Merge tag 'drm-fixes-for-v4.15-rc2' of git://people.freedesktop.org/~airlied/linux

Pull drm fixes and cleanups from Dave Airlie:
 "The main thing are a bunch of fixes for the new amd display code, a
  bunch of smatch fixes.

  core:
   - Atomic helper regression fix.
   - Deferred fbdev fallout regression fix.

  amdgpu:
   - New display code (dc) dpms, suspend/resume and smatch fixes, along
     with some others
   - Some regression fixes for amdkfd/radeon.
   - Fix a ttm regression for swiotlb disabled

  bridge:
   - A bunch of fixes for the tc358767 bridge

  mali-dp + hdlcd:
   - some fixes and internal API catchups.

  imx-drm:
   -regression fix in atomic code.

  omapdrm:
   - platform detection regression fixes"

* tag 'drm-fixes-for-v4.15-rc2' of git://people.freedesktop.org/~airlied/linux: (76 commits)
  drm/imx: always call wait_for_flip_done in commit_tail
  omapdrm: hdmi4_cec: signedness bug in hdmi4_cec_init()
  drm: omapdrm: Fix DPI on platforms using the DSI VDDS
  omapdrm: hdmi4: Correct the SoC revision matching
  drm/omap: displays: panel-dpi: add backlight dependency
  drm/omap: Fix error handling path in 'omap_dmm_probe()'
  drm/i915: Disable THP until we have a GPU read BW W/A
  drm/bridge: tc358767: fix 1-lane behavior
  drm/bridge: tc358767: fix AUXDATAn registers access
  drm/bridge: tc358767: fix timing calculations
  drm/bridge: tc358767: fix DP0_MISC register set
  drm/bridge: tc358767: filter out too high modes
  drm/bridge: tc358767: do no fail on hi-res displays
  drm/bridge: Fix lvds-encoder since the panel_bridge rework.
  drm/bridge: synopsys/dw-hdmi: Enable cec clock
  drm/bridge: adv7511/33: Fix adv7511_cec_init() failure handling
  drm/radeon: remove init of CIK VMIDs 8-16 for amdkfd
  drm/ttm: fix populate_and_map() functions once more
  drm/fb_helper: Disable all crtc's when initial setup fails.
  drm/atomic: make drm_atomic_helper_wait_for_vblanks more agressive
  ...

67 files changed, 814 insertions, 483 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 5afaf6016b4a..0b14b5373783 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -717,7 +717,7 @@ int amdgpu_queue_mgr_fini(struct amdgpu_device *adev,
 			  struct amdgpu_queue_mgr *mgr);
 int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 			 struct amdgpu_queue_mgr *mgr,
-			 int hw_ip, int instance, int ring,
+			 u32 hw_ip, u32 instance, u32 ring,
 			 struct amdgpu_ring **out_ring);
 
 /*
@@ -1572,18 +1572,14 @@ struct amdgpu_device {
 	/* sdma */
 	struct amdgpu_sdma		sdma;
 
-	union {
-		struct {
-			/* uvd */
-			struct amdgpu_uvd		uvd;
+	/* uvd */
+	struct amdgpu_uvd		uvd;
 
-			/* vce */
-			struct amdgpu_vce		vce;
-		};
+	/* vce */
+	struct amdgpu_vce		vce;
 
-		/* vcn */
-		struct amdgpu_vcn		vcn;
-	};
+	/* vcn */
+	struct amdgpu_vcn		vcn;
 
 	/* firmwares */
 	struct amdgpu_firmware		firmware;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index 47d1c132ac40..1e3e9be7d77e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -379,29 +379,50 @@ static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct cik_sdma_rlc_registers *m;
+	unsigned long end_jiffies;
 	uint32_t sdma_base_addr;
+	uint32_t data;
 
 	m = get_sdma_mqd(mqd);
 	sdma_base_addr = get_sdma_base_addr(m);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_VIRTUAL_ADDR,
-			m->sdma_rlc_virtual_addr);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
+		m->sdma_rlc_rb_cntl & (~SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK));
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE,
-			m->sdma_rlc_rb_base);
+	end_jiffies = msecs_to_jiffies(2000) + jiffies;
+	while (true) {
+		data = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
+		if (data & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
+			break;
+		if (time_after(jiffies, end_jiffies))
+			return -ETIME;
+		usleep_range(500, 1000);
+	}
+	if (m->sdma_engine_id) {
+		data = RREG32(mmSDMA1_GFX_CONTEXT_CNTL);
+		data = REG_SET_FIELD(data, SDMA1_GFX_CONTEXT_CNTL,
+				RESUME_CTX, 0);
+		WREG32(mmSDMA1_GFX_CONTEXT_CNTL, data);
+	} else {
+		data = RREG32(mmSDMA0_GFX_CONTEXT_CNTL);
+		data = REG_SET_FIELD(data, SDMA0_GFX_CONTEXT_CNTL,
+				RESUME_CTX, 0);
+		WREG32(mmSDMA0_GFX_CONTEXT_CNTL, data);
+	}
 
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL,
+				m->sdma_rlc_doorbell);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR, 0);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR, 0);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_VIRTUAL_ADDR,
+				m->sdma_rlc_virtual_addr);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE, m->sdma_rlc_rb_base);
 	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE_HI,
 			m->sdma_rlc_rb_base_hi);
-
 	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_LO,
 			m->sdma_rlc_rb_rptr_addr_lo);
-
 	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_HI,
 			m->sdma_rlc_rb_rptr_addr_hi);
-
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL,
-			m->sdma_rlc_doorbell);
-
 	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
 			m->sdma_rlc_rb_cntl);
 
@@ -574,9 +595,9 @@ static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
 	}
 
 	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, 0);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR, 0);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR, 0);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE, 0);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
+		RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL) |
+		SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index a57cec737c18..57abf7abd7a9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -409,6 +409,10 @@ static bool amdgpu_cs_try_evict(struct amdgpu_cs_parser *p,
 		if (candidate->robj == validated)
 			break;
 
+		/* We can't move pinned BOs here */
+		if (bo->pin_count)
+			continue;
+
 		other = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type);
 
 		/* Check if this BO is in one of the domains we need space for */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 2c574374d9b6..3573ecdb06ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1837,9 +1837,6 @@ static int amdgpu_fini(struct amdgpu_device *adev)
 		adev->ip_blocks[i].status.hw = false;
 	}
 
-	if (adev->firmware.load_type == AMDGPU_FW_LOAD_SMU)
-		amdgpu_ucode_fini_bo(adev);
-
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.sw)
 			continue;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index ec96bb1f9eaf..c2f414ffb2cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -536,7 +536,7 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x686c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10},
 	{0x1002, 0x687f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10},
 	/* Raven */
-	{0x1002, 0x15dd, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU|AMD_EXP_HW_SUPPORT},
+	{0x1002, 0x15dd, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU},
 
 	{0, 0, 0}
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
index 033fba2def6f..5f5aa5fddc16 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
@@ -164,6 +164,9 @@ static int amdgpu_pp_hw_fini(void *handle)
 		ret = adev->powerplay.ip_funcs->hw_fini(
 					adev->powerplay.pp_handle);
 
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_SMU)
+		amdgpu_ucode_fini_bo(adev);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 7714f4a6c8b0..447d446b5015 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -442,6 +442,8 @@ static int psp_hw_fini(void *handle)
 	if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP)
 		return 0;
 
+	amdgpu_ucode_fini_bo(adev);
+
 	psp_ring_destroy(psp, PSP_RING_TYPE__KM);
 
 	amdgpu_bo_free_kernel(&psp->tmr_bo, &psp->tmr_mc_addr, &psp->tmr_buf);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
index 190e28cb827e..93d86619e802 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
@@ -63,7 +63,7 @@ static int amdgpu_update_cached_map(struct amdgpu_queue_mapper *mapper,
 
 static int amdgpu_identity_map(struct amdgpu_device *adev,
 			       struct amdgpu_queue_mapper *mapper,
-			       int ring,
+			       u32 ring,
 			       struct amdgpu_ring **out_ring)
 {
 	switch (mapper->hw_ip) {
@@ -121,7 +121,7 @@ static enum amdgpu_ring_type amdgpu_hw_ip_to_ring_type(int hw_ip)
 
 static int amdgpu_lru_map(struct amdgpu_device *adev,
 			  struct amdgpu_queue_mapper *mapper,
-			  int user_ring, bool lru_pipe_order,
+			  u32 user_ring, bool lru_pipe_order,
 			  struct amdgpu_ring **out_ring)
 {
 	int r, i, j;
@@ -208,7 +208,7 @@ int amdgpu_queue_mgr_fini(struct amdgpu_device *adev,
  */
 int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 			 struct amdgpu_queue_mgr *mgr,
-			 int hw_ip, int instance, int ring,
+			 u32 hw_ip, u32 instance, u32 ring,
 			 struct amdgpu_ring **out_ring)
 {
 	int r, ip_num_rings;
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 793b1470284d..a296f7bbe57c 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1023,22 +1023,101 @@ static const struct amdgpu_allowed_register_entry cik_allowed_read_registers[] =
 	{mmPA_SC_RASTER_CONFIG_1, true},
 };
 
-static uint32_t cik_read_indexed_register(struct amdgpu_device *adev,
-					  u32 se_num, u32 sh_num,
-					  u32 reg_offset)
+
+static uint32_t cik_get_register_value(struct amdgpu_device *adev,
+				       bool indexed, u32 se_num,
+				       u32 sh_num, u32 reg_offset)
 {
-	uint32_t val;
+	if (indexed) {
+		uint32_t val;
+		unsigned se_idx = (se_num == 0xffffffff) ? 0 : se_num;
+		unsigned sh_idx = (sh_num == 0xffffffff) ? 0 : sh_num;
+
+		switch (reg_offset) {
+		case mmCC_RB_BACKEND_DISABLE:
+			return adev->gfx.config.rb_config[se_idx][sh_idx].rb_backend_disable;
+		case mmGC_USER_RB_BACKEND_DISABLE:
+			return adev->gfx.config.rb_config[se_idx][sh_idx].user_rb_backend_disable;
+		case mmPA_SC_RASTER_CONFIG:
+			return adev->gfx.config.rb_config[se_idx][sh_idx].raster_config;
+		case mmPA_SC_RASTER_CONFIG_1:
+			return adev->gfx.config.rb_config[se_idx][sh_idx].raster_config_1;
+		}
 
-	mutex_lock(&adev->grbm_idx_mutex);
-	if (se_num != 0xffffffff || sh_num != 0xffffffff)
-		amdgpu_gfx_select_se_sh(adev, se_num, sh_num, 0xffffffff);
+		mutex_lock(&adev->grbm_idx_mutex);
+		if (se_num != 0xffffffff || sh_num != 0xffffffff)
+			amdgpu_gfx_select_se_sh(adev, se_num, sh_num, 0xffffffff);
 
-	val = RREG32(reg_offset);
+		val = RREG32(reg_offset);
 
-	if (se_num != 0xffffffff || sh_num != 0xffffffff)
-		amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
-	mutex_unlock(&adev->grbm_idx_mutex);
-	return val;
+		if (se_num != 0xffffffff || sh_num != 0xffffffff)
+			amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+		mutex_unlock(&adev->grbm_idx_mutex);
+		return val;
+	} else {
+		unsigned idx;
+
+		switch (reg_offset) {
+		case mmGB_ADDR_CONFIG:
+			return adev->gfx.config.gb_addr_config;
+		case mmMC_ARB_RAMCFG:
+			return adev->gfx.config.mc_arb_ramcfg;
+		case mmGB_TILE_MODE0:
+		case mmGB_TILE_MODE1:
+		case mmGB_TILE_MODE2:
+		case mmGB_TILE_MODE3:
+		case mmGB_TILE_MODE4:
+		case mmGB_TILE_MODE5:
+		case mmGB_TILE_MODE6:
+		case mmGB_TILE_MODE7:
+		case mmGB_TILE_MODE8:
+		case mmGB_TILE_MODE9:
+		case mmGB_TILE_MODE10:
+		case mmGB_TILE_MODE11:
+		case mmGB_TILE_MODE12:
+		case mmGB_TILE_MODE13:
+		case mmGB_TILE_MODE14:
+		case mmGB_TILE_MODE15:
+		case mmGB_TILE_MODE16:
+		case mmGB_TILE_MODE17:
+		case mmGB_TILE_MODE18:
+		case mmGB_TILE_MODE19:
+		case mmGB_TILE_MODE20:
+		case mmGB_TILE_MODE21:
+		case mmGB_TILE_MODE22:
+		case mmGB_TILE_MODE23:
+		case mmGB_TILE_MODE24:
+		case mmGB_TILE_MODE25:
+		case mmGB_TILE_MODE26:
+		case mmGB_TILE_MODE27:
+		case mmGB_TILE_MODE28:
+		case mmGB_TILE_MODE29:
+		case mmGB_TILE_MODE30:
+		case mmGB_TILE_MODE31:
+			idx = (reg_offset - mmGB_TILE_MODE0);
+			return adev->gfx.config.tile_mode_array[idx];
+		case mmGB_MACROTILE_MODE0:
+		case mmGB_MACROTILE_MODE1:
+		case mmGB_MACROTILE_MODE2:
+		case mmGB_MACROTILE_MODE3:
+		case mmGB_MACROTILE_MODE4:
+		case mmGB_MACROTILE_MODE5:
+		case mmGB_MACROTILE_MODE6:
+		case mmGB_MACROTILE_MODE7:
+		case mmGB_MACROTILE_MODE8:
+		case mmGB_MACROTILE_MODE9:
+		case mmGB_MACROTILE_MODE10:
+		case mmGB_MACROTILE_MODE11:
+		case mmGB_MACROTILE_MODE12:
+		case mmGB_MACROTILE_MODE13:
+		case mmGB_MACROTILE_MODE14:
+		case mmGB_MACROTILE_MODE15:
+			idx = (reg_offset - mmGB_MACROTILE_MODE0);
+			return adev->gfx.config.macrotile_mode_array[idx];
+		default:
+			return RREG32(reg_offset);
+		}
+	}
 }
 
 static int cik_read_register(struct amdgpu_device *adev, u32 se_num,
@@ -1048,13 +1127,13 @@ static int cik_read_register(struct amdgpu_device *adev, u32 se_num,
 
 	*value = 0;
 	for (i = 0; i < ARRAY_SIZE(cik_allowed_read_registers); i++) {
+		bool indexed = cik_allowed_read_registers[i].grbm_indexed;
+
 		if (reg_offset != cik_allowed_read_registers[i].reg_offset)
 			continue;
 
-		*value = cik_allowed_read_registers[i].grbm_indexed ?
-			 cik_read_indexed_register(adev, se_num,
-						   sh_num, reg_offset) :
-			 RREG32(reg_offset);
+		*value = cik_get_register_value(adev, indexed, se_num, sh_num,
+						reg_offset);
 		return 0;
 	}
 	return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 5c8a7a48a4ad..419ba0ce7ee5 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -1819,6 +1819,22 @@ static void gfx_v7_0_setup_rb(struct amdgpu_device *adev)
 							adev->gfx.config.backend_enable_mask,
 							num_rb_pipes);
 	}
+
+	/* cache the values for userspace */
+	for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
+		for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
+			gfx_v7_0_select_se_sh(adev, i, j, 0xffffffff);
+			adev->gfx.config.rb_config[i][j].rb_backend_disable =
+				RREG32(mmCC_RB_BACKEND_DISABLE);
+			adev->gfx.config.rb_config[i][j].user_rb_backend_disable =
+				RREG32(mmGC_USER_RB_BACKEND_DISABLE);
+			adev->gfx.config.rb_config[i][j].raster_config =
+				RREG32(mmPA_SC_RASTER_CONFIG);
+			adev->gfx.config.rb_config[i][j].raster_config_1 =
+				RREG32(mmPA_SC_RASTER_CONFIG_1);
+		}
+	}
+	gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 	mutex_unlock(&adev->grbm_idx_mutex);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 1eb4d79d6e30..0450ac5ba6b6 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -1175,7 +1175,7 @@ static const struct amdgpu_irq_src_funcs vcn_v1_0_irq_funcs = {
 
 static void vcn_v1_0_set_irq_funcs(struct amdgpu_device *adev)
 {
-	adev->uvd.irq.num_types = adev->vcn.num_enc_rings + 1;
+	adev->vcn.irq.num_types = adev->vcn.num_enc_rings + 1;
 	adev->vcn.irq.funcs = &vcn_v1_0_irq_funcs;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
index 6c5a9cab55de..f744caeaee04 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
@@ -24,6 +24,7 @@
 #include <linux/sched.h>
 #include <linux/moduleparam.h>
 #include <linux/device.h>
+#include <linux/printk.h>
 #include "kfd_priv.h"
 
 #define KFD_DRIVER_AUTHOR	"AMD Inc. and others"
@@ -132,7 +133,7 @@ static void __exit kfd_module_exit(void)
 	kfd_process_destroy_wq();
 	kfd_topology_shutdown();
 	kfd_chardev_exit();
-	dev_info(kfd_device, "Removed module\n");
+	pr_info("amdkfd: Removed module\n");
 }
 
 module_init(kfd_module_init);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
index 4859d263fa2a..4728fad3fd74 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
@@ -202,8 +202,8 @@ static int update_mqd_sdma(struct mqd_manager *mm, void *mqd,
 	struct cik_sdma_rlc_registers *m;
 
 	m = get_sdma_mqd(mqd);
-	m->sdma_rlc_rb_cntl = ffs(q->queue_size / sizeof(unsigned int)) <<
-			SDMA0_RLC0_RB_CNTL__RB_SIZE__SHIFT |
+	m->sdma_rlc_rb_cntl = (ffs(q->queue_size / sizeof(unsigned int)) - 1)
+			<< SDMA0_RLC0_RB_CNTL__RB_SIZE__SHIFT |
 			q->vmid << SDMA0_RLC0_RB_CNTL__RB_VMID__SHIFT |
 			1 << SDMA0_RLC0_RB_CNTL__RPTR_WRITEBACK_ENABLE__SHIFT |
 			6 << SDMA0_RLC0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 2bec902fc939..a3f1e62c60ba 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -191,6 +191,24 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 
 	switch (type) {
 	case KFD_QUEUE_TYPE_SDMA:
+		if (dev->dqm->queue_count >=
+			CIK_SDMA_QUEUES_PER_ENGINE * CIK_SDMA_ENGINE_NUM) {
+			pr_err("Over-subscription is not allowed for SDMA.\n");
+			retval = -EPERM;
+			goto err_create_queue;
+		}
+
+		retval = create_cp_queue(pqm, dev, &q, properties, f, *qid);
+		if (retval != 0)
+			goto err_create_queue;
+		pqn->q = q;
+		pqn->kq = NULL;
+		retval = dev->dqm->ops.create_queue(dev