Merge git://git.infradead.org/mtd-2.6

[linux-2.6-omap-h63xx.git] / arch / powerpc / platforms / cell / spufs / sched.c

diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 1c1b627ee8436dc8e2fce9098d274183b8f18011..2ad914c47493fbd870cc6eaf1acd70991f256440 100644 (file)
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -312,6 +312,15 @@ static struct spu *aff_ref_location(struct spu_context *ctx, int mem_aff,
         */
        node = cpu_to_node(raw_smp_processor_id());
        for (n = 0; n < MAX_NUMNODES; n++, node++) {
+               /*
+                * "available_spus" counts how many spus are not potentially
+                * going to be used by other affinity gangs whose reference
+                * context is already in place. Although this code seeks to
+                * avoid having affinity gangs with a summed amount of
+                * contexts bigger than the amount of spus in the node,
+                * this may happen sporadically. In this case, available_spus
+                * becomes negative, which is harmless.
+                */
                int available_spus;
 
                node = (node < MAX_NUMNODES) ? node : 0;
@@ -321,12 +330,10 @@ static struct spu *aff_ref_location(struct spu_context *ctx, int mem_aff,
                available_spus = 0;
                mutex_lock(&cbe_spu_info[node].list_mutex);
                list_for_each_entry(spu, &cbe_spu_info[node].spus, cbe_list) {
-                       if (spu->ctx && spu->ctx->gang
-                                       && spu->ctx->aff_offset == 0)
-                               available_spus -=
-                                       (spu->ctx->gang->contexts - 1);
-                       else
-                               available_spus++;
+                       if (spu->ctx && spu->ctx->gang && !spu->ctx->aff_offset
+                                       && spu->ctx->gang->aff_ref_spu)
+                               available_spus -= spu->ctx->gang->contexts;
+                       available_spus++;
                }
                if (available_spus < ctx->gang->contexts) {
                        mutex_unlock(&cbe_spu_info[node].list_mutex);
@@ -437,6 +444,11 @@ static void spu_unbind_context(struct spu *spu, struct spu_context *ctx)
                atomic_dec(&cbe_spu_info[spu->node].reserved_spus);
 
        if (ctx->gang)
+               /*
+                * If ctx->gang->aff_sched_count is positive, SPU affinity is
+                * being considered in this gang. Using atomic_dec_if_positive
+                * allow us to skip an explicit check for affinity in this gang
+                */
                atomic_dec_if_positive(&ctx->gang->aff_sched_count);
 
        spu_switch_notify(spu, NULL);
@@ -643,9 +655,10 @@ static struct spu *find_victim(struct spu_context *ctx)
                            !(tmp->flags & SPU_CREATE_NOSCHED) &&
                            (!victim || tmp->prio > victim->prio)) {
                                victim = spu->ctx;
-                               get_spu_context(victim);
                        }
                }
+               if (victim)
+                       get_spu_context(victim);
                mutex_unlock(&cbe_spu_info[node].list_mutex);
 
                if (victim) {
@@ -727,17 +740,33 @@ static void spu_schedule(struct spu *spu, struct spu_context *ctx)
        /* not a candidate for interruptible because it's called either
           from the scheduler thread or from spu_deactivate */
        mutex_lock(&ctx->state_mutex);
-       __spu_schedule(spu, ctx);
+       if (ctx->state == SPU_STATE_SAVED)
+               __spu_schedule(spu, ctx);
        spu_release(ctx);
 }
 
-static void spu_unschedule(struct spu *spu, struct spu_context *ctx)
+/**
+ * spu_unschedule - remove a context from a spu, and possibly release it.
+ * @spu:       The SPU to unschedule from
+ * @ctx:       The context currently scheduled on the SPU
+ * @free_spu   Whether to free the SPU for other contexts
+ *
+ * Unbinds the context @ctx from the SPU @spu. If @free_spu is non-zero, the
+ * SPU is made available for other contexts (ie, may be returned by
+ * spu_get_idle). If this is zero, the caller is expected to schedule another
+ * context to this spu.
+ *
+ * Should be called with ctx->state_mutex held.
+ */
+static void spu_unschedule(struct spu *spu, struct spu_context *ctx,
+               int free_spu)
 {
        int node = spu->node;
 
        mutex_lock(&cbe_spu_info[node].list_mutex);
        cbe_spu_info[node].nr_active--;
-       spu->alloc_state = SPU_FREE;
+       if (free_spu)
+               spu->alloc_state = SPU_FREE;
        spu_unbind_context(spu, ctx);
        ctx->stats.invol_ctx_switch++;
        spu->stats.invol_ctx_switch++;
@@ -837,7 +866,7 @@ static int __spu_deactivate(struct spu_context *ctx, int force, int max_prio)
        if (spu) {
                new = grab_runnable_context(max_prio, spu->node);
                if (new || force) {
-                       spu_unschedule(spu, ctx);
+                       spu_unschedule(spu, ctx, new == NULL);
                        if (new) {
                                if (new->flags & SPU_CREATE_NOSCHED)
                                        wake_up(&new->stop_wq);
@@ -910,7 +939,7 @@ static noinline void spusched_tick(struct spu_context *ctx)
 
        new = grab_runnable_context(ctx->prio + 1, spu->node);
        if (new) {
-               spu_unschedule(spu, ctx);
+               spu_unschedule(spu, ctx, 0);
                if (test_bit(SPU_SCHED_SPU_RUN, &ctx->sched_flags))
                        spu_add_to_rq(ctx);
        } else {