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, Waiman Long <Waiman.Long@hp.com>,
	Rik van Riel <riel@redhat.com>,
	Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>,
	Gleb Natapov <gleb@redhat.com>,
	kvm@vger.kernel.org,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Scott J Norton <scott.norton@hp.com>,
	x86@kernel.org, Paolo Bonzini <paolo.bonzini@gmail.com>,
	linux-kernel@vger.kernel.org,
	virtualization@lists.linux-foundation.org,
	Chegu Vinod <chegu_vinod@hp.com>,
	David Vrabel <david.vrabel@citrix.com>,
	Oleg Nesterov <oleg@redhat.com>,
	xen-devel@lists.xenproject.org,
	Boris Ostrovsky <boris.ostrovsky@oracle.com>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	Linus Torvalds <torvalds@linux-foundation.org>
Subject: [PATCH v11 02/16] qspinlock, x86: Enable x86-64 to use queue spinlock
Date: Fri, 30 May 2014 11:43:48 -0400	[thread overview]
Message-ID: <1401464642-33890-3-git-send-email-Waiman.Long@hp.com> (raw)
In-Reply-To: <1401464642-33890-1-git-send-email-Waiman.Long@hp.com>

This patch makes the necessary changes at the x86 architecture
specific layer to enable the use of queue spinlock for x86-64. As
x86-32 machines are typically not multi-socket. The benefit of queue
spinlock may not be apparent. So queue spinlock is not enabled.

Currently, there is some incompatibilities between the para-virtualized
spinlock code (which hard-codes the use of ticket spinlock) and the
queue spinlock. Therefore, the use of queue spinlock is disabled when
the para-virtualized spinlock is enabled.

The arch/x86/include/asm/qspinlock.h header file includes some x86
specific optimization which will make the queue spinlock code perform
better than the generic implementation.

Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
---
 arch/x86/Kconfig                      |    1 +
 arch/x86/include/asm/qspinlock.h      |   29 +++++++++++++++++++++++++++++
 arch/x86/include/asm/spinlock.h       |    5 +++++
 arch/x86/include/asm/spinlock_types.h |    4 ++++
 4 files changed, 39 insertions(+), 0 deletions(-)
 create mode 100644 arch/x86/include/asm/qspinlock.h

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 25d2c6f..95c9c4e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -29,6 +29,7 @@ config X86
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select ARCH_SUPPORTS_INT128 if X86_64
 	select ARCH_WANTS_PROT_NUMA_PROT_NONE
+	select ARCH_USE_QUEUE_SPINLOCK
 	select HAVE_IDE
 	select HAVE_OPROFILE
 	select HAVE_PCSPKR_PLATFORM
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
new file mode 100644
index 0000000..e4a4f5d
--- /dev/null
+++ b/arch/x86/include/asm/qspinlock.h
@@ -0,0 +1,29 @@
+#ifndef _ASM_X86_QSPINLOCK_H
+#define _ASM_X86_QSPINLOCK_H
+
+#include <asm-generic/qspinlock_types.h>
+
+#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE)
+
+#define	queue_spin_unlock queue_spin_unlock
+/**
+ * queue_spin_unlock - release a queue spinlock
+ * @lock : Pointer to queue spinlock structure
+ *
+ * No special memory barrier other than a compiler one is needed for the
+ * x86 architecture. A compiler barrier is added at the end to make sure
+ * that the clearing the lock bit is done ASAP without artificial delay
+ * due to compiler optimization.
+ */
+static inline void queue_spin_unlock(struct qspinlock *lock)
+{
+	barrier();
+	ACCESS_ONCE(*(u8 *)lock) = 0;
+	barrier();
+}
+
+#endif /* !CONFIG_X86_OOSTORE && !CONFIG_X86_PPRO_FENCE */
+
+#include <asm-generic/qspinlock.h>
+
+#endif /* _ASM_X86_QSPINLOCK_H */
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 0f62f54..958d20f 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -42,6 +42,10 @@
 extern struct static_key paravirt_ticketlocks_enabled;
 static __always_inline bool static_key_false(struct static_key *key);
 
+#ifdef CONFIG_QUEUE_SPINLOCK
+#include <asm/qspinlock.h>
+#else
+
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
 
 static inline void __ticket_enter_slowpath(arch_spinlock_t *lock)
@@ -180,6 +184,7 @@ static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
 {
 	arch_spin_lock(lock);
 }
+#endif /* CONFIG_QUEUE_SPINLOCK */
 
 static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index 4f1bea1..7960268 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -23,6 +23,9 @@ typedef u32 __ticketpair_t;
 
 #define TICKET_SHIFT	(sizeof(__ticket_t) * 8)
 
+#ifdef CONFIG_QUEUE_SPINLOCK
+#include <asm-generic/qspinlock_types.h>
+#else
 typedef struct arch_spinlock {
 	union {
 		__ticketpair_t head_tail;
@@ -33,6 +36,7 @@ typedef struct arch_spinlock {
 } arch_spinlock_t;
 
 #define __ARCH_SPIN_LOCK_UNLOCKED	{ { 0 } }
+#endif /* CONFIG_QUEUE_SPINLOCK */
 
 #include <asm/rwlock.h>
 
-- 
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>, Gleb Natapov <gleb@redhat.com>,
	Scott J Norton <scott.norton@hp.com>,
	Chegu Vinod <chegu_vinod@hp.com>,
	Waiman Long <Waiman.Long@hp.com>
Subject: [PATCH v11 02/16] qspinlock, x86: Enable x86-64 to use queue spinlock
Date: Fri, 30 May 2014 11:43:48 -0400	[thread overview]
Message-ID: <1401464642-33890-3-git-send-email-Waiman.Long@hp.com> (raw)
Message-ID: <20140530154348.gisKL0Glg2kI7LnPesTrP90zB_mVT8k0cAdq38iO8vc@z> (raw)
In-Reply-To: <1401464642-33890-1-git-send-email-Waiman.Long@hp.com>

This patch makes the necessary changes at the x86 architecture
specific layer to enable the use of queue spinlock for x86-64. As
x86-32 machines are typically not multi-socket. The benefit of queue
spinlock may not be apparent. So queue spinlock is not enabled.

Currently, there is some incompatibilities between the para-virtualized
spinlock code (which hard-codes the use of ticket spinlock) and the
queue spinlock. Therefore, the use of queue spinlock is disabled when
the para-virtualized spinlock is enabled.

The arch/x86/include/asm/qspinlock.h header file includes some x86
specific optimization which will make the queue spinlock code perform
better than the generic implementation.

Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
---
 arch/x86/Kconfig                      |    1 +
 arch/x86/include/asm/qspinlock.h      |   29 +++++++++++++++++++++++++++++
 arch/x86/include/asm/spinlock.h       |    5 +++++
 arch/x86/include/asm/spinlock_types.h |    4 ++++
 4 files changed, 39 insertions(+), 0 deletions(-)
 create mode 100644 arch/x86/include/asm/qspinlock.h

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 25d2c6f..95c9c4e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -29,6 +29,7 @@ config X86
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select ARCH_SUPPORTS_INT128 if X86_64
 	select ARCH_WANTS_PROT_NUMA_PROT_NONE
+	select ARCH_USE_QUEUE_SPINLOCK
 	select HAVE_IDE
 	select HAVE_OPROFILE
 	select HAVE_PCSPKR_PLATFORM
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
new file mode 100644
index 0000000..e4a4f5d
--- /dev/null
+++ b/arch/x86/include/asm/qspinlock.h
@@ -0,0 +1,29 @@
+#ifndef _ASM_X86_QSPINLOCK_H
+#define _ASM_X86_QSPINLOCK_H
+
+#include <asm-generic/qspinlock_types.h>
+
+#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE)
+
+#define	queue_spin_unlock queue_spin_unlock
+/**
+ * queue_spin_unlock - release a queue spinlock
+ * @lock : Pointer to queue spinlock structure
+ *
+ * No special memory barrier other than a compiler one is needed for the
+ * x86 architecture. A compiler barrier is added at the end to make sure
+ * that the clearing the lock bit is done ASAP without artificial delay
+ * due to compiler optimization.
+ */
+static inline void queue_spin_unlock(struct qspinlock *lock)
+{
+	barrier();
+	ACCESS_ONCE(*(u8 *)lock) = 0;
+	barrier();
+}
+
+#endif /* !CONFIG_X86_OOSTORE && !CONFIG_X86_PPRO_FENCE */
+
+#include <asm-generic/qspinlock.h>
+
+#endif /* _ASM_X86_QSPINLOCK_H */
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 0f62f54..958d20f 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -42,6 +42,10 @@
 extern struct static_key paravirt_ticketlocks_enabled;
 static __always_inline bool static_key_false(struct static_key *key);
 
+#ifdef CONFIG_QUEUE_SPINLOCK
+#include <asm/qspinlock.h>
+#else
+
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
 
 static inline void __ticket_enter_slowpath(arch_spinlock_t *lock)
@@ -180,6 +184,7 @@ static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
 {
 	arch_spin_lock(lock);
 }
+#endif /* CONFIG_QUEUE_SPINLOCK */
 
 static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index 4f1bea1..7960268 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -23,6 +23,9 @@ typedef u32 __ticketpair_t;
 
 #define TICKET_SHIFT	(sizeof(__ticket_t) * 8)
 
+#ifdef CONFIG_QUEUE_SPINLOCK
+#include <asm-generic/qspinlock_types.h>
+#else
 typedef struct arch_spinlock {
 	union {
 		__ticketpair_t head_tail;
@@ -33,6 +36,7 @@ typedef struct arch_spinlock {
 } arch_spinlock_t;
 
 #define __ARCH_SPIN_LOCK_UNLOCKED	{ { 0 } }
+#endif /* CONFIG_QUEUE_SPINLOCK */
 
 #include <asm/rwlock.h>
 
-- 
1.7.1


  parent reply	other threads:[~2014-05-30 15:43 UTC|newest]

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-05-30 15:43 [PATCH v11 00/16] qspinlock: a 4-byte queue spinlock with PV support Waiman Long
2014-05-30 15:43 ` [PATCH v11 01/16] qspinlock: A simple generic 4-byte queue spinlock Waiman Long
2014-05-30 15:43   ` Waiman Long
2014-05-30 15:43 ` Waiman Long [this message]
2014-05-30 15:43   ` [PATCH v11 02/16] qspinlock, x86: Enable x86-64 to use " Waiman Long
2014-05-30 15:43 ` [PATCH v11 03/16] qspinlock: Add pending bit Waiman Long
2014-05-30 15:43   ` Waiman Long
2014-05-30 15:43 ` [PATCH v11 04/16] qspinlock: Extract out the exchange of tail code word Waiman Long
2014-05-30 15:43   ` Waiman Long
2014-05-30 15:43 ` [PATCH v11 05/16] qspinlock: Optimize for smaller NR_CPUS Waiman Long
2014-05-30 15:43   ` Waiman Long
2014-05-30 15:43 ` [PATCH v11 06/16] qspinlock: prolong the stay in the pending bit path Waiman Long
2014-05-30 15:43   ` Waiman Long
2014-06-11 10:26   ` Peter Zijlstra
2014-06-11 10:26     ` Peter Zijlstra
2014-06-11 21:22     ` Long, Wai Man
2014-06-11 21:22       ` Long, Wai Man
2014-06-12  6:00       ` Peter Zijlstra
2014-06-12 20:54         ` Waiman Long
2014-06-12 20:54           ` Waiman Long
2014-06-15 13:12           ` Peter Zijlstra
2014-06-15 13:12             ` Peter Zijlstra
2014-05-30 15:43 ` [PATCH v11 07/16] qspinlock: Use a simple write to grab the lock, if applicable Waiman Long
2014-05-30 15:43   ` Waiman Long
2014-05-30 15:43 ` [PATCH v11 08/16] qspinlock: Prepare for unfair lock support Waiman Long
2014-05-30 15:43   ` Waiman Long
2014-05-30 15:43 ` [PATCH v11 09/16] qspinlock, x86: Allow unfair spinlock in a virtual guest Waiman Long
2014-05-30 15:43   ` Waiman Long
2014-06-11 10:54   ` Peter Zijlstra
2014-06-11 10:54     ` Peter Zijlstra
2014-06-11 11:38     ` Peter Zijlstra
2014-06-12  1:37     ` Long, Wai Man
2014-06-12  1:37       ` Long, Wai Man
2014-06-12  5:50       ` Peter Zijlstra
2014-06-12  5:50         ` Peter Zijlstra
2014-06-12 21:08         ` Waiman Long
2014-06-12 21:08           ` Waiman Long
2014-06-15 13:14           ` Peter Zijlstra
2014-06-15 13:14             ` Peter Zijlstra
2014-05-30 15:43 ` [PATCH v11 10/16] qspinlock: Split the MCS queuing code into a separate slowerpath Waiman Long
2014-05-30 15:43   ` Waiman Long
2014-05-30 15:43 ` [PATCH v11 11/16] pvqspinlock, x86: Rename paravirt_ticketlocks_enabled Waiman Long
2014-05-30 15:43   ` Waiman Long
2014-05-30 15:43 ` [PATCH v11 12/16] pvqspinlock, x86: Add PV data structure & methods Waiman Long
2014-05-30 15:43   ` Waiman Long
2014-05-30 15:43 ` [PATCH v11 13/16] pvqspinlock: Enable coexistence with the unfair lock Waiman Long
2014-05-30 15:43   ` Waiman Long
2014-05-30 15:44 ` [PATCH v11 14/16] pvqspinlock: Add qspinlock para-virtualization support Waiman Long
2014-05-30 15:44   ` Waiman Long
2014-06-12  8:17   ` Peter Zijlstra
2014-06-12  8:17     ` Peter Zijlstra
2014-06-12 20:48     ` Waiman Long
2014-06-12 20:48       ` Waiman Long
2014-06-15 13:16       ` Peter Zijlstra
2014-06-15 13:16         ` Peter Zijlstra
2014-06-17 20:59         ` Konrad Rzeszutek Wilk
2014-06-17 20:59           ` Konrad Rzeszutek Wilk
2014-05-30 15:44 ` [PATCH v11 15/16] pvqspinlock, x86: Enable PV qspinlock PV for KVM Waiman Long
2014-05-30 15:44   ` Waiman Long
2014-05-30 15:44 ` [PATCH v11 16/16] pvqspinlock, x86: Enable PV qspinlock for XEN Waiman Long
2014-05-30 15:44   ` 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=1401464642-33890-3-git-send-email-Waiman.Long@hp.com \
    --to=waiman.long@hp.com \
    --cc=boris.ostrovsky@oracle.com \
    --cc=chegu_vinod@hp.com \
    --cc=david.vrabel@citrix.com \
    --cc=gleb@redhat.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).