From 9d77db3c730780c8ef5ccd4b66403ff5675cfe4e Mon Sep 17 00:00:00 2001 From: hc <hc@nodka.com> Date: Mon, 13 May 2024 10:30:14 +0000 Subject: [PATCH] modify sin led gpio --- kernel/drivers/gpu/drm/msm/msm_gem_submit.c | 360 +++++++++++++++++++++++++++++++++++++++++++++++++---------- 1 files changed, 297 insertions(+), 63 deletions(-) diff --git a/kernel/drivers/gpu/drm/msm/msm_gem_submit.c b/kernel/drivers/gpu/drm/msm/msm_gem_submit.c index c3ae750..c4e5037 100644 --- a/kernel/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/kernel/drivers/gpu/drm/msm/msm_gem_submit.c @@ -1,25 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2013 Red Hat * Author: Rob Clark <robdclark@gmail.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/file.h> #include <linux/sync_file.h> +#include <linux/uaccess.h> + +#include <drm/drm_drv.h> +#include <drm/drm_file.h> +#include <drm/drm_syncobj.h> #include "msm_drv.h" #include "msm_gpu.h" #include "msm_gem.h" +#include "msm_gpu_trace.h" /* * Cmdstream submission: @@ -31,12 +27,13 @@ #define BO_PINNED 0x2000 static struct msm_gem_submit *submit_create(struct drm_device *dev, - struct msm_gpu *gpu, struct msm_gpu_submitqueue *queue, - uint32_t nr_bos, uint32_t nr_cmds) + struct msm_gpu *gpu, + struct msm_gpu_submitqueue *queue, uint32_t nr_bos, + uint32_t nr_cmds) { struct msm_gem_submit *submit; - uint64_t sz = sizeof(*submit) + ((u64)nr_bos * sizeof(submit->bos[0])) + - ((u64)nr_cmds * sizeof(submit->cmd[0])); + uint64_t sz = struct_size(submit, bos, nr_bos) + + ((u64)nr_cmds * sizeof(submit->cmd[0])); if (sz > SIZE_MAX) return NULL; @@ -46,9 +43,9 @@ return NULL; submit->dev = dev; + submit->aspace = queue->ctx->aspace; submit->gpu = gpu; submit->fence = NULL; - submit->pid = get_pid(task_pid(current)); submit->cmd = (void *)&submit->bos[nr_bos]; submit->queue = queue; submit->ring = gpu->rb[queue->prio]; @@ -59,7 +56,6 @@ INIT_LIST_HEAD(&submit->node); INIT_LIST_HEAD(&submit->bo_list); - ww_acquire_init(&submit->ticket, &reservation_ww_class); return submit; } @@ -74,27 +70,14 @@ kfree(submit); } -static inline unsigned long __must_check -copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) -{ - if (access_ok(VERIFY_READ, from, n)) - return __copy_from_user_inatomic(to, from, n); - return -EFAULT; -} - static int submit_lookup_objects(struct msm_gem_submit *submit, struct drm_msm_gem_submit *args, struct drm_file *file) { unsigned i; int ret = 0; - spin_lock(&file->table_lock); - pagefault_disable(); - for (i = 0; i < args->nr_bos; i++) { struct drm_msm_gem_submit_bo submit_bo; - struct drm_gem_object *obj; - struct msm_gem_object *msm_obj; void __user *userptr = u64_to_user_ptr(args->bos + (i * sizeof(submit_bo))); @@ -103,34 +86,41 @@ */ submit->bos[i].flags = 0; - if (copy_from_user_inatomic(&submit_bo, userptr, sizeof(submit_bo))) { - pagefault_enable(); - spin_unlock(&file->table_lock); - if (copy_from_user(&submit_bo, userptr, sizeof(submit_bo))) { - ret = -EFAULT; - goto out; - } - spin_lock(&file->table_lock); - pagefault_disable(); + if (copy_from_user(&submit_bo, userptr, sizeof(submit_bo))) { + ret = -EFAULT; + i = 0; + goto out; } + +/* at least one of READ and/or WRITE flags should be set: */ +#define MANDATORY_FLAGS (MSM_SUBMIT_BO_READ | MSM_SUBMIT_BO_WRITE) if ((submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) || - !(submit_bo.flags & MSM_SUBMIT_BO_FLAGS)) { + !(submit_bo.flags & MANDATORY_FLAGS)) { DRM_ERROR("invalid flags: %x\n", submit_bo.flags); ret = -EINVAL; - goto out_unlock; + i = 0; + goto out; } + submit->bos[i].handle = submit_bo.handle; submit->bos[i].flags = submit_bo.flags; /* in validate_objects() we figure out if this is true: */ submit->bos[i].iova = submit_bo.presumed; + } + + spin_lock(&file->table_lock); + + for (i = 0; i < args->nr_bos; i++) { + struct drm_gem_object *obj; + struct msm_gem_object *msm_obj; /* normally use drm_gem_object_lookup(), but for bulk lookup * all under single table_lock just hit object_idr directly: */ - obj = idr_find(&file->object_idr, submit_bo.handle); + obj = idr_find(&file->object_idr, submit->bos[i].handle); if (!obj) { - DRM_ERROR("invalid handle %u at index %u\n", submit_bo.handle, i); + DRM_ERROR("invalid handle %u at index %u\n", submit->bos[i].handle, i); ret = -EINVAL; goto out_unlock; } @@ -139,12 +129,12 @@ if (!list_empty(&msm_obj->submit_entry)) { DRM_ERROR("handle %u at index %u already on submit list\n", - submit_bo.handle, i); + submit->bos[i].handle, i); ret = -EINVAL; goto out_unlock; } - drm_gem_object_reference(obj); + drm_gem_object_get(obj); submit->bos[i].obj = msm_obj; @@ -152,7 +142,6 @@ } out_unlock: - pagefault_enable(); spin_unlock(&file->table_lock); out: @@ -167,10 +156,10 @@ struct msm_gem_object *msm_obj = submit->bos[i].obj; if (submit->bos[i].flags & BO_PINNED) - msm_gem_put_iova(&msm_obj->base, submit->gpu->aspace); + msm_gem_unpin_iova(&msm_obj->base, submit->aspace); if (submit->bos[i].flags & BO_LOCKED) - ww_mutex_unlock(&msm_obj->resv->lock); + dma_resv_unlock(msm_obj->base.resv); if (backoff && !(submit->bos[i].flags & BO_VALID)) submit->bos[i].iova = 0; @@ -193,8 +182,8 @@ contended = i; if (!(submit->bos[i].flags & BO_LOCKED)) { - ret = ww_mutex_lock_interruptible(&msm_obj->resv->lock, - &submit->ticket); + ret = dma_resv_lock_interruptible(msm_obj->base.resv, + &submit->ticket); if (ret) goto fail; submit->bos[i].flags |= BO_LOCKED; @@ -215,8 +204,8 @@ if (ret == -EDEADLK) { struct msm_gem_object *msm_obj = submit->bos[contended].obj; /* we lost out in a seqno race, lock and retry.. */ - ret = ww_mutex_lock_slow_interruptible(&msm_obj->resv->lock, - &submit->ticket); + ret = dma_resv_lock_slow_interruptible(msm_obj->base.resv, + &submit->ticket); if (!ret) { submit->bos[contended].flags |= BO_LOCKED; slow_locked = contended; @@ -241,7 +230,8 @@ * strange place to call it. OTOH this is a * convenient can-fail point to hook it in. */ - ret = reservation_object_reserve_shared(msm_obj->resv); + ret = dma_resv_reserve_shared(msm_obj->base.resv, + 1); if (ret) return ret; } @@ -269,8 +259,8 @@ uint64_t iova; /* if locking succeeded, pin bo: */ - ret = msm_gem_get_iova(&msm_obj->base, - submit->gpu->aspace, &iova); + ret = msm_gem_get_and_pin_iova(&msm_obj->base, + submit->aspace, &iova); if (ret) break; @@ -316,6 +306,9 @@ uint32_t i, last_offset = 0; uint32_t *ptr; int ret = 0; + + if (!nr_relocs) + return 0; if (offset % 4) { DRM_ERROR("non-aligned cmdstream buffer: %u\n", offset); @@ -396,15 +389,193 @@ struct msm_gem_object *msm_obj = submit->bos[i].obj; submit_unlock_unpin_bo(submit, i, false); list_del_init(&msm_obj->submit_entry); - drm_gem_object_unreference(&msm_obj->base); + drm_gem_object_put_locked(&msm_obj->base); + } +} + + +struct msm_submit_post_dep { + struct drm_syncobj *syncobj; + uint64_t point; + struct dma_fence_chain *chain; +}; + +static struct drm_syncobj **msm_wait_deps(struct drm_device *dev, + struct drm_file *file, + uint64_t in_syncobjs_addr, + uint32_t nr_in_syncobjs, + size_t syncobj_stride, + struct msm_ringbuffer *ring) +{ + struct drm_syncobj **syncobjs = NULL; + struct drm_msm_gem_submit_syncobj syncobj_desc = {0}; + int ret = 0; + uint32_t i, j; + + syncobjs = kcalloc(nr_in_syncobjs, sizeof(*syncobjs), + GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); + if (!syncobjs) + return ERR_PTR(-ENOMEM); + + for (i = 0; i < nr_in_syncobjs; ++i) { + uint64_t address = in_syncobjs_addr + i * syncobj_stride; + struct dma_fence *fence; + + if (copy_from_user(&syncobj_desc, + u64_to_user_ptr(address), + min(syncobj_stride, sizeof(syncobj_desc)))) { + ret = -EFAULT; + break; + } + + if (syncobj_desc.point && + !drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE)) { + ret = -EOPNOTSUPP; + break; + } + + if (syncobj_desc.flags & ~MSM_SUBMIT_SYNCOBJ_FLAGS) { + ret = -EINVAL; + break; + } + + ret = drm_syncobj_find_fence(file, syncobj_desc.handle, + syncobj_desc.point, 0, &fence); + if (ret) + break; + + if (!dma_fence_match_context(fence, ring->fctx->context)) + ret = dma_fence_wait(fence, true); + + dma_fence_put(fence); + if (ret) + break; + + if (syncobj_desc.flags & MSM_SUBMIT_SYNCOBJ_RESET) { + syncobjs[i] = + drm_syncobj_find(file, syncobj_desc.handle); + if (!syncobjs[i]) { + ret = -EINVAL; + break; + } + } } - ww_acquire_fini(&submit->ticket); + if (ret) { + for (j = 0; j <= i; ++j) { + if (syncobjs[j]) + drm_syncobj_put(syncobjs[j]); + } + kfree(syncobjs); + return ERR_PTR(ret); + } + return syncobjs; +} + +static void msm_reset_syncobjs(struct drm_syncobj **syncobjs, + uint32_t nr_syncobjs) +{ + uint32_t i; + + for (i = 0; syncobjs && i < nr_syncobjs; ++i) { + if (syncobjs[i]) + drm_syncobj_replace_fence(syncobjs[i], NULL); + } +} + +static struct msm_submit_post_dep *msm_parse_post_deps(struct drm_device *dev, + struct drm_file *file, + uint64_t syncobjs_addr, + uint32_t nr_syncobjs, + size_t syncobj_stride) +{ + struct msm_submit_post_dep *post_deps; + struct drm_msm_gem_submit_syncobj syncobj_desc = {0}; + int ret = 0; + uint32_t i, j; + + post_deps = kcalloc(nr_syncobjs, sizeof(*post_deps), + GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); + if (!post_deps) + return ERR_PTR(-ENOMEM); + + for (i = 0; i < nr_syncobjs; ++i) { + uint64_t address = syncobjs_addr + i * syncobj_stride; + + if (copy_from_user(&syncobj_desc, + u64_to_user_ptr(address), + min(syncobj_stride, sizeof(syncobj_desc)))) { + ret = -EFAULT; + break; + } + + post_deps[i].point = syncobj_desc.point; + + if (syncobj_desc.flags) { + ret = -EINVAL; + break; + } + + if (syncobj_desc.point) { + if (!drm_core_check_feature(dev, + DRIVER_SYNCOBJ_TIMELINE)) { + ret = -EOPNOTSUPP; + break; + } + + post_deps[i].chain = + kmalloc(sizeof(*post_deps[i].chain), + GFP_KERNEL); + if (!post_deps[i].chain) { + ret = -ENOMEM; + break; + } + } + + post_deps[i].syncobj = + drm_syncobj_find(file, syncobj_desc.handle); + if (!post_deps[i].syncobj) { + ret = -EINVAL; + break; + } + } + + if (ret) { + for (j = 0; j <= i; ++j) { + kfree(post_deps[j].chain); + if (post_deps[j].syncobj) + drm_syncobj_put(post_deps[j].syncobj); + } + + kfree(post_deps); + return ERR_PTR(ret); + } + + return post_deps; +} + +static void msm_process_post_deps(struct msm_submit_post_dep *post_deps, + uint32_t count, struct dma_fence *fence) +{ + uint32_t i; + + for (i = 0; post_deps && i < count; ++i) { + if (post_deps[i].chain) { + drm_syncobj_add_point(post_deps[i].syncobj, + post_deps[i].chain, + fence, post_deps[i].point); + post_deps[i].chain = NULL; + } else { + drm_syncobj_replace_fence(post_deps[i].syncobj, + fence); + } + } } int msm_ioctl_gem_submit(struct drm_device *dev, void *data, struct drm_file *file) { + static atomic_t ident = ATOMIC_INIT(0); struct msm_drm_private *priv = dev->dev_private; struct drm_msm_gem_submit *args = data; struct msm_file_private *ctx = file->driver_priv; @@ -413,12 +584,18 @@ struct sync_file *sync_file = NULL; struct msm_gpu_submitqueue *queue; struct msm_ringbuffer *ring; + struct msm_submit_post_dep *post_deps = NULL; + struct drm_syncobj **syncobjs_to_reset = NULL; int out_fence_fd = -1; + struct pid *pid = get_pid(task_pid(current)); + bool has_ww_ticket = false; unsigned i; - int ret; - + int ret, submitid; if (!gpu) return -ENXIO; + + if (args->pad) + return -EINVAL; /* for now, we just have 3d pipe.. eventually this would need to * be more clever to dispatch to appropriate gpu module: @@ -439,7 +616,12 @@ if (!queue) return -ENOENT; + /* Get a unique identifier for the submission for logging purposes */ + submitid = atomic_inc_return(&ident) - 1; + ring = gpu->rb[queue->prio]; + trace_msm_gpu_submit(pid_nr(pid), ring->id, submitid, + args->nr_bos, args->nr_cmds); if (args->flags & MSM_SUBMIT_FENCE_FD_IN) { struct dma_fence *in_fence; @@ -462,9 +644,29 @@ return ret; } + if (args->flags & MSM_SUBMIT_SYNCOBJ_IN) { + syncobjs_to_reset = msm_wait_deps(dev, file, + args->in_syncobjs, + args->nr_in_syncobjs, + args->syncobj_stride, ring); + if (IS_ERR(syncobjs_to_reset)) + return PTR_ERR(syncobjs_to_reset); + } + + if (args->flags & MSM_SUBMIT_SYNCOBJ_OUT) { + post_deps = msm_parse_post_deps(dev, file, + args->out_syncobjs, + args->nr_out_syncobjs, + args->syncobj_stride); + if (IS_ERR(post_deps)) { + ret = PTR_ERR(post_deps); + goto out_post_unlock; + } + } + ret = mutex_lock_interruptible(&dev->struct_mutex); if (ret) - return ret; + goto out_post_unlock; if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) { out_fence_fd = get_unused_fd_flags(O_CLOEXEC); @@ -474,11 +676,15 @@ } } - submit = submit_create(dev, gpu, queue, args->nr_bos, args->nr_cmds); + submit = submit_create(dev, gpu, queue, args->nr_bos, + args->nr_cmds); if (!submit) { ret = -ENOMEM; goto out_unlock; } + + submit->pid = pid; + submit->ident = submitid; if (args->flags & MSM_SUBMIT_SUDO) submit->in_rb = true; @@ -487,6 +693,9 @@ if (ret) goto out; + /* copy_*_user while holding a ww ticket upsets lockdep */ + ww_acquire_init(&submit->ticket, &reservation_ww_class); + has_ww_ticket = true; ret = submit_lock_objects(submit); if (ret) goto out; @@ -575,7 +784,7 @@ } } - msm_gpu_submit(gpu, submit, ctx); + msm_gpu_submit(gpu, submit); args->fence = submit->fence->seqno; @@ -584,13 +793,38 @@ args->fence_fd = out_fence_fd; } + msm_reset_syncobjs(syncobjs_to_reset, args->nr_in_syncobjs); + msm_process_post_deps(post_deps, args->nr_out_syncobjs, + submit->fence); + + out: submit_cleanup(submit); + if (has_ww_ticket) + ww_acquire_fini(&submit->ticket); if (ret) msm_gem_submit_free(submit); out_unlock: if (ret && (out_fence_fd >= 0)) put_unused_fd(out_fence_fd); mutex_unlock(&dev->struct_mutex); + +out_post_unlock: + if (!IS_ERR_OR_NULL(post_deps)) { + for (i = 0; i < args->nr_out_syncobjs; ++i) { + kfree(post_deps[i].chain); + drm_syncobj_put(post_deps[i].syncobj); + } + kfree(post_deps); + } + + if (!IS_ERR_OR_NULL(syncobjs_to_reset)) { + for (i = 0; i < args->nr_in_syncobjs; ++i) { + if (syncobjs_to_reset[i]) + drm_syncobj_put(syncobjs_to_reset[i]); + } + kfree(syncobjs_to_reset); + } + return ret; } -- Gitblit v1.6.2