Merge tag 'drm-next-2018-10-24' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "This is going to rebuild more than drm as it adds a new helper to
  list.h for doing bulk updates. Seemed like a reasonable addition to
  me.

  Otherwise the usual merge window stuff lots of i915 and amdgpu, not so
  much nouveau, and piles of everything else.

  Core:
   - Adds a new list.h helper for doing bulk list updates for TTM.
   - Don't leak fb address in smem_start to userspace (comes with EXPORT
     workaround for people using mali out of tree hacks)
   - udmabuf device to turn memfd regions into dma-buf
   - Per-plane blend mode property
   - ref/unref replacements with get/put
   - fbdev conflicting framebuffers code cleaned up
   - host-endian format variants
   - panel orientation quirk for Acer One 10

  bridge:
   - TI SN65DSI86 chip support

  vkms:
   - GEM support.
   - Cursor support

  amdgpu:
   - Merge amdkfd and amdgpu into one module
   - CEC over DP AUX support
   - Picasso APU support + VCN dynamic powergating
   - Raven2 APU support
   - Vega20 enablement + kfd support
   - ACP powergating improvements
   - ABGR/XBGR display support
   - VCN jpeg support
   - xGMI support
   - DC i2c/aux cleanup
   - Ycbcr 4:2:0 support
   - GPUVM improvements
   - Powerplay and powerplay endian fixes
   - Display underflow fixes

  vmwgfx:
   - Move vmwgfx specific TTM code to vmwgfx
   - Split out vmwgfx buffer/resource validation code
   - Atomic operation rework

  bochs:
   - use more helpers
   - format/byteorder improvements

  qxl:
   - use more helpers

  i915:
   - GGTT coherency getparam
   - Turn off resource streamer API
   - More Icelake enablement + DMC firmware
   - Full PPGTT for Ivybridge, Haswell and Valleyview
   - DDB distribution based on resolution
   - Limited range DP display support

  nouveau:
   - CEC over DP AUX support
   - Initial HDMI 2.0 support

  virtio-gpu:
   - vmap support for PRIME objects

  tegra:
   - Initial Tegra194 support
   - DMA/IOMMU integration fixes

  msm:
   - a6xx perf improvements + clock prefix
   - GPU preemption optimisations
   - a6xx devfreq support
   - cursor support

  rockchip:
   - PX30 support
   - rgb output interface support

  mediatek:
   - HDMI output support on mt2701 and mt7623

  rcar-du:
   - Interlaced modes on Gen3
   - LVDS on R8A77980
   - D3 and E3 SoC support

  hisilicon:
   - misc fixes

  mxsfb:
   - runtime pm support

  sun4i:
   - R40 TCON support
   - Allwinner A64 support
   - R40 HDMI support

  omapdrm:
   - Driver rework changing display pipeline ordering to use common code
   - DMM memory barrier and irq fixes
   - Errata workarounds

  exynos:
   - out-bridge support for LVDS bridge driver
   - Samsung 16x16 tiled format support
   - Plane alpha and pixel blend mode support

  tilcdc:
   - suspend/resume update

  mali-dp:
   - misc updates"

* tag 'drm-next-2018-10-24' of git://anongit.freedesktop.org/drm/drm: (1382 commits)
  firmware/dmc/icl: Add missing MODULE_FIRMWARE() for Icelake.
  drm/i915/icl: Fix signal_levels
  drm/i915/icl: Fix DDI/TC port clk_off bits
  drm/i915/icl: create function to identify combophy port
  drm/i915/gen9+: Fix initial readout for Y tiled framebuffers
  drm/i915: Large page offsets for pread/pwrite
  drm/i915/selftests: Disable shrinker across mmap-exhaustion
  drm/i915/dp: Link train Fallback on eDP only if fallback link BW can fit panel's native mode
  drm/i915: Fix intel_dp_mst_best_encoder()
  drm/i915: Skip vcpi allocation for MSTB ports that are gone
  drm/i915: Don't unset intel_connector->mst_port
  drm/i915: Only reset seqno if actually idle
  drm/i915: Use the correct crtc when sanitizing plane mapping
  drm/i915: Restore vblank interrupts earlier
  drm/i915: Check fb stride against plane max stride
  drm/amdgpu/vcn:Fix uninitialized symbol error
  drm: panel-orientation-quirks: Add quirk for Acer One 10 (S1003)
  drm/amd/amdgpu: Fix debugfs error handling
  drm/amdgpu: Update gc_9_0 golden settings.
  drm/amd/powerplay: update PPtable with DC BTC and Tvr SocLimit fields
  ...

1 files changed, 75 insertions, 13 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index ee4996029a86..56412b0e7e1c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -346,15 +346,15 @@ static int kfd_parse_subtype_iolink(struct crat_subtype_iolink *iolink,
 					struct list_head *device_list)
 {
 	struct kfd_iolink_properties *props = NULL, *props2;
-	struct kfd_topology_device *dev, *cpu_dev;
+	struct kfd_topology_device *dev, *to_dev;
 	uint32_t id_from;
 	uint32_t id_to;
 
 	id_from = iolink->proximity_domain_from;
 	id_to = iolink->proximity_domain_to;
 
-	pr_debug("Found IO link entry in CRAT table with id_from=%d\n",
-			id_from);
+	pr_debug("Found IO link entry in CRAT table with id_from=%d, id_to %d\n",
+			id_from, id_to);
 	list_for_each_entry(dev, device_list, list) {
 		if (id_from == dev->proximity_domain) {
 			props = kfd_alloc_struct(props);
@@ -369,6 +369,8 @@ static int kfd_parse_subtype_iolink(struct crat_subtype_iolink *iolink,
 
 			if (props->iolink_type == CRAT_IOLINK_TYPE_PCIEXPRESS)
 				props->weight = 20;
+			else if (props->iolink_type == CRAT_IOLINK_TYPE_XGMI)
+				props->weight = 15;
 			else
 				props->weight = node_distance(id_from, id_to);
 
@@ -389,20 +391,23 @@ static int kfd_parse_subtype_iolink(struct crat_subtype_iolink *iolink,
 	/* CPU topology is created before GPUs are detected, so CPU->GPU
 	 * links are not built at that time. If a PCIe type is discovered, it
 	 * means a GPU is detected and we are adding GPU->CPU to the topology.
-	 * At this time, also add the corresponded CPU->GPU link.
+	 * At this time, also add the corresponded CPU->GPU link if GPU
+	 * is large bar.
+	 * For xGMI, we only added the link with one direction in the crat
+	 * table, add corresponded reversed direction link now.
 	 */
-	if (props && props->iolink_type == CRAT_IOLINK_TYPE_PCIEXPRESS) {
-		cpu_dev = kfd_topology_device_by_proximity_domain(id_to);
-		if (!cpu_dev)
+	if (props && (iolink->flags & CRAT_IOLINK_FLAGS_BI_DIRECTIONAL)) {
+		to_dev = kfd_topology_device_by_proximity_domain(id_to);
+		if (!to_dev)
 			return -ENODEV;
 		/* same everything but the other direction */
 		props2 = kmemdup(props, sizeof(*props2), GFP_KERNEL);
 		props2->node_from = id_to;
 		props2->node_to = id_from;
 		props2->kobj = NULL;
-		cpu_dev->io_link_count++;
-		cpu_dev->node_props.io_links_count++;
-		list_add_tail(&props2->list, &cpu_dev->io_link_props);
+		to_dev->io_link_count++;
+		to_dev->node_props.io_links_count++;
+		list_add_tail(&props2->list, &to_dev->io_link_props);
 	}
 
 	return 0;
@@ -642,6 +647,7 @@ static int kfd_fill_gpu_cache_info(struct kfd_dev *kdev,
 		num_of_cache_types = ARRAY_SIZE(polaris11_cache_info);
 		break;
 	case CHIP_VEGA10:
+	case CHIP_VEGA20:
 		pcache_info = vega10_cache_info;
 		num_of_cache_types = ARRAY_SIZE(vega10_cache_info);
 		break;
@@ -1037,7 +1043,7 @@ static int kfd_fill_gpu_memory_affinity(int *avail_size,
  *
  *	Return 0 if successful else return -ve value
  */
-static int kfd_fill_gpu_direct_io_link(int *avail_size,
+static int kfd_fill_gpu_direct_io_link_to_cpu(int *avail_size,
 			struct kfd_dev *kdev,
 			struct crat_subtype_iolink *sub_type_hdr,
 			uint32_t proximity_domain)
@@ -1052,6 +1058,8 @@ static int kfd_fill_gpu_direct_io_link(int *avail_size,
 	sub_type_hdr->type = CRAT_SUBTYPE_IOLINK_AFFINITY;
 	sub_type_hdr->length = sizeof(struct crat_subtype_iolink);
 	sub_type_hdr->flags |= CRAT_SUBTYPE_FLAGS_ENABLED;
+	if (kfd_dev_is_large_bar(kdev))
+		sub_type_hdr->flags |= CRAT_IOLINK_FLAGS_BI_DIRECTIONAL;
 
 	/* Fill in IOLINK subtype.
 	 * TODO: Fill-in other fields of iolink subtype
@@ -1069,6 +1077,29 @@ static int kfd_fill_gpu_direct_io_link(int *avail_size,
 	return 0;
 }
 
+static int kfd_fill_gpu_xgmi_link_to_gpu(int *avail_size,
+			struct kfd_dev *kdev,
+			struct crat_subtype_iolink *sub_type_hdr,
+			uint32_t proximity_domain_from,
+			uint32_t proximity_domain_to)
+{
+	*avail_size -= sizeof(struct crat_subtype_iolink);
+	if (*avail_size < 0)
+		return -ENOMEM;
+
+	memset((void *)sub_type_hdr, 0, sizeof(struct crat_subtype_iolink));
+
+	sub_type_hdr->type = CRAT_SUBTYPE_IOLINK_AFFINITY;
+	sub_type_hdr->length = sizeof(struct crat_subtype_iolink);
+	sub_type_hdr->flags |= CRAT_SUBTYPE_FLAGS_ENABLED |
+			       CRAT_IOLINK_FLAGS_BI_DIRECTIONAL;
+
+	sub_type_hdr->io_interface_type = CRAT_IOLINK_TYPE_XGMI;
+	sub_type_hdr->proximity_domain_from = proximity_domain_from;
+	sub_type_hdr->proximity_domain_to = proximity_domain_to;
+	return 0;
+}
+
 /* kfd_create_vcrat_image_gpu - Create Virtual CRAT for CPU
  *
  *	@pcrat_image: Fill in VCRAT for GPU
@@ -1081,14 +1112,16 @@ static int kfd_create_vcrat_image_gpu(void *pcrat_image,
 {
 	struct crat_header *crat_table = (struct crat_header *)pcrat_image;
 	struct crat_subtype_generic *sub_type_hdr;
+	struct kfd_local_mem_info local_mem_info;
+	struct kfd_topology_device *peer_dev;
 	struct crat_subtype_computeunit *cu;
 	struct kfd_cu_info cu_info;
 	int avail_size = *size;
 	uint32_t total_num_of_cu;
 	int num_of_cache_entries = 0;
 	int cache_mem_filled = 0;
+	uint32_t nid = 0;
 	int ret = 0;
-	struct kfd_local_mem_info local_mem_info;
 
 	if (!pcrat_image || avail_size < VCRAT_SIZE_FOR_GPU)
 		return -EINVAL;
@@ -1212,7 +1245,7 @@ static int kfd_create_vcrat_image_gpu(void *pcrat_image,
 	 */
 	sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
 		cache_mem_filled);
-	ret = kfd_fill_gpu_direct_io_link(&avail_size, kdev,
+	ret = kfd_fill_gpu_direct_io_link_to_cpu(&avail_size, kdev,
 		(struct crat_subtype_iolink *)sub_type_hdr, proximity_domain);
 
 	if (ret < 0)
@@ -1221,6 +1254,35 @@ static int kfd_create_vcrat_image_gpu(void *pcrat_image,
 	crat_table->length += sub_type_hdr->length;
 	crat_table->total_entries++;
 
+
+	/* Fill in Subtype: IO_LINKS
+	 * Direct links from GPU to other GPUs through xGMI.
+	 * We will loop GPUs that already be processed (with lower value
+	 * of proximity_domain), add the link for the GPUs with same
+	 * hive id (from this GPU to other GPU) . The reversed iolink
+	 * (from other GPU to this GPU) will be added
+	 * in kfd_parse_subtype_iolink.
+	 */
+	if (kdev->hive_id) {
+		for (nid = 0; nid < proximity_domain; ++nid) {
+			peer_dev = kfd_topology_device_by_proximity_domain(nid);
+			if (!peer_dev->gpu)
+				continue;
+			if (peer_dev->gpu->hive_id != kdev->hive_id)
+				continue;
+			sub_type_hdr = (typeof(sub_type_hdr))(
+				(char *)sub_type_hdr +
+				sizeof(struct crat_subtype_iolink));
+			ret = kfd_fill_gpu_xgmi_link_to_gpu(
+				&avail_size, kdev,
+				(struct crat_subtype_iolink *)sub_type_hdr,
+				proximity_domain, nid);
+			if (ret < 0)
+				return ret;
+			crat_table->length += sub_type_hdr->length;
+			crat_table->total_entries++;
+		}
+	}
 	*size = crat_table->length;
 	pr_info("Virtual CRAT table created for GPU\n");