Merge tag 'amd-drm-next-5.19-2022-05-18' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.19-2022-05-18:

amdgpu:
- Misc code cleanups
- Additional SMU 13.x enablement
- Smartshift fixes
- GFX11 fixes
- Support for SMU 13.0.4
- SMU mutex fix
- Suspend/resume fix

amdkfd:
- static checker fix
- Doorbell/MMIO resource handling fix

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220518205621.5741-1-alexander.deucher@amd.com

1 files changed, 199 insertions, 81 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index 8298926f8502..06b2635b142a 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -248,7 +248,7 @@ 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);
@@ -268,7 +268,7 @@ 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));
@@ -301,8 +301,8 @@ 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);
@@ -460,14 +460,15 @@ static void sdma_v5_2_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se
 		amdgpu_ring_write(ring, upper_32_bits(seq));
 	}
 
-	if (flags & AMDGPU_FENCE_FLAG_INT) {
+	if ((flags & AMDGPU_FENCE_FLAG_INT)) {
+		uint32_t ctx = ring->is_mes_queue ?
+			(ring->hw_queue_id | AMDGPU_FENCE_MES_QUEUE_FLAG) : 0;
 		/* generate an interrupt */
 		amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_TRAP));
-		amdgpu_ring_write(ring, SDMA_PKT_TRAP_INT_CONTEXT_INT_CONTEXT(0));
+		amdgpu_ring_write(ring, SDMA_PKT_TRAP_INT_CONTEXT_INT_CONTEXT(ctx));
 	}
 }
 
-
 /**
  * sdma_v5_2_gfx_stop - stop the gfx async dma engines
  *
@@ -513,17 +514,21 @@ static void sdma_v5_2_rlc_stop(struct amdgpu_device *adev)
 }
 
 /**
- * sdma_v5_2_ctx_switch_enable - stop the async dma engines context switch
+ * sdma_v5_2_ctx_switch_enable_for_instance - start the async dma engines
+ * context switch for an instance
  *
  * @adev: amdgpu_device pointer
- * @enable: enable/disable the DMA MEs context switch.
+ * @instance_idx: the index of the SDMA instance
  *
- * Halt or unhalt the async dma engines context switch.
+ * Unhalt the async dma engines context switch.
  */
-static void sdma_v5_2_ctx_switch_enable(struct amdgpu_device *adev, bool enable)
+static void sdma_v5_2_ctx_switch_enable_for_instance(struct amdgpu_device *adev, int instance_idx)
 {
 	u32 f32_cntl, phase_quantum = 0;
-	int i;
+
+	if (WARN_ON(instance_idx >= adev->sdma.num_instances)) {
+		return;
+	}
 
 	if (amdgpu_sdma_phase_quantum) {
 		unsigned value = amdgpu_sdma_phase_quantum;
@@ -547,50 +552,68 @@ static void sdma_v5_2_ctx_switch_enable(struct amdgpu_device *adev, bool enable)
 		phase_quantum =
 			value << SDMA0_PHASE0_QUANTUM__VALUE__SHIFT |
 			unit  << SDMA0_PHASE0_QUANTUM__UNIT__SHIFT;
-	}
 
-	for (i = 0; i < adev->sdma.num_instances; i++) {
-		if (enable && amdgpu_sdma_phase_quantum) {
-			WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_PHASE0_QUANTUM),
-			       phase_quantum);
-			WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_PHASE1_QUANTUM),
-			       phase_quantum);
-			WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_PHASE2_QUANTUM),
-			       phase_quantum);
-		}
-
-		if (!amdgpu_sriov_vf(adev)) {
-			f32_cntl = RREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_CNTL));
-			f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_CNTL,
-					AUTO_CTXSW_ENABLE, enable ? 1 : 0);
-			WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_CNTL), f32_cntl);
-		}
+		WREG32_SOC15_IP(GC,
+			sdma_v5_2_get_reg_offset(adev, instance_idx, mmSDMA0_PHASE0_QUANTUM),
+			phase_quantum);
+		WREG32_SOC15_IP(GC,
+			sdma_v5_2_get_reg_offset(adev, instance_idx, mmSDMA0_PHASE1_QUANTUM),
+		    phase_quantum);
+		WREG32_SOC15_IP(GC,
+			sdma_v5_2_get_reg_offset(adev, instance_idx, mmSDMA0_PHASE2_QUANTUM),
+		    phase_quantum);
 	}
 
+	if (!amdgpu_sriov_vf(adev)) {
+		f32_cntl = RREG32(sdma_v5_2_get_reg_offset(adev, instance_idx, mmSDMA0_CNTL));
+		f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_CNTL,
+				AUTO_CTXSW_ENABLE, 1);
+		WREG32(sdma_v5_2_get_reg_offset(adev, instance_idx, mmSDMA0_CNTL), f32_cntl);
+	}
 }
 
 /**
- * sdma_v5_2_enable - stop the async dma engines
+ * sdma_v5_2_ctx_switch_disable_all - stop the async dma engines context switch
  *
  * @adev: amdgpu_device pointer
- * @enable: enable/disable the DMA MEs.
  *
- * Halt or unhalt the async dma engines.
+ * Halt the async dma engines context switch.
  */
-static void sdma_v5_2_enable(struct amdgpu_device *adev, bool enable)
+static void sdma_v5_2_ctx_switch_disable_all(struct amdgpu_device *adev)
 {
 	u32 f32_cntl;
 	int i;
 
-	if (!enable) {
-		sdma_v5_2_gfx_stop(adev);
-		sdma_v5_2_rlc_stop(adev);
+	if (amdgpu_sriov_vf(adev))
+		return;
+
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		f32_cntl = RREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_CNTL));
+		f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_CNTL,
+				AUTO_CTXSW_ENABLE, 0);
+		WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_CNTL), f32_cntl);
 	}
+}
+
+/**
+ * sdma_v5_2_halt - stop the async dma engines
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Halt the async dma engines.
+ */
+static void sdma_v5_2_halt(struct amdgpu_device *adev)
+{
+	int i;
+	u32 f32_cntl;
+
+	sdma_v5_2_gfx_stop(adev);
+	sdma_v5_2_rlc_stop(adev);
 
 	if (!amdgpu_sriov_vf(adev)) {
 		for (i = 0; i < adev->sdma.num_instances; i++) {
 			f32_cntl = RREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_F32_CNTL));
-			f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_F32_CNTL, HALT, enable ? 0 : 1);
+			f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_F32_CNTL, HALT, 1);
 			WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_F32_CNTL), f32_cntl);
 		}
 	}
@@ -602,6 +625,9 @@ static void sdma_v5_2_enable(struct amdgpu_device *adev, bool enable)
  * @adev: amdgpu_device pointer
  *
  * Set up the gfx DMA ring buffers and enable them.
+ * It assumes that the dma engine is stopped for each instance.
+ * The function enables the engine and preemptions sequentially for each instance.
+ *
  * Returns 0 for success, error for failure.
  */
 static int sdma_v5_2_gfx_resume(struct amdgpu_device *adev)
@@ -609,7 +635,6 @@ 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;
@@ -619,7 +644,6 @@ 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);
 
 		if (!amdgpu_sriov_vf(adev))
 			WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_SEM_WAIT_FAIL_TIMER_CNTL), 0);
@@ -642,7 +666,7 @@ static int sdma_v5_2_gfx_resume(struct amdgpu_device *adev)
 		WREG32_SOC15_IP(GC, 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_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_LO),
 		       lower_32_bits(wptr_gpu_addr));
 		WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_HI),
@@ -657,9 +681,9 @@ static int sdma_v5_2_gfx_resume(struct amdgpu_device *adev)
 
 		/* set the wb address whether it's enabled or not */
 		WREG32_SOC15_IP(GC, 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_SOC15_IP(GC, 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);
 
@@ -745,10 +769,7 @@ static int sdma_v5_2_gfx_resume(struct amdgpu_device *adev)
 
 		ring->sched.ready = true;
 
-		if (amdgpu_sriov_vf(adev)) { /* bare-metal sequence doesn't need below to lines */
-			sdma_v5_2_ctx_switch_enable(adev, true);
-			sdma_v5_2_enable(adev, true);
-		}
+		sdma_v5_2_ctx_switch_enable_for_instance(adev, i);
 
 		r = amdgpu_ring_test_ring(ring);
 		if (r) {
@@ -792,7 +813,7 @@ static int sdma_v5_2_load_microcode(struct amdgpu_device *adev)
 	int i, j;
 
 	/* halt the MEs */
-	sdma_v5_2_enable(adev, false);
+	sdma_v5_2_halt(adev);
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		if (!adev->sdma.instance[i].fw)
@@ -864,8 +885,8 @@ static int sdma_v5_2_start(struct amdgpu_device *adev)
 	int r = 0;
 
 	if (amdgpu_sriov_vf(adev)) {
-		sdma_v5_2_ctx_switch_enable(adev, false);
-		sdma_v5_2_enable(adev, false);
+		sdma_v5_2_ctx_switch_disable_all(adev);
+		sdma_v5_2_halt(adev);
 
 		/* set RB registers */
 		r = sdma_v5_2_gfx_resume(adev);
@@ -889,12 +910,10 @@ static int sdma_v5_2_start(struct amdgpu_device *adev)
 		amdgpu_gfx_off_ctrl(adev, false);
 
 	sdma_v5_2_soft_reset(adev);
-	/* unhalt the MEs */
-	sdma_v5_2_enable(adev, true);
-	/* enable sdma ring preemption */
-	sdma_v5_2_ctx_switch_enable(adev, true);
 
-	/* start the gfx rings and rlc compute queues */
+	/* Soft reset supposes to disable the dma engine and preemption.
+	 * Now start the gfx rings and rlc compute queues.
+	 */
 	r = sdma_v5_2_gfx_resume(adev);
 	if (adev->in_s0ix)
 		amdgpu_gfx_off_ctrl(adev, true);
@@ -905,6 +924,49 @@ static int sdma_v5_2_start(struct amdgpu_device *adev)
 	return r;
 }
 
+static int sdma_v5_2_mqd_init(struct amdgpu_device *adev, void *mqd,
+			      struct amdgpu_mqd_prop *prop)
+{
+	struct v10_sdma_mqd *m = mqd;
+	uint64_t wb_gpu_addr;
+
+	m->sdmax_rlcx_rb_cntl =
+		order_base_2(prop->queue_size / 4) << SDMA0_RLC0_RB_CNTL__RB_SIZE__SHIFT |
+		1 << SDMA0_RLC0_RB_CNTL__RPTR_WRITEBACK_ENABLE__SHIFT |
+		6 << SDMA0_RLC0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT |
+		1 << SDMA0_RLC0_RB_CNTL__RB_PRIV__SHIFT;
+
+	m->sdmax_rlcx_rb_base = lower_32_bits(prop->hqd_base_gpu_addr >> 8);
+	m->sdmax_rlcx_rb_base_hi = upper_32_bits(prop->hqd_base_gpu_addr >> 8);
+
+	m->sdmax_rlcx_rb_wptr_poll_cntl = RREG32(sdma_v5_2_get_reg_offset(adev, 0,
+						  mmSDMA0_GFX_RB_WPTR_POLL_CNTL));
+
+	wb_gpu_addr = prop->wptr_gpu_addr;
+	m->sdmax_rlcx_rb_wptr_poll_addr_lo = lower_32_bits(wb_gpu_addr);
+	m->sdmax_rlcx_rb_wptr_poll_addr_hi = upper_32_bits(wb_gpu_addr);
+
+	wb_gpu_addr = prop->rptr_gpu_addr;
+	m->sdmax_rlcx_rb_rptr_addr_lo = lower_32_bits(wb_gpu_addr);
+	m->sdmax_rlcx_rb_rptr_addr_hi = upper_32_bits(wb_gpu_addr);
+
+	m->sdmax_rlcx_ib_cntl = RREG32(sdma_v5_2_get_reg_offset(adev, 0,
+							mmSDMA0_GFX_IB_CNTL));
+
+	m->sdmax_rlcx_doorbell_offset =
+		prop->doorbell_index << SDMA0_RLC0_DOORBELL_OFFSET__OFFSET__SHIFT;
+
+	m->sdmax_rlcx_doorbell = REG_SET_FIELD(0, SDMA0_RLC0_DOORBELL, ENABLE, 1);
+
+	return 0;
+}
+
+static void sdma_v5_2_set_mqd_funcs(struct amdgpu_device *adev)
+{
+	adev->mqds[AMDGPU_HW_IP_DMA].mqd_size = sizeof(struct v10_sdma_mqd);
+	adev->mqds[AMDGPU_HW_IP_DMA].init_mqd = sdma_v5_2_mqd_init;
+}
+
 /**
  * sdma_v5_2_ring_test_ring - simple async dma engine test
  *
@@ -922,18 +984,29 @@ static int sdma_v5_2_ring_test_ring(struct amdgpu_ring *ring)
 	int r;
 	u32 tmp;
 	u64 gpu_addr;
+	volatile uint32_t *cpu_ptr = NULL;
 
-	r = amdgpu_device_wb_get(adev, &index);
-	if (r) {
-		dev_err(adev->dev, "(%d) failed to allocate wb slot\n", r);
-		return r;
-	}
-
-	gpu_addr = adev->wb.gpu_addr + (index * 4);
 	tmp = 0xCAFEDEAD;
-	adev->wb.wb[index] = cpu_to_le32(tmp);
 
-	r = amdgpu_ring_alloc(ring, 5);
+	if (ring->is_mes_queue) {
+		uint32_t offset = 0;
+		offset = amdgpu_mes_ctx_get_offs(ring,
+					 AMDGPU_MES_CTX_PADDING_OFFS);
+		gpu_addr = amdgpu_mes_ctx_get_offs_gpu_addr(ring, offset);
+		cpu_ptr = amdgpu_mes_ctx_get_offs_cpu_addr(ring, offset);
+		*cpu_ptr = tmp;
+	} else {
+		r = amdgpu_device_wb_get(adev, &index);
+		if (r) {
+			dev_err(adev->dev, "(%d) failed to allocate wb slot\n", r);
+			return r;
+		}
+
+		gpu_addr = adev->wb.gpu_addr + (index * 4);
+		adev->wb.wb[index] = cpu_to_le32(tmp);
+	}
+
+	r = amdgpu_ring_alloc(ring, 20);
 	if (r) {
 		DRM_ERROR("amdgpu: dma failed to lock ring %d (%d).\n", ring->idx, r);
 		amdgpu_device_wb_free(adev, index);
@@ -949,7 +1022,10 @@ static int sdma_v5_2_ring_test_ring(struct amdgpu_ring *ring)
 	amdgpu_ring_commit(ring);
 
 	for (i = 0; i < adev->usec_timeout; i++) {
-		tmp = le32_to_cpu(adev->wb.wb[index]);
+		if (ring->is_mes_queue)
+			tmp = le32_to_cpu(*cpu_ptr);
+		else
+			tmp = le32_to_cpu(adev->wb.wb[index]);
 		if (tmp == 0xDEADBEEF)
 			break;
 		if (amdgpu_emu_mode == 1)
@@ -961,7 +1037,8 @@ static int sdma_v5_2_ring_test_ring(struct amdgpu_ring *ring)
 	if (i >= adev->usec_timeout)
 		r = -ETIMEDOUT;
 
-	amdgpu_device_wb_free(adev, index);
+	if (!ring->is_mes_queue)
+		amdgpu_device_wb_free(adev, index);
 
 	return r;
 }
@@ -984,21 +1061,37 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	long r;
 	u32 tmp = 0;
 	u64 gpu_addr;
+	volatile uint32_t *cpu_ptr = NULL;
 
-	r = amdgpu_device_wb_get(adev, &index);
-	if (r) {
-		dev_err(adev->dev, "(%ld) failed to allocate wb slot\n", r);
-		return r;
-	}
-
-	gpu_addr = adev->wb.gpu_addr + (index * 4);
 	tmp = 0xCAFEDEAD;
-	adev->wb.wb[index] = cpu_to_le32(tmp);
 	memset(&ib, 0, sizeof(ib));
-	r = amdgpu_ib_get(adev, NULL, 256, AMDGPU_IB_POOL_DIRECT, &ib);
-	if (r) {
-		DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r);
-		goto err0;
+
+	if (ring->is_mes_queue) {
+		uint32_t offset = 0;
+		offset = amdgpu_mes_ctx_get_offs(ring, AMDGPU_MES_CTX_IB_OFFS);
+		ib.gpu_addr = amdgpu_mes_ctx_get_offs_gpu_addr(ring, offset);
+		ib.ptr = (void *)amdgpu_mes_ctx_get_offs_cpu_addr(ring, offset);
+
+		offset = amdgpu_mes_ctx_get_offs(ring,
+					 AMDGPU_MES_CTX_PADDING_OFFS);
+		gpu_addr = amdgpu_mes_ctx_get_offs_gpu_addr(ring, offset);
+		cpu_ptr = amdgpu_mes_ctx_get_offs_cpu_addr(ring, offset);
+		*cpu_ptr = tmp;
+	} else {
+		r = amdgpu_device_wb_get(adev, &index);
+		if (r) {
+			dev_err(adev->dev, "(%ld) failed to allocate wb slot\n", r);
+			return r;
+		}
+
+		gpu_addr = adev->wb.gpu_addr + (index * 4);
+		adev->wb.wb[index] = cpu_to_le32(tmp);
+
+		r = amdgpu_ib_get(adev, NULL, 256, AMDGPU_IB_POOL_DIRECT, &ib);
+		if (r) {
+			DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r);
+			goto err0;
+		}
 	}
 
 	ib.ptr[0] = SDMA_PKT_HEADER_OP(SDMA_OP_WRITE) |
@@ -1025,7 +1118,12 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
 		goto err1;
 	}
-	tmp = le32_to_cpu(adev->wb.wb[index]);
+
+	if (ring->is_mes_queue)
+		tmp = le32_to_cpu(*cpu_ptr);
+	else
+		tmp = le32_to_cpu(adev->wb.wb[index]);
+
 	if (tmp == 0xDEADBEEF)
 		r = 0;
 	else
@@ -1035,7 +1133,8 @@ err1:
 	amdgpu_ib_free(adev, &ib, NULL);
 	dma_fence_put(f);
 err0:
-	amdgpu_device_wb_free(adev, index);
+	if (!ring->is_mes_queue)
+		amdgpu_device_wb_free(adev, index);
 	return r;
 }
 
@@ -1235,6 +1334,7 @@ static int sdma_v5_2_early_init(void *handle)
 	sdma_v5_2_set_buffer_funcs(adev);
 	sdma_v5_2_set_vm_pte_funcs(adev);
 	sdma_v5_2_set_irq_funcs(adev);
+	sdma_v5_2_set_mqd_funcs(adev);
 
 	return 0;
 }
@@ -1347,8 +1447,8 @@ static int sdma_v5_2_hw_fini(void *handle)
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
-	sdma_v5_2_ctx_switch_enable(adev, false);
-	sdma_v5_2_enable(adev, false);
+	sdma_v5_2_ctx_switch_disable_all(adev);
+	sdma_v5_2_halt(adev);
 
 	return 0;
 }
@@ -1468,7 +1568,25 @@ static int sdma_v5_2_process_trap_irq(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
 {
+	uint32_t mes_queue_id = entry->src_data[0];
+
 	DRM_DEBUG("IH: SDMA trap\n");
+
+	if (adev->enable_mes && (mes_queue_id & AMDGPU_FENCE_MES_QUEUE_FLAG)) {
+		struct amdgpu_mes_queue *queue;
+
+		mes_queue_id &= AMDGPU_FENCE_MES_QUEUE_ID_MASK;
+
+		spin_lock(&adev->mes.queue_id_lock);
+		queue = idr_find(&adev->mes.queue_id_idr, mes_queue_id);
+		if (queue) {
+			DRM_DEBUG("process smda queue id = %d\n", mes_queue_id);
+			amdgpu_fence_process(queue->ring);
+		}
+		spin_unlock(&adev->mes.queue_id_lock);
+		return 0;
+	}
+
 	switch (entry->client_id) {
 	case SOC15_IH_CLIENTID_SDMA0:
 		switch (entry->ring_id) {