Merge tag 'drm-fixes-2020-08-21' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Regular fixes pull for rc2. Usual rc2 doesn't seem too busy, mainly
  i915 and amdgpu. I'd expect the usual uptick for rc3.

  amdgpu:
   - Fix allocation size
   - SR-IOV fixes
   - Vega20 SMU feature state caching fix
   - Fix custom pptable handling
   - Arcturus golden settings update
   - Several display fixes
   - Fixes for Navy Flounder
   - Misc display fixes
   - RAS fix

  amdkfd:
   - SDMA fix for renoir

  i915:
   - Fix device parameter usage for selftest mock i915 device
   - Fix LPSP capability debugfs NULL dereference
   - Fix buddy register pagemask table
   - Fix intel_atomic_check() non-negative return value
   - Fix selftests passing a random 0 into ilog2()
   - Fix TGL power well enable/disable ordering
   - Switch to PMU module refcounting
   - GVT fixes

  virtio:
   - Add missing dma_fence_put() in virtio_gpu_execbuffer_ioctl()
   - Fix memory leak in virtio_gpu_cleanup_object()"

* tag 'drm-fixes-2020-08-21' of git://anongit.freedesktop.org/drm/drm: (34 commits)
  Revert "drm/amdgpu: disable gfxoff for navy_flounder"
  drm/i915/tgl: Make sure TC-cold is blocked before enabling TC AUX power wells
  drm/i915/selftests: Avoid passing a random 0 into ilog2
  drm/i915: Fix wrong return value in intel_atomic_check()
  drm/i915: Update bw_buddy pagemask table
  drm/i915/display: Check for an LPSP encoder before dereferencing
  drm/i915: Copy default modparams to mock i915_device
  drm/i915: Provide the perf pmu.module
  drm/amd/display: fix pow() crashing when given base 0
  drm/amd/display: Reset scrambling on Test Pattern
  drm/amd/display: fix dcn3 wide timing dsc validation
  drm/amd/display: Fix DFPstate hang due to view port changed
  drm/amd/display: Assign correct left shift
  drm/amd/display: Call DMUB for eDP power control
  drm/amdkfd: fix the wrong sdma instance query for renoir
  drm/amdgpu: parse ta firmware for navy_flounder
  drm/amdgpu: fix NULL pointer access issue when unloading driver
  drm/amdgpu: fix uninit-value in arcturus_log_thermal_throttling_event()
  drm/amdgpu: disable gfxoff for navy_flounder
  drm/amdgpu/display: use GFP_ATOMIC in dcn20_validate_bandwidth_internal
  ...

7 files changed, 63 insertions, 14 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index c7fd0c47b254..1102de76d876 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -195,19 +195,32 @@ static uint32_t get_sdma_rlc_reg_offset(struct amdgpu_device *adev,
 				unsigned int engine_id,
 				unsigned int queue_id)
 {
-	uint32_t sdma_engine_reg_base[2] = {
-		SOC15_REG_OFFSET(SDMA0, 0,
-				 mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL,
-		SOC15_REG_OFFSET(SDMA1, 0,
-				 mmSDMA1_RLC0_RB_CNTL) - mmSDMA1_RLC0_RB_CNTL
-	};
-	uint32_t retval = sdma_engine_reg_base[engine_id]
+	uint32_t sdma_engine_reg_base = 0;
+	uint32_t sdma_rlc_reg_offset;
+
+	switch (engine_id) {
+	default:
+		dev_warn(adev->dev,
+			 "Invalid sdma engine id (%d), using engine id 0\n",
+			 engine_id);
+		fallthrough;
+	case 0:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA0, 0,
+				mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL;
+		break;
+	case 1:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA1, 0,
+				mmSDMA1_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL;
+		break;
+	}
+
+	sdma_rlc_reg_offset = sdma_engine_reg_base
 		+ queue_id * (mmSDMA0_RLC1_RB_CNTL - mmSDMA0_RLC0_RB_CNTL);
 
 	pr_debug("RLC register offset for SDMA%d RLC%d: 0x%x\n", engine_id,
-			queue_id, retval);
+		 queue_id, sdma_rlc_reg_offset);
 
-	return retval;
+	return sdma_rlc_reg_offset;
 }
 
 static inline struct v9_mqd *get_mqd(void *mqd)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index bcce4c0be462..1bedb416eebd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1243,7 +1243,6 @@ void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev,
 	if (!obj || !obj->ent)
 		return;
 
-	debugfs_remove(obj->ent);
 	obj->ent = NULL;
 	put_obj(obj);
 }
@@ -1257,7 +1256,6 @@ static void amdgpu_ras_debugfs_remove_all(struct amdgpu_device *adev)
 		amdgpu_ras_debugfs_remove(adev, &obj->head);
 	}
 
-	debugfs_remove_recursive(con->dir);
 	con->dir = NULL;
 }
 /* debugfs end */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 134cc36e30c5..0739e259bf91 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -462,7 +462,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
 	unsigned int pages;
 	int i, r;
 
-	*sgt = kmalloc(sizeof(*sg), GFP_KERNEL);
+	*sgt = kmalloc(sizeof(**sgt), GFP_KERNEL);
 	if (!*sgt)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index cb9d60a4e05e..b95f22262a90 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -691,6 +691,7 @@ static const struct soc15_reg_golden golden_settings_gc_9_4_1_arct[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_5_ARCT, 0x3ff, 0x135),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_CONFIG, 0xffffffff, 0x011A0000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_FIFO_SIZES, 0xffffffff, 0x00000f00),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_UTCL1_CNTL1, 0x30000000, 0x30000000)
 };
 
 static const struct soc15_reg_rlcg rlcg_access_gc_9_0[] = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
index fa0bca3e1f73..5d2505956f84 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
@@ -135,6 +135,12 @@ static void gfxhub_v2_1_init_cache_regs(struct amdgpu_device *adev)
 {
 	uint32_t tmp;
 
+	/* These registers are not accessible to VF-SRIOV.
+	 * The PF will program them instead.
+	 */
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	/* Setup L2 cache */
 	tmp = RREG32_SOC15(GC, 0, mmGCVM_L2_CNTL);
 	tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL, ENABLE_L2_CACHE, 1);
@@ -190,6 +196,12 @@ static void gfxhub_v2_1_enable_system_domain(struct amdgpu_device *adev)
 
 static void gfxhub_v2_1_disable_identity_aperture(struct amdgpu_device *adev)
 {
+	/* These registers are not accessible to VF-SRIOV.
+	 * The PF will program them instead.
+	 */
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	WREG32_SOC15(GC, 0, mmGCVM_L2_CONTEXT1_IDENTITY_APERTURE_LOW_ADDR_LO32,
 		     0xFFFFFFFF);
 	WREG32_SOC15(GC, 0, mmGCVM_L2_CONTEXT1_IDENTITY_APERTURE_LOW_ADDR_HI32,
@@ -326,6 +338,13 @@ void gfxhub_v2_1_set_fault_enable_default(struct amdgpu_device *adev,
 					  bool value)
 {
 	u32 tmp;
+
+	/* These registers are not accessible to VF-SRIOV.
+	 * The PF will program them instead.
+	 */
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	tmp = RREG32_SOC15(GC, 0, mmGCVM_L2_PROTECTION_FAULT_CNTL);
 	tmp = REG_SET_FIELD(tmp, GCVM_L2_PROTECTION_FAULT_CNTL,
 			    RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, value);
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index 757fa8e83f5b..c79fc54bc3c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -134,6 +134,12 @@ static void mmhub_v2_0_init_cache_regs(struct amdgpu_device *adev)
 {
 	uint32_t tmp;
 
+	/* These registers are not accessible to VF-SRIOV.
+	 * The PF will program them instead.
+	 */
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	/* Setup L2 cache */
 	tmp = RREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL);
 	tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL, ENABLE_L2_CACHE, 1);
@@ -189,6 +195,12 @@ static void mmhub_v2_0_enable_system_domain(struct amdgpu_device *adev)
 
 static void mmhub_v2_0_disable_identity_aperture(struct amdgpu_device *adev)
 {
+	/* These registers are not accessible to VF-SRIOV.
+	 * The PF will program them instead.
+	 */
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	WREG32_SOC15(MMHUB, 0,
 		     mmMMVM_L2_CONTEXT1_IDENTITY_APERTURE_LOW_ADDR_LO32,
 		     0xFFFFFFFF);
@@ -318,6 +330,13 @@ void mmhub_v2_0_gart_disable(struct amdgpu_device *adev)
 void mmhub_v2_0_set_fault_enable_default(struct amdgpu_device *adev, bool value)
 {
 	u32 tmp;
+
+	/* These registers are not accessible to VF-SRIOV.
+	 * The PF will program them instead.
+	 */
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	tmp = RREG32_SOC15(MMHUB, 0, mmMMVM_L2_PROTECTION_FAULT_CNTL);
 	tmp = REG_SET_FIELD(tmp, MMVM_L2_PROTECTION_FAULT_CNTL,
 			    RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, value);
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index d488d250805d..e16874f30d5d 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -179,12 +179,11 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
 		}
 		break;
 	case CHIP_SIENNA_CICHLID:
+	case CHIP_NAVY_FLOUNDER:
 		err = psp_init_ta_microcode(&adev->psp, chip_name);
 		if (err)
 			return err;
 		break;
-	case CHIP_NAVY_FLOUNDER:
-		break;
 	default:
 		BUG();
 	}