[PATCH 1/4] drm/amdgpu: define ring structure to access rptr/wptr/fence

[PATCH 1/4] drm/amdgpu: define ring structure to access rptr/wptr/fence

[Jack Xiao]

Define ring structure to access the cpu/gpu address of rptr/wptr/fence
instead of dynamic calculation.

Cc: Christian König <christian.koenig@amd.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index da871d84b742..940618d1bd4d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -208,6 +208,8 @@ struct amdgpu_ring {
 	struct amdgpu_bo	*ring_obj;
 	volatile uint32_t	*ring;
 	unsigned		rptr_offs;
+	u64			rptr_gpu_addr;
+	volatile u32		*rptr_cpu_addr;
 	u64			wptr;
 	u64			wptr_old;
 	unsigned		ring_size;
@@ -228,7 +230,11 @@ struct amdgpu_ring {
 	bool			use_doorbell;
 	bool			use_pollmem;
 	unsigned		wptr_offs;
+	u64			wptr_gpu_addr;
+	volatile u32		*wptr_cpu_addr;
 	unsigned		fence_offs;
+	u64			fence_gpu_addr;
+	volatile u32		*fence_cpu_addr;
 	uint64_t		current_ctx;
 	char			name[16];
 	u32                     trail_seq;
-- 
2.26.2

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH 2/4] drm/amdgpu: initialize the cpu/gpu address of rptr/wptr/fence

[Jack Xiao]

Initialize the cpu/gpu address of rptr/wptr/fence.

Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 37 ++++++++++++++++++++----
 1 file changed, 32 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 13ea8ebc421c..ff63ecc861bc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -150,6 +150,12 @@ void amdgpu_ring_undo(struct amdgpu_ring *ring)
 		ring->funcs->end_use(ring);
 }
 
+#define amdgpu_ring_get_gpu_addr(ring, offset)	\
+	(ring->adev->wb.gpu_addr + offset * 4)
+
+#define amdgpu_ring_get_cpu_addr(ring, offset)	\
+	(&ring->adev->wb.wb[offset])
+
 /**
  * amdgpu_ring_init - init driver ring struct.
  *
@@ -217,17 +223,38 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 			"(%d) ring trail_fence_offs wb alloc failed\n", r);
 		return r;
 	}
-	ring->trail_fence_gpu_addr =
-		adev->wb.gpu_addr + (ring->trail_fence_offs * 4);
-	ring->trail_fence_cpu_addr = &adev->wb.wb[ring->trail_fence_offs];
 
 	r = amdgpu_device_wb_get(adev, &ring->cond_exe_offs);
 	if (r) {
 		dev_err(adev->dev, "(%d) ring cond_exec_polling wb alloc failed\n", r);
 		return r;
 	}
-	ring->cond_exe_gpu_addr = adev->wb.gpu_addr + (ring->cond_exe_offs * 4);
-	ring->cond_exe_cpu_addr = &adev->wb.wb[ring->cond_exe_offs];
+
+	ring->fence_gpu_addr =
+		amdgpu_ring_get_gpu_addr(ring, ring->fence_offs);
+	ring->fence_cpu_addr =
+		amdgpu_ring_get_cpu_addr(ring, ring->fence_offs);
+
+	ring->rptr_gpu_addr =
+		amdgpu_ring_get_gpu_addr(ring, ring->rptr_offs);
+	ring->rptr_cpu_addr =
+		amdgpu_ring_get_cpu_addr(ring, ring->rptr_offs);
+
+	ring->wptr_gpu_addr =
+		amdgpu_ring_get_gpu_addr(ring, ring->wptr_offs);
+	ring->wptr_cpu_addr =
+		amdgpu_ring_get_cpu_addr(ring, ring->wptr_offs);
+
+	ring->trail_fence_gpu_addr =
+		amdgpu_ring_get_gpu_addr(ring, ring->trail_fence_offs);
+	ring->trail_fence_cpu_addr =
+		amdgpu_ring_get_cpu_addr(ring, ring->trail_fence_offs);
+
+	ring->cond_exe_gpu_addr =
+		amdgpu_ring_get_gpu_addr(ring, ring->cond_exe_offs);
+	ring->cond_exe_cpu_addr =
+		amdgpu_ring_get_cpu_addr(ring, ring->cond_exe_offs);
+
 	/* always set cond_exec_polling to CONTINUE */
 	*ring->cond_exe_cpu_addr = 1;
 
-- 
2.26.2

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH 3/4] drm/amdgpu: use ring structure to access rptr/wptr v2

[Jack Xiao]

Use ring structure to access the cpu/gpu address of rptr/wptr.

v2: merge gfx10/sdma5/sdma5.2 patches

Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/cik_sdma.c  |  8 +++---
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 37 +++++++++++++-------------
 drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c  |  8 +++---
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c  | 12 ++++-----
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c  | 20 +++++++-------
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c  | 25 +++++++++--------
 drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c |  4 +--
 drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c |  4 +--
 drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c |  4 +--
 drivers/gpu/drm/amd/amdgpu/mes_v10_1.c | 11 ++++----
 drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c |  8 +++---
 drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 16 +++++------
 drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 28 ++++++++-----------
 drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 16 +++++------
 drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 16 +++++------
 drivers/gpu/drm/amd/amdgpu/si_dma.c    |  4 +--
 drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c  |  6 ++---
 drivers/gpu/drm/amd/amdgpu/vce_v4_0.c  |  6 ++---
 drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c  | 12 ++++-----
 drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c  | 12 ++++-----
 drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c  | 12 ++++-----
 21 files changed, 126 insertions(+), 143 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index 20f108818b2b..a6a7aa9e9aec 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -164,7 +164,7 @@ static uint64_t cik_sdma_ring_get_rptr(struct amdgpu_ring *ring)
 {
 	u32 rptr;
 
-	rptr = ring->adev->wb.wb[ring->rptr_offs];
+	rptr = *ring->rptr_cpu_addr;
 
 	return (rptr & 0x3fffc) >> 2;
 }
@@ -432,12 +432,10 @@ static int cik_sdma_gfx_resume(struct amdgpu_device *adev)
 	struct amdgpu_ring *ring;
 	u32 rb_cntl, ib_cntl;
 	u32 rb_bufsz;
-	u32 wb_offset;
 	int i, j, r;
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		ring = &adev->sdma.instance[i].ring;
-		wb_offset = (ring->rptr_offs * 4);
 
 		mutex_lock(&adev->srbm_mutex);
 		for (j = 0; j < 16; j++) {
@@ -473,9 +471,9 @@ static int cik_sdma_gfx_resume(struct amdgpu_device *adev)
 
 		/* set the wb address whether it's enabled or not */
 		WREG32(mmSDMA0_GFX_RB_RPTR_ADDR_HI + sdma_offsets[i],
-		       upper_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFF);
+		       upper_32_bits(ring->rptr_gpu_addr) & 0xFFFFFFFF);
 		WREG32(mmSDMA0_GFX_RB_RPTR_ADDR_LO + sdma_offsets[i],
-		       ((adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFC));
+		       ((ring->rptr_gpu_addr) & 0xFFFFFFFC));
 
 		rb_cntl |= SDMA0_GFX_RB_CNTL__RPTR_WRITEBACK_ENABLE_MASK;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index db9f1e89a0f8..7036e286b627 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -3205,9 +3205,8 @@ static void gfx10_kiq_set_resources(struct amdgpu_ring *kiq_ring, uint64_t queue
 static void gfx10_kiq_map_queues(struct amdgpu_ring *kiq_ring,
 				 struct amdgpu_ring *ring)
 {
-	struct amdgpu_device *adev = kiq_ring->adev;
 	uint64_t mqd_addr = amdgpu_bo_gpu_offset(ring->mqd_obj);
-	uint64_t wptr_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	uint64_t wptr_addr = ring->wptr_gpu_addr;
 	uint32_t eng_sel = ring->funcs->type == AMDGPU_RING_TYPE_GFX ? 4 : 0;
 
 	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_MAP_QUEUES, 5));
@@ -5835,12 +5834,12 @@ static int gfx_v10_0_cp_gfx_resume(struct amdgpu_device *adev)
 	WREG32_SOC15(GC, 0, mmCP_RB0_WPTR_HI, upper_32_bits(ring->wptr));
 
 	/* set the wb address wether it's enabled or not */
-	rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+	rptr_addr = ring->rptr_gpu_addr;
 	WREG32_SOC15(GC, 0, mmCP_RB0_RPTR_ADDR, lower_32_bits(rptr_addr));
 	WREG32_SOC15(GC, 0, mmCP_RB0_RPTR_ADDR_HI, upper_32_bits(rptr_addr) &
 		     CP_RB_RPTR_ADDR_HI__RB_RPTR_ADDR_HI_MASK);
 
-	wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	wptr_gpu_addr = ring->wptr_gpu_addr;
 	WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_LO,
 		     lower_32_bits(wptr_gpu_addr));
 	WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_HI,
@@ -5873,11 +5872,11 @@ static int gfx_v10_0_cp_gfx_resume(struct amdgpu_device *adev)
 		WREG32_SOC15(GC, 0, mmCP_RB1_WPTR, lower_32_bits(ring->wptr));
 		WREG32_SOC15(GC, 0, mmCP_RB1_WPTR_HI, upper_32_bits(ring->wptr));
 		/* Set the wb address wether it's enabled or not */
-		rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+		rptr_addr = ring->rptr_gpu_addr;
 		WREG32_SOC15(GC, 0, mmCP_RB1_RPTR_ADDR, lower_32_bits(rptr_addr));
 		WREG32_SOC15(GC, 0, mmCP_RB1_RPTR_ADDR_HI, upper_32_bits(rptr_addr) &
 			     CP_RB1_RPTR_ADDR_HI__RB_RPTR_ADDR_HI_MASK);
-		wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+		wptr_gpu_addr = ring->wptr_gpu_addr;
 		WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_LO,
 			     lower_32_bits(wptr_gpu_addr));
 		WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_HI,
@@ -6083,13 +6082,13 @@ static int gfx_v10_0_gfx_mqd_init(struct amdgpu_ring *ring)
 	mqd->cp_gfx_hqd_base_hi = upper_32_bits(hqd_gpu_addr);
 
 	/* set up hqd_rptr_addr/_hi, similar as CP_RB_RPTR */
-	wb_gpu_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+	wb_gpu_addr = ring->rptr_gpu_addr;
 	mqd->cp_gfx_hqd_rptr_addr = wb_gpu_addr & 0xfffffffc;
 	mqd->cp_gfx_hqd_rptr_addr_hi =
 		upper_32_bits(wb_gpu_addr) & 0xffff;
 
 	/* set up rb_wptr_poll addr */
-	wb_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	wb_gpu_addr = ring->wptr_gpu_addr;
 	mqd->cp_rb_wptr_poll_addr_lo = wb_gpu_addr & 0xfffffffc;
 	mqd->cp_rb_wptr_poll_addr_hi = upper_32_bits(wb_gpu_addr) & 0xffff;
 
@@ -6198,7 +6197,7 @@ static int gfx_v10_0_gfx_init_queue(struct amdgpu_ring *ring)
 			memcpy(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd));
 		/* reset the ring */
 		ring->wptr = 0;
-		adev->wb.wb[ring->wptr_offs] = 0;
+		*ring->wptr_cpu_addr = 0;
 		amdgpu_ring_clear_ring(ring);
 #ifdef BRING_UP_DEBUG
 		mutex_lock(&adev->srbm_mutex);
@@ -6372,13 +6371,13 @@ static int gfx_v10_0_compute_mqd_init(struct amdgpu_ring *ring)
 	mqd->cp_hqd_pq_control = tmp;
 
 	/* set the wb address whether it's enabled or not */
-	wb_gpu_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+	wb_gpu_addr = ring->rptr_gpu_addr;
 	mqd->cp_hqd_pq_rptr_report_addr_lo = wb_gpu_addr & 0xfffffffc;
 	mqd->cp_hqd_pq_rptr_report_addr_hi =
 		upper_32_bits(wb_gpu_addr) & 0xffff;
 
 	/* only used if CP_PQ_WPTR_POLL_CNTL.CP_PQ_WPTR_POLL_CNTL__EN_MASK=1 */
-	wb_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	wb_gpu_addr = ring->wptr_gpu_addr;
 	mqd->cp_hqd_pq_wptr_poll_addr_lo = wb_gpu_addr & 0xfffffffc;
 	mqd->cp_hqd_pq_wptr_poll_addr_hi = upper_32_bits(wb_gpu_addr) & 0xffff;
 
@@ -6594,7 +6593,7 @@ static int gfx_v10_0_kcq_init_queue(struct amdgpu_ring *ring)
 
 		/* reset ring buffer */
 		ring->wptr = 0;
-		atomic64_set((atomic64_t *)&adev->wb.wb[ring->wptr_offs], 0);
+		atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0);
 		amdgpu_ring_clear_ring(ring);
 	} else {
 		amdgpu_ring_clear_ring(ring);
@@ -7601,7 +7600,8 @@ static void gfx_v10_0_get_clockgating_state(void *handle, u32 *flags)
 
 static u64 gfx_v10_0_ring_get_rptr_gfx(struct amdgpu_ring *ring)
 {
-	return ring->adev->wb.wb[ring->rptr_offs]; /* gfx10 is 32bit rptr*/
+	/* gfx10 is 32bit rptr*/
+	return *(uint32_t *)ring->rptr_cpu_addr;
 }
 
 static u64 gfx_v10_0_ring_get_wptr_gfx(struct amdgpu_ring *ring)
@@ -7611,7 +7611,7 @@ static u64 gfx_v10_0_ring_get_wptr_gfx(struct amdgpu_ring *ring)
 
 	/* XXX check if swapping is necessary on BE */
 	if (ring->use_doorbell) {
-		wptr = atomic64_read((atomic64_t *)&adev->wb.wb[ring->wptr_offs]);
+		wptr = atomic64_read((atomic64_t *)ring->wptr_cpu_addr);
 	} else {
 		wptr = RREG32_SOC15(GC, 0, mmCP_RB0_WPTR);
 		wptr += (u64)RREG32_SOC15(GC, 0, mmCP_RB0_WPTR_HI) << 32;
@@ -7626,7 +7626,7 @@ static void gfx_v10_0_ring_set_wptr_gfx(struct amdgpu_ring *ring)
 
 	if (ring->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
-		atomic64_set((atomic64_t *)&adev->wb.wb[ring->wptr_offs], ring->wptr);
+		atomic64_set((atomic64_t *)ring->wptr_cpu_addr, ring->wptr);
 		WDOORBELL64(ring->doorbell_index, ring->wptr);
 	} else {
 		WREG32_SOC15(GC, 0, mmCP_RB0_WPTR, lower_32_bits(ring->wptr));
@@ -7636,7 +7636,8 @@ static void gfx_v10_0_ring_set_wptr_gfx(struct amdgpu_ring *ring)
 
 static u64 gfx_v10_0_ring_get_rptr_compute(struct amdgpu_ring *ring)
 {
-	return ring->adev->wb.wb[ring->rptr_offs]; /* gfx10 hardware is 32bit rptr */
+	/* gfx10 hardware is 32bit rptr */
+	return *(uint32_t *)ring->rptr_cpu_addr;
 }
 
 static u64 gfx_v10_0_ring_get_wptr_compute(struct amdgpu_ring *ring)
@@ -7645,7 +7646,7 @@ static u64 gfx_v10_0_ring_get_wptr_compute(struct amdgpu_ring *ring)
 
 	/* XXX check if swapping is necessary on BE */
 	if (ring->use_doorbell)
-		wptr = atomic64_read((atomic64_t *)&ring->adev->wb.wb[ring->wptr_offs]);
+		wptr = atomic64_read((atomic64_t *)ring->wptr_cpu_addr);
 	else
 		BUG();
 	return wptr;
@@ -7657,7 +7658,7 @@ static void gfx_v10_0_ring_set_wptr_compute(struct amdgpu_ring *ring)
 
 	/* XXX check if swapping is necessary on BE */
 	if (ring->use_doorbell) {
-		atomic64_set((atomic64_t *)&adev->wb.wb[ring->wptr_offs], ring->wptr);
+		atomic64_set((atomic64_t *)ring->wptr_cpu_addr, ring->wptr);
 		WDOORBELL64(ring->doorbell_index, ring->wptr);
 	} else {
 		BUG(); /* only DOORBELL method supported on gfx10 now */
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index 79c52c7a02e3..e4ef551dd85c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -2116,7 +2116,7 @@ static int gfx_v6_0_cp_gfx_resume(struct amdgpu_device *adev)
 	WREG32(mmCP_RB0_WPTR, ring->wptr);
 
 	/* set the wb address whether it's enabled or not */
-	rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+	rptr_addr = ring->rptr_gpu_addr;
 	WREG32(mmCP_RB0_RPTR_ADDR, lower_32_bits(rptr_addr));
 	WREG32(mmCP_RB0_RPTR_ADDR_HI, upper_32_bits(rptr_addr) & 0xFF);
 
@@ -2138,7 +2138,7 @@ static int gfx_v6_0_cp_gfx_resume(struct amdgpu_device *adev)
 
 static u64 gfx_v6_0_ring_get_rptr(struct amdgpu_ring *ring)
 {
-	return ring->adev->wb.wb[ring->rptr_offs];
+	return *ring->rptr_cpu_addr;
 }
 
 static u64 gfx_v6_0_ring_get_wptr(struct amdgpu_ring *ring)
@@ -2202,7 +2202,7 @@ static int gfx_v6_0_cp_compute_resume(struct amdgpu_device *adev)
 	ring->wptr = 0;
 	WREG32(mmCP_RB1_WPTR, ring->wptr);
 
-	rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+	rptr_addr = ring->rptr_gpu_addr;
 	WREG32(mmCP_RB1_RPTR_ADDR, lower_32_bits(rptr_addr));
 	WREG32(mmCP_RB1_RPTR_ADDR_HI, upper_32_bits(rptr_addr) & 0xFF);
 
@@ -2221,7 +2221,7 @@ static int gfx_v6_0_cp_compute_resume(struct amdgpu_device *adev)
 	WREG32(mmCP_RB2_CNTL, tmp | CP_RB2_CNTL__RB_RPTR_WR_ENA_MASK);
 	ring->wptr = 0;
 	WREG32(mmCP_RB2_WPTR, ring->wptr);
-	rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+	rptr_addr = ring->rptr_gpu_addr;
 	WREG32(mmCP_RB2_RPTR_ADDR, lower_32_bits(rptr_addr));
 	WREG32(mmCP_RB2_RPTR_ADDR_HI, upper_32_bits(rptr_addr) & 0xFF);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 04eaf3a8fddb..186e117d2fee 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -2628,7 +2628,7 @@ static int gfx_v7_0_cp_gfx_resume(struct amdgpu_device *adev)
 	WREG32(mmCP_RB0_WPTR, lower_32_bits(ring->wptr));
 
 	/* set the wb address wether it's enabled or not */
-	rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+	rptr_addr = ring->rptr_gpu_addr;
 	WREG32(mmCP_RB0_RPTR_ADDR, lower_32_bits(rptr_addr));
 	WREG32(mmCP_RB0_RPTR_ADDR_HI, upper_32_bits(rptr_addr) & 0xFF);
 
@@ -2653,7 +2653,7 @@ static int gfx_v7_0_cp_gfx_resume(struct amdgpu_device *adev)
 
 static u64 gfx_v7_0_ring_get_rptr(struct amdgpu_ring *ring)
 {
-	return ring->adev->wb.wb[ring->rptr_offs];
+	return *ring->rptr_cpu_addr;
 }
 
 static u64 gfx_v7_0_ring_get_wptr_gfx(struct amdgpu_ring *ring)
@@ -2674,7 +2674,7 @@ static void gfx_v7_0_ring_set_wptr_gfx(struct amdgpu_ring *ring)
 static u64 gfx_v7_0_ring_get_wptr_compute(struct amdgpu_ring *ring)
 {
 	/* XXX check if swapping is necessary on BE */
-	return ring->adev->wb.wb[ring->wptr_offs];
+	return *ring->wptr_cpu_addr;
 }
 
 static void gfx_v7_0_ring_set_wptr_compute(struct amdgpu_ring *ring)
@@ -2682,7 +2682,7 @@ static void gfx_v7_0_ring_set_wptr_compute(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 
 	/* XXX check if swapping is necessary on BE */
-	adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+	*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
 	WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 }
 
@@ -2978,12 +2978,12 @@ static void gfx_v7_0_mqd_init(struct amdgpu_device *adev,
 		CP_HQD_PQ_CONTROL__KMD_QUEUE_MASK; /* assuming kernel queue control */
 
 	/* only used if CP_PQ_WPTR_POLL_CNTL.CP_PQ_WPTR_POLL_CNTL__EN_MASK=1 */
-	wb_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	wb_gpu_addr = ring->wptr_gpu_addr;
 	mqd->cp_hqd_pq_wptr_poll_addr_lo = wb_gpu_addr & 0xfffffffc;
 	mqd->cp_hqd_pq_wptr_poll_addr_hi = upper_32_bits(wb_gpu_addr) & 0xffff;
 
 	/* set the wb address wether it's enabled or not */
-	wb_gpu_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+	wb_gpu_addr = ring->rptr_gpu_addr;
 	mqd->cp_hqd_pq_rptr_report_addr_lo = wb_gpu_addr & 0xfffffffc;
 	mqd->cp_hqd_pq_rptr_report_addr_hi =
 		upper_32_bits(wb_gpu_addr) & 0xffff;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 8d7208959c95..392b541bb98f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -4296,11 +4296,11 @@ static int gfx_v8_0_cp_gfx_resume(struct amdgpu_device *adev)
 	WREG32(mmCP_RB0_WPTR, lower_32_bits(ring->wptr));
 
 	/* set the wb address wether it's enabled or not */
-	rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+	rptr_addr = ring->rptr_gpu_addr;
 	WREG32(mmCP_RB0_RPTR_ADDR, lower_32_bits(rptr_addr));
 	WREG32(mmCP_RB0_RPTR_ADDR_HI, upper_32_bits(rptr_addr) & 0xFF);
 
-	wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	wptr_gpu_addr = ring->wptr_gpu_addr;
 	WREG32(mmCP_RB_WPTR_POLL_ADDR_LO, lower_32_bits(wptr_gpu_addr));
 	WREG32(mmCP_RB_WPTR_POLL_ADDR_HI, upper_32_bits(wptr_gpu_addr));
 	mdelay(1);
@@ -4383,7 +4383,7 @@ static int gfx_v8_0_kiq_kcq_enable(struct amdgpu_device *adev)
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 		struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
 		uint64_t mqd_addr = amdgpu_bo_gpu_offset(ring->mqd_obj);
-		uint64_t wptr_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+		uint64_t wptr_addr = ring->wptr_gpu_addr;
 
 		/* map queues */
 		amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_MAP_QUEUES, 5));
@@ -4507,13 +4507,13 @@ static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring)
 	mqd->cp_hqd_pq_control = tmp;
 
 	/* set the wb address whether it's enabled or not */
-	wb_gpu_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+	wb_gpu_addr = ring->rptr_gpu_addr;
 	mqd->cp_hqd_pq_rptr_report_addr_lo = wb_gpu_addr & 0xfffffffc;
 	mqd->cp_hqd_pq_rptr_report_addr_hi =
 		upper_32_bits(wb_gpu_addr) & 0xffff;
 
 	/* only used if CP_PQ_WPTR_POLL_CNTL.CP_PQ_WPTR_POLL_CNTL__EN_MASK=1 */
-	wb_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	wb_gpu_addr = ring->wptr_gpu_addr;
 	mqd->cp_hqd_pq_wptr_poll_addr_lo = wb_gpu_addr & 0xfffffffc;
 	mqd->cp_hqd_pq_wptr_poll_addr_hi = upper_32_bits(wb_gpu_addr) & 0xffff;
 
@@ -6043,7 +6043,7 @@ static int gfx_v8_0_set_clockgating_state(void *handle,
 
 static u64 gfx_v8_0_ring_get_rptr(struct amdgpu_ring *ring)
 {
-	return ring->adev->wb.wb[ring->rptr_offs];
+	return *ring->rptr_cpu_addr;
 }
 
 static u64 gfx_v8_0_ring_get_wptr_gfx(struct amdgpu_ring *ring)
@@ -6052,7 +6052,7 @@ static u64 gfx_v8_0_ring_get_wptr_gfx(struct amdgpu_ring *ring)
 
 	if (ring->use_doorbell)
 		/* XXX check if swapping is necessary on BE */
-		return ring->adev->wb.wb[ring->wptr_offs];
+		return *ring->wptr_cpu_addr;
 	else
 		return RREG32(mmCP_RB0_WPTR);
 }
@@ -6063,7 +6063,7 @@ static void gfx_v8_0_ring_set_wptr_gfx(struct amdgpu_ring *ring)
 
 	if (ring->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
-		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+		*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
 		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 	} else {
 		WREG32(mmCP_RB0_WPTR, lower_32_bits(ring->wptr));
@@ -6263,7 +6263,7 @@ static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 
 static u64 gfx_v8_0_ring_get_wptr_compute(struct amdgpu_ring *ring)
 {
-	return ring->adev->wb.wb[ring->wptr_offs];
+	return *ring->wptr_cpu_addr;
 }
 
 static void gfx_v8_0_ring_set_wptr_compute(struct amdgpu_ring *ring)
@@ -6271,7 +6271,7 @@ static void gfx_v8_0_ring_set_wptr_compute(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 
 	/* XXX check if swapping is necessary on BE */
-	adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+	*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
 	WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index e4e751f87092..dcf351adc280 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -817,9 +817,8 @@ static void gfx_v9_0_kiq_set_resources(struct amdgpu_ring *kiq_ring,
 static void gfx_v9_0_kiq_map_queues(struct amdgpu_ring *kiq_ring,
 				 struct amdgpu_ring *ring)
 {
-	struct amdgpu_device *adev = kiq_ring->adev;
 	uint64_t mqd_addr = amdgpu_bo_gpu_offset(ring->mqd_obj);
-	uint64_t wptr_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	uint64_t wptr_addr = ring->wptr_gpu_addr;
 	uint32_t eng_sel = ring->funcs->type == AMDGPU_RING_TYPE_GFX ? 4 : 0;
 
 	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_MAP_QUEUES, 5));
@@ -3260,11 +3259,11 @@ static int gfx_v9_0_cp_gfx_resume(struct amdgpu_device *adev)
 	WREG32_SOC15(GC, 0, mmCP_RB0_WPTR_HI, upper_32_bits(ring->wptr));
 
 	/* set the wb address wether it's enabled or not */
-	rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+	rptr_addr = ring->rptr_gpu_addr;
 	WREG32_SOC15(GC, 0, mmCP_RB0_RPTR_ADDR, lower_32_bits(rptr_addr));
 	WREG32_SOC15(GC, 0, mmCP_RB0_RPTR_ADDR_HI, upper_32_bits(rptr_addr) & CP_RB_RPTR_ADDR_HI__RB_RPTR_ADDR_HI_MASK);
 
-	wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	wptr_gpu_addr = ring->wptr_gpu_addr;
 	WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_LO, lower_32_bits(wptr_gpu_addr));
 	WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_HI, upper_32_bits(wptr_gpu_addr));
 
@@ -3476,13 +3475,13 @@ static int gfx_v9_0_mqd_init(struct amdgpu_ring *ring)
 	mqd->cp_hqd_pq_control = tmp;
 
 	/* set the wb address whether it's enabled or not */
-	wb_gpu_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+	wb_gpu_addr = ring->rptr_gpu_addr;
 	mqd->cp_hqd_pq_rptr_report_addr_lo = wb_gpu_addr & 0xfffffffc;
 	mqd->cp_hqd_pq_rptr_report_addr_hi =
 		upper_32_bits(wb_gpu_addr) & 0xffff;
 
 	/* only used if CP_PQ_WPTR_POLL_CNTL.CP_PQ_WPTR_POLL_CNTL__EN_MASK=1 */
-	wb_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	wb_gpu_addr = ring->wptr_gpu_addr;
 	mqd->cp_hqd_pq_wptr_poll_addr_lo = wb_gpu_addr & 0xfffffffc;
 	mqd->cp_hqd_pq_wptr_poll_addr_hi = upper_32_bits(wb_gpu_addr) & 0xffff;
 
@@ -3741,7 +3740,7 @@ static int gfx_v9_0_kcq_init_queue(struct amdgpu_ring *ring)
 
 		/* reset ring buffer */
 		ring->wptr = 0;
-		atomic64_set((atomic64_t *)&adev->wb.wb[ring->wptr_offs], 0);
+		atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0);
 		amdgpu_ring_clear_ring(ring);
 	} else {
 		amdgpu_ring_clear_ring(ring);
@@ -5144,7 +5143,7 @@ static void gfx_v9_0_get_clockgating_state(void *handle, u32 *flags)
 
 static u64 gfx_v9_0_ring_get_rptr_gfx(struct amdgpu_ring *ring)
 {
-	return ring->adev->wb.wb[ring->rptr_offs]; /* gfx9 is 32bit rptr*/
+	return *ring->rptr_cpu_addr; /* gfx9 is 32bit rptr*/
 }
 
 static u64 gfx_v9_0_ring_get_wptr_gfx(struct amdgpu_ring *ring)
@@ -5154,7 +5153,7 @@ static u64 gfx_v9_0_ring_get_wptr_gfx(struct amdgpu_ring *ring)
 
 	/* XXX check if swapping is necessary on BE */
 	if (ring->use_doorbell) {
-		wptr = atomic64_read((atomic64_t *)&adev->wb.wb[ring->wptr_offs]);
+		wptr = atomic64_read((atomic64_t *)ring->wptr_cpu_addr);
 	} else {
 		wptr = RREG32_SOC15(GC, 0, mmCP_RB0_WPTR);
 		wptr += (u64)RREG32_SOC15(GC, 0, mmCP_RB0_WPTR_HI) << 32;
@@ -5169,7 +5168,7 @@ static void gfx_v9_0_ring_set_wptr_gfx(struct amdgpu_ring *ring)
 
 	if (ring->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
-		atomic64_set((atomic64_t*)&adev->wb.wb[ring->wptr_offs], ring->wptr);
+		atomic64_set((atomic64_t*)ring->wptr_cpu_addr, ring->wptr);
 		WDOORBELL64(ring->doorbell_index, ring->wptr);
 	} else {
 		WREG32_SOC15(GC, 0, mmCP_RB0_WPTR, lower_32_bits(ring->wptr));
@@ -5334,7 +5333,7 @@ static void gfx_v9_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 
 static u64 gfx_v9_0_ring_get_rptr_compute(struct amdgpu_ring *ring)
 {
-	return ring->adev->wb.wb[ring->rptr_offs]; /* gfx9 hardware is 32bit rptr */
+	return *ring->rptr_cpu_addr; /* gfx9 hardware is 32bit rptr */
 }
 
 static u64 gfx_v9_0_ring_get_wptr_compute(struct amdgpu_ring *ring)
@@ -5343,7 +5342,7 @@ static u64 gfx_v9_0_ring_get_wptr_compute(struct amdgpu_ring *ring)
 
 	/* XXX check if swapping is necessary on BE */
 	if (ring->use_doorbell)
-		wptr = atomic64_read((atomic64_t *)&ring->adev->wb.wb[ring->wptr_offs]);
+		wptr = atomic64_read((atomic64_t *)ring->wptr_cpu_addr);
 	else
 		BUG();
 	return wptr;
@@ -5355,7 +5354,7 @@ static void gfx_v9_0_ring_set_wptr_compute(struct amdgpu_ring *ring)
 
 	/* XXX check if swapping is necessary on BE */
 	if (ring->use_doorbell) {
-		atomic64_set((atomic64_t*)&adev->wb.wb[ring->wptr_offs], ring->wptr);
+		atomic64_set((atomic64_t*)ring->wptr_cpu_addr, ring->wptr);
 		WDOORBELL64(ring->doorbell_index, ring->wptr);
 	} else{
 		BUG(); /* only DOORBELL method supported on gfx9 now */
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
index 94caf5204c8b..92f21a192ed7 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
@@ -425,7 +425,7 @@ static uint64_t jpeg_v2_0_dec_ring_get_wptr(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 
 	if (ring->use_doorbell)
-		return adev->wb.wb[ring->wptr_offs];
+		return *ring->wptr_cpu_addr;
 	else
 		return RREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR);
 }
@@ -442,7 +442,7 @@ static void jpeg_v2_0_dec_ring_set_wptr(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 
 	if (ring->use_doorbell) {
-		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+		*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
 		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 	} else {
 		WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
index 845306f63cdb..e2461dae8bb0 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
@@ -401,7 +401,7 @@ static uint64_t jpeg_v2_5_dec_ring_get_wptr(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 
 	if (ring->use_doorbell)
-		return adev->wb.wb[ring->wptr_offs];
+		return *ring->wptr_cpu_addr;
 	else
 		return RREG32_SOC15(JPEG, ring->me, mmUVD_JRBC_RB_WPTR);
 }
@@ -418,7 +418,7 @@ static void jpeg_v2_5_dec_ring_set_wptr(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 
 	if (ring->use_doorbell) {
-		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+		*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
 		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 	} else {
 		WREG32_SOC15(JPEG, ring->me, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
index c41e5590a701..23b0729bcc4f 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
@@ -421,7 +421,7 @@ static uint64_t jpeg_v3_0_dec_ring_get_wptr(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 
 	if (ring->use_doorbell)
-		return adev->wb.wb[ring->wptr_offs];
+		return *ring->wptr_cpu_addr;
 	else
 		return RREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR);
 }
@@ -438,7 +438,7 @@ static void jpeg_v3_0_dec_ring_set_wptr(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 
 	if (ring->use_doorbell) {
-		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+		*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
 		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 	} else {
 		WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c b/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c
index 4b746584a797..6bd8d74ff278 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c
@@ -46,7 +46,7 @@ static void mes_v10_1_ring_set_wptr(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 
 	if (ring->use_doorbell) {
-		atomic64_set((atomic64_t*)&adev->wb.wb[ring->wptr_offs],
+		atomic64_set((atomic64_t*)ring->wptr_cpu_addr,
 			     ring->wptr);
 		WDOORBELL64(ring->doorbell_index, ring->wptr);
 	} else {
@@ -56,7 +56,7 @@ static void mes_v10_1_ring_set_wptr(struct amdgpu_ring *ring)
 
 static u64 mes_v10_1_ring_get_rptr(struct amdgpu_ring *ring)
 {
-	return ring->adev->wb.wb[ring->rptr_offs];
+	return *ring->rptr_cpu_addr;
 }
 
 static u64 mes_v10_1_ring_get_wptr(struct amdgpu_ring *ring)
@@ -64,8 +64,7 @@ static u64 mes_v10_1_ring_get_wptr(struct amdgpu_ring *ring)
 	u64 wptr;
 
 	if (ring->use_doorbell)
-		wptr = atomic64_read((atomic64_t *)
-				     &ring->adev->wb.wb[ring->wptr_offs]);
+		wptr = atomic64_read((atomic64_t *)ring->wptr_cpu_addr);
 	else
 		BUG();
 	return wptr;
@@ -673,13 +672,13 @@ static int mes_v10_1_mqd_init(struct amdgpu_ring *ring)
 	mqd->cp_hqd_pq_control = tmp;
 
 	/* set the wb address whether it's enabled or not */
-	wb_gpu_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+	wb_gpu_addr = ring->rptr_gpu_addr;
 	mqd->cp_hqd_pq_rptr_report_addr_lo = wb_gpu_addr & 0xfffffffc;
 	mqd->cp_hqd_pq_rptr_report_addr_hi =
 		upper_32_bits(wb_gpu_addr) & 0xffff;
 
 	/* only used if CP_PQ_WPTR_POLL_CNTL.CP_PQ_WPTR_POLL_CNTL__EN_MASK=1 */
-	wb_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	wb_gpu_addr = ring->wptr_gpu_addr;
 	mqd->cp_hqd_pq_wptr_poll_addr_lo = wb_gpu_addr & 0xfffffff8;
 	mqd->cp_hqd_pq_wptr_poll_addr_hi = upper_32_bits(wb_gpu_addr) & 0xffff;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index 5f304d61999e..13ca406dbd63 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -194,7 +194,7 @@ static int sdma_v2_4_init_microcode(struct amdgpu_device *adev)
 static uint64_t sdma_v2_4_ring_get_rptr(struct amdgpu_ring *ring)
 {
 	/* XXX check if swapping is necessary on BE */
-	return ring->adev->wb.wb[ring->rptr_offs] >> 2;
+	return *ring->rptr_cpu_addr >> 2;
 }
 
 /**
@@ -410,12 +410,10 @@ static int sdma_v2_4_gfx_resume(struct amdgpu_device *adev)
 	struct amdgpu_ring *ring;
 	u32 rb_cntl, ib_cntl;
 	u32 rb_bufsz;
-	u32 wb_offset;
 	int i, j, r;
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		ring = &adev->sdma.instance[i].ring;
-		wb_offset = (ring->rptr_offs * 4);
 
 		mutex_lock(&adev->srbm_mutex);
 		for (j = 0; j < 16; j++) {
@@ -451,9 +449,9 @@ static int sdma_v2_4_gfx_resume(struct amdgpu_device *adev)
 
 		/* set the wb address whether it's enabled or not */
 		WREG32(mmSDMA0_GFX_RB_RPTR_ADDR_HI + sdma_offsets[i],
-		       upper_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFF);
+		       upper_32_bits(ring->rptr_gpu_addr) & 0xFFFFFFFF);
 		WREG32(mmSDMA0_GFX_RB_RPTR_ADDR_LO + sdma_offsets[i],
-		       lower_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFC);
+		       lower_32_bits(ring->rptr_gpu_addr) & 0xFFFFFFFC);
 
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RPTR_WRITEBACK_ENABLE, 1);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index c59f6f6f4c09..61567269af99 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -350,7 +350,7 @@ static int sdma_v3_0_init_microcode(struct amdgpu_device *adev)
 static uint64_t sdma_v3_0_ring_get_rptr(struct amdgpu_ring *ring)
 {
 	/* XXX check if swapping is necessary on BE */
-	return ring->adev->wb.wb[ring->rptr_offs] >> 2;
+	return *ring->rptr_cpu_addr >> 2;
 }
 
 /**
@@ -367,7 +367,7 @@ static uint64_t sdma_v3_0_ring_get_wptr(struct amdgpu_ring *ring)
 
 	if (ring->use_doorbell || ring->use_pollmem) {
 		/* XXX check if swapping is necessary on BE */
-		wptr = ring->adev->wb.wb[ring->wptr_offs] >> 2;
+		wptr = *ring->wptr_cpu_addr >> 2;
 	} else {
 		wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me]) >> 2;
 	}
@@ -387,12 +387,12 @@ static void sdma_v3_0_ring_set_wptr(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 
 	if (ring->use_doorbell) {
-		u32 *wb = (u32 *)&adev->wb.wb[ring->wptr_offs];
+		u32 *wb = (u32 *)ring->wptr_cpu_addr;
 		/* XXX check if swapping is necessary on BE */
 		WRITE_ONCE(*wb, (lower_32_bits(ring->wptr) << 2));
 		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr) << 2);
 	} else if (ring->use_pollmem) {
-		u32 *wb = (u32 *)&adev->wb.wb[ring->wptr_offs];
+		u32 *wb = (u32 *)ring->wptr_cpu_addr;
 
 		WRITE_ONCE(*wb, (lower_32_bits(ring->wptr) << 2));
 	} else {
@@ -645,7 +645,6 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev)
 	struct amdgpu_ring *ring;
 	u32 rb_cntl, ib_cntl, wptr_poll_cntl;
 	u32 rb_bufsz;
-	u32 wb_offset;
 	u32 doorbell;
 	u64 wptr_gpu_addr;
 	int i, j, r;
@@ -653,7 +652,6 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev)
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		ring = &adev->sdma.instance[i].ring;
 		amdgpu_ring_clear_ring(ring);
-		wb_offset = (ring->rptr_offs * 4);
 
 		mutex_lock(&adev->srbm_mutex);
 		for (j = 0; j < 16; j++) {
@@ -690,9 +688,9 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev)
 
 		/* set the wb address whether it's enabled or not */
 		WREG32(mmSDMA0_GFX_RB_RPTR_ADDR_HI + sdma_offsets[i],
-		       upper_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFF);
+		       upper_32_bits(ring->rptr_gpu_addr) & 0xFFFFFFFF);
 		WREG32(mmSDMA0_GFX_RB_RPTR_ADDR_LO + sdma_offsets[i],
-		       lower_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFC);
+		       lower_32_bits(ring->rptr_gpu_addr) & 0xFFFFFFFC);
 
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RPTR_WRITEBACK_ENABLE, 1);
 
@@ -711,7 +709,7 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev)
 		WREG32(mmSDMA0_GFX_DOORBELL + sdma_offsets[i], doorbell);
 
 		/* setup the wptr shadow polling */
-		wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+		wptr_gpu_addr = ring->wptr_gpu_addr;
 
 		WREG32(mmSDMA0_GFX_RB_WPTR_POLL_ADDR_LO + sdma_offsets[i],
 		       lower_32_bits(wptr_gpu_addr));
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 2985c61bc6a1..5f29a01c2395 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -687,7 +687,7 @@ static uint64_t sdma_v4_0_ring_get_rptr(struct amdgpu_ring *ring)
 	u64 *rptr;
 
 	/* XXX check if swapping is necessary on BE */
-	rptr = ((u64 *)&ring->adev->wb.wb[ring->rptr_offs]);
+	rptr = ((u64 *)ring->rptr_cpu_addr);
 
 	DRM_DEBUG("rptr before shift == 0x%016llx\n", *rptr);
 	return ((*rptr) >> 2);
@@ -707,7 +707,7 @@ static uint64_t sdma_v4_0_ring_get_wptr(struct amdgpu_ring *ring)
 
 	if (ring->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
-		wptr = READ_ONCE(*((u64 *)&adev->wb.wb[ring->wptr_offs]));
+		wptr = READ_ONCE(*((u64 *)ring->wptr_cpu_addr));
 		DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", wptr);
 	} else {
 		wptr = RREG32_SDMA(ring->me, mmSDMA0_GFX_RB_WPTR_HI);
@@ -733,7 +733,7 @@ static void sdma_v4_0_ring_set_wptr(struct amdgpu_ring *ring)
 
 	DRM_DEBUG("Setting write pointer\n");
 	if (ring->use_doorbell) {
-		u64 *wb = (u64 *)&adev->wb.wb[ring->wptr_offs];
+		u64 *wb = (u64 *)ring->wptr_cpu_addr;
 
 		DRM_DEBUG("Using doorbell -- "
 				"wptr_offs == 0x%08x "
@@ -776,7 +776,7 @@ static uint64_t sdma_v4_0_page_ring_get_wptr(struct amdgpu_ring *ring)
 
 	if (ring->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
-		wptr = READ_ONCE(*((u64 *)&adev->wb.wb[ring->wptr_offs]));
+		wptr = READ_ONCE(*((u64 *)ring->wptr_cpu_addr));
 	} else {
 		wptr = RREG32_SDMA(ring->me, mmSDMA0_PAGE_RB_WPTR_HI);
 		wptr = wptr << 32;
@@ -798,7 +798,7 @@ static void sdma_v4_0_page_ring_set_wptr(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 
 	if (ring->use_doorbell) {
-		u64 *wb = (u64 *)&adev->wb.wb[ring->wptr_offs];
+		u64 *wb = (u64 *)ring->wptr_cpu_addr;
 
 		/* XXX check if swapping is necessary on BE */
 		WRITE_ONCE(*wb, (ring->wptr << 2));
@@ -1124,13 +1124,10 @@ static void sdma_v4_0_gfx_resume(struct amdgpu_device *adev, unsigned int i)
 {
 	struct amdgpu_ring *ring = &adev->sdma.instance[i].ring;
 	u32 rb_cntl, ib_cntl, wptr_poll_cntl;
-	u32 wb_offset;
 	u32 doorbell;
 	u32 doorbell_offset;
 	u64 wptr_gpu_addr;
 
-	wb_offset = (ring->rptr_offs * 4);
-
 	rb_cntl = RREG32_SDMA(i, mmSDMA0_GFX_RB_CNTL);
 	rb_cntl = sdma_v4_0_rb_cntl(ring, rb_cntl);
 	WREG32_SDMA(i, mmSDMA0_GFX_RB_CNTL, rb_cntl);
@@ -1143,9 +1140,9 @@ static void sdma_v4_0_gfx_resume(struct amdgpu_device *adev, unsigned int i)
 
 	/* set the wb address whether it's enabled or not */
 	WREG32_SDMA(i, mmSDMA0_GFX_RB_RPTR_ADDR_HI,
-	       upper_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFF);
+	       upper_32_bits(ring->rptr_gpu_addr) & 0xFFFFFFFF);
 	WREG32_SDMA(i, mmSDMA0_GFX_RB_RPTR_ADDR_LO,
-	       lower_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFC);
+	       lower_32_bits(ring->rptr_gpu_addr) & 0xFFFFFFFC);
 
 	rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL,
 				RPTR_WRITEBACK_ENABLE, 1);
@@ -1175,7 +1172,7 @@ static void sdma_v4_0_gfx_resume(struct amdgpu_device *adev, unsigned int i)
 	WREG32_SDMA(i, mmSDMA0_GFX_MINOR_PTR_UPDATE, 0);
 
 	/* setup the wptr shadow polling */
-	wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	wptr_gpu_addr = ring->wptr_gpu_addr;
 	WREG32_SDMA(i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_LO,
 		    lower_32_bits(wptr_gpu_addr));
 	WREG32_SDMA(i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_HI,
@@ -1214,13 +1211,10 @@ static void sdma_v4_0_page_resume(struct amdgpu_device *adev, unsigned int i)
 {
 	struct amdgpu_ring *ring = &adev->sdma.instance[i].page;
 	u32 rb_cntl, ib_cntl, wptr_poll_cntl;
-	u32 wb_offset;
 	u32 doorbell;
 	u32 doorbell_offset;
 	u64 wptr_gpu_addr;
 
-	wb_offset = (ring->rptr_offs * 4);
-
 	rb_cntl = RREG32_SDMA(i, mmSDMA0_PAGE_RB_CNTL);
 	rb_cntl = sdma_v4_0_rb_cntl(ring, rb_cntl);
 	WREG32_SDMA(i, mmSDMA0_PAGE_RB_CNTL, rb_cntl);
@@ -1233,9 +1227,9 @@ static void sdma_v4_0_page_resume(struct amdgpu_device *adev, unsigned int i)
 
 	/* set the wb address whether it's enabled or not */
 	WREG32_SDMA(i, mmSDMA0_PAGE_RB_RPTR_ADDR_HI,
-	       upper_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFF);
+	       upper_32_bits(ring->rptr_gpu_addr) & 0xFFFFFFFF);
 	WREG32_SDMA(i, mmSDMA0_PAGE_RB_RPTR_ADDR_LO,
-	       lower_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFC);
+	       lower_32_bits(ring->rptr_gpu_addr) & 0xFFFFFFFC);
 
 	rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_PAGE_RB_CNTL,
 				RPTR_WRITEBACK_ENABLE, 1);
@@ -1266,7 +1260,7 @@ static void sdma_v4_0_page_resume(struct amdgpu_device *adev, unsigned int i)
 	WREG32_SDMA(i, mmSDMA0_PAGE_MINOR_PTR_UPDATE, 0);
 
 	/* setup the wptr shadow polling */
-	wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	wptr_gpu_addr = ring->wptr_gpu_addr;
 	WREG32_SDMA(i, mmSDMA0_PAGE_RB_WPTR_POLL_ADDR_LO,
 		    lower_32_bits(wptr_gpu_addr));
 	WREG32_SDMA(i, mmSDMA0_PAGE_RB_WPTR_POLL_ADDR_HI,
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index e2232dd12d8e..e45f61b001dc 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -299,7 +299,7 @@ static uint64_t sdma_v5_0_ring_get_rptr(struct amdgpu_ring *ring)
 	u64 *rptr;
 
 	/* XXX check if swapping is necessary on BE */
-	rptr = ((u64 *)&ring->adev->wb.wb[ring->rptr_offs]);
+	rptr = (u64 *)ring->rptr_cpu_addr;
 
 	DRM_DEBUG("rptr before shift == 0x%016llx\n", *rptr);
 	return ((*rptr) >> 2);
@@ -319,7 +319,7 @@ static uint64_t sdma_v5_0_ring_get_wptr(struct amdgpu_ring *ring)
 
 	if (ring->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
-		wptr = READ_ONCE(*((u64 *)&adev->wb.wb[ring->wptr_offs]));
+		wptr = READ_ONCE(*((u64 *)ring->wptr_cpu_addr));
 		DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", wptr);
 	} else {
 		wptr = RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI));
@@ -352,8 +352,8 @@ static void sdma_v5_0_ring_set_wptr(struct amdgpu_ring *ring)
 				lower_32_bits(ring->wptr << 2),
 				upper_32_bits(ring->wptr << 2));
 		/* XXX check if swapping is necessary on BE */
-		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr << 2);
-		adev->wb.wb[ring->wptr_offs + 1] = upper_32_bits(ring->wptr << 2);
+		atomic64_set((atomic64_t *)ring->wptr_cpu_addr,
+			     ring->wptr << 2);
 		DRM_DEBUG("calling WDOORBELL64(0x%08x, 0x%016llx)\n",
 				ring->doorbell_index, ring->wptr << 2);
 		WDOORBELL64(ring->doorbell_index, ring->wptr << 2);
@@ -644,7 +644,6 @@ static int sdma_v5_0_gfx_resume(struct amdgpu_device *adev)
 	struct amdgpu_ring *ring;
 	u32 rb_cntl, ib_cntl;
 	u32 rb_bufsz;
-	u32 wb_offset;
 	u32 doorbell;
 	u32 doorbell_offset;
 	u32 temp;
@@ -654,7 +653,6 @@ static int sdma_v5_0_gfx_resume(struct amdgpu_device *adev)
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		ring = &adev->sdma.instance[i].ring;
-		wb_offset = (ring->rptr_offs * 4);
 
 		if (!amdgpu_sriov_vf(adev))
 			WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_SEM_WAIT_FAIL_TIMER_CNTL), 0);
@@ -677,7 +675,7 @@ static int sdma_v5_0_gfx_resume(struct amdgpu_device *adev)
 		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_HI), 0);
 
 		/* setup the wptr shadow polling */
-		wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+		wptr_gpu_addr = ring->wptr_gpu_addr;
 		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_LO),
 		       lower_32_bits(wptr_gpu_addr));
 		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_HI),
@@ -692,9 +690,9 @@ static int sdma_v5_0_gfx_resume(struct amdgpu_device *adev)
 
 		/* set the wb address whether it's enabled or not */
 		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_ADDR_HI),
-		       upper_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFF);
+		       upper_32_bits(ring->rptr_gpu_addr) & 0xFFFFFFFF);
 		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_ADDR_LO),
-		       lower_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFC);
+		       lower_32_bits(ring->rptr_gpu_addr) & 0xFFFFFFFC);
 
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RPTR_WRITEBACK_ENABLE, 1);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index 46a9617fee5f..df5c4c1f137d 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -252,7 +252,7 @@ static uint64_t sdma_v5_2_ring_get_rptr(struct amdgpu_ring *ring)
 	u64 *rptr;
 
 	/* XXX check if swapping is necessary on BE */
-	rptr = ((u64 *)&ring->adev->wb.wb[ring->rptr_offs]);
+	rptr = (u64 *)ring->rptr_cpu_addr;
 
 	DRM_DEBUG("rptr before shift == 0x%016llx\n", *rptr);
 	return ((*rptr) >> 2);
@@ -272,7 +272,7 @@ static uint64_t sdma_v5_2_ring_get_wptr(struct amdgpu_ring *ring)
 
 	if (ring->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
-		wptr = READ_ONCE(*((u64 *)&adev->wb.wb[ring->wptr_offs]));
+		wptr = READ_ONCE(*((u64 *)ring->wptr_cpu_addr));
 		DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", wptr);
 	} else {
 		wptr = RREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI));
@@ -305,8 +305,8 @@ static void sdma_v5_2_ring_set_wptr(struct amdgpu_ring *ring)
 				lower_32_bits(ring->wptr << 2),
 				upper_32_bits(ring->wptr << 2));
 		/* XXX check if swapping is necessary on BE */
-		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr << 2);
-		adev->wb.wb[ring->wptr_offs + 1] = upper_32_bits(ring->wptr << 2);
+		atomic64_set((atomic64_t *)ring->wptr_cpu_addr,
+			     ring->wptr << 2);
 		DRM_DEBUG("calling WDOORBELL64(0x%08x, 0x%016llx)\n",
 				ring->doorbell_index, ring->wptr << 2);
 		WDOORBELL64(ring->doorbell_index, ring->wptr << 2);
@@ -584,7 +584,6 @@ static int sdma_v5_2_gfx_resume(struct amdgpu_device *adev)
 	struct amdgpu_ring *ring;
 	u32 rb_cntl, ib_cntl;
 	u32 rb_bufsz;
-	u32 wb_offset;
 	u32 doorbell;
 	u32 doorbell_offset;
 	u32 temp;
@@ -594,7 +593,6 @@ static int sdma_v5_2_gfx_resume(struct amdgpu_device *adev)
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		ring = &adev->sdma.instance[i].ring;
-		wb_offset = (ring->rptr_offs * 4);
 
 		WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_SEM_WAIT_FAIL_TIMER_CNTL), 0);
 
@@ -616,7 +614,7 @@ static int sdma_v5_2_gfx_resume(struct amdgpu_device *adev)
 		WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_HI), 0);
 
 		/* setup the wptr shadow polling */
-		wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+		wptr_gpu_addr = ring->wptr_gpu_addr;
 		WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_LO),
 		       lower_32_bits(wptr_gpu_addr));
 		WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_HI),
@@ -631,9 +629,9 @@ static int sdma_v5_2_gfx_resume(struct amdgpu_device *adev)
 
 		/* set the wb address whether it's enabled or not */
 		WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_ADDR_HI),
-		       upper_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFF);
+		       upper_32_bits(ring->rptr_gpu_addr) & 0xFFFFFFFF);
 		WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_ADDR_LO),
-		       lower_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFC);
+		       lower_32_bits(ring->rptr_gpu_addr) & 0xFFFFFFFC);
 
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RPTR_WRITEBACK_ENABLE, 1);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c
index 7d2bbcbe547b..15ade3cc25cd 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dma.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dma.c
@@ -40,7 +40,7 @@ static void si_dma_set_irq_funcs(struct amdgpu_device *adev);
 
 static uint64_t si_dma_ring_get_rptr(struct amdgpu_ring *ring)
 {
-	return ring->adev->wb.wb[ring->rptr_offs>>2];
+	return *ring->rptr_cpu_addr;
 }
 
 static uint64_t si_dma_ring_get_wptr(struct amdgpu_ring *ring)
@@ -152,7 +152,7 @@ static int si_dma_start(struct amdgpu_device *adev)
 		WREG32(DMA_RB_RPTR + sdma_offsets[i], 0);
 		WREG32(DMA_RB_WPTR + sdma_offsets[i], 0);
 
-		rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+		rptr_addr = ring->rptr_gpu_addr;
 
 		WREG32(DMA_RB_RPTR_ADDR_LO + sdma_offsets[i], lower_32_bits(rptr_addr));
 		WREG32(DMA_RB_RPTR_ADDR_HI + sdma_offsets[i], upper_32_bits(rptr_addr) & 0xFF);
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index e07e3fae99b5..a65fca04d094 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -118,7 +118,7 @@ static uint64_t uvd_v7_0_enc_ring_get_wptr(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 
 	if (ring->use_doorbell)
-		return adev->wb.wb[ring->wptr_offs];
+		return *ring->wptr_cpu_addr;
 
 	if (ring == &adev->uvd.inst[ring->me].ring_enc[0])
 		return RREG32_SOC15(UVD, ring->me, mmUVD_RB_WPTR);
@@ -153,7 +153,7 @@ static void uvd_v7_0_enc_ring_set_wptr(struct amdgpu_ring *ring)
 
 	if (ring->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
-		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+		*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
 		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 		return;
 	}
@@ -735,7 +735,7 @@ static int uvd_v7_0_mmsch_start(struct amdgpu_device *adev,
 		if (adev->uvd.harvest_config & (1 << i))
 			continue;
 		WDOORBELL32(adev->uvd.inst[i].ring_enc[0].doorbell_index, 0);
-		adev->wb.wb[adev->uvd.inst[i].ring_enc[0].wptr_offs] = 0;
+		*adev->uvd.inst[i].ring_enc[0].wptr_cpu_addr = 0;
 		adev->uvd.inst[i].ring_enc[0].wptr = 0;
 		adev->uvd.inst[i].ring_enc[0].wptr_old = 0;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
index 37fa163393fd..0101d9235773 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
@@ -82,7 +82,7 @@ static uint64_t vce_v4_0_ring_get_wptr(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 
 	if (ring->use_doorbell)
-		return adev->wb.wb[ring->wptr_offs];
+		return *ring->wptr_cpu_addr;
 
 	if (ring->me == 0)
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_WPTR));
@@ -105,7 +105,7 @@ static void vce_v4_0_ring_set_wptr(struct amdgpu_ring *ring)
 
 	if (ring->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
-		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+		*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
 		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 		return;
 	}
@@ -176,7 +176,7 @@ static int vce_v4_0_mmsch_start(struct amdgpu_device *adev,
 	WREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_MMSCH_VF_MAILBOX_RESP), 0);
 
 	WDOORBELL32(adev->vce.ring[0].doorbell_index, 0);
-	adev->wb.wb[adev->vce.ring[0].wptr_offs] = 0;
+	*adev->vce.ring[0].wptr_cpu_addr = 0;
 	adev->vce.ring[0].wptr = 0;
 	adev->vce.ring[0].wptr_old = 0;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index 23a9eb5b2c8a..844b705fcf97 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -1333,7 +1333,7 @@ static uint64_t vcn_v2_0_dec_ring_get_wptr(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 
 	if (ring->use_doorbell)
-		return adev->wb.wb[ring->wptr_offs];
+		return *ring->wptr_cpu_addr;
 	else
 		return RREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR);
 }
@@ -1354,7 +1354,7 @@ static void vcn_v2_0_dec_ring_set_wptr(struct amdgpu_ring *ring)
 			lower_32_bits(ring->wptr) | 0x80000000);
 
 	if (ring->use_doorbell) {
-		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+		*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
 		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 	} else {
 		WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr));
@@ -1557,12 +1557,12 @@ static uint64_t vcn_v2_0_enc_ring_get_wptr(struct amdgpu_ring *ring)
 
 	if (ring == &adev->vcn.inst->ring_enc[0]) {
 		if (ring->use_doorbell)
-			return adev->wb.wb[ring->wptr_offs];
+			return *ring->wptr_cpu_addr;
 		else
 			return RREG32_SOC15(UVD, 0, mmUVD_RB_WPTR);
 	} else {
 		if (ring->use_doorbell)
-			return adev->wb.wb[ring->wptr_offs];
+			return *ring->wptr_cpu_addr;
 		else
 			return RREG32_SOC15(UVD, 0, mmUVD_RB_WPTR2);
 	}
@@ -1581,14 +1581,14 @@ static void vcn_v2_0_enc_ring_set_wptr(struct amdgpu_ring *ring)
 
 	if (ring == &adev->vcn.inst->ring_enc[0]) {
 		if (ring->use_doorbell) {
-			adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+			*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
 			WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 		} else {
 			WREG32_SOC15(UVD, 0, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
 		}
 	} else {
 		if (ring->use_doorbell) {
-			adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+			*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
 			WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 		} else {
 			WREG32_SOC15(UVD, 0, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index 2719ef9de3bd..60fd3d676cdf 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -1491,7 +1491,7 @@ static uint64_t vcn_v2_5_dec_ring_get_wptr(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 
 	if (ring->use_doorbell)
-		return adev->wb.wb[ring->wptr_offs];
+		return *ring->wptr_cpu_addr;
 	else
 		return RREG32_SOC15(VCN, ring->me, mmUVD_RBC_RB_WPTR);
 }
@@ -1508,7 +1508,7 @@ static void vcn_v2_5_dec_ring_set_wptr(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 
 	if (ring->use_doorbell) {
-		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+		*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
 		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 	} else {
 		WREG32_SOC15(VCN, ring->me, mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr));
@@ -1575,12 +1575,12 @@ static uint64_t vcn_v2_5_enc_ring_get_wptr(struct amdgpu_ring *ring)
 
 	if (ring == &adev->vcn.inst[ring->me].ring_enc[0]) {
 		if (ring->use_doorbell)
-			return adev->wb.wb[ring->wptr_offs];
+			return *ring->wptr_cpu_addr;
 		else
 			return RREG32_SOC15(VCN, ring->me, mmUVD_RB_WPTR);
 	} else {
 		if (ring->use_doorbell)
-			return adev->wb.wb[ring->wptr_offs];
+			return *ring->wptr_cpu_addr;
 		else
 			return RREG32_SOC15(VCN, ring->me, mmUVD_RB_WPTR2);
 	}
@@ -1599,14 +1599,14 @@ static void vcn_v2_5_enc_ring_set_wptr(struct amdgpu_ring *ring)
 
 	if (ring == &adev->vcn.inst[ring->me].ring_enc[0]) {
 		if (ring->use_doorbell) {
-			adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+			*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
 			WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 		} else {
 			WREG32_SOC15(VCN, ring->me, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
 		}
 	} else {
 		if (ring->use_doorbell) {
-			adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+			*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
 			WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 		} else {
 			WREG32_SOC15(VCN, ring->me, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 63e5547cfb16..967c20157b34 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -1614,7 +1614,7 @@ static uint64_t vcn_v3_0_dec_ring_get_wptr(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 
 	if (ring->use_doorbell)
-		return adev->wb.wb[ring->wptr_offs];
+		return *ring->wptr_cpu_addr;
 	else
 		return RREG32_SOC15(VCN, ring->me, mmUVD_RBC_RB_WPTR);
 }
@@ -1635,7 +1635,7 @@ static void vcn_v3_0_dec_ring_set_wptr(struct amdgpu_ring *ring)
 			lower_32_bits(ring->wptr) | 0x80000000);
 
 	if (ring->use_doorbell) {
-		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+		*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
 		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 	} else {
 		WREG32_SOC15(VCN, ring->me, mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr));
@@ -1702,12 +1702,12 @@ static uint64_t vcn_v3_0_enc_ring_get_wptr(struct amdgpu_ring *ring)
 
 	if (ring == &adev->vcn.inst[ring->me].ring_enc[0]) {
 		if (ring->use_doorbell)
-			return adev->wb.wb[ring->wptr_offs];
+			return *ring->wptr_cpu_addr;
 		else
 			return RREG32_SOC15(VCN, ring->me, mmUVD_RB_WPTR);
 	} else {
 		if (ring->use_doorbell)
-			return adev->wb.wb[ring->wptr_offs];
+			return *ring->wptr_cpu_addr;
 		else
 			return RREG32_SOC15(VCN, ring->me, mmUVD_RB_WPTR2);
 	}
@@ -1726,14 +1726,14 @@ static void vcn_v3_0_enc_ring_set_wptr(struct amdgpu_ring *ring)
 
 	if (ring == &adev->vcn.inst[ring->me].ring_enc[0]) {
 		if (ring->use_doorbell) {
-			adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+			*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
 			WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 		} else {
 			WREG32_SOC15(VCN, ring->me, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
 		}
 	} else {
 		if (ring->use_doorbell) {
-			adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+			*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
 			WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 		} else {
 			WREG32_SOC15(VCN, ring->me, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
-- 
2.26.2

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH 4/4] drm/amdgpu: assign the cpu/gpu address of fence from ring

[Jack Xiao]

assign the cpu/gpu address of fence for the normal or mes ring
from ring structure.

Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 58d4c219178a..0be3e2007387 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -407,8 +407,8 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
 	uint64_t index;
 
 	if (ring->funcs->type != AMDGPU_RING_TYPE_UVD) {
-		ring->fence_drv.cpu_addr = &adev->wb.wb[ring->fence_offs];
-		ring->fence_drv.gpu_addr = adev->wb.gpu_addr + (ring->fence_offs * 4);
+		ring->fence_drv.cpu_addr = ring->fence_cpu_addr;
+		ring->fence_drv.gpu_addr = ring->fence_gpu_addr;
 	} else {
 		/* put fence directly behind firmware */
 		index = ALIGN(adev->uvd.fw->size, 8);
-- 
2.26.2

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

RE: [PATCH 4/4] drm/amdgpu: assign the cpu/gpu address of fence from ring

[Ma, Le]

[AMD Public Use]

Series is Reviewed-by: Le Ma <Le.Ma@amd.com>

Regards,
Ma Le

-----Original Message-----
From: Xiao, Jack <Jack.Xiao@amd.com> 
Sent: Tuesday, July 28, 2020 6:22 PM
To: amd-gfx@lists.freedesktop.org; Deucher, Alexander <Alexander.Deucher@amd.com>; Zhang, Hawking <Hawking.Zhang@amd.com>; Koenig, Christian <Christian.Koenig@amd.com>; Ma, Le <Le.Ma@amd.com>
Cc: Xiao, Jack <Jack.Xiao@amd.com>; Koenig, Christian <Christian.Koenig@amd.com>
Subject: [PATCH 4/4] drm/amdgpu: assign the cpu/gpu address of fence from ring

assign the cpu/gpu address of fence for the normal or mes ring from ring structure.

Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 58d4c219178a..0be3e2007387 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -407,8 +407,8 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
 	uint64_t index;
 
 	if (ring->funcs->type != AMDGPU_RING_TYPE_UVD) {
-		ring->fence_drv.cpu_addr = &adev->wb.wb[ring->fence_offs];
-		ring->fence_drv.gpu_addr = adev->wb.gpu_addr + (ring->fence_offs * 4);
+		ring->fence_drv.cpu_addr = ring->fence_cpu_addr;
+		ring->fence_drv.gpu_addr = ring->fence_gpu_addr;
 	} else {
 		/* put fence directly behind firmware */
 		index = ALIGN(adev->uvd.fw->size, 8);
--
2.26.2
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH 2/4] drm/amdgpu: initialize the cpu/gpu address of rptr/wptr/fence

[Christian König]

Am 28.07.20 um 12:21 schrieb Jack Xiao:
> Initialize the cpu/gpu address of rptr/wptr/fence.
>
> Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 37 ++++++++++++++++++++----
>   1 file changed, 32 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
> index 13ea8ebc421c..ff63ecc861bc 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
> @@ -150,6 +150,12 @@ void amdgpu_ring_undo(struct amdgpu_ring *ring)
>   		ring->funcs->end_use(ring);
>   }
>   
> +#define amdgpu_ring_get_gpu_addr(ring, offset)	\
> +	(ring->adev->wb.gpu_addr + offset * 4)
> +
> +#define amdgpu_ring_get_cpu_addr(ring, offset)	\
> +	(&ring->adev->wb.wb[offset])

Those are not ring functions, but rather wb functions. Please clean that up.

Christian.

> +
>   /**
>    * amdgpu_ring_init - init driver ring struct.
>    *
> @@ -217,17 +223,38 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
>   			"(%d) ring trail_fence_offs wb alloc failed\n", r);
>   		return r;
>   	}
> -	ring->trail_fence_gpu_addr =
> -		adev->wb.gpu_addr + (ring->trail_fence_offs * 4);
> -	ring->trail_fence_cpu_addr = &adev->wb.wb[ring->trail_fence_offs];
>   
>   	r = amdgpu_device_wb_get(adev, &ring->cond_exe_offs);
>   	if (r) {
>   		dev_err(adev->dev, "(%d) ring cond_exec_polling wb alloc failed\n", r);
>   		return r;
>   	}
> -	ring->cond_exe_gpu_addr = adev->wb.gpu_addr + (ring->cond_exe_offs * 4);
> -	ring->cond_exe_cpu_addr = &adev->wb.wb[ring->cond_exe_offs];
> +
> +	ring->fence_gpu_addr =
> +		amdgpu_ring_get_gpu_addr(ring, ring->fence_offs);
> +	ring->fence_cpu_addr =
> +		amdgpu_ring_get_cpu_addr(ring, ring->fence_offs);
> +
> +	ring->rptr_gpu_addr =
> +		amdgpu_ring_get_gpu_addr(ring, ring->rptr_offs);
> +	ring->rptr_cpu_addr =
> +		amdgpu_ring_get_cpu_addr(ring, ring->rptr_offs);
> +
> +	ring->wptr_gpu_addr =
> +		amdgpu_ring_get_gpu_addr(ring, ring->wptr_offs);
> +	ring->wptr_cpu_addr =
> +		amdgpu_ring_get_cpu_addr(ring, ring->wptr_offs);
> +
> +	ring->trail_fence_gpu_addr =
> +		amdgpu_ring_get_gpu_addr(ring, ring->trail_fence_offs);
> +	ring->trail_fence_cpu_addr =
> +		amdgpu_ring_get_cpu_addr(ring, ring->trail_fence_offs);
> +
> +	ring->cond_exe_gpu_addr =
> +		amdgpu_ring_get_gpu_addr(ring, ring->cond_exe_offs);
> +	ring->cond_exe_cpu_addr =
> +		amdgpu_ring_get_cpu_addr(ring, ring->cond_exe_offs);
> +
>   	/* always set cond_exec_polling to CONTINUE */
>   	*ring->cond_exe_cpu_addr = 1;
>   

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH 4/4] drm/amdgpu: assign the cpu/gpu address of fence from ring

[Christian König]

Am 28.07.20 um 12:21 schrieb Jack Xiao:
> assign the cpu/gpu address of fence for the normal or mes ring
> from ring structure.
>
> Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
> Acked-by: Christian König <christian.koenig@amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 4 ++--
>   1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> index 58d4c219178a..0be3e2007387 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> @@ -407,8 +407,8 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
>   	uint64_t index;
>   
>   	if (ring->funcs->type != AMDGPU_RING_TYPE_UVD) {
> -		ring->fence_drv.cpu_addr = &adev->wb.wb[ring->fence_offs];
> -		ring->fence_drv.gpu_addr = adev->wb.gpu_addr + (ring->fence_offs * 4);
> +		ring->fence_drv.cpu_addr = ring->fence_cpu_addr;
> +		ring->fence_drv.gpu_addr = ring->fence_gpu_addr;

That doesn't look like a good idea to me. We should probably rather 
remove ring->fence_offs and move all the handling here instead.

Christian.

>   	} else {
>   		/* put fence directly behind firmware */
>   		index = ALIGN(adev->uvd.fw->size, 8);

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx