diff options
| author | Ravikiran G Thirumalai <kiran@scalex86.org> | 2006-01-08 10:01:27 +0100 |
|---|---|---|
| committer | Linus Torvalds <torvalds@g5.osdl.org> | 2006-01-09 05:13:38 +0100 |
| commit | 22fc6eccbf4ce4eb6265e6ada7b50a7b9cc57d05 (patch) | |
| tree | 3887dc6f1eeb658d773be037971b98d6f5fb3dd7 /kernel/rcupdate.c | |
| parent | [PATCH] frv: fix uninitialised variable in serverworks driver (diff) | |
| download | linux-22fc6eccbf4ce4eb6265e6ada7b50a7b9cc57d05.tar.xz linux-22fc6eccbf4ce4eb6265e6ada7b50a7b9cc57d05.zip | |
[PATCH] Change maxaligned_in_smp alignemnt macros to internodealigned_in_smp macros
____cacheline_maxaligned_in_smp is currently used to align critical structures
and avoid false sharing. It uses per-arch L1_CACHE_SHIFT_MAX and people find
L1_CACHE_SHIFT_MAX useless.
However, we have been using ____cacheline_maxaligned_in_smp to align
structures on the internode cacheline size. As per Andi's suggestion,
following patch kills ____cacheline_maxaligned_in_smp and introduces
INTERNODE_CACHE_SHIFT, which defaults to L1_CACHE_SHIFT for all arches.
Arches needing L3/Internode cacheline alignment can define
INTERNODE_CACHE_SHIFT in the arch asm/cache.h. Patch replaces
____cacheline_maxaligned_in_smp with ____cacheline_internodealigned_in_smp
With this patch, L1_CACHE_SHIFT_MAX can be killed
Signed-off-by: Ravikiran Thirumalai <kiran@scalex86.org>
Signed-off-by: Shai Fultheim <shai@scalex86.org>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'kernel/rcupdate.c')
| -rw-r--r-- | kernel/rcupdate.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 48d3bce465b8..c9afc61240e4 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -61,9 +61,9 @@ struct rcu_state { /* for current batch to proceed. */ }; -static struct rcu_state rcu_state ____cacheline_maxaligned_in_smp = +static struct rcu_state rcu_state ____cacheline_internodealigned_in_smp = {.lock = SPIN_LOCK_UNLOCKED, .cpumask = CPU_MASK_NONE }; -static struct rcu_state rcu_bh_state ____cacheline_maxaligned_in_smp = +static struct rcu_state rcu_bh_state ____cacheline_internodealigned_in_smp = {.lock = SPIN_LOCK_UNLOCKED, .cpumask = CPU_MASK_NONE }; DEFINE_PER_CPU(struct rcu_data, rcu_data) = { 0L }; |