[Cbe-oss-dev] [PATCH] spufs: fix aff_mutex and cbe_spu_info[n].list_mutex deadlock
Andre Detsch
adetsch at br.ibm.com
Wed Jun 11 01:47:13 EST 2008
Subject: spufs: fix aff_mutex and cbe_spu_info[n].list_mutex deadlock
From: Andre Detsch <adetsch at br.ibm.com>
In the old code, it was possible to lock aff_mutex and
cbe_spu_info[n].list_mutex in different orders, allowing a deadlock
to occur. With this patch, aff_mutex is not taken within a list_mutex
critical section anymore.
Signed-off-by: Andre Detsch <adetsch at br.ibm.com>
Index: spufs/arch/powerpc/platforms/cell/spufs/sched.c
===================================================================
--- spufs.orig/arch/powerpc/platforms/cell/spufs/sched.c
+++ spufs/arch/powerpc/platforms/cell/spufs/sched.c
@@ -399,6 +399,9 @@ static int has_affinity(struct spu_conte
if (list_empty(&ctx->aff_list))
return 0;
+ if (atomic_read(&ctx->gang->aff_sched_count) == 0)
+ ctx->gang->aff_ref_spu = NULL;
+
if (!gang->aff_ref_spu) {
if (!(gang->aff_flags & AFF_MERGED))
aff_merge_remaining_ctxs(gang);
@@ -424,14 +427,8 @@ static void spu_unbind_context(struct sp
if (spu->ctx->flags & SPU_CREATE_NOSCHED)
atomic_dec(&cbe_spu_info[spu->node].reserved_spus);
- if (ctx->gang){
- mutex_lock(&ctx->gang->aff_mutex);
- if (has_affinity(ctx)) {
- if (atomic_dec_and_test(&ctx->gang->aff_sched_count))
- ctx->gang->aff_ref_spu = NULL;
- }
- mutex_unlock(&ctx->gang->aff_mutex);
- }
+ if (ctx->gang)
+ atomic_dec_if_positive(&ctx->gang->aff_sched_count);
spu_switch_notify(spu, NULL);
spu_unmap_mappings(ctx);
@@ -562,10 +559,7 @@ static struct spu *spu_get_idle(struct s
goto found;
mutex_unlock(&cbe_spu_info[node].list_mutex);
- mutex_lock(&ctx->gang->aff_mutex);
- if (atomic_dec_and_test(&ctx->gang->aff_sched_count))
- ctx->gang->aff_ref_spu = NULL;
- mutex_unlock(&ctx->gang->aff_mutex);
+ atomic_dec(&ctx->gang->aff_sched_count);
goto not_found;
}
mutex_unlock(&ctx->gang->aff_mutex);
More information about the cbe-oss-dev
mailing list