Merge tag 'drm-next-2020-08-06' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "New xilinx displayport driver, AMD support for two new GPUs (more
  header files), i915 initial support for RocketLake and some work on
  their DG1 (discrete chip).

  The core also grew some lockdep annotations to try and constrain what
  drivers do with dma-fences, and added some documentation on why the
  idea of indefinite fences doesn't work.

  The long list is below.

  I do have some fixes trees outstanding, but I'll follow up with those
  later.

  core:
   - add user def flag to cmd line modes
   - dma_fence_wait added might_sleep
   - dma-fence lockdep annotations
   - indefinite fences are bad documentation
   - gem CMA functions used in more drivers
   - struct mutex removal
   - more drm_ debug macro usage
   - set/drop master api fixes
   - fix for drm/mm hole size comparison
   - drm/mm remove invalid entry optimization
   - optimise drm/mm hole handling
   - VRR debugfs added
   - uncompressed AFBC modifier support
   - multiple display id blocks in EDID
   - multiple driver sg handling fixes
   - __drm_atomic_helper_crtc_reset in all drivers
   - managed vram helpers

  ttm:
   - ttm_mem_reg handling cleanup
   - remove bo offset field
   - drop CMA memtype flag
   - drop mappable flag

  xilinx:
   - New Xilinx ZynqMP DisplayPort Subsystem driver

  nouveau:
   - add CRC support
   - start using NVIDIA published class header files
   - convert all push buffer emission to new macros
   - Proper push buffer space management for EVO/NVD channels.
   - firmware loading fixes
   - 2MiB system memory pages support on Pascal and newer

  vkms:
   - larger cursor support

  i915:
   - Rocketlake platform enablement
   - Early DG1 enablement
   - Numerous GEM refactorings
   - DP MST fixes
   - FBC, PSR, Cursor, Color, Gamma fixes
   - TGL, RKL, EHL workaround updates
   - TGL 8K display support fixes
   - SDVO/HDMI/DVI fixes

  amdgpu:
   - Initial support for Sienna Cichlid GPU
   - Initial support for Navy Flounder GPU
   - SI UVD/VCE support
   - expose rotation property
   - Add support for unique id on Arcturus
   - Enable runtime PM on vega10 boards that support BACO
   - Skip BAR resizing if the bios already did id
   - Major swSMU code cleanup
   - Fixes for DCN bandwidth calculations

  amdkfd:
   - Track SDMA usage per process
   - SMI events interface

  radeon:
   - Default to on chip GART for AGP boards on all arches
   - Runtime PM reference count fixes

  msm:
   - headers regenerated causing churn
   - a650/a640 display and GPU enablement
   - dpu dither support for 6bpc panels
   - dpu cursor fix
   - dsi/mdp5 enablement for sdm630/sdm636/sdm66

  tegra:
   - video capture prep support
   - reflection support

  mediatek:
   - convert mtk_dsi to bridge API

  meson:
   - FBC support

  sun4i:
   - iommu support

  rockchip:
   - register locking fix
   - per-pixel alpha support PX30 VOP

  mgag200:
   - ported to simple and shmem helpers
   - device init cleanups
   - use managed pci functions
   - dropped hw cursor support

  ast:
   - use managed pci functions
   - use managed VRAM helpers
   - rework cursor support

  malidp:
   - dev_groups support

  hibmc:
   - refactor hibmc_drv_vdac:

  vc4:
   - create TXP CRTC

  imx:
   - error path fixes and cleanups

  etnaviv:
   - clock handling and error handling cleanups
   - use pin_user_pages"

* tag 'drm-next-2020-08-06' of git://anongit.freedesktop.org/drm/drm: (1747 commits)
  drm/msm: use kthread_create_worker instead of kthread_run
  drm/msm/mdp5: Add MDP5 configuration for SDM636/660
  drm/msm/dsi: Add DSI configuration for SDM660
  drm/msm/mdp5: Add MDP5 configuration for SDM630
  drm/msm/dsi: Add phy configuration for SDM630/636/660
  drm/msm/a6xx: add A640/A650 hwcg
  drm/msm/a6xx: hwcg tables in gpulist
  drm/msm/dpu: add SM8250 to hw catalog
  drm/msm/dpu: add SM8150 to hw catalog
  drm/msm/dpu: intf timing path for displayport
  drm/msm/dpu: set missing flush bits for INTF_2 and INTF_3
  drm/msm/dpu: don't use INTF_INPUT_CTRL feature on sdm845
  drm/msm/dpu: move some sspp caps to dpu_caps
  drm/msm/dpu: update UBWC config for sm8150 and sm8250
  drm/msm/dpu: use right setup_blend_config for sm8150 and sm8250
  drm/msm/a6xx: set ubwc config for A640 and A650
  drm/msm/adreno: un-open-code some packets
  drm/msm: sync generated headers
  drm/msm/a6xx: add build_bw_table for A640/A650
  drm/msm/a6xx: fix crashstate capture for A650
  ...

6 files changed, 170 insertions, 12 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 4e873dcbe68f..3218576e109d 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -502,15 +502,15 @@ struct drm_amdgpu_gem_op {
 #define AMDGPU_VM_MTYPE_MASK		(0xf << 5)
 /* Default MTYPE. Pre-AI must use this.  Recommended for newer ASICs. */
 #define AMDGPU_VM_MTYPE_DEFAULT		(0 << 5)
-/* Use NC MTYPE instead of default MTYPE */
+/* Use Non Coherent MTYPE instead of default MTYPE */
 #define AMDGPU_VM_MTYPE_NC		(1 << 5)
-/* Use WC MTYPE instead of default MTYPE */
+/* Use Write Combine MTYPE instead of default MTYPE */
 #define AMDGPU_VM_MTYPE_WC		(2 << 5)
-/* Use CC MTYPE instead of default MTYPE */
+/* Use Cache Coherent MTYPE instead of default MTYPE */
 #define AMDGPU_VM_MTYPE_CC		(3 << 5)
-/* Use UC MTYPE instead of default MTYPE */
+/* Use UnCached MTYPE instead of default MTYPE */
 #define AMDGPU_VM_MTYPE_UC		(4 << 5)
-/* Use RW MTYPE instead of default MTYPE */
+/* Use Read Write MTYPE instead of default MTYPE */
 #define AMDGPU_VM_MTYPE_RW		(5 << 5)
 
 struct drm_amdgpu_gem_va {
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index 490143500a50..4bee7de5f306 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -236,6 +236,12 @@ extern "C" {
 #define DRM_FORMAT_NV61		fourcc_code('N', 'V', '6', '1') /* 2x1 subsampled Cb:Cr plane */
 #define DRM_FORMAT_NV24		fourcc_code('N', 'V', '2', '4') /* non-subsampled Cr:Cb plane */
 #define DRM_FORMAT_NV42		fourcc_code('N', 'V', '4', '2') /* non-subsampled Cb:Cr plane */
+/*
+ * 2 plane YCbCr
+ * index 0 = Y plane, [39:0] Y3:Y2:Y1:Y0 little endian
+ * index 1 = Cr:Cb plane, [39:0] Cr1:Cb1:Cr0:Cb0 little endian
+ */
+#define DRM_FORMAT_NV15		fourcc_code('N', 'V', '1', '5') /* 2x2 subsampled Cr:Cb plane */
 
 /*
  * 2 plane YCbCr MSB aligned
@@ -265,6 +271,22 @@ extern "C" {
  */
 #define DRM_FORMAT_P016		fourcc_code('P', '0', '1', '6') /* 2x2 subsampled Cr:Cb plane 16 bits per channel */
 
+/* 3 plane non-subsampled (444) YCbCr
+ * 16 bits per component, but only 10 bits are used and 6 bits are padded
+ * index 0: Y plane, [15:0] Y:x [10:6] little endian
+ * index 1: Cb plane, [15:0] Cb:x [10:6] little endian
+ * index 2: Cr plane, [15:0] Cr:x [10:6] little endian
+ */
+#define DRM_FORMAT_Q410		fourcc_code('Q', '4', '1', '0')
+
+/* 3 plane non-subsampled (444) YCrCb
+ * 16 bits per component, but only 10 bits are used and 6 bits are padded
+ * index 0: Y plane, [15:0] Y:x [10:6] little endian
+ * index 1: Cr plane, [15:0] Cr:x [10:6] little endian
+ * index 2: Cb plane, [15:0] Cb:x [10:6] little endian
+ */
+#define DRM_FORMAT_Q401		fourcc_code('Q', '4', '0', '1')
+
 /*
  * 3 plane YCbCr
  * index 0: Y plane, [7:0] Y
@@ -309,6 +331,7 @@ extern "C" {
 #define DRM_FORMAT_MOD_VENDOR_BROADCOM 0x07
 #define DRM_FORMAT_MOD_VENDOR_ARM     0x08
 #define DRM_FORMAT_MOD_VENDOR_ALLWINNER 0x09
+#define DRM_FORMAT_MOD_VENDOR_AMLOGIC 0x0a
 
 /* add more to the end as needed */
 
@@ -323,8 +346,33 @@ extern "C" {
  * When adding a new token please document the layout with a code comment,
  * similar to the fourcc codes above. drm_fourcc.h is considered the
  * authoritative source for all of these.
+ *
+ * Generic modifier names:
+ *
+ * DRM_FORMAT_MOD_GENERIC_* definitions are used to provide vendor-neutral names
+ * for layouts which are common across multiple vendors. To preserve
+ * compatibility, in cases where a vendor-specific definition already exists and
+ * a generic name for it is desired, the common name is a purely symbolic alias
+ * and must use the same numerical value as the original definition.
+ *
+ * Note that generic names should only be used for modifiers which describe
+ * generic layouts (such as pixel re-ordering), which may have
+ * independently-developed support across multiple vendors.
+ *
+ * In future cases where a generic layout is identified before merging with a
+ * vendor-specific modifier, a new 'GENERIC' vendor or modifier using vendor
+ * 'NONE' could be considered. This should only be for obvious, exceptional
+ * cases to avoid polluting the 'GENERIC' namespace with modifiers which only
+ * apply to a single vendor.
+ *
+ * Generic names should not be used for cases where multiple hardware vendors
+ * have implementations of the same standardised compression scheme (such as
+ * AFBC). In those cases, all implementations should use the same format
+ * modifier(s), reflecting the vendor of the standard.
  */
 
+#define DRM_FORMAT_MOD_GENERIC_16_16_TILE DRM_FORMAT_MOD_SAMSUNG_16_16_TILE
+
 /*
  * Invalid Modifier
  *
@@ -892,6 +940,18 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
  */
 #define AFBC_FORMAT_MOD_BCH     (1ULL << 11)
 
+/* AFBC uncompressed storage mode
+ *
+ * Indicates that the buffer is using AFBC uncompressed storage mode.
+ * In this mode all superblock payloads in the buffer use the uncompressed
+ * storage mode, which is usually only used for data which cannot be compressed.
+ * The buffer layout is the same as for AFBC buffers without USM set, this only
+ * affects the storage mode of the individual superblocks. Note that even a
+ * buffer without USM set may use uncompressed storage mode for some or all
+ * superblocks, USM just guarantees it for all.
+ */
+#define AFBC_FORMAT_MOD_USM	(1ULL << 12)
+
 /*
  * Arm 16x16 Block U-Interleaved modifier
  *
@@ -916,6 +976,86 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
  */
 #define DRM_FORMAT_MOD_ALLWINNER_TILED fourcc_mod_code(ALLWINNER, 1)
 
+/*
+ * Amlogic Video Framebuffer Compression modifiers
+ *
+ * Amlogic uses a proprietary lossless image compression protocol and format
+ * for their hardware video codec accelerators, either video decoders or
+ * video input encoders.
+ *
+ * It considerably reduces memory bandwidth while writing and reading
+ * frames in memory.
+ *
+ * The underlying storage is considered to be 3 components, 8bit or 10-bit
+ * per component YCbCr 420, single plane :
+ * - DRM_FORMAT_YUV420_8BIT
+ * - DRM_FORMAT_YUV420_10BIT
+ *
+ * The first 8 bits of the mode defines the layout, then the following 8 bits
+ * defines the options changing the layout.
+ *
+ * Not all combinations are valid, and different SoCs may support different
+ * combinations of layout and options.
+ */
+#define __fourcc_mod_amlogic_layout_mask 0xf
+#define __fourcc_mod_amlogic_options_shift 8
+#define __fourcc_mod_amlogic_options_mask 0xf
+
+#define DRM_FORMAT_MOD_AMLOGIC_FBC(__layout, __options) \
+	fourcc_mod_code(AMLOGIC, \
+			((__layout) & __fourcc_mod_amlogic_layout_mask) | \
+			((__options) & __fourcc_mod_amlogic_options_mask \
+			 << __fourcc_mod_amlogic_options_shift))
+
+/* Amlogic FBC Layouts */
+
+/*
+ * Amlogic FBC Basic Layout
+ *
+ * The basic layout is composed of:
+ * - a body content organized in 64x32 superblocks with 4096 bytes per
+ *   superblock in default mode.
+ * - a 32 bytes per 128x64 header block
+ *
+ * This layout is transferrable between Amlogic SoCs supporting this modifier.
+ */
+#define AMLOGIC_FBC_LAYOUT_BASIC		(1ULL)
+
+/*
+ * Amlogic FBC Scatter Memory layout
+ *
+ * Indicates the header contains IOMMU references to the compressed
+ * frames content to optimize memory access and layout.
+ *
+ * In this mode, only the header memory address is needed, thus the
+ * content memory organization is tied to the current producer
+ * execution and cannot be saved/dumped neither transferrable between
+ * Amlogic SoCs supporting this modifier.
+ *
+ * Due to the nature of the layout, these buffers are not expected to
+ * be accessible by the user-space clients, but only accessible by the
+ * hardware producers and consumers.
+ *
+ * The user-space clients should expect a failure while trying to mmap
+ * the DMA-BUF handle returned by the producer.
+ */
+#define AMLOGIC_FBC_LAYOUT_SCATTER		(2ULL)
+
+/* Amlogic FBC Layout Options Bit Mask */
+
+/*
+ * Amlogic FBC Memory Saving mode
+ *
+ * Indicates the storage is packed when pixel size is multiple of word
+ * boudaries, i.e. 8bit should be stored in this mode to save allocation
+ * memory.
+ *
+ * This mode reduces body layout to 3072 bytes per 64x32 superblock with
+ * the basic layout and 3200 bytes per 64x32 superblock combined with
+ * the scatter layout.
+ */
+#define AMLOGIC_FBC_OPTION_MEM_SAVING		(1ULL << 0)
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 735c8cfdaaa1..deea447e5f22 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -497,7 +497,7 @@ struct drm_mode_fb_cmd2 {
 	 * In case of planar formats, this ioctl allows up to 4
 	 * buffer objects with offsets and pitches per plane.
 	 * The pitch and offset order is dictated by the fourcc,
-	 * e.g. NV12 (http://fourcc.org/yuv.php#NV12) is described as:
+	 * e.g. NV12 (https://fourcc.org/yuv.php#NV12) is described as:
 	 *
 	 *   YUV 4:2:0 image with a plane of 8 bit Y samples
 	 *   followed by an interleaved U/V plane containing
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 14b67cd6b54b..00546062e023 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -55,7 +55,7 @@ extern "C" {
  *	cause the related events to not be seen.
  *
  * I915_RESET_UEVENT - Event is generated just before an attempt to reset the
- *	the GPU. The value supplied with the event is always 1. NOTE: Disable
+ *	GPU. The value supplied with the event is always 1. NOTE: Disable
  *	reset via module parameter will cause this event to not be seen.
  */
 #define I915_L3_PARITY_UEVENT		"L3_PARITY_ERROR"
@@ -1934,7 +1934,7 @@ enum drm_i915_perf_property_id {
 
 	/**
 	 * The value specifies which set of OA unit metrics should be
-	 * be configured, defining the contents of any OA unit reports.
+	 * configured, defining the contents of any OA unit reports.
 	 *
 	 * This property is available in perf revision 1.
 	 */
diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index 19806eb3a8e8..a6c1f3eb2623 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/msm_drm.h
@@ -252,8 +252,8 @@ struct drm_msm_gem_submit {
 	__u64 cmds;           /* in, ptr to array of submit_cmd's */
 	__s32 fence_fd;       /* in/out fence fd (see MSM_SUBMIT_FENCE_FD_IN/OUT) */
 	__u32 queueid;        /* in, submitqueue id */
-	__u64 in_syncobjs;    /* in, ptr to to array of drm_msm_gem_submit_syncobj */
-	__u64 out_syncobjs;   /* in, ptr to to array of drm_msm_gem_submit_syncobj */
+	__u64 in_syncobjs;    /* in, ptr to array of drm_msm_gem_submit_syncobj */
+	__u64 out_syncobjs;   /* in, ptr to array of drm_msm_gem_submit_syncobj */
 	__u32 nr_in_syncobjs; /* in, number of entries in in_syncobj */
 	__u32 nr_out_syncobjs; /* in, number of entries in out_syncobj. */
 	__u32 syncobj_stride; /* in, stride of syncobj arrays. */
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index b6be62356d34..f738c3b53f4e 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -26,8 +26,12 @@
 #include <drm/drm.h>
 #include <linux/ioctl.h>
 
+/*
+ * - 1.1 - initial version
+ * - 1.3 - Add SMI events support
+ */
 #define KFD_IOCTL_MAJOR_VERSION 1
-#define KFD_IOCTL_MINOR_VERSION 1
+#define KFD_IOCTL_MINOR_VERSION 3
 
 struct kfd_ioctl_get_version_args {
 	__u32 major_version;	/* from KFD */
@@ -442,6 +446,17 @@ struct kfd_ioctl_import_dmabuf_args {
 	__u32 dmabuf_fd;	/* to KFD */
 };
 
+/*
+ * KFD SMI(System Management Interface) events
+ */
+/* Event type (defined by bitmask) */
+#define KFD_SMI_EVENT_VMFAULT     0x0000000000000001
+
+struct kfd_ioctl_smi_events_args {
+	__u32 gpuid;	/* to KFD */
+	__u32 anon_fd;	/* from KFD */
+};
+
 /* Register offset inside the remapped mmio page
  */
 enum kfd_mmio_remap {
@@ -546,7 +561,10 @@ enum kfd_mmio_remap {
 #define AMDKFD_IOC_ALLOC_QUEUE_GWS		\
 		AMDKFD_IOWR(0x1E, struct kfd_ioctl_alloc_queue_gws_args)
 
+#define AMDKFD_IOC_SMI_EVENTS			\
+		AMDKFD_IOWR(0x1F, struct kfd_ioctl_smi_events_args)
+
 #define AMDKFD_COMMAND_START		0x01
-#define AMDKFD_COMMAND_END		0x1F
+#define AMDKFD_COMMAND_END		0x20
 
 #endif