Merge tag 'drm-next-2020-06-02' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Highlights:

   - Core DRM had a lot of refactoring around managed drm resources to
     make drivers simpler.

   - Intel Tigerlake support is on by default

   - amdgpu now support p2p PCI buffer sharing and encrypted GPU memory

  Details:

  core:
   - uapi: error out EBUSY when existing master
   - uapi: rework SET/DROP MASTER permission handling
   - remove drm_pci.h
   - drm_pci* are now legacy
   - introduced managed DRM resources
   - subclassing support for drm_framebuffer
   - simple encoder helper
   - edid improvements
   - vblank + writeback documentation improved
   - drm/mm - optimise tree searches
   - port drivers to use devm_drm_dev_alloc

  dma-buf:
   - add flag for p2p buffer support

  mst:
   - ACT timeout improvements
   - remove drm_dp_mst_has_audio
   - don't use 2nd TX slot - spec recommends against it

  bridge:
   - dw-hdmi various improvements
   - chrontel ch7033 support
   - fix stack issues with old gcc

  hdmi:
   - add unpack function for drm infoframe

  fbdev:
   - misc fbdev driver fixes

  i915:
   - uapi: global sseu pinning
   - uapi: OA buffer polling
   - uapi: remove generated perf code
   - uapi: per-engine default property values in sysfs
   - Tigerlake GEN12 enabled.
   - Lots of gem refactoring
   - Tigerlake enablement patches
   - move to drm_device logging
   - Icelake gamma HW readout
   - push MST link retrain to hotplug work
   - bandwidth atomic helpers
   - ICL fixes
   - RPS/GT refactoring
   - Cherryview full-ppgtt support
   - i915 locking guidelines documented
   - require linear fb stride to be 512 multiple on gen9
   - Tigerlake SAGV support

  amdgpu:
   - uapi: encrypted GPU memory handling
   - uapi: add MEM_SYNC IB flag
   - p2p dma-buf support
   - export VRAM dma-bufs
   - FRU chip access support
   - RAS/SR-IOV updates
   - Powerplay locking fixes
   - VCN DPG (powergating) enablement
   - GFX10 clockgating fixes
   - DC fixes
   - GPU reset fixes
   - navi SDMA fix
   - expose FP16 for modesetting
   - DP 1.4 compliance fixes
   - gfx10 soft recovery
   - Improved Critical Thermal Faults handling
   - resizable BAR on gmc10

  amdkfd:
   - uapi: GWS resource management
   - track GPU memory per process
   - report PCI domain in topology

  radeon:
   - safe reg list generator fixes

  nouveau:
   - HD audio fixes on recent systems
   - vGPU detection (fail probe if we're on one, for now)
   - Interlaced mode fixes (mostly avoidance on Turing, which doesn't support it)
   - SVM improvements/fixes
   - NVIDIA format modifier support
   - Misc other fixes.

  adv7511:
   - HDMI SPDIF support

  ast:
   - allocate crtc state size
   - fix double assignment
   - fix suspend

  bochs:
   - drop connector register

  cirrus:
   - move to tiny drivers.

  exynos:
   - fix imported dma-buf mapping
   - enable runtime PM
   - fixes and cleanups

  mediatek:
   - DPI pin mode swap
   - config mipi_tx current/impedance

  lima:
   - devfreq + cooling device support
   - task handling improvements
   - runtime PM support

  pl111:
   - vexpress init improvements
   - fix module auto-load

  rcar-du:
   - DT bindings conversion to YAML
   - Planes zpos sanity check and fix
   - MAINTAINERS entry for LVDS panel driver

  mcde:
   - fix return value

  mgag200:
   - use managed config init

  stm:
   - read endpoints from DT

  vboxvideo:
   - use PCI managed functions
   - drop WC mtrr

  vkms:
   - enable cursor by default

  rockchip:
   - afbc support

  virtio:
   - various cleanups

  qxl:
   - fix cursor notify port

  hisilicon:
   - 128-byte stride alignment fix

  sun4i:
   - improved format handling"

* tag 'drm-next-2020-06-02' of git://anongit.freedesktop.org/drm/drm: (1401 commits)
  drm/amd/display: Fix potential integer wraparound resulting in a hang
  drm/amd/display: drop cursor position check in atomic test
  drm/amdgpu: fix device attribute node create failed with multi gpu
  drm/nouveau: use correct conflicting framebuffer API
  drm/vblank: Fix -Wformat compile warnings on some arches
  drm/amdgpu: Sync with VM root BO when switching VM to CPU update mode
  drm/amd/display: Handle GPU reset for DC block
  drm/amdgpu: add apu flags (v2)
  drm/amd/powerpay: Disable gfxoff when setting manual mode on picasso and raven
  drm/amdgpu: fix pm sysfs node handling (v2)
  drm/amdgpu: move gpu_info parsing after common early init
  drm/amdgpu: move discovery gfx config fetching
  drm/nouveau/dispnv50: fix runtime pm imbalance on error
  drm/nouveau: fix runtime pm imbalance on error
  drm/nouveau: fix runtime pm imbalance on error
  drm/nouveau/debugfs: fix runtime pm imbalance on error
  drm/nouveau/nouveau/hmm: fix migrate zero page to GPU
  drm/nouveau/nouveau/hmm: fix nouveau_dmem_chunk allocations
  drm/nouveau/kms/nv50-: Share DP SST mode_valid() handling with MST
  drm/nouveau/kms/nv50-: Move 8BPC limit for MST into nv50_mstc_get_modes()
  ...

4 files changed, 183 insertions, 17 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index d28b4ce744d5..4e873dcbe68f 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -133,6 +133,11 @@ extern "C" {
  * releasing the memory
  */
 #define AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE	(1 << 9)
+/* Flag that BO will be encrypted and that the TMZ bit should be
+ * set in the PTEs when mapping this buffer via GPUVM or
+ * accessing it with various hw blocks
+ */
+#define AMDGPU_GEM_CREATE_ENCRYPTED		(1 << 10)
 
 struct drm_amdgpu_gem_create_in  {
 	/** the requested memory size */
@@ -559,7 +564,7 @@ struct drm_amdgpu_cs_in {
 	/**  Handle of resource list associated with CS */
 	__u32		bo_list_handle;
 	__u32		num_chunks;
-	__u32		_pad;
+	__u32		flags;
 	/** this points to __u64 * which point to cs chunks */
 	__u64		chunks;
 };
@@ -593,6 +598,14 @@ union drm_amdgpu_cs {
  */
 #define AMDGPU_IB_FLAG_RESET_GDS_MAX_WAVE_ID (1 << 4)
 
+/* Flag the IB as secure (TMZ)
+ */
+#define AMDGPU_IB_FLAGS_SECURE  (1 << 5)
+
+/* Tell KMD to flush and invalidate caches
+ */
+#define AMDGPU_IB_FLAG_EMIT_MEM_SYNC  (1 << 6)
+
 struct drm_amdgpu_cs_chunk_ib {
 	__u32 _pad;
 	/** AMDGPU_IB_FLAG_* */
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index 8bc0b31597d8..490143500a50 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -354,9 +354,12 @@ extern "C" {
  * a platform-dependent stride. On top of that the memory can apply
  * platform-depending swizzling of some higher address bits into bit6.
  *
- * This format is highly platforms specific and not useful for cross-driver
- * sharing. It exists since on a given platform it does uniquely identify the
- * layout in a simple way for i915-specific userspace.
+ * Note that this layout is only accurate on intel gen 8+ or valleyview chipsets.
+ * On earlier platforms the is highly platforms specific and not useful for
+ * cross-driver sharing. It exists since on a given platform it does uniquely
+ * identify the layout in a simple way for i915-specific userspace, which
+ * facilitated conversion of userspace to modifiers. Additionally the exact
+ * format on some really old platforms is not known.
  */
 #define I915_FORMAT_MOD_X_TILED	fourcc_mod_code(INTEL, 1)
 
@@ -369,9 +372,12 @@ extern "C" {
  * memory can apply platform-depending swizzling of some higher address bits
  * into bit6.
  *
- * This format is highly platforms specific and not useful for cross-driver
- * sharing. It exists since on a given platform it does uniquely identify the
- * layout in a simple way for i915-specific userspace.
+ * Note that this layout is only accurate on intel gen 8+ or valleyview chipsets.
+ * On earlier platforms the is highly platforms specific and not useful for
+ * cross-driver sharing. It exists since on a given platform it does uniquely
+ * identify the layout in a simple way for i915-specific userspace, which
+ * facilitated conversion of userspace to modifiers. Additionally the exact
+ * format on some really old platforms is not known.
  */
 #define I915_FORMAT_MOD_Y_TILED	fourcc_mod_code(INTEL, 2)
 
@@ -521,7 +527,113 @@ extern "C" {
 #define DRM_FORMAT_MOD_NVIDIA_TEGRA_TILED fourcc_mod_code(NVIDIA, 1)
 
 /*
- * 16Bx2 Block Linear layout, used by desktop GPUs, and Tegra K1 and later
+ * Generalized Block Linear layout, used by desktop GPUs starting with NV50/G80,
+ * and Tegra GPUs starting with Tegra K1.
+ *
+ * Pixels are arranged in Groups of Bytes (GOBs).  GOB size and layout varies
+ * based on the architecture generation.  GOBs themselves are then arranged in
+ * 3D blocks, with the block dimensions (in terms of GOBs) always being a power
+ * of two, and hence expressible as their log2 equivalent (E.g., "2" represents
+ * a block depth or height of "4").
+ *
+ * Chapter 20 "Pixel Memory Formats" of the Tegra X1 TRM describes this format
+ * in full detail.
+ *
+ *       Macro
+ * Bits  Param Description
+ * ----  ----- -----------------------------------------------------------------
+ *
+ *  3:0  h     log2(height) of each block, in GOBs.  Placed here for
+ *             compatibility with the existing
+ *             DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK()-based modifiers.
+ *
+ *  4:4  -     Must be 1, to indicate block-linear layout.  Necessary for
+ *             compatibility with the existing
+ *             DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK()-based modifiers.
+ *
+ *  8:5  -     Reserved (To support 3D-surfaces with variable log2(depth) block
+ *             size).  Must be zero.
+ *
+ *             Note there is no log2(width) parameter.  Some portions of the
+ *             hardware support a block width of two gobs, but it is impractical
+ *             to use due to lack of support elsewhere, and has no known
+ *             benefits.
+ *
+ * 11:9  -     Reserved (To support 2D-array textures with variable array stride
+ *             in blocks, specified via log2(tile width in blocks)).  Must be
+ *             zero.
+ *
+ * 19:12 k     Page Kind.  This value directly maps to a field in the page
+ *             tables of all GPUs >= NV50.  It affects the exact layout of bits
+ *             in memory and can be derived from the tuple
+ *
+ *               (format, GPU model, compression type, samples per pixel)
+ *
+ *             Where compression type is defined below.  If GPU model were
+ *             implied by the format modifier, format, or memory buffer, page
+ *             kind would not need to be included in the modifier itself, but
+ *             since the modifier should define the layout of the associated
+ *             memory buffer independent from any device or other context, it
+ *             must be included here.
+ *
+ * 21:20 g     GOB Height and Page Kind Generation.  The height of a GOB changed
+ *             starting with Fermi GPUs.  Additionally, the mapping between page
+ *             kind and bit layout has changed at various points.
+ *
+ *               0 = Gob Height 8, Fermi - Volta, Tegra K1+ Page Kind mapping
+ *               1 = Gob Height 4, G80 - GT2XX Page Kind mapping
+ *               2 = Gob Height 8, Turing+ Page Kind mapping
+ *               3 = Reserved for future use.
+ *
+ * 22:22 s     Sector layout.  On Tegra GPUs prior to Xavier, there is a further
+ *             bit remapping step that occurs at an even lower level than the
+ *             page kind and block linear swizzles.  This causes the layout of
+ *             surfaces mapped in those SOC's GPUs to be incompatible with the
+ *             equivalent mapping on other GPUs in the same system.
+ *
+ *               0 = Tegra K1 - Tegra Parker/TX2 Layout.
+ *               1 = Desktop GPU and Tegra Xavier+ Layout
+ *
+ * 25:23 c     Lossless Framebuffer Compression type.
+ *
+ *               0 = none
+ *               1 = ROP/3D, layout 1, exact compression format implied by Page
+ *                   Kind field
+ *               2 = ROP/3D, layout 2, exact compression format implied by Page
+ *                   Kind field
+ *               3 = CDE horizontal
+ *               4 = CDE vertical
+ *               5 = Reserved for future use
+ *               6 = Reserved for future use
+ *               7 = Reserved for future use
+ *
+ * 55:25 -     Reserved for future use.  Must be zero.
+ */
+#define DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(c, s, g, k, h) \
+	fourcc_mod_code(NVIDIA, (0x10 | \
+				 ((h) & 0xf) | \
+				 (((k) & 0xff) << 12) | \
+				 (((g) & 0x3) << 20) | \
+				 (((s) & 0x1) << 22) | \
+				 (((c) & 0x7) << 23)))
+
+/* To grandfather in prior block linear format modifiers to the above layout,
+ * the page kind "0", which corresponds to "pitch/linear" and hence is unusable
+ * with block-linear layouts, is remapped within drivers to the value 0xfe,
+ * which corresponds to the "generic" kind used for simple single-sample
+ * uncompressed color formats on Fermi - Volta GPUs.
+ */
+static inline __u64
+drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
+{
+	if (!(modifier & 0x10) || (modifier & (0xff << 12)))
+		return modifier;
+	else
+		return modifier | (0xfe << 12);
+}
+
+/*
+ * 16Bx2 Block Linear layout, used by Tegra K1 and later
  *
  * Pixels are arranged in 64x8 Groups Of Bytes (GOBs). GOBs are then stacked
  * vertically by a power of 2 (1 to 32 GOBs) to form a block.
@@ -542,20 +654,20 @@ extern "C" {
  * in full detail.
  */
 #define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(v) \
-	fourcc_mod_code(NVIDIA, 0x10 | ((v) & 0xf))
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 0, 0, 0, (v))
 
 #define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_ONE_GOB \
-	fourcc_mod_code(NVIDIA, 0x10)
+	DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(0)
 #define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_TWO_GOB \
-	fourcc_mod_code(NVIDIA, 0x11)
+	DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(1)
 #define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_FOUR_GOB \
-	fourcc_mod_code(NVIDIA, 0x12)
+	DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(2)
 #define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_EIGHT_GOB \
-	fourcc_mod_code(NVIDIA, 0x13)
+	DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(3)
 #define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_SIXTEEN_GOB \
-	fourcc_mod_code(NVIDIA, 0x14)
+	DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(4)
 #define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_THIRTYTWO_GOB \
-	fourcc_mod_code(NVIDIA, 0x15)
+	DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(5)
 
 /*
  * Some Broadcom modifiers take parameters, for example the number of
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 2813e579b480..14b67cd6b54b 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1969,6 +1969,30 @@ enum drm_i915_perf_property_id {
 	 */
 	DRM_I915_PERF_PROP_HOLD_PREEMPTION,
 
+	/**
+	 * Specifying this pins all contexts to the specified SSEU power
+	 * configuration for the duration of the recording.
+	 *
+	 * This parameter's value is a pointer to a struct
+	 * drm_i915_gem_context_param_sseu.
+	 *
+	 * This property is available in perf revision 4.
+	 */
+	DRM_I915_PERF_PROP_GLOBAL_SSEU,
+
+	/**
+	 * This optional parameter specifies the timer interval in nanoseconds
+	 * at which the i915 driver will check the OA buffer for available data.
+	 * Minimum allowed value is 100 microseconds. A default value is used by
+	 * the driver if this parameter is not specified. Note that larger timer
+	 * values will reduce cpu consumption during OA perf captures. However,
+	 * excessively large values would potentially result in OA buffer
+	 * overwrites as captures reach end of the OA buffer.
+	 *
+	 * This property is available in perf revision 5.
+	 */
+	DRM_I915_PERF_PROP_POLL_OA_PERIOD,
+
 	DRM_I915_PERF_PROP_MAX /* non-ABI */
 };
 
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 20917c59f39c..b6be62356d34 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -251,7 +251,7 @@ struct kfd_memory_exception_failure {
 	__u32 imprecise;	/* Can't determine the	exact fault address */
 };
 
-/* memory exception data*/
+/* memory exception data */
 struct kfd_hsa_memory_exception_data {
 	struct kfd_memory_exception_failure failure;
 	__u64 va;
@@ -410,6 +410,20 @@ struct kfd_ioctl_unmap_memory_from_gpu_args {
 	__u32 n_success;		/* to/from KFD */
 };
 
+/* Allocate GWS for specific queue
+ *
+ * @queue_id:    queue's id that GWS is allocated for
+ * @num_gws:     how many GWS to allocate
+ * @first_gws:   index of the first GWS allocated.
+ *               only support contiguous GWS allocation
+ */
+struct kfd_ioctl_alloc_queue_gws_args {
+	__u32 queue_id;		/* to KFD */
+	__u32 num_gws;		/* to KFD */
+	__u32 first_gws;	/* from KFD */
+	__u32 pad;
+};
+
 struct kfd_ioctl_get_dmabuf_info_args {
 	__u64 size;		/* from KFD */
 	__u64 metadata_ptr;	/* to KFD */
@@ -529,7 +543,10 @@ enum kfd_mmio_remap {
 #define AMDKFD_IOC_IMPORT_DMABUF		\
 		AMDKFD_IOWR(0x1D, struct kfd_ioctl_import_dmabuf_args)
 
+#define AMDKFD_IOC_ALLOC_QUEUE_GWS		\
+		AMDKFD_IOWR(0x1E, struct kfd_ioctl_alloc_queue_gws_args)
+
 #define AMDKFD_COMMAND_START		0x01
-#define AMDKFD_COMMAND_END		0x1E
+#define AMDKFD_COMMAND_END		0x1F
 
 #endif