Merge tag 'amd-drm-next-6.10-2024-04-26' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.10-2024-04-26:

amdgpu:
- Misc code cleanups and refactors
- Support setting reset method at runtime
- Report OD status
- SMU 14.0.1 fixes
- SDMA 4.4.2 fixes
- VPE fixes
- MES fixes
- Update BO eviction priorities
- UMSCH fixes
- Reset fixes
- Freesync fixes
- GFXIP 9.4.3 fixes
- SDMA 5.2 fixes
- MES UAF fix
- RAS updates
- Devcoredump updates for dumping IP state
- DSC fixes
- JPEG fix
- Fix VRAM memory accounting
- VCN 5.0 fixes
- MES fixes
- UMC 12.0 updates
- Modify contiguous flags handling
- Initial support for mapping kernel queues via MES

amdkfd:
- Fix rescheduling of restore worker
- VRAM accounting for SVM migrations
- mGPU fix
- Enable SQ watchpoint for gfx10

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240426221245.1613332-1-alexander.deucher@amd.com

6 files changed, 22 insertions, 5 deletions

diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 569bc6e61b77..c11952a4389b 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -4406,6 +4406,8 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev)
 		ret = amdgpu_od_set_init(adev);
 		if (ret)
 			goto err_out1;
+	} else if (adev->pm.pp_feature & PP_OVERDRIVE_MASK) {
+		dev_info(adev->dev, "overdrive feature is not supported\n");
 	}
 
 	adev->pm.sysfs_initialized = true;
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
index 5cb4725c773f..6bb42d04b247 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
@@ -3316,6 +3316,8 @@ static const struct amd_ip_funcs kv_dpm_ip_funcs = {
 	.soft_reset = kv_dpm_soft_reset,
 	.set_clockgating_state = kv_dpm_set_clockgating_state,
 	.set_powergating_state = kv_dpm_set_powergating_state,
+	.dump_ip_state = NULL,
+	.print_ip_state = NULL,
 };
 
 const struct amdgpu_ip_block_version kv_smu_ip_block = {
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
index eb4da3666e05..f245fc0bc6d3 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
@@ -8060,6 +8060,8 @@ static const struct amd_ip_funcs si_dpm_ip_funcs = {
 	.soft_reset = si_dpm_soft_reset,
 	.set_clockgating_state = si_dpm_set_clockgating_state,
 	.set_powergating_state = si_dpm_set_powergating_state,
+	.dump_ip_state = NULL,
+	.print_ip_state = NULL,
 };
 
 const struct amdgpu_ip_block_version si_smu_ip_block =
diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
index 133d1ee6e67c..5fb21a0508cd 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
@@ -302,6 +302,8 @@ static const struct amd_ip_funcs pp_ip_funcs = {
 	.soft_reset = pp_sw_reset,
 	.set_clockgating_state = pp_set_clockgating_state,
 	.set_powergating_state = pp_set_powergating_state,
+	.dump_ip_state = NULL,
+	.print_ip_state = NULL,
 };
 
 const struct amdgpu_ip_block_version pp_smu_ip_block =
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 7a9f85dc06b5..4d3eca2fc3f1 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -2716,6 +2716,11 @@ static int mca_umc_mca_get_err_count(const struct mca_ras_info *mca_ras, struct
 	    umc_v12_0_is_correctable_error(adev, status0))
 		*count = (ext_error_code == 0) ? odecc_err_cnt : 1;
 
+	amdgpu_umc_update_ecc_status(adev,
+			entry->regs[MCA_REG_IDX_STATUS],
+			entry->regs[MCA_REG_IDX_IPID],
+			entry->regs[MCA_REG_IDX_ADDR]);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
index 3bc9662fbd28..68b9bf822e8d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
@@ -65,7 +65,7 @@ int smu_v14_0_init_microcode(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 	char fw_name[30];
-	char ucode_prefix[30];
+	char ucode_prefix[15];
 	int err = 0;
 	const struct smc_firmware_header_v1_0 *hdr;
 	const struct common_firmware_header *header;
@@ -136,7 +136,8 @@ int smu_v14_0_load_microcode(struct smu_context *smu)
 		    1 & ~MP1_SMN_PUB_CTRL__LX3_RESET_MASK);
 
 	for (i = 0; i < adev->usec_timeout; i++) {
-		if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0))
+		if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0) ||
+			amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1))
 			mp1_fw_flags = RREG32_PCIE(MP1_Public |
 						   (smnMP1_FIRMWARE_FLAGS_14_0_0 & 0xffffffff));
 		else
@@ -209,7 +210,8 @@ int smu_v14_0_check_fw_status(struct smu_context *smu)
 	struct amdgpu_device *adev = smu->adev;
 	uint32_t mp1_fw_flags;
 
-	if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0))
+	if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0) ||
+		amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1))
 		mp1_fw_flags = RREG32_PCIE(MP1_Public |
 					   (smnMP1_FIRMWARE_FLAGS_14_0_0 & 0xffffffff));
 	else
@@ -856,7 +858,8 @@ static int smu_v14_0_set_irq_state(struct amdgpu_device *adev,
 		// TODO
 
 		/* For MP1 SW irqs */
-		if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0)) {
+		if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0) ||
+			amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1)) {
 			val = RREG32_SOC15(MP1, 0, regMP1_SMN_IH_SW_INT_CTRL_mp1_14_0_0);
 			val = REG_SET_FIELD(val, MP1_SMN_IH_SW_INT_CTRL, INT_MASK, 1);
 			WREG32_SOC15(MP1, 0, regMP1_SMN_IH_SW_INT_CTRL_mp1_14_0_0, val);
@@ -872,7 +875,8 @@ static int smu_v14_0_set_irq_state(struct amdgpu_device *adev,
 		// TODO
 
 		/* For MP1 SW irqs */
-		if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0)) {
+		if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0) ||
+			amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1)) {
 			val = RREG32_SOC15(MP1, 0, regMP1_SMN_IH_SW_INT_mp1_14_0_0);
 			val = REG_SET_FIELD(val, MP1_SMN_IH_SW_INT, ID, 0xFE);
 			val = REG_SET_FIELD(val, MP1_SMN_IH_SW_INT, VALID, 0);