diff options
Diffstat (limited to 'include/uapi')
| -rw-r--r-- | include/uapi/drm/amdgpu_drm.h | 7 | ||||
| -rw-r--r-- | include/uapi/drm/amdxdna_accel.h | 47 | ||||
| -rw-r--r-- | include/uapi/drm/drm_fourcc.h | 16 | ||||
| -rw-r--r-- | include/uapi/drm/drm_mode.h | 84 | ||||
| -rw-r--r-- | include/uapi/drm/drm_ras.h | 49 | ||||
| -rw-r--r-- | include/uapi/drm/msm_drm.h | 1 | ||||
| -rw-r--r-- | include/uapi/drm/nouveau_drm.h | 66 | ||||
| -rw-r--r-- | include/uapi/drm/panthor_drm.h | 63 | ||||
| -rw-r--r-- | include/uapi/drm/xe_drm.h | 268 | ||||
| -rw-r--r-- | include/uapi/linux/const.h | 18 |
10 files changed, 602 insertions, 17 deletions
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index ebbd861ef0bc..9f3090db2f16 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -479,7 +479,9 @@ struct drm_amdgpu_userq_signal { * @num_syncobj_handles: A count that represents the number of syncobj handles in * @syncobj_handles. */ - __u64 num_syncobj_handles; + __u16 num_syncobj_handles; + __u16 pad0; + __u32 pad1; /** * @bo_read_handles: The list of BO handles that the submitted user queue job * is using for read only. This will update BO fences in the kernel. @@ -563,7 +565,8 @@ struct drm_amdgpu_userq_wait { * @num_syncobj_handles: A count that represents the number of syncobj handles in * @syncobj_handles. */ - __u32 num_syncobj_handles; + __u16 num_syncobj_handles; + __u16 pad0; /** * @num_bo_read_handles: A count that represents the number of read BO handles in * @bo_read_handles. diff --git a/include/uapi/drm/amdxdna_accel.h b/include/uapi/drm/amdxdna_accel.h index 9c44db2b3dcd..61d3686fa3b1 100644 --- a/include/uapi/drm/amdxdna_accel.h +++ b/include/uapi/drm/amdxdna_accel.h @@ -156,10 +156,11 @@ struct amdxdna_drm_config_hwctx { enum amdxdna_bo_type { AMDXDNA_BO_INVALID = 0, - AMDXDNA_BO_SHMEM, - AMDXDNA_BO_DEV_HEAP, - AMDXDNA_BO_DEV, - AMDXDNA_BO_CMD, + AMDXDNA_BO_SHMEM = 1, /* Be compatible with legacy application code. */ + AMDXDNA_BO_SHARE = 1, + AMDXDNA_BO_DEV_HEAP = 2, + AMDXDNA_BO_DEV = 3, + AMDXDNA_BO_CMD = 4, }; /** @@ -353,7 +354,8 @@ struct amdxdna_drm_query_clock_metadata { }; enum amdxdna_sensor_type { - AMDXDNA_SENSOR_TYPE_POWER + AMDXDNA_SENSOR_TYPE_POWER, + AMDXDNA_SENSOR_TYPE_COLUMN_UTILIZATION }; /** @@ -589,8 +591,37 @@ struct amdxdna_async_error { __u64 ex_err_code; }; +/** + * struct amdxdna_drm_bo_usage - all types of BO usage + * BOs managed by XRT/SHIM/driver is counted as internal. + * Others are counted as external which are managed by applications. + * + * Among all types of BOs: + * AMDXDNA_BO_DEV_HEAP - is counted for internal. + * AMDXDNA_BO_SHARE - is counted for external. + * AMDXDNA_BO_CMD - is counted for internal. + * AMDXDNA_BO_DEV - is counted by heap_usage only, not internal + * or external. It does not add to the total memory + * footprint since its mem comes from heap which is + * already counted as internal. + */ +struct amdxdna_drm_bo_usage { + /** @pid: The ID of the process to query from. */ + __s64 pid; + /** @total_usage: Total BO size used by process. */ + __u64 total_usage; + /** @internal_usage: Total internal BO size used by process. */ + __u64 internal_usage; + /** @heap_usage: Total device BO size used by process. */ + __u64 heap_usage; +}; + +/* + * Supported params in struct amdxdna_drm_get_array + */ #define DRM_AMDXDNA_HW_CONTEXT_ALL 0 #define DRM_AMDXDNA_HW_LAST_ASYNC_ERR 2 +#define DRM_AMDXDNA_BO_USAGE 6 /** * struct amdxdna_drm_get_array - Get information array. @@ -603,6 +634,12 @@ struct amdxdna_drm_get_array { * * %DRM_AMDXDNA_HW_CONTEXT_ALL: * Returns all created hardware contexts. + * + * %DRM_AMDXDNA_HW_LAST_ASYNC_ERR: + * Returns last async error. + * + * %DRM_AMDXDNA_BO_USAGE: + * Returns usage of heap/internal/external BOs. */ __u32 param; /** diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index c89aede3cb12..ac66fa93b5a3 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -1423,6 +1423,22 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier) DRM_FORMAT_MOD_ARM_CODE(DRM_FORMAT_MOD_ARM_TYPE_MISC, 1ULL) /* + * ARM 64k interleaved modifier + * + * This is used by ARM Mali v10+ GPUs. With this modifier, the plane is divided + * into 64k byte 1:1 or 2:1 -sided tiles. The 64k tiles are laid out linearly. + * Each 64k tile is divided into blocks of 16x16 texel blocks, which are + * themselves laid out linearly within a 64k tile. Then within each 16x16 + * block, texel blocks are laid out according to U order, similar to + * 16X16_BLOCK_U_INTERLEAVED. + * + * Note that unlike 16X16_BLOCK_U_INTERLEAVED, the layout does not change + * depending on whether a format is compressed or not. + */ +#define DRM_FORMAT_MOD_ARM_INTERLEAVED_64K \ + DRM_FORMAT_MOD_ARM_CODE(DRM_FORMAT_MOD_ARM_TYPE_MISC, 2ULL) + +/* * Allwinner tiled modifier * * This tiling mode is implemented by the VPU found on all Allwinner platforms, diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index cbbbfc1dfe2b..a4bdc4bd11bc 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -27,6 +27,9 @@ #ifndef _DRM_MODE_H #define _DRM_MODE_H +#include <linux/bits.h> +#include <linux/const.h> + #include "drm.h" #if defined(__cplusplus) @@ -166,6 +169,10 @@ extern "C" { #define DRM_MODE_LINK_STATUS_GOOD 0 #define DRM_MODE_LINK_STATUS_BAD 1 +/* Panel type property */ +#define DRM_MODE_PANEL_TYPE_UNKNOWN 0 +#define DRM_MODE_PANEL_TYPE_OLED 1 + /* * DRM_MODE_ROTATE_<degrees> * @@ -1545,6 +1552,83 @@ struct drm_mode_closefb { __u32 pad; }; +/* + * Put 16-bit ARGB values into a standard 64-bit representation that can be + * used for ioctl parameters, inter-driver communication, etc. + * + * If the component values being provided contain less than 16 bits of + * precision, use a conversion ratio to get a better color approximation. + * The ratio is computed as (2^16 - 1) / (2^bpc - 1), where bpc and 16 are + * the input and output precision, respectively. + * Also note bpc must be greater than 0. + */ +#define __DRM_ARGB64_PREP(c, shift) \ + (((__u64)(c) & __GENMASK(15, 0)) << (shift)) + +#define __DRM_ARGB64_PREP_BPC(c, shift, bpc) \ +({ \ + __u16 mask = __GENMASK((bpc) - 1, 0); \ + __u16 conv = __KERNEL_DIV_ROUND_CLOSEST((mask & (c)) * \ + __GENMASK(15, 0), mask);\ + __DRM_ARGB64_PREP(conv, shift); \ +}) + +#define DRM_ARGB64_PREP(alpha, red, green, blue) \ +( \ + __DRM_ARGB64_PREP(alpha, 48) | \ + __DRM_ARGB64_PREP(red, 32) | \ + __DRM_ARGB64_PREP(green, 16) | \ + __DRM_ARGB64_PREP(blue, 0) \ +) + +#define DRM_ARGB64_PREP_BPC(alpha, red, green, blue, bpc) \ +({ \ + __typeof__(bpc) __bpc = bpc; \ + __DRM_ARGB64_PREP_BPC(alpha, 48, __bpc) | \ + __DRM_ARGB64_PREP_BPC(red, 32, __bpc) | \ + __DRM_ARGB64_PREP_BPC(green, 16, __bpc) | \ + __DRM_ARGB64_PREP_BPC(blue, 0, __bpc); \ +}) + +/* + * Extract the specified color component from a standard 64-bit ARGB value. + * + * If the requested precision is less than 16 bits, make use of a conversion + * ratio calculated as (2^bpc - 1) / (2^16 - 1), where bpc and 16 are the + * output and input precision, respectively. + * + * If speed is more important than accuracy, use DRM_ARGB64_GET*_BPCS() + * instead of DRM_ARGB64_GET*_BPC() in order to replace the expensive + * division with a simple bit right-shift operation. + */ +#define __DRM_ARGB64_GET(c, shift) \ + ((__u16)(((__u64)(c) >> (shift)) & __GENMASK(15, 0))) + +#define __DRM_ARGB64_GET_BPC(c, shift, bpc) \ +({ \ + __u16 comp = __DRM_ARGB64_GET(c, shift); \ + __KERNEL_DIV_ROUND_CLOSEST(comp * __GENMASK((bpc) - 1, 0), \ + __GENMASK(15, 0)); \ +}) + +#define __DRM_ARGB64_GET_BPCS(c, shift, bpc) \ + (__DRM_ARGB64_GET(c, shift) >> (16 - (bpc))) + +#define DRM_ARGB64_GETA(c) __DRM_ARGB64_GET(c, 48) +#define DRM_ARGB64_GETR(c) __DRM_ARGB64_GET(c, 32) +#define DRM_ARGB64_GETG(c) __DRM_ARGB64_GET(c, 16) +#define DRM_ARGB64_GETB(c) __DRM_ARGB64_GET(c, 0) + +#define DRM_ARGB64_GETA_BPC(c, bpc) __DRM_ARGB64_GET_BPC(c, 48, bpc) +#define DRM_ARGB64_GETR_BPC(c, bpc) __DRM_ARGB64_GET_BPC(c, 32, bpc) +#define DRM_ARGB64_GETG_BPC(c, bpc) __DRM_ARGB64_GET_BPC(c, 16, bpc) +#define DRM_ARGB64_GETB_BPC(c, bpc) __DRM_ARGB64_GET_BPC(c, 0, bpc) + +#define DRM_ARGB64_GETA_BPCS(c, bpc) __DRM_ARGB64_GET_BPCS(c, 48, bpc) +#define DRM_ARGB64_GETR_BPCS(c, bpc) __DRM_ARGB64_GET_BPCS(c, 32, bpc) +#define DRM_ARGB64_GETG_BPCS(c, bpc) __DRM_ARGB64_GET_BPCS(c, 16, bpc) +#define DRM_ARGB64_GETB_BPCS(c, bpc) __DRM_ARGB64_GET_BPCS(c, 0, bpc) + #if defined(__cplusplus) } #endif diff --git a/include/uapi/drm/drm_ras.h b/include/uapi/drm/drm_ras.h new file mode 100644 index 000000000000..5f40fa5b869d --- /dev/null +++ b/include/uapi/drm/drm_ras.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/drm_ras.yaml */ +/* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ + +#ifndef _UAPI_LINUX_DRM_RAS_H +#define _UAPI_LINUX_DRM_RAS_H + +#define DRM_RAS_FAMILY_NAME "drm-ras" +#define DRM_RAS_FAMILY_VERSION 1 + +/* + * Type of the node. Currently, only error-counter nodes are supported, which + * expose reliability counters for a hardware/software component. + */ +enum drm_ras_node_type { + DRM_RAS_NODE_TYPE_ERROR_COUNTER = 1, +}; + +enum { + DRM_RAS_A_NODE_ATTRS_NODE_ID = 1, + DRM_RAS_A_NODE_ATTRS_DEVICE_NAME, + DRM_RAS_A_NODE_ATTRS_NODE_NAME, + DRM_RAS_A_NODE_ATTRS_NODE_TYPE, + + __DRM_RAS_A_NODE_ATTRS_MAX, + DRM_RAS_A_NODE_ATTRS_MAX = (__DRM_RAS_A_NODE_ATTRS_MAX - 1) +}; + +enum { + DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID = 1, + DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID, + DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_NAME, + DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_VALUE, + + __DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX, + DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX = (__DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX - 1) +}; + +enum { + DRM_RAS_CMD_LIST_NODES = 1, + DRM_RAS_CMD_GET_ERROR_COUNTER, + + __DRM_RAS_CMD_MAX, + DRM_RAS_CMD_MAX = (__DRM_RAS_CMD_MAX - 1) +}; + +#endif /* _UAPI_LINUX_DRM_RAS_H */ diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index 5c67294edc95..b99098792371 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -117,6 +117,7 @@ struct drm_msm_timespec { * ioctl will throw -EPIPE. */ #define MSM_PARAM_EN_VM_BIND 0x16 /* WO, once */ +#define MSM_PARAM_AQE 0x17 /* RO */ /* For backwards compat. The original support for preemption was based on * a single ring per priority level so # of priority levels equals the # diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h index dd87f8f30793..1fa82fa6af38 100644 --- a/include/uapi/drm/nouveau_drm.h +++ b/include/uapi/drm/nouveau_drm.h @@ -432,6 +432,69 @@ struct drm_nouveau_exec { __u64 push_ptr; }; +struct drm_nouveau_get_zcull_info { + /** + * @width_align_pixels: required alignment for region widths, in pixels + * (typically #TPC's * 16). + */ + __u32 width_align_pixels; + /** + * @height_align_pixels: required alignment for region heights, in + * pixels (typically 32). + */ + __u32 height_align_pixels; + /** + * @pixel_squares_by_aliquots: the pixel area covered by an aliquot + * (typically #Zcull_banks * 16 * 16). + */ + __u32 pixel_squares_by_aliquots; + /** + * @aliquot_total: the total aliquot pool available in hardware + */ + __u32 aliquot_total; + /** + * @zcull_region_byte_multiplier: the size of an aliquot in bytes, which + * is used for save/restore operations on a region + */ + __u32 zcull_region_byte_multiplier; + /** + * @zcull_region_header_size: the region header size in bytes, which is + * used for save/restore operations on a region + */ + __u32 zcull_region_header_size; + /** + * @zcull_subregion_header_size: the subregion header size in bytes, + * which is used for save/restore operations on a region + */ + __u32 zcull_subregion_header_size; + /** + * @subregion_count: the total number of subregions the hardware + * supports + */ + __u32 subregion_count; + /** + * @subregion_width_align_pixels: required alignment for subregion + * widths, in pixels (typically #TPC's * 16). + */ + __u32 subregion_width_align_pixels; + /** + * @subregion_height_align_pixels: required alignment for subregion + * heights, in pixels + */ + __u32 subregion_height_align_pixels; + + /** + * @ctxsw_size: the size, in bytes, of a zcull context switching region. + * Will be zero if the kernel does not support zcull context switching. + */ + __u32 ctxsw_size; + /** + * @ctxsw_align: the alignment, in bytes, of a zcull context switching + * region + */ + __u32 ctxsw_align; +}; + #define DRM_NOUVEAU_GETPARAM 0x00 #define DRM_NOUVEAU_SETPARAM 0x01 /* deprecated */ #define DRM_NOUVEAU_CHANNEL_ALLOC 0x02 @@ -445,6 +508,7 @@ struct drm_nouveau_exec { #define DRM_NOUVEAU_VM_INIT 0x10 #define DRM_NOUVEAU_VM_BIND 0x11 #define DRM_NOUVEAU_EXEC 0x12 +#define DRM_NOUVEAU_GET_ZCULL_INFO 0x13 #define DRM_NOUVEAU_GEM_NEW 0x40 #define DRM_NOUVEAU_GEM_PUSHBUF 0x41 #define DRM_NOUVEAU_GEM_CPU_PREP 0x42 @@ -513,6 +577,8 @@ struct drm_nouveau_svm_bind { #define DRM_IOCTL_NOUVEAU_VM_INIT DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_VM_INIT, struct drm_nouveau_vm_init) #define DRM_IOCTL_NOUVEAU_VM_BIND DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_VM_BIND, struct drm_nouveau_vm_bind) #define DRM_IOCTL_NOUVEAU_EXEC DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_EXEC, struct drm_nouveau_exec) + +#define DRM_IOCTL_NOUVEAU_GET_ZCULL_INFO DRM_IOR (DRM_COMMAND_BASE + DRM_NOUVEAU_GET_ZCULL_INFO, struct drm_nouveau_get_zcull_info) #if defined(__cplusplus) } #endif diff --git a/include/uapi/drm/panthor_drm.h b/include/uapi/drm/panthor_drm.h index b401ac585d6a..0e455d91e77d 100644 --- a/include/uapi/drm/panthor_drm.h +++ b/include/uapi/drm/panthor_drm.h @@ -410,6 +410,38 @@ struct drm_panthor_csif_info { }; /** + * enum drm_panthor_timestamp_info_flags - drm_panthor_timestamp_info.flags + */ +enum drm_panthor_timestamp_info_flags { + /** @DRM_PANTHOR_TIMESTAMP_GPU: Query GPU time. */ + DRM_PANTHOR_TIMESTAMP_GPU = 1 << 0, + + /** @DRM_PANTHOR_TIMESTAMP_CPU_NONE: Don't query CPU time. */ + DRM_PANTHOR_TIMESTAMP_CPU_NONE = 0 << 1, + + /** @DRM_PANTHOR_TIMESTAMP_CPU_MONOTONIC: Query CPU time using CLOCK_MONOTONIC. */ + DRM_PANTHOR_TIMESTAMP_CPU_MONOTONIC = 1 << 1, + + /** @DRM_PANTHOR_TIMESTAMP_CPU_MONOTONIC_RAW: Query CPU time using CLOCK_MONOTONIC_RAW. */ + DRM_PANTHOR_TIMESTAMP_CPU_MONOTONIC_RAW = 2 << 1, + + /** @DRM_PANTHOR_TIMESTAMP_CPU_TYPE_MASK: Space reserved for CPU clock type. */ + DRM_PANTHOR_TIMESTAMP_CPU_TYPE_MASK = 7 << 1, + + /** @DRM_PANTHOR_TIMESTAMP_GPU_OFFSET: Query GPU offset. */ + DRM_PANTHOR_TIMESTAMP_GPU_OFFSET = 1 << 4, + + /** @DRM_PANTHOR_TIMESTAMP_GPU_CYCLE_COUNT: Query GPU cycle count. */ + DRM_PANTHOR_TIMESTAMP_GPU_CYCLE_COUNT = 1 << 5, + + /** @DRM_PANTHOR_TIMESTAMP_FREQ: Query timestamp frequency. */ + DRM_PANTHOR_TIMESTAMP_FREQ = 1 << 6, + + /** @DRM_PANTHOR_TIMESTAMP_DURATION: Return duration of time query. */ + DRM_PANTHOR_TIMESTAMP_DURATION = 1 << 7, +}; + +/** * struct drm_panthor_timestamp_info - Timestamp information * * Structure grouping all queryable information relating to the GPU timestamp. @@ -421,11 +453,38 @@ struct drm_panthor_timestamp_info { */ __u64 timestamp_frequency; - /** @current_timestamp: The current timestamp. */ + /** @current_timestamp: The current GPU timestamp. */ __u64 current_timestamp; - /** @timestamp_offset: The offset of the timestamp timer. */ + /** @timestamp_offset: The offset of the GPU timestamp timer. */ __u64 timestamp_offset; + + /** + * @flags: Bitmask of drm_panthor_timestamp_info_flags. + * + * If set to 0, then it is interpreted as: + * DRM_PANTHOR_TIMESTAMP_GPU | + * DRM_PANTHOR_TIMESTAMP_GPU_OFFSET | + * DRM_PANTHOR_TIMESTAMP_FREQ + * + * Note: these flags are exclusive to each other (only one can be used): + * - DRM_PANTHOR_TIMESTAMP_CPU_NONE + * - DRM_PANTHOR_TIMESTAMP_CPU_MONOTONIC + * - DRM_PANTHOR_TIMESTAMP_CPU_MONOTONIC_RAW + */ + __u32 flags; + + /** @duration_nsec: Duration of time query. */ + __u32 duration_nsec; + + /** @cycle_count: Value of GPU_CYCLE_COUNT. */ + __u64 cycle_count; + + /** @cpu_timestamp_sec: Seconds part of CPU timestamp. */ + __u64 cpu_timestamp_sec; + + /** @cpu_timestamp_nsec: Nanseconds part of CPU timestamp. */ + __u64 cpu_timestamp_nsec; }; /** diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 077e66a682e2..ae2fda23ce7c 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -83,6 +83,7 @@ extern "C" { * - &DRM_IOCTL_XE_OBSERVATION * - &DRM_IOCTL_XE_MADVISE * - &DRM_IOCTL_XE_VM_QUERY_MEM_RANGE_ATTRS + * - &DRM_IOCTL_XE_VM_GET_PROPERTY */ /* @@ -107,6 +108,7 @@ extern "C" { #define DRM_XE_MADVISE 0x0c #define DRM_XE_VM_QUERY_MEM_RANGE_ATTRS 0x0d #define DRM_XE_EXEC_QUEUE_SET_PROPERTY 0x0e +#define DRM_XE_VM_GET_PROPERTY 0x0f /* Must be kept compact -- no holes */ @@ -125,6 +127,7 @@ extern "C" { #define DRM_IOCTL_XE_MADVISE DRM_IOW(DRM_COMMAND_BASE + DRM_XE_MADVISE, struct drm_xe_madvise) #define DRM_IOCTL_XE_VM_QUERY_MEM_RANGE_ATTRS DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_VM_QUERY_MEM_RANGE_ATTRS, struct drm_xe_vm_query_mem_range_attr) #define DRM_IOCTL_XE_EXEC_QUEUE_SET_PROPERTY DRM_IOW(DRM_COMMAND_BASE + DRM_XE_EXEC_QUEUE_SET_PROPERTY, struct drm_xe_exec_queue_set_property) +#define DRM_IOCTL_XE_VM_GET_PROPERTY DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_VM_GET_PROPERTY, struct drm_xe_vm_get_property) /** * DOC: Xe IOCTL Extensions @@ -335,10 +338,6 @@ struct drm_xe_mem_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; /** @@ -363,9 +362,7 @@ struct drm_xe_mem_region { * @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 + * Note this is only currently tracked for * DRM_XE_MEM_REGION_CLASS_VRAM regions (for other types the value * here will always be zero). */ @@ -412,6 +409,9 @@ struct drm_xe_query_mem_regions { * - %DRM_XE_QUERY_CONFIG_FLAG_HAS_NO_COMPRESSION_HINT - Flag is set if the * device supports the userspace hint %DRM_XE_GEM_CREATE_FLAG_NO_COMPRESSION. * This is exposed only on Xe2+. + * - %DRM_XE_QUERY_CONFIG_FLAG_HAS_DISABLE_STATE_CACHE_PERF_FIX - Flag is set + * if a queue can be creaed with + * %DRM_XE_EXEC_QUEUE_SET_DISABLE_STATE_CACHE_PERF_FIX * - %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 @@ -431,6 +431,8 @@ struct drm_xe_query_config { #define DRM_XE_QUERY_CONFIG_FLAG_HAS_LOW_LATENCY (1 << 1) #define DRM_XE_QUERY_CONFIG_FLAG_HAS_CPU_ADDR_MIRROR (1 << 2) #define DRM_XE_QUERY_CONFIG_FLAG_HAS_NO_COMPRESSION_HINT (1 << 3) + #define DRM_XE_QUERY_CONFIG_FLAG_HAS_DISABLE_STATE_CACHE_PERF_FIX (1 << 4) + #define DRM_XE_QUERY_CONFIG_FLAG_HAS_PURGING_SUPPORT (1 << 5) #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 @@ -975,6 +977,11 @@ struct drm_xe_gem_mmap_offset { * demand when accessed, and also allows per-VM overcommit of memory. * The xe driver internally uses recoverable pagefaults to implement * this. + * - %DRM_XE_VM_CREATE_FLAG_NO_VM_OVERCOMMIT - Requires also + * DRM_XE_VM_CREATE_FLAG_FAULT_MODE. This disallows per-VM overcommit + * but only during a &DRM_IOCTL_XE_VM_BIND operation with the + * %DRM_XE_VM_BIND_FLAG_IMMEDIATE flag set. This may be useful for + * user-space naively probing the amount of available memory. */ struct drm_xe_vm_create { /** @extensions: Pointer to the first extension struct, if any */ @@ -983,6 +990,7 @@ struct drm_xe_vm_create { #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) +#define DRM_XE_VM_CREATE_FLAG_NO_VM_OVERCOMMIT (1 << 3) /** @flags: Flags */ __u32 flags; @@ -1053,6 +1061,13 @@ struct drm_xe_vm_destroy { * not invoke autoreset. Neither will stack variables going out of scope. * Therefore it's recommended to always explicitly reset the madvises when * freeing the memory backing a region used in a &DRM_IOCTL_XE_MADVISE call. + * - %DRM_XE_VM_BIND_FLAG_DECOMPRESS - Request on-device decompression for a MAP. + * When set on a MAP bind operation, request the driver schedule an on-device + * in-place decompression (via the migrate/resolve path) for the GPU mapping + * created by this bind. Only valid for DRM_XE_VM_BIND_OP_MAP; usage on + * other ops is rejected. The bind's pat_index must select the device's + * "no-compression" PAT. Only meaningful for VRAM-backed BOs on devices that + * support Flat CCS and the required HW generation XE2+. * * The @prefetch_mem_region_instance for %DRM_XE_VM_BIND_OP_PREFETCH can also be: * - %DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC, which ensures prefetching occurs in @@ -1103,7 +1118,9 @@ struct drm_xe_vm_bind_op { * incoherent GT access is possible. * * Note: For userptr and externally imported dma-buf the kernel expects - * either 1WAY or 2WAY for the @pat_index. + * either 1WAY or 2WAY for the @pat_index. Starting from NVL-P, for + * userptr, svm, madvise and externally imported dma-buf the kernel expects + * either 2WAY or 1WAY and XA @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 @@ -1160,6 +1177,7 @@ struct drm_xe_vm_bind_op { #define DRM_XE_VM_BIND_FLAG_CHECK_PXP (1 << 4) #define DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR (1 << 5) #define DRM_XE_VM_BIND_FLAG_MADVISE_AUTORESET (1 << 6) +#define DRM_XE_VM_BIND_FLAG_DECOMPRESS (1 << 7) /** @flags: Bind flags */ __u32 flags; @@ -1249,6 +1267,89 @@ struct drm_xe_vm_bind { __u64 reserved[2]; }; +/** struct xe_vm_fault - Describes faults for %DRM_XE_VM_GET_PROPERTY_FAULTS */ +struct xe_vm_fault { + /** @address: Canonical address of the fault */ + __u64 address; + /** @address_precision: Precision of faulted address */ + __u32 address_precision; + /** @access_type: Type of address access that resulted in fault */ +#define FAULT_ACCESS_TYPE_READ 0 +#define FAULT_ACCESS_TYPE_WRITE 1 +#define FAULT_ACCESS_TYPE_ATOMIC 2 + __u8 access_type; + /** @fault_type: Type of fault reported */ +#define FAULT_TYPE_NOT_PRESENT 0 +#define FAULT_TYPE_WRITE_ACCESS 1 +#define FAULT_TYPE_ATOMIC_ACCESS 2 + __u8 fault_type; + /** @fault_level: fault level of the fault */ +#define FAULT_LEVEL_PTE 0 +#define FAULT_LEVEL_PDE 1 +#define FAULT_LEVEL_PDP 2 +#define FAULT_LEVEL_PML4 3 +#define FAULT_LEVEL_PML5 4 + __u8 fault_level; + /** @pad: MBZ */ + __u8 pad; + /** @reserved: MBZ */ + __u64 reserved[4]; +}; + +/** + * struct drm_xe_vm_get_property - Input of &DRM_IOCTL_XE_VM_GET_PROPERTY + * + * The user provides a VM and a property to query among DRM_XE_VM_GET_PROPERTY_*, + * and sets the values in the vm_id and property members, respectively. This + * determines both the VM to get the property of, as well as the property to + * report. + * + * If size is set to 0, the driver fills it with the required size for the + * requested property. The user is expected here to allocate memory for the + * property structure and to provide a pointer to the allocated memory using the + * data member. For some properties, this may be zero, in which case, the + * value of the property will be saved to the value member and size will remain + * zero on return. + * + * If size is not zero, then the IOCTL will attempt to copy the requested + * property into the data member. + * + * The IOCTL will return -ENOENT if the VM could not be identified from the + * provided VM ID, or -EINVAL if the IOCTL fails for any other reason, such as + * providing an invalid size for the given property or if the property data + * could not be copied to the memory allocated to the data member. + * + * The property member can be: + * - %DRM_XE_VM_GET_PROPERTY_FAULTS + */ +struct drm_xe_vm_get_property { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + + /** @vm_id: The ID of the VM to query the properties of */ + __u32 vm_id; + +#define DRM_XE_VM_GET_PROPERTY_FAULTS 0 + /** @property: property to get */ + __u32 property; + + /** @size: Size to allocate for @data */ + __u32 size; + + /** @pad: MBZ */ + __u32 pad; + + union { + /** @data: Pointer to user-defined array of flexible size and type */ + __u64 data; + /** @value: Return value for scalar queries */ + __u64 value; + }; + + /** @reserved: MBZ */ + __u64 reserved[3]; +}; + /** * struct drm_xe_exec_queue_create - Input of &DRM_IOCTL_XE_EXEC_QUEUE_CREATE * @@ -1285,6 +1386,9 @@ struct drm_xe_vm_bind { * - %DRM_XE_EXEC_QUEUE_SET_PROPERTY_MULTI_QUEUE_PRIORITY - Set the queue * priority within the multi-queue group. Current valid priority values are 0–2 * (default is 1), with higher values indicating higher priority. + * - %DRM_XE_EXEC_QUEUE_SET_DISABLE_STATE_CACHE_PERF_FIX - Set the queue to + * enable render color cache keying on BTP+BTI instead of just BTI + * (only valid for render queues). * * The example below shows how to use @drm_xe_exec_queue_create to create * a simple exec_queue (no parallel submission) of class @@ -1329,6 +1433,7 @@ struct drm_xe_exec_queue_create { #define DRM_XE_EXEC_QUEUE_SET_PROPERTY_MULTI_GROUP 4 #define DRM_XE_MULTI_GROUP_CREATE (1ull << 63) #define DRM_XE_EXEC_QUEUE_SET_PROPERTY_MULTI_QUEUE_PRIORITY 5 +#define DRM_XE_EXEC_QUEUE_SET_DISABLE_STATE_CACHE_PERF_FIX 6 /** @extensions: Pointer to the first extension struct, if any */ __u64 extensions; @@ -2067,6 +2172,7 @@ struct drm_xe_query_eu_stall { * - DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC: Set preferred memory location. * - DRM_XE_MEM_RANGE_ATTR_ATOMIC: Set atomic access policy. * - DRM_XE_MEM_RANGE_ATTR_PAT: Set page attribute table index. + * - DRM_XE_VMA_ATTR_PURGEABLE_STATE: Set purgeable state for BOs. * * Example: * @@ -2099,6 +2205,7 @@ struct drm_xe_madvise { #define DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC 0 #define DRM_XE_MEM_RANGE_ATTR_ATOMIC 1 #define DRM_XE_MEM_RANGE_ATTR_PAT 2 +#define DRM_XE_VMA_ATTR_PURGEABLE_STATE 3 /** @type: type of attribute */ __u32 type; @@ -2189,6 +2296,72 @@ struct drm_xe_madvise { /** @pat_index.reserved: Reserved */ __u64 reserved; } pat_index; + + /** + * @purge_state_val: Purgeable state configuration + * + * Used when @type == DRM_XE_VMA_ATTR_PURGEABLE_STATE. + * + * Configures the purgeable state of buffer objects in the specified + * virtual address range. This allows applications to hint to the kernel + * about bo's usage patterns for better memory management. + * + * By default all VMAs are in WILLNEED state. + * + * Supported values for @purge_state_val.val: + * - DRM_XE_VMA_PURGEABLE_STATE_WILLNEED (0): Marks BO as needed. + * If the BO was previously purged, the kernel sets the __u32 at + * @retained_ptr to 0 (backing store lost) so the application knows + * it must recreate the BO. + * + * - DRM_XE_VMA_PURGEABLE_STATE_DONTNEED (1): Marks BO as not currently + * needed. Kernel may purge it under memory pressure to reclaim memory. + * Only applies to non-shared BOs. The kernel sets the __u32 at + * @retained_ptr to 1 if the backing store still exists (not yet purged), + * or 0 if it was already purged. + * + * Important: Once marked as DONTNEED, touching the BO's memory + * is undefined behavior. It may succeed temporarily (before the + * kernel purges the backing store) but will suddenly fail once + * the BO transitions to PURGED state. + * + * To transition back: use WILLNEED and check @retained_ptr — + * if 0, backing store was lost and the BO must be recreated. + * + * The following operations are blocked in DONTNEED state to + * prevent the BO from being re-mapped after madvise: + * - New mmap() calls: Fail with -EBUSY + * - VM_BIND operations: Fail with -EBUSY + * - New dma-buf exports: Fail with -EBUSY + * - CPU page faults (existing mmap): Fail with SIGBUS + * - GPU page faults (fault-mode VMs): Fail with -EACCES + */ + struct { +#define DRM_XE_VMA_PURGEABLE_STATE_WILLNEED 0 +#define DRM_XE_VMA_PURGEABLE_STATE_DONTNEED 1 + /** @purge_state_val.val: value for DRM_XE_VMA_ATTR_PURGEABLE_STATE */ + __u32 val; + + /** @purge_state_val.pad: MBZ */ + __u32 pad; + /** + * @purge_state_val.retained_ptr: Pointer to a __u32 output + * field for backing store status. + * + * Userspace must initialize the __u32 value at this address + * to 0 before the ioctl. Kernel writes a __u32 after the + * operation: + * - 1 if backing store exists (not purged) + * - 0 if backing store was purged + * + * If userspace fails to initialize to 0, ioctl returns -EINVAL. + * This ensures a safe default (0 = assume purged) if kernel + * cannot write the result. + * + * Similar to i915's drm_i915_gem_madvise.retained field. + */ + __u64 retained_ptr; + } purge_state_val; }; /** @reserved: Reserved */ @@ -2357,6 +2530,85 @@ struct drm_xe_exec_queue_set_property { __u64 reserved[2]; }; +/** + * DOC: Xe DRM RAS + * + * The enums and strings defined below map to the attributes of the DRM RAS Netlink Interface. + * Refer to Documentation/netlink/specs/drm_ras.yaml for complete interface specification. + * + * Node Registration + * ================= + * + * The driver registers DRM RAS nodes for each error severity level. + * enum drm_xe_ras_error_severity defines the node-id, while DRM_XE_RAS_ERROR_SEVERITY_NAMES maps + * node-id to node-name. + * + * Error Classification + * ==================== + * + * Each node contains a list of error counters. Each error is identified by a error-id and + * an error-name. enum drm_xe_ras_error_component defines the error-id, while + * DRM_XE_RAS_ERROR_COMPONENT_NAMES maps error-id to error-name. + * + * User Interface + * ============== + * + * To retrieve error values of a error counter, userspace applications should + * follow the below steps: + * + * 1. Use command LIST_NODES to enumerate all available nodes + * 2. Select node by node-id or node-name + * 3. Use command GET_ERROR_COUNTERS to list errors of specific node + * 4. Query specific error values using either error-id or error-name + * + * .. code-block:: C + * + * // Lookup tables for ID-to-name resolution + * static const char *nodes[] = DRM_XE_RAS_ERROR_SEVERITY_NAMES; + * static const char *errors[] = DRM_XE_RAS_ERROR_COMPONENT_NAMES; + * + */ + +/** + * enum drm_xe_ras_error_severity - DRM RAS error severity. + */ +enum drm_xe_ras_error_severity { + /** @DRM_XE_RAS_ERR_SEV_CORRECTABLE: Correctable Error */ + DRM_XE_RAS_ERR_SEV_CORRECTABLE = 0, + /** @DRM_XE_RAS_ERR_SEV_UNCORRECTABLE: Uncorrectable Error */ + DRM_XE_RAS_ERR_SEV_UNCORRECTABLE, + /** @DRM_XE_RAS_ERR_SEV_MAX: Max severity */ + DRM_XE_RAS_ERR_SEV_MAX /* non-ABI */ +}; + +/** + * enum drm_xe_ras_error_component - DRM RAS error component. + */ +enum drm_xe_ras_error_component { + /** @DRM_XE_RAS_ERR_COMP_CORE_COMPUTE: Core Compute Error */ + DRM_XE_RAS_ERR_COMP_CORE_COMPUTE = 1, + /** @DRM_XE_RAS_ERR_COMP_SOC_INTERNAL: SoC Internal Error */ + DRM_XE_RAS_ERR_COMP_SOC_INTERNAL, + /** @DRM_XE_RAS_ERR_COMP_MAX: Max Error */ + DRM_XE_RAS_ERR_COMP_MAX /* non-ABI */ +}; + +/* + * Error severity to name mapping. + */ +#define DRM_XE_RAS_ERROR_SEVERITY_NAMES { \ + [DRM_XE_RAS_ERR_SEV_CORRECTABLE] = "correctable-errors", \ + [DRM_XE_RAS_ERR_SEV_UNCORRECTABLE] = "uncorrectable-errors", \ +} + +/* + * Error component to name mapping. + */ +#define DRM_XE_RAS_ERROR_COMPONENT_NAMES { \ + [DRM_XE_RAS_ERR_COMP_CORE_COMPUTE] = "core-compute", \ + [DRM_XE_RAS_ERR_COMP_SOC_INTERNAL] = "soc-internal" \ +} + #if defined(__cplusplus) } #endif diff --git a/include/uapi/linux/const.h b/include/uapi/linux/const.h index b8f629ef135f..565f309b9df8 100644 --- a/include/uapi/linux/const.h +++ b/include/uapi/linux/const.h @@ -50,4 +50,22 @@ #define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) +/* + * Divide positive or negative dividend by positive or negative divisor + * and round to closest integer. Result is undefined for negative + * divisors if the dividend variable type is unsigned and for negative + * dividends if the divisor variable type is unsigned. + */ +#define __KERNEL_DIV_ROUND_CLOSEST(x, divisor) \ +({ \ + __typeof__(x) __x = x; \ + __typeof__(divisor) __d = divisor; \ + \ + (((__typeof__(x))-1) > 0 || \ + ((__typeof__(divisor))-1) > 0 || \ + (((__x) > 0) == ((__d) > 0))) ? \ + (((__x) + ((__d) / 2)) / (__d)) : \ + (((__x) - ((__d) / 2)) / (__d)); \ +}) + #endif /* _UAPI_LINUX_CONST_H */ |