From 01a69402cf9d38ff180345d55c2ee51c7e89fbc7 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sat, 18 May 2024 20:50:03 +0200 Subject: Adding upstream version 6.8.9. Signed-off-by: Daniel Baumann --- include/uapi/drm/drm.h | 72 +- include/uapi/drm/drm_fourcc.h | 10 +- include/uapi/drm/drm_mode.h | 45 +- include/uapi/drm/habanalabs_accel.h | 28 + include/uapi/drm/i915_drm.h | 12 +- include/uapi/drm/ivpu_accel.h | 28 +- include/uapi/drm/msm_drm.h | 3 + include/uapi/drm/nouveau_drm.h | 14 + include/uapi/drm/pvr_drm.h | 1295 ++++++++++++++++++++++++++++++++++ include/uapi/drm/qaic_accel.h | 5 +- include/uapi/drm/v3d_drm.h | 245 ++++++- include/uapi/drm/virtgpu_drm.h | 2 + include/uapi/drm/xe_drm.h | 1327 +++++++++++++++++++++++++++++++++++ 13 files changed, 3056 insertions(+), 30 deletions(-) create mode 100644 include/uapi/drm/pvr_drm.h create mode 100644 include/uapi/drm/xe_drm.h (limited to 'include/uapi/drm') diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index de723566c5..16122819ed 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -713,7 +713,8 @@ struct drm_gem_open { /** * DRM_CAP_ASYNC_PAGE_FLIP * - * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC. + * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC for legacy + * page-flips. */ #define DRM_CAP_ASYNC_PAGE_FLIP 0x7 /** @@ -773,6 +774,13 @@ struct drm_gem_open { * :ref:`drm_sync_objects`. */ #define DRM_CAP_SYNCOBJ_TIMELINE 0x14 +/** + * DRM_CAP_ATOMIC_ASYNC_PAGE_FLIP + * + * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC for atomic + * commits. + */ +#define DRM_CAP_ATOMIC_ASYNC_PAGE_FLIP 0x15 /* DRM_IOCTL_GET_CAP ioctl argument type */ struct drm_get_cap { @@ -842,6 +850,31 @@ struct drm_get_cap { */ #define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS 5 +/** + * DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT + * + * Drivers for para-virtualized hardware (e.g. vmwgfx, qxl, virtio and + * virtualbox) have additional restrictions for cursor planes (thus + * making cursor planes on those drivers not truly universal,) e.g. + * they need cursor planes to act like one would expect from a mouse + * cursor and have correctly set hotspot properties. + * If this client cap is not set the DRM core will hide cursor plane on + * those virtualized drivers because not setting it implies that the + * client is not capable of dealing with those extra restictions. + * Clients which do set cursor hotspot and treat the cursor plane + * like a mouse cursor should set this property. + * The client must enable &DRM_CLIENT_CAP_ATOMIC first. + * + * Setting this property on drivers which do not special case + * cursor planes (i.e. non-virtualized drivers) will return + * EOPNOTSUPP, which can be used by userspace to gauge + * requirements of the hardware/drivers they're running on. + * + * This capability is always supported for atomic-capable virtualized + * drivers starting from kernel version 6.6. + */ +#define DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT 6 + /* DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */ struct drm_set_client_cap { __u64 capability; @@ -893,6 +926,7 @@ struct drm_syncobj_transfer { #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0) #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1) #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE (1 << 2) /* wait for time point to become available */ +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE (1 << 3) /* set fence deadline to deadline_nsec */ struct drm_syncobj_wait { __u64 handles; /* absolute timeout */ @@ -901,6 +935,14 @@ struct drm_syncobj_wait { __u32 flags; __u32 first_signaled; /* only valid when not waiting all */ __u32 pad; + /** + * @deadline_nsec - fence deadline hint + * + * Deadline hint, in absolute CLOCK_MONOTONIC, to set on backing + * fence(s) if the DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE flag is + * set. + */ + __u64 deadline_nsec; }; struct drm_syncobj_timeline_wait { @@ -913,6 +955,14 @@ struct drm_syncobj_timeline_wait { __u32 flags; __u32 first_signaled; /* only valid when not waiting all */ __u32 pad; + /** + * @deadline_nsec - fence deadline hint + * + * Deadline hint, in absolute CLOCK_MONOTONIC, to set on backing + * fence(s) if the DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE flag is + * set. + */ + __u64 deadline_nsec; }; /** @@ -1218,6 +1268,26 @@ extern "C" { #define DRM_IOCTL_SYNCOBJ_EVENTFD DRM_IOWR(0xCF, struct drm_syncobj_eventfd) +/** + * DRM_IOCTL_MODE_CLOSEFB - Close a framebuffer. + * + * This closes a framebuffer previously added via ADDFB/ADDFB2. The IOCTL + * argument is a framebuffer object ID. + * + * This IOCTL is similar to &DRM_IOCTL_MODE_RMFB, except it doesn't disable + * planes and CRTCs. As long as the framebuffer is used by a plane, it's kept + * alive. When the plane no longer uses the framebuffer (because the + * framebuffer is replaced with another one, or the plane is disabled), the + * framebuffer is cleaned up. + * + * This is useful to implement flicker-free transitions between two processes. + * + * Depending on the threat model, user-space may want to ensure that the + * framebuffer doesn't expose any sensitive user information: closed + * framebuffers attached to a plane can be read back by the next DRM master. + */ +#define DRM_IOCTL_MODE_CLOSEFB DRM_IOWR(0xD0, struct drm_mode_closefb) + /* * Device specific ioctls should only be in their respective headers * The device specific ioctl range is from 0x40 to 0x9f. diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index 3151f1fc7e..84d502e429 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -54,7 +54,7 @@ extern "C" { * Format modifiers may change any property of the buffer, including the number * of planes and/or the required allocation size. Format modifiers are * vendor-namespaced, and as such the relationship between a fourcc code and a - * modifier is specific to the modifer being used. For example, some modifiers + * modifier is specific to the modifier being used. For example, some modifiers * may preserve meaning - such as number of planes - from the fourcc code, * whereas others may not. * @@ -79,7 +79,7 @@ extern "C" { * format. * - Higher-level programs interfacing with KMS/GBM/EGL/Vulkan/etc: these users * see modifiers as opaque tokens they can check for equality and intersect. - * These users musn't need to know to reason about the modifier value + * These users mustn't need to know to reason about the modifier value * (i.e. they are not expected to extract information out of the modifier). * * Vendors should document their modifier usage in as much detail as @@ -540,7 +540,7 @@ extern "C" { * This is a tiled layout using 4Kb tiles in row-major layout. * Within the tile pixels are laid out in 16 256 byte units / sub-tiles which * are arranged in four groups (two wide, two high) with column-major layout. - * Each group therefore consits out of four 256 byte units, which are also laid + * Each group therefore consists out of four 256 byte units, which are also laid * out as 2x2 column-major. * 256 byte units are made out of four 64 byte blocks of pixels, producing * either a square block or a 2:1 unit. @@ -1103,7 +1103,7 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier) */ /* - * The top 4 bits (out of the 56 bits alloted for specifying vendor specific + * The top 4 bits (out of the 56 bits allotted for specifying vendor specific * modifiers) denote the category for modifiers. Currently we have three * categories of modifiers ie AFBC, MISC and AFRC. We can have a maximum of * sixteen different categories. @@ -1419,7 +1419,7 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier) * 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 + * boundaries, 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 diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index 128d09138c..7040e7ea80 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -36,10 +36,10 @@ extern "C" { /** * DOC: overview * - * DRM exposes many UAPI and structure definition to have a consistent - * and standardized interface with user. + * DRM exposes many UAPI and structure definitions to have a consistent + * and standardized interface with users. * Userspace can refer to these structure definitions and UAPI formats - * to communicate to driver + * to communicate to drivers. */ #define DRM_CONNECTOR_NAME_LEN 32 @@ -540,7 +540,7 @@ struct drm_mode_get_connector { /* the PROP_ATOMIC flag is used to hide properties from userspace that * is not aware of atomic properties. This is mostly to work around * older userspace (DDX drivers) that read/write each prop they find, - * witout being aware that this could be triggering a lengthy modeset. + * without being aware that this could be triggering a lengthy modeset. */ #define DRM_MODE_PROP_ATOMIC 0x80000000 @@ -664,7 +664,7 @@ struct drm_mode_fb_cmd { }; #define DRM_MODE_FB_INTERLACED (1<<0) /* for interlaced framebuffers */ -#define DRM_MODE_FB_MODIFIERS (1<<1) /* enables ->modifer[] */ +#define DRM_MODE_FB_MODIFIERS (1<<1) /* enables ->modifier[] */ /** * struct drm_mode_fb_cmd2 - Frame-buffer metadata. @@ -846,6 +846,14 @@ struct drm_color_ctm { __u64 matrix[9]; }; +struct drm_color_ctm_3x4 { + /* + * Conversion matrix with 3x4 dimensions in S31.32 sign-magnitude + * (not two's complement!) format. + */ + __u64 matrix[12]; +}; + struct drm_color_lut { /* * Values are mapped linearly to 0.0 - 1.0 range, with 0x0 == 0.0 and @@ -881,8 +889,8 @@ struct hdr_metadata_infoframe { * These are coded as unsigned 16-bit values in units of * 0.00002, where 0x0000 represents zero and 0xC350 * represents 1.0000. - * @display_primaries.x: X cordinate of color primary. - * @display_primaries.y: Y cordinate of color primary. + * @display_primaries.x: X coordinate of color primary. + * @display_primaries.y: Y coordinate of color primary. */ struct { __u16 x, y; @@ -892,8 +900,8 @@ struct hdr_metadata_infoframe { * These are coded as unsigned 16-bit values in units of * 0.00002, where 0x0000 represents zero and 0xC350 * represents 1.0000. - * @white_point.x: X cordinate of whitepoint of color primary. - * @white_point.y: Y cordinate of whitepoint of color primary. + * @white_point.x: X coordinate of whitepoint of color primary. + * @white_point.y: Y coordinate of whitepoint of color primary. */ struct { __u16 x, y; @@ -957,6 +965,15 @@ struct hdr_output_metadata { * Request that the page-flip is performed as soon as possible, ie. with no * delay due to waiting for vblank. This may cause tearing to be visible on * the screen. + * + * When used with atomic uAPI, the driver will return an error if the hardware + * doesn't support performing an asynchronous page-flip for this update. + * User-space should handle this, e.g. by falling back to a regular page-flip. + * + * Note, some hardware might need to perform one last synchronous page-flip + * before being able to switch to asynchronous page-flips. As an exception, + * the driver will return success even though that first page-flip is not + * asynchronous. */ #define DRM_MODE_PAGE_FLIP_ASYNC 0x02 #define DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE 0x4 @@ -1323,6 +1340,16 @@ struct drm_mode_rect { __s32 y2; }; +/** + * struct drm_mode_closefb + * @fb_id: Framebuffer ID. + * @pad: Must be zero. + */ +struct drm_mode_closefb { + __u32 fb_id; + __u32 pad; +}; + #if defined(__cplusplus) } #endif diff --git a/include/uapi/drm/habanalabs_accel.h b/include/uapi/drm/habanalabs_accel.h index 347c7b62e6..a512dc4cff 100644 --- a/include/uapi/drm/habanalabs_accel.h +++ b/include/uapi/drm/habanalabs_accel.h @@ -846,6 +846,7 @@ enum hl_server_type { #define HL_INFO_HW_ERR_EVENT 36 #define HL_INFO_FW_ERR_EVENT 37 #define HL_INFO_USER_ENGINE_ERR_EVENT 38 +#define HL_INFO_DEV_SIGNED 40 #define HL_INFO_VERSION_MAX_LEN 128 #define HL_INFO_CARD_NAME_MAX_LEN 16 @@ -1256,6 +1257,7 @@ struct hl_info_dev_memalloc_page_sizes { #define SEC_SIGNATURE_BUF_SZ 255 /* (256 - 1) 1 byte used for size */ #define SEC_PUB_DATA_BUF_SZ 510 /* (512 - 2) 2 bytes used for size */ #define SEC_CERTIFICATE_BUF_SZ 2046 /* (2048 - 2) 2 bytes used for size */ +#define SEC_DEV_INFO_BUF_SZ 5120 /* * struct hl_info_sec_attest - attestation report of the boot @@ -1290,6 +1292,32 @@ struct hl_info_sec_attest { __u8 pad0[2]; }; +/* + * struct hl_info_signed - device information signed by a secured device. + * @nonce: number only used once. random number provided by host. this also passed to the quote + * command as a qualifying data. + * @pub_data_len: length of the public data (bytes) + * @certificate_len: length of the certificate (bytes) + * @info_sig_len: length of the attestation signature (bytes) + * @public_data: public key info signed info data (outPublic + name + qualifiedName) + * @certificate: certificate for the signing key + * @info_sig: signature of the info + nonce data. + * @dev_info_len: length of device info (bytes) + * @dev_info: device info as byte array. + */ +struct hl_info_signed { + __u32 nonce; + __u16 pub_data_len; + __u16 certificate_len; + __u8 info_sig_len; + __u8 public_data[SEC_PUB_DATA_BUF_SZ]; + __u8 certificate[SEC_CERTIFICATE_BUF_SZ]; + __u8 info_sig[SEC_SIGNATURE_BUF_SZ]; + __u16 dev_info_len; + __u8 dev_info[SEC_DEV_INFO_BUF_SZ]; + __u8 pad[2]; +}; + /** * struct hl_page_fault_info - page fault information. * @timestamp: timestamp of page fault. diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 218edb0a96..fd4f9574d1 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -693,7 +693,7 @@ typedef struct drm_i915_irq_wait { #define I915_PARAM_HAS_EXEC_FENCE 44 /* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to capture - * user specified bufffers for post-mortem debugging of GPU hangs. See + * user-specified buffers for post-mortem debugging of GPU hangs. See * EXEC_OBJECT_CAPTURE. */ #define I915_PARAM_HAS_EXEC_CAPTURE 45 @@ -1606,7 +1606,7 @@ struct drm_i915_gem_busy { * is accurate. * * The returned dword is split into two fields to indicate both - * the engine classess on which the object is being read, and the + * the engine classes on which the object is being read, and the * engine class on which it is currently being written (if any). * * The low word (bits 0:15) indicate if the object is being written @@ -1815,7 +1815,7 @@ struct drm_i915_gem_madvise { __u32 handle; /* Advice: either the buffer will be needed again in the near future, - * or wont be and could be discarded under memory pressure. + * or won't be and could be discarded under memory pressure. */ __u32 madv; @@ -3246,7 +3246,7 @@ struct drm_i915_query_topology_info { * // enough to hold our array of engines. The kernel will fill out the * // item.length for us, which is the number of bytes we need. * // - * // Alternatively a large buffer can be allocated straight away enabling + * // Alternatively a large buffer can be allocated straightaway enabling * // querying in one pass, in which case item.length should contain the * // length of the provided buffer. * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); @@ -3256,7 +3256,7 @@ struct drm_i915_query_topology_info { * // Now that we allocated the required number of bytes, we call the ioctl * // again, this time with the data_ptr pointing to our newly allocated * // blob, which the kernel can then populate with info on all engines. - * item.data_ptr = (uintptr_t)&info, + * item.data_ptr = (uintptr_t)&info; * * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); * if (err) ... @@ -3286,7 +3286,7 @@ struct drm_i915_query_topology_info { /** * struct drm_i915_engine_info * - * Describes one engine and it's capabilities as known to the driver. + * Describes one engine and its capabilities as known to the driver. */ struct drm_i915_engine_info { /** @engine: Engine class and instance. */ diff --git a/include/uapi/drm/ivpu_accel.h b/include/uapi/drm/ivpu_accel.h index 262db0c3be..19a13468ec 100644 --- a/include/uapi/drm/ivpu_accel.h +++ b/include/uapi/drm/ivpu_accel.h @@ -53,7 +53,7 @@ extern "C" { #define DRM_IVPU_PARAM_CORE_CLOCK_RATE 3 #define DRM_IVPU_PARAM_NUM_CONTEXTS 4 #define DRM_IVPU_PARAM_CONTEXT_BASE_ADDRESS 5 -#define DRM_IVPU_PARAM_CONTEXT_PRIORITY 6 +#define DRM_IVPU_PARAM_CONTEXT_PRIORITY 6 /* Deprecated */ #define DRM_IVPU_PARAM_CONTEXT_ID 7 #define DRM_IVPU_PARAM_FW_API_VERSION 8 #define DRM_IVPU_PARAM_ENGINE_HEARTBEAT 9 @@ -64,11 +64,18 @@ extern "C" { #define DRM_IVPU_PLATFORM_TYPE_SILICON 0 +/* Deprecated, use DRM_IVPU_JOB_PRIORITY */ #define DRM_IVPU_CONTEXT_PRIORITY_IDLE 0 #define DRM_IVPU_CONTEXT_PRIORITY_NORMAL 1 #define DRM_IVPU_CONTEXT_PRIORITY_FOCUS 2 #define DRM_IVPU_CONTEXT_PRIORITY_REALTIME 3 +#define DRM_IVPU_JOB_PRIORITY_DEFAULT 0 +#define DRM_IVPU_JOB_PRIORITY_IDLE 1 +#define DRM_IVPU_JOB_PRIORITY_NORMAL 2 +#define DRM_IVPU_JOB_PRIORITY_FOCUS 3 +#define DRM_IVPU_JOB_PRIORITY_REALTIME 4 + /** * DRM_IVPU_CAP_METRIC_STREAMER * @@ -112,10 +119,6 @@ struct drm_ivpu_param { * %DRM_IVPU_PARAM_CONTEXT_BASE_ADDRESS: * Lowest VPU virtual address available in the current context (read-only) * - * %DRM_IVPU_PARAM_CONTEXT_PRIORITY: - * Value of current context scheduling priority (read-write). - * See DRM_IVPU_CONTEXT_PRIORITY_* for possible values. - * * %DRM_IVPU_PARAM_CONTEXT_ID: * Current context ID, always greater than 0 (read-only) * @@ -196,7 +199,7 @@ struct drm_ivpu_bo_create { * * %DRM_IVPU_BO_UNCACHED: * - * Allocated BO will not be cached on host side nor snooped on the VPU side. + * Not supported. Use DRM_IVPU_BO_WC instead. * * %DRM_IVPU_BO_WC: * @@ -286,10 +289,23 @@ struct drm_ivpu_submit { * to be executed. The offset has to be 8-byte aligned. */ __u32 commands_offset; + + /** + * @priority: + * + * Priority to be set for related job command queue, can be one of the following: + * %DRM_IVPU_JOB_PRIORITY_DEFAULT + * %DRM_IVPU_JOB_PRIORITY_IDLE + * %DRM_IVPU_JOB_PRIORITY_NORMAL + * %DRM_IVPU_JOB_PRIORITY_FOCUS + * %DRM_IVPU_JOB_PRIORITY_REALTIME + */ + __u32 priority; }; /* drm_ivpu_bo_wait job status codes */ #define DRM_IVPU_JOB_STATUS_SUCCESS 0 +#define DRM_IVPU_JOB_STATUS_ABORTED 256 /** * struct drm_ivpu_bo_wait - Wait for BO to become inactive diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index 6c34272a13..d8a6b34727 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -86,6 +86,7 @@ struct drm_msm_timespec { #define MSM_PARAM_CMDLINE 0x0d /* WO: override for task cmdline */ #define MSM_PARAM_VA_START 0x0e /* RO: start of valid GPU iova range */ #define MSM_PARAM_VA_SIZE 0x0f /* RO: size of valid GPU iova range (bytes) */ +#define MSM_PARAM_HIGHEST_BANK_BIT 0x10 /* RO */ /* For backwards compat. The original support for preemption was based on * a single ring per priority level so # of priority levels equals the # @@ -139,6 +140,8 @@ struct drm_msm_gem_new { #define MSM_INFO_GET_NAME 0x03 /* get debug name, returned by pointer */ #define MSM_INFO_SET_IOVA 0x04 /* set the iova, passed by value */ #define MSM_INFO_GET_FLAGS 0x05 /* get the MSM_BO_x flags */ +#define MSM_INFO_SET_METADATA 0x06 /* set userspace metadata */ +#define MSM_INFO_GET_METADATA 0x07 /* get userspace metadata */ struct drm_msm_gem_info { __u32 handle; /* in */ diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h index 0bade1592f..77d7ff0d5b 100644 --- a/include/uapi/drm/nouveau_drm.h +++ b/include/uapi/drm/nouveau_drm.h @@ -54,6 +54,20 @@ extern "C" { */ #define NOUVEAU_GETPARAM_EXEC_PUSH_MAX 17 +/* + * NOUVEAU_GETPARAM_VRAM_BAR_SIZE - query bar size + * + * Query the VRAM BAR size. + */ +#define NOUVEAU_GETPARAM_VRAM_BAR_SIZE 18 + +/* + * NOUVEAU_GETPARAM_VRAM_USED + * + * Get remaining VRAM size. + */ +#define NOUVEAU_GETPARAM_VRAM_USED 19 + struct drm_nouveau_getparam { __u64 param; __u64 value; diff --git a/include/uapi/drm/pvr_drm.h b/include/uapi/drm/pvr_drm.h new file mode 100644 index 0000000000..ccf6c21124 --- /dev/null +++ b/include/uapi/drm/pvr_drm.h @@ -0,0 +1,1295 @@ +/* SPDX-License-Identifier: (GPL-2.0-only WITH Linux-syscall-note) OR MIT */ +/* Copyright (c) 2023 Imagination Technologies Ltd. */ + +#ifndef PVR_DRM_UAPI_H +#define PVR_DRM_UAPI_H + +#include "drm.h" + +#include +#include + +#if defined(__cplusplus) +extern "C" { +#endif + +/** + * DOC: PowerVR UAPI + * + * The PowerVR IOCTL argument structs have a few limitations in place, in + * addition to the standard kernel restrictions: + * + * - All members must be type-aligned. + * - The overall struct must be padded to 64-bit alignment. + * - Explicit padding is almost always required. This takes the form of + * ``_padding_[x]`` members of sufficient size to pad to the next power-of-two + * alignment, where [x] is the offset into the struct in hexadecimal. Arrays + * are never used for alignment. Padding fields must be zeroed; this is + * always checked. + * - Unions may only appear as the last member of a struct. + * - Individual union members may grow in the future. The space between the + * end of a union member and the end of its containing union is considered + * "implicit padding" and must be zeroed. This is always checked. + * + * In addition to the IOCTL argument structs, the PowerVR UAPI makes use of + * DEV_QUERY argument structs. These are used to fetch information about the + * device and runtime. These structs are subject to the same rules set out + * above. + */ + +/** + * struct drm_pvr_obj_array - Container used to pass arrays of objects + * + * It is not unusual to have to extend objects to pass new parameters, and the DRM + * ioctl infrastructure is supporting that by padding ioctl arguments with zeros + * when the data passed by userspace is smaller than the struct defined in the + * drm_ioctl_desc, thus keeping things backward compatible. This type is just + * applying the same concepts to indirect objects passed through arrays referenced + * from the main ioctl arguments structure: the stride basically defines the size + * of the object passed by userspace, which allows the kernel driver to pad with + * zeros when it's smaller than the size of the object it expects. + * + * Use ``DRM_PVR_OBJ_ARRAY()`` to fill object array fields, unless you + * have a very good reason not to. + */ +struct drm_pvr_obj_array { + /** @stride: Stride of object struct. Used for versioning. */ + __u32 stride; + + /** @count: Number of objects in the array. */ + __u32 count; + + /** @array: User pointer to an array of objects. */ + __u64 array; +}; + +/** + * DRM_PVR_OBJ_ARRAY() - Helper macro for filling &struct drm_pvr_obj_array. + * @cnt: Number of elements pointed to py @ptr. + * @ptr: Pointer to start of a C array. + * + * Return: Literal of type &struct drm_pvr_obj_array. + */ +#define DRM_PVR_OBJ_ARRAY(cnt, ptr) \ + { .stride = sizeof((ptr)[0]), .count = (cnt), .array = (__u64)(uintptr_t)(ptr) } + +/** + * DOC: PowerVR IOCTL interface + */ + +/** + * PVR_IOCTL() - Build a PowerVR IOCTL number + * @_ioctl: An incrementing id for this IOCTL. Added to %DRM_COMMAND_BASE. + * @_mode: Must be one of %DRM_IOR, %DRM_IOW or %DRM_IOWR. + * @_data: The type of the args struct passed by this IOCTL. + * + * The struct referred to by @_data must have a ``drm_pvr_ioctl_`` prefix and an + * ``_args suffix``. They are therefore omitted from @_data. + * + * This should only be used to build the constants described below; it should + * never be used to call an IOCTL directly. + * + * Return: An IOCTL number to be passed to ioctl() from userspace. + */ +#define PVR_IOCTL(_ioctl, _mode, _data) \ + _mode(DRM_COMMAND_BASE + (_ioctl), struct drm_pvr_ioctl_##_data##_args) + +#define DRM_IOCTL_PVR_DEV_QUERY PVR_IOCTL(0x00, DRM_IOWR, dev_query) +#define DRM_IOCTL_PVR_CREATE_BO PVR_IOCTL(0x01, DRM_IOWR, create_bo) +#define DRM_IOCTL_PVR_GET_BO_MMAP_OFFSET PVR_IOCTL(0x02, DRM_IOWR, get_bo_mmap_offset) +#define DRM_IOCTL_PVR_CREATE_VM_CONTEXT PVR_IOCTL(0x03, DRM_IOWR, create_vm_context) +#define DRM_IOCTL_PVR_DESTROY_VM_CONTEXT PVR_IOCTL(0x04, DRM_IOW, destroy_vm_context) +#define DRM_IOCTL_PVR_VM_MAP PVR_IOCTL(0x05, DRM_IOW, vm_map) +#define DRM_IOCTL_PVR_VM_UNMAP PVR_IOCTL(0x06, DRM_IOW, vm_unmap) +#define DRM_IOCTL_PVR_CREATE_CONTEXT PVR_IOCTL(0x07, DRM_IOWR, create_context) +#define DRM_IOCTL_PVR_DESTROY_CONTEXT PVR_IOCTL(0x08, DRM_IOW, destroy_context) +#define DRM_IOCTL_PVR_CREATE_FREE_LIST PVR_IOCTL(0x09, DRM_IOWR, create_free_list) +#define DRM_IOCTL_PVR_DESTROY_FREE_LIST PVR_IOCTL(0x0a, DRM_IOW, destroy_free_list) +#define DRM_IOCTL_PVR_CREATE_HWRT_DATASET PVR_IOCTL(0x0b, DRM_IOWR, create_hwrt_dataset) +#define DRM_IOCTL_PVR_DESTROY_HWRT_DATASET PVR_IOCTL(0x0c, DRM_IOW, destroy_hwrt_dataset) +#define DRM_IOCTL_PVR_SUBMIT_JOBS PVR_IOCTL(0x0d, DRM_IOW, submit_jobs) + +/** + * DOC: PowerVR IOCTL DEV_QUERY interface + */ + +/** + * struct drm_pvr_dev_query_gpu_info - Container used to fetch information about + * the graphics processor. + * + * When fetching this type &struct drm_pvr_ioctl_dev_query_args.type must be set + * to %DRM_PVR_DEV_QUERY_GPU_INFO_GET. + */ +struct drm_pvr_dev_query_gpu_info { + /** + * @gpu_id: GPU identifier. + * + * For all currently supported GPUs this is the BVNC encoded as a 64-bit + * value as follows: + * + * +--------+--------+--------+-------+ + * | 63..48 | 47..32 | 31..16 | 15..0 | + * +========+========+========+=======+ + * | B | V | N | C | + * +--------+--------+--------+-------+ + */ + __u64 gpu_id; + + /** + * @num_phantoms: Number of Phantoms present. + */ + __u32 num_phantoms; + + /** @_padding_c: Reserved. This field must be zeroed. */ + __u32 _padding_c; +}; + +/** + * struct drm_pvr_dev_query_runtime_info - Container used to fetch information + * about the graphics runtime. + * + * When fetching this type &struct drm_pvr_ioctl_dev_query_args.type must be set + * to %DRM_PVR_DEV_QUERY_RUNTIME_INFO_GET. + */ +struct drm_pvr_dev_query_runtime_info { + /** + * @free_list_min_pages: Minimum allowed free list size, + * in PM physical pages. + */ + __u64 free_list_min_pages; + + /** + * @free_list_max_pages: Maximum allowed free list size, + * in PM physical pages. + */ + __u64 free_list_max_pages; + + /** + * @common_store_alloc_region_size: Size of the Allocation + * Region within the Common Store used for coefficient and shared + * registers, in dwords. + */ + __u32 common_store_alloc_region_size; + + /** + * @common_store_partition_space_size: Size of the + * Partition Space within the Common Store for output buffers, in + * dwords. + */ + __u32 common_store_partition_space_size; + + /** + * @max_coeffs: Maximum coefficients, in dwords. + */ + __u32 max_coeffs; + + /** + * @cdm_max_local_mem_size_regs: Maximum amount of local + * memory available to a compute kernel, in dwords. + */ + __u32 cdm_max_local_mem_size_regs; +}; + +/** + * struct drm_pvr_dev_query_quirks - Container used to fetch information about + * hardware fixes for which the device may require support in the user mode + * driver. + * + * When fetching this type &struct drm_pvr_ioctl_dev_query_args.type must be set + * to %DRM_PVR_DEV_QUERY_QUIRKS_GET. + */ +struct drm_pvr_dev_query_quirks { + /** + * @quirks: A userspace address for the hardware quirks __u32 array. + * + * The first @musthave_count items in the list are quirks that the + * client must support for this device. If userspace does not support + * all these quirks then functionality is not guaranteed and client + * initialisation must fail. + * The remaining quirks in the list affect userspace and the kernel or + * firmware. They are disabled by default and require userspace to + * opt-in. The opt-in mechanism depends on the quirk. + */ + __u64 quirks; + + /** @count: Length of @quirks (number of __u32). */ + __u16 count; + + /** + * @musthave_count: The number of entries in @quirks that are + * mandatory, starting at index 0. + */ + __u16 musthave_count; + + /** @_padding_c: Reserved. This field must be zeroed. */ + __u32 _padding_c; +}; + +/** + * struct drm_pvr_dev_query_enhancements - Container used to fetch information + * about optional enhancements supported by the device that require support in + * the user mode driver. + * + * When fetching this type &struct drm_pvr_ioctl_dev_query_args.type must be set + * to %DRM_PVR_DEV_ENHANCEMENTS_GET. + */ +struct drm_pvr_dev_query_enhancements { + /** + * @enhancements: A userspace address for the hardware enhancements + * __u32 array. + * + * These enhancements affect userspace and the kernel or firmware. They + * are disabled by default and require userspace to opt-in. The opt-in + * mechanism depends on the enhancement. + */ + __u64 enhancements; + + /** @count: Length of @enhancements (number of __u32). */ + __u16 count; + + /** @_padding_a: Reserved. This field must be zeroed. */ + __u16 _padding_a; + + /** @_padding_c: Reserved. This field must be zeroed. */ + __u32 _padding_c; +}; + +/** + * enum drm_pvr_heap_id - Array index for heap info data returned by + * %DRM_PVR_DEV_QUERY_HEAP_INFO_GET. + * + * For compatibility reasons all indices will be present in the returned array, + * however some heaps may not be present. These are indicated where + * &struct drm_pvr_heap.size is set to zero. + */ +enum drm_pvr_heap_id { + /** @DRM_PVR_HEAP_GENERAL: General purpose heap. */ + DRM_PVR_HEAP_GENERAL = 0, + /** @DRM_PVR_HEAP_PDS_CODE_DATA: PDS code and data heap. */ + DRM_PVR_HEAP_PDS_CODE_DATA, + /** @DRM_PVR_HEAP_USC_CODE: USC code heap. */ + DRM_PVR_HEAP_USC_CODE, + /** @DRM_PVR_HEAP_RGNHDR: Region header heap. Only used if GPU has BRN63142. */ + DRM_PVR_HEAP_RGNHDR, + /** @DRM_PVR_HEAP_VIS_TEST: Visibility test heap. */ + DRM_PVR_HEAP_VIS_TEST, + /** @DRM_PVR_HEAP_TRANSFER_FRAG: Transfer fragment heap. */ + DRM_PVR_HEAP_TRANSFER_FRAG, + + /** + * @DRM_PVR_HEAP_COUNT: The number of heaps returned by + * %DRM_PVR_DEV_QUERY_HEAP_INFO_GET. + * + * More heaps may be added, so this also serves as the copy limit when + * sent by the caller. + */ + DRM_PVR_HEAP_COUNT + /* Please only add additional heaps above DRM_PVR_HEAP_COUNT! */ +}; + +/** + * struct drm_pvr_heap - Container holding information about a single heap. + * + * This will always be fetched as an array. + */ +struct drm_pvr_heap { + /** @base: Base address of heap. */ + __u64 base; + + /** @size: Size of heap, in bytes. Will be 0 if the heap is not present. */ + __u64 size; + + /** @flags: Flags for this heap. Currently always 0. */ + __u32 flags; + + /** @page_size_log2: Log2 of page size. */ + __u32 page_size_log2; +}; + +/** + * struct drm_pvr_dev_query_heap_info - Container used to fetch information + * about heaps supported by the device driver. + * + * Please note all driver-supported heaps will be returned up to &heaps.count. + * Some heaps will not be present in all devices, which will be indicated by + * &struct drm_pvr_heap.size being set to zero. + * + * When fetching this type &struct drm_pvr_ioctl_dev_query_args.type must be set + * to %DRM_PVR_DEV_QUERY_HEAP_INFO_GET. + */ +struct drm_pvr_dev_query_heap_info { + /** + * @heaps: Array of &struct drm_pvr_heap. If pointer is NULL, the count + * and stride will be updated with those known to the driver version, to + * facilitate allocation by the caller. + */ + struct drm_pvr_obj_array heaps; +}; + +/** + * enum drm_pvr_static_data_area_usage - Array index for static data area info + * returned by %DRM_PVR_DEV_QUERY_STATIC_DATA_AREAS_GET. + * + * For compatibility reasons all indices will be present in the returned array, + * however some areas may not be present. These are indicated where + * &struct drm_pvr_static_data_area.size is set to zero. + */ +enum drm_pvr_static_data_area_usage { + /** + * @DRM_PVR_STATIC_DATA_AREA_EOT: End of Tile PDS program code segment. + * + * The End of Tile PDS task runs at completion of a tile during a fragment job, and is + * responsible for emitting the tile to the Pixel Back End. + */ + DRM_PVR_STATIC_DATA_AREA_EOT = 0, + + /** + * @DRM_PVR_STATIC_DATA_AREA_FENCE: MCU fence area, used during cache flush and + * invalidation. + * + * This must point to valid physical memory but the contents otherwise are not used. + */ + DRM_PVR_STATIC_DATA_AREA_FENCE, + + /** + * @DRM_PVR_STATIC_DATA_AREA_VDM_SYNC: VDM sync program. + * + * The VDM sync program is used to synchronise multiple areas of the GPU hardware. + */ + DRM_PVR_STATIC_DATA_AREA_VDM_SYNC, + + /** + * @DRM_PVR_STATIC_DATA_AREA_YUV_CSC: YUV coefficients. + * + * Area contains up to 16 slots with stride of 64 bytes. Each is a 3x4 matrix of u16 fixed + * point numbers, with 1 sign bit, 2 integer bits and 13 fractional bits. + * + * The slots are : + * 0 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_RGB_IDENTITY_KHR + * 1 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_IDENTITY_KHR (full range) + * 2 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_IDENTITY_KHR (conformant range) + * 3 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_709_KHR (full range) + * 4 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_709_KHR (conformant range) + * 5 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_601_KHR (full range) + * 6 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_601_KHR (conformant range) + * 7 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_2020_KHR (full range) + * 8 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_2020_KHR (conformant range) + * 9 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_601_KHR (conformant range, 10 bit) + * 10 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_709_KHR (conformant range, 10 bit) + * 11 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_2020_KHR (conformant range, 10 bit) + * 14 = Identity (biased) + * 15 = Identity + */ + DRM_PVR_STATIC_DATA_AREA_YUV_CSC, +}; + +/** + * struct drm_pvr_static_data_area - Container holding information about a + * single static data area. + * + * This will always be fetched as an array. + */ +struct drm_pvr_static_data_area { + /** + * @area_usage: Usage of static data area. + * See &enum drm_pvr_static_data_area_usage. + */ + __u16 area_usage; + + /** + * @location_heap_id: Array index of heap where this of static data + * area is located. This array is fetched using + * %DRM_PVR_DEV_QUERY_HEAP_INFO_GET. + */ + __u16 location_heap_id; + + /** @size: Size of static data area. Not present if set to zero. */ + __u32 size; + + /** @offset: Offset of static data area from start of heap. */ + __u64 offset; +}; + +/** + * struct drm_pvr_dev_query_static_data_areas - Container used to fetch + * information about the static data areas in heaps supported by the device + * driver. + * + * Please note all driver-supported static data areas will be returned up to + * &static_data_areas.count. Some will not be present for all devices which, + * will be indicated by &struct drm_pvr_static_data_area.size being set to zero. + * + * Further, some heaps will not be present either. See &struct + * drm_pvr_dev_query_heap_info. + * + * When fetching this type &struct drm_pvr_ioctl_dev_query_args.type must be set + * to %DRM_PVR_DEV_QUERY_STATIC_DATA_AREAS_GET. + */ +struct drm_pvr_dev_query_static_data_areas { + /** + * @static_data_areas: Array of &struct drm_pvr_static_data_area. If + * pointer is NULL, the count and stride will be updated with those + * known to the driver version, to facilitate allocation by the caller. + */ + struct drm_pvr_obj_array static_data_areas; +}; + +/** + * enum drm_pvr_dev_query - For use with &drm_pvr_ioctl_dev_query_args.type to + * indicate the type of the receiving container. + * + * Append only. Do not reorder. + */ +enum drm_pvr_dev_query { + /** + * @DRM_PVR_DEV_QUERY_GPU_INFO_GET: The dev query args contain a pointer + * to &struct drm_pvr_dev_query_gpu_info. + */ + DRM_PVR_DEV_QUERY_GPU_INFO_GET = 0, + + /** + * @DRM_PVR_DEV_QUERY_RUNTIME_INFO_GET: The dev query args contain a + * pointer to &struct drm_pvr_dev_query_runtime_info. + */ + DRM_PVR_DEV_QUERY_RUNTIME_INFO_GET, + + /** + * @DRM_PVR_DEV_QUERY_QUIRKS_GET: The dev query args contain a pointer + * to &struct drm_pvr_dev_query_quirks. + */ + DRM_PVR_DEV_QUERY_QUIRKS_GET, + + /** + * @DRM_PVR_DEV_QUERY_ENHANCEMENTS_GET: The dev query args contain a + * pointer to &struct drm_pvr_dev_query_enhancements. + */ + DRM_PVR_DEV_QUERY_ENHANCEMENTS_GET, + + /** + * @DRM_PVR_DEV_QUERY_HEAP_INFO_GET: The dev query args contain a + * pointer to &struct drm_pvr_dev_query_heap_info. + */ + DRM_PVR_DEV_QUERY_HEAP_INFO_GET, + + /** + * @DRM_PVR_DEV_QUERY_STATIC_DATA_AREAS_GET: The dev query args contain + * a pointer to &struct drm_pvr_dev_query_static_data_areas. + */ + DRM_PVR_DEV_QUERY_STATIC_DATA_AREAS_GET, +}; + +/** + * struct drm_pvr_ioctl_dev_query_args - Arguments for %DRM_IOCTL_PVR_DEV_QUERY. + */ +struct drm_pvr_ioctl_dev_query_args { + /** + * @type: Type of query and output struct. See &enum drm_pvr_dev_query. + */ + __u32 type; + + /** + * @size: Size of the receiving struct, see @type. + * + * After a successful call this will be updated to the written byte + * length. + * Can also be used to get the minimum byte length (see @pointer). + * This allows additional fields to be appended to the structs in + * future. + */ + __u32 size; + + /** + * @pointer: Pointer to struct @type. + * + * Must be large enough to contain @size bytes. + * If pointer is NULL, the expected size will be returned in the @size + * field, but no other data will be written. + */ + __u64 pointer; +}; + +/** + * DOC: PowerVR IOCTL CREATE_BO interface + */ + +/** + * DOC: Flags for CREATE_BO + * + * We use "device" to refer to the GPU here because of the ambiguity between CPU and GPU in some + * fonts. + * + * Device mapping options + * :DRM_PVR_BO_BYPASS_DEVICE_CACHE: Specify that device accesses to this memory will bypass the + * cache. This is used for buffers that will either be regularly updated by the CPU (eg free + * lists) or will be accessed only once and therefore isn't worth caching (eg partial render + * buffers). + * By default, the device flushes its memory caches after every job, so this is not normally + * required for coherency. + * :DRM_PVR_BO_PM_FW_PROTECT: Specify that only the Parameter Manager (PM) and/or firmware + * processor should be allowed to access this memory when mapped to the device. It is not + * valid to specify this flag with DRM_PVR_BO_ALLOW_CPU_USERSPACE_ACCESS. + * + * CPU mapping options + * :DRM_PVR_BO_ALLOW_CPU_USERSPACE_ACCESS: Allow userspace to map and access the contents of this + * memory. It is not valid to specify this flag with DRM_PVR_BO_PM_FW_PROTECT. + */ +#define DRM_PVR_BO_BYPASS_DEVICE_CACHE _BITULL(0) +#define DRM_PVR_BO_PM_FW_PROTECT _BITULL(1) +#define DRM_PVR_BO_ALLOW_CPU_USERSPACE_ACCESS _BITULL(2) +/* Bits 3..63 are reserved. */ + +#define DRM_PVR_BO_FLAGS_MASK (DRM_PVR_BO_BYPASS_DEVICE_CACHE | DRM_PVR_BO_PM_FW_PROTECT | \ + DRM_PVR_BO_ALLOW_CPU_USERSPACE_ACCESS) + +/** + * struct drm_pvr_ioctl_create_bo_args - Arguments for %DRM_IOCTL_PVR_CREATE_BO + */ +struct drm_pvr_ioctl_create_bo_args { + /** + * @size: [IN] Size of buffer object to create. This must be page size + * aligned. + */ + __u64 size; + + /** + * @handle: [OUT] GEM handle of the new buffer object for use in + * userspace. + */ + __u32 handle; + + /** @_padding_c: Reserved. This field must be zeroed. */ + __u32 _padding_c; + + /** + * @flags: [IN] Options which will affect the behaviour of this + * creation operation and future mapping operations on the created + * object. This field must be a valid combination of ``DRM_PVR_BO_*`` + * values, with all bits marked as reserved set to zero. + */ + __u64 flags; +}; + +/** + * DOC: PowerVR IOCTL GET_BO_MMAP_OFFSET interface + */ + +/** + * struct drm_pvr_ioctl_get_bo_mmap_offset_args - Arguments for + * %DRM_IOCTL_PVR_GET_BO_MMAP_OFFSET + * + * Like other DRM drivers, the "mmap" IOCTL doesn't actually map any memory. + * Instead, it allocates a fake offset which refers to the specified buffer + * object. This offset can be used with a real mmap call on the DRM device + * itself. + */ +struct drm_pvr_ioctl_get_bo_mmap_offset_args { + /** @handle: [IN] GEM handle of the buffer object to be mapped. */ + __u32 handle; + + /** @_padding_4: Reserved. This field must be zeroed. */ + __u32 _padding_4; + + /** @offset: [OUT] Fake offset to use in the real mmap call. */ + __u64 offset; +}; + +/** + * DOC: PowerVR IOCTL CREATE_VM_CONTEXT and DESTROY_VM_CONTEXT interfaces + */ + +/** + * struct drm_pvr_ioctl_create_vm_context_args - Arguments for + * %DRM_IOCTL_PVR_CREATE_VM_CONTEXT + */ +struct drm_pvr_ioctl_create_vm_context_args { + /** @handle: [OUT] Handle for new VM context. */ + __u32 handle; + + /** @_padding_4: Reserved. This field must be zeroed. */ + __u32 _padding_4; +}; + +/** + * struct drm_pvr_ioctl_destroy_vm_context_args - Arguments for + * %DRM_IOCTL_PVR_DESTROY_VM_CONTEXT + */ +struct drm_pvr_ioctl_destroy_vm_context_args { + /** + * @handle: [IN] Handle for VM context to be destroyed. + */ + __u32 handle; + + /** @_padding_4: Reserved. This field must be zeroed. */ + __u32 _padding_4; +}; + +/** + * DOC: PowerVR IOCTL VM_MAP and VM_UNMAP interfaces + * + * The VM UAPI allows userspace to create buffer object mappings in GPU virtual address space. + * + * The client is responsible for managing GPU address space. It should allocate mappings within + * the heaps returned by %DRM_PVR_DEV_QUERY_HEAP_INFO_GET. + * + * %DRM_IOCTL_PVR_VM_MAP creates a new mapping. The client provides the target virtual address for + * the mapping. Size and offset within the mapped buffer object can be specified, so the client can + * partially map a buffer. + * + * %DRM_IOCTL_PVR_VM_UNMAP removes a mapping. The entire mapping will be removed from GPU address + * space only if the size of the mapping matches that known to the driver. + */ + +/** + * struct drm_pvr_ioctl_vm_map_args - Arguments for %DRM_IOCTL_PVR_VM_MAP. + */ +struct drm_pvr_ioctl_vm_map_args { + /** + * @vm_context_handle: [IN] Handle for VM context for this mapping to + * exist in. + */ + __u32 vm_context_handle; + + /** @flags: [IN] Flags which affect this mapping. Currently always 0. */ + __u32 flags; + + /** + * @device_addr: [IN] Requested device-virtual address for the mapping. + * This must be non-zero and aligned to the device page size for the + * heap containing the requested address. It is an error to specify an + * address which is not contained within one of the heaps returned by + * %DRM_PVR_DEV_QUERY_HEAP_INFO_GET. + */ + __u64 device_addr; + + /** + * @handle: [IN] Handle of the target buffer object. This must be a + * valid handle returned by %DRM_IOCTL_PVR_CREATE_BO. + */ + __u32 handle; + + /** @_padding_14: Reserved. This field must be zeroed. */ + __u32 _padding_14; + + /** + * @offset: [IN] Offset into the target bo from which to begin the + * mapping. + */ + __u64 offset; + + /** + * @size: [IN] Size of the requested mapping. Must be aligned to + * the device page size for the heap containing the requested address, + * as well as the host page size. When added to @device_addr, the + * result must not overflow the heap which contains @device_addr (i.e. + * the range specified by @device_addr and @size must be completely + * contained within a single heap specified by + * %DRM_PVR_DEV_QUERY_HEAP_INFO_GET). + */ + __u64 size; +}; + +/** + * struct drm_pvr_ioctl_vm_unmap_args - Arguments for %DRM_IOCTL_PVR_VM_UNMAP. + */ +struct drm_pvr_ioctl_vm_unmap_args { + /** + * @vm_context_handle: [IN] Handle for VM context that this mapping + * exists in. + */ + __u32 vm_context_handle; + + /** @_padding_4: Reserved. This field must be zeroed. */ + __u32 _padding_4; + + /** + * @device_addr: [IN] Device-virtual address at the start of the target + * mapping. This must be non-zero. + */ + __u64 device_addr; + + /** + * @size: Size in bytes of the target mapping. This must be non-zero. + */ + __u64 size; +}; + +/** + * DOC: PowerVR IOCTL CREATE_CONTEXT and DESTROY_CONTEXT interfaces + */ + +/** + * enum drm_pvr_ctx_priority - Arguments for + * &drm_pvr_ioctl_create_context_args.priority + */ +enum drm_pvr_ctx_priority { + /** @DRM_PVR_CTX_PRIORITY_LOW: Priority below normal. */ + DRM_PVR_CTX_PRIORITY_LOW = -512, + + /** @DRM_PVR_CTX_PRIORITY_NORMAL: Normal priority. */ + DRM_PVR_CTX_PRIORITY_NORMAL = 0, + + /** + * @DRM_PVR_CTX_PRIORITY_HIGH: Priority above normal. + * Note this requires ``CAP_SYS_NICE`` or ``DRM_MASTER``. + */ + DRM_PVR_CTX_PRIORITY_HIGH = 512, +}; + +/** + * enum drm_pvr_ctx_type - Arguments for + * &struct drm_pvr_ioctl_create_context_args.type + */ +enum drm_pvr_ctx_type { + /** + * @DRM_PVR_CTX_TYPE_RENDER: Render context. + */ + DRM_PVR_CTX_TYPE_RENDER = 0, + + /** + * @DRM_PVR_CTX_TYPE_COMPUTE: Compute context. + */ + DRM_PVR_CTX_TYPE_COMPUTE, + + /** + * @DRM_PVR_CTX_TYPE_TRANSFER_FRAG: Transfer context for fragment data + * master. + */ + DRM_PVR_CTX_TYPE_TRANSFER_FRAG, +}; + +/** + * struct drm_pvr_ioctl_create_context_args - Arguments for + * %DRM_IOCTL_PVR_CREATE_CONTEXT + */ +struct drm_pvr_ioctl_create_context_args { + /** + * @type: [IN] Type of context to create. + * + * This must be one of the values defined by &enum drm_pvr_ctx_type. + */ + __u32 type; + + /** @flags: [IN] Flags for context. */ + __u32 flags; + + /** + * @priority: [IN] Priority of new context. + * + * This must be one of the values defined by &enum drm_pvr_ctx_priority. + */ + __s32 priority; + + /** @handle: [OUT] Handle for new context. */ + __u32 handle; + + /** + * @static_context_state: [IN] Pointer to static context state stream. + */ + __u64 static_context_state; + + /** + * @static_context_state_len: [IN] Length of static context state, in bytes. + */ + __u32 static_context_state_len; + + /** + * @vm_context_handle: [IN] Handle for VM context that this context is + * associated with. + */ + __u32 vm_context_handle; + + /** + * @callstack_addr: [IN] Address for initial call stack pointer. Only valid + * if @type is %DRM_PVR_CTX_TYPE_RENDER, otherwise must be 0. + */ + __u64 callstack_addr; +}; + +/** + * struct drm_pvr_ioctl_destroy_context_args - Arguments for + * %DRM_IOCTL_PVR_DESTROY_CONTEXT + */ +struct drm_pvr_ioctl_destroy_context_args { + /** + * @handle: [IN] Handle for context to be destroyed. + */ + __u32 handle; + + /** @_padding_4: Reserved. This field must be zeroed. */ + __u32 _padding_4; +}; + +/** + * DOC: PowerVR IOCTL CREATE_FREE_LIST and DESTROY_FREE_LIST interfaces + */ + +/** + * struct drm_pvr_ioctl_create_free_list_args - Arguments for + * %DRM_IOCTL_PVR_CREATE_FREE_LIST + * + * Free list arguments have the following constraints : + * + * - @max_num_pages must be greater than zero. + * - @grow_threshold must be between 0 and 100. + * - @grow_num_pages must be less than or equal to &max_num_pages. + * - @initial_num_pages, @max_num_pages and @grow_num_pages must be multiples + * of 4. + * - When &grow_num_pages is 0, @initial_num_pages must be equal to + * @max_num_pages. + * - When &grow_num_pages is non-zero, @initial_num_pages must be less than + * @max_num_pages. + */ +struct drm_pvr_ioctl_create_free_list_args { + /** + * @free_list_gpu_addr: [IN] Address of GPU mapping of buffer object + * containing memory to be used by free list. + * + * The mapped region of the buffer object must be at least + * @max_num_pages * ``sizeof(__u32)``. + * + * The buffer object must have been created with + * %DRM_PVR_BO_DEVICE_PM_FW_PROTECT set and + * %DRM_PVR_BO_CPU_ALLOW_USERSPACE_ACCESS not set. + */ + __u64 free_list_gpu_addr; + + /** @initial_num_pages: [IN] Pages initially allocated to free list. */ + __u32 initial_num_pages; + + /** @max_num_pages: [IN] Maximum number of pages in free list. */ + __u32 max_num_pages; + + /** @grow_num_pages: [IN] Pages to grow free list by per request. */ + __u32 grow_num_pages; + + /** + * @grow_threshold: [IN] Percentage of FL memory used that should + * trigger a new grow request. + */ + __u32 grow_threshold; + + /** + * @vm_context_handle: [IN] Handle for VM context that the free list buffer + * object is mapped in. + */ + __u32 vm_context_handle; + + /** + * @handle: [OUT] Handle for created free list. + */ + __u32 handle; +}; + +/** + * struct drm_pvr_ioctl_destroy_free_list_args - Arguments for + * %DRM_IOCTL_PVR_DESTROY_FREE_LIST + */ +struct drm_pvr_ioctl_destroy_free_list_args { + /** + * @handle: [IN] Handle for free list to be destroyed. + */ + __u32 handle; + + /** @_padding_4: Reserved. This field must be zeroed. */ + __u32 _padding_4; +}; + +/** + * DOC: PowerVR IOCTL CREATE_HWRT_DATASET and DESTROY_HWRT_DATASET interfaces + */ + +/** + * struct drm_pvr_create_hwrt_geom_data_args - Geometry data arguments used for + * &struct drm_pvr_ioctl_create_hwrt_dataset_args.geom_data_args. + */ +struct drm_pvr_create_hwrt_geom_data_args { + /** @tpc_dev_addr: [IN] Tail pointer cache GPU virtual address. */ + __u64 tpc_dev_addr; + + /** @tpc_size: [IN] Size of TPC, in bytes. */ + __u32 tpc_size; + + /** @tpc_stride: [IN] Stride between layers in TPC, in pages */ + __u32 tpc_stride; + + /** @vheap_table_dev_addr: [IN] VHEAP table GPU virtual address. */ + __u64 vheap_table_dev_addr; + + /** @rtc_dev_addr: [IN] Render Target Cache virtual address. */ + __u64 rtc_dev_addr; +}; + +/** + * struct drm_pvr_create_hwrt_rt_data_args - Render target arguments used for + * &struct drm_pvr_ioctl_create_hwrt_dataset_args.rt_data_args. + */ +struct drm_pvr_create_hwrt_rt_data_args { + /** @pm_mlist_dev_addr: [IN] PM MLIST GPU virtual address. */ + __u64 pm_mlist_dev_addr; + + /** @macrotile_array_dev_addr: [IN] Macrotile array GPU virtual address. */ + __u64 macrotile_array_dev_addr; + + /** @region_header_dev_addr: [IN] Region header array GPU virtual address. */ + __u64 region_header_dev_addr; +}; + +#define PVR_DRM_HWRT_FREE_LIST_LOCAL 0 +#define PVR_DRM_HWRT_FREE_LIST_GLOBAL 1U + +/** + * struct drm_pvr_ioctl_create_hwrt_dataset_args - Arguments for + * %DRM_IOCTL_PVR_CREATE_HWRT_DATASET + */ +struct drm_pvr_ioctl_create_hwrt_dataset_args { + /** @geom_data_args: [IN] Geometry data arguments. */ + struct drm_pvr_create_hwrt_geom_data_args geom_data_args; + + /** + * @rt_data_args: [IN] Array of render target arguments. + * + * Each entry in this array represents a render target in a double buffered + * setup. + */ + struct drm_pvr_create_hwrt_rt_data_args rt_data_args[2]; + + /** + * @free_list_handles: [IN] Array of free list handles. + * + * free_list_handles[PVR_DRM_HWRT_FREE_LIST_LOCAL] must have initial + * size of at least that reported by + * &drm_pvr_dev_query_runtime_info.free_list_min_pages. + */ + __u32 free_list_handles[2]; + + /** @width: [IN] Width in pixels. */ + __u32 width; + + /** @height: [IN] Height in pixels. */ + __u32 height; + + /** @samples: [IN] Number of samples. */ + __u32 samples; + + /** @layers: [IN] Number of layers. */ + __u32 layers; + + /** @isp_merge_lower_x: [IN] Lower X coefficient for triangle merging. */ + __u32 isp_merge_lower_x; + + /** @isp_merge_lower_y: [IN] Lower Y coefficient for triangle merging. */ + __u32 isp_merge_lower_y; + + /** @isp_merge_scale_x: [IN] Scale X coefficient for triangle merging. */ + __u32 isp_merge_scale_x; + + /** @isp_merge_scale_y: [IN] Scale Y coefficient for triangle merging. */ + __u32 isp_merge_scale_y; + + /** @isp_merge_upper_x: [IN] Upper X coefficient for triangle merging. */ + __u32 isp_merge_upper_x; + + /** @isp_merge_upper_y: [IN] Upper Y coefficient for triangle merging. */ + __u32 isp_merge_upper_y; + + /** + * @region_header_size: [IN] Size of region header array. This common field is used by + * both render targets in this data set. + * + * The units for this field differ depending on what version of the simple internal + * parameter format the device uses. If format 2 is in use then this is interpreted as the + * number of region headers. For other formats it is interpreted as the size in dwords. + */ + __u32 region_header_size; + + /** + * @handle: [OUT] Handle for created HWRT dataset. + */ + __u32 handle; +}; + +/** + * struct drm_pvr_ioctl_destroy_hwrt_dataset_args - Arguments for + * %DRM_IOCTL_PVR_DESTROY_HWRT_DATASET + */ +struct drm_pvr_ioctl_destroy_hwrt_dataset_args { + /** + * @handle: [IN] Handle for HWRT dataset to be destroyed. + */ + __u32 handle; + + /** @_padding_4: Reserved. This field must be zeroed. */ + __u32 _padding_4; +}; + +/** + * DOC: PowerVR IOCTL SUBMIT_JOBS interface + */ + +/** + * DOC: Flags for the drm_pvr_sync_op object. + * + * .. c:macro:: DRM_PVR_SYNC_OP_HANDLE_TYPE_MASK + * + * Handle type mask for the drm_pvr_sync_op::flags field. + * + * .. c:macro:: DRM_PVR_SYNC_OP_FLAG_HANDLE_TYPE_SYNCOBJ + * + * Indicates the handle passed in drm_pvr_sync_op::handle is a syncobj handle. + * This is the default type. + * + * .. c:macro:: DRM_PVR_SYNC_OP_FLAG_HANDLE_TYPE_TIMELINE_SYNCOBJ + * + * Indicates the handle passed in drm_pvr_sync_op::handle is a timeline syncobj handle. + * + * .. c:macro:: DRM_PVR_SYNC_OP_FLAG_SIGNAL + * + * Signal operation requested. The out-fence bound to the job will be attached to + * the syncobj whose handle is passed in drm_pvr_sync_op::handle. + * + * .. c:macro:: DRM_PVR_SYNC_OP_FLAG_WAIT + * + * Wait operation requested. The job will wait for this particular syncobj or syncobj + * point to be signaled before being started. + * This is the default operation. + */ +#define DRM_PVR_SYNC_OP_FLAG_HANDLE_TYPE_MASK 0xf +#define DRM_PVR_SYNC_OP_FLAG_HANDLE_TYPE_SYNCOBJ 0 +#define DRM_PVR_SYNC_OP_FLAG_HANDLE_TYPE_TIMELINE_SYNCOBJ 1 +#define DRM_PVR_SYNC_OP_FLAG_SIGNAL _BITULL(31) +#define DRM_PVR_SYNC_OP_FLAG_WAIT 0 + +#define DRM_PVR_SYNC_OP_FLAGS_MASK (DRM_PVR_SYNC_OP_FLAG_HANDLE_TYPE_MASK | \ + DRM_PVR_SYNC_OP_FLAG_SIGNAL) + +/** + * struct drm_pvr_sync_op - Object describing a sync operation + */ +struct drm_pvr_sync_op { + /** @handle: Handle of sync object. */ + __u32 handle; + + /** @flags: Combination of ``DRM_PVR_SYNC_OP_FLAG_`` flags. */ + __u32 flags; + + /** @value: Timeline value for this drm_syncobj. MBZ for a binary syncobj. */ + __u64 value; +}; + +/** + * DOC: Flags for SUBMIT_JOB ioctl geometry command. + * + * .. c:macro:: DRM_PVR_SUBMIT_JOB_GEOM_CMD_FIRST + * + * Indicates if this the first command to be issued for a render. + * + * .. c:macro:: DRM_PVR_SUBMIT_JOB_GEOM_CMD_LAST + * + * Indicates if this the last command to be issued for a render. + * + * .. c:macro:: DRM_PVR_SUBMIT_JOB_GEOM_CMD_SINGLE_CORE + * + * Forces to use single core in a multi core device. + * + * .. c:macro:: DRM_PVR_SUBMIT_JOB_GEOM_CMD_FLAGS_MASK + * + * Logical OR of all the geometry cmd flags. + */ +#define DRM_PVR_SUBMIT_JOB_GEOM_CMD_FIRST _BITULL(0) +#define DRM_PVR_SUBMIT_JOB_GEOM_CMD_LAST _BITULL(1) +#define DRM_PVR_SUBMIT_JOB_GEOM_CMD_SINGLE_CORE _BITULL(2) +#define DRM_PVR_SUBMIT_JOB_GEOM_CMD_FLAGS_MASK \ + (DRM_PVR_SUBMIT_JOB_GEOM_CMD_FIRST | \ + DRM_PVR_SUBMIT_JOB_GEOM_CMD_LAST | \ + DRM_PVR_SUBMIT_JOB_GEOM_CMD_SINGLE_CORE) + +/** + * DOC: Flags for SUBMIT_JOB ioctl fragment command. + * + * .. c:macro:: DRM_PVR_SUBMIT_JOB_FRAG_CMD_SINGLE_CORE + * + * Use single core in a multi core setup. + * + * .. c:macro:: DRM_PVR_SUBMIT_JOB_FRAG_CMD_DEPTHBUFFER + * + * Indicates whether a depth buffer is present. + * + * .. c:macro:: DRM_PVR_SUBMIT_JOB_FRAG_CMD_STENCILBUFFER + * + * Indicates whether a stencil buffer is present. + * + * .. c:macro:: DRM_PVR_SUBMIT_JOB_FRAG_CMD_PREVENT_CDM_OVERLAP + * + * Disallow compute overlapped with this render. + * + * .. c:macro:: DRM_PVR_SUBMIT_JOB_FRAG_CMD_GET_VIS_RESULTS + * + * Indicates whether this render produces visibility results. + * + * .. c:macro:: DRM_PVR_SUBMIT_JOB_FRAG_CMD_SCRATCHBUFFER + * + * Indicates whether partial renders write to a scratch buffer instead of + * the final surface. It also forces the full screen copy expected to be + * present on the last render after all partial renders have completed. + * + * .. c:macro:: DRM_PVR_SUBMIT_JOB_FRAG_CMD_DISABLE_PIXELMERGE + * + * Disable pixel merging for this render. + * + * .. c:macro:: DRM_PVR_SUBMIT_JOB_FRAG_CMD_FLAGS_MASK + * + * Logical OR of all the fragment cmd flags. + */ +#define DRM_PVR_SUBMIT_JOB_FRAG_CMD_SINGLE_CORE _BITULL(0) +#define DRM_PVR_SUBMIT_JOB_FRAG_CMD_DEPTHBUFFER _BITULL(1) +#define DRM_PVR_SUBMIT_JOB_FRAG_CMD_STENCILBUFFER _BITULL(2) +#define DRM_PVR_SUBMIT_JOB_FRAG_CMD_PREVENT_CDM_OVERLAP _BITULL(3) +#define DRM_PVR_SUBMIT_JOB_FRAG_CMD_SCRATCHBUFFER _BITULL(4) +#define DRM_PVR_SUBMIT_JOB_FRAG_CMD_GET_VIS_RESULTS _BITULL(5) +#define DRM_PVR_SUBMIT_JOB_FRAG_CMD_PARTIAL_RENDER _BITULL(6) +#define DRM_PVR_SUBMIT_JOB_FRAG_CMD_DISABLE_PIXELMERGE _BITULL(7) +#define DRM_PVR_SUBMIT_JOB_FRAG_CMD_FLAGS_MASK \ + (DRM_PVR_SUBMIT_JOB_FRAG_CMD_SINGLE_CORE | \ + DRM_PVR_SUBMIT_JOB_FRAG_CMD_DEPTHBUFFER | \ + DRM_PVR_SUBMIT_JOB_FRAG_CMD_STENCILBUFFER | \ + DRM_PVR_SUBMIT_JOB_FRAG_CMD_PREVENT_CDM_OVERLAP | \ + DRM_PVR_SUBMIT_JOB_FRAG_CMD_SCRATCHBUFFER | \ + DRM_PVR_SUBMIT_JOB_FRAG_CMD_GET_VIS_RESULTS | \ + DRM_PVR_SUBMIT_JOB_FRAG_CMD_PARTIAL_RENDER | \ + DRM_PVR_SUBMIT_JOB_FRAG_CMD_DISABLE_PIXELMERGE) + +/** + * DOC: Flags for SUBMIT_JOB ioctl compute command. + * + * .. c:macro:: DRM_PVR_SUBMIT_JOB_COMPUTE_CMD_PREVENT_ALL_OVERLAP + * + * Disallow other jobs overlapped with this compute. + * + * .. c:macro:: DRM_PVR_SUBMIT_JOB_COMPUTE_CMD_SINGLE_CORE + * + * Forces to use single core in a multi core device. + * + * .. c:macro:: DRM_PVR_SUBMIT_JOB_COMPUTE_CMD_FLAGS_MASK + * + * Logical OR of all the compute cmd flags. + */ +#define DRM_PVR_SUBMIT_JOB_COMPUTE_CMD_PREVENT_ALL_OVERLAP _BITULL(0) +#define DRM_PVR_SUBMIT_JOB_COMPUTE_CMD_SINGLE_CORE _BITULL(1) +#define DRM_PVR_SUBMIT_JOB_COMPUTE_CMD_FLAGS_MASK \ + (DRM_PVR_SUBMIT_JOB_COMPUTE_CMD_PREVENT_ALL_OVERLAP | \ + DRM_PVR_SUBMIT_JOB_COMPUTE_CMD_SINGLE_CORE) + +/** + * DOC: Flags for SUBMIT_JOB ioctl transfer command. + * + * .. c:macro:: DRM_PVR_SUBMIT_JOB_TRANSFER_CMD_SINGLE_CORE + * + * Forces job to use a single core in a multi core device. + * + * .. c:macro:: DRM_PVR_SUBMIT_JOB_TRANSFER_CMD_FLAGS_MASK + * + * Logical OR of all the transfer cmd flags. + */ +#define DRM_PVR_SUBMIT_JOB_TRANSFER_CMD_SINGLE_CORE _BITULL(0) + +#define DRM_PVR_SUBMIT_JOB_TRANSFER_CMD_FLAGS_MASK \ + DRM_PVR_SUBMIT_JOB_TRANSFER_CMD_SINGLE_CORE + +/** + * enum drm_pvr_job_type - Arguments for &struct drm_pvr_job.job_type + */ +enum drm_pvr_job_type { + /** @DRM_PVR_JOB_TYPE_GEOMETRY: Job type is geometry. */ + DRM_PVR_JOB_TYPE_GEOMETRY = 0, + + /** @DRM_PVR_JOB_TYPE_FRAGMENT: Job type is fragment. */ + DRM_PVR_JOB_TYPE_FRAGMENT, + + /** @DRM_PVR_JOB_TYPE_COMPUTE: Job type is compute. */ + DRM_PVR_JOB_TYPE_COMPUTE, + + /** @DRM_PVR_JOB_TYPE_TRANSFER_FRAG: Job type is a fragment transfer. */ + DRM_PVR_JOB_TYPE_TRANSFER_FRAG, +}; + +/** + * struct drm_pvr_hwrt_data_ref - Reference HWRT data + */ +struct drm_pvr_hwrt_data_ref { + /** @set_handle: HWRT data set handle. */ + __u32 set_handle; + + /** @data_index: Index of the HWRT data inside the data set. */ + __u32 data_index; +}; + +/** + * struct drm_pvr_job - Job arguments passed to the %DRM_IOCTL_PVR_SUBMIT_JOBS ioctl + */ +struct drm_pvr_job { + /** + * @type: [IN] Type of job being submitted + * + * This must be one of the values defined by &enum drm_pvr_job_type. + */ + __u32 type; + + /** + * @context_handle: [IN] Context handle. + * + * When @job_type is %DRM_PVR_JOB_TYPE_RENDER, %DRM_PVR_JOB_TYPE_COMPUTE or + * %DRM_PVR_JOB_TYPE_TRANSFER_FRAG, this must be a valid handle returned by + * %DRM_IOCTL_PVR_CREATE_CONTEXT. The type of context must be compatible + * with the type of job being submitted. + * + * When @job_type is %DRM_PVR_JOB_TYPE_NULL, this must be zero. + */ + __u32 context_handle; + + /** + * @flags: [IN] Flags for command. + * + * Those are job-dependent. See all ``DRM_PVR_SUBMIT_JOB_*``. + */ + __u32 flags; + + /** + * @cmd_stream_len: [IN] Length of command stream, in bytes. + */ + __u32 cmd_stream_len; + + /** + * @cmd_stream: [IN] Pointer to command stream for command. + * + * The command stream must be u64-aligned. + */ + __u64 cmd_stream; + + /** @sync_ops: [IN] Fragment sync operations. */ + struct drm_pvr_obj_array sync_ops; + + /** + * @hwrt: [IN] HWRT data used by render jobs (geometry or fragment). + * + * Must be zero for non-render jobs. + */ + struct drm_pvr_hwrt_data_ref hwrt; +}; + +/** + * struct drm_pvr_ioctl_submit_jobs_args - Arguments for %DRM_IOCTL_PVR_SUBMIT_JOB + * + * If the syscall returns an error it is important to check the value of + * @jobs.count. This indicates the index into @jobs.array where the + * error occurred. + */ +struct drm_pvr_ioctl_submit_jobs_args { + /** @jobs: [IN] Array of jobs to submit. */ + struct drm_pvr_obj_array jobs; +}; + +#if defined(__cplusplus) +} +#endif + +#endif /* PVR_DRM_UAPI_H */ diff --git a/include/uapi/drm/qaic_accel.h b/include/uapi/drm/qaic_accel.h index 43ac5d8645..9dab32316a 100644 --- a/include/uapi/drm/qaic_accel.h +++ b/include/uapi/drm/qaic_accel.h @@ -287,8 +287,9 @@ struct qaic_execute_entry { * struct qaic_partial_execute_entry - Defines a BO to resize and submit. * @handle: In. GEM handle of the BO to commit to the device. * @dir: In. Direction of data. 1 = to device, 2 = from device. - * @resize: In. New size of the BO. Must be <= the original BO size. 0 is - * short for no resize. + * @resize: In. New size of the BO. Must be <= the original BO size. + * @resize as 0 would be interpreted as no DMA transfer is + * involved. */ struct qaic_partial_execute_entry { __u32 handle; diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h index 3dfc0af875..dce1835ece 100644 --- a/include/uapi/drm/v3d_drm.h +++ b/include/uapi/drm/v3d_drm.h @@ -41,6 +41,7 @@ extern "C" { #define DRM_V3D_PERFMON_CREATE 0x08 #define DRM_V3D_PERFMON_DESTROY 0x09 #define DRM_V3D_PERFMON_GET_VALUES 0x0a +#define DRM_V3D_SUBMIT_CPU 0x0b #define DRM_IOCTL_V3D_SUBMIT_CL DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CL, struct drm_v3d_submit_cl) #define DRM_IOCTL_V3D_WAIT_BO DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_WAIT_BO, struct drm_v3d_wait_bo) @@ -56,6 +57,7 @@ extern "C" { struct drm_v3d_perfmon_destroy) #define DRM_IOCTL_V3D_PERFMON_GET_VALUES DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_GET_VALUES, \ struct drm_v3d_perfmon_get_values) +#define DRM_IOCTL_V3D_SUBMIT_CPU DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CPU, struct drm_v3d_submit_cpu) #define DRM_V3D_SUBMIT_CL_FLUSH_CACHE 0x01 #define DRM_V3D_SUBMIT_EXTENSION 0x02 @@ -69,7 +71,13 @@ extern "C" { struct drm_v3d_extension { __u64 next; __u32 id; -#define DRM_V3D_EXT_ID_MULTI_SYNC 0x01 +#define DRM_V3D_EXT_ID_MULTI_SYNC 0x01 +#define DRM_V3D_EXT_ID_CPU_INDIRECT_CSD 0x02 +#define DRM_V3D_EXT_ID_CPU_TIMESTAMP_QUERY 0x03 +#define DRM_V3D_EXT_ID_CPU_RESET_TIMESTAMP_QUERY 0x04 +#define DRM_V3D_EXT_ID_CPU_COPY_TIMESTAMP_QUERY 0x05 +#define DRM_V3D_EXT_ID_CPU_RESET_PERFORMANCE_QUERY 0x06 +#define DRM_V3D_EXT_ID_CPU_COPY_PERFORMANCE_QUERY 0x07 __u32 flags; /* mbz */ }; @@ -93,6 +101,7 @@ enum v3d_queue { V3D_TFU, V3D_CSD, V3D_CACHE_CLEAN, + V3D_CPU, }; /** @@ -276,6 +285,7 @@ enum drm_v3d_param { DRM_V3D_PARAM_SUPPORTS_CACHE_FLUSH, DRM_V3D_PARAM_SUPPORTS_PERFMON, DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT, + DRM_V3D_PARAM_SUPPORTS_CPU_QUEUE, }; struct drm_v3d_get_param { @@ -319,6 +329,11 @@ struct drm_v3d_submit_tfu { /* Pointer to an array of ioctl extensions*/ __u64 extensions; + + struct { + __u32 ioc; + __u32 pad; + } v71; }; /* Submits a compute shader for dispatch. This job will block on any @@ -356,6 +371,234 @@ struct drm_v3d_submit_csd { __u32 pad; }; +/** + * struct drm_v3d_indirect_csd - ioctl extension for the CPU job to create an + * indirect CSD + * + * When an extension of DRM_V3D_EXT_ID_CPU_INDIRECT_CSD id is defined, it + * points to this extension to define a indirect CSD submission. It creates a + * CPU job linked to a CSD job. The CPU job waits for the indirect CSD + * dependencies and, once they are signaled, it updates the CSD job config + * before allowing the CSD job execution. + */ +struct drm_v3d_indirect_csd { + struct drm_v3d_extension base; + + /* Indirect CSD */ + struct drm_v3d_submit_csd submit; + + /* Handle of the indirect BO, that should be also attached to the + * indirect CSD. + */ + __u32 indirect; + + /* Offset within the BO where the workgroup counts are stored */ + __u32 offset; + + /* Workgroups size */ + __u32 wg_size; + + /* Indices of the uniforms with the workgroup dispatch counts + * in the uniform stream. If the uniform rewrite is not needed, + * the offset must be 0xffffffff. + */ + __u32 wg_uniform_offsets[3]; +}; + +/** + * struct drm_v3d_timestamp_query - ioctl extension for the CPU job to calculate + * a timestamp query + * + * When an extension DRM_V3D_EXT_ID_TIMESTAMP_QUERY is defined, it points to + * this extension to define a timestamp query submission. This CPU job will + * calculate the timestamp query and update the query value within the + * timestamp BO. Moreover, it will signal the timestamp syncobj to indicate + * query availability. + */ +struct drm_v3d_timestamp_query { + struct drm_v3d_extension base; + + /* Array of queries' offsets within the timestamp BO for their value */ + __u64 offsets; + + /* Array of timestamp's syncobjs to indicate its availability */ + __u64 syncs; + + /* Number of queries */ + __u32 count; + + /* mbz */ + __u32 pad; +}; + +/** + * struct drm_v3d_reset_timestamp_query - ioctl extension for the CPU job to + * reset timestamp queries + * + * When an extension DRM_V3D_EXT_ID_CPU_RESET_TIMESTAMP_QUERY is defined, it + * points to this extension to define a reset timestamp submission. This CPU + * job will reset the timestamp queries based on value offset of the first + * query. Moreover, it will reset the timestamp syncobj to reset query + * availability. + */ +struct drm_v3d_reset_timestamp_query { + struct drm_v3d_extension base; + + /* Array of timestamp's syncobjs to indicate its availability */ + __u64 syncs; + + /* Offset of the first query within the timestamp BO for its value */ + __u32 offset; + + /* Number of queries */ + __u32 count; +}; + +/** + * struct drm_v3d_copy_timestamp_query - ioctl extension for the CPU job to copy + * query results to a buffer + * + * When an extension DRM_V3D_EXT_ID_CPU_COPY_TIMESTAMP_QUERY is defined, it + * points to this extension to define a copy timestamp query submission. This + * CPU job will copy the timestamp queries results to a BO with the offset + * and stride defined in the extension. + */ +struct drm_v3d_copy_timestamp_query { + struct drm_v3d_extension base; + + /* Define if should write to buffer using 64 or 32 bits */ + __u8 do_64bit; + + /* Define if it can write to buffer even if the query is not available */ + __u8 do_partial; + + /* Define if it should write availability bit to buffer */ + __u8 availability_bit; + + /* mbz */ + __u8 pad; + + /* Offset of the buffer in the BO */ + __u32 offset; + + /* Stride of the buffer in the BO */ + __u32 stride; + + /* Number of queries */ + __u32 count; + + /* Array of queries' offsets within the timestamp BO for their value */ + __u64 offsets; + + /* Array of timestamp's syncobjs to indicate its availability */ + __u64 syncs; +}; + +/** + * struct drm_v3d_reset_performance_query - ioctl extension for the CPU job to + * reset performance queries + * + * When an extension DRM_V3D_EXT_ID_CPU_RESET_PERFORMANCE_QUERY is defined, it + * points to this extension to define a reset performance submission. This CPU + * job will reset the performance queries by resetting the values of the + * performance monitors. Moreover, it will reset the syncobj to reset query + * availability. + */ +struct drm_v3d_reset_performance_query { + struct drm_v3d_extension base; + + /* Array of performance queries's syncobjs to indicate its availability */ + __u64 syncs; + + /* Number of queries */ + __u32 count; + + /* Number of performance monitors */ + __u32 nperfmons; + + /* Array of u64 user-pointers that point to an array of kperfmon_ids */ + __u64 kperfmon_ids; +}; + +/** + * struct drm_v3d_copy_performance_query - ioctl extension for the CPU job to copy + * performance query results to a buffer + * + * When an extension DRM_V3D_EXT_ID_CPU_COPY_PERFORMANCE_QUERY is defined, it + * points to this extension to define a copy performance query submission. This + * CPU job will copy the performance queries results to a BO with the offset + * and stride defined in the extension. + */ +struct drm_v3d_copy_performance_query { + struct drm_v3d_extension base; + + /* Define if should write to buffer using 64 or 32 bits */ + __u8 do_64bit; + + /* Define if it can write to buffer even if the query is not available */ + __u8 do_partial; + + /* Define if it should write availability bit to buffer */ + __u8 availability_bit; + + /* mbz */ + __u8 pad; + + /* Offset of the buffer in the BO */ + __u32 offset; + + /* Stride of the buffer in the BO */ + __u32 stride; + + /* Number of performance monitors */ + __u32 nperfmons; + + /* Number of performance counters related to this query pool */ + __u32 ncounters; + + /* Number of queries */ + __u32 count; + + /* Array of performance queries's syncobjs to indicate its availability */ + __u64 syncs; + + /* Array of u64 user-pointers that point to an array of kperfmon_ids */ + __u64 kperfmon_ids; +}; + +struct drm_v3d_submit_cpu { + /* Pointer to a u32 array of the BOs that are referenced by the job. + * + * For DRM_V3D_EXT_ID_CPU_INDIRECT_CSD, it must contain only one BO, + * that contains the workgroup counts. + * + * For DRM_V3D_EXT_ID_TIMESTAMP_QUERY, it must contain only one BO, + * that will contain the timestamp. + * + * For DRM_V3D_EXT_ID_CPU_RESET_TIMESTAMP_QUERY, it must contain only + * one BO, that contains the timestamp. + * + * For DRM_V3D_EXT_ID_CPU_COPY_TIMESTAMP_QUERY, it must contain two + * BOs. The first is the BO where the timestamp queries will be written + * to. The second is the BO that contains the timestamp. + * + * For DRM_V3D_EXT_ID_CPU_RESET_PERFORMANCE_QUERY, it must contain no + * BOs. + * + * For DRM_V3D_EXT_ID_CPU_COPY_PERFORMANCE_QUERY, it must contain one + * BO, where the performance queries will be written. + */ + __u64 bo_handles; + + /* Number of BO handles passed in (size is that times 4). */ + __u32 bo_handle_count; + + __u32 flags; + + /* Pointer to an array of ioctl extensions*/ + __u64 extensions; +}; + enum { V3D_PERFCNT_FEP_VALID_PRIMTS_NO_PIXELS, V3D_PERFCNT_FEP_VALID_PRIMS, diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h index b1d0e56565..c2ce71987e 100644 --- a/include/uapi/drm/virtgpu_drm.h +++ b/include/uapi/drm/virtgpu_drm.h @@ -97,6 +97,7 @@ struct drm_virtgpu_execbuffer { #define VIRTGPU_PARAM_CROSS_DEVICE 5 /* Cross virtio-device resource sharing */ #define VIRTGPU_PARAM_CONTEXT_INIT 6 /* DRM_VIRTGPU_CONTEXT_INIT */ #define VIRTGPU_PARAM_SUPPORTED_CAPSET_IDs 7 /* Bitmask of supported capability set ids */ +#define VIRTGPU_PARAM_EXPLICIT_DEBUG_NAME 8 /* Ability to set debug name from userspace */ struct drm_virtgpu_getparam { __u64 param; @@ -198,6 +199,7 @@ struct drm_virtgpu_resource_create_blob { #define VIRTGPU_CONTEXT_PARAM_CAPSET_ID 0x0001 #define VIRTGPU_CONTEXT_PARAM_NUM_RINGS 0x0002 #define VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK 0x0003 +#define VIRTGPU_CONTEXT_PARAM_DEBUG_NAME 0x0004 struct drm_virtgpu_context_set_param { __u64 param; __u64 value; diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h new file mode 100644 index 0000000000..bb0c8a9941 --- /dev/null +++ b/include/uapi/drm/xe_drm.h @@ -0,0 +1,1327 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2023 Intel Corporation + */ + +#ifndef _UAPI_XE_DRM_H_ +#define _UAPI_XE_DRM_H_ + +#include "drm.h" + +#if defined(__cplusplus) +extern "C" { +#endif + +/* + * Please note that modifications to all structs defined here are + * subject to backwards-compatibility constraints. + * Sections in this file are organized as follows: + * 1. IOCTL definition + * 2. Extension definition and helper structs + * 3. IOCTL's Query structs in the order of the Query's entries. + * 4. The rest of IOCTL structs in the order of IOCTL declaration. + */ + +/** + * DOC: Xe Device Block Diagram + * + * The diagram below represents a high-level simplification of a discrete + * GPU supported by the Xe driver. It shows some device components which + * are necessary to understand this API, as well as how their relations + * to each other. This diagram does not represent real hardware:: + * + * ┌──────────────────────────────────────────────────────────────────┐ + * │ ┌──────────────────────────────────────────────────┐ ┌─────────┐ │ + * │ │ ┌───────────────────────┐ ┌─────┐ │ │ ┌─────┐ │ │ + * │ │ │ VRAM0 ├───┤ ... │ │ │ │VRAM1│ │ │ + * │ │ └───────────┬───────────┘ └─GT1─┘ │ │ └──┬──┘ │ │ + * │ │ ┌──────────────────┴───────────────────────────┐ │ │ ┌──┴──┐ │ │ + * │ │ │ ┌─────────────────────┐ ┌─────────────────┐ │ │ │ │ │ │ │ + * │ │ │ │ ┌──┐ ┌──┐ ┌──┐ ┌──┐ │ │ ┌─────┐ ┌─────┐ │ │ │ │ │ │ │ │ + * │ │ │ │ │EU│ │EU│ │EU│ │EU│ │ │ │RCS0 │ │BCS0 │ │ │ │ │ │ │ │ │ + * │ │ │ │ └──┘ └──┘ └──┘ └──┘ │ │ └─────┘ └─────┘ │ │ │ │ │ │ │ │ + * │ │ │ │ ┌──┐ ┌──┐ ┌──┐ ┌──┐ │ │ ┌─────┐ ┌─────┐ │ │ │ │ │ │ │ │ + * │ │ │ │ │EU│ │EU│ │EU│ │EU│ │ │ │VCS0 │ │VCS1 │ │ │ │ │ │ │ │ │ + * │ │ │ │ └──┘ └──┘ └──┘ └──┘ │ │ └─────┘ └─────┘ │ │ │ │ │ │ │ │ + * │ │ │ │ ┌──┐ ┌──┐ ┌──┐ ┌──┐ │ │ ┌─────┐ ┌─────┐ │ │ │ │ │ │ │ │ + * │ │ │ │ │EU│ │EU│ │EU│ │EU│ │ │ │VECS0│ │VECS1│ │ │ │ │ │ ... │ │ │ + * │ │ │ │ └──┘ └──┘ └──┘ └──┘ │ │ └─────┘ └─────┘ │ │ │ │ │ │ │ │ + * │ │ │ │ ┌──┐ ┌──┐ ┌──┐ ┌──┐ │ │ ┌─────┐ ┌─────┐ │ │ │ │ │ │ │ │ + * │ │ │ │ │EU│ │EU│ │EU│ │EU│ │ │ │CCS0 │ │CCS1 │ │ │ │ │ │ │ │ │ + * │ │ │ │ └──┘ └──┘ └──┘ └──┘ │ │ └─────┘ └─────┘ │ │ │ │ │ │ │ │ + * │ │ │ └─────────DSS─────────┘ │ ┌─────┐ ┌─────┐ │ │ │ │ │ │ │ │ + * │ │ │ │ │CCS2 │ │CCS3 │ │ │ │ │ │ │ │ │ + * │ │ │ ┌─────┐ ┌─────┐ ┌─────┐ │ └─────┘ └─────┘ │ │ │ │ │ │ │ │ + * │ │ │ │ ... │ │ ... │ │ ... │ │ │ │ │ │ │ │ │ │ + * │ │ │ └─DSS─┘ └─DSS─┘ └─DSS─┘ └─────Engines─────┘ │ │ │ │ │ │ │ + * │ │ └───────────────────────────GT0────────────────┘ │ │ └─GT2─┘ │ │ + * │ └────────────────────────────Tile0─────────────────┘ └─ Tile1──┘ │ + * └─────────────────────────────Device0───────┬──────────────────────┘ + * │ + * ───────────────────────┴────────── PCI bus + */ + +/** + * DOC: Xe uAPI Overview + * + * This section aims to describe the Xe's IOCTL entries, its structs, and other + * Xe related uAPI such as uevents and PMU (Platform Monitoring Unit) related + * entries and usage. + * + * List of supported IOCTLs: + * - &DRM_IOCTL_XE_DEVICE_QUERY + * - &DRM_IOCTL_XE_GEM_CREATE + * - &DRM_IOCTL_XE_GEM_MMAP_OFFSET + * - &DRM_IOCTL_XE_VM_CREATE + * - &DRM_IOCTL_XE_VM_DESTROY + * - &DRM_IOCTL_XE_VM_BIND + * - &DRM_IOCTL_XE_EXEC_QUEUE_CREATE + * - &DRM_IOCTL_XE_EXEC_QUEUE_DESTROY + * - &DRM_IOCTL_XE_EXEC_QUEUE_GET_PROPERTY + * - &DRM_IOCTL_XE_EXEC + * - &DRM_IOCTL_XE_WAIT_USER_FENCE + */ + +/* + * xe specific ioctls. + * + * The device specific ioctl range is [DRM_COMMAND_BASE, DRM_COMMAND_END) ie + * [0x40, 0xa0) (a0 is excluded). The numbers below are defined as offset + * against DRM_COMMAND_BASE and should be between [0x0, 0x60). + */ +#define DRM_XE_DEVICE_QUERY 0x00 +#define DRM_XE_GEM_CREATE 0x01 +#define DRM_XE_GEM_MMAP_OFFSET 0x02 +#define DRM_XE_VM_CREATE 0x03 +#define DRM_XE_VM_DESTROY 0x04 +#define DRM_XE_VM_BIND 0x05 +#define DRM_XE_EXEC_QUEUE_CREATE 0x06 +#define DRM_XE_EXEC_QUEUE_DESTROY 0x07 +#define DRM_XE_EXEC_QUEUE_GET_PROPERTY 0x08 +#define DRM_XE_EXEC 0x09 +#define DRM_XE_WAIT_USER_FENCE 0x0a +/* Must be kept compact -- no holes */ + +#define DRM_IOCTL_XE_DEVICE_QUERY DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_DEVICE_QUERY, struct drm_xe_device_query) +#define DRM_IOCTL_XE_GEM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_GEM_CREATE, struct drm_xe_gem_create) +#define DRM_IOCTL_XE_GEM_MMAP_OFFSET DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_GEM_MMAP_OFFSET, struct drm_xe_gem_mmap_offset) +#define DRM_IOCTL_XE_VM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_VM_CREATE, struct drm_xe_vm_create) +#define DRM_IOCTL_XE_VM_DESTROY DRM_IOW(DRM_COMMAND_BASE + DRM_XE_VM_DESTROY, struct drm_xe_vm_destroy) +#define DRM_IOCTL_XE_VM_BIND DRM_IOW(DRM_COMMAND_BASE + DRM_XE_VM_BIND, struct drm_xe_vm_bind) +#define DRM_IOCTL_XE_EXEC_QUEUE_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_EXEC_QUEUE_CREATE, struct drm_xe_exec_queue_create) +#define DRM_IOCTL_XE_EXEC_QUEUE_DESTROY DRM_IOW(DRM_COMMAND_BASE + DRM_XE_EXEC_QUEUE_DESTROY, struct drm_xe_exec_queue_destroy) +#define DRM_IOCTL_XE_EXEC_QUEUE_GET_PROPERTY DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_EXEC_QUEUE_GET_PROPERTY, struct drm_xe_exec_queue_get_property) +#define DRM_IOCTL_XE_EXEC DRM_IOW(DRM_COMMAND_BASE + DRM_XE_EXEC, struct drm_xe_exec) +#define DRM_IOCTL_XE_WAIT_USER_FENCE DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_WAIT_USER_FENCE, struct drm_xe_wait_user_fence) + +/** + * DOC: Xe IOCTL Extensions + * + * Before detailing the IOCTLs and its structs, it is important to highlight + * that every IOCTL in Xe is extensible. + * + * Many interfaces need to grow over time. In most cases we can simply + * extend the struct and have userspace pass in more data. Another option, + * as demonstrated by Vulkan's approach to providing extensions for forward + * and backward compatibility, is to use a list of optional structs to + * provide those extra details. + * + * The key advantage to using an extension chain is that it allows us to + * redefine the interface more easily than an ever growing struct of + * increasing complexity, and for large parts of that interface to be + * entirely optional. The downside is more pointer chasing; chasing across + * the __user boundary with pointers encapsulated inside u64. + * + * Example chaining: + * + * .. code-block:: C + * + * struct drm_xe_user_extension ext3 { + * .next_extension = 0, // end + * .name = ..., + * }; + * struct drm_xe_user_extension ext2 { + * .next_extension = (uintptr_t)&ext3, + * .name = ..., + * }; + * struct drm_xe_user_extension ext1 { + * .next_extension = (uintptr_t)&ext2, + * .name = ..., + * }; + * + * Typically the struct drm_xe_user_extension would be embedded in some uAPI + * struct, and in this case we would feed it the head of the chain(i.e ext1), + * which would then apply all of the above extensions. +*/ + +/** + * struct drm_xe_user_extension - Base class for defining a chain of extensions + */ +struct drm_xe_user_extension { + /** + * @next_extension: + * + * Pointer to the next struct drm_xe_user_extension, or zero if the end. + */ + __u64 next_extension; + + /** + * @name: Name of the extension. + * + * Note that the name here is just some integer. + * + * Also note that the name space for this is not global for the whole + * driver, but rather its scope/meaning is limited to the specific piece + * of uAPI which has embedded the struct drm_xe_user_extension. + */ + __u32 name; + + /** + * @pad: MBZ + * + * All undefined bits must be zero. + */ + __u32 pad; +}; + +/** + * struct drm_xe_ext_set_property - Generic set property extension + * + * A generic struct that allows any of the Xe's IOCTL to be extended + * with a set_property operation. + */ +struct drm_xe_ext_set_property { + /** @base: base user extension */ + struct drm_xe_user_extension base; + + /** @property: property to set */ + __u32 property; + + /** @pad: MBZ */ + __u32 pad; + + /** @value: property value */ + __u64 value; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_engine_class_instance - instance of an engine class + * + * It is returned as part of the @drm_xe_engine, but it also is used as + * the input of engine selection for both @drm_xe_exec_queue_create and + * @drm_xe_query_engine_cycles + * + * The @engine_class can be: + * - %DRM_XE_ENGINE_CLASS_RENDER + * - %DRM_XE_ENGINE_CLASS_COPY + * - %DRM_XE_ENGINE_CLASS_VIDEO_DECODE + * - %DRM_XE_ENGINE_CLASS_VIDEO_ENHANCE + * - %DRM_XE_ENGINE_CLASS_COMPUTE + * - %DRM_XE_ENGINE_CLASS_VM_BIND - Kernel only classes (not actual + * hardware engine class). Used for creating ordered queues of VM + * bind operations. + */ +struct drm_xe_engine_class_instance { +#define DRM_XE_ENGINE_CLASS_RENDER 0 +#define DRM_XE_ENGINE_CLASS_COPY 1 +#define DRM_XE_ENGINE_CLASS_VIDEO_DECODE 2 +#define DRM_XE_ENGINE_CLASS_VIDEO_ENHANCE 3 +#define DRM_XE_ENGINE_CLASS_COMPUTE 4 +#define DRM_XE_ENGINE_CLASS_VM_BIND 5 + /** @engine_class: engine class id */ + __u16 engine_class; + /** @engine_instance: engine instance id */ + __u16 engine_instance; + /** @gt_id: Unique ID of this GT within the PCI Device */ + __u16 gt_id; + /** @pad: MBZ */ + __u16 pad; +}; + +/** + * struct drm_xe_engine - describe hardware engine + */ +struct drm_xe_engine { + /** @instance: The @drm_xe_engine_class_instance */ + struct drm_xe_engine_class_instance instance; + + /** @reserved: Reserved */ + __u64 reserved[3]; +}; + +/** + * struct drm_xe_query_engines - describe engines + * + * If a query is made with a struct @drm_xe_device_query where .query + * is equal to %DRM_XE_DEVICE_QUERY_ENGINES, then the reply uses an array of + * struct @drm_xe_query_engines in .data. + */ +struct drm_xe_query_engines { + /** @num_engines: number of engines returned in @engines */ + __u32 num_engines; + /** @pad: MBZ */ + __u32 pad; + /** @engines: The returned engines for this device */ + struct drm_xe_engine engines[]; +}; + +/** + * enum drm_xe_memory_class - Supported memory classes. + */ +enum drm_xe_memory_class { + /** @DRM_XE_MEM_REGION_CLASS_SYSMEM: Represents system memory. */ + DRM_XE_MEM_REGION_CLASS_SYSMEM = 0, + /** + * @DRM_XE_MEM_REGION_CLASS_VRAM: On discrete platforms, this + * represents the memory that is local to the device, which we + * call VRAM. Not valid on integrated platforms. + */ + DRM_XE_MEM_REGION_CLASS_VRAM +}; + +/** + * struct drm_xe_mem_region - Describes some region as known to + * the driver. + */ +struct drm_xe_mem_region { + /** + * @mem_class: The memory class describing this region. + * + * See enum drm_xe_memory_class for supported values. + */ + __u16 mem_class; + /** + * @instance: The unique ID for this region, which serves as the + * index in the placement bitmask used as argument for + * &DRM_IOCTL_XE_GEM_CREATE + */ + __u16 instance; + /** + * @min_page_size: Min page-size in bytes for this region. + * + * When the kernel allocates memory for this region, the + * underlying pages will be at least @min_page_size in size. + * Buffer objects with an allowable placement in this region must be + * created with a size aligned to this value. + * GPU virtual address mappings of (parts of) buffer objects that + * may be placed in this region must also have their GPU virtual + * address and range aligned to this value. + * Affected IOCTLS will return %-EINVAL if alignment restrictions are + * not met. + */ + __u32 min_page_size; + /** + * @total_size: The usable size in bytes for this region. + */ + __u64 total_size; + /** + * @used: Estimate of the memory used in bytes for this region. + * + * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable + * accounting. Without this the value here will always equal + * zero. + */ + __u64 used; + /** + * @cpu_visible_size: How much of this region can be CPU + * accessed, in bytes. + * + * This will always be <= @total_size, and the remainder (if + * any) will not be CPU accessible. If the CPU accessible part + * is smaller than @total_size then this is referred to as a + * small BAR system. + * + * On systems without small BAR (full BAR), the probed_size will + * always equal the @total_size, since all of it will be CPU + * accessible. + * + * Note this is only tracked for DRM_XE_MEM_REGION_CLASS_VRAM + * regions (for other types the value here will always equal + * zero). + */ + __u64 cpu_visible_size; + /** + * @cpu_visible_used: Estimate of CPU visible memory used, in + * bytes. + * + * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable + * accounting. Without this the value here will always equal + * zero. Note this is only currently tracked for + * DRM_XE_MEM_REGION_CLASS_VRAM regions (for other types the value + * here will always be zero). + */ + __u64 cpu_visible_used; + /** @reserved: Reserved */ + __u64 reserved[6]; +}; + +/** + * struct drm_xe_query_mem_regions - describe memory regions + * + * If a query is made with a struct drm_xe_device_query where .query + * is equal to DRM_XE_DEVICE_QUERY_MEM_REGIONS, then the reply uses + * struct drm_xe_query_mem_regions in .data. + */ +struct drm_xe_query_mem_regions { + /** @num_mem_regions: number of memory regions returned in @mem_regions */ + __u32 num_mem_regions; + /** @pad: MBZ */ + __u32 pad; + /** @mem_regions: The returned memory regions for this device */ + struct drm_xe_mem_region mem_regions[]; +}; + +/** + * struct drm_xe_query_config - describe the device configuration + * + * If a query is made with a struct drm_xe_device_query where .query + * is equal to DRM_XE_DEVICE_QUERY_CONFIG, then the reply uses + * struct drm_xe_query_config in .data. + * + * The index in @info can be: + * - %DRM_XE_QUERY_CONFIG_REV_AND_DEVICE_ID - Device ID (lower 16 bits) + * and the device revision (next 8 bits) + * - %DRM_XE_QUERY_CONFIG_FLAGS - Flags describing the device + * configuration, see list below + * + * - %DRM_XE_QUERY_CONFIG_FLAG_HAS_VRAM - Flag is set if the device + * has usable VRAM + * - %DRM_XE_QUERY_CONFIG_MIN_ALIGNMENT - Minimal memory alignment + * required by this device, typically SZ_4K or SZ_64K + * - %DRM_XE_QUERY_CONFIG_VA_BITS - Maximum bits of a virtual address + * - %DRM_XE_QUERY_CONFIG_MAX_EXEC_QUEUE_PRIORITY - Value of the highest + * available exec queue priority + */ +struct drm_xe_query_config { + /** @num_params: number of parameters returned in info */ + __u32 num_params; + + /** @pad: MBZ */ + __u32 pad; + +#define DRM_XE_QUERY_CONFIG_REV_AND_DEVICE_ID 0 +#define DRM_XE_QUERY_CONFIG_FLAGS 1 + #define DRM_XE_QUERY_CONFIG_FLAG_HAS_VRAM (1 << 0) +#define DRM_XE_QUERY_CONFIG_MIN_ALIGNMENT 2 +#define DRM_XE_QUERY_CONFIG_VA_BITS 3 +#define DRM_XE_QUERY_CONFIG_MAX_EXEC_QUEUE_PRIORITY 4 + /** @info: array of elements containing the config info */ + __u64 info[]; +}; + +/** + * struct drm_xe_gt - describe an individual GT. + * + * To be used with drm_xe_query_gt_list, which will return a list with all the + * existing GT individual descriptions. + * Graphics Technology (GT) is a subset of a GPU/tile that is responsible for + * implementing graphics and/or media operations. + * + * The index in @type can be: + * - %DRM_XE_QUERY_GT_TYPE_MAIN + * - %DRM_XE_QUERY_GT_TYPE_MEDIA + */ +struct drm_xe_gt { +#define DRM_XE_QUERY_GT_TYPE_MAIN 0 +#define DRM_XE_QUERY_GT_TYPE_MEDIA 1 + /** @type: GT type: Main or Media */ + __u16 type; + /** @tile_id: Tile ID where this GT lives (Information only) */ + __u16 tile_id; + /** @gt_id: Unique ID of this GT within the PCI Device */ + __u16 gt_id; + /** @pad: MBZ */ + __u16 pad[3]; + /** @reference_clock: A clock frequency for timestamp */ + __u32 reference_clock; + /** + * @near_mem_regions: Bit mask of instances from + * drm_xe_query_mem_regions that are nearest to the current engines + * of this GT. + * Each index in this mask refers directly to the struct + * drm_xe_query_mem_regions' instance, no assumptions should + * be made about order. The type of each region is described + * by struct drm_xe_query_mem_regions' mem_class. + */ + __u64 near_mem_regions; + /** + * @far_mem_regions: Bit mask of instances from + * drm_xe_query_mem_regions that are far from the engines of this GT. + * In general, they have extra indirections when compared to the + * @near_mem_regions. For a discrete device this could mean system + * memory and memory living in a different tile. + * Each index in this mask refers directly to the struct + * drm_xe_query_mem_regions' instance, no assumptions should + * be made about order. The type of each region is described + * by struct drm_xe_query_mem_regions' mem_class. + */ + __u64 far_mem_regions; + /** @reserved: Reserved */ + __u64 reserved[8]; +}; + +/** + * struct drm_xe_query_gt_list - A list with GT description items. + * + * If a query is made with a struct drm_xe_device_query where .query + * is equal to DRM_XE_DEVICE_QUERY_GT_LIST, then the reply uses struct + * drm_xe_query_gt_list in .data. + */ +struct drm_xe_query_gt_list { + /** @num_gt: number of GT items returned in gt_list */ + __u32 num_gt; + /** @pad: MBZ */ + __u32 pad; + /** @gt_list: The GT list returned for this device */ + struct drm_xe_gt gt_list[]; +}; + +/** + * struct drm_xe_query_topology_mask - describe the topology mask of a GT + * + * This is the hardware topology which reflects the internal physical + * structure of the GPU. + * + * If a query is made with a struct drm_xe_device_query where .query + * is equal to DRM_XE_DEVICE_QUERY_GT_TOPOLOGY, then the reply uses + * struct drm_xe_query_topology_mask in .data. + * + * The @type can be: + * - %DRM_XE_TOPO_DSS_GEOMETRY - To query the mask of Dual Sub Slices + * (DSS) available for geometry operations. For example a query response + * containing the following in mask: + * ``DSS_GEOMETRY ff ff ff ff 00 00 00 00`` + * means 32 DSS are available for geometry. + * - %DRM_XE_TOPO_DSS_COMPUTE - To query the mask of Dual Sub Slices + * (DSS) available for compute operations. For example a query response + * containing the following in mask: + * ``DSS_COMPUTE ff ff ff ff 00 00 00 00`` + * means 32 DSS are available for compute. + * - %DRM_XE_TOPO_EU_PER_DSS - To query the mask of Execution Units (EU) + * available per Dual Sub Slices (DSS). For example a query response + * containing the following in mask: + * ``EU_PER_DSS ff ff 00 00 00 00 00 00`` + * means each DSS has 16 EU. + */ +struct drm_xe_query_topology_mask { + /** @gt_id: GT ID the mask is associated with */ + __u16 gt_id; + +#define DRM_XE_TOPO_DSS_GEOMETRY (1 << 0) +#define DRM_XE_TOPO_DSS_COMPUTE (1 << 1) +#define DRM_XE_TOPO_EU_PER_DSS (1 << 2) + /** @type: type of mask */ + __u16 type; + + /** @num_bytes: number of bytes in requested mask */ + __u32 num_bytes; + + /** @mask: little-endian mask of @num_bytes */ + __u8 mask[]; +}; + +/** + * struct drm_xe_query_engine_cycles - correlate CPU and GPU timestamps + * + * If a query is made with a struct drm_xe_device_query where .query is equal to + * DRM_XE_DEVICE_QUERY_ENGINE_CYCLES, then the reply uses struct drm_xe_query_engine_cycles + * in .data. struct drm_xe_query_engine_cycles is allocated by the user and + * .data points to this allocated structure. + * + * The query returns the engine cycles, which along with GT's @reference_clock, + * can be used to calculate the engine timestamp. In addition the + * query returns a set of cpu timestamps that indicate when the command + * streamer cycle count was captured. + */ +struct drm_xe_query_engine_cycles { + /** + * @eci: This is input by the user and is the engine for which command + * streamer cycles is queried. + */ + struct drm_xe_engine_class_instance eci; + + /** + * @clockid: This is input by the user and is the reference clock id for + * CPU timestamp. For definition, see clock_gettime(2) and + * perf_event_open(2). Supported clock ids are CLOCK_MONOTONIC, + * CLOCK_MONOTONIC_RAW, CLOCK_REALTIME, CLOCK_BOOTTIME, CLOCK_TAI. + */ + __s32 clockid; + + /** @width: Width of the engine cycle counter in bits. */ + __u32 width; + + /** + * @engine_cycles: Engine cycles as read from its register + * at 0x358 offset. + */ + __u64 engine_cycles; + + /** + * @cpu_timestamp: CPU timestamp in ns. The timestamp is captured before + * reading the engine_cycles register using the reference clockid set by the + * user. + */ + __u64 cpu_timestamp; + + /** + * @cpu_delta: Time delta in ns captured around reading the lower dword + * of the engine_cycles register. + */ + __u64 cpu_delta; +}; + +/** + * struct drm_xe_device_query - Input of &DRM_IOCTL_XE_DEVICE_QUERY - main + * structure to query device information + * + * The user selects the type of data to query among DRM_XE_DEVICE_QUERY_* + * and sets the value in the query member. This determines the type of + * the structure provided by the driver in data, among struct drm_xe_query_*. + * + * The @query can be: + * - %DRM_XE_DEVICE_QUERY_ENGINES + * - %DRM_XE_DEVICE_QUERY_MEM_REGIONS + * - %DRM_XE_DEVICE_QUERY_CONFIG + * - %DRM_XE_DEVICE_QUERY_GT_LIST + * - %DRM_XE_DEVICE_QUERY_HWCONFIG - Query type to retrieve the hardware + * configuration of the device such as information on slices, memory, + * caches, and so on. It is provided as a table of key / value + * attributes. + * - %DRM_XE_DEVICE_QUERY_GT_TOPOLOGY + * - %DRM_XE_DEVICE_QUERY_ENGINE_CYCLES + * + * If size is set to 0, the driver fills it with the required size for + * the requested type of data to query. If size is equal to the required + * size, the queried information is copied into data. If size is set to + * a value different from 0 and different from the required size, the + * IOCTL call returns -EINVAL. + * + * For example the following code snippet allows retrieving and printing + * information about the device engines with DRM_XE_DEVICE_QUERY_ENGINES: + * + * .. code-block:: C + * + * struct drm_xe_query_engines *engines; + * struct drm_xe_device_query query = { + * .extensions = 0, + * .query = DRM_XE_DEVICE_QUERY_ENGINES, + * .size = 0, + * .data = 0, + * }; + * ioctl(fd, DRM_IOCTL_XE_DEVICE_QUERY, &query); + * engines = malloc(query.size); + * query.data = (uintptr_t)engines; + * ioctl(fd, DRM_IOCTL_XE_DEVICE_QUERY, &query); + * for (int i = 0; i < engines->num_engines; i++) { + * printf("Engine %d: %s\n", i, + * engines->engines[i].instance.engine_class == + * DRM_XE_ENGINE_CLASS_RENDER ? "RENDER": + * engines->engines[i].instance.engine_class == + * DRM_XE_ENGINE_CLASS_COPY ? "COPY": + * engines->engines[i].instance.engine_class == + * DRM_XE_ENGINE_CLASS_VIDEO_DECODE ? "VIDEO_DECODE": + * engines->engines[i].instance.engine_class == + * DRM_XE_ENGINE_CLASS_VIDEO_ENHANCE ? "VIDEO_ENHANCE": + * engines->engines[i].instance.engine_class == + * DRM_XE_ENGINE_CLASS_COMPUTE ? "COMPUTE": + * "UNKNOWN"); + * } + * free(engines); + */ +struct drm_xe_device_query { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + +#define DRM_XE_DEVICE_QUERY_ENGINES 0 +#define DRM_XE_DEVICE_QUERY_MEM_REGIONS 1 +#define DRM_XE_DEVICE_QUERY_CONFIG 2 +#define DRM_XE_DEVICE_QUERY_GT_LIST 3 +#define DRM_XE_DEVICE_QUERY_HWCONFIG 4 +#define DRM_XE_DEVICE_QUERY_GT_TOPOLOGY 5 +#define DRM_XE_DEVICE_QUERY_ENGINE_CYCLES 6 + /** @query: The type of data to query */ + __u32 query; + + /** @size: Size of the queried data */ + __u32 size; + + /** @data: Queried data is placed here */ + __u64 data; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_gem_create - Input of &DRM_IOCTL_XE_GEM_CREATE - A structure for + * gem creation + * + * The @flags can be: + * - %DRM_XE_GEM_CREATE_FLAG_DEFER_BACKING + * - %DRM_XE_GEM_CREATE_FLAG_SCANOUT + * - %DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM - When using VRAM as a + * possible placement, ensure that the corresponding VRAM allocation + * will always use the CPU accessible part of VRAM. This is important + * for small-bar systems (on full-bar systems this gets turned into a + * noop). + * Note1: System memory can be used as an extra placement if the kernel + * should spill the allocation to system memory, if space can't be made + * available in the CPU accessible part of VRAM (giving the same + * behaviour as the i915 interface, see + * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS). + * Note2: For clear-color CCS surfaces the kernel needs to read the + * clear-color value stored in the buffer, and on discrete platforms we + * need to use VRAM for display surfaces, therefore the kernel requires + * setting this flag for such objects, otherwise an error is thrown on + * small-bar systems. + * + * @cpu_caching supports the following values: + * - %DRM_XE_GEM_CPU_CACHING_WB - Allocate the pages with write-back + * caching. On iGPU this can't be used for scanout surfaces. Currently + * not allowed for objects placed in VRAM. + * - %DRM_XE_GEM_CPU_CACHING_WC - Allocate the pages as write-combined. This + * is uncached. Scanout surfaces should likely use this. All objects + * that can be placed in VRAM must use this. + */ +struct drm_xe_gem_create { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + + /** + * @size: Size of the object to be created, must match region + * (system or vram) minimum alignment (&min_page_size). + */ + __u64 size; + + /** + * @placement: A mask of memory instances of where BO can be placed. + * Each index in this mask refers directly to the struct + * drm_xe_query_mem_regions' instance, no assumptions should + * be made about order. The type of each region is described + * by struct drm_xe_query_mem_regions' mem_class. + */ + __u32 placement; + +#define DRM_XE_GEM_CREATE_FLAG_DEFER_BACKING (1 << 0) +#define DRM_XE_GEM_CREATE_FLAG_SCANOUT (1 << 1) +#define DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM (1 << 2) + /** + * @flags: Flags, currently a mask of memory instances of where BO can + * be placed + */ + __u32 flags; + + /** + * @vm_id: Attached VM, if any + * + * If a VM is specified, this BO must: + * + * 1. Only ever be bound to that VM. + * 2. Cannot be exported as a PRIME fd. + */ + __u32 vm_id; + + /** + * @handle: Returned handle for the object. + * + * Object handles are nonzero. + */ + __u32 handle; + +#define DRM_XE_GEM_CPU_CACHING_WB 1 +#define DRM_XE_GEM_CPU_CACHING_WC 2 + /** + * @cpu_caching: The CPU caching mode to select for this object. If + * mmaping the object the mode selected here will also be used. + */ + __u16 cpu_caching; + /** @pad: MBZ */ + __u16 pad[3]; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_gem_mmap_offset - Input of &DRM_IOCTL_XE_GEM_MMAP_OFFSET + */ +struct drm_xe_gem_mmap_offset { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + + /** @handle: Handle for the object being mapped. */ + __u32 handle; + + /** @flags: Must be zero */ + __u32 flags; + + /** @offset: The fake offset to use for subsequent mmap call */ + __u64 offset; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_vm_create - Input of &DRM_IOCTL_XE_VM_CREATE + * + * The @flags can be: + * - %DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE + * - %DRM_XE_VM_CREATE_FLAG_LR_MODE - An LR, or Long Running VM accepts + * exec submissions to its exec_queues that don't have an upper time + * limit on the job execution time. But exec submissions to these + * don't allow any of the flags DRM_XE_SYNC_FLAG_SYNCOBJ, + * DRM_XE_SYNC_FLAG_TIMELINE_SYNCOBJ, DRM_XE_SYNC_FLAG_DMA_BUF, + * used as out-syncobjs, that is, together with DRM_XE_SYNC_FLAG_SIGNAL. + * LR VMs can be created in recoverable page-fault mode using + * DRM_XE_VM_CREATE_FLAG_FAULT_MODE, if the device supports it. + * If that flag is omitted, the UMD can not rely on the slightly + * different per-VM overcommit semantics that are enabled by + * DRM_XE_VM_CREATE_FLAG_FAULT_MODE (see below), but KMD may + * still enable recoverable pagefaults if supported by the device. + * - %DRM_XE_VM_CREATE_FLAG_FAULT_MODE - Requires also + * DRM_XE_VM_CREATE_FLAG_LR_MODE. It allows memory to be allocated on + * demand when accessed, and also allows per-VM overcommit of memory. + * The xe driver internally uses recoverable pagefaults to implement + * this. + */ +struct drm_xe_vm_create { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + +#define DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE (1 << 0) +#define DRM_XE_VM_CREATE_FLAG_LR_MODE (1 << 1) +#define DRM_XE_VM_CREATE_FLAG_FAULT_MODE (1 << 2) + /** @flags: Flags */ + __u32 flags; + + /** @vm_id: Returned VM ID */ + __u32 vm_id; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_vm_destroy - Input of &DRM_IOCTL_XE_VM_DESTROY + */ +struct drm_xe_vm_destroy { + /** @vm_id: VM ID */ + __u32 vm_id; + + /** @pad: MBZ */ + __u32 pad; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_vm_bind_op - run bind operations + * + * The @op can be: + * - %DRM_XE_VM_BIND_OP_MAP + * - %DRM_XE_VM_BIND_OP_UNMAP + * - %DRM_XE_VM_BIND_OP_MAP_USERPTR + * - %DRM_XE_VM_BIND_OP_UNMAP_ALL + * - %DRM_XE_VM_BIND_OP_PREFETCH + * + * and the @flags can be: + * - %DRM_XE_VM_BIND_FLAG_NULL - When the NULL flag is set, the page + * tables are setup with a special bit which indicates writes are + * dropped and all reads return zero. In the future, the NULL flags + * will only be valid for DRM_XE_VM_BIND_OP_MAP operations, the BO + * handle MBZ, and the BO offset MBZ. This flag is intended to + * implement VK sparse bindings. + */ +struct drm_xe_vm_bind_op { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + + /** + * @obj: GEM object to operate on, MBZ for MAP_USERPTR, MBZ for UNMAP + */ + __u32 obj; + + /** + * @pat_index: The platform defined @pat_index to use for this mapping. + * The index basically maps to some predefined memory attributes, + * including things like caching, coherency, compression etc. The exact + * meaning of the pat_index is platform specific and defined in the + * Bspec and PRMs. When the KMD sets up the binding the index here is + * encoded into the ppGTT PTE. + * + * For coherency the @pat_index needs to be at least 1way coherent when + * drm_xe_gem_create.cpu_caching is DRM_XE_GEM_CPU_CACHING_WB. The KMD + * will extract the coherency mode from the @pat_index and reject if + * there is a mismatch (see note below for pre-MTL platforms). + * + * Note: On pre-MTL platforms there is only a caching mode and no + * explicit coherency mode, but on such hardware there is always a + * shared-LLC (or is dgpu) so all GT memory accesses are coherent with + * CPU caches even with the caching mode set as uncached. It's only the + * display engine that is incoherent (on dgpu it must be in VRAM which + * is always mapped as WC on the CPU). However to keep the uapi somewhat + * consistent with newer platforms the KMD groups the different cache + * levels into the following coherency buckets on all pre-MTL platforms: + * + * ppGTT UC -> COH_NONE + * ppGTT WC -> COH_NONE + * ppGTT WT -> COH_NONE + * ppGTT WB -> COH_AT_LEAST_1WAY + * + * In practice UC/WC/WT should only ever used for scanout surfaces on + * such platforms (or perhaps in general for dma-buf if shared with + * another device) since it is only the display engine that is actually + * incoherent. Everything else should typically use WB given that we + * have a shared-LLC. On MTL+ this completely changes and the HW + * defines the coherency mode as part of the @pat_index, where + * incoherent GT access is possible. + * + * Note: For userptr and externally imported dma-buf the kernel expects + * either 1WAY or 2WAY for the @pat_index. + * + * For DRM_XE_VM_BIND_FLAG_NULL bindings there are no KMD restrictions + * on the @pat_index. For such mappings there is no actual memory being + * mapped (the address in the PTE is invalid), so the various PAT memory + * attributes likely do not apply. Simply leaving as zero is one + * option (still a valid pat_index). + */ + __u16 pat_index; + + /** @pad: MBZ */ + __u16 pad; + + union { + /** + * @obj_offset: Offset into the object, MBZ for CLEAR_RANGE, + * ignored for unbind + */ + __u64 obj_offset; + + /** @userptr: user pointer to bind on */ + __u64 userptr; + }; + + /** + * @range: Number of bytes from the object to bind to addr, MBZ for UNMAP_ALL + */ + __u64 range; + + /** @addr: Address to operate on, MBZ for UNMAP_ALL */ + __u64 addr; + +#define DRM_XE_VM_BIND_OP_MAP 0x0 +#define DRM_XE_VM_BIND_OP_UNMAP 0x1 +#define DRM_XE_VM_BIND_OP_MAP_USERPTR 0x2 +#define DRM_XE_VM_BIND_OP_UNMAP_ALL 0x3 +#define DRM_XE_VM_BIND_OP_PREFETCH 0x4 + /** @op: Bind operation to perform */ + __u32 op; + +#define DRM_XE_VM_BIND_FLAG_NULL (1 << 2) +#define DRM_XE_VM_BIND_FLAG_DUMPABLE (1 << 3) + /** @flags: Bind flags */ + __u32 flags; + + /** + * @prefetch_mem_region_instance: Memory region to prefetch VMA to. + * It is a region instance, not a mask. + * To be used only with %DRM_XE_VM_BIND_OP_PREFETCH operation. + */ + __u32 prefetch_mem_region_instance; + + /** @pad2: MBZ */ + __u32 pad2; + + /** @reserved: Reserved */ + __u64 reserved[3]; +}; + +/** + * struct drm_xe_vm_bind - Input of &DRM_IOCTL_XE_VM_BIND + * + * Below is an example of a minimal use of @drm_xe_vm_bind to + * asynchronously bind the buffer `data` at address `BIND_ADDRESS` to + * illustrate `userptr`. It can be synchronized by using the example + * provided for @drm_xe_sync. + * + * .. code-block:: C + * + * data = aligned_alloc(ALIGNMENT, BO_SIZE); + * struct drm_xe_vm_bind bind = { + * .vm_id = vm, + * .num_binds = 1, + * .bind.obj = 0, + * .bind.obj_offset = to_user_pointer(data), + * .bind.range = BO_SIZE, + * .bind.addr = BIND_ADDRESS, + * .bind.op = DRM_XE_VM_BIND_OP_MAP_USERPTR, + * .bind.flags = 0, + * .num_syncs = 1, + * .syncs = &sync, + * .exec_queue_id = 0, + * }; + * ioctl(fd, DRM_IOCTL_XE_VM_BIND, &bind); + * + */ +struct drm_xe_vm_bind { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + + /** @vm_id: The ID of the VM to bind to */ + __u32 vm_id; + + /** + * @exec_queue_id: exec_queue_id, must be of class DRM_XE_ENGINE_CLASS_VM_BIND + * and exec queue must have same vm_id. If zero, the default VM bind engine + * is used. + */ + __u32 exec_queue_id; + + /** @pad: MBZ */ + __u32 pad; + + /** @num_binds: number of binds in this IOCTL */ + __u32 num_binds; + + union { + /** @bind: used if num_binds == 1 */ + struct drm_xe_vm_bind_op bind; + + /** + * @vector_of_binds: userptr to array of struct + * drm_xe_vm_bind_op if num_binds > 1 + */ + __u64 vector_of_binds; + }; + + /** @pad2: MBZ */ + __u32 pad2; + + /** @num_syncs: amount of syncs to wait on */ + __u32 num_syncs; + + /** @syncs: pointer to struct drm_xe_sync array */ + __u64 syncs; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_exec_queue_create - Input of &DRM_IOCTL_XE_EXEC_QUEUE_CREATE + * + * The example below shows how to use @drm_xe_exec_queue_create to create + * a simple exec_queue (no parallel submission) of class + * &DRM_XE_ENGINE_CLASS_RENDER. + * + * .. code-block:: C + * + * struct drm_xe_engine_class_instance instance = { + * .engine_class = DRM_XE_ENGINE_CLASS_RENDER, + * }; + * struct drm_xe_exec_queue_create exec_queue_create = { + * .extensions = 0, + * .vm_id = vm, + * .num_bb_per_exec = 1, + * .num_eng_per_bb = 1, + * .instances = to_user_pointer(&instance), + * }; + * ioctl(fd, DRM_IOCTL_XE_EXEC_QUEUE_CREATE, &exec_queue_create); + * + */ +struct drm_xe_exec_queue_create { +#define DRM_XE_EXEC_QUEUE_EXTENSION_SET_PROPERTY 0 +#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY 0 +#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE 1 + + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + + /** @width: submission width (number BB per exec) for this exec queue */ + __u16 width; + + /** @num_placements: number of valid placements for this exec queue */ + __u16 num_placements; + + /** @vm_id: VM to use for this exec queue */ + __u32 vm_id; + + /** @flags: MBZ */ + __u32 flags; + + /** @exec_queue_id: Returned exec queue ID */ + __u32 exec_queue_id; + + /** + * @instances: user pointer to a 2-d array of struct + * drm_xe_engine_class_instance + * + * length = width (i) * num_placements (j) + * index = j + i * width + */ + __u64 instances; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_exec_queue_destroy - Input of &DRM_IOCTL_XE_EXEC_QUEUE_DESTROY + */ +struct drm_xe_exec_queue_destroy { + /** @exec_queue_id: Exec queue ID */ + __u32 exec_queue_id; + + /** @pad: MBZ */ + __u32 pad; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_exec_queue_get_property - Input of &DRM_IOCTL_XE_EXEC_QUEUE_GET_PROPERTY + * + * The @property can be: + * - %DRM_XE_EXEC_QUEUE_GET_PROPERTY_BAN + */ +struct drm_xe_exec_queue_get_property { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + + /** @exec_queue_id: Exec queue ID */ + __u32 exec_queue_id; + +#define DRM_XE_EXEC_QUEUE_GET_PROPERTY_BAN 0 + /** @property: property to get */ + __u32 property; + + /** @value: property value */ + __u64 value; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_sync - sync object + * + * The @type can be: + * - %DRM_XE_SYNC_TYPE_SYNCOBJ + * - %DRM_XE_SYNC_TYPE_TIMELINE_SYNCOBJ + * - %DRM_XE_SYNC_TYPE_USER_FENCE + * + * and the @flags can be: + * - %DRM_XE_SYNC_FLAG_SIGNAL + * + * A minimal use of @drm_xe_sync looks like this: + * + * .. code-block:: C + * + * struct drm_xe_sync sync = { + * .flags = DRM_XE_SYNC_FLAG_SIGNAL, + * .type = DRM_XE_SYNC_TYPE_SYNCOBJ, + * }; + * struct drm_syncobj_create syncobj_create = { 0 }; + * ioctl(fd, DRM_IOCTL_SYNCOBJ_CREATE, &syncobj_create); + * sync.handle = syncobj_create.handle; + * ... + * use of &sync in drm_xe_exec or drm_xe_vm_bind + * ... + * struct drm_syncobj_wait wait = { + * .handles = &sync.handle, + * .timeout_nsec = INT64_MAX, + * .count_handles = 1, + * .flags = 0, + * .first_signaled = 0, + * .pad = 0, + * }; + * ioctl(fd, DRM_IOCTL_SYNCOBJ_WAIT, &wait); + */ +struct drm_xe_sync { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + +#define DRM_XE_SYNC_TYPE_SYNCOBJ 0x0 +#define DRM_XE_SYNC_TYPE_TIMELINE_SYNCOBJ 0x1 +#define DRM_XE_SYNC_TYPE_USER_FENCE 0x2 + /** @type: Type of the this sync object */ + __u32 type; + +#define DRM_XE_SYNC_FLAG_SIGNAL (1 << 0) + /** @flags: Sync Flags */ + __u32 flags; + + union { + /** @handle: Handle for the object */ + __u32 handle; + + /** + * @addr: Address of user fence. When sync is passed in via exec + * IOCTL this is a GPU address in the VM. When sync passed in via + * VM bind IOCTL this is a user pointer. In either case, it is + * the users responsibility that this address is present and + * mapped when the user fence is signalled. Must be qword + * aligned. + */ + __u64 addr; + }; + + /** + * @timeline_value: Input for the timeline sync object. Needs to be + * different than 0 when used with %DRM_XE_SYNC_FLAG_TIMELINE_SYNCOBJ. + */ + __u64 timeline_value; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_exec - Input of &DRM_IOCTL_XE_EXEC + * + * This is an example to use @drm_xe_exec for execution of the object + * at BIND_ADDRESS (see example in @drm_xe_vm_bind) by an exec_queue + * (see example in @drm_xe_exec_queue_create). It can be synchronized + * by using the example provided for @drm_xe_sync. + * + * .. code-block:: C + * + * struct drm_xe_exec exec = { + * .exec_queue_id = exec_queue, + * .syncs = &sync, + * .num_syncs = 1, + * .address = BIND_ADDRESS, + * .num_batch_buffer = 1, + * }; + * ioctl(fd, DRM_IOCTL_XE_EXEC, &exec); + * + */ +struct drm_xe_exec { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + + /** @exec_queue_id: Exec queue ID for the batch buffer */ + __u32 exec_queue_id; + + /** @num_syncs: Amount of struct drm_xe_sync in array. */ + __u32 num_syncs; + + /** @syncs: Pointer to struct drm_xe_sync array. */ + __u64 syncs; + + /** + * @address: address of batch buffer if num_batch_buffer == 1 or an + * array of batch buffer addresses + */ + __u64 address; + + /** + * @num_batch_buffer: number of batch buffer in this exec, must match + * the width of the engine + */ + __u16 num_batch_buffer; + + /** @pad: MBZ */ + __u16 pad[3]; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_wait_user_fence - Input of &DRM_IOCTL_XE_WAIT_USER_FENCE + * + * Wait on user fence, XE will wake-up on every HW engine interrupt in the + * instances list and check if user fence is complete:: + * + * (*addr & MASK) OP (VALUE & MASK) + * + * Returns to user on user fence completion or timeout. + * + * The @op can be: + * - %DRM_XE_UFENCE_WAIT_OP_EQ + * - %DRM_XE_UFENCE_WAIT_OP_NEQ + * - %DRM_XE_UFENCE_WAIT_OP_GT + * - %DRM_XE_UFENCE_WAIT_OP_GTE + * - %DRM_XE_UFENCE_WAIT_OP_LT + * - %DRM_XE_UFENCE_WAIT_OP_LTE + * + * and the @flags can be: + * - %DRM_XE_UFENCE_WAIT_FLAG_ABSTIME + * - %DRM_XE_UFENCE_WAIT_FLAG_SOFT_OP + * + * The @mask values can be for example: + * - 0xffu for u8 + * - 0xffffu for u16 + * - 0xffffffffu for u32 + * - 0xffffffffffffffffu for u64 + */ +struct drm_xe_wait_user_fence { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + + /** + * @addr: user pointer address to wait on, must qword aligned + */ + __u64 addr; + +#define DRM_XE_UFENCE_WAIT_OP_EQ 0x0 +#define DRM_XE_UFENCE_WAIT_OP_NEQ 0x1 +#define DRM_XE_UFENCE_WAIT_OP_GT 0x2 +#define DRM_XE_UFENCE_WAIT_OP_GTE 0x3 +#define DRM_XE_UFENCE_WAIT_OP_LT 0x4 +#define DRM_XE_UFENCE_WAIT_OP_LTE 0x5 + /** @op: wait operation (type of comparison) */ + __u16 op; + +#define DRM_XE_UFENCE_WAIT_FLAG_ABSTIME (1 << 0) + /** @flags: wait flags */ + __u16 flags; + + /** @pad: MBZ */ + __u32 pad; + + /** @value: compare value */ + __u64 value; + + /** @mask: comparison mask */ + __u64 mask; + + /** + * @timeout: how long to wait before bailing, value in nanoseconds. + * Without DRM_XE_UFENCE_WAIT_FLAG_ABSTIME flag set (relative timeout) + * it contains timeout expressed in nanoseconds to wait (fence will + * expire at now() + timeout). + * When DRM_XE_UFENCE_WAIT_FLAG_ABSTIME flat is set (absolute timeout) wait + * will end at timeout (uses system MONOTONIC_CLOCK). + * Passing negative timeout leads to neverending wait. + * + * On relative timeout this value is updated with timeout left + * (for restarting the call in case of signal delivery). + * On absolute timeout this value stays intact (restarted call still + * expire at the same point of time). + */ + __s64 timeout; + + /** @exec_queue_id: exec_queue_id returned from xe_exec_queue_create_ioctl */ + __u32 exec_queue_id; + + /** @pad2: MBZ */ + __u32 pad2; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +#if defined(__cplusplus) +} +#endif + +#endif /* _UAPI_XE_DRM_H_ */ -- cgit v1.2.3