drm/amdgpu: separate PASID mapping from VM flush v2

Stuffing the PASID mapping into the VM flush isn't flexible enough since
the PASID mapping changes not as often as we need a VM flush.

v2: add missing use of gmc_v7_0_emit_pasid_mapping

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -1774,7 +1774,8 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_asic_flush_hdp(adev, r) (adev)->asic_funcs->flush_hdp((adev), (r))
 #define amdgpu_asic_invalidate_hdp(adev, r) (adev)->asic_funcs->invalidate_hdp((adev), (r))
 #define amdgpu_gmc_flush_gpu_tlb(adev, vmid) (adev)->gmc.gmc_funcs->flush_gpu_tlb((adev), (vmid))
-#define amdgpu_gmc_emit_flush_gpu_tlb(r, vmid, pasid, addr) (r)->adev->gmc.gmc_funcs->emit_flush_gpu_tlb((r), (vmid), (pasid), (addr))
+#define amdgpu_gmc_emit_flush_gpu_tlb(r, vmid, addr) (r)->adev->gmc.gmc_funcs->emit_flush_gpu_tlb((r), (vmid), (addr))
+#define amdgpu_gmc_emit_pasid_mapping(r, vmid, pasid) (r)->adev->gmc.gmc_funcs->emit_pasid_mapping((r), (vmid), (pasid))
 #define amdgpu_gmc_set_pte_pde(adev, pt, idx, addr, flags) (adev)->gmc.gmc_funcs->set_pte_pde((adev), (pt), (idx), (addr), (flags))
 #define amdgpu_gmc_get_vm_pde(adev, level, dst, flags) (adev)->gmc.gmc_funcs->get_vm_pde((adev), (level), (dst), (flags))
 #define amdgpu_gmc_get_pte_flags(adev, flags) (adev)->gmc.gmc_funcs->get_vm_pte_flags((adev),(flags))
@@ -1789,7 +1790,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_ring_set_wptr(r) (r)->funcs->set_wptr((r))
 #define amdgpu_ring_emit_ib(r, ib, vmid, c) (r)->funcs->emit_ib((r), (ib), (vmid), (c))
 #define amdgpu_ring_emit_pipeline_sync(r) (r)->funcs->emit_pipeline_sync((r))
-#define amdgpu_ring_emit_vm_flush(r, vmid, pasid, addr) (r)->funcs->emit_vm_flush((r), (vmid), (pasid), (addr))
+#define amdgpu_ring_emit_vm_flush(r, vmid, addr) (r)->funcs->emit_vm_flush((r), (vmid), (addr))
 #define amdgpu_ring_emit_fence(r, addr, seq, flags) (r)->funcs->emit_fence((r), (addr), (seq), (flags))
 #define amdgpu_ring_emit_gds_switch(r, v, db, ds, wb, ws, ab, as) (r)->funcs->emit_gds_switch((r), (v), (db), (ds), (wb), (ws), (ab), (as))
 #define amdgpu_ring_emit_hdp_flush(r) (r)->funcs->emit_hdp_flush((r))

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

@@ -54,7 +54,10 @@ struct amdgpu_gmc_funcs {
 			      uint32_t vmid);
 	/* flush the vm tlb via ring */
 	uint64_t (*emit_flush_gpu_tlb)(struct amdgpu_ring *ring, unsigned vmid,
-				       unsigned pasid, uint64_t pd_addr);
+				       uint64_t pd_addr);
+	/* Change the VMID -> PASID mapping */
+	void (*emit_pasid_mapping)(struct amdgpu_ring *ring, unsigned vmid,
+				   unsigned pasid);
 	/* write pte/pde updates using the cpu */
 	int (*set_pte_pde)(struct amdgpu_device *adev,
 			   void *cpu_pt_addr, /* cpu addr of page table */

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

@@ -126,7 +126,7 @@ struct amdgpu_ring_funcs {
 			   uint64_t seq, unsigned flags);
 	void (*emit_pipeline_sync)(struct amdgpu_ring *ring);
 	void (*emit_vm_flush)(struct amdgpu_ring *ring, unsigned vmid,
-			      unsigned pasid, uint64_t pd_addr);
+			      uint64_t pd_addr);
 	void (*emit_hdp_flush)(struct amdgpu_ring *ring);
 	void (*emit_gds_switch)(struct amdgpu_ring *ring, uint32_t vmid,
 				uint32_t gds_base, uint32_t gds_size,

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

@@ -612,8 +612,11 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_
 		struct dma_fence *fence;
 
 		trace_amdgpu_vm_flush(ring, job->vmid, job->vm_pd_addr);
-		amdgpu_ring_emit_vm_flush(ring, job->vmid, job->pasid,
+		amdgpu_ring_emit_vm_flush(ring, job->vmid, job->vm_pd_addr);
-					  job->vm_pd_addr);
+		if (adev->gmc.gmc_funcs->emit_pasid_mapping &&
+		    ring->funcs->emit_wreg)
+			amdgpu_gmc_emit_pasid_mapping(ring, job->vmid,
+						      job->pasid);
 
 		r = amdgpu_fence_emit(ring, &fence);
 		if (r)

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

@@ -873,13 +873,12 @@ static void cik_sdma_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
  * using sDMA (CIK).
  */
 static void cik_sdma_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					unsigned vmid, unsigned pasid,
+					unsigned vmid, uint64_t pd_addr)
-					uint64_t pd_addr)
 {
 	u32 extra_bits = (SDMA_POLL_REG_MEM_EXTRA_OP(0) |
 			  SDMA_POLL_REG_MEM_EXTRA_FUNC(0)); /* always */
 
-	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pasid, pd_addr);
+	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
 
 	amdgpu_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_POLL_REG_MEM, 0, extra_bits));
 	amdgpu_ring_write(ring, mmVM_INVALIDATE_REQUEST << 2);

drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c

@@ -2326,12 +2326,11 @@ static void gfx_v6_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
 }
 
 static void gfx_v6_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					unsigned vmid, unsigned pasid,
+					unsigned vmid, uint64_t pd_addr)
-					uint64_t pd_addr)
 {
 	int usepfp = (ring->funcs->type == AMDGPU_RING_TYPE_GFX);
 
-	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pasid, pd_addr);
+	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
 
 	/* wait for the invalidate to complete */
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));

drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c

@@ -3219,12 +3219,11 @@ static void gfx_v7_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
  * using the CP (CIK).
  */
 static void gfx_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					unsigned vmid, unsigned pasid,
+					unsigned vmid, uint64_t pd_addr)
-					uint64_t pd_addr)
 {
 	int usepfp = (ring->funcs->type == AMDGPU_RING_TYPE_GFX);
 
-	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pasid, pd_addr);
+	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
 
 	/* wait for the invalidate to complete */
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c

@@ -6311,12 +6311,11 @@ static void gfx_v8_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
 }
 
 static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					unsigned vmid, unsigned pasid,
+					unsigned vmid, uint64_t pd_addr)
-					uint64_t pd_addr)
 {
 	int usepfp = (ring->funcs->type == AMDGPU_RING_TYPE_GFX);
 
-	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pasid, pd_addr);
+	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
 
 	/* wait for the invalidate to complete */
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

@@ -3676,10 +3676,9 @@ static void gfx_v9_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
 }
 
 static void gfx_v9_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					unsigned vmid, unsigned pasid,
+					unsigned vmid, uint64_t pd_addr)
-					uint64_t pd_addr)
 {
-	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pasid, pd_addr);
+	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
 
 	/* compute doesn't have PFP */
 	if (ring->funcs->type == AMDGPU_RING_TYPE_GFX) {

drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c

@@ -363,8 +363,7 @@ static void gmc_v6_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid)
 }
 
 static uint64_t gmc_v6_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
-					    unsigned vmid, unsigned pasid,
+					    unsigned vmid, uint64_t pd_addr)
-					    uint64_t pd_addr)
 {
 	uint32_t reg;
 

drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c

@@ -436,8 +436,7 @@ static void gmc_v7_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid)
 }
 
 static uint64_t gmc_v7_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
-					    unsigned vmid, unsigned pasid,
+					    unsigned vmid, uint64_t pd_addr)
-					    uint64_t pd_addr)
 {
 	uint32_t reg;
 
@@ -447,14 +446,18 @@ static uint64_t gmc_v7_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
 		reg = mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + vmid - 8;
 	amdgpu_ring_emit_wreg(ring, reg, pd_addr >> 12);
 
-	amdgpu_ring_emit_wreg(ring, mmIH_VMID_0_LUT + vmid, pasid);
-
 	/* bits 0-15 are the VM contexts0-15 */
 	amdgpu_ring_emit_wreg(ring, mmVM_INVALIDATE_REQUEST, 1 << vmid);
 
 	return pd_addr;
 }
 
+static void gmc_v7_0_emit_pasid_mapping(struct amdgpu_ring *ring, unsigned vmid,
+					unsigned pasid)
+{
+	amdgpu_ring_emit_wreg(ring, mmIH_VMID_0_LUT + vmid, pasid);
+}
+
 /**
  * gmc_v7_0_set_pte_pde - update the page tables using MMIO
  *
@@ -1327,6 +1330,7 @@ static const struct amd_ip_funcs gmc_v7_0_ip_funcs = {
 static const struct amdgpu_gmc_funcs gmc_v7_0_gmc_funcs = {
 	.flush_gpu_tlb = gmc_v7_0_flush_gpu_tlb,
 	.emit_flush_gpu_tlb = gmc_v7_0_emit_flush_gpu_tlb,
+	.emit_pasid_mapping = gmc_v7_0_emit_pasid_mapping,
 	.set_pte_pde = gmc_v7_0_set_pte_pde,
 	.set_prt = gmc_v7_0_set_prt,
 	.get_vm_pte_flags = gmc_v7_0_get_vm_pte_flags,

drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c

@@ -612,8 +612,7 @@ static void gmc_v8_0_flush_gpu_tlb(struct amdgpu_device *adev,
 }
 
 static uint64_t gmc_v8_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
-					    unsigned vmid, unsigned pasid,
+					    unsigned vmid, uint64_t pd_addr)
-					    uint64_t pd_addr)
 {
 	uint32_t reg;
 
@@ -623,14 +622,18 @@ static uint64_t gmc_v8_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
 		reg = mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + vmid - 8;
 	amdgpu_ring_emit_wreg(ring, reg, pd_addr >> 12);
 
-	amdgpu_ring_emit_wreg(ring, mmIH_VMID_0_LUT + vmid, pasid);
-
 	/* bits 0-15 are the VM contexts0-15 */
 	amdgpu_ring_emit_wreg(ring, mmVM_INVALIDATE_REQUEST, 1 << vmid);
 
 	return pd_addr;
 }
 
+static void gmc_v8_0_emit_pasid_mapping(struct amdgpu_ring *ring, unsigned vmid,
+					unsigned pasid)
+{
+	amdgpu_ring_emit_wreg(ring, mmIH_VMID_0_LUT + vmid, pasid);
+}
+
 /**
  * gmc_v8_0_set_pte_pde - update the page tables using MMIO
  *
@@ -1662,6 +1665,7 @@ static const struct amd_ip_funcs gmc_v8_0_ip_funcs = {
 static const struct amdgpu_gmc_funcs gmc_v8_0_gmc_funcs = {
 	.flush_gpu_tlb = gmc_v8_0_flush_gpu_tlb,
 	.emit_flush_gpu_tlb = gmc_v8_0_emit_flush_gpu_tlb,
+	.emit_pasid_mapping = gmc_v8_0_emit_pasid_mapping,
 	.set_pte_pde = gmc_v8_0_set_pte_pde,
 	.set_prt = gmc_v8_0_set_prt,
 	.get_vm_pte_flags = gmc_v8_0_get_vm_pte_flags,

drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c

@@ -368,17 +368,15 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev,
 }
 
 static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
-					    unsigned vmid, unsigned pasid,
+					    unsigned vmid, uint64_t pd_addr)
-					    uint64_t pd_addr)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_vmhub *hub = &adev->vmhub[ring->funcs->vmhub];
 	uint32_t req = gmc_v9_0_get_invalidate_req(vmid);
 	uint64_t flags = AMDGPU_PTE_VALID;
 	unsigned eng = ring->vm_inv_eng;
-	uint32_t reg;
 
-	amdgpu_gmc_get_vm_pde(ring->adev, -1, &pd_addr, &flags);
+	amdgpu_gmc_get_vm_pde(adev, -1, &pd_addr, &flags);
 	pd_addr |= flags;
 
 	amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_lo32 + (2 * vmid),
@@ -387,13 +385,6 @@ static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
 	amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_hi32 + (2 * vmid),
 			      upper_32_bits(pd_addr));
 
-	if (ring->funcs->vmhub == AMDGPU_GFXHUB)
-		reg = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_VMID_0_LUT) + vmid;
-	else
-		reg = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_VMID_0_LUT_MM) + vmid;
-
-	amdgpu_ring_emit_wreg(ring, reg, pasid);
-
 	amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_req + eng, req);
 
 	/* wait for the invalidate to complete */
@@ -403,6 +394,20 @@ static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
 	return pd_addr;
 }
 
+static void gmc_v9_0_emit_pasid_mapping(struct amdgpu_ring *ring, unsigned vmid,
+					unsigned pasid)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t reg;
+
+	if (ring->funcs->vmhub == AMDGPU_GFXHUB)
+		reg = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_VMID_0_LUT) + vmid;
+	else
+		reg = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_VMID_0_LUT_MM) + vmid;
+
+	amdgpu_ring_emit_wreg(ring, reg, pasid);
+}
+
 /**
  * gmc_v9_0_set_pte_pde - update the page tables using MMIO
  *
@@ -529,6 +534,7 @@ static void gmc_v9_0_get_vm_pde(struct amdgpu_device *adev, int level,
 static const struct amdgpu_gmc_funcs gmc_v9_0_gmc_funcs = {
 	.flush_gpu_tlb = gmc_v9_0_flush_gpu_tlb,
 	.emit_flush_gpu_tlb = gmc_v9_0_emit_flush_gpu_tlb,
+	.emit_pasid_mapping = gmc_v9_0_emit_pasid_mapping,
 	.set_pte_pde = gmc_v9_0_set_pte_pde,
 	.get_vm_pte_flags = gmc_v9_0_get_vm_pte_flags,
 	.get_vm_pde = gmc_v9_0_get_vm_pde

drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c

@@ -852,10 +852,9 @@ static void sdma_v2_4_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
  * using sDMA (VI).
  */
 static void sdma_v2_4_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					 unsigned vmid, unsigned pasid,
+					 unsigned vmid, uint64_t pd_addr)
-					 uint64_t pd_addr)
 {
-	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pasid, pd_addr);
+	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
 
 	/* wait for flush */
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) |

drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c

@@ -1117,10 +1117,9 @@ static void sdma_v3_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
  * using sDMA (VI).
  */
 static void sdma_v3_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					 unsigned vmid, unsigned pasid,
+					 unsigned vmid, uint64_t pd_addr)
-					 uint64_t pd_addr)
 {
-	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pasid, pd_addr);
+	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
 
 	/* wait for flush */
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) |

drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c

@@ -1123,10 +1123,9 @@ static void sdma_v4_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
  * using sDMA (VEGA10).
  */
 static void sdma_v4_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					 unsigned vmid, unsigned pasid,
+					 unsigned vmid, uint64_t pd_addr)
-					 uint64_t pd_addr)
 {
-	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pasid, pd_addr);
+	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
 }
 
 static void sdma_v4_0_ring_emit_wreg(struct amdgpu_ring *ring,

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

@@ -460,10 +460,9 @@ static void si_dma_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
  * using sDMA (VI).
  */
 static void si_dma_ring_emit_vm_flush(struct amdgpu_ring *ring,
-				      unsigned vmid, unsigned pasid,
+				      unsigned vmid, uint64_t pd_addr)
-				      uint64_t pd_addr)
 {
-	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pasid, pd_addr);
+	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
 
 	/* wait for invalidate to complete */
 	amdgpu_ring_write(ring, DMA_PACKET(DMA_PACKET_POLL_REG_MEM, 0, 0, 0, 0));

drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c

@@ -1058,10 +1058,9 @@ static void uvd_v6_0_ring_emit_wreg(struct amdgpu_ring *ring,
 }
 
 static void uvd_v6_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					unsigned vmid, unsigned pasid,
+					unsigned vmid, uint64_t pd_addr)
-					uint64_t pd_addr)
 {
-	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pasid, pd_addr);
+	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
 
 	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0, 0));
 	amdgpu_ring_write(ring, mmVM_INVALIDATE_REQUEST << 2);
@@ -1107,8 +1106,7 @@ static void uvd_v6_0_enc_ring_insert_end(struct amdgpu_ring *ring)
 }
 
 static void uvd_v6_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					    unsigned int vmid, unsigned pasid,
+					    unsigned int vmid, uint64_t pd_addr)
-					    uint64_t pd_addr)
 {
 	amdgpu_ring_write(ring, HEVC_ENC_CMD_UPDATE_PTB);
 	amdgpu_ring_write(ring, vmid);

drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c

@@ -1261,13 +1261,12 @@ static void uvd_v7_0_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
 }
 
 static void uvd_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					unsigned vmid, unsigned pasid,
+					unsigned vmid, uint64_t pd_addr)
-					uint64_t pd_addr)
 {
 	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
 	uint32_t data0, data1, mask;
 
-	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pasid, pd_addr);
+	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
 
 	/* wait for reg writes */
 	data0 = hub->ctx0_ptb_addr_lo32 + vmid * 2;
@@ -1302,12 +1301,11 @@ static void uvd_v7_0_enc_ring_emit_reg_wait(struct amdgpu_ring *ring,
 }
 
 static void uvd_v7_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					    unsigned int vmid, unsigned pasid,
+					    unsigned int vmid, uint64_t pd_addr)
-					    uint64_t pd_addr)
 {
 	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
 
-	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pasid, pd_addr);
+	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
 
 	/* wait for reg writes */
 	uvd_v7_0_enc_ring_emit_reg_wait(ring, hub->ctx0_ptb_addr_lo32 + vmid * 2,

drivers/gpu/drm/amd/amdgpu/vce_v3_0.c

@@ -844,8 +844,7 @@ static void vce_v3_0_ring_emit_ib(struct amdgpu_ring *ring,
 }
 
 static void vce_v3_0_emit_vm_flush(struct amdgpu_ring *ring,
-				   unsigned int vmid, unsigned pasid,
+				   unsigned int vmid, uint64_t pd_addr)
-				   uint64_t pd_addr)
 {
 	amdgpu_ring_write(ring, VCE_CMD_UPDATE_PTB);
 	amdgpu_ring_write(ring, vmid);

drivers/gpu/drm/amd/amdgpu/vce_v4_0.c

@@ -975,12 +975,11 @@ static void vce_v4_0_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
 }
 
 static void vce_v4_0_emit_vm_flush(struct amdgpu_ring *ring,
-				   unsigned int vmid, unsigned pasid,
+				   unsigned int vmid, uint64_t pd_addr)
-				   uint64_t pd_addr)
 {
 	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
 
-	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pasid, pd_addr);
+	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
 
 	/* wait for reg writes */
 	vce_v4_0_emit_reg_wait(ring, hub->ctx0_ptb_addr_lo32 + vmid * 2,

drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c

@@ -859,13 +859,12 @@ static void vcn_v1_0_dec_ring_emit_reg_wait(struct amdgpu_ring *ring,
 }
 
 static void vcn_v1_0_dec_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					    unsigned vmid, unsigned pasid,
+					    unsigned vmid, uint64_t pd_addr)
-					    uint64_t pd_addr)
 {
 	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
 	uint32_t data0, data1, mask;
 
-	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pasid, pd_addr);
+	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
 
 	/* wait for register write */
 	data0 = hub->ctx0_ptb_addr_lo32 + vmid * 2;
@@ -997,12 +996,11 @@ static void vcn_v1_0_enc_ring_emit_reg_wait(struct amdgpu_ring *ring,
 }
 
 static void vcn_v1_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
-					    unsigned int vmid, unsigned pasid,
+					    unsigned int vmid, uint64_t pd_addr)
-					    uint64_t pd_addr)
 {
 	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
 
-	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pasid, pd_addr);
+	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
 
 	/* wait for reg writes */
 	vcn_v1_0_enc_ring_emit_reg_wait(ring, hub->ctx0_ptb_addr_lo32 + vmid * 2,