Backmerge remote-tracking branch 'drm/drm-next' into drm-misc-next

Some conflicts with ttm_bo->offset removal, but drm-misc-next needs updating to v5.8.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>

4 files changed, 179 insertions, 10 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 65f69723cbdc..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 */
@@ -346,6 +351,10 @@ struct drm_amdgpu_gem_userptr {
 #define AMDGPU_TILING_DCC_PITCH_MAX_MASK		0x3FFF
 #define AMDGPU_TILING_DCC_INDEPENDENT_64B_SHIFT		43
 #define AMDGPU_TILING_DCC_INDEPENDENT_64B_MASK		0x1
+#define AMDGPU_TILING_DCC_INDEPENDENT_128B_SHIFT	44
+#define AMDGPU_TILING_DCC_INDEPENDENT_128B_MASK		0x1
+#define AMDGPU_TILING_SCANOUT_SHIFT			63
+#define AMDGPU_TILING_SCANOUT_MASK			0x1
 
 /* Set/Get helpers for tiling flags. */
 #define AMDGPU_TILING_SET(field, value) \
@@ -555,7 +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;
 };
@@ -589,6 +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 299f9ac4840b..993c1b342315 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -549,7 +549,113 @@ 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.
@@ -570,20 +676,20 @@ 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/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index 0b85ed6a3710..19806eb3a8e8 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/msm_drm.h
@@ -217,13 +217,28 @@ struct drm_msm_gem_submit_bo {
 #define MSM_SUBMIT_FENCE_FD_IN   0x40000000 /* enable input fence_fd */
 #define MSM_SUBMIT_FENCE_FD_OUT  0x20000000 /* enable output fence_fd */
 #define MSM_SUBMIT_SUDO          0x10000000 /* run submitted cmds from RB */
+#define MSM_SUBMIT_SYNCOBJ_IN    0x08000000 /* enable input syncobj */
+#define MSM_SUBMIT_SYNCOBJ_OUT   0x04000000 /* enable output syncobj */
 #define MSM_SUBMIT_FLAGS                ( \
 		MSM_SUBMIT_NO_IMPLICIT   | \
 		MSM_SUBMIT_FENCE_FD_IN   | \
 		MSM_SUBMIT_FENCE_FD_OUT  | \
 		MSM_SUBMIT_SUDO          | \
+		MSM_SUBMIT_SYNCOBJ_IN    | \
+		MSM_SUBMIT_SYNCOBJ_OUT   | \
 		0)
 
+#define MSM_SUBMIT_SYNCOBJ_RESET 0x00000001 /* Reset syncobj after wait. */
+#define MSM_SUBMIT_SYNCOBJ_FLAGS        ( \
+		MSM_SUBMIT_SYNCOBJ_RESET | \
+		0)
+
+struct drm_msm_gem_submit_syncobj {
+	__u32 handle;     /* in, syncobj handle. */
+	__u32 flags;      /* in, from MSM_SUBMIT_SYNCOBJ_FLAGS */
+	__u64 point;      /* in, timepoint for timeline syncobjs. */
+};
+
 /* Each cmdstream submit consists of a table of buffers involved, and
  * one or more cmdstream buffers.  This allows for conditional execution
  * (context-restore), and IB buffers needed for per tile/bin draw cmds.
@@ -236,7 +251,14 @@ struct drm_msm_gem_submit {
 	__u64 bos;            /* in, ptr to array of submit_bo's */
 	__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 */
+	__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 */
+	__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. */
+	__u32 pad;            /*in, reserved for future use, always 0. */
+
 };
 
 /* The normal way to synchronize with the GPU is just to CPU_PREP on