drm/radeon: record what is next valid wptr for each ring v4

Before emitting any indirect buffer, emit the offset of the next
valid ring content if any. This allow code that want to resume
ring to resume ring right after ib that caused GPU lockup.

v2: use scratch registers instead of storing it into memory
v3: skip over the surface sync for ni and si as well
v4: use SET_CONFIG_REG instead of PACKET0
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Christian König <deathsimple@vodafone.de>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/radeon/evergreen.c

@@ -1368,7 +1368,15 @@ void evergreen_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 	/* set to DX10/11 mode */
 	radeon_ring_write(ring, PACKET3(PACKET3_MODE_CONTROL, 0));
 	radeon_ring_write(ring, 1);
-	/* FIXME: implement */
+
+	if (ring->rptr_save_reg) {
+		uint32_t next_rptr = ring->wptr + 3 + 4;
+		radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
+		radeon_ring_write(ring, ((ring->rptr_save_reg - 
+					  PACKET3_SET_CONFIG_REG_START) >> 2));
+		radeon_ring_write(ring, next_rptr);
+	}
+
 	radeon_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
 	radeon_ring_write(ring,
 #ifdef __BIG_ENDIAN

drivers/gpu/drm/radeon/ni.c

@@ -855,6 +855,15 @@ void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 	/* set to DX10/11 mode */
 	radeon_ring_write(ring, PACKET3(PACKET3_MODE_CONTROL, 0));
 	radeon_ring_write(ring, 1);
+
+	if (ring->rptr_save_reg) {
+		uint32_t next_rptr = ring->wptr + 3 + 4 + 8;
+		radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
+		radeon_ring_write(ring, ((ring->rptr_save_reg - 
+					  PACKET3_SET_CONFIG_REG_START) >> 2));
+		radeon_ring_write(ring, next_rptr);
+	}
+
 	radeon_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
 	radeon_ring_write(ring,
 #ifdef __BIG_ENDIAN
@@ -981,8 +990,10 @@ static int cayman_cp_start(struct radeon_device *rdev)
 
 static void cayman_cp_fini(struct radeon_device *rdev)
 {
+	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	cayman_cp_enable(rdev, false);
-	radeon_ring_fini(rdev, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
+	radeon_ring_fini(rdev, ring);
+	radeon_scratch_free(rdev, ring->rptr_save_reg);
 }
 
 int cayman_cp_resume(struct radeon_device *rdev)

drivers/gpu/drm/radeon/r600.c

@@ -2155,18 +2155,27 @@ int r600_cp_resume(struct radeon_device *rdev)
 void r600_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsigned ring_size)
 {
 	u32 rb_bufsz;
+	int r;
 
 	/* Align ring size */
 	rb_bufsz = drm_order(ring_size / 8);
 	ring_size = (1 << (rb_bufsz + 1)) * 4;
 	ring->ring_size = ring_size;
 	ring->align_mask = 16 - 1;
+
+	r = radeon_scratch_get(rdev, &ring->rptr_save_reg);
+	if (r) {
+		DRM_ERROR("failed to get scratch reg for rptr save (%d).\n", r);
+		ring->rptr_save_reg = 0;
+	}
 }
 
 void r600_cp_fini(struct radeon_device *rdev)
 {
+	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	r600_cp_stop(rdev);
-	radeon_ring_fini(rdev, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
+	radeon_ring_fini(rdev, ring);
+	radeon_scratch_free(rdev, ring->rptr_save_reg);
 }
 
 
@@ -2568,7 +2577,14 @@ void r600_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 {
 	struct radeon_ring *ring = &rdev->ring[ib->ring];
 
-	/* FIXME: implement */
+	if (ring->rptr_save_reg) {
+		uint32_t next_rptr = ring->wptr + 3 + 4;
+		radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
+		radeon_ring_write(ring, ((ring->rptr_save_reg -
+					 PACKET3_SET_CONFIG_REG_OFFSET) >> 2));
+		radeon_ring_write(ring, next_rptr);
+	}
+
 	radeon_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
 	radeon_ring_write(ring,
 #ifdef __BIG_ENDIAN

drivers/gpu/drm/radeon/radeon.h

@@ -622,6 +622,7 @@ struct radeon_ring {
 	unsigned		rptr;
 	unsigned		rptr_offs;
 	unsigned		rptr_reg;
+	unsigned		rptr_save_reg;
 	unsigned		wptr;
 	unsigned		wptr_old;
 	unsigned		wptr_reg;

drivers/gpu/drm/radeon/radeon_ring.c

@@ -451,6 +451,10 @@ static int radeon_debugfs_ring_info(struct seq_file *m, void *data)
 	count = (ring->ring_size / 4) - ring->ring_free_dw;
 	seq_printf(m, "wptr(0x%04x): 0x%08x\n", ring->wptr_reg, RREG32(ring->wptr_reg));
 	seq_printf(m, "rptr(0x%04x): 0x%08x\n", ring->rptr_reg, RREG32(ring->rptr_reg));
+	if (ring->rptr_save_reg) {
+		seq_printf(m, "rptr next(0x%04x): 0x%08x\n", ring->rptr_save_reg,
+			   RREG32(ring->rptr_save_reg));
+	}
 	seq_printf(m, "driver's copy of the wptr: 0x%08x\n", ring->wptr);
 	seq_printf(m, "driver's copy of the rptr: 0x%08x\n", ring->rptr);
 	seq_printf(m, "%u free dwords in ring\n", ring->ring_free_dw);

drivers/gpu/drm/radeon/rv770.c

@@ -358,8 +358,10 @@ static int rv770_cp_load_microcode(struct radeon_device *rdev)
 
 void r700_cp_fini(struct radeon_device *rdev)
 {
+	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	r700_cp_stop(rdev);
-	radeon_ring_fini(rdev, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
+	radeon_ring_fini(rdev, ring);
+	radeon_scratch_free(rdev, ring->rptr_save_reg);
 }
 
 /*

drivers/gpu/drm/radeon/si.c

@@ -1765,6 +1765,14 @@ void si_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 	struct radeon_ring *ring = &rdev->ring[ib->ring];
 	u32 header;
 
+	if (ring->rptr_save_reg) {
+		uint32_t next_rptr = ring->wptr + 3 + 4 + 8;
+		radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
+		radeon_ring_write(ring, ((ring->rptr_save_reg - 
+					  PACKET3_SET_CONFIG_REG_START) >> 2));
+		radeon_ring_write(ring, next_rptr);
+	}
+
 	if (ib->is_const_ib)
 		header = PACKET3(PACKET3_INDIRECT_BUFFER_CONST, 2);
 	else
@@ -1917,10 +1925,20 @@ static int si_cp_start(struct radeon_device *rdev)
 
 static void si_cp_fini(struct radeon_device *rdev)
 {
+	struct radeon_ring *ring;
 	si_cp_enable(rdev, false);
-	radeon_ring_fini(rdev, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
-	radeon_ring_fini(rdev, &rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX]);
-	radeon_ring_fini(rdev, &rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX]);
+
+	ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
+	radeon_ring_fini(rdev, ring);
+	radeon_scratch_free(rdev, ring->rptr_save_reg);
+
+	ring = &rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX];
+	radeon_ring_fini(rdev, ring);
+	radeon_scratch_free(rdev, ring->rptr_save_reg);
+
+	ring = &rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX];
+	radeon_ring_fini(rdev, ring);
+	radeon_scratch_free(rdev, ring->rptr_save_reg);
 }
 
 static int si_cp_resume(struct radeon_device *rdev)