[PATCH] drm/radeon: Sync ME and PFP after CP semaphore waits v2

[Christian König]

From: Christian König <christian.koenig at amd.com>

Fixes lockups due to CP read GPUVM faults when running piglit on Cape
Verde.

v2 (chk): apply the fix to R600+ as well, on CIK only the GFX CP has
	  a PFP, add more comments to R600 code, enable flushing again

Signed-off-by: Michel Dänzer <michel.daenzer at amd.com>
Signed-off-by: Christian König <christian.koenig at amd.com>
---
 drivers/gpu/drm/radeon/cik.c       | 17 +++++++++++++++++
 drivers/gpu/drm/radeon/r600.c      | 17 +++++++++++++++++
 drivers/gpu/drm/radeon/r600d.h     |  1 +
 drivers/gpu/drm/radeon/radeon_vm.c |  4 +---
 4 files changed, 36 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index e7d99e1..8b556f2 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -3920,6 +3920,17 @@ void cik_fence_compute_ring_emit(struct radeon_device *rdev,
 	radeon_ring_write(ring, 0);
 }
 
+/**
+ * cik_semaphore_ring_emit - emit a semaphore on the CP ring
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon ring buffer object
+ * @semaphore: radeon semaphore object
+ * @emit_wait: Is this a sempahore wait?
+ *
+ * Emits a semaphore signal/wait packet to the CP ring and prevents the PFP
+ * from running ahead of semaphore waits.
+ */
 bool cik_semaphore_ring_emit(struct radeon_device *rdev,
 			     struct radeon_ring *ring,
 			     struct radeon_semaphore *semaphore,
@@ -3932,6 +3943,12 @@ bool cik_semaphore_ring_emit(struct radeon_device *rdev,
 	radeon_ring_write(ring, lower_32_bits(addr));
 	radeon_ring_write(ring, (upper_32_bits(addr) & 0xffff) | sel);
 
+	if (emit_wait && ring->idx == RADEON_RING_TYPE_GFX_INDEX) {
+		/* Prevent the PFP from running ahead of the semaphore wait */
+		radeon_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0));
+		radeon_ring_write(ring, 0x0);
+	}
+
 	return true;
 }
 
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index c70a504..d659fa5 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2753,6 +2753,17 @@ void r600_fence_ring_emit(struct radeon_device *rdev,
 	}
 }
 
+/**
+ * r600_semaphore_ring_emit - emit a semaphore on the CP ring
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon ring buffer object
+ * @semaphore: radeon semaphore object
+ * @emit_wait: Is this a sempahore wait?
+ *
+ * Emits a semaphore signal/wait packet to the CP ring and prevents the PFP
+ * from running ahead of semaphore waits.
+ */
 bool r600_semaphore_ring_emit(struct radeon_device *rdev,
 			      struct radeon_ring *ring,
 			      struct radeon_semaphore *semaphore,
@@ -2768,6 +2779,12 @@ bool r600_semaphore_ring_emit(struct radeon_device *rdev,
 	radeon_ring_write(ring, lower_32_bits(addr));
 	radeon_ring_write(ring, (upper_32_bits(addr) & 0xff) | sel);
 
+	if (emit_wait) {
+		/* Prevent the PFP from running ahead of the semaphore wait */
+		radeon_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0));
+		radeon_ring_write(ring, 0x0);
+	}
+
 	return true;
 }
 
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index f94e7a9..1272c0d 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -1597,6 +1597,7 @@
 		 */
 #              define PACKET3_CP_DMA_CMD_SAIC      (1 << 28)
 #              define PACKET3_CP_DMA_CMD_DAIC      (1 << 29)
+#define PACKET3_PFP_SYNC_ME				0x42
 #define	PACKET3_SURFACE_SYNC				0x43
 #              define PACKET3_CB0_DEST_BASE_ENA    (1 << 6)
 #              define PACKET3_FULL_CACHE_ENA       (1 << 20) /* r7xx+ only */
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index 058f200..9c8358f 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -238,9 +238,7 @@ void radeon_vm_flush(struct radeon_device *rdev,
 	uint64_t pd_addr = radeon_bo_gpu_offset(vm->page_directory);
 
 	/* if we can't remember our last VM flush then flush now! */
-	/* XXX figure out why we have to flush all the time before CIK */
-	if (rdev->family < CHIP_BONAIRE ||
-	    !vm->last_flush || pd_addr != vm->pd_gpu_addr) {
+	if (!vm->last_flush || pd_addr != vm->pd_gpu_addr) {
 		trace_radeon_vm_flush(pd_addr, ring, vm->id);
 		vm->pd_gpu_addr = pd_addr;
 		radeon_ring_vm_flush(rdev, ring, vm);
-- 
1.9.1