summaryrefslogtreecommitdiff
path: root/include/asm-generic
diff options
context:
space:
mode:
authorPeter Zijlstra (Intel) <peterz@infradead.org>2015-04-24 14:56:34 -0400
committerIngo Molnar <mingo@kernel.org>2015-05-08 12:36:48 +0200
commit69f9cae90907e09af95fb991ed384670cef8dd32 (patch)
tree3ead8be87208a16234f8260353285b46cd77cb55 /include/asm-generic
parent6403bd7d0ea1878a487296114eccf78658d7dd7a (diff)
locking/qspinlock: Optimize for smaller NR_CPUS
When we allow for a max NR_CPUS < 2^14 we can optimize the pending wait-acquire and the xchg_tail() operations. By growing the pending bit to a byte, we reduce the tail to 16bit. This means we can use xchg16 for the tail part and do away with all the repeated compxchg() operations. This in turn allows us to unconditionally acquire; the locked state as observed by the wait loops cannot change. And because both locked and pending are now a full byte we can use simple stores for the state transition, obviating one atomic operation entirely. This optimization is needed to make the qspinlock achieve performance parity with ticket spinlock at light load. All this is horribly broken on Alpha pre EV56 (and any other arch that cannot do single-copy atomic byte stores). Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Daniel J Blueman <daniel@numascale.com> Cc: David Vrabel <david.vrabel@citrix.com> Cc: Douglas Hatch <doug.hatch@hp.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Paolo Bonzini <paolo.bonzini@gmail.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com> Cc: Rik van Riel <riel@redhat.com> Cc: Scott J Norton <scott.norton@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: virtualization@lists.linux-foundation.org Cc: xen-devel@lists.xenproject.org Link: http://lkml.kernel.org/r/1429901803-29771-6-git-send-email-Waiman.Long@hp.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'include/asm-generic')
-rw-r--r--include/asm-generic/qspinlock_types.h13
1 files changed, 13 insertions, 0 deletions
diff --git a/include/asm-generic/qspinlock_types.h b/include/asm-generic/qspinlock_types.h
index 3a7f67173bd0..85f888e86761 100644
--- a/include/asm-generic/qspinlock_types.h
+++ b/include/asm-generic/qspinlock_types.h
@@ -35,6 +35,14 @@ typedef struct qspinlock {
/*
* Bitfields in the atomic value:
*
+ * When NR_CPUS < 16K
+ * 0- 7: locked byte
+ * 8: pending
+ * 9-15: not used
+ * 16-17: tail index
+ * 18-31: tail cpu (+1)
+ *
+ * When NR_CPUS >= 16K
* 0- 7: locked byte
* 8: pending
* 9-10: tail index
@@ -47,7 +55,11 @@ typedef struct qspinlock {
#define _Q_LOCKED_MASK _Q_SET_MASK(LOCKED)
#define _Q_PENDING_OFFSET (_Q_LOCKED_OFFSET + _Q_LOCKED_BITS)
+#if CONFIG_NR_CPUS < (1U << 14)
+#define _Q_PENDING_BITS 8
+#else
#define _Q_PENDING_BITS 1
+#endif
#define _Q_PENDING_MASK _Q_SET_MASK(PENDING)
#define _Q_TAIL_IDX_OFFSET (_Q_PENDING_OFFSET + _Q_PENDING_BITS)
@@ -58,6 +70,7 @@ typedef struct qspinlock {
#define _Q_TAIL_CPU_BITS (32 - _Q_TAIL_CPU_OFFSET)
#define _Q_TAIL_CPU_MASK _Q_SET_MASK(TAIL_CPU)
+#define _Q_TAIL_OFFSET _Q_TAIL_IDX_OFFSET
#define _Q_TAIL_MASK (_Q_TAIL_IDX_MASK | _Q_TAIL_CPU_MASK)
#define _Q_LOCKED_VAL (1U << _Q_LOCKED_OFFSET)