Merge tag 'drm-fixes-2022-10-28' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Regularly scheduled fixes for drm, live from a Red Hat office for the
  first time in a while.

  The core has two fixes, one for scheduler leak and one for aperture
  uninit read.

  Otherwise a single bridge fix, and msm, amdgpu/kfd and i915 have a set
  of fixes each.

  sched:
   - Stop leaking fences when killing a sched entity.

  aperture:
   - Avoid uninitialized read in aperture_remove_conflicting_pci_device()

  bridge:
   - Fix HPD on bridge/ps8640.

  msm:
   - Fix shrinker deadlock
   - Fix crash during suspend after unbind
   - Fix IRQ lifetime issues
   - Fix potential memory corruption with too many bridges
   - Fix memory corruption on GPU state capture

  amdgpu:
   - Stable pstate fix
   - SMU 13.x updates
   - SR-IOV fixes
   - PCI AER fix
   - GC 11.x fixes
   - Display fixes
   - Expose IMU firmware version for debugging
   - Plane modifier fix
   - S0i3 fix

  amdkfd:
   - Fix possible memory leak
   - Fix GC 10.x cache info reporting

  i915:
   - Extend Wa_1607297627 to Alderlake-P
   - Keep PCI autosuspend control 'on' by default on all dGPU
   - Reset frl trained flag before restarting FRL training"

* tag 'drm-fixes-2022-10-28' of git://anongit.freedesktop.org/drm/drm: (39 commits)
  fbdev/core: Avoid uninitialized read in aperture_remove_conflicting_pci_device()
  drm/amdgpu: disallow gfxoff until GC IP blocks complete s2idle resume
  drm/scheduler: fix fence ref counting
  drm/amd/display: Revert logic for plane modifiers
  drm/amdkfd: correct the cache info for gfx1036
  drm/amdkfd: update gfx1037 Lx cache setting
  drm/amdgpu: skip mes self test for gc 11.0.3 in recover
  drm/amd: Add IMU fw version to fw version queries
  drm/amd/display: Don't return false if no stream
  drm/amd/display: Remove wrong pipe control lock
  drm/amd/pm: allow gfxoff on gc_11_0_3
  drm/amdkfd: Fix memory leak in kfd_mem_dmamap_userptr()
  drm/amdgpu: Remove ATC L2 access for MMHUB 2.1.x
  drm/i915/dp: Reset frl trained flag before restarting FRL training
  drm/i915/dgfx: Keep PCI autosuspend control 'on' by default on all dGPU
  drm/i915: Extend Wa_1607297627 to Alderlake-P
  drm/amdgpu: Adjust MES polling timeout for sriov
  drm/amd/pm: update driver-if header for smu_v13_0_10
  drm/amdgpu: fix pstate setting issue
  drm/bridge: ps8640: Add back the 50 ms mystery delay after HPD
  ...

Author: torvalds

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c

@@ -510,13 +510,13 @@ kfd_mem_dmamap_userptr(struct kgd_mem *mem,
 	struct ttm_tt *ttm = bo->tbo.ttm;
 	int ret;
 
+	if (WARN_ON(ttm->num_pages != src_ttm->num_pages))
+		return -EINVAL;
+
 	ttm->sg = kmalloc(sizeof(*ttm->sg), GFP_KERNEL);
 	if (unlikely(!ttm->sg))
 		return -ENOMEM;
 
-	if (WARN_ON(ttm->num_pages != src_ttm->num_pages))
-		return -EINVAL;
-
 	/* Same sequence as in amdgpu_ttm_tt_pin_userptr */
 	ret = sg_alloc_table_from_pages(ttm->sg, src_ttm->pages,
 					ttm->num_pages, 0,

drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c

@@ -326,7 +326,10 @@ static int amdgpu_ctx_init(struct amdgpu_ctx_mgr *mgr, int32_t priority,
 	if (r)
 		return r;
 
-	ctx->stable_pstate = current_stable_pstate;
+	if (mgr->adev->pm.stable_pstate_ctx)
+		ctx->stable_pstate = mgr->adev->pm.stable_pstate_ctx->stable_pstate;
+	else
+		ctx->stable_pstate = current_stable_pstate;
 
 	return 0;
 }

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -3210,6 +3210,15 @@ static int amdgpu_device_ip_resume_phase2(struct amdgpu_device *adev)
 			return r;
 		}
 		adev->ip_blocks[i].status.hw = true;
+
+		if (adev->in_s0ix && adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SMC) {
+			/* disable gfxoff for IP resume. The gfxoff will be re-enabled in
+			 * amdgpu_device_resume() after IP resume.
+			 */
+			amdgpu_gfx_off_ctrl(adev, false);
+			DRM_DEBUG("will disable gfxoff for re-initializing other blocks\n");
+		}
+
 	}
 
 	return 0;
@@ -4185,6 +4194,13 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 	/* Make sure IB tests flushed */
 	flush_delayed_work(&adev->delayed_init_work);
 
+	if (adev->in_s0ix) {
+		/* re-enable gfxoff after IP resume. This re-enables gfxoff after
+		 * it was disabled for IP resume in amdgpu_device_ip_resume_phase2().
+		 */
+		amdgpu_gfx_off_ctrl(adev, true);
+		DRM_DEBUG("will enable gfxoff for the mission mode\n");
+	}
 	if (fbcon)
 		drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, false);
 
@@ -5381,7 +5397,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 			drm_sched_start(&ring->sched, !tmp_adev->asic_reset_res);
 		}
 
-		if (adev->enable_mes)
+		if (adev->enable_mes && adev->ip_versions[GC_HWIP][0] != IP_VERSION(11, 0, 3))
 			amdgpu_mes_self_test(tmp_adev);
 
 		if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled) {

drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c

@@ -344,6 +344,10 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
 		fw_info->ver = adev->mes.ucode_fw_version[1];
 		fw_info->feature = 0;
 		break;
+	case AMDGPU_INFO_FW_IMU:
+		fw_info->ver = adev->gfx.imu_fw_version;
+		fw_info->feature = 0;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1520,6 +1524,15 @@ static int amdgpu_debugfs_firmware_info_show(struct seq_file *m, void *unused)
 			   fw_info.feature, fw_info.ver);
 	}
 
+	/* IMU */
+	query_fw.fw_type = AMDGPU_INFO_FW_IMU;
+	query_fw.index = 0;
+	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+	if (ret)
+		return ret;
+	seq_printf(m, "IMU feature version: %u, firmware version: 0x%08x\n",
+		   fw_info.feature, fw_info.ver);
+
 	/* PSP SOS */
 	query_fw.fw_type = AMDGPU_INFO_FW_SOS;
 	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);

drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c

@@ -698,6 +698,7 @@ FW_VERSION_ATTR(rlc_srlg_fw_version, 0444, gfx.rlc_srlg_fw_version);
 FW_VERSION_ATTR(rlc_srls_fw_version, 0444, gfx.rlc_srls_fw_version);
 FW_VERSION_ATTR(mec_fw_version, 0444, gfx.mec_fw_version);
 FW_VERSION_ATTR(mec2_fw_version, 0444, gfx.mec2_fw_version);
+FW_VERSION_ATTR(imu_fw_version, 0444, gfx.imu_fw_version);
 FW_VERSION_ATTR(sos_fw_version, 0444, psp.sos.fw_version);
 FW_VERSION_ATTR(asd_fw_version, 0444, psp.asd_context.bin_desc.fw_version);
 FW_VERSION_ATTR(ta_ras_fw_version, 0444, psp.ras_context.context.bin_desc.fw_version);
@@ -719,7 +720,8 @@ static struct attribute *fw_attrs[] = {
 	&dev_attr_ta_ras_fw_version.attr, &dev_attr_ta_xgmi_fw_version.attr,
 	&dev_attr_smc_fw_version.attr, &dev_attr_sdma_fw_version.attr,
 	&dev_attr_sdma2_fw_version.attr, &dev_attr_vcn_fw_version.attr,
-	&dev_attr_dmcu_fw_version.attr, NULL
+	&dev_attr_dmcu_fw_version.attr, &dev_attr_imu_fw_version.attr,
+	NULL
 };
 
 static const struct attribute_group fw_attr_group = {

drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c

@@ -547,6 +547,7 @@ static void amdgpu_virt_populate_vf2pf_ucode_info(struct amdgpu_device *adev)
 	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_RLC_SRLS, adev->gfx.rlc_srls_fw_version);
 	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_MEC,      adev->gfx.mec_fw_version);
 	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_MEC2,     adev->gfx.mec2_fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_IMU,      adev->gfx.imu_fw_version);
 	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SOS,      adev->psp.sos.fw_version);
 	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_ASD,
 			    adev->psp.asd_context.bin_desc.fw_version);

drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h

@@ -70,6 +70,7 @@ enum amd_sriov_ucode_engine_id {
 	AMD_SRIOV_UCODE_ID_RLC_SRLS,
 	AMD_SRIOV_UCODE_ID_MEC,
 	AMD_SRIOV_UCODE_ID_MEC2,
+	AMD_SRIOV_UCODE_ID_IMU,
 	AMD_SRIOV_UCODE_ID_SOS,
 	AMD_SRIOV_UCODE_ID_ASD,
 	AMD_SRIOV_UCODE_ID_TA_RAS,

drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c

@@ -5051,6 +5051,7 @@ static int gfx_v11_0_set_powergating_state(void *handle,
 	switch (adev->ip_versions[GC_HWIP][0]) {
 	case IP_VERSION(11, 0, 0):
 	case IP_VERSION(11, 0, 2):
+	case IP_VERSION(11, 0, 3):
 		amdgpu_gfx_off_ctrl(adev, enable);
 		break;
 	case IP_VERSION(11, 0, 1):

drivers/gpu/drm/amd/amdgpu/mes_v11_0.c

@@ -98,7 +98,14 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
 	struct amdgpu_device *adev = mes->adev;
 	struct amdgpu_ring *ring = &mes->ring;
 	unsigned long flags;
+	signed long timeout = adev->usec_timeout;
 
+	if (amdgpu_emu_mode) {
+		timeout *= 100;
+	} else if (amdgpu_sriov_vf(adev)) {
+		/* Worst case in sriov where all other 15 VF timeout, each VF needs about 600ms */
+		timeout = 15 * 600 * 1000;
+	}
 	BUG_ON(size % 4 != 0);
 
 	spin_lock_irqsave(&mes->ring_lock, flags);
@@ -118,7 +125,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
 	DRM_DEBUG("MES msg=%d was emitted\n", x_pkt->header.opcode);
 
 	r = amdgpu_fence_wait_polling(ring, ring->fence_drv.sync_seq,
-		      adev->usec_timeout * (amdgpu_emu_mode ? 100 : 1));
+		      timeout);
 	if (r < 1) {
 		DRM_ERROR("MES failed to response msg=%d\n",
 			  x_pkt->header.opcode);

drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c

@@ -32,8 +32,6 @@
 #include "gc/gc_10_1_0_offset.h"
 #include "soc15_common.h"
 
-#define mmMM_ATC_L2_MISC_CG_Sienna_Cichlid                      0x064d
-#define mmMM_ATC_L2_MISC_CG_Sienna_Cichlid_BASE_IDX             0
 #define mmDAGB0_CNTL_MISC2_Sienna_Cichlid                       0x0070
 #define mmDAGB0_CNTL_MISC2_Sienna_Cichlid_BASE_IDX              0
 
@@ -574,7 +572,6 @@ static void mmhub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *ad
 	case IP_VERSION(2, 1, 0):
 	case IP_VERSION(2, 1, 1):
 	case IP_VERSION(2, 1, 2):
-		def  = data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid);
 		def1 = data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2_Sienna_Cichlid);
 		break;
 	default:
@@ -608,8 +605,6 @@ static void mmhub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *ad
 	case IP_VERSION(2, 1, 0):
 	case IP_VERSION(2, 1, 1):
 	case IP_VERSION(2, 1, 2):
-		if (def != data)
-			WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid, data);
 		if (def1 != data1)
 			WREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2_Sienna_Cichlid, data1);
 		break;
@@ -634,8 +629,8 @@ static void mmhub_v2_0_update_medium_grain_light_sleep(struct amdgpu_device *ade
 	case IP_VERSION(2, 1, 0):
 	case IP_VERSION(2, 1, 1):
 	case IP_VERSION(2, 1, 2):
-		def  = data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid);
-		break;
+		/* There is no ATCL2 in MMHUB for 2.1.x */
+		return;
 	default:
 		def  = data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG);
 		break;
@@ -646,18 +641,8 @@ static void mmhub_v2_0_update_medium_grain_light_sleep(struct amdgpu_device *ade
 	else
 		data &= ~MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK;
 
-	if (def != data) {
-		switch (adev->ip_versions[MMHUB_HWIP][0]) {
-		case IP_VERSION(2, 1, 0):
-		case IP_VERSION(2, 1, 1):
-		case IP_VERSION(2, 1, 2):
-			WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid, data);
-			break;
-		default:
-			WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG, data);
-			break;
-		}
-	}
+	if (def != data)
+		WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG, data);
 }
 
 static int mmhub_v2_0_set_clockgating(struct amdgpu_device *adev,
@@ -695,7 +680,10 @@ static void mmhub_v2_0_get_clockgating(struct amdgpu_device *adev, u64 *flags)
 	case IP_VERSION(2, 1, 0):
 	case IP_VERSION(2, 1, 1):
 	case IP_VERSION(2, 1, 2):
-		data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid);
+		/* There is no ATCL2 in MMHUB for 2.1.x. Keep the status
+		 * based on DAGB
+		 */
+		data = MM_ATC_L2_MISC_CG__ENABLE_MASK;
 		data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2_Sienna_Cichlid);
 		break;
 	default: