1 files changed, 217 insertions, 97 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 1785fdad6ecb..d78059fd2c72 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -35,6 +35,8 @@
 
 #include "gc/gc_10_1_0_offset.h"
 #include "gc/gc_10_1_0_sh_mask.h"
+#include "smuio/smuio_11_0_0_offset.h"
+#include "smuio/smuio_11_0_0_sh_mask.h"
 #include "navi10_enum.h"
 #include "hdp/hdp_5_0_0_offset.h"
 #include "ivsrcid/gfx/irqsrcs_gfx_10_1.h"
@@ -52,7 +54,7 @@
  * 1. Primary ring
  * 2. Async ring
  */
-#define GFX10_NUM_GFX_RINGS	2
+#define GFX10_NUM_GFX_RINGS_NV1X	1
 #define GFX10_MEC_HPD_SIZE	2048
 
 #define F32_CE_PROGRAM_RAM_SIZE		65536
@@ -222,6 +224,49 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_2[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffffffff, 0x00800000)
 };
 
+static void gfx_v10_rlcg_wreg(struct amdgpu_device *adev, u32 offset, u32 v)
+{
+	static void *scratch_reg0;
+	static void *scratch_reg1;
+	static void *scratch_reg2;
+	static void *scratch_reg3;
+	static void *spare_int;
+	static uint32_t grbm_cntl;
+	static uint32_t grbm_idx;
+	uint32_t i = 0;
+	uint32_t retries = 50000;
+
+	scratch_reg0 = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG0_BASE_IDX] + mmSCRATCH_REG0)*4;
+	scratch_reg1 = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG1_BASE_IDX] + mmSCRATCH_REG1)*4;
+	scratch_reg2 = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG1_BASE_IDX] + mmSCRATCH_REG2)*4;
+	scratch_reg3 = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG1_BASE_IDX] + mmSCRATCH_REG3)*4;
+	spare_int = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmRLC_SPARE_INT_BASE_IDX] + mmRLC_SPARE_INT)*4;
+
+	grbm_cntl = adev->reg_offset[GC_HWIP][0][mmGRBM_GFX_CNTL_BASE_IDX] + mmGRBM_GFX_CNTL;
+	grbm_idx = adev->reg_offset[GC_HWIP][0][mmGRBM_GFX_INDEX_BASE_IDX] + mmGRBM_GFX_INDEX;
+
+	if (amdgpu_sriov_runtime(adev)) {
+		pr_err("shouldn't call rlcg write register during runtime\n");
+		return;
+	}
+
+	writel(v, scratch_reg0);
+	writel(offset | 0x80000000, scratch_reg1);
+	writel(1, spare_int);
+	for (i = 0; i < retries; i++) {
+		u32 tmp;
+
+		tmp = readl(scratch_reg1);
+		if (!(tmp & 0x80000000))
+			break;
+
+		udelay(10);
+	}
+
+	if (i >= retries)
+		pr_err("timeout: rlcg program reg:0x%05x failed !\n", offset);
+}
+
 static const struct soc15_reg_golden golden_settings_gc_10_1_nv14[] =
 {
 	/* Pending on emulation bring up */
@@ -234,7 +279,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_2_nv12[] =
 
 #define DEFAULT_SH_MEM_CONFIG \
 	((SH_MEM_ADDRESS_MODE_64 << SH_MEM_CONFIG__ADDRESS_MODE__SHIFT) | \
-	 (SH_MEM_ALIGNMENT_MODE_UNALIGNED << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | \
+	 (SH_MEM_ALIGNMENT_MODE_DWORD << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | \
 	 (SH_MEM_RETRY_MODE_ALL << SH_MEM_CONFIG__RETRY_MODE__SHIFT) | \
 	 (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT))
 
@@ -500,29 +545,28 @@ static int gfx_v10_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_ib ib;
 	struct dma_fence *f = NULL;
-	uint32_t scratch;
-	uint32_t tmp = 0;
+	unsigned index;
+	uint64_t gpu_addr;
+	uint32_t tmp;
 	long r;
 
-	r = amdgpu_gfx_scratch_get(adev, &scratch);
-	if (r) {
-		DRM_ERROR("amdgpu: failed to get scratch reg (%ld).\n", r);
+	r = amdgpu_device_wb_get(adev, &index);
+	if (r)
 		return r;
-	}
-
-	WREG32(scratch, 0xCAFEDEAD);
 
+	gpu_addr = adev->wb.gpu_addr + (index * 4);
+	adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD);
 	memset(&ib, 0, sizeof(ib));
-	r = amdgpu_ib_get(adev, NULL, 256, &ib);
-	if (r) {
-		DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r);
+	r = amdgpu_ib_get(adev, NULL, 16, &ib);
+	if (r)
 		goto err1;
-	}
 
-	ib.ptr[0] = PACKET3(PACKET3_SET_UCONFIG_REG, 1);
-	ib.ptr[1] = ((scratch - PACKET3_SET_UCONFIG_REG_START));
-	ib.ptr[2] = 0xDEADBEEF;
-	ib.length_dw = 3;
+	ib.ptr[0] = PACKET3(PACKET3_WRITE_DATA, 3);
+	ib.ptr[1] = WRITE_DATA_DST_SEL(5) | WR_CONFIRM;
+	ib.ptr[2] = lower_32_bits(gpu_addr);
+	ib.ptr[3] = upper_32_bits(gpu_addr);
+	ib.ptr[4] = 0xDEADBEEF;
+	ib.length_dw = 5;
 
 	r = amdgpu_ib_schedule(ring, 1, &ib, NULL, &f);
 	if (r)
@@ -530,15 +574,13 @@ static int gfx_v10_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 
 	r = dma_fence_wait_timeout(f, false, timeout);
 	if (r == 0) {
-		DRM_ERROR("amdgpu: IB test timed out.\n");
 		r = -ETIMEDOUT;
 		goto err2;
 	} else if (r < 0) {
-		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
 		goto err2;
 	}
 
-	tmp = RREG32(scratch);
+	tmp = adev->wb.wb[index];
 	if (tmp == 0xDEADBEEF)
 		r = 0;
 	else
@@ -547,8 +589,7 @@ err2:
 	amdgpu_ib_free(adev, &ib, NULL);
 	dma_fence_put(f);
 err1:
-	amdgpu_gfx_scratch_free(adev, scratch);
-
+	amdgpu_device_wb_free(adev, index);
 	return r;
 }
 
@@ -1016,6 +1057,10 @@ static int gfx_v10_0_rlc_init(struct amdgpu_device *adev)
 			return r;
 	}
 
+	/* init spm vmid with 0xf */
+	if (adev->gfx.rlc.funcs->update_spm_vmid)
+		adev->gfx.rlc.funcs->update_spm_vmid(adev, 0xf);
+
 	return 0;
 }
 
@@ -1068,7 +1113,7 @@ static int gfx_v10_0_mec_init(struct amdgpu_device *adev)
 		return r;
 	}
 
-	memset(hpd, 0, adev->gfx.mec.hpd_eop_obj->tbo.mem.size);
+	memset(hpd, 0, mec_hpd_size);
 
 	amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
 	amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
@@ -1304,7 +1349,7 @@ static int gfx_v10_0_sw_init(void *handle)
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
 		adev->gfx.me.num_me = 1;
-		adev->gfx.me.num_pipe_per_me = 2;
+		adev->gfx.me.num_pipe_per_me = 1;
 		adev->gfx.me.num_queue_per_pipe = 1;
 		adev->gfx.mec.num_mec = 2;
 		adev->gfx.mec.num_pipe_per_mec = 4;
@@ -1783,11 +1828,11 @@ static int gfx_v10_0_init_csb(struct amdgpu_device *adev)
 	adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr);
 
 	/* csib */
-	WREG32_SOC15(GC, 0, mmRLC_CSIB_ADDR_HI,
+	WREG32_SOC15_RLC(GC, 0, mmRLC_CSIB_ADDR_HI,
 		     adev->gfx.rlc.clear_state_gpu_addr >> 32);
-	WREG32_SOC15(GC, 0, mmRLC_CSIB_ADDR_LO,
+	WREG32_SOC15_RLC(GC, 0, mmRLC_CSIB_ADDR_LO,
 		     adev->gfx.rlc.clear_state_gpu_addr & 0xfffffffc);
-	WREG32_SOC15(GC, 0, mmRLC_CSIB_LENGTH, adev->gfx.rlc.clear_state_size);
+	WREG32_SOC15_RLC(GC, 0, mmRLC_CSIB_LENGTH, adev->gfx.rlc.clear_state_size);
 
 	return 0;
 }
@@ -1895,6 +1940,11 @@ static int gfx_v10_0_rlc_resume(struct amdgpu_device *adev)
 		if (!amdgpu_sriov_vf(adev)) /* enable RLC SRM */
 			gfx_v10_0_rlc_enable_srm(adev);
 	} else {
+		if (amdgpu_sriov_vf(adev)) {
+			gfx_v10_0_init_csb(adev);
+			return 0;
+		}
+
 		adev->gfx.rlc.funcs->stop(adev);
 
 		/* disable CG */
@@ -2395,7 +2445,7 @@ static int gfx_v10_0_cp_gfx_enable(struct amdgpu_device *adev, bool enable)
 		for (i = 0; i < adev->gfx.num_gfx_rings; i++)
 			adev->gfx.gfx_ring[i].sched.ready = false;
 	}
-	WREG32_SOC15(GC, 0, mmCP_ME_CNTL, tmp);
+	WREG32_SOC15_RLC(GC, 0, mmCP_ME_CNTL, tmp);
 
 	for (i = 0; i < adev->usec_timeout; i++) {
 		if (RREG32_SOC15(GC, 0, mmCP_STAT) == 0)
@@ -2710,18 +2760,20 @@ static int gfx_v10_0_cp_gfx_start(struct amdgpu_device *adev)
 	amdgpu_ring_commit(ring);
 
 	/* submit cs packet to copy state 0 to next available state */
-	ring = &adev->gfx.gfx_ring[1];
-	r = amdgpu_ring_alloc(ring, 2);
-	if (r) {
-		DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r);
-		return r;
-	}
-
-	amdgpu_ring_write(ring, PACKET3(PACKET3_CLEAR_STATE, 0));
-	amdgpu_ring_write(ring, 0);
+	if (adev->gfx.num_gfx_rings > 1) {
+		/* maximum supported gfx ring is 2 */
+		ring = &adev->gfx.gfx_ring[1];
+		r = amdgpu_ring_alloc(ring, 2);
+		if (r) {
+			DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r);
+			return r;
+		}
 
-	amdgpu_ring_commit(ring);
+		amdgpu_ring_write(ring, PACKET3(PACKET3_CLEAR_STATE, 0));
+		amdgpu_ring_write(ring, 0);
 
+		amdgpu_ring_commit(ring);
+	}
 	return 0;
 }
 
@@ -2818,39 +2870,41 @@ static int gfx_v10_0_cp_gfx_resume(struct amdgpu_device *adev)
 	mutex_unlock(&adev->srbm_mutex);
 
 	/* Init gfx ring 1 for pipe 1 */
-	mutex_lock(&adev->srbm_mutex);
-	gfx_v10_0_cp_gfx_switch_pipe(adev, PIPE_ID1);
-	ring = &adev->gfx.gfx_ring[1];
-	rb_bufsz = order_base_2(ring->ring_size / 8);
-	tmp = REG_SET_FIELD(0, CP_RB1_CNTL, RB_BUFSZ, rb_bufsz);
-	tmp = REG_SET_FIELD(tmp, CP_RB1_CNTL, RB_BLKSZ, rb_bufsz - 2);
-	WREG32_SOC15(GC, 0, mmCP_RB1_CNTL, tmp);
-	/* Initialize the ring buffer's write pointers */
-	ring->wptr = 0;
-	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);
-	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);
-	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));
-
-	mdelay(1);
-	WREG32_SOC15(GC, 0, mmCP_RB1_CNTL, tmp);
-
-	rb_addr = ring->gpu_addr >> 8;
-	WREG32_SOC15(GC, 0, mmCP_RB1_BASE, rb_addr);
-	WREG32_SOC15(GC, 0, mmCP_RB1_BASE_HI, upper_32_bits(rb_addr));
-	WREG32_SOC15(GC, 0, mmCP_RB1_ACTIVE, 1);
-
-	gfx_v10_0_cp_gfx_set_doorbell(adev, ring);
-	mutex_unlock(&adev->srbm_mutex);
-
+	if (adev->gfx.num_gfx_rings > 1) {
+		mutex_lock(&adev->srbm_mutex);
+		gfx_v10_0_cp_gfx_switch_pipe(adev, PIPE_ID1);
+		/* maximum supported gfx ring is 2 */
+		ring = &adev->gfx.gfx_ring[1];
+		rb_bufsz = order_base_2(ring->ring_size / 8);
+		tmp = REG_SET_FIELD(0, CP_RB1_CNTL, RB_BUFSZ, rb_bufsz);
+		tmp = REG_SET_FIELD(tmp, CP_RB1_CNTL, RB_BLKSZ, rb_bufsz - 2);
+		WREG32_SOC15(GC, 0, mmCP_RB1_CNTL, tmp);
+		/* Initialize the ring buffer's write pointers */
+		ring->wptr = 0;
+		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);
+		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);
+		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));
+
+		mdelay(1);
+		WREG32_SOC15(GC, 0, mmCP_RB1_CNTL, tmp);
+
+		rb_addr = ring->gpu_addr >> 8;
+		WREG32_SOC15(GC, 0, mmCP_RB1_BASE, rb_addr);
+		WREG32_SOC15(GC, 0, mmCP_RB1_BASE_HI, upper_32_bits(rb_addr));
+		WREG32_SOC15(GC, 0, mmCP_RB1_ACTIVE, 1);
+
+		gfx_v10_0_cp_gfx_set_doorbell(adev, ring);
+		mutex_unlock(&adev->srbm_mutex);
+	}
 	/* Switch to pipe 0 */
 	mutex_lock(&adev->srbm_mutex);
 	gfx_v10_0_cp_gfx_switch_pipe(adev, PIPE_ID0);
@@ -3164,12 +3218,7 @@ static int gfx_v10_0_kiq_enable_kgq(struct amdgpu_device *adev)
 	for (i = 0; i < adev->gfx.num_gfx_rings; i++)
 		kiq->pmf->kiq_map_queues(kiq_ring, &adev->gfx.gfx_ring[i]);
 
-	r = amdgpu_ring_test_ring(kiq_ring);
-	if (r) {
-		DRM_ERROR("kfq enable failed\n");
-		kiq_ring->sched.ready = false;
-	}
-	return r;
+	return amdgpu_ring_test_helper(kiq_ring);
 }
 #endif
 
@@ -3212,6 +3261,22 @@ done:
 	return r;
 }
 
+static void gfx_v10_0_compute_mqd_set_priority(struct amdgpu_ring *ring, struct v10_compute_mqd *mqd)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	if (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE) {
+		if (amdgpu_gfx_is_high_priority_compute_queue(adev, ring->queue)) {
+			mqd->cp_hqd_pipe_priority = AMDGPU_GFX_PIPE_PRIO_HIGH;
+			ring->has_high_prio = true;
+			mqd->cp_hqd_queue_priority =
+				AMDGPU_GFX_QUEUE_PRIORITY_MAXIMUM;
+		} else {
+			ring->has_high_prio = false;
+		}
+	}
+}
+
 static int gfx_v10_0_compute_mqd_init(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
@@ -3337,6 +3402,9 @@ static int gfx_v10_0_compute_mqd_init(struct amdgpu_ring *ring)
 	tmp = REG_SET_FIELD(tmp, CP_HQD_IB_CONTROL, MIN_IB_AVAIL_SIZE, 3);
 	mqd->cp_hqd_ib_control = tmp;
 
+	/* set static priority for a compute queue/ring */
+	gfx_v10_0_compute_mqd_set_priority(ring, mqd);
+
 	/* map_queues packet doesn't need activate the queue,
 	 * so only kiq need set this field.
 	 */
@@ -3513,6 +3581,7 @@ 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);
 		amdgpu_ring_clear_ring(ring);
 	} else {
 		amdgpu_ring_clear_ring(ring);
@@ -3785,7 +3854,7 @@ static int gfx_v10_0_kiq_disable_kgq(struct amdgpu_device *adev)
 		kiq->pmf->kiq_unmap_queues(kiq_ring, &adev->gfx.gfx_ring[i],
 					   PREEMPT_QUEUES, 0, 0);
 
-	return amdgpu_ring_test_ring(kiq_ring);
+	return amdgpu_ring_test_helper(kiq_ring);
 }
 #endif
 
@@ -3923,11 +3992,12 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev)
 {
 	uint64_t clock;
 
+	amdgpu_gfx_off_ctrl(adev, false);
 	mutex_lock(&adev->gfx.gpu_clock_mutex);
-	WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1);
-	clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) |
-		((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
+	clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER) |
+		((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER) << 32ULL);
 	mutex_unlock(&adev->gfx.gpu_clock_mutex);
+	amdgpu_gfx_off_ctrl(adev, true);
 	return clock;
 }
 
@@ -3964,7 +4034,8 @@ static int gfx_v10_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	adev->gfx.num_gfx_rings = GFX10_NUM_GFX_RINGS;
+	adev->gfx.num_gfx_rings = GFX10_NUM_GFX_RINGS_NV1X;
+
 	adev->gfx.num_compute_rings = AMDGPU_MAX_COMPUTE_RINGS;
 
 	gfx_v10_0_set_kiq_pm4_funcs(adev);
@@ -4033,6 +4104,12 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade
 
 	/* It is disabled by HW by default */
 	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) {
+		/* 0 - Disable some blocks' MGCG */
+		WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, 0xe0000000);
+		WREG32_SOC15(GC, 0, mmCGTT_WD_CLK_CTRL, 0xff000000);
+		WREG32_SOC15(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xff000000);
+		WREG32_SOC15(GC, 0, mmCGTT_IA_CLK_CTRL, 0xff000000);
+
 		/* 1 - RLC_CGTT_MGCG_OVERRIDE */
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
 		data &= ~(RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK |
@@ -4072,19 +4149,20 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
 
-		/* 2 - disable MGLS in RLC */
+		/* 2 - disable MGLS in CP */
+		data = RREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL);
+		if (data & CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK) {
+			data &= ~CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK;
+			WREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL, data);
+		}
+
+		/* 3 - disable MGLS in RLC */
 		data = RREG32_SOC15(GC, 0, mmRLC_MEM_SLP_CNTL);
 		if (data & RLC_MEM_SLP_CNTL__RLC_MEM_LS_EN_MASK) {
 			data &= ~RLC_MEM_SLP_CNTL__RLC_MEM_LS_EN_MASK;
 			WREG32_SOC15(GC, 0, mmRLC_MEM_SLP_CNTL, data);
 		}
 
-		/* 3 - disable MGLS in CP */
-		data = RREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL);
-		if (data & CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK) {
-			data &= ~CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK;
-			WREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL, data);
-		}
 	}
 }
 
@@ -4195,7 +4273,7 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 		/* ===  CGCG /CGLS for GFX 3D Only === */
 		gfx_v10_0_update_3d_clock_gating(adev, enable);
 		/* ===  MGCG + MGLS === */
-		gfx_v10_0_update_medium_grain_clock_gating(adev, enable);
+		/* gfx_v10_0_update_medium_grain_clock_gating(adev, enable); */
 	}
 
 	if (adev->cg_flags &
@@ -4212,6 +4290,45 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 	return 0;
 }
 
+static void gfx_v10_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
+{
+	u32 data;
+
+	data = RREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL);
+
+	data &= ~RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK;
+	data |= (vmid & RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK) << RLC_SPM_MC_CNTL__RLC_SPM_VMID__SHIFT;
+
+	WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data);
+}
+
+static bool gfx_v10_0_check_rlcg_range(struct amdgpu_device *adev,
+					uint32_t offset,
+					struct soc15_reg_rlcg *entries, int arr_size)
+{
+	int i;
+	uint32_t reg;
+
+	if (!entries)
+		return false;
+
+	for (i = 0; i < arr_size; i++) {
+		const struct soc15_reg_rlcg *entry;
+
+		entry = &entries[i];
+		reg = adev->reg_offset[entry->hwip][entry->instance][entry->segment] + entry->reg;
+		if (offset == reg)
+			return true;
+	}
+
+	return false;
+}
+
+static bool gfx_v10_0_is_rlcg_access_range(struct amdgpu_device *adev, u32 offset)
+{
+	return gfx_v10_0_check_rlcg_range(adev, offset, NULL, 0);
+}
+
 static const struct amdgpu_rlc_funcs gfx_v10_0_rlc_funcs = {
 	.is_rlc_enabled = gfx_v10_0_is_rlc_enabled,
 	.set_safe_mode = gfx_v10_0_set_safe_mode,
@@ -4222,7 +4339,10 @@ static const struct amdgpu_rlc_funcs gfx_v10_0_rlc_funcs = {
 	.resume = gfx_v10_0_rlc_resume,
 	.stop = gfx_v10_0_rlc_stop,
 	.reset = gfx_v10_0_rlc_reset,
-	.start = gfx_v10_0_rlc_start
+	.start = gfx_v10_0_rlc_start,
+	.update_spm_vmid = gfx_v10_0_update_spm_vmid,
+	.rlcg_wreg = gfx_v10_rlcg_wreg,
+	.is_rlcg_access_range = gfx_v10_0_is_rlcg_access_range,
 };
 
 static int gfx_v10_0_set_powergating_state(void *handle,
@@ -4411,15 +4531,15 @@ static void gfx_v10_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 
 	control |= ib->length_dw | (vmid << 24);
 
-	if (amdgpu_mcbp && (ib->flags & AMDGPU_IB_FLAG_PREEMPT)) {
+	if ((amdgpu_sriov_vf(ring->adev) || amdgpu_mcbp) && (ib->flags & AMDGPU_IB_FLAG_PREEMPT)) {
 		control |= INDIRECT_BUFFER_PRE_ENB(1);
 
 		if (flags & AMDGPU_IB_PREEMPTED)
 			control |= INDIRECT_BUFFER_PRE_RESUME(1);
 
-		if (!(ib->flags & AMDGPU_IB_FLAG_CE))
+		if (!(ib->flags & AMDGPU_IB_FLAG_CE) && vmid)
 			gfx_v10_0_ring_emit_de_meta(ring,
-				    flags & AMDGPU_IB_PREEMPTED ? true : false);
+				    (!amdgpu_sriov_vf(ring->adev) && flags & AMDGPU_IB_PREEMPTED) ? true : false);
 	}
 
 	amdgpu_ring_write(ring, header);
@@ -4566,9 +4686,9 @@ static void gfx_v10_0_ring_emit_cntxcntl(struct amdgpu_ring *ring, uint32_t flag
 {
 	uint32_t dw2 = 0;
 
-	if (amdgpu_mcbp)
+	if (amdgpu_mcbp || amdgpu_sriov_vf(ring->adev))
 		gfx_v10_0_ring_emit_ce_meta(ring,
-				    flags & AMDGPU_IB_PREEMPTED ? true : false);
+				    (!amdgpu_sriov_vf(ring->adev) && flags & AMDGPU_IB_PREEMPTED) ? true : false);
 
 	gfx_v10_0_ring_emit_tmz(ring, true);