[PATCH 4/4]x86: avoid tlbstate lock if no enough cpus

[PATCH 4/4]x86: avoid tlbstate lock if no enough cpus

[Shaohua Li]

This one isn't related to previous patch. If online cpus are below
NUM_INVALIDATE_TLB_VECTORS, we don't need the lock. The comments
in the code declares we don't need the check, but a hot lock still
needs an atomic operation and expensive, so add the check here.

Uses nr_cpu_ids here as suggested by Eric Dumazet.

Signed-off-by: Shaohua Li <shaohua.li@intel.com>
---
 arch/x86/mm/tlb.c |   11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

Index: linux/arch/x86/mm/tlb.c
===================================================================
--- linux.orig/arch/x86/mm/tlb.c	2010-11-04 10:59:09.000000000 +0800
+++ linux/arch/x86/mm/tlb.c	2010-11-04 13:17:51.000000000 +0800
@@ -179,12 +179,8 @@ static void flush_tlb_others_ipi(const s
 	sender = this_cpu_read(tlb_vector_offset);
 	f = &flush_state[sender];
 
-	/*
-	 * Could avoid this lock when
-	 * num_online_cpus() <= NUM_INVALIDATE_TLB_VECTORS, but it is
-	 * probably not worth checking this for a cache-hot lock.
-	 */
-	raw_spin_lock(&f->tlbstate_lock);
+	if (nr_cpu_ids > NUM_INVALIDATE_TLB_VECTORS)
+		raw_spin_lock(&f->tlbstate_lock);
 
 	f->flush_mm = mm;
 	f->flush_va = va;
@@ -202,7 +198,8 @@ static void flush_tlb_others_ipi(const s
 
 	f->flush_mm = NULL;
 	f->flush_va = 0;
-	raw_spin_unlock(&f->tlbstate_lock);
+	if (nr_cpu_ids > NUM_INVALIDATE_TLB_VECTORS)
+		raw_spin_unlock(&f->tlbstate_lock);
 }
 
 void native_flush_tlb_others(const struct cpumask *cpumask,

[tip:x86/mm] x86: Avoid tlbstate lock if not enough cpus

[tip-bot for Shaohua Li]

Commit-ID:  7064d865af804b9b841e7b9a3e9b653e40c3e5ca
Gitweb:     http://git.kernel.org/tip/7064d865af804b9b841e7b9a3e9b653e40c3e5ca
Author:     Shaohua Li <shaohua.li@intel.com>
AuthorDate: Mon, 17 Jan 2011 10:52:10 +0800
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Mon, 14 Feb 2011 13:03:08 +0100

x86: Avoid tlbstate lock if not enough cpus

This one isn't related to previous patch. If online cpus are
below NUM_INVALIDATE_TLB_VECTORS, we don't need the lock. The
comments in the code declares we don't need the check, but a hot
lock still needs an atomic operation and expensive, so add the
check here.

Uses nr_cpu_ids here as suggested by Eric Dumazet.

Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Andi Kleen <andi@firstfloor.org>
LKML-Reference: <1295232730.1949.710.camel@sli10-conroe>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/tlb.c |   11 ++++-------
 1 files changed, 4 insertions(+), 7 deletions(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 6acc724..55272d7 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -179,12 +179,8 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask,
 	sender = this_cpu_read(tlb_vector_offset);
 	f = &flush_state[sender];
 
-	/*
-	 * Could avoid this lock when
-	 * num_online_cpus() <= NUM_INVALIDATE_TLB_VECTORS, but it is
-	 * probably not worth checking this for a cache-hot lock.
-	 */
-	raw_spin_lock(&f->tlbstate_lock);
+	if (nr_cpu_ids > NUM_INVALIDATE_TLB_VECTORS)
+		raw_spin_lock(&f->tlbstate_lock);
 
 	f->flush_mm = mm;
 	f->flush_va = va;
@@ -202,7 +198,8 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask,
 
 	f->flush_mm = NULL;
 	f->flush_va = 0;
-	raw_spin_unlock(&f->tlbstate_lock);
+	if (nr_cpu_ids > NUM_INVALIDATE_TLB_VECTORS)
+		raw_spin_unlock(&f->tlbstate_lock);
 }
 
 void native_flush_tlb_others(const struct cpumask *cpumask,