Import libdrm 2.4.82

4 files changed, 231 insertions, 5 deletions

diff --git a/lib/libdrm/include/drm/amdgpu_drm.h b/lib/libdrm/include/drm/amdgpu_drm.h
index 516a9f285..d9aa4a339 100644
--- a/lib/libdrm/include/drm/amdgpu_drm.h
+++ b/lib/libdrm/include/drm/amdgpu_drm.h
@@ -51,6 +51,7 @@ extern "C" {
 #define DRM_AMDGPU_GEM_OP		0x10
 #define DRM_AMDGPU_GEM_USERPTR		0x11
 #define DRM_AMDGPU_WAIT_FENCES		0x12
+#define DRM_AMDGPU_VM			0x13
 
 #define DRM_IOCTL_AMDGPU_GEM_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_CREATE, union drm_amdgpu_gem_create)
 #define DRM_IOCTL_AMDGPU_GEM_MMAP	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_MMAP, union drm_amdgpu_gem_mmap)
@@ -65,6 +66,7 @@ extern "C" {
 #define DRM_IOCTL_AMDGPU_GEM_OP		DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_OP, struct drm_amdgpu_gem_op)
 #define DRM_IOCTL_AMDGPU_GEM_USERPTR	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_USERPTR, struct drm_amdgpu_gem_userptr)
 #define DRM_IOCTL_AMDGPU_WAIT_FENCES	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_WAIT_FENCES, union drm_amdgpu_wait_fences)
+#define DRM_IOCTL_AMDGPU_VM		DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_VM, union drm_amdgpu_vm)
 
 #define AMDGPU_GEM_DOMAIN_CPU		0x1
 #define AMDGPU_GEM_DOMAIN_GTT		0x2
@@ -190,6 +192,26 @@ union drm_amdgpu_ctx {
 	union drm_amdgpu_ctx_out out;
 };
 
+/* vm ioctl */
+#define AMDGPU_VM_OP_RESERVE_VMID	1
+#define AMDGPU_VM_OP_UNRESERVE_VMID	2
+
+struct drm_amdgpu_vm_in {
+	/** AMDGPU_VM_OP_* */
+	__u32	op;
+	__u32	flags;
+};
+
+struct drm_amdgpu_vm_out {
+	/** For future use, no flags defined so far */
+	__u64	flags;
+};
+
+union drm_amdgpu_vm {
+	struct drm_amdgpu_vm_in in;
+	struct drm_amdgpu_vm_out out;
+};
+
 /*
  * This is not a reliable API and you should expect it to fail for any
  * number of reasons and have fallback path that do not use userptr to
@@ -295,7 +317,10 @@ union drm_amdgpu_gem_wait_idle {
 };
 
 struct drm_amdgpu_wait_cs_in {
-	/** Command submission handle */
+	/* Command submission handle
+         * handle equals 0 means none to wait for
+         * handle equals ~0ull means wait for the latest sequence number
+         */
 	__u64 handle;
 	/** Absolute timeout to wait */
 	__u64 timeout;
@@ -406,13 +431,17 @@ struct drm_amdgpu_gem_va {
 #define AMDGPU_HW_IP_UVD          3
 #define AMDGPU_HW_IP_VCE          4
 #define AMDGPU_HW_IP_UVD_ENC      5
-#define AMDGPU_HW_IP_NUM          6
+#define AMDGPU_HW_IP_VCN_DEC      6
+#define AMDGPU_HW_IP_VCN_ENC      7
+#define AMDGPU_HW_IP_NUM          8
 
 #define AMDGPU_HW_IP_INSTANCE_MAX_COUNT 1
 
 #define AMDGPU_CHUNK_ID_IB		0x01
 #define AMDGPU_CHUNK_ID_FENCE		0x02
 #define AMDGPU_CHUNK_ID_DEPENDENCIES	0x03
+#define AMDGPU_CHUNK_ID_SYNCOBJ_IN      0x04
+#define AMDGPU_CHUNK_ID_SYNCOBJ_OUT     0x05
 
 struct drm_amdgpu_cs_chunk {
 	__u32		chunk_id;
@@ -480,6 +509,10 @@ struct drm_amdgpu_cs_chunk_fence {
 	__u32 offset;
 };
 
+struct drm_amdgpu_cs_chunk_sem {
+	__u32 handle;
+};
+
 struct drm_amdgpu_cs_chunk_data {
 	union {
 		struct drm_amdgpu_cs_chunk_ib		ib_data;
@@ -576,6 +609,8 @@ struct drm_amdgpu_cs_chunk_data {
 	#define AMDGPU_INFO_SENSOR_VDDNB		0x6
 	/* Subquery id: Query graphics voltage */
 	#define AMDGPU_INFO_SENSOR_VDDGFX		0x7
+/* Number of VRAM page faults on CPU access. */
+#define AMDGPU_INFO_NUM_VRAM_CPU_PAGE_FAULTS	0x1E
 
 #define AMDGPU_INFO_MMR_SE_INDEX_SHIFT	0
 #define AMDGPU_INFO_MMR_SE_INDEX_MASK	0xff
@@ -764,6 +799,25 @@ struct drm_amdgpu_info_device {
 	__u64 cntl_sb_buf_gpu_addr;
 	/* NGG Parameter Cache */
 	__u64 param_buf_gpu_addr;
+	__u32 prim_buf_size;
+	__u32 pos_buf_size;
+	__u32 cntl_sb_buf_size;
+	__u32 param_buf_size;
+	/* wavefront size*/
+	__u32 wave_front_size;
+	/* shader visible vgprs*/
+	__u32 num_shader_visible_vgprs;
+	/* CU per shader array*/
+	__u32 num_cu_per_sh;
+	/* number of tcc blocks*/
+	__u32 num_tcc_blocks;
+	/* gs vgt table depth*/
+	__u32 gs_vgt_table_depth;
+	/* gs primitive buffer depth*/
+	__u32 gs_prim_buffer_depth;
+	/* max gs wavefront per vgt*/
+	__u32 max_gs_waves_per_vgt;
+	__u32 _pad1;
 };
 
 struct drm_amdgpu_info_hw_ip {
@@ -816,6 +870,7 @@ struct drm_amdgpu_info_vce_clock_table {
 #define AMDGPU_FAMILY_VI			130 /* Iceland, Tonga */
 #define AMDGPU_FAMILY_CZ			135 /* Carrizo, Stoney */
 #define AMDGPU_FAMILY_AI			141 /* Vega10 */
+#define AMDGPU_FAMILY_RV			142 /* Raven */
 
 #if defined(__cplusplus)
 }
diff --git a/lib/libdrm/include/drm/drm_fourcc.h b/lib/libdrm/include/drm/drm_fourcc.h
index 4d8da699a..7586c46f6 100644
--- a/lib/libdrm/include/drm/drm_fourcc.h
+++ b/lib/libdrm/include/drm/drm_fourcc.h
@@ -26,6 +26,10 @@
 
 #include "drm.h"
 
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
 #define fourcc_code(a, b, c, d) ((__u32)(a) | ((__u32)(b) << 8) | \
 				 ((__u32)(c) << 16) | ((__u32)(d) << 24))
 
@@ -37,10 +41,17 @@
 /* 8 bpp Red */
 #define DRM_FORMAT_R8		fourcc_code('R', '8', ' ', ' ') /* [7:0] R */
 
+/* 16 bpp Red */
+#define DRM_FORMAT_R16		fourcc_code('R', '1', '6', ' ') /* [15:0] R little endian */
+
 /* 16 bpp RG */
 #define DRM_FORMAT_RG88		fourcc_code('R', 'G', '8', '8') /* [15:0] R:G 8:8 little endian */
 #define DRM_FORMAT_GR88		fourcc_code('G', 'R', '8', '8') /* [15:0] G:R 8:8 little endian */
 
+/* 32 bpp RG */
+#define DRM_FORMAT_RG1616	fourcc_code('R', 'G', '3', '2') /* [31:0] R:G 16:16 little endian */
+#define DRM_FORMAT_GR1616	fourcc_code('G', 'R', '3', '2') /* [31:0] G:R 16:16 little endian */
+
 /* 8 bpp RGB */
 #define DRM_FORMAT_RGB332	fourcc_code('R', 'G', 'B', '8') /* [7:0] R:G:B 3:3:2 */
 #define DRM_FORMAT_BGR233	fourcc_code('B', 'G', 'R', '8') /* [7:0] B:G:R 2:3:3 */
@@ -103,6 +114,20 @@
 #define DRM_FORMAT_AYUV		fourcc_code('A', 'Y', 'U', 'V') /* [31:0] A:Y:Cb:Cr 8:8:8:8 little endian */
 
 /*
+ * 2 plane RGB + A
+ * index 0 = RGB plane, same format as the corresponding non _A8 format has
+ * index 1 = A plane, [7:0] A
+ */
+#define DRM_FORMAT_XRGB8888_A8	fourcc_code('X', 'R', 'A', '8')
+#define DRM_FORMAT_XBGR8888_A8	fourcc_code('X', 'B', 'A', '8')
+#define DRM_FORMAT_RGBX8888_A8	fourcc_code('R', 'X', 'A', '8')
+#define DRM_FORMAT_BGRX8888_A8	fourcc_code('B', 'X', 'A', '8')
+#define DRM_FORMAT_RGB888_A8	fourcc_code('R', '8', 'A', '8')
+#define DRM_FORMAT_BGR888_A8	fourcc_code('B', '8', 'A', '8')
+#define DRM_FORMAT_RGB565_A8	fourcc_code('R', '5', 'A', '8')
+#define DRM_FORMAT_BGR565_A8	fourcc_code('B', '5', 'A', '8')
+
+/*
  * 2 plane YCbCr
  * index 0 = Y plane, [7:0] Y
  * index 1 = Cr:Cb plane, [15:0] Cr:Cb little endian
@@ -150,11 +175,14 @@
 
 /* Vendor Ids: */
 #define DRM_FORMAT_MOD_NONE           0
+#define DRM_FORMAT_MOD_VENDOR_NONE    0
 #define DRM_FORMAT_MOD_VENDOR_INTEL   0x01
 #define DRM_FORMAT_MOD_VENDOR_AMD     0x02
 #define DRM_FORMAT_MOD_VENDOR_NV      0x03
 #define DRM_FORMAT_MOD_VENDOR_SAMSUNG 0x04
 #define DRM_FORMAT_MOD_VENDOR_QCOM    0x05
+#define DRM_FORMAT_MOD_VENDOR_VIVANTE 0x06
+#define DRM_FORMAT_MOD_VENDOR_BROADCOM 0x07
 /* add more to the end as needed */
 
 #define fourcc_mod_code(vendor, val) \
@@ -168,6 +196,16 @@
  * authoritative source for all of these.
  */
 
+/*
+ * Linear Layout
+ *
+ * Just plain linear layout. Note that this is different from no specifying any
+ * modifier (e.g. not setting DRM_MODE_FB_MODIFIERS in the DRM_ADDFB2 ioctl),
+ * which tells the driver to also take driver-internal information into account
+ * and so might actually result in a tiled framebuffer.
+ */
+#define DRM_FORMAT_MOD_LINEAR	fourcc_mod_code(NONE, 0)
+
 /* Intel framebuffer modifiers */
 
 /*
@@ -229,4 +267,113 @@
  */
 #define DRM_FORMAT_MOD_SAMSUNG_64_32_TILE	fourcc_mod_code(SAMSUNG, 1)
 
+/* Vivante framebuffer modifiers */
+
+/*
+ * Vivante 4x4 tiling layout
+ *
+ * This is a simple tiled layout using tiles of 4x4 pixels in a row-major
+ * layout.
+ */
+#define DRM_FORMAT_MOD_VIVANTE_TILED		fourcc_mod_code(VIVANTE, 1)
+
+/*
+ * Vivante 64x64 super-tiling layout
+ *
+ * This is a tiled layout using 64x64 pixel super-tiles, where each super-tile
+ * contains 8x4 groups of 2x4 tiles of 4x4 pixels (like above) each, all in row-
+ * major layout.
+ *
+ * For more information: see
+ * https://github.com/etnaviv/etna_viv/blob/master/doc/hardware.md#texture-tiling
+ */
+#define DRM_FORMAT_MOD_VIVANTE_SUPER_TILED	fourcc_mod_code(VIVANTE, 2)
+
+/*
+ * Vivante 4x4 tiling layout for dual-pipe
+ *
+ * Same as the 4x4 tiling layout, except every second 4x4 pixel tile starts at a
+ * different base address. Offsets from the base addresses are therefore halved
+ * compared to the non-split tiled layout.
+ */
+#define DRM_FORMAT_MOD_VIVANTE_SPLIT_TILED	fourcc_mod_code(VIVANTE, 3)
+
+/*
+ * Vivante 64x64 super-tiling layout for dual-pipe
+ *
+ * Same as the 64x64 super-tiling layout, except every second 4x4 pixel tile
+ * starts at a different base address. Offsets from the base addresses are
+ * therefore halved compared to the non-split super-tiled layout.
+ */
+#define DRM_FORMAT_MOD_VIVANTE_SPLIT_SUPER_TILED fourcc_mod_code(VIVANTE, 4)
+
+/* NVIDIA Tegra frame buffer modifiers */
+
+/*
+ * Some modifiers take parameters, for example the number of vertical GOBs in
+ * a block. Reserve the lower 32 bits for parameters
+ */
+#define __fourcc_mod_tegra_mode_shift 32
+#define fourcc_mod_tegra_code(val, params) \
+	fourcc_mod_code(NV, ((((__u64)val) << __fourcc_mod_tegra_mode_shift) | params))
+#define fourcc_mod_tegra_mod(m) \
+	(m & ~((1ULL << __fourcc_mod_tegra_mode_shift) - 1))
+#define fourcc_mod_tegra_param(m) \
+	(m & ((1ULL << __fourcc_mod_tegra_mode_shift) - 1))
+
+/*
+ * Tegra Tiled Layout, used by Tegra 2, 3 and 4.
+ *
+ * Pixels are arranged in simple tiles of 16 x 16 bytes.
+ */
+#define NV_FORMAT_MOD_TEGRA_TILED fourcc_mod_tegra_code(1, 0)
+
+/*
+ * Tegra 16Bx2 Block Linear layout, used by TK1/TX1
+ *
+ * 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.
+ *
+ * Within a GOB, data is ordered as 16B x 2 lines sectors laid in Z-shape.
+ *
+ * Parameter 'v' is the log2 encoding of the number of GOBs stacked vertically.
+ * Valid values are:
+ *
+ * 0 == ONE_GOB
+ * 1 == TWO_GOBS
+ * 2 == FOUR_GOBS
+ * 3 == EIGHT_GOBS
+ * 4 == SIXTEEN_GOBS
+ * 5 == THIRTYTWO_GOBS
+ *
+ * Chapter 20 "Pixel Memory Formats" of the Tegra X1 TRM describes this format
+ * in full detail.
+ */
+#define NV_FORMAT_MOD_TEGRA_16BX2_BLOCK(v) fourcc_mod_tegra_code(2, v)
+
+/*
+ * Broadcom VC4 "T" format
+ *
+ * This is the primary layout that the V3D GPU can texture from (it
+ * can't do linear).  The T format has:
+ *
+ * - 64b utiles of pixels in a raster-order grid according to cpp.  It's 4x4
+ *   pixels at 32 bit depth.
+ *
+ * - 1k subtiles made of a 4x4 raster-order grid of 64b utiles (so usually
+ *   16x16 pixels).
+ *
+ * - 4k tiles made of a 2x2 grid of 1k subtiles (so usually 32x32 pixels).  On
+ *   even 4k tile rows, they're arranged as (BL, TL, TR, BR), and on odd rows
+ *   they're (TR, BR, BL, TL), where bottom left is start of memory.
+ *
+ * - an image made of 4k tiles in rows either left-to-right (even rows of 4k
+ *   tiles) or right-to-left (odd rows of 4k tiles).
+ */
+#define DRM_FORMAT_MOD_BROADCOM_VC4_T_TILED fourcc_mod_code(BROADCOM, 1)
+
+#if defined(__cplusplus)
+}
+#endif
+
 #endif /* DRM_FOURCC_H */
diff --git a/lib/libdrm/include/drm/drm_sarea.h b/lib/libdrm/include/drm/drm_sarea.h
index 502934edc..93025be8b 100644
--- a/lib/libdrm/include/drm/drm_sarea.h
+++ b/lib/libdrm/include/drm/drm_sarea.h
@@ -34,6 +34,10 @@
 
 #include "drm.h"
 
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
 /* SAREA area needs to be at least a page */
 #if defined(__alpha__)
 #define SAREA_MAX                       0x2000U
@@ -81,4 +85,8 @@ typedef struct drm_sarea_drawable drm_sarea_drawable_t;
 typedef struct drm_sarea_frame drm_sarea_frame_t;
 typedef struct drm_sarea drm_sarea_t;
 
+#if defined(__cplusplus)
+}
+#endif
+
 #endif				/* _DRM_SAREA_H_ */
diff --git a/lib/libdrm/include/drm/vc4_drm.h b/lib/libdrm/include/drm/vc4_drm.h
index 319881d8e..6ac4c5c01 100644
--- a/lib/libdrm/include/drm/vc4_drm.h
+++ b/lib/libdrm/include/drm/vc4_drm.h
@@ -21,8 +21,8 @@
  * IN THE SOFTWARE.
  */
 
-#ifndef _VC4_DRM_H_
-#define _VC4_DRM_H_
+#ifndef _UAPI_VC4_DRM_H_
+#define _UAPI_VC4_DRM_H_
 
 #include "drm.h"
 
@@ -38,6 +38,8 @@ extern "C" {
 #define DRM_VC4_CREATE_SHADER_BO                  0x05
 #define DRM_VC4_GET_HANG_STATE                    0x06
 #define DRM_VC4_GET_PARAM                         0x07
+#define DRM_VC4_SET_TILING                        0x08
+#define DRM_VC4_GET_TILING                        0x09
 
 #define DRM_IOCTL_VC4_SUBMIT_CL           DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_SUBMIT_CL, struct drm_vc4_submit_cl)
 #define DRM_IOCTL_VC4_WAIT_SEQNO          DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_WAIT_SEQNO, struct drm_vc4_wait_seqno)
@@ -47,6 +49,8 @@ extern "C" {
 #define DRM_IOCTL_VC4_CREATE_SHADER_BO    DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_CREATE_SHADER_BO, struct drm_vc4_create_shader_bo)
 #define DRM_IOCTL_VC4_GET_HANG_STATE      DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_GET_HANG_STATE, struct drm_vc4_get_hang_state)
 #define DRM_IOCTL_VC4_GET_PARAM           DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_GET_PARAM, struct drm_vc4_get_param)
+#define DRM_IOCTL_VC4_SET_TILING          DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_SET_TILING, struct drm_vc4_set_tiling)
+#define DRM_IOCTL_VC4_GET_TILING          DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_GET_TILING, struct drm_vc4_get_tiling)
 
 struct drm_vc4_submit_rcl_surface {
 	__u32 hindex; /* Handle index, or ~0 if not present. */
@@ -295,8 +299,20 @@ struct drm_vc4_get_param {
 	__u64 value;
 };
 
+struct drm_vc4_get_tiling {
+	__u32 handle;
+	__u32 flags;
+	__u64 modifier;
+};
+
+struct drm_vc4_set_tiling {
+	__u32 handle;
+	__u32 flags;
+	__u64 modifier;
+};
+
 #if defined(__cplusplus)
 }
 #endif
 
-#endif /* _VC4_DRM_H_ */
+#endif /* _UAPI_VC4_DRM_H_ */