Merge tag 'drm-next-2020-10-15' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Not a major amount of change, the i915 trees got split into display
  and gt trees to better facilitate higher level review, and there's a
  major refactoring of i915 GEM locking to use more core kernel concepts
  (like ww-mutexes). msm gets per-process pagetables, older AMD SI cards
  get DC support, nouveau got a bump in displayport support with common
  code extraction from i915.

  Outside of drm this contains a couple of patches for hexint
  moduleparams which you've acked, and a virtio common code tree that
  you should also get via it's regular path.

  New driver:
   - Cadence MHDP8546 DisplayPort bridge driver

  core:
   - cross-driver scatterlist cleanups
   - devm_drm conversions
   - remove drm_dev_init
   - devm_drm_dev_alloc conversion

  ttm:
   - lots of refactoring and cleanups

  bridges:
   - chained bridge support in more drivers

  panel:
   - misc new panels

  scheduler:
   - cleanup priority levels

  displayport:
   - refactor i915 code into helpers for nouveau

  i915:
   - split into display and GT trees
   - WW locking refactoring in GEM
   - execbuf2 extension mechanism
   - syncobj timeline support
   - GEN 12 HOBL display powersaving
   - Rocket Lake display additions
   - Disable FBC on Tigerlake
   - Tigerlake Type-C + DP improvements
   - Hotplug interrupt refactoring

  amdgpu:
   - Sienna Cichlid updates
   - Navy Flounder updates
   - DCE6 (SI) support for DC
   - Plane rotation enabled
   - TMZ state info ioctl
   - PCIe DPC recovery support
   - DC interrupt handling refactor
   - OLED panel fixes

  amdkfd:
   - add SMI events for thermal throttling
   - SMI interface events ioctl update
   - process eviction counters

  radeon:
   - move to dma_ for allocations
   - expose sclk via sysfs

  msm:
   - DSI support for sm8150/sm8250
   - per-process GPU pagetable support
   - Displayport support

  mediatek:
   - move HDMI phy driver to PHY
   - convert mtk-dpi to bridge API
   - disable mt2701 tmds

  tegra:
   - bridge support

  exynos:
   - misc cleanups

  vc4:
   - dual display cleanups

  ast:
   - cleanups

  gma500:
   - conversion to GPIOd API

  hisilicon:
   - misc reworks

  ingenic:
   - clock handling and format improvements

  mcde:
   - DSI support

  mgag200:
   - desktop g200 support

  mxsfb:
   - i.MX7 + i.MX8M
   - alpha plane support

  panfrost:
   - devfreq support
   - amlogic SoC support

  ps8640:
   - EDID from eDP retrieval

  tidss:
   - AM65xx YUV workaround

  virtio:
   - virtio-gpu exported resources

  rcar-du:
   - R8A7742, R8A774E1 and R8A77961 support
   - YUV planar format fixes
   - non-visible plane handling
   - VSP device reference count fix
   - Kconfig fix to avoid displaying disabled options in .config"

* tag 'drm-next-2020-10-15' of git://anongit.freedesktop.org/drm/drm: (1494 commits)
  drm/ingenic: Fix bad revert
  drm/amdgpu: Fix invalid number of character '{' in amdgpu_acpi_init
  drm/amdgpu: Remove warning for virtual_display
  drm/amdgpu: kfd_initialized can be static
  drm/amd/pm: setup APU dpm clock table in SMU HW initialization
  drm/amdgpu: prevent spurious warning
  drm/amdgpu/swsmu: fix ARC build errors
  drm/amd/display: Fix OPTC_DATA_FORMAT programming
  drm/amd/display: Don't allow pstate if no support in blank
  drm/panfrost: increase readl_relaxed_poll_timeout values
  MAINTAINERS: Update entry for st7703 driver after the rename
  Revert "gpu/drm: ingenic: Add option to mmap GEM buffers cached"
  drm/amd/display: HDMI remote sink need mode validation for Linux
  drm/amd/display: Change to correct unit on audio rate
  drm/amd/display: Avoid set zero in the requested clk
  drm/amdgpu: align frag_end to covered address space
  drm/amdgpu: fix NULL pointer dereference for Renoir
  drm/vmwgfx: fix regression in thp code due to ttm init refactor.
  drm/amdgpu/swsmu: add interrupt work handler for smu11 parts
  drm/amdgpu/swsmu: add interrupt work function
  ...

1 files changed, 119 insertions, 102 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index e3a3755cb999..1162913c8bf4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -35,11 +35,9 @@
 
 static DEFINE_MUTEX(xgmi_mutex);
 
-#define AMDGPU_MAX_XGMI_HIVE			8
 #define AMDGPU_MAX_XGMI_DEVICE_PER_HIVE		4
 
-static struct amdgpu_hive_info xgmi_hives[AMDGPU_MAX_XGMI_HIVE];
-static unsigned hive_count = 0;
+static LIST_HEAD(xgmi_hive_list);
 
 static const int xgmi_pcs_err_status_reg_vg20[] = {
 	smnXGMI0_PCS_GOPX16_PCS_ERROR_STATUS,
@@ -171,65 +169,53 @@ static const struct amdgpu_pcs_ras_field wafl_pcs_ras_fields[] = {
  *
  */
 
+static struct attribute amdgpu_xgmi_hive_id = {
+	.name = "xgmi_hive_id",
+	.mode = S_IRUGO
+};
 
-static ssize_t amdgpu_xgmi_show_hive_id(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	struct amdgpu_hive_info *hive =
-			container_of(attr, struct amdgpu_hive_info, dev_attr);
-
-	return snprintf(buf, PAGE_SIZE, "%llu\n", hive->hive_id);
-}
+static struct attribute *amdgpu_xgmi_hive_attrs[] = {
+	&amdgpu_xgmi_hive_id,
+	NULL
+};
 
-static int amdgpu_xgmi_sysfs_create(struct amdgpu_device *adev,
-				    struct amdgpu_hive_info *hive)
+static ssize_t amdgpu_xgmi_show_attrs(struct kobject *kobj,
+	struct attribute *attr, char *buf)
 {
-	int ret = 0;
+	struct amdgpu_hive_info *hive = container_of(
+		kobj, struct amdgpu_hive_info, kobj);
 
-	if (WARN_ON(hive->kobj))
-		return -EINVAL;
-
-	hive->kobj = kobject_create_and_add("xgmi_hive_info", &adev->dev->kobj);
-	if (!hive->kobj) {
-		dev_err(adev->dev, "XGMI: Failed to allocate sysfs entry!\n");
-		return -EINVAL;
-	}
-
-	hive->dev_attr = (struct device_attribute) {
-		.attr = {
-			.name = "xgmi_hive_id",
-			.mode = S_IRUGO,
-
-		},
-		.show = amdgpu_xgmi_show_hive_id,
-	};
+	if (attr == &amdgpu_xgmi_hive_id)
+		return snprintf(buf, PAGE_SIZE, "%llu\n", hive->hive_id);
 
-	ret = sysfs_create_file(hive->kobj, &hive->dev_attr.attr);
-	if (ret) {
-		dev_err(adev->dev, "XGMI: Failed to create device file xgmi_hive_id\n");
-		kobject_del(hive->kobj);
-		kobject_put(hive->kobj);
-		hive->kobj = NULL;
-	}
-
-	return ret;
+	return 0;
 }
 
-static void amdgpu_xgmi_sysfs_destroy(struct amdgpu_device *adev,
-				    struct amdgpu_hive_info *hive)
+static void amdgpu_xgmi_hive_release(struct kobject *kobj)
 {
-	sysfs_remove_file(hive->kobj, &hive->dev_attr.attr);
-	kobject_del(hive->kobj);
-	kobject_put(hive->kobj);
-	hive->kobj = NULL;
+	struct amdgpu_hive_info *hive = container_of(
+		kobj, struct amdgpu_hive_info, kobj);
+
+	mutex_destroy(&hive->hive_lock);
+	kfree(hive);
 }
 
+static const struct sysfs_ops amdgpu_xgmi_hive_ops = {
+	.show = amdgpu_xgmi_show_attrs,
+};
+
+struct kobj_type amdgpu_xgmi_hive_type = {
+	.release = amdgpu_xgmi_hive_release,
+	.sysfs_ops = &amdgpu_xgmi_hive_ops,
+	.default_attrs = amdgpu_xgmi_hive_attrs,
+};
+
 static ssize_t amdgpu_xgmi_show_device_id(struct device *dev,
 				     struct device_attribute *attr,
 				     char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 
 	return snprintf(buf, PAGE_SIZE, "%llu\n", adev->gmc.xgmi.node_id);
 
@@ -241,7 +227,7 @@ static ssize_t amdgpu_xgmi_show_error(struct device *dev,
 				      char *buf)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(ddev);
 	uint32_t ficaa_pie_ctl_in, ficaa_pie_status_in;
 	uint64_t fica_out;
 	unsigned int error_count = 0;
@@ -287,8 +273,8 @@ static int amdgpu_xgmi_sysfs_add_dev_info(struct amdgpu_device *adev,
 
 
 	/* Create sysfs link to hive info folder on the first device */
-	if (adev != hive->adev) {
-		ret = sysfs_create_link(&adev->dev->kobj, hive->kobj,
+	if (hive->kobj.parent != (&adev->dev->kobj)) {
+		ret = sysfs_create_link(&adev->dev->kobj, &hive->kobj,
 					"xgmi_hive_info");
 		if (ret) {
 			dev_err(adev->dev, "XGMI: Failed to create link to hive info");
@@ -296,9 +282,9 @@ static int amdgpu_xgmi_sysfs_add_dev_info(struct amdgpu_device *adev,
 		}
 	}
 
-	sprintf(node, "node%d", hive->number_devices);
+	sprintf(node, "node%d", atomic_read(&hive->number_devices));
 	/* Create sysfs link form the hive folder to yourself */
-	ret = sysfs_create_link(hive->kobj, &adev->dev->kobj, node);
+	ret = sysfs_create_link(&hive->kobj, &adev->dev->kobj, node);
 	if (ret) {
 		dev_err(adev->dev, "XGMI: Failed to create link from hive info");
 		goto remove_link;
@@ -308,7 +294,7 @@ static int amdgpu_xgmi_sysfs_add_dev_info(struct amdgpu_device *adev,
 
 
 remove_link:
-	sysfs_remove_link(&adev->dev->kobj, adev->ddev->unique);
+	sysfs_remove_link(&adev->dev->kobj, adev_to_drm(adev)->unique);
 
 remove_file:
 	device_remove_file(adev->dev, &dev_attr_xgmi_device_id);
@@ -326,78 +312,96 @@ static void amdgpu_xgmi_sysfs_rem_dev_info(struct amdgpu_device *adev,
 	device_remove_file(adev->dev, &dev_attr_xgmi_device_id);
 	device_remove_file(adev->dev, &dev_attr_xgmi_error);
 
-	if (adev != hive->adev)
+	if (hive->kobj.parent != (&adev->dev->kobj))
 		sysfs_remove_link(&adev->dev->kobj,"xgmi_hive_info");
 
-	sprintf(node, "node%d", hive->number_devices);
-	sysfs_remove_link(hive->kobj, node);
+	sprintf(node, "node%d", atomic_read(&hive->number_devices));
+	sysfs_remove_link(&hive->kobj, node);
 
 }
 
 
 
-struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev, int lock)
+struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev)
 {
-	int i;
-	struct amdgpu_hive_info *tmp;
+	struct amdgpu_hive_info *hive = NULL, *tmp = NULL;
+	int ret;
 
 	if (!adev->gmc.xgmi.hive_id)
 		return NULL;
 
+	if (adev->hive) {
+		kobject_get(&adev->hive->kobj);
+		return adev->hive;
+	}
+
 	mutex_lock(&xgmi_mutex);
 
-	for (i = 0 ; i < hive_count; ++i) {
-		tmp = &xgmi_hives[i];
-		if (tmp->hive_id == adev->gmc.xgmi.hive_id) {
-			if (lock)
-				mutex_lock(&tmp->hive_lock);
-			mutex_unlock(&xgmi_mutex);
-			return tmp;
+	if (!list_empty(&xgmi_hive_list)) {
+		list_for_each_entry_safe(hive, tmp, &xgmi_hive_list, node)  {
+			if (hive->hive_id == adev->gmc.xgmi.hive_id)
+				goto pro_end;
 		}
 	}
-	if (i >= AMDGPU_MAX_XGMI_HIVE) {
-		mutex_unlock(&xgmi_mutex);
-		return NULL;
+
+	hive = kzalloc(sizeof(*hive), GFP_KERNEL);
+	if (!hive) {
+		dev_err(adev->dev, "XGMI: allocation failed\n");
+		hive = NULL;
+		goto pro_end;
 	}
 
 	/* initialize new hive if not exist */
-	tmp = &xgmi_hives[hive_count++];
-
-	if (amdgpu_xgmi_sysfs_create(adev, tmp)) {
-		mutex_unlock(&xgmi_mutex);
-		return NULL;
+	ret = kobject_init_and_add(&hive->kobj,
+			&amdgpu_xgmi_hive_type,
+			&adev->dev->kobj,
+			"%s", "xgmi_hive_info");
+	if (ret) {
+		dev_err(adev->dev, "XGMI: failed initializing kobject for xgmi hive\n");
+		kfree(hive);
+		hive = NULL;
+		goto pro_end;
 	}
 
-	tmp->adev = adev;
-	tmp->hive_id = adev->gmc.xgmi.hive_id;
-	INIT_LIST_HEAD(&tmp->device_list);
-	mutex_init(&tmp->hive_lock);
-	mutex_init(&tmp->reset_lock);
-	task_barrier_init(&tmp->tb);
-
-	if (lock)
-		mutex_lock(&tmp->hive_lock);
-	tmp->pstate = AMDGPU_XGMI_PSTATE_UNKNOWN;
-	tmp->hi_req_gpu = NULL;
+	hive->hive_id = adev->gmc.xgmi.hive_id;
+	INIT_LIST_HEAD(&hive->device_list);
+	INIT_LIST_HEAD(&hive->node);
+	mutex_init(&hive->hive_lock);
+	atomic_set(&hive->in_reset, 0);
+	atomic_set(&hive->number_devices, 0);
+	task_barrier_init(&hive->tb);
+	hive->pstate = AMDGPU_XGMI_PSTATE_UNKNOWN;
+	hive->hi_req_gpu = NULL;
 	/*
 	 * hive pstate on boot is high in vega20 so we have to go to low
 	 * pstate on after boot.
 	 */
-	tmp->hi_req_count = AMDGPU_MAX_XGMI_DEVICE_PER_HIVE;
+	hive->hi_req_count = AMDGPU_MAX_XGMI_DEVICE_PER_HIVE;
+	list_add_tail(&hive->node, &xgmi_hive_list);
+
+pro_end:
+	if (hive)
+		kobject_get(&hive->kobj);
 	mutex_unlock(&xgmi_mutex);
+	return hive;
+}
 
-	return tmp;
+void amdgpu_put_xgmi_hive(struct amdgpu_hive_info *hive)
+{
+	if (hive)
+		kobject_put(&hive->kobj);
 }
 
 int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate)
 {
 	int ret = 0;
-	struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev, 0);
+	struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev);
 	struct amdgpu_device *request_adev = hive->hi_req_gpu ?
 						hive->hi_req_gpu : adev;
 	bool is_hi_req = pstate == AMDGPU_XGMI_PSTATE_MAX_VEGA20;
 	bool init_low = hive->pstate == AMDGPU_XGMI_PSTATE_UNKNOWN;
 
+	amdgpu_put_xgmi_hive(hive);
 	/* fw bug so temporarily disable pstate switching */
 	return 0;
 
@@ -449,7 +453,7 @@ int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_dev
 
 	/* Each psp need to set the latest topology */
 	ret = psp_xgmi_set_topology_info(&adev->psp,
-					 hive->number_devices,
+					 atomic_read(&hive->number_devices),
 					 &adev->psp.xgmi_context.top_info);
 	if (ret)
 		dev_err(adev->dev,
@@ -511,7 +515,7 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 		adev->gmc.xgmi.node_id = adev->gmc.xgmi.physical_node_id + 16;
 	}
 
-	hive = amdgpu_get_xgmi_hive(adev, 1);
+	hive = amdgpu_get_xgmi_hive(adev);
 	if (!hive) {
 		ret = -EINVAL;
 		dev_err(adev->dev,
@@ -519,6 +523,7 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 			adev->gmc.xgmi.node_id, adev->gmc.xgmi.hive_id);
 		goto exit;
 	}
+	mutex_lock(&hive->hive_lock);
 
 	top_info = &adev->psp.xgmi_context.top_info;
 
@@ -526,7 +531,7 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 	list_for_each_entry(entry, &hive->device_list, head)
 		top_info->nodes[count++].node_id = entry->node_id;
 	top_info->num_nodes = count;
-	hive->number_devices = count;
+	atomic_set(&hive->number_devices, count);
 
 	task_barrier_add_task(&hive->tb);
 
@@ -541,7 +546,7 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 			}
 			ret = amdgpu_xgmi_update_topology(hive, tmp_adev);
 			if (ret)
-				goto exit;
+				goto exit_unlock;
 		}
 
 		/* get latest topology info for each device from psp */
@@ -554,7 +559,7 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 					tmp_adev->gmc.xgmi.node_id,
 					tmp_adev->gmc.xgmi.hive_id, ret);
 				/* To do : continue with some node failed or disable the whole hive */
-				goto exit;
+				goto exit_unlock;
 			}
 		}
 	}
@@ -562,39 +567,51 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 	if (!ret)
 		ret = amdgpu_xgmi_sysfs_add_dev_info(adev, hive);
 
-
+exit_unlock:
 	mutex_unlock(&hive->hive_lock);
 exit:
-	if (!ret)
+	if (!ret) {
+		adev->hive = hive;
 		dev_info(adev->dev, "XGMI: Add node %d, hive 0x%llx.\n",
 			 adev->gmc.xgmi.physical_node_id, adev->gmc.xgmi.hive_id);
-	else
+	} else {
+		amdgpu_put_xgmi_hive(hive);
 		dev_err(adev->dev, "XGMI: Failed to add node %d, hive 0x%llx ret: %d\n",
 			adev->gmc.xgmi.physical_node_id, adev->gmc.xgmi.hive_id,
 			ret);
+	}
 
 	return ret;
 }
 
 int amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
 {
-	struct amdgpu_hive_info *hive;
+	struct amdgpu_hive_info *hive = adev->hive;
 
 	if (!adev->gmc.xgmi.supported)
 		return -EINVAL;
 
-	hive = amdgpu_get_xgmi_hive(adev, 1);
 	if (!hive)
 		return -EINVAL;
 
+	mutex_lock(&hive->hive_lock);
 	task_barrier_rem_task(&hive->tb);
 	amdgpu_xgmi_sysfs_rem_dev_info(adev, hive);
+	if (hive->hi_req_gpu == adev)
+		hive->hi_req_gpu = NULL;
+	list_del(&adev->gmc.xgmi.head);
 	mutex_unlock(&hive->hive_lock);
 
-	if(!(--hive->number_devices)){
-		amdgpu_xgmi_sysfs_destroy(adev, hive);
-		mutex_destroy(&hive->hive_lock);
-		mutex_destroy(&hive->reset_lock);
+	amdgpu_put_xgmi_hive(hive);
+	adev->hive = NULL;
+
+	if (atomic_dec_return(&hive->number_devices) == 0) {
+		/* Remove the hive from global hive list */
+		mutex_lock(&xgmi_mutex);
+		list_del(&hive->node);
+		mutex_unlock(&xgmi_mutex);
+
+		amdgpu_put_xgmi_hive(hive);
 	}
 
 	return psp_xgmi_terminate(&adev->psp);