linux-arch.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Waiman Long <Waiman.Long@hp.com>
To: Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>
Cc: linux-arch@vger.kernel.org, x86@kernel.org,
	linux-kernel@vger.kernel.org,
	virtualization@lists.linux-foundation.org,
	xen-devel@lists.xenproject.org, kvm@vger.kernel.org,
	Paolo Bonzini <paolo.bonzini@gmail.com>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	Boris Ostrovsky <boris.ostrovsky@oracle.com>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	Rik van Riel <riel@redhat.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>,
	David Vrabel <david.vrabel@citrix.com>,
	Oleg Nesterov <oleg@redhat.com>,
	Daniel J Blueman <daniel@numascale.com>,
	Scott J Norton <scott.norton@hp.com>,
	Douglas Hatch <doug.hatch@hp.com>,
	"Peter Zijlstra (Intel)" <peterz@infradead.org>,
	Waiman Long <Waiman.Long@hp.com>
Subject: [PATCH v15 10/15] pvqspinlock: Implement the paravirt qspinlock for x86
Date: Mon,  6 Apr 2015 22:55:45 -0400	[thread overview]
Message-ID: <1428375350-9213-11-git-send-email-Waiman.Long@hp.com> (raw)
In-Reply-To: <1428375350-9213-1-git-send-email-Waiman.Long@hp.com>

From: Peter Zijlstra (Intel) <peterz@infradead.org>

We use the regular paravirt call patching to switch between:

  native_queue_spin_lock_slowpath()	__pv_queue_spin_lock_slowpath()
  native_queue_spin_unlock()		__pv_queue_spin_unlock()

We use a callee saved call for the unlock function which reduces the
i-cache footprint and allows 'inlining' of SPIN_UNLOCK functions
again.

We further optimize the unlock path by patching the direct call with a
"movb $0,%arg1" if we are indeed using the native unlock code. This
makes the unlock code almost as fast as the !PARAVIRT case.

This significantly lowers the overhead of having
CONFIG_PARAVIRT_SPINLOCKS enabled, even for native code.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
---
 arch/x86/Kconfig                      |    2 +-
 arch/x86/include/asm/paravirt.h       |   28 +++++++++++++++++++++++++++-
 arch/x86/include/asm/paravirt_types.h |   10 ++++++++++
 arch/x86/include/asm/qspinlock.h      |   25 ++++++++++++++++++++++++-
 arch/x86/kernel/paravirt-spinlocks.c  |   24 +++++++++++++++++++++++-
 arch/x86/kernel/paravirt_patch_32.c   |   22 ++++++++++++++++++----
 arch/x86/kernel/paravirt_patch_64.c   |   22 ++++++++++++++++++----
 7 files changed, 121 insertions(+), 12 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 49fecb1..a0946e7 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -661,7 +661,7 @@ config PARAVIRT_DEBUG
 config PARAVIRT_SPINLOCKS
 	bool "Paravirtualization layer for spinlocks"
 	depends on PARAVIRT && SMP
-	select UNINLINE_SPIN_UNLOCK
+	select UNINLINE_SPIN_UNLOCK if !QUEUE_SPINLOCK
 	---help---
 	  Paravirtualized spinlocks allow a pvops backend to replace the
 	  spinlock implementation with something virtualization-friendly
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 965c47d..dd40269 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -712,6 +712,30 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 
 #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
 
+#ifdef CONFIG_QUEUE_SPINLOCK
+
+static __always_inline void pv_queue_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+{
+	PVOP_VCALL2(pv_lock_ops.queue_spin_lock_slowpath, lock, val);
+}
+
+static __always_inline void pv_queue_spin_unlock(struct qspinlock *lock)
+{
+	PVOP_VCALLEE1(pv_lock_ops.queue_spin_unlock, lock);
+}
+
+static __always_inline void pv_wait(u8 *ptr, u8 val)
+{
+	PVOP_VCALL2(pv_lock_ops.wait, ptr, val);
+}
+
+static __always_inline void pv_kick(int cpu)
+{
+	PVOP_VCALL1(pv_lock_ops.kick, cpu);
+}
+
+#else /* !CONFIG_QUEUE_SPINLOCK */
+
 static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock,
 							__ticket_t ticket)
 {
@@ -724,7 +748,9 @@ static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock,
 	PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket);
 }
 
-#endif
+#endif /* CONFIG_QUEUE_SPINLOCK */
+
+#endif /* SMP && PARAVIRT_SPINLOCKS */
 
 #ifdef CONFIG_X86_32
 #define PV_SAVE_REGS "pushl %ecx; pushl %edx;"
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 7549b8b..f6acaea 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -333,9 +333,19 @@ struct arch_spinlock;
 typedef u16 __ticket_t;
 #endif
 
+struct qspinlock;
+
 struct pv_lock_ops {
+#ifdef CONFIG_QUEUE_SPINLOCK
+	void (*queue_spin_lock_slowpath)(struct qspinlock *lock, u32 val);
+	struct paravirt_callee_save queue_spin_unlock;
+
+	void (*wait)(u8 *ptr, u8 val);
+	void (*kick)(int cpu);
+#else /* !CONFIG_QUEUE_SPINLOCK */
 	struct paravirt_callee_save lock_spinning;
 	void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket);
+#endif /* !CONFIG_QUEUE_SPINLOCK */
 };
 
 /* This contains all the paravirt structures: we get a convenient
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index 64c925e..c8290db 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -3,6 +3,7 @@
 
 #include <asm/cpufeature.h>
 #include <asm-generic/qspinlock_types.h>
+#include <asm/paravirt.h>
 
 #define	queue_spin_unlock queue_spin_unlock
 /**
@@ -11,11 +12,33 @@
  *
  * A smp_store_release() on the least-significant byte.
  */
-static inline void queue_spin_unlock(struct qspinlock *lock)
+static inline void native_queue_spin_unlock(struct qspinlock *lock)
 {
 	smp_store_release((u8 *)lock, 0);
 }
 
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+extern void native_queue_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __pv_init_lock_hash(void);
+extern void __pv_queue_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __raw_callee_save___pv_queue_spin_unlock(struct qspinlock *lock);
+
+static inline void queue_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+{
+	pv_queue_spin_lock_slowpath(lock, val);
+}
+
+static inline void queue_spin_unlock(struct qspinlock *lock)
+{
+	pv_queue_spin_unlock(lock);
+}
+#else
+static inline void queue_spin_unlock(struct qspinlock *lock)
+{
+	native_queue_spin_unlock(lock);
+}
+#endif
+
 #define virt_queue_spin_lock virt_queue_spin_lock
 
 static inline bool virt_queue_spin_lock(struct qspinlock *lock)
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index bbb6c73..ff134b4 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -8,11 +8,33 @@
 
 #include <asm/paravirt.h>
 
+#ifdef CONFIG_QUEUE_SPINLOCK
+__visible void __native_queue_spin_unlock(struct qspinlock *lock)
+{
+	native_queue_spin_unlock(lock);
+}
+
+PV_CALLEE_SAVE_REGS_THUNK(__native_queue_spin_unlock);
+
+bool pv_is_native_spin_unlock(void)
+{
+	return pv_lock_ops.queue_spin_unlock.func ==
+		__raw_callee_save___native_queue_spin_unlock;
+}
+#endif
+
 struct pv_lock_ops pv_lock_ops = {
 #ifdef CONFIG_SMP
+#ifdef CONFIG_QUEUE_SPINLOCK
+	.queue_spin_lock_slowpath = native_queue_spin_lock_slowpath,
+	.queue_spin_unlock = PV_CALLEE_SAVE(__native_queue_spin_unlock),
+	.wait = paravirt_nop,
+	.kick = paravirt_nop,
+#else /* !CONFIG_QUEUE_SPINLOCK */
 	.lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop),
 	.unlock_kick = paravirt_nop,
-#endif
+#endif /* !CONFIG_QUEUE_SPINLOCK */
+#endif /* SMP */
 };
 EXPORT_SYMBOL(pv_lock_ops);
 
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index d9f32e6..5462727 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -12,6 +12,10 @@ DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax");
 DEF_NATIVE(pv_cpu_ops, clts, "clts");
 DEF_NATIVE(pv_cpu_ops, read_tsc, "rdtsc");
 
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUE_SPINLOCKS)
+DEF_NATIVE(pv_lock_ops, queue_spin_unlock, "movb $0, (%eax)");
+#endif
+
 unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
 {
 	/* arg in %eax, return in %eax */
@@ -24,6 +28,8 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
 	return 0;
 }
 
+extern bool pv_is_native_spin_unlock(void);
+
 unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		      unsigned long addr, unsigned len)
 {
@@ -47,14 +53,22 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_mmu_ops, write_cr3);
 		PATCH_SITE(pv_cpu_ops, clts);
 		PATCH_SITE(pv_cpu_ops, read_tsc);
-
-	patch_site:
-		ret = paravirt_patch_insns(ibuf, len, start, end);
-		break;
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUE_SPINLOCKS)
+		case PARAVIRT_PATCH(pv_lock_ops.queue_spin_unlock):
+			if (pv_is_native_spin_unlock()) {
+				start = start_pv_lock_ops_queue_spin_unlock;
+				end   = end_pv_lock_ops_queue_spin_unlock;
+				goto patch_site;
+			}
+#endif
 
 	default:
 		ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
 		break;
+
+	patch_site:
+		ret = paravirt_patch_insns(ibuf, len, start, end);
+		break;
 	}
 #undef PATCH_SITE
 	return ret;
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index a1da673..6936344 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -21,6 +21,10 @@ DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs");
 DEF_NATIVE(, mov32, "mov %edi, %eax");
 DEF_NATIVE(, mov64, "mov %rdi, %rax");
 
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUE_SPINLOCK)
+DEF_NATIVE(pv_lock_ops, queue_spin_unlock, "movb $0, (%rdi)");
+#endif
+
 unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
 {
 	return paravirt_patch_insns(insnbuf, len,
@@ -33,6 +37,8 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
 				    start__mov64, end__mov64);
 }
 
+extern bool pv_is_native_spin_unlock(void);
+
 unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		      unsigned long addr, unsigned len)
 {
@@ -59,14 +65,22 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_cpu_ops, clts);
 		PATCH_SITE(pv_mmu_ops, flush_tlb_single);
 		PATCH_SITE(pv_cpu_ops, wbinvd);
-
-	patch_site:
-		ret = paravirt_patch_insns(ibuf, len, start, end);
-		break;
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUE_SPINLOCK)
+		case PARAVIRT_PATCH(pv_lock_ops.queue_spin_unlock):
+			if (pv_is_native_spin_unlock()) {
+				start = start_pv_lock_ops_queue_spin_unlock;
+				end   = end_pv_lock_ops_queue_spin_unlock;
+				goto patch_site;
+			}
+#endif
 
 	default:
 		ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
 		break;
+
+	patch_site:
+		ret = paravirt_patch_insns(ibuf, len, start, end);
+		break;
 	}
 #undef PATCH_SITE
 	return ret;
-- 
1.7.1

WARNING: multiple messages have this Message-ID (diff)
From: Waiman Long <Waiman.Long@hp.com>
To: Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
	Peter Zijlstra <peterz@infradead.org>
Cc: linux-arch@vger.kernel.org, x86@kernel.org,
	linux-kernel@vger.kernel.org,
	virtualization@lists.linux-foundation.org,
	xen-devel@lists.xenproject.org, kvm@vger.kernel.org,
	Paolo Bonzini <paolo.bonzini@gmail.com>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	Boris Ostrovsky <boris.ostrovsky@oracle.com>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	Rik van Riel <riel@redhat.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>,
	David Vrabel <david.vrabel@citrix.com>,
	Oleg Nesterov <oleg@redhat.com>,
	Daniel J Blueman <daniel@numascale.com>,
	Scott J Norton <scott.norton@hp.com>,
	Douglas Hatch <doug.hatch@hp.com>,
	Waiman Long <Waiman.Long@hp.com>
Subject: [PATCH v15 10/15] pvqspinlock: Implement the paravirt qspinlock for x86
Date: Mon,  6 Apr 2015 22:55:45 -0400	[thread overview]
Message-ID: <1428375350-9213-11-git-send-email-Waiman.Long@hp.com> (raw)
Message-ID: <20150407025545.--urC_cyhnpjgxJNRaaeQgAUM7EtFVfT9lCC1tgqSJA@z> (raw)
In-Reply-To: <1428375350-9213-1-git-send-email-Waiman.Long@hp.com>

From: Peter Zijlstra (Intel) <peterz@infradead.org>

We use the regular paravirt call patching to switch between:

  native_queue_spin_lock_slowpath()	__pv_queue_spin_lock_slowpath()
  native_queue_spin_unlock()		__pv_queue_spin_unlock()

We use a callee saved call for the unlock function which reduces the
i-cache footprint and allows 'inlining' of SPIN_UNLOCK functions
again.

We further optimize the unlock path by patching the direct call with a
"movb $0,%arg1" if we are indeed using the native unlock code. This
makes the unlock code almost as fast as the !PARAVIRT case.

This significantly lowers the overhead of having
CONFIG_PARAVIRT_SPINLOCKS enabled, even for native code.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
---
 arch/x86/Kconfig                      |    2 +-
 arch/x86/include/asm/paravirt.h       |   28 +++++++++++++++++++++++++++-
 arch/x86/include/asm/paravirt_types.h |   10 ++++++++++
 arch/x86/include/asm/qspinlock.h      |   25 ++++++++++++++++++++++++-
 arch/x86/kernel/paravirt-spinlocks.c  |   24 +++++++++++++++++++++++-
 arch/x86/kernel/paravirt_patch_32.c   |   22 ++++++++++++++++++----
 arch/x86/kernel/paravirt_patch_64.c   |   22 ++++++++++++++++++----
 7 files changed, 121 insertions(+), 12 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 49fecb1..a0946e7 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -661,7 +661,7 @@ config PARAVIRT_DEBUG
 config PARAVIRT_SPINLOCKS
 	bool "Paravirtualization layer for spinlocks"
 	depends on PARAVIRT && SMP
-	select UNINLINE_SPIN_UNLOCK
+	select UNINLINE_SPIN_UNLOCK if !QUEUE_SPINLOCK
 	---help---
 	  Paravirtualized spinlocks allow a pvops backend to replace the
 	  spinlock implementation with something virtualization-friendly
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 965c47d..dd40269 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -712,6 +712,30 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 
 #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
 
+#ifdef CONFIG_QUEUE_SPINLOCK
+
+static __always_inline void pv_queue_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+{
+	PVOP_VCALL2(pv_lock_ops.queue_spin_lock_slowpath, lock, val);
+}
+
+static __always_inline void pv_queue_spin_unlock(struct qspinlock *lock)
+{
+	PVOP_VCALLEE1(pv_lock_ops.queue_spin_unlock, lock);
+}
+
+static __always_inline void pv_wait(u8 *ptr, u8 val)
+{
+	PVOP_VCALL2(pv_lock_ops.wait, ptr, val);
+}
+
+static __always_inline void pv_kick(int cpu)
+{
+	PVOP_VCALL1(pv_lock_ops.kick, cpu);
+}
+
+#else /* !CONFIG_QUEUE_SPINLOCK */
+
 static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock,
 							__ticket_t ticket)
 {
@@ -724,7 +748,9 @@ static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock,
 	PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket);
 }
 
-#endif
+#endif /* CONFIG_QUEUE_SPINLOCK */
+
+#endif /* SMP && PARAVIRT_SPINLOCKS */
 
 #ifdef CONFIG_X86_32
 #define PV_SAVE_REGS "pushl %ecx; pushl %edx;"
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 7549b8b..f6acaea 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -333,9 +333,19 @@ struct arch_spinlock;
 typedef u16 __ticket_t;
 #endif
 
+struct qspinlock;
+
 struct pv_lock_ops {
+#ifdef CONFIG_QUEUE_SPINLOCK
+	void (*queue_spin_lock_slowpath)(struct qspinlock *lock, u32 val);
+	struct paravirt_callee_save queue_spin_unlock;
+
+	void (*wait)(u8 *ptr, u8 val);
+	void (*kick)(int cpu);
+#else /* !CONFIG_QUEUE_SPINLOCK */
 	struct paravirt_callee_save lock_spinning;
 	void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket);
+#endif /* !CONFIG_QUEUE_SPINLOCK */
 };
 
 /* This contains all the paravirt structures: we get a convenient
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index 64c925e..c8290db 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -3,6 +3,7 @@
 
 #include <asm/cpufeature.h>
 #include <asm-generic/qspinlock_types.h>
+#include <asm/paravirt.h>
 
 #define	queue_spin_unlock queue_spin_unlock
 /**
@@ -11,11 +12,33 @@
  *
  * A smp_store_release() on the least-significant byte.
  */
-static inline void queue_spin_unlock(struct qspinlock *lock)
+static inline void native_queue_spin_unlock(struct qspinlock *lock)
 {
 	smp_store_release((u8 *)lock, 0);
 }
 
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+extern void native_queue_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __pv_init_lock_hash(void);
+extern void __pv_queue_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __raw_callee_save___pv_queue_spin_unlock(struct qspinlock *lock);
+
+static inline void queue_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+{
+	pv_queue_spin_lock_slowpath(lock, val);
+}
+
+static inline void queue_spin_unlock(struct qspinlock *lock)
+{
+	pv_queue_spin_unlock(lock);
+}
+#else
+static inline void queue_spin_unlock(struct qspinlock *lock)
+{
+	native_queue_spin_unlock(lock);
+}
+#endif
+
 #define virt_queue_spin_lock virt_queue_spin_lock
 
 static inline bool virt_queue_spin_lock(struct qspinlock *lock)
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index bbb6c73..ff134b4 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -8,11 +8,33 @@
 
 #include <asm/paravirt.h>
 
+#ifdef CONFIG_QUEUE_SPINLOCK
+__visible void __native_queue_spin_unlock(struct qspinlock *lock)
+{
+	native_queue_spin_unlock(lock);
+}
+
+PV_CALLEE_SAVE_REGS_THUNK(__native_queue_spin_unlock);
+
+bool pv_is_native_spin_unlock(void)
+{
+	return pv_lock_ops.queue_spin_unlock.func ==
+		__raw_callee_save___native_queue_spin_unlock;
+}
+#endif
+
 struct pv_lock_ops pv_lock_ops = {
 #ifdef CONFIG_SMP
+#ifdef CONFIG_QUEUE_SPINLOCK
+	.queue_spin_lock_slowpath = native_queue_spin_lock_slowpath,
+	.queue_spin_unlock = PV_CALLEE_SAVE(__native_queue_spin_unlock),
+	.wait = paravirt_nop,
+	.kick = paravirt_nop,
+#else /* !CONFIG_QUEUE_SPINLOCK */
 	.lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop),
 	.unlock_kick = paravirt_nop,
-#endif
+#endif /* !CONFIG_QUEUE_SPINLOCK */
+#endif /* SMP */
 };
 EXPORT_SYMBOL(pv_lock_ops);
 
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index d9f32e6..5462727 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -12,6 +12,10 @@ DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax");
 DEF_NATIVE(pv_cpu_ops, clts, "clts");
 DEF_NATIVE(pv_cpu_ops, read_tsc, "rdtsc");
 
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUE_SPINLOCKS)
+DEF_NATIVE(pv_lock_ops, queue_spin_unlock, "movb $0, (%eax)");
+#endif
+
 unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
 {
 	/* arg in %eax, return in %eax */
@@ -24,6 +28,8 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
 	return 0;
 }
 
+extern bool pv_is_native_spin_unlock(void);
+
 unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		      unsigned long addr, unsigned len)
 {
@@ -47,14 +53,22 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_mmu_ops, write_cr3);
 		PATCH_SITE(pv_cpu_ops, clts);
 		PATCH_SITE(pv_cpu_ops, read_tsc);
-
-	patch_site:
-		ret = paravirt_patch_insns(ibuf, len, start, end);
-		break;
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUE_SPINLOCKS)
+		case PARAVIRT_PATCH(pv_lock_ops.queue_spin_unlock):
+			if (pv_is_native_spin_unlock()) {
+				start = start_pv_lock_ops_queue_spin_unlock;
+				end   = end_pv_lock_ops_queue_spin_unlock;
+				goto patch_site;
+			}
+#endif
 
 	default:
 		ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
 		break;
+
+	patch_site:
+		ret = paravirt_patch_insns(ibuf, len, start, end);
+		break;
 	}
 #undef PATCH_SITE
 	return ret;
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index a1da673..6936344 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -21,6 +21,10 @@ DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs");
 DEF_NATIVE(, mov32, "mov %edi, %eax");
 DEF_NATIVE(, mov64, "mov %rdi, %rax");
 
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUE_SPINLOCK)
+DEF_NATIVE(pv_lock_ops, queue_spin_unlock, "movb $0, (%rdi)");
+#endif
+
 unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
 {
 	return paravirt_patch_insns(insnbuf, len,
@@ -33,6 +37,8 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
 				    start__mov64, end__mov64);
 }
 
+extern bool pv_is_native_spin_unlock(void);
+
 unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		      unsigned long addr, unsigned len)
 {
@@ -59,14 +65,22 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_cpu_ops, clts);
 		PATCH_SITE(pv_mmu_ops, flush_tlb_single);
 		PATCH_SITE(pv_cpu_ops, wbinvd);
-
-	patch_site:
-		ret = paravirt_patch_insns(ibuf, len, start, end);
-		break;
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUE_SPINLOCK)
+		case PARAVIRT_PATCH(pv_lock_ops.queue_spin_unlock):
+			if (pv_is_native_spin_unlock()) {
+				start = start_pv_lock_ops_queue_spin_unlock;
+				end   = end_pv_lock_ops_queue_spin_unlock;
+				goto patch_site;
+			}
+#endif
 
 	default:
 		ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
 		break;
+
+	patch_site:
+		ret = paravirt_patch_insns(ibuf, len, start, end);
+		break;
 	}
 #undef PATCH_SITE
 	return ret;
-- 
1.7.1


  parent reply	other threads:[~2015-04-07  2:55 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-04-07  2:55 [PATCH v15 00/15] qspinlock: a 4-byte queue spinlock with PV support Waiman Long
2015-04-07  2:55 ` [PATCH v15 01/15] qspinlock: A simple generic 4-byte queue spinlock Waiman Long
2015-04-07  2:55   ` Waiman Long
2015-04-07  2:55 ` [PATCH v15 02/15] qspinlock, x86: Enable x86-64 to use " Waiman Long
2015-04-07  2:55   ` Waiman Long
2015-04-07  2:55 ` [PATCH v15 03/15] qspinlock: Add pending bit Waiman Long
2015-04-07  2:55   ` Waiman Long
2015-04-07  2:55 ` [PATCH v15 04/15] qspinlock: Extract out code snippets for the next patch Waiman Long
2015-04-07  2:55   ` Waiman Long
2015-04-07  2:55 ` [PATCH v15 05/15] qspinlock: Optimize for smaller NR_CPUS Waiman Long
2015-04-07  2:55   ` Waiman Long
2015-04-07  2:55 ` [PATCH v15 06/15] qspinlock: Use a simple write to grab the lock Waiman Long
2015-04-07  2:55   ` Waiman Long
2015-04-07  2:55 ` [PATCH v15 07/15] qspinlock: Revert to test-and-set on hypervisors Waiman Long
2015-04-07  2:55   ` Waiman Long
2015-04-07  2:55 ` [PATCH v15 08/15] lfsr: a simple binary Galois linear feedback shift register Waiman Long
2015-04-07  2:55   ` Waiman Long
2015-04-07  2:55 ` [PATCH v15 09/15] pvqspinlock: Implement simple paravirt support for the qspinlock Waiman Long
2015-04-07  2:55   ` Waiman Long
2015-04-09 18:13   ` Peter Zijlstra
2015-04-09 18:13     ` Peter Zijlstra
2015-04-09 18:23     ` Peter Zijlstra
2015-04-09 18:23       ` Peter Zijlstra
2015-04-09 20:36       ` Waiman Long
2015-04-09 20:36         ` Waiman Long
2015-04-09 21:41     ` Waiman Long
2015-04-09 21:41       ` Waiman Long
2015-04-13 14:47       ` Peter Zijlstra
2015-04-13 15:45         ` Waiman Long
2015-04-13 15:45           ` Waiman Long
2015-04-13 15:08       ` Peter Zijlstra
2015-04-13 15:51         ` Waiman Long
2015-04-13 15:51           ` Waiman Long
2015-04-13 15:09       ` Peter Zijlstra
2015-04-13 16:19         ` Waiman Long
2015-04-07  2:55 ` Waiman Long [this message]
2015-04-07  2:55   ` [PATCH v15 10/15] pvqspinlock: Implement the paravirt qspinlock for x86 Waiman Long
2015-04-07  2:55 ` [PATCH v15 11/15] pvqspinlock, x86: Enable PV qspinlock for KVM Waiman Long
2015-04-07  2:55   ` Waiman Long
2015-04-07  2:55 ` [PATCH v15 12/15] pvqspinlock, x86: Enable PV qspinlock for Xen Waiman Long
2015-04-07  2:55   ` Waiman Long
2015-04-08 12:01   ` [Xen-devel] " David Vrabel
2015-04-08 12:01     ` David Vrabel
2015-04-08 17:42     ` Waiman Long
2015-04-07  2:55 ` [PATCH v15 13/15] pvqspinlock: Only kick CPU at unlock time Waiman Long
2015-04-07  2:55   ` Waiman Long
2015-04-09 19:57   ` Peter Zijlstra
2015-04-09 20:07     ` Peter Zijlstra
2015-04-09 20:07       ` Peter Zijlstra
2015-04-09 22:06     ` Waiman Long
2015-04-07  2:55 ` [PATCH v15 14/15] pvqspinlock: Improve slowpath performance by avoiding cmpxchg Waiman Long
2015-04-07  2:55   ` Waiman Long
2015-04-07  2:55 ` [PATCH v15 15/15] pvqspinlock: Add debug code to check for PV lock hash sanity Waiman Long
2015-04-07  2:55   ` Waiman Long

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1428375350-9213-11-git-send-email-Waiman.Long@hp.com \
    --to=waiman.long@hp.com \
    --cc=boris.ostrovsky@oracle.com \
    --cc=daniel@numascale.com \
    --cc=david.vrabel@citrix.com \
    --cc=doug.hatch@hp.com \
    --cc=hpa@zytor.com \
    --cc=konrad.wilk@oracle.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=oleg@redhat.com \
    --cc=paolo.bonzini@gmail.com \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=raghavendra.kt@linux.vnet.ibm.com \
    --cc=riel@redhat.com \
    --cc=scott.norton@hp.com \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=virtualization@lists.linux-foundation.org \
    --cc=x86@kernel.org \
    --cc=xen-devel@lists.xenproject.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).