Merge tag 'drm-fixes-2025-02-28' of https://gitlab.freedesktop.org/dr…

…m/kernel

Pull drm fixes from Dave Airlie:
 "This week's fixes pull, amdgpu mostly, with some xe and a few misc
  others, the fb defio fix is bit of a change, but it avoids some nasty
  NULL pointer crashes due to defio assuming page backing in places it
  didn't have pages.

  amdgpu:
   - Legacy dpm suspend/resume fix
   - Runtime PM fix for DELL G5 SE
   - MAINTAINERS updates
   - Enforce Isolation fixes
   - mailmap update
   - EDID reading i2c fix
   - PSR fix
   - eDP fix
   - HPD interrupt handling fix
   - Clear memory fix

  amdkfd:
   - MQD handling fix

  vkms:
   - fix rounding error

  imagination:
   - header fix

  nouveau:
   - connector status fix

  fb/defio:
   - NULL ptr fix for defio drivers

  i915:
   - Fix encoder HW state readout for DP UHBR MST

  xe:
   - OA uapi fix (Umesh)
   - Userptr related fixes
   - Remove a duplicated register entry
   - Scheduler related fix to prevent exec races when freeing it"

* tag 'drm-fixes-2025-02-28' of https://gitlab.freedesktop.org/drm/kernel: (25 commits)
  drm/fbdev-dma: Add shadow buffering for deferred I/O
  drm/nouveau: Do not override forced connector status
  drm/i915/dp_mst: Fix encoder HW state readout for UHBR MST
  drm/xe: cancel pending job timer before freeing scheduler
  drm/xe/regs: remove a duplicate definition for RING_CTL_SIZE(size)
  drm/imagination: remove unnecessary header include path
  drm/amdgpu: init return value in amdgpu_ttm_clear_buffer
  drm/amd/display: Fix HPD after gpu reset
  drm/amd/display: add a quirk to enable eDP0 on DP1
  drm/amd/display: Disable PSR-SU on eDP panels
  MAINTAINERS: Update AMDGPU DML maintainers info
  drm/amd/display: restore edid reading from a given i2c adapter
  mailmap: Add entry for Rodrigo Siqueira
  MAINTAINERS: Change my role from Maintainer to Reviewer
  drm/amdgpu/mes: keep enforce isolation up to date
  drm/amdgpu/gfx: only call mes for enforce isolation if supported
  MAINTAINERS: update amdgpu maintainers list
  drm/amdgpu: disable BAR resize on Dell G5 SE
  drm/amdkfd: Preserve cp_hqd_pq_control on update_mqd
  amdgpu/pm/legacy: fix suspend/resume issues
  ...

.mailmap

@@ -522,6 +522,7 @@ Nadav Amit <[email protected]> <[email protected]>
 Nadia Yvette Chambers <[email protected]> William Lee Irwin III <[email protected]>
 Naoya Horiguchi <[email protected]> <[email protected]>
 Naoya Horiguchi <[email protected]> <[email protected]>
+Natalie Vock <[email protected]> <[email protected]>
 Nathan Chancellor <[email protected]> <[email protected]>
 Naveen N Rao <[email protected]> <[email protected]>
 Naveen N Rao <[email protected]> <[email protected]>
@@ -613,6 +614,8 @@ Richard Leitner <[email protected]> <[email protected]>
 Richard Leitner <[email protected]> <[email protected]>
 Robert Foss <[email protected]> <[email protected]>
 Rocky Liao <[email protected]> <[email protected]>
+Rodrigo Siqueira <[email protected]> <[email protected]>
+Rodrigo Siqueira <[email protected]> <[email protected]>
 Roman Gushchin <[email protected]> <[email protected]>
 Roman Gushchin <[email protected]> <[email protected]>
 Roman Gushchin <[email protected]> <[email protected]>

MAINTAINERS

@@ -1046,14 +1046,14 @@ F:	drivers/crypto/ccp/hsti.*
 AMD DISPLAY CORE
 M:	Harry Wentland <[email protected]>
 M:	Leo Li <[email protected]>
-M:	Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
+R:	Rodrigo Siqueira <siqueira@igalia.com>
 L:	[email protected]
 S:	Supported
 T:	git https://gitlab.freedesktop.org/agd5f/linux.git
 F:	drivers/gpu/drm/amd/display/
 
 AMD DISPLAY CORE - DML
-M:	Chaitanya Dhere <chaitanya.dhere@amd.com>
+M:	Austin Zheng <austin.zheng@amd.com>
 M:	Jun Lei <[email protected]>
 S:	Supported
 F:	drivers/gpu/drm/amd/display/dc/dml/
@@ -5926,6 +5926,17 @@ F:	tools/testing/selftests/cgroup/test_cpuset.c
 F:	tools/testing/selftests/cgroup/test_cpuset_prs.sh
 F:	tools/testing/selftests/cgroup/test_cpuset_v1_base.sh
 
+CONTROL GROUP - DEVICE MEMORY CONTROLLER (DMEM)
+M:	Maarten Lankhorst <[email protected]>
+M:	Maxime Ripard <[email protected]>
+M:	Natalie Vock <[email protected]>
+L:	[email protected]
+L:	[email protected]
+S:	Maintained
+T:	git https://gitlab.freedesktop.org/drm/misc/kernel.git
+F:	include/linux/cgroup_dmem.h
+F:	kernel/cgroup/dmem.c
+
 CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)
 M:	Johannes Weiner <[email protected]>
 M:	Michal Hocko <[email protected]>
@@ -19655,7 +19666,6 @@ F:	drivers/net/wireless/quantenna
 RADEON and AMDGPU DRM DRIVERS
 M:	Alex Deucher <[email protected]>
 M:	Christian König <[email protected]>
-M:	Xinhui Pan <[email protected]>
 L:	[email protected]
 S:	Supported
 B:	https://gitlab.freedesktop.org/drm/amd/-/issues

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

@@ -1638,6 +1638,13 @@ int amdgpu_device_resize_fb_bar(struct amdgpu_device *adev)
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
+	/* resizing on Dell G5 SE platforms causes problems with runtime pm */
+	if ((amdgpu_runtime_pm != 0) &&
+	    adev->pdev->vendor == PCI_VENDOR_ID_ATI &&
+	    adev->pdev->device == 0x731f &&
+	    adev->pdev->subsystem_vendor == PCI_VENDOR_ID_DELL)
+		return 0;
+
 	/* PCI_EXT_CAP_ID_VNDR extended capability is located at 0x100 */
 	if (!pci_find_ext_capability(adev->pdev, PCI_EXT_CAP_ID_VNDR))
 		DRM_WARN("System can't access extended configuration space, please check!!\n");

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

@@ -1638,22 +1638,19 @@ static ssize_t amdgpu_gfx_set_enforce_isolation(struct device *dev,
 	}
 
 	mutex_lock(&adev->enforce_isolation_mutex);
-
 	for (i = 0; i < num_partitions; i++) {
-		if (adev->enforce_isolation[i] && !partition_values[i]) {
+		if (adev->enforce_isolation[i] && !partition_values[i])
 			/* Going from enabled to disabled */
 			amdgpu_vmid_free_reserved(adev, AMDGPU_GFXHUB(i));
-			amdgpu_mes_set_enforce_isolation(adev, i, false);
-		} else if (!adev->enforce_isolation[i] && partition_values[i]) {
+		else if (!adev->enforce_isolation[i] && partition_values[i])
 			/* Going from disabled to enabled */
 			amdgpu_vmid_alloc_reserved(adev, AMDGPU_GFXHUB(i));
-			amdgpu_mes_set_enforce_isolation(adev, i, true);
-		}
 		adev->enforce_isolation[i] = partition_values[i];
 	}
-
 	mutex_unlock(&adev->enforce_isolation_mutex);
 
+	amdgpu_mes_update_enforce_isolation(adev);
+
 	return count;
 }
 

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

@@ -1681,7 +1681,8 @@ bool amdgpu_mes_suspend_resume_all_supported(struct amdgpu_device *adev)
 }
 
 /* Fix me -- node_id is used to identify the correct MES instances in the future */
-int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, uint32_t node_id, bool enable)
+static int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev,
+					    uint32_t node_id, bool enable)
 {
 	struct mes_misc_op_input op_input = {0};
 	int r;
@@ -1703,6 +1704,23 @@ int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, uint32_t node_i
 	return r;
 }
 
+int amdgpu_mes_update_enforce_isolation(struct amdgpu_device *adev)
+{
+	int i, r = 0;
+
+	if (adev->enable_mes && adev->gfx.enable_cleaner_shader) {
+		mutex_lock(&adev->enforce_isolation_mutex);
+		for (i = 0; i < (adev->xcp_mgr ? adev->xcp_mgr->num_xcps : 1); i++) {
+			if (adev->enforce_isolation[i])
+				r |= amdgpu_mes_set_enforce_isolation(adev, i, true);
+			else
+				r |= amdgpu_mes_set_enforce_isolation(adev, i, false);
+		}
+		mutex_unlock(&adev->enforce_isolation_mutex);
+	}
+	return r;
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 static int amdgpu_debugfs_mes_event_log_show(struct seq_file *m, void *unused)

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

@@ -534,6 +534,6 @@ static inline void amdgpu_mes_unlock(struct amdgpu_mes *mes)
 
 bool amdgpu_mes_suspend_resume_all_supported(struct amdgpu_device *adev);
 
-int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, uint32_t node_id, bool enable);
+int amdgpu_mes_update_enforce_isolation(struct amdgpu_device *adev);
 
 #endif /* __AMDGPU_MES_H__ */

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

@@ -2281,7 +2281,7 @@ int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo,
 	struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
 	struct amdgpu_res_cursor cursor;
 	u64 addr;
-	int r;
+	int r = 0;
 
 	if (!adev->mman.buffer_funcs_enabled)
 		return -EINVAL;

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

@@ -1633,6 +1633,10 @@ static int mes_v11_0_hw_init(struct amdgpu_ip_block *ip_block)
 		goto failure;
 	}
 
+	r = amdgpu_mes_update_enforce_isolation(adev);
+	if (r)
+		goto failure;
+
 out:
 	/*
 	 * Disable KIQ ring usage from the driver once MES is enabled.

drivers/gpu/drm/amd/amdgpu/mes_v12_0.c

@@ -1743,6 +1743,10 @@ static int mes_v12_0_hw_init(struct amdgpu_ip_block *ip_block)
 		goto failure;
 	}
 
+	r = amdgpu_mes_update_enforce_isolation(adev);
+	if (r)
+		goto failure;
+
 out:
 	/*
 	 * Disable KIQ ring usage from the driver once MES is enabled.

drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c

@@ -107,6 +107,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
 			0x53 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
 
+	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
 
 	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
@@ -167,10 +169,10 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 
 	m = get_mqd(mqd);
 
-	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
 	m->cp_hqd_pq_control |=
 			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
-	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
+
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);

drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c

@@ -154,6 +154,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
 			0x55 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
 
+	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
 
 	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
@@ -221,10 +223,9 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 
 	m = get_mqd(mqd);
 
-	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
 	m->cp_hqd_pq_control |=
 			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
-	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);

drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c

@@ -121,6 +121,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
 			0x55 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
 
+	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
 
 	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
@@ -184,10 +186,9 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 
 	m = get_mqd(mqd);
 
-	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
 	m->cp_hqd_pq_control |=
 			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
-	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);

drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c

@@ -183,6 +183,9 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
 			0x53 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
 
+	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
+
 	m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
 
 	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
@@ -245,7 +248,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 
 	m = get_mqd(mqd);
 
-	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
 	m->cp_hqd_pq_control |= order_base_2(q->queue_size / 4) - 1;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);