualized remote TLB flushing and hypercall improvements

Back to article view | Back to linux.kernel

Contents

  [PATCH 00/10] Hyper-V: paravirtualized remote TLB flushing and hypercall improvements                                                       kys@exchange.microsoft.com - 2017-06-25 19:10 +0200
    [PATCH 03/10] x86/hyper-v: make hv_do_hypercall() inline kys@exchange.microsoft.com - 2017-06-25 19:10 +0200
    [PATCH 08/10] x86/hyper-v: use hypercall for remote TLB flush kys@exchange.microsoft.com - 2017-06-25 19:10 +0200
    [PATCH 06/10] x86/hyper-v: implement rep hypercalls kys@exchange.microsoft.com - 2017-06-25 19:10 +0200

#1674263 — [PATCH 00/10] Hyper-V: paravirtualized remote TLB flushing and hypercall improvements

From: K. Y. Srinivasan <kys@microsoft.com>

Hyper-V supports hypercalls for doing local and remote TLB flushing and
gives its guests hints when using hypercall is preferred. While doing
hypercalls for local TLB flushes is probably not practical (and is not
being suggested by modern Hyper-V versions) remote TLB flush with a
hypercall brings significant improvement.

To test the series I wrote a special 'TLB trasher': on a 16 vCPU guest I
was creating 32 threads which were doing 100000 mmap/munmaps each on
some
big file. Here are the results:

Before:
# time ./pthread_mmap ./randfile 
real	3m33.118s
user	0m3.698s
sys	3m16.624s

After:
# time ./pthread_mmap ./randfile 
real	2m19.920s
user	0m2.662s
sys	2m9.948s

This series brings a number of small improvements along the way: fast
hypercall implementation and using it for event signaling, rep
hypercalls
implementation, hyperv tracing subsystem (which only traces the newly
added
remote TLB flush for now).

Vitaly Kuznetsov (10):
  x86/hyper-v: include hyperv/ only when CONFIG_HYPERV is set
  x86/hyper-v: stash the max number of virtual/logical processor
  x86/hyper-v: make hv_do_hypercall() inline
  x86/hyper-v: fast hypercall implementation
  hyper-v: use fast hypercall for HVCALL_SIGNAL_EVENT
  x86/hyper-v: implement rep hypercalls
  hyper-v: globalize vp_index
  x86/hyper-v: use hypercall for remote TLB flush
  x86/hyper-v: support extended CPU ranges for TLB flush hypercalls
  tracing/hyper-v: trace hyperv_mmu_flush_tlb_others()

 MAINTAINERS                         |    1 +
 arch/x86/Kbuild                     |    2 +-
 arch/x86/hyperv/Makefile            |    2 +-
 arch/x86/hyperv/hv_init.c           |   90 +++++-------
 arch/x86/hyperv/mmu.c               |  268 +++++++++++++++++++++++++++++++++++
 arch/x86/include/asm/mshyperv.h     |  149 +++++++++++++++++++-
 arch/x86/include/asm/trace/hyperv.h |   38 +++++
 arch/x86/include/uapi/asm/hyperv.h  |   17 +++
 arch/x86/kernel/cpu/mshyperv.c      |   13 ++-
 drivers/hv/channel_mgmt.c           |   20 +--
 drivers/hv/connection.c             |    7 +-
 drivers/hv/hv.c                     |    9 --
 drivers/hv/hyperv_vmbus.h           |   11 --
 drivers/hv/vmbus_drv.c              |   17 ---
 drivers/pci/host/pci-hyperv.c       |   10 +-
 include/linux/hyperv.h              |   17 +--
 16 files changed, 540 insertions(+), 131 deletions(-)
 create mode 100644 arch/x86/hyperv/mmu.c
 create mode 100644 arch/x86/include/asm/trace/hyperv.h

[toc] | [next] | [standalone]

#1674266 — [PATCH 03/10] x86/hyper-v: make hv_do_hypercall() inline

From: Vitaly Kuznetsov <vkuznets@redhat.com>

We have only three call sites for hv_do_hypercall() and we're going to
change HVCALL_SIGNAL_EVENT to doing fast hypercall so we can inline this
function for optimization.

Hyper-V top level functional specification states that r9-r11 registers
and flags may be clobbered by the hypervisor during hypercall and with
inlining this is somewhat important, add the clobbers.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 arch/x86/hyperv/hv_init.c       |   54 +++-----------------------------------
 arch/x86/include/asm/mshyperv.h |   39 ++++++++++++++++++++++++++++
 drivers/hv/connection.c         |    2 +
 include/linux/hyperv.h          |    1 -
 4 files changed, 46 insertions(+), 50 deletions(-)

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 5b882cc..691603e 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -75,7 +75,8 @@ static u64 read_hv_clock_msr(struct clocksource *arg)
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static void *hypercall_pg;
+void *hv_hypercall_pg;
+EXPORT_SYMBOL_GPL(hv_hypercall_pg);
 struct clocksource *hyperv_cs;
 EXPORT_SYMBOL_GPL(hyperv_cs);
 
@@ -102,15 +103,15 @@ void hyperv_init(void)
 	guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0);
 	wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id);
 
-	hypercall_pg  = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_RX);
-	if (hypercall_pg == NULL) {
+	hv_hypercall_pg  = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_RX);
+	if (hv_hypercall_pg == NULL) {
 		wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
 		return;
 	}
 
 	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 	hypercall_msr.enable = 1;
-	hypercall_msr.guest_physical_address = vmalloc_to_pfn(hypercall_pg);
+	hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
 	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 
 	/*
@@ -170,51 +171,6 @@ void hyperv_cleanup(void)
 }
 EXPORT_SYMBOL_GPL(hyperv_cleanup);
 
-/*
- * hv_do_hypercall- Invoke the specified hypercall
- */
-u64 hv_do_hypercall(u64 control, void *input, void *output)
-{
-	u64 input_address = (input) ? virt_to_phys(input) : 0;
-	u64 output_address = (output) ? virt_to_phys(output) : 0;
-#ifdef CONFIG_X86_64
-	u64 hv_status = 0;
-
-	if (!hypercall_pg)
-		return (u64)ULLONG_MAX;
-
-	__asm__ __volatile__("mov %0, %%r8" : : "r" (output_address) : "r8");
-	__asm__ __volatile__("call *%3" : "=a" (hv_status) :
-			     "c" (control), "d" (input_address),
-			     "m" (hypercall_pg));
-
-	return hv_status;
-
-#else
-
-	u32 control_hi = control >> 32;
-	u32 control_lo = control & 0xFFFFFFFF;
-	u32 hv_status_hi = 1;
-	u32 hv_status_lo = 1;
-	u32 input_address_hi = input_address >> 32;
-	u32 input_address_lo = input_address & 0xFFFFFFFF;
-	u32 output_address_hi = output_address >> 32;
-	u32 output_address_lo = output_address & 0xFFFFFFFF;
-
-	if (!hypercall_pg)
-		return (u64)ULLONG_MAX;
-
-	__asm__ __volatile__ ("call *%8" : "=d"(hv_status_hi),
-			      "=a"(hv_status_lo) : "d" (control_hi),
-			      "a" (control_lo), "b" (input_address_hi),
-			      "c" (input_address_lo), "D"(output_address_hi),
-			      "S"(output_address_lo), "m" (hypercall_pg));
-
-	return hv_status_lo | ((u64)hv_status_hi << 32);
-#endif /* !x86_64 */
-}
-EXPORT_SYMBOL_GPL(hv_do_hypercall);
-
 void hyperv_report_panic(struct pt_regs *regs)
 {
 	static bool panic_reported;
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 115a0e2..a004b3b 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -171,6 +171,45 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
 
 #if IS_ENABLED(CONFIG_HYPERV)
 extern struct clocksource *hyperv_cs;
+extern void *hv_hypercall_pg;
+
+static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
+{
+	u64 input_address = input ? virt_to_phys(input) : 0;
+	u64 output_address = output ? virt_to_phys(output) : 0;
+	u64 hv_status;
+	register void *__sp asm(_ASM_SP);
+
+#ifdef CONFIG_X86_64
+	if (!hv_hypercall_pg)
+		return U64_MAX;
+
+	__asm__ __volatile__("mov %4, %%r8\n"
+			     "call *%5"
+			     : "=a" (hv_status), "+r" (__sp),
+			       "+c" (control), "+d" (input_address)
+			     :  "r" (output_address), "m" (hv_hypercall_pg)
+			     : "cc", "memory", "r8", "r9", "r10", "r11");
+#else
+	u32 input_address_hi = upper_32_bits(input_address);
+	u32 input_address_lo = lower_32_bits(input_address);
+	u32 output_address_hi = upper_32_bits(output_address);
+	u32 output_address_lo = lower_32_bits(output_address);
+
+	if (!hv_hypercall_pg)
+		return U64_MAX;
+
+	__asm__ __volatile__("call *%7"
+			     : "=A" (hv_status),
+			       "+c" (input_address_lo), "+r" (__sp)
+			     : "A" (control),
+			       "b" (input_address_hi),
+			       "D"(output_address_hi), "S"(output_address_lo),
+			       "m" (hv_hypercall_pg)
+			     : "cc", "memory");
+#endif /* !x86_64 */
+	return hv_status;
+}
 
 void hyperv_init(void);
 void hyperv_report_panic(struct pt_regs *regs);
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 59c11ff..45e806e 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -32,6 +32,8 @@
 #include <linux/hyperv.h>
 #include <linux/export.h>
 #include <asm/hyperv.h>
+#include <asm/mshyperv.h>
+
 #include "hyperv_vmbus.h"
 
 
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index e09fc82..d1ae02d 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1188,7 +1188,6 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj,
 			bool fb_overlap_ok);
 void vmbus_free_mmio(resource_size_t start, resource_size_t size);
 int vmbus_cpu_number_to_vp_number(int cpu_number);
-u64 hv_do_hypercall(u64 control, void *input, void *output);
 
 /*
  * GUID definitions of various offer types - services offered to the guest.
-- 
1.7.1

[toc] | [prev] | [next] | [standalone]

#1674267 — [PATCH 08/10] x86/hyper-v: use hypercall for remote TLB flush

From: Vitaly Kuznetsov <vkuznets@redhat.com>

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@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 arch/x86/hyperv/Makefile           |    2 +-
 arch/x86/hyperv/hv_init.c          |    2 +
 arch/x86/hyperv/mmu.c              |  135 ++++++++++++++++++++++++++++++++++++
 arch/x86/include/asm/mshyperv.h    |    4 +
 arch/x86/include/uapi/asm/hyperv.h |    7 ++
 arch/x86/kernel/cpu/mshyperv.c     |    1 +
 6 files changed, 150 insertions(+), 1 deletions(-)
 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 e93b9a0..1a8eb55 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 0000000..fe87ffe
--- /dev/null
+++ b/arch/x86/hyperv/mmu.c
@@ -0,0 +1,135 @@
+#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 filled
+ * in gva_list (including offset)
+ */
+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;
+}
+
+static void hyperv_flush_tlb_others(const struct cpumask *cpus,
+				    struct mm_struct *mm, unsigned long start,
+				    unsigned long end)
+{
+	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 (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 < 64)
+				__set_bit(vcpu, (unsigned long *)
+					  &flush->processor_mask);
+			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)) / sizeof(flush->gva_list[0]);
+
+	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 if (end && ((end - 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, start, 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, 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 7581251..fe4ebdb 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -6,6 +6,7 @@
 #include <linux/clocksource.h>
 #include <linux/nmi.h>
 #include <asm/hyperv.h>
+#include <asm/paravirt_types.h>
 
 /*
  * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
@@ -309,6 +310,8 @@ 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);
@@ -316,6 +319,7 @@ static inline int hv_cpu_number_to_vp_number(int cpu_number)
 static inline void hyperv_init(void) {}
 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 */
 
 #ifdef CONFIG_HYPERV_TSCPAGE
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index 432df4b..cc0e70c 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			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 f259e01..2a1918d 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -239,6 +239,7 @@ 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
 }
 
-- 
1.7.1

[toc] | [prev] | [next] | [standalone]

#1674268 — [PATCH 06/10] x86/hyper-v: implement rep hypercalls

From: Vitaly Kuznetsov <vkuznets@redhat.com>

Rep hypercalls are normal hypercalls which perform multiple actions at
once. Hyper-V guarantees to return exectution to the caller in not more
than 50us and the caller needs to use hypercall continuation. Touch NMI
watchdog between hypercall invocations.

This is going to be used for HvFlushVirtualAddressList hypercall for
remote TLB flushing.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 arch/x86/include/asm/mshyperv.h |   39 +++++++++++++++++++++++++++++++++++++++
 1 files changed, 39 insertions(+), 0 deletions(-)

diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index f3bedb4..ed8107d 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -4,6 +4,7 @@
 #include <linux/types.h>
 #include <linux/interrupt.h>
 #include <linux/clocksource.h>
+#include <linux/nmi.h>
 #include <asm/hyperv.h>
 
 /*
@@ -211,7 +212,13 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 	return hv_status;
 }
 
+#define HV_HYPERCALL_RESULT_MASK	GENMASK_ULL(15, 0)
 #define HV_HYPERCALL_FAST_BIT		BIT(16)
+#define HV_HYPERCALL_VARHEAD_OFFSET	17
+#define HV_HYPERCALL_REP_COMP_OFFSET	32
+#define HV_HYPERCALL_REP_COMP_MASK	GENMASK_ULL(43, 32)
+#define HV_HYPERCALL_REP_START_OFFSET	48
+#define HV_HYPERCALL_REP_START_MASK	GENMASK_ULL(59, 48)
 
 /* Fast hypercall with 8 bytes of input and no output */
 static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
@@ -245,6 +252,38 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
 		return hv_status;
 }
 
+/*
+ * Rep hypercalls. Callers of this functions are supposed to ensure that
+ * rep_count and varhead_size comply with Hyper-V hypercall definition.
+ */
+static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size,
+				      void *input, void *output)
+{
+	u64 control = code;
+	u64 status;
+	u16 rep_comp;
+
+	control |= (u64)varhead_size << HV_HYPERCALL_VARHEAD_OFFSET;
+	control |= (u64)rep_count << HV_HYPERCALL_REP_COMP_OFFSET;
+
+	do {
+		status = hv_do_hypercall(control, input, output);
+		if ((status & HV_HYPERCALL_RESULT_MASK) != HV_STATUS_SUCCESS)
+			return status;
+
+		/* Bits 32-43 of status have 'Reps completed' data. */
+		rep_comp = (status & HV_HYPERCALL_REP_COMP_MASK) >>
+			HV_HYPERCALL_REP_COMP_OFFSET;
+
+		control &= ~HV_HYPERCALL_REP_START_MASK;
+		control |= (u64)rep_comp << HV_HYPERCALL_REP_START_OFFSET;
+
+		touch_nmi_watchdog();
+	} while (rep_comp < rep_count);
+
+	return status;
+}
+
 void hyperv_init(void);
 void hyperv_report_panic(struct pt_regs *regs);
 bool hv_is_hypercall_page_setup(void);
-- 
1.7.1

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web