AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

freedreno/drm: Import new UABI for VM_BIND

Browse Source 
Imported from kernel commit 203dcde88156
("Merge tag 'drm-msm-next-2025-07-05' of https://gitlab.freedesktop.org/drm/msm into drm-next").

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32533>
This commit is contained in:
Connor Abbott
2024-11-13 14:35:19 -05:00
committed by Marge Bot
parent 51a7aebc86
commit d8d0e73899
3 changed files with 141 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

149
include/drm-uapi/msm_drm.h
View File

@@ -91,6 +91,32 @@ struct drm_msm_timespec {
#define MSM_PARAM_UBWC_SWIZZLE 0x12 /* RO */
#define MSM_PARAM_MACROTILE_MODE 0x13 /* RO */
#define MSM_PARAM_UCHE_TRAP_BASE 0x14 /* RO */
/* PRR (Partially Resident Region) is required for sparse residency: */
#define MSM_PARAM_HAS_PRR 0x15 /* RO */
/* MSM_PARAM_EN_VM_BIND is set to 1 to enable VM_BIND ops.
*
* With VM_BIND enabled, userspace is required to allocate iova and use the
* VM_BIND ops for map/unmap ioctls. MSM_INFO_SET_IOVA and MSM_INFO_GET_IOVA
* will be rejected. (The latter does not have a sensible meaning when a BO
* can have multiple and/or partial mappings.)
*
* With VM_BIND enabled, userspace does not include a submit_bo table in the
* SUBMIT ioctl (this will be rejected), the resident set is determined by
* the the VM_BIND ops.
*
* Enabling VM_BIND will fail on devices which do not have per-process pgtables.
* And it is not allowed to disable VM_BIND once it has been enabled.
*
* Enabling VM_BIND should be done (attempted) prior to allocating any BOs or
* submitqueues of type MSM_SUBMITQUEUE_VM_BIND.
*
* Relatedly, when VM_BIND mode is enabled, the kernel will not try to recover
* from GPU faults or failed async VM_BIND ops, in particular because it is
* difficult to communicate to userspace which op failed so that userspace
* could rewind and try again. When the VM is marked unusable, the SUBMIT
* ioctl will throw -EPIPE.
*/
#define MSM_PARAM_EN_VM_BIND 0x16 /* WO, once */
/* For backwards compat. The original support for preemption was based on
* a single ring per priority level so # of priority levels equals the #
@@ -114,6 +140,19 @@ struct drm_msm_param {
#define MSM_BO_SCANOUT 0x00000001 /* scanout capable */
#define MSM_BO_GPU_READONLY 0x00000002
/* Private buffers do not need to be explicitly listed in the SUBMIT
* ioctl, unless referenced by a drm_msm_gem_submit_cmd. Private
* buffers may NOT be imported/exported or used for scanout (or any
* other situation where buffers can be indefinitely pinned, but
* cases other than scanout are all kernel owned BOs which are not
* visible to userspace).
*
* In exchange for those constraints, all private BOs associated with
* a single context (drm_file) share a single dma_resv, and if there
* has been no eviction since the last submit, there are no per-BO
* bookeeping to do, significantly cutting the SUBMIT overhead.
*/
#define MSM_BO_NO_SHARE 0x00000004
#define MSM_BO_CACHE_MASK 0x000f0000
/* cache modes */
#define MSM_BO_CACHED 0x00010000
@@ -123,6 +162,7 @@ struct drm_msm_param {
#define MSM_BO_FLAGS (MSM_BO_SCANOUT | \
MSM_BO_GPU_READONLY | \
MSM_BO_NO_SHARE | \
MSM_BO_CACHE_MASK)
struct drm_msm_gem_new {
@@ -180,6 +220,17 @@ struct drm_msm_gem_cpu_fini {
* Cmdstream Submission:
*/
#define MSM_SYNCOBJ_RESET 0x00000001 /* Reset syncobj after wait. */
#define MSM_SYNCOBJ_FLAGS ( \
MSM_SYNCOBJ_RESET | \
0)
struct drm_msm_syncobj {
__u32 handle; /* in, syncobj handle. */
__u32 flags; /* in, from MSM_SUBMIT_SYNCOBJ_FLAGS */
__u64 point; /* in, timepoint for timeline syncobjs. */
};
/* The value written into the cmdstream is logically:
*
* ((relocbuf->gpuaddr + reloc_offset) << shift) | or
@@ -221,7 +272,10 @@ struct drm_msm_gem_submit_cmd {
__u32 size; /* in, cmdstream size */
__u32 pad;
__u32 nr_relocs; /* in, number of submit_reloc's */
__u64 relocs; /* in, ptr to array of submit_reloc's */
union {
__u64 relocs; /* in, ptr to array of submit_reloc's */
__u64 iova; /* cmdstream address (for VM_BIND contexts) */
};
};
/* Each buffer referenced elsewhere in the cmdstream submit (ie. the
@@ -269,17 +323,6 @@ struct drm_msm_gem_submit_bo {
MSM_SUBMIT_FENCE_SN_IN | \
0)
#define MSM_SUBMIT_SYNCOBJ_RESET 0x00000001 /* Reset syncobj after wait. */
#define MSM_SUBMIT_SYNCOBJ_FLAGS ( \
MSM_SUBMIT_SYNCOBJ_RESET | \
0)
struct drm_msm_gem_submit_syncobj {
__u32 handle; /* in, syncobj handle. */
__u32 flags; /* in, from MSM_SUBMIT_SYNCOBJ_FLAGS */
__u64 point; /* in, timepoint for timeline syncobjs. */
};
/* Each cmdstream submit consists of a table of buffers involved, and
* one or more cmdstream buffers. This allows for conditional execution
* (context-restore), and IB buffers needed for per tile/bin draw cmds.
@@ -293,13 +336,80 @@ struct drm_msm_gem_submit {
__u64 cmds; /* in, ptr to array of submit_cmd's */
__s32 fence_fd; /* in/out fence fd (see MSM_SUBMIT_FENCE_FD_IN/OUT) */
__u32 queueid; /* in, submitqueue id */
__u64 in_syncobjs; /* in, ptr to array of drm_msm_gem_submit_syncobj */
__u64 out_syncobjs; /* in, ptr to array of drm_msm_gem_submit_syncobj */
__u64 in_syncobjs; /* in, ptr to array of drm_msm_syncobj */
__u64 out_syncobjs; /* in, ptr to array of drm_msm_syncobj */
__u32 nr_in_syncobjs; /* in, number of entries in in_syncobj */
__u32 nr_out_syncobjs; /* in, number of entries in out_syncobj. */
__u32 syncobj_stride; /* in, stride of syncobj arrays. */
__u32 pad; /*in, reserved for future use, always 0. */
};
#define MSM_VM_BIND_OP_UNMAP 0
#define MSM_VM_BIND_OP_MAP 1
#define MSM_VM_BIND_OP_MAP_NULL 2
#define MSM_VM_BIND_OP_DUMP 1
#define MSM_VM_BIND_OP_FLAGS ( \
MSM_VM_BIND_OP_DUMP | \
0)
/**
* struct drm_msm_vm_bind_op - bind/unbind op to run
*/
struct drm_msm_vm_bind_op {
/** @op: one of MSM_VM_BIND_OP_x */
__u32 op;
/** @handle: GEM object handle, MBZ for UNMAP or MAP_NULL */
__u32 handle;
/** @obj_offset: Offset into GEM object, MBZ for UNMAP or MAP_NULL */
__u64 obj_offset;
/** @iova: Address to operate on */
__u64 iova;
/** @range: Number of bites to to map/unmap */
__u64 range;
/** @flags: Bitmask of MSM_VM_BIND_OP_FLAG_x */
__u32 flags;
/** @pad: MBZ */
__u32 pad;
};
#define MSM_VM_BIND_FENCE_FD_IN 0x00000001
#define MSM_VM_BIND_FENCE_FD_OUT 0x00000002
#define MSM_VM_BIND_FLAGS ( \
MSM_VM_BIND_FENCE_FD_IN | \
MSM_VM_BIND_FENCE_FD_OUT | \
0)
/**
* struct drm_msm_vm_bind - Input of &DRM_IOCTL_MSM_VM_BIND
*/
struct drm_msm_vm_bind {
/** @flags: in, bitmask of MSM_VM_BIND_x */
__u32 flags;
/** @nr_ops: the number of bind ops in this ioctl */
__u32 nr_ops;
/** @fence_fd: in/out fence fd (see MSM_VM_BIND_FENCE_FD_IN/OUT) */
__s32 fence_fd;
/** @queue_id: in, submitqueue id */
__u32 queue_id;
/** @in_syncobjs: in, ptr to array of drm_msm_gem_syncobj */
__u64 in_syncobjs;
/** @out_syncobjs: in, ptr to array of drm_msm_gem_syncobj */
__u64 out_syncobjs;
/** @nr_in_syncobjs: in, number of entries in in_syncobj */
__u32 nr_in_syncobjs;
/** @nr_out_syncobjs: in, number of entries in out_syncobj */
__u32 nr_out_syncobjs;
/** @syncobj_stride: in, stride of syncobj arrays */
__u32 syncobj_stride;
/** @op_stride: sizeof each struct drm_msm_vm_bind_op in @ops */
__u32 op_stride;
union {
/** @op: used if num_ops == 1 */
struct drm_msm_vm_bind_op op;
/** @ops: userptr to array of drm_msm_vm_bind_op if num_ops > 1 */
__u64 ops;
};
};
#define MSM_WAIT_FENCE_BOOST 0x00000001
@@ -345,12 +455,19 @@ struct drm_msm_gem_madvise {
/*
* Draw queues allow the user to set specific submission parameter. Command
* submissions specify a specific submitqueue to use. ID 0 is reserved for
* backwards compatibility as a "default" submitqueue
* backwards compatibility as a "default" submitqueue.
*
* Because VM_BIND async updates happen on the CPU, they must run on a
* virtual queue created with the flag MSM_SUBMITQUEUE_VM_BIND. If we had
* a way to do pgtable updates on the GPU, we could drop this restriction.
*/
#define MSM_SUBMITQUEUE_ALLOW_PREEMPT 0x00000001
#define MSM_SUBMITQUEUE_VM_BIND 0x00000002 /* virtual queue for VM_BIND ops */
#define MSM_SUBMITQUEUE_FLAGS ( \
MSM_SUBMITQUEUE_ALLOW_PREEMPT | \
MSM_SUBMITQUEUE_VM_BIND | \
0)
/*
@@ -388,6 +505,7 @@ struct drm_msm_submitqueue_query {
#define DRM_MSM_SUBMITQUEUE_NEW 0x0A
#define DRM_MSM_SUBMITQUEUE_CLOSE 0x0B
#define DRM_MSM_SUBMITQUEUE_QUERY 0x0C
#define DRM_MSM_VM_BIND 0x0D
#define DRM_IOCTL_MSM_GET_PARAM DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GET_PARAM, struct drm_msm_param)
#define DRM_IOCTL_MSM_SET_PARAM DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_SET_PARAM, struct drm_msm_param)
@@ -401,6 +519,7 @@ struct drm_msm_submitqueue_query {
#define DRM_IOCTL_MSM_SUBMITQUEUE_NEW DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_SUBMITQUEUE_NEW, struct drm_msm_submitqueue)
#define DRM_IOCTL_MSM_SUBMITQUEUE_CLOSE DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_SUBMITQUEUE_CLOSE, __u32)
#define DRM_IOCTL_MSM_SUBMITQUEUE_QUERY DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_SUBMITQUEUE_QUERY, struct drm_msm_submitqueue_query)
#define DRM_IOCTL_MSM_VM_BIND DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_VM_BIND, struct drm_msm_vm_bind)
#if defined(__cplusplus)
}

2
src/freedreno/decode/replay.c
View File

@@ -584,7 +584,7 @@ device_submit_cmdstreams(struct device *dev)
.out_syncobjs = 0,
.nr_in_syncobjs = 0,
.nr_out_syncobjs = 0,
.syncobj_stride = sizeof(struct drm_msm_gem_submit_syncobj),
.syncobj_stride = sizeof(struct drm_msm_syncobj),
};
int ret = drmCommandWriteRead(dev->fd, DRM_MSM_GEM_SUBMIT, &submit_req,

12
src/freedreno/vulkan/tu_knl_drm_msm.cc
View File

@@ -907,7 +907,7 @@ msm_queue_submit(struct tu_queue *queue, void *_submit,
int ret;
struct tu_msm_queue_submit *submit =
(struct tu_msm_queue_submit *)_submit;
struct drm_msm_gem_submit_syncobj *in_syncobjs, *out_syncobjs;
struct drm_msm_syncobj *in_syncobjs, *out_syncobjs;
struct drm_msm_gem_submit req;
uint64_t gpu_offset = 0;
uint32_t entry_count =
@@ -920,7 +920,7 @@ msm_queue_submit(struct tu_queue *queue, void *_submit,
uint32_t flags = MSM_PIPE_3D0;
/* Allocate without wait timeline semaphores */
in_syncobjs = (struct drm_msm_gem_submit_syncobj *) vk_zalloc(
in_syncobjs = (struct drm_msm_syncobj *) vk_zalloc(
&queue->device->vk.alloc,
wait_count * sizeof(*in_syncobjs), 8,
VK_SYSTEM_ALLOCATION_SCOPE_DEVICE);
@@ -931,7 +931,7 @@ msm_queue_submit(struct tu_queue *queue, void *_submit,
}
/* Allocate with signal timeline semaphores considered */
out_syncobjs = (struct drm_msm_gem_submit_syncobj *) vk_zalloc(
out_syncobjs = (struct drm_msm_syncobj *) vk_zalloc(
&queue->device->vk.alloc,
signal_count * sizeof(*out_syncobjs), 8,
VK_SYSTEM_ALLOCATION_SCOPE_DEVICE);
@@ -944,7 +944,7 @@ msm_queue_submit(struct tu_queue *queue, void *_submit,
for (uint32_t i = 0; i < wait_count; i++) {
struct vk_sync *sync = waits[i].sync;
in_syncobjs[i] = (struct drm_msm_gem_submit_syncobj) {
in_syncobjs[i] = (struct drm_msm_syncobj) {
.handle = vk_sync_as_drm_syncobj(sync)->syncobj,
.flags = 0,
.point = waits[i].wait_value,
@@ -954,7 +954,7 @@ msm_queue_submit(struct tu_queue *queue, void *_submit,
for (uint32_t i = 0; i < signal_count; i++) {
struct vk_sync *sync = signals[i].sync;
out_syncobjs[i] = (struct drm_msm_gem_submit_syncobj) {
out_syncobjs[i] = (struct drm_msm_syncobj) {
.handle = vk_sync_as_drm_syncobj(sync)->syncobj,
.flags = 0,
.point = signals[i].signal_value,
@@ -1013,7 +1013,7 @@ msm_queue_submit(struct tu_queue *queue, void *_submit,
.out_syncobjs = (uint64_t)(uintptr_t)out_syncobjs,
.nr_in_syncobjs = wait_count,
.nr_out_syncobjs = signal_count,
.syncobj_stride = sizeof(struct drm_msm_gem_submit_syncobj),
.syncobj_stride = sizeof(struct drm_msm_syncobj),
};
{