[PATCH v5 03/10] x86/hyper-v: make hv_do_hypercall() inline

[Vitaly Kuznetsov]

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@xxxxxxxxxx>
Acked-by: K. Y. Srinivasan <kys@xxxxxxxxxxxxx>
---
Changes since v4:
- Use upper_32_bits()/lower_32_bits macros [Andy Shevchenko]
- Use "A" in 32 bits asm [Jork Loeser]
---
 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 struct clocksource hyperv_cs_msr = {
 	.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 d42b6eb..282eaed 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -172,6 +172,45 @@ void hv_remove_crash_handler(void);
 
 #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)ULLONG_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)ULLONG_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 c2d74ee..4a0a9f6 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.
-- 
2.9.4