diff options
| author | Mathias Krause <mathias.krause@secunet.com> | 2013-10-25 14:14:15 +0400 |
|---|---|---|
| committer | Herbert Xu <herbert@gondor.apana.org.au> | 2013-10-30 08:02:58 +0400 |
| commit | 0b6b098efcddac2bf4e2a895c9b655560bbfcee4 (patch) | |
| tree | 0facc6f31504a5be471d4592f99bce0b28f995e2 | |
| parent | cfc6f11b768a9bdda17aac280474de1f0e344fea (diff) | |
| download | linux-0b6b098efcddac2bf4e2a895c9b655560bbfcee4.tar.xz | |
padata: make the sequence counter an atomic_t
Using a spinlock to atomically increase a counter sounds wrong -- we've
atomic_t for this!
Also move 'seq_nr' to a different cache line than 'lock' to reduce cache
line trashing. This has the nice side effect of decreasing the size of
struct parallel_data from 192 to 128 bytes for a x86-64 build, e.g.
occupying only two instead of three cache lines.
Those changes results in a 5% performance increase on an IPsec test run
using pcrypt.
Btw. the seq_lock spinlock was never explicitly initialized -- one more
reason to get rid of it.
Signed-off-by: Mathias Krause <mathias.krause@secunet.com>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
| -rw-r--r-- | include/linux/padata.h | 3 | ||||
| -rw-r--r-- | kernel/padata.c | 9 |
2 files changed, 5 insertions, 7 deletions
diff --git a/include/linux/padata.h b/include/linux/padata.h index 86292beebfe2..438694650471 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -129,10 +129,9 @@ struct parallel_data { struct padata_serial_queue __percpu *squeue; atomic_t reorder_objects; atomic_t refcnt; + atomic_t seq_nr; struct padata_cpumask cpumask; spinlock_t lock ____cacheline_aligned; - spinlock_t seq_lock; - unsigned int seq_nr; unsigned int processed; struct timer_list timer; }; diff --git a/kernel/padata.c b/kernel/padata.c index 07af2c95dcfe..2abd25d79cc8 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -46,6 +46,7 @@ static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index) static int padata_cpu_hash(struct parallel_data *pd) { + unsigned int seq_nr; int cpu_index; /* @@ -53,10 +54,8 @@ static int padata_cpu_hash(struct parallel_data *pd) * seq_nr mod. number of cpus in use. */ - spin_lock(&pd->seq_lock); - cpu_index = pd->seq_nr % cpumask_weight(pd->cpumask.pcpu); - pd->seq_nr++; - spin_unlock(&pd->seq_lock); + seq_nr = atomic_inc_return(&pd->seq_nr); + cpu_index = seq_nr % cpumask_weight(pd->cpumask.pcpu); return padata_index_to_cpu(pd, cpu_index); } @@ -429,7 +428,7 @@ static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst, padata_init_pqueues(pd); padata_init_squeues(pd); setup_timer(&pd->timer, padata_reorder_timer, (unsigned long)pd); - pd->seq_nr = 0; + atomic_set(&pd->seq_nr, -1); atomic_set(&pd->reorder_objects, 0); atomic_set(&pd->refcnt, 0); pd->pinst = pinst; |