dma-buf/fence: make fence context 64 bit v2

Fence contexts are created on the fly (for example) by the GPU scheduler used
in the amdgpu driver as a result of an userspace request. Because of this
userspace could in theory force a wrap around of the 32bit context number
if it doesn't behave well.

Avoid this by increasing the context number to 64bits. This way even when
userspace manages to allocate a billion contexts per second it takes more
than 500 years for the context number to wrap around.

v2: fix printf formats as well.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
Acked-by: Sumit Semwal <sumit.semwal@linaro.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1464786612-5010-2-git-send-email-deathsimple@vodafone.de

drivers/dma-buf/fence.c

@@ -35,7 +35,7 @@ EXPORT_TRACEPOINT_SYMBOL(fence_emit);
  * context or not. One device can have multiple separate contexts,
  * and they're used if some engine can run independently of another.
  */
-static atomic_t fence_context_counter = ATOMIC_INIT(0);
+static atomic64_t fence_context_counter = ATOMIC64_INIT(0);
 
 /**
  * fence_context_alloc - allocate an array of fence contexts
@@ -44,10 +44,10 @@ static atomic_t fence_context_counter = ATOMIC_INIT(0);
  * This function will return the first index of the number of fences allocated.
  * The fence context is used for setting fence->context to a unique number.
  */
-unsigned fence_context_alloc(unsigned num)
+u64 fence_context_alloc(unsigned num)
 {
 	BUG_ON(!num);
-	return atomic_add_return(num, &fence_context_counter) - num;
+	return atomic64_add_return(num, &fence_context_counter) - num;
 }
 EXPORT_SYMBOL(fence_context_alloc);
 
@@ -513,7 +513,7 @@ EXPORT_SYMBOL(fence_wait_any_timeout);
  */
 void
 fence_init(struct fence *fence, const struct fence_ops *ops,
-	     spinlock_t *lock, unsigned context, unsigned seqno)
+	     spinlock_t *lock, u64 context, unsigned seqno)
 {
 	BUG_ON(!lock);
 	BUG_ON(!ops || !ops->wait || !ops->enable_signaling ||

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -2032,7 +2032,7 @@ struct amdgpu_device {
 	struct amdgpu_irq_src		hpd_irq;
 
 	/* rings */
-	unsigned			fence_context;
+	u64				fence_context;
 	unsigned			num_rings;
 	struct amdgpu_ring		*rings[AMDGPU_MAX_RINGS];
 	bool				ib_pool_ready;

drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c

@@ -427,7 +427,7 @@ void amdgpu_sa_bo_dump_debug_info(struct amdgpu_sa_manager *sa_manager,
 			   soffset, eoffset, eoffset - soffset);
 
 		if (i->fence)
-			seq_printf(m, " protected by 0x%08x on context %d",
+			seq_printf(m, " protected by 0x%08x on context %llu",
 				   i->fence->seqno, i->fence->context);
 
 		seq_printf(m, "\n");

drivers/gpu/drm/etnaviv/etnaviv_gpu.h

@@ -125,7 +125,7 @@ struct etnaviv_gpu {
 	u32 completed_fence;
 	u32 retired_fence;
 	wait_queue_head_t fence_event;
-	unsigned int fence_context;
+	u64 fence_context;
 	spinlock_t fence_spinlock;
 
 	/* worker for handling active-list retiring: */

drivers/gpu/drm/nouveau/nouveau_fence.h

@@ -57,7 +57,8 @@ struct nouveau_fence_priv {
 	int  (*context_new)(struct nouveau_channel *);
 	void (*context_del)(struct nouveau_channel *);
 
-	u32 contexts, context_base;
+	u32 contexts;
+	u64 context_base;
 	bool uevent;
 };
 

drivers/gpu/drm/qxl/qxl_release.c

@@ -96,7 +96,7 @@ retry:
 			return 0;
 
 		if (have_drawable_releases && sc > 300) {
-			FENCE_WARN(fence, "failed to wait on release %d "
+			FENCE_WARN(fence, "failed to wait on release %llu "
 					  "after spincount %d\n",
 					  fence->context & ~0xf0000000, sc);
 			goto signaled;

drivers/gpu/drm/radeon/radeon.h

@@ -2386,7 +2386,7 @@ struct radeon_device {
 	struct radeon_mman		mman;
 	struct radeon_fence_driver	fence_drv[RADEON_NUM_RINGS];
 	wait_queue_head_t		fence_queue;
-	unsigned			fence_context;
+	u64				fence_context;
 	struct mutex			ring_lock;
 	struct radeon_ring		ring[RADEON_NUM_RINGS];
 	bool				ib_pool_ready;

drivers/gpu/drm/vmwgfx/vmwgfx_fence.c

@@ -46,7 +46,7 @@ struct vmw_fence_manager {
 	bool goal_irq_on; /* Protected by @goal_irq_mutex */
 	bool seqno_valid; /* Protected by @lock, and may not be set to true
 			     without the @goal_irq_mutex held. */
-	unsigned ctx;
+	u64 ctx;
 };
 
 struct vmw_user_fence {

drivers/staging/android/sync.h

@@ -68,7 +68,8 @@ struct sync_timeline {
 
 	/* protected by child_list_lock */
 	bool			destroyed;
-	int			context, value;
+	u64			context;
+	int			value;
 
 	struct list_head	child_list_head;
 	spinlock_t		child_list_lock;

include/linux/fence.h

@@ -75,7 +75,8 @@ struct fence {
 	struct rcu_head rcu;
 	struct list_head cb_list;
 	spinlock_t *lock;
-	unsigned context, seqno;
+	u64 context;
+	unsigned seqno;
 	unsigned long flags;
 	ktime_t timestamp;
 	int status;
@@ -178,7 +179,7 @@ struct fence_ops {
 };
 
 void fence_init(struct fence *fence, const struct fence_ops *ops,
-		spinlock_t *lock, unsigned context, unsigned seqno);
+		spinlock_t *lock, u64 context, unsigned seqno);
 
 void fence_release(struct kref *kref);
 void fence_free(struct fence *fence);
@@ -352,27 +353,27 @@ static inline signed long fence_wait(struct fence *fence, bool intr)
 	return ret < 0 ? ret : 0;
 }
 
-unsigned fence_context_alloc(unsigned num);
+u64 fence_context_alloc(unsigned num);
 
 #define FENCE_TRACE(f, fmt, args...) \
 	do {								\
 		struct fence *__ff = (f);				\
 		if (config_enabled(CONFIG_FENCE_TRACE))			\
-			pr_info("f %u#%u: " fmt,			\
+			pr_info("f %llu#%u: " fmt,			\
 				__ff->context, __ff->seqno, ##args);	\
 	} while (0)
 
 #define FENCE_WARN(f, fmt, args...) \
 	do {								\
 		struct fence *__ff = (f);				\
-		pr_warn("f %u#%u: " fmt, __ff->context, __ff->seqno,	\
+		pr_warn("f %llu#%u: " fmt, __ff->context, __ff->seqno,	\
 			 ##args);					\
 	} while (0)
 
 #define FENCE_ERR(f, fmt, args...) \
 	do {								\
 		struct fence *__ff = (f);				\
-		pr_err("f %u#%u: " fmt, __ff->context, __ff->seqno,	\
+		pr_err("f %llu#%u: " fmt, __ff->context, __ff->seqno,	\
 			##args);					\
 	} while (0)