Merge branch 'drm-fixes-5.2' of git://people.freedesktop.org/~agd5f/linux into drm-fixes

Fixes for 5.2:
- Fix for DMCU firmware issues for stable
- Add missing polaris10 pci id to kfd
- Screen corruption fix on picasso
- Fix for driver reload on vega10
- SR-IOV fixes
- Locking fix in new SMU code
- Compute profile switching fix for KFD

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190522205425.3657-1-alexander.deucher@amd.com

9 files changed, 70 insertions, 19 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 05897b05766b..86cc24b2e0aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -877,13 +877,16 @@ static int psp_load_fw(struct amdgpu_device *adev)
 	if (!psp->cmd)
 		return -ENOMEM;
 
-	ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
-					AMDGPU_GEM_DOMAIN_GTT,
-					&psp->fw_pri_bo,
-					&psp->fw_pri_mc_addr,
-					&psp->fw_pri_buf);
-	if (ret)
-		goto failed;
+	/* this fw pri bo is not used under SRIOV */
+	if (!amdgpu_sriov_vf(psp->adev)) {
+		ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
+					      AMDGPU_GEM_DOMAIN_GTT,
+					      &psp->fw_pri_bo,
+					      &psp->fw_pri_mc_addr,
+					      &psp->fw_pri_buf);
+		if (ret)
+			goto failed;
+	}
 
 	ret = amdgpu_bo_create_kernel(adev, PSP_FENCE_BUFFER_SIZE, PAGE_SIZE,
 					AMDGPU_GEM_DOMAIN_VRAM,
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 3fd79e07944d..3b7370d914a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -626,6 +626,7 @@ static bool gmc_v9_0_keep_stolen_memory(struct amdgpu_device *adev)
 	case CHIP_VEGA10:
 		return true;
 	case CHIP_RAVEN:
+		return (adev->pdev->device == 0x15d8);
 	case CHIP_VEGA12:
 	case CHIP_VEGA20:
 	default:
@@ -812,8 +813,16 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev)
 	int chansize, numchan;
 	int r;
 
-	if (amdgpu_emu_mode != 1)
+	if (amdgpu_sriov_vf(adev)) {
+		/* For Vega10 SR-IOV, vram_width can't be read from ATOM as RAVEN,
+		 * and DF related registers is not readable, seems hardcord is the
+		 * only way to set the correct vram_width
+		 */
+		adev->gmc.vram_width = 2048;
+	} else if (amdgpu_emu_mode != 1) {
 		adev->gmc.vram_width = amdgpu_atomfirmware_get_vram_width(adev);
+	}
+
 	if (!adev->gmc.vram_width) {
 		/* hbm memory channel size */
 		if (adev->flags & AMD_IS_APU)
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 4900e4958dec..b7e594c2bfb4 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -730,6 +730,11 @@ static bool soc15_need_reset_on_init(struct amdgpu_device *adev)
 {
 	u32 sol_reg;
 
+	/* Just return false for soc15 GPUs.  Reset does not seem to
+	 * be necessary.
+	 */
+	return false;
+
 	if (adev->flags & AMD_IS_APU)
 		return false;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index c1e4d44d6137..765b58a17dc7 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -355,6 +355,7 @@ static const struct kfd_deviceid supported_devices[] = {
 	{ 0x67CF, &polaris10_device_info },	/* Polaris10 */
 	{ 0x67D0, &polaris10_vf_device_info },	/* Polaris10 vf*/
 	{ 0x67DF, &polaris10_device_info },	/* Polaris10 */
+	{ 0x6FDF, &polaris10_device_info },	/* Polaris10 */
 	{ 0x67E0, &polaris11_device_info },	/* Polaris11 */
 	{ 0x67E1, &polaris11_device_info },	/* Polaris11 */
 	{ 0x67E3, &polaris11_device_info },	/* Polaris11 */
@@ -462,6 +463,7 @@ struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd,
 	kfd->pdev = pdev;
 	kfd->init_complete = false;
 	kfd->kfd2kgd = f2g;
+	atomic_set(&kfd->compute_profile, 0);
 
 	mutex_init(&kfd->doorbell_mutex);
 	memset(&kfd->doorbell_available_index, 0,
@@ -1036,6 +1038,21 @@ void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd)
 		atomic_inc(&kfd->sram_ecc_flag);
 }
 
+void kfd_inc_compute_active(struct kfd_dev *kfd)
+{
+	if (atomic_inc_return(&kfd->compute_profile) == 1)
+		amdgpu_amdkfd_set_compute_idle(kfd->kgd, false);
+}
+
+void kfd_dec_compute_active(struct kfd_dev *kfd)
+{
+	int count = atomic_dec_return(&kfd->compute_profile);
+
+	if (count == 0)
+		amdgpu_amdkfd_set_compute_idle(kfd->kgd, true);
+	WARN_ONCE(count < 0, "Compute profile ref. count error");
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 /* This function will send a package to HIQ to hang the HWS
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index c6c9530e704e..ae381450601c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -811,8 +811,8 @@ static int register_process(struct device_queue_manager *dqm,
 
 	retval = dqm->asic_ops.update_qpd(dqm, qpd);
 
-	if (dqm->processes_count++ == 0)
-		amdgpu_amdkfd_set_compute_idle(dqm->dev->kgd, false);
+	dqm->processes_count++;
+	kfd_inc_compute_active(dqm->dev);
 
 	dqm_unlock(dqm);
 
@@ -835,9 +835,8 @@ static int unregister_process(struct device_queue_manager *dqm,
 		if (qpd == cur->qpd) {
 			list_del(&cur->list);
 			kfree(cur);
-			if (--dqm->processes_count == 0)
-				amdgpu_amdkfd_set_compute_idle(
-					dqm->dev->kgd, true);
+			dqm->processes_count--;
+			kfd_dec_compute_active(dqm->dev);
 			goto out;
 		}
 	}
@@ -1539,6 +1538,7 @@ static int process_termination_nocpsch(struct device_queue_manager *dqm,
 			list_del(&cur->list);
 			kfree(cur);
 			dqm->processes_count--;
+			kfd_dec_compute_active(dqm->dev);
 			break;
 		}
 	}
@@ -1626,6 +1626,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
 			list_del(&cur->list);
 			kfree(cur);
 			dqm->processes_count--;
+			kfd_dec_compute_active(dqm->dev);
 			break;
 		}
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 9e0230965675..487d5da337c1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -279,6 +279,9 @@ struct kfd_dev {
 
 	/* SRAM ECC flag */
 	atomic_t sram_ecc_flag;
+
+	/* Compute Profile ref. count */
+	atomic_t compute_profile;
 };
 
 enum kfd_mempool {
@@ -978,6 +981,10 @@ int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p);
 
 bool kfd_is_locked(void);
 
+/* Compute profile */
+void kfd_inc_compute_active(struct kfd_dev *dev);
+void kfd_dec_compute_active(struct kfd_dev *dev);
+
 /* Debugfs */
 #if defined(CONFIG_DEBUG_FS)
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 995f9df66142..0680c740f6fe 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -29,6 +29,7 @@
 #include "dm_services_types.h"
 #include "dc.h"
 #include "dc/inc/core_types.h"
+#include "dal_asic_id.h"
 
 #include "vid.h"
 #include "amdgpu.h"
@@ -640,7 +641,7 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev)
 
 static int load_dmcu_fw(struct amdgpu_device *adev)
 {
-	const char *fw_name_dmcu;
+	const char *fw_name_dmcu = NULL;
 	int r;
 	const struct dmcu_firmware_header_v1_0 *hdr;
 
@@ -663,7 +664,14 @@ static int load_dmcu_fw(struct amdgpu_device *adev)
 	case CHIP_VEGA20:
 		return 0;
 	case CHIP_RAVEN:
-		fw_name_dmcu = FIRMWARE_RAVEN_DMCU;
+		if (ASICREV_IS_PICASSO(adev->external_rev_id))
+			fw_name_dmcu = FIRMWARE_RAVEN_DMCU;
+#if defined(CONFIG_DRM_AMD_DC_DCN1_01)
+		else if (ASICREV_IS_RAVEN2(adev->external_rev_id))
+			fw_name_dmcu = FIRMWARE_RAVEN_DMCU;
+#endif
+		else
+			return 0;
 		break;
 	default:
 		DRM_ERROR("Unsupported ASIC type: 0x%X\n", adev->asic_type);
diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
index 34d6fdcb32e2..4c8ce7938f01 100644
--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -138,13 +138,14 @@
 #endif
 #define RAVEN_UNKNOWN 0xFF
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_01)
-#define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < 0xF0))
-#endif /* DCN1_01 */
 #define ASIC_REV_IS_RAVEN(eChipRev) ((eChipRev >= RAVEN_A0) && eChipRev < RAVEN_UNKNOWN)
 #define RAVEN1_F0 0xF0
 #define ASICREV_IS_RV1_F0(eChipRev) ((eChipRev >= RAVEN1_F0) && (eChipRev < RAVEN_UNKNOWN))
 
+#if defined(CONFIG_DRM_AMD_DC_DCN1_01)
+#define ASICREV_IS_PICASSO(eChipRev) ((eChipRev >= PICASSO_A0) && (eChipRev < RAVEN2_A0))
+#define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < 0xF0))
+#endif /* DCN1_01 */
 
 #define FAMILY_RV 142 /* DCN 1*/
 
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index c058c784180e..eec329ab6037 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -280,7 +280,7 @@ int smu_feature_set_supported(struct smu_context *smu, int feature_id,
 
 	WARN_ON(feature_id > feature->feature_num);
 
-	mutex_unlock(&feature->mutex);
+	mutex_lock(&feature->mutex);
 	if (enable)
 		test_and_set_bit(feature_id, feature->supported);
 	else