7 files changed, 32 insertions, 13 deletions

diff --git a/arch/powerpc/platforms/cell/spufs/context.c b/arch/powerpc/platforms/cell/spufs/context.c
index 133995ed5cc7..0ad83aeb70b1 100644
--- a/arch/powerpc/platforms/cell/spufs/context.c
+++ b/arch/powerpc/platforms/cell/spufs/context.c
@@ -109,13 +109,12 @@ void spu_forget(struct spu_context *ctx)
 
 	/*
 	 * This is basically an open-coded spu_acquire_saved, except that
-	 * we don't acquire the state mutex interruptible.
+	 * we don't acquire the state mutex interruptible, and we don't
+	 * want this context to be rescheduled on release.
 	 */
 	mutex_lock(&ctx->state_mutex);
-	if (ctx->state != SPU_STATE_SAVED) {
-		set_bit(SPU_SCHED_WAS_ACTIVE, &ctx->sched_flags);
+	if (ctx->state != SPU_STATE_SAVED)
 		spu_deactivate(ctx);
-	}
 
 	mm = ctx->owner;
 	ctx->owner = NULL;
@@ -171,7 +170,8 @@ void spu_release_saved(struct spu_context *ctx)
 {
 	BUG_ON(ctx->state != SPU_STATE_SAVED);
 
-	if (test_and_clear_bit(SPU_SCHED_WAS_ACTIVE, &ctx->sched_flags))
+	if (test_and_clear_bit(SPU_SCHED_WAS_ACTIVE, &ctx->sched_flags) &&
+			test_bit(SPU_SCHED_SPU_RUN, &ctx->sched_flags))
 		spu_activate(ctx, 0);
 
 	spu_release(ctx);
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index c66c3756970d..f7a7e8635fb6 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -367,6 +367,13 @@ static unsigned long spufs_ps_nopfn(struct vm_area_struct *vma,
 		return NOPFN_SIGBUS;
 
 	/*
+	 * Because we release the mmap_sem, the context may be destroyed while
+	 * we're in spu_wait. Grab an extra reference so it isn't destroyed
+	 * in the meantime.
+	 */
+	get_spu_context(ctx);
+
+	/*
 	 * We have to wait for context to be loaded before we have
 	 * pages to hand out to the user, but we don't want to wait
 	 * with the mmap_sem held.
@@ -375,7 +382,7 @@ static unsigned long spufs_ps_nopfn(struct vm_area_struct *vma,
 	 * hanged.
 	 */
 	if (spu_acquire(ctx))
-		return NOPFN_REFAULT;
+		goto refault;
 
 	if (ctx->state == SPU_STATE_SAVED) {
 		up_read(&current->mm->mmap_sem);
@@ -391,6 +398,9 @@ static unsigned long spufs_ps_nopfn(struct vm_area_struct *vma,
 
 	if (!ret)
 		spu_release(ctx);
+
+refault:
+	put_spu_context(ctx);
 	return NOPFN_REFAULT;
 }
 
diff --git a/arch/powerpc/platforms/cell/spufs/run.c b/arch/powerpc/platforms/cell/spufs/run.c
index 6221968c2a3c..cac69e116776 100644
--- a/arch/powerpc/platforms/cell/spufs/run.c
+++ b/arch/powerpc/platforms/cell/spufs/run.c
@@ -220,6 +220,7 @@ static int spu_run_init(struct spu_context *ctx, u32 *npc)
 		}
 	}
 
+	set_bit(SPU_SCHED_SPU_RUN, &ctx->sched_flags);
 	return 0;
 }
 
@@ -234,7 +235,7 @@ static int spu_run_fini(struct spu_context *ctx, u32 *npc,
 	*npc = ctx->ops->npc_read(ctx);
 
 	spuctx_switch_state(ctx, SPU_UTIL_IDLE_LOADED);
-	ctx->policy = SCHED_IDLE;
+	clear_bit(SPU_SCHED_SPU_RUN, &ctx->sched_flags);
 	spu_release(ctx);
 
 	if (signal_pending(current))
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 3a5972117de7..00528ef84ad2 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -246,7 +246,7 @@ static void spu_bind_context(struct spu *spu, struct spu_context *ctx)
 	spu_switch_notify(spu, ctx);
 	ctx->state = SPU_STATE_RUNNABLE;
 
-	spuctx_switch_state(ctx, SPU_UTIL_IDLE_LOADED);
+	spuctx_switch_state(ctx, SPU_UTIL_USER);
 }
 
 /*
@@ -867,7 +867,7 @@ static noinline void spusched_tick(struct spu_context *ctx)
 	if (ctx->policy == SCHED_FIFO)
 		goto out;
 
-	if (--ctx->time_slice && ctx->policy != SCHED_IDLE)
+	if (--ctx->time_slice && test_bit(SPU_SCHED_SPU_RUN, &ctx->sched_flags))
 		goto out;
 
 	spu = ctx->spu;
@@ -877,7 +877,7 @@ static noinline void spusched_tick(struct spu_context *ctx)
 	new = grab_runnable_context(ctx->prio + 1, spu->node);
 	if (new) {
 		spu_unschedule(spu, ctx);
-		if (ctx->policy != SCHED_IDLE)
+		if (test_bit(SPU_SCHED_SPU_RUN, &ctx->sched_flags))
 			spu_add_to_rq(ctx);
 	} else {
 		spu_context_nospu_trace(spusched_tick__newslice, ctx);
diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h
index 2c2fe3c07d72..cdc515182f82 100644
--- a/arch/powerpc/platforms/cell/spufs/spufs.h
+++ b/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -44,6 +44,7 @@ struct spu_gang;
 enum {
 	SPU_SCHED_NOTIFY_ACTIVE,
 	SPU_SCHED_WAS_ACTIVE,	/* was active upon spu_acquire_saved()  */
+	SPU_SCHED_SPU_RUN,	/* context is within spu_run */
 };
 
 struct spu_context {
diff --git a/arch/powerpc/platforms/cell/spufs/sputrace.c b/arch/powerpc/platforms/cell/spufs/sputrace.c
index 01974f7776e1..79aa773f3c99 100644
--- a/arch/powerpc/platforms/cell/spufs/sputrace.c
+++ b/arch/powerpc/platforms/cell/spufs/sputrace.c
@@ -58,12 +58,12 @@ static int sputrace_sprint(char *tbuf, int n)
 		ktime_to_timespec(ktime_sub(t->tstamp, sputrace_start));
 
 	return snprintf(tbuf, n,
-		"[%lu.%09lu] %d: %s (thread = %d, spu = %d)\n",
+		"[%lu.%09lu] %d: %s (ctxthread = %d, spu = %d)\n",
 		(unsigned long) tv.tv_sec,
 		(unsigned long) tv.tv_nsec,
-		t->owner_tid,
-		t->name,
 		t->curr_tid,
+		t->name,
+		t->owner_tid,
 		t->number);
 }
 
@@ -188,6 +188,7 @@ struct spu_probe spu_probes[] = {
 	{ "spufs_ps_nopfn__insert", "%p %p", spu_context_event },
 	{ "spu_acquire_saved__enter", "%p", spu_context_nospu_event },
 	{ "destroy_spu_context__enter", "%p", spu_context_nospu_event },
+	{ "spufs_stop_callback__enter", "%p %p", spu_context_event },
 };
 
 static int __init sputrace_init(void)
diff --git a/arch/powerpc/platforms/cell/spufs/switch.c b/arch/powerpc/platforms/cell/spufs/switch.c
index 6f5886c7b1f9..e9dc7a55d1b9 100644
--- a/arch/powerpc/platforms/cell/spufs/switch.c
+++ b/arch/powerpc/platforms/cell/spufs/switch.c
@@ -34,6 +34,7 @@
 
 #include <linux/module.h>
 #include <linux/errno.h>
+#include <linux/hardirq.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
@@ -117,6 +118,8 @@ static inline void disable_interrupts(struct spu_state *csa, struct spu *spu)
 	 *     Write INT_MASK_class1 with value of 0.
 	 *     Save INT_Mask_class2 in CSA.
 	 *     Write INT_MASK_class2 with value of 0.
+	 *     Synchronize all three interrupts to be sure
+	 *     we no longer execute a handler on another CPU.
 	 */
 	spin_lock_irq(&spu->register_lock);
 	if (csa) {
@@ -129,6 +132,9 @@ static inline void disable_interrupts(struct spu_state *csa, struct spu *spu)
 	spu_int_mask_set(spu, 2, 0ul);
 	eieio();
 	spin_unlock_irq(&spu->register_lock);
+	synchronize_irq(spu->irqs[0]);
+	synchronize_irq(spu->irqs[1]);
+	synchronize_irq(spu->irqs[2]);
 }
 
 static inline void set_watchdog_timer(struct spu_state *csa, struct spu *spu)