diff options
Diffstat (limited to 'drivers/dma-buf')
-rw-r--r-- | drivers/dma-buf/Kconfig | 6 | ||||
-rw-r--r-- | drivers/dma-buf/Makefile | 6 | ||||
-rw-r--r-- | drivers/dma-buf/dma-buf-sysfs-stats.c | 2 | ||||
-rw-r--r-- | drivers/dma-buf/dma-buf.c | 203 | ||||
-rw-r--r-- | drivers/dma-buf/dma-fence-array.c | 52 | ||||
-rw-r--r-- | drivers/dma-buf/dma-fence-chain.c | 19 | ||||
-rw-r--r-- | drivers/dma-buf/dma-fence-unwrap.c | 163 | ||||
-rw-r--r-- | drivers/dma-buf/dma-fence.c | 39 | ||||
-rw-r--r-- | drivers/dma-buf/dma-heap.c | 2 | ||||
-rw-r--r-- | drivers/dma-buf/dma-resv.c | 546 | ||||
-rw-r--r-- | drivers/dma-buf/heaps/cma_heap.c | 16 | ||||
-rw-r--r-- | drivers/dma-buf/heaps/system_heap.c | 10 | ||||
-rw-r--r-- | drivers/dma-buf/selftests.h | 2 | ||||
-rw-r--r-- | drivers/dma-buf/st-dma-fence-chain.c | 4 | ||||
-rw-r--r-- | drivers/dma-buf/st-dma-fence-unwrap.c | 382 | ||||
-rw-r--r-- | drivers/dma-buf/st-dma-fence.c | 16 | ||||
-rw-r--r-- | drivers/dma-buf/st-dma-resv.c | 316 | ||||
-rw-r--r-- | drivers/dma-buf/sync_file.c | 157 | ||||
-rw-r--r-- | drivers/dma-buf/udmabuf.c | 38 |
19 files changed, 1519 insertions, 460 deletions
diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig index 541efe01abc7..e4dc53a36428 100644 --- a/drivers/dma-buf/Kconfig +++ b/drivers/dma-buf/Kconfig @@ -75,7 +75,7 @@ menuconfig DMABUF_HEAPS between drivers. menuconfig DMABUF_SYSFS_STATS - bool "DMA-BUF sysfs statistics" + bool "DMA-BUF sysfs statistics (DEPRECATED)" depends on DMA_SHARED_BUFFER help Choose this option to enable DMA-BUF sysfs statistics @@ -85,6 +85,10 @@ menuconfig DMABUF_SYSFS_STATS statistics for the DMA-BUF with the unique inode number <inode_number>. + This option is deprecated and should sooner or later be removed. + Android is the only user of this and it turned out that this resulted + in quite some performance problems. + source "drivers/dma-buf/heaps/Kconfig" endmenu diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile index 1ef021273a06..70ec901edf2c 100644 --- a/drivers/dma-buf/Makefile +++ b/drivers/dma-buf/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y := dma-buf.o dma-fence.o dma-fence-array.o dma-fence-chain.o \ - dma-resv.o + dma-fence-unwrap.o dma-resv.o obj-$(CONFIG_DMABUF_HEAPS) += dma-heap.o obj-$(CONFIG_DMABUF_HEAPS) += heaps/ obj-$(CONFIG_SYNC_FILE) += sync_file.o @@ -11,6 +11,8 @@ obj-$(CONFIG_DMABUF_SYSFS_STATS) += dma-buf-sysfs-stats.o dmabuf_selftests-y := \ selftest.o \ st-dma-fence.o \ - st-dma-fence-chain.o + st-dma-fence-chain.o \ + st-dma-fence-unwrap.o \ + st-dma-resv.o obj-$(CONFIG_DMABUF_SELFTESTS) += dmabuf_selftests.o diff --git a/drivers/dma-buf/dma-buf-sysfs-stats.c b/drivers/dma-buf/dma-buf-sysfs-stats.c index 053baadcada9..2bba0babcb62 100644 --- a/drivers/dma-buf/dma-buf-sysfs-stats.c +++ b/drivers/dma-buf/dma-buf-sysfs-stats.c @@ -132,7 +132,7 @@ void dma_buf_stats_teardown(struct dma_buf *dmabuf) /* Statistics files do not need to send uevents. */ -static int dmabuf_sysfs_uevent_filter(struct kset *kset, struct kobject *kobj) +static int dmabuf_sysfs_uevent_filter(struct kobject *kobj) { return 0; } diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 6437b2e978fb..dd0f83ee505b 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -20,6 +20,7 @@ #include <linux/debugfs.h> #include <linux/module.h> #include <linux/seq_file.h> +#include <linux/sync_file.h> #include <linux/poll.h> #include <linux/dma-resv.h> #include <linux/mm.h> @@ -52,7 +53,7 @@ static char *dmabuffs_dname(struct dentry *dentry, char *buffer, int buflen) ret = strlcpy(name, dmabuf->name, DMA_BUF_NAME_LEN); spin_unlock(&dmabuf->name_lock); - return dynamic_dname(dentry, buffer, buflen, "/%s:%s", + return dynamic_dname(buffer, buflen, "/%s:%s", dentry->d_name.name, ret > 0 ? name : ""); } @@ -192,6 +193,9 @@ static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence) * Note that this only signals the completion of the respective fences, i.e. the * DMA transfers are complete. Cache flushing and any other necessary * preparations before CPU access can begin still need to happen. + * + * As an alternative to poll(), the set of fences on DMA buffer can be + * exported as a &sync_file using &dma_buf_sync_file_export. */ static void dma_buf_poll_cb(struct dma_fence *fence, struct dma_fence_cb *cb) @@ -216,7 +220,8 @@ static bool dma_buf_poll_add_cb(struct dma_resv *resv, bool write, struct dma_fence *fence; int r; - dma_resv_for_each_fence(&cursor, resv, write, fence) { + dma_resv_for_each_fence(&cursor, resv, dma_resv_usage_rw(write), + fence) { dma_fence_get(fence); r = dma_fence_add_callback(fence, &dcb->cb, dma_buf_poll_cb); if (!r) @@ -299,10 +304,8 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll) /** * dma_buf_set_name - Set a name to a specific dma_buf to track the usage. - * The name of the dma-buf buffer can only be set when the dma-buf is not - * attached to any devices. It could theoritically support changing the - * name of the dma-buf if the same piece of memory is used for multiple - * purpose between different devices. + * It could support changing the name of the dma-buf if the same + * piece of memory is used for multiple purpose between different devices. * * @dmabuf: [in] dmabuf buffer that will be renamed. * @buf: [in] A piece of userspace memory that contains the name of @@ -315,26 +318,112 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll) static long dma_buf_set_name(struct dma_buf *dmabuf, const char __user *buf) { char *name = strndup_user(buf, DMA_BUF_NAME_LEN); - long ret = 0; if (IS_ERR(name)) return PTR_ERR(name); - dma_resv_lock(dmabuf->resv, NULL); - if (!list_empty(&dmabuf->attachments)) { - ret = -EBUSY; - kfree(name); - goto out_unlock; - } spin_lock(&dmabuf->name_lock); kfree(dmabuf->name); dmabuf->name = name; spin_unlock(&dmabuf->name_lock); -out_unlock: + return 0; +} + +#if IS_ENABLED(CONFIG_SYNC_FILE) +static long dma_buf_export_sync_file(struct dma_buf *dmabuf, + void __user *user_data) +{ + struct dma_buf_export_sync_file arg; + enum dma_resv_usage usage; + struct dma_fence *fence = NULL; + struct sync_file *sync_file; + int fd, ret; + + if (copy_from_user(&arg, user_data, sizeof(arg))) + return -EFAULT; + + if (arg.flags & ~DMA_BUF_SYNC_RW) + return -EINVAL; + + if ((arg.flags & DMA_BUF_SYNC_RW) == 0) + return -EINVAL; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) + return fd; + + usage = dma_resv_usage_rw(arg.flags & DMA_BUF_SYNC_WRITE); + ret = dma_resv_get_singleton(dmabuf->resv, usage, &fence); + if (ret) + goto err_put_fd; + + if (!fence) + fence = dma_fence_get_stub(); + + sync_file = sync_file_create(fence); + + dma_fence_put(fence); + + if (!sync_file) { + ret = -ENOMEM; + goto err_put_fd; + } + + arg.fd = fd; + if (copy_to_user(user_data, &arg, sizeof(arg))) { + ret = -EFAULT; + goto err_put_file; + } + + fd_install(fd, sync_file->file); + + return 0; + +err_put_file: + fput(sync_file->file); +err_put_fd: + put_unused_fd(fd); + return ret; +} + +static long dma_buf_import_sync_file(struct dma_buf *dmabuf, + const void __user *user_data) +{ + struct dma_buf_import_sync_file arg; + struct dma_fence *fence; + enum dma_resv_usage usage; + int ret = 0; + + if (copy_from_user(&arg, user_data, sizeof(arg))) + return -EFAULT; + + if (arg.flags & ~DMA_BUF_SYNC_RW) + return -EINVAL; + + if ((arg.flags & DMA_BUF_SYNC_RW) == 0) + return -EINVAL; + + fence = sync_file_get_fence(arg.fd); + if (!fence) + return -EINVAL; + + usage = (arg.flags & DMA_BUF_SYNC_WRITE) ? DMA_RESV_USAGE_WRITE : + DMA_RESV_USAGE_READ; + + dma_resv_lock(dmabuf->resv, NULL); + + ret = dma_resv_reserve_fences(dmabuf->resv, 1); + if (!ret) + dma_resv_add_fence(dmabuf->resv, fence, usage); + dma_resv_unlock(dmabuf->resv); + + dma_fence_put(fence); + return ret; } +#endif static long dma_buf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) @@ -379,6 +468,13 @@ static long dma_buf_ioctl(struct file *file, case DMA_BUF_SET_NAME_B: return dma_buf_set_name(dmabuf, (const char __user *)arg); +#if IS_ENABLED(CONFIG_SYNC_FILE) + case DMA_BUF_IOCTL_EXPORT_SYNC_FILE: + return dma_buf_export_sync_file(dmabuf, (void __user *)arg); + case DMA_BUF_IOCTL_IMPORT_SYNC_FILE: + return dma_buf_import_sync_file(dmabuf, (const void __user *)arg); +#endif + default: return -ENOTTY; } @@ -418,6 +514,7 @@ static inline int is_dma_buf_file(struct file *file) static struct file *dma_buf_getfile(struct dma_buf *dmabuf, int flags) { + static atomic64_t dmabuf_inode = ATOMIC64_INIT(0); struct file *file; struct inode *inode = alloc_anon_inode(dma_buf_mnt->mnt_sb); @@ -427,11 +524,18 @@ static struct file *dma_buf_getfile(struct dma_buf *dmabuf, int flags) inode->i_size = dmabuf->size; inode_set_bytes(inode, dmabuf->size); + /* + * The ->i_ino acquired from get_next_ino() is not unique thus + * not suitable for using it as dentry name by dmabuf stats. + * Override ->i_ino with the unique and dmabuffs specific + * value. + */ + inode->i_ino = atomic64_add_return(1, &dmabuf_inode); + flags &= O_ACCMODE | O_NONBLOCK; file = alloc_file_pseudo(inode, dma_buf_mnt, "dmabuf", flags, &dma_buf_fops); if (IS_ERR(file)) goto err_alloc_file; - file->f_flags = flags & (O_ACCMODE | O_NONBLOCK); file->private_data = dmabuf; file->f_path.dentry->d_fsdata = dmabuf; @@ -454,7 +558,7 @@ err_alloc_file: * as a file descriptor by calling dma_buf_fd(). * * 2. Userspace passes this file-descriptors to all drivers it wants this buffer - * to share with: First the filedescriptor is converted to a &dma_buf using + * to share with: First the file descriptor is converted to a &dma_buf using * dma_buf_get(). Then the buffer is attached to the device using * dma_buf_attach(). * @@ -551,13 +655,8 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) goto err_dmabuf; } - file->f_mode |= FMODE_LSEEK; dmabuf->file = file; - ret = dma_buf_stats_setup(dmabuf); - if (ret) - goto err_sysfs; - mutex_init(&dmabuf->lock); INIT_LIST_HEAD(&dmabuf->attachments); @@ -565,6 +664,10 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) list_add(&dmabuf->list_node, &db_list.head); mutex_unlock(&db_list.lock); + ret = dma_buf_stats_setup(dmabuf); + if (ret) + goto err_sysfs; + return dmabuf; err_sysfs: @@ -671,12 +774,24 @@ static struct sg_table * __map_dma_buf(struct dma_buf_attachment *attach, enum dma_data_direction direction) { struct sg_table *sg_table; + signed long ret; sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction); + if (IS_ERR_OR_NULL(sg_table)) + return sg_table; + + if (!dma_buf_attachment_is_dynamic(attach)) { + ret = dma_resv_wait_timeout(attach->dmabuf->resv, + DMA_RESV_USAGE_KERNEL, true, + MAX_SCHEDULE_TIMEOUT); + if (ret < 0) { + attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, + direction); + return ERR_PTR(ret); + } + } - if (!IS_ERR_OR_NULL(sg_table)) - mangle_sg_table(sg_table); - + mangle_sg_table(sg_table); return sg_table; } @@ -1058,8 +1173,8 @@ EXPORT_SYMBOL_NS_GPL(dma_buf_move_notify, DMA_BUF); * * Interfaces:: * - * void \*dma_buf_vmap(struct dma_buf \*dmabuf) - * void dma_buf_vunmap(struct dma_buf \*dmabuf, void \*vaddr) + * void \*dma_buf_vmap(struct dma_buf \*dmabuf, struct iosys_map \*map) + * void dma_buf_vunmap(struct dma_buf \*dmabuf, struct iosys_map \*map) * * The vmap call can fail if there is no vmap support in the exporter, or if * it runs out of vmalloc space. Note that the dma-buf layer keeps a reference @@ -1135,7 +1250,8 @@ static int __dma_buf_begin_cpu_access(struct dma_buf *dmabuf, long ret; /* Wait on any implicit rendering fences */ - ret = dma_resv_wait_timeout(resv, write, true, MAX_SCHEDULE_TIMEOUT); + ret = dma_resv_wait_timeout(resv, dma_resv_usage_rw(write), + true, MAX_SCHEDULE_TIMEOUT); if (ret < 0) return ret; @@ -1271,12 +1387,12 @@ EXPORT_SYMBOL_NS_GPL(dma_buf_mmap, DMA_BUF); * * Returns 0 on success, or a negative errno code otherwise. */ -int dma_buf_vmap(struct dma_buf *dmabuf, struct dma_buf_map *map) +int dma_buf_vmap(struct dma_buf *dmabuf, struct iosys_map *map) { - struct dma_buf_map ptr; + struct iosys_map ptr; int ret = 0; - dma_buf_map_clear(map); + iosys_map_clear(map); if (WARN_ON(!dmabuf)) return -EINVAL; @@ -1287,12 +1403,12 @@ int dma_buf_vmap(struct dma_buf *dmabuf, struct dma_buf_map *map) mutex_lock(&dmabuf->lock); if (dmabuf->vmapping_counter) { dmabuf->vmapping_counter++; - BUG_ON(dma_buf_map_is_null(&dmabuf->vmap_ptr)); + BUG_ON(iosys_map_is_null(&dmabuf->vmap_ptr)); *map = dmabuf->vmap_ptr; goto out_unlock; } - BUG_ON(dma_buf_map_is_set(&dmabuf->vmap_ptr)); + BUG_ON(iosys_map_is_set(&dmabuf->vmap_ptr)); ret = dmabuf->ops->vmap(dmabuf, &ptr); if (WARN_ON_ONCE(ret)) @@ -1314,20 +1430,20 @@ EXPORT_SYMBOL_NS_GPL(dma_buf_vmap, DMA_BUF); * @dmabuf: [in] buffer to vunmap * @map: [in] vmap pointer to vunmap */ -void dma_buf_vunmap(struct dma_buf *dmabuf, struct dma_buf_map *map) +void dma_buf_vunmap(struct dma_buf *dmabuf, struct iosys_map *map) { if (WARN_ON(!dmabuf)) return; - BUG_ON(dma_buf_map_is_null(&dmabuf->vmap_ptr)); + BUG_ON(iosys_map_is_null(&dmabuf->vmap_ptr)); BUG_ON(dmabuf->vmapping_counter == 0); - BUG_ON(!dma_buf_map_is_equal(&dmabuf->vmap_ptr, map)); + BUG_ON(!iosys_map_is_equal(&dmabuf->vmap_ptr, map)); mutex_lock(&dmabuf->lock); if (--dmabuf->vmapping_counter == 0) { if (dmabuf->ops->vunmap) dmabuf->ops->vunmap(dmabuf, map); - dma_buf_map_clear(&dmabuf->vmap_ptr); + iosys_map_clear(&dmabuf->vmap_ptr); } mutex_unlock(&dmabuf->lock); } @@ -1338,8 +1454,6 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused) { struct dma_buf *buf_obj; struct dma_buf_attachment *attach_obj; - struct dma_resv_iter cursor; - struct dma_fence *fence; int count = 0, attach_count; size_t size = 0; int ret; @@ -1350,7 +1464,7 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused) return ret; seq_puts(s, "\nDma-buf Objects:\n"); - seq_printf(s, "%-8s\t%-8s\t%-8s\t%-8s\texp_name\t%-8s\n", + seq_printf(s, "%-8s\t%-8s\t%-8s\t%-8s\texp_name\t%-8s\tname\n", "size", "flags", "mode", "count", "ino"); list_for_each_entry(buf_obj, &db_list.head, list_node) { @@ -1367,17 +1481,10 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused) file_count(buf_obj->file), buf_obj->exp_name, file_inode(buf_obj->file)->i_ino, - buf_obj->name ?: ""); + buf_obj->name ?: "<none>"); spin_unlock(&buf_obj->name_lock); - dma_resv_for_each_fence(&cursor, buf_obj->resv, true, fence) { - seq_printf(s, "\t%s fence: %s %s %ssignalled\n", - dma_resv_iter_is_exclusive(&cursor) ? - "Exclusive" : "Shared", - fence->ops->get_driver_name(fence), - fence->ops->get_timeline_name(fence), - dma_fence_is_signaled(fence) ? "" : "un"); - } + dma_resv_describe(buf_obj->resv, s); seq_puts(s, "\tAttached Devices:\n"); attach_count = 0; diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c index d3fbd950be94..5c8a7084577b 100644 --- a/drivers/dma-buf/dma-fence-array.c +++ b/drivers/dma-buf/dma-fence-array.c @@ -104,7 +104,11 @@ static bool dma_fence_array_signaled(struct dma_fence *fence) { struct dma_fence_array *array = to_dma_fence_array(fence); - return atomic_read(&array->num_pending) <= 0; + if (atomic_read(&array->num_pending) > 0) + return false; + + dma_fence_array_clear_pending_error(array); + return true; } static void dma_fence_array_release(struct dma_fence *fence) @@ -155,6 +159,8 @@ struct dma_fence_array *dma_fence_array_create(int num_fences, struct dma_fence_array *array; size_t size = sizeof(*array); + WARN_ON(!num_fences || !fences); + /* Allocate the callback structures behind the array. */ size += num_fences * sizeof(struct dma_fence_array_cb); array = kzalloc(size, GFP_KERNEL); @@ -172,6 +178,20 @@ struct dma_fence_array *dma_fence_array_create(int num_fences, array->base.error = PENDING_ERROR; + /* + * dma_fence_array objects should never contain any other fence + * containers or otherwise we run into recursion and potential kernel + * stack overflow on operations on the dma_fence_array. + * + * The correct way of handling this is to flatten out the array by the + * caller instead. + * + * Enforce this here by checking that we don't create a dma_fence_array + * with any container inside. + */ + while (num_fences--) + WARN_ON(dma_fence_is_container(fences[num_fences])); + return array; } EXPORT_SYMBOL(dma_fence_array_create); @@ -201,3 +221,33 @@ bool dma_fence_match_context(struct dma_fence *fence, u64 context) return true; } EXPORT_SYMBOL(dma_fence_match_context); + +struct dma_fence *dma_fence_array_first(struct dma_fence *head) +{ + struct dma_fence_array *array; + + if (!head) + return NULL; + + array = to_dma_fence_array(head); + if (!array) + return head; + + if (!array->num_fences) + return NULL; + + return array->fences[0]; +} +EXPORT_SYMBOL(dma_fence_array_first); + +struct dma_fence *dma_fence_array_next(struct dma_fence *head, + unsigned int index) +{ + struct dma_fence_array *array = to_dma_fence_array(head); + + if (!array || index >= array->num_fences) + return NULL; + + return array->fences[index]; +} +EXPORT_SYMBOL(dma_fence_array_next); diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c index 1b4cb3e5cec9..a0d920576ba6 100644 --- a/drivers/dma-buf/dma-fence-chain.c +++ b/drivers/dma-buf/dma-fence-chain.c @@ -62,8 +62,8 @@ struct dma_fence *dma_fence_chain_walk(struct dma_fence *fence) replacement = NULL; } - tmp = cmpxchg((struct dma_fence __force **)&chain->prev, - prev, replacement); + tmp = unrcu_pointer(cmpxchg(&chain->prev, RCU_INITIALIZER(prev), + RCU_INITIALIZER(replacement))); if (tmp == prev) dma_fence_put(tmp); else @@ -148,8 +148,7 @@ static bool dma_fence_chain_enable_signaling(struct dma_fence *fence) dma_fence_get(&head->base); dma_fence_chain_for_each(fence, &head->base) { - struct dma_fence_chain *chain = to_dma_fence_chain(fence); - struct dma_fence *f = chain ? chain->fence : fence; + struct dma_fence *f = dma_fence_chain_contained(fence); dma_fence_get(f); if (!dma_fence_add_callback(f, &head->cb, dma_fence_chain_cb)) { @@ -165,8 +164,7 @@ static bool dma_fence_chain_enable_signaling(struct dma_fence *fence) static bool dma_fence_chain_signaled(struct dma_fence *fence) { dma_fence_chain_for_each(fence, fence) { - struct dma_fence_chain *chain = to_dma_fence_chain(fence); - struct dma_fence *f = chain ? chain->fence : fence; + struct dma_fence *f = dma_fence_chain_contained(fence); if (!dma_fence_is_signaled(f)) { dma_fence_put(fence); @@ -254,5 +252,14 @@ void dma_fence_chain_init(struct dma_fence_chain *chain, dma_fence_init(&chain->base, &dma_fence_chain_ops, &chain->lock, context, seqno); + + /* + * Chaining dma_fence_chain container together is only allowed through + * the prev fence and not through the contained fence. + * + * The correct way of handling this is to flatten out the fence + * structure into a dma_fence_array by the caller instead. + */ + WARN_ON(dma_fence_is_chain(fence)); } EXPORT_SYMBOL(dma_fence_chain_init); diff --git a/drivers/dma-buf/dma-fence-unwrap.c b/drivers/dma-buf/dma-fence-unwrap.c new file mode 100644 index 000000000000..7002bca792ff --- /dev/null +++ b/drivers/dma-buf/dma-fence-unwrap.c @@ -0,0 +1,163 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * dma-fence-util: misc functions for dma_fence objects + * + * Copyright (C) 2022 Advanced Micro Devices, Inc. + * Authors: + * Christian König <christian.koenig@amd.com> + */ + +#include <linux/dma-fence.h> +#include <linux/dma-fence-array.h> +#include <linux/dma-fence-chain.h> +#include <linux/dma-fence-unwrap.h> +#include <linux/slab.h> + +/* Internal helper to start new array iteration, don't use directly */ +static struct dma_fence * +__dma_fence_unwrap_array(struct dma_fence_unwrap *cursor) +{ + cursor->array = dma_fence_chain_contained(cursor->chain); + cursor->index = 0; + return dma_fence_array_first(cursor->array); +} + +/** + * dma_fence_unwrap_first - return the first fence from fence containers + * @head: the entrypoint into the containers + * @cursor: current position inside the containers + * + * Unwraps potential dma_fence_chain/dma_fence_array containers and return the + * first fence. + */ +struct dma_fence *dma_fence_unwrap_first(struct dma_fence *head, + struct dma_fence_unwrap *cursor) +{ + cursor->chain = dma_fence_get(head); + return __dma_fence_unwrap_array(cursor); +} +EXPORT_SYMBOL_GPL(dma_fence_unwrap_first); + +/** + * dma_fence_unwrap_next - return the next fence from a fence containers + * @cursor: current position inside the containers + * + * Continue unwrapping the dma_fence_chain/dma_fence_array containers and return + * the next fence from them. + */ +struct dma_fence *dma_fence_unwrap_next(struct dma_fence_unwrap *cursor) +{ + struct dma_fence *tmp; + + ++cursor->index; + tmp = dma_fence_array_next(cursor->array, cursor->index); + if (tmp) + return tmp; + + cursor->chain = dma_fence_chain_walk(cursor->chain); + return __dma_fence_unwrap_array(cursor); +} +EXPORT_SYMBOL_GPL(dma_fence_unwrap_next); + +/* Implementation for the dma_fence_merge() marco, don't use directly */ +struct dma_fence *__dma_fence_unwrap_merge(unsigned int num_fences, + struct dma_fence **fences, + struct dma_fence_unwrap *iter) +{ + struct dma_fence_array *result; + struct dma_fence *tmp, **array; + unsigned int i; + size_t count; + + count = 0; + for (i = 0; i < num_fences; ++i) { + dma_fence_unwrap_for_each(tmp, &iter[i], fences[i]) + if (!dma_fence_is_signaled(tmp)) + ++count; + } + + if (count == 0) + return dma_fence_get_stub(); + + array = kmalloc_array(count, sizeof(*array), GFP_KERNEL); + if (!array) + return NULL; + + /* + * This trashes the input fence array and uses it as position for the + * following merge loop. This works because the dma_fence_merge() + * wrapper macro is creating this temporary array on the stack together + * with the iterators. + */ + for (i = 0; i < num_fences; ++i) + fences[i] = dma_fence_unwrap_first(fences[i], &iter[i]); + + count = 0; + do { + unsigned int sel; + +restart: + tmp = NULL; + for (i = 0; i < num_fences; ++i) { + struct dma_fence *next; + + while (fences[i] && dma_fence_is_signaled(fences[i])) + fences[i] = dma_fence_unwrap_next(&iter[i]); + + next = fences[i]; + if (!next) + continue; + + /* + * We can't guarantee that inpute fences are ordered by + * context, but it is still quite likely when this + * function is used multiple times. So attempt to order + * the fences by context as we pass over them and merge + * fences with the same context. + */ + if (!tmp || tmp->context > next->context) { + tmp = next; + sel = i; + + } else if (tmp->context < next->context) { + continue; + + } else if (dma_fence_is_later(tmp, next)) { + fences[i] = dma_fence_unwrap_next(&iter[i]); + goto restart; + } else { + fences[sel] = dma_fence_unwrap_next(&iter[sel]); + goto restart; + } + } + + if (tmp) { + array[count++] = dma_fence_get(tmp); + fences[sel] = dma_fence_unwrap_next(&iter[sel]); + } + } while (tmp); + + if (count == 0) { + tmp = dma_fence_get_stub(); + goto return_tmp; + } + + if (count == 1) { + tmp = array[0]; + goto return_tmp; + } + + result = dma_fence_array_create(count, array, + dma_fence_context_alloc(1), + 1, false); + if (!result) { + tmp = NULL; + goto return_tmp; + } + return &result->base; + +return_tmp: + kfree(array); + return tmp; +} +EXPORT_SYMBOL_GPL(__dma_fence_unwrap_merge); diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 1e82ecd443fa..406b4e26f538 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -15,6 +15,7 @@ #include <linux/atomic.h> #include <linux/dma-fence.h> #include <linux/sched/signal.h> +#include <linux/seq_file.h> #define CREATE_TRACE_POINTS #include <trace/events/dma_fence.h> @@ -135,6 +136,10 @@ struct dma_fence *dma_fence_get_stub(void) &dma_fence_stub_ops, &dma_fence_stub_lock, 0, 0); + + set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, + &dma_fence_stub.flags); + dma_fence_signal_locked(&dma_fence_stub); } spin_unlock(&dma_fence_stub_lock); @@ -160,6 +165,10 @@ struct dma_fence *dma_fence_allocate_private_stub(void) &dma_fence_stub_ops, &dma_fence_stub_lock, 0, 0); + + set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, + &dma_fence_stub.flags); + dma_fence_signal(fence); return fence; @@ -499,6 +508,8 @@ dma_fence_wait_timeout(struct dma_fence *fence, bool intr, signed long timeout) __dma_fence_might_wait(); + dma_fence_enable_sw_signaling(fence); + trace_dma_fence_wait_start(fence); if (fence->ops->wait) ret = fence->ops->wait(fence, intr, timeout); @@ -600,9 +611,6 @@ void dma_fence_enable_sw_signaling(struct dma_fence *fence) { unsigned long flags; - if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) - return; - spin_lock_irqsave(fence->lock, flags); __dma_fence_enable_signaling(fence); spin_unlock_irqrestore(fence->lock, flags); @@ -755,19 +763,16 @@ dma_fence_default_wait(struct dma_fence *fence, bool intr, signed long timeout) unsigned long flags; signed long ret = timeout ? timeout : 1; - if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) - return ret; - spin_lock_irqsave(fence->lock, flags); + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + goto out; + if (intr && signal_pending(current)) { ret = -ERESTARTSYS; goto out; } - if (!__dma_fence_enable_signaling(fence)) - goto out; - if (!timeout) { ret = 0; goto out; @@ -908,6 +913,22 @@ err_free_cb: EXPORT_SYMBOL(dma_fence_wait_any_timeout); /** + * dma_fence_describe - Dump fence describtion into seq_file + * @fence: the 6fence to describe + * @seq: the seq_file to put the textual description into + * + * Dump a textual description of the fence and it's state into the seq_file. + */ +void dma_fence_describe(struct dma_fence *fence, struct seq_file *seq) +{ + seq_printf(seq, "%s %s seq %llu %ssignalled\n", + fence->ops->get_driver_name(fence), + fence->ops->get_timeline_name(fence), fence->seqno, + dma_fence_is_signaled(fence) ? "" : "un"); +} +EXPORT_SYMBOL(dma_fence_describe); + +/** * dma_fence_init - Initialize a custom fence. * @fence: the fence to initialize * @ops: the dma_fence_ops for operations on this fence diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c index 56bf5ad01ad5..8f5848aa144f 100644 --- a/drivers/dma-buf/dma-heap.c +++ b/drivers/dma-buf/dma-heap.c @@ -14,6 +14,7 @@ #include <linux/xarray.h> #include <linux/list.h> #include <linux/slab.h> +#include <linux/nospec.h> #include <linux/uaccess.h> #include <linux/syscalls.h> #include <linux/dma-heap.h> @@ -135,6 +136,7 @@ static long dma_heap_ioctl(struct file *file, unsigned int ucmd, if (nr >= ARRAY_SIZE(dma_heap_ioctl_cmds)) return -EINVAL; + nr = array_index_nospec(nr, ARRAY_SIZE(dma_heap_ioctl_cmds)); /* Get the kernel ioctl cmd that matches */ kcmd = dma_heap_ioctl_cmds[nr]; diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index 9eb2baa387d4..e3885c90a3ac 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -34,20 +34,22 @@ */ #include <linux/dma-resv.h> +#include <linux/dma-fence-array.h> #include <linux/export.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/mmu_notifier.h> +#include <linux/seq_file.h> /** * DOC: Reservation Object Overview * - * The reservation object provides a mechanism to manage shared and - * exclusive fences associated with a buffer. A reservation object - * can have attached one exclusive fence (normally associated with - * write operations) or N shared fences (read operations). The RCU - * mechanism is used to protect read access to fences from locked - * write-side updates. + * The reservation object provides a mechanism to manage a container of + * dma_fence object associated with a resource. A reservation object + * can have any number of fences attaches to it. Each fence carries an usage + * parameter determining how the operation represented by the fence is using the + * resource. The RCU mechanism is used to protect read access to fences from + * locked write-side updates. * * See struct dma_resv for more details. */ @@ -55,33 +57,59 @@ DEFINE_WD_CLASS(reservation_ww_class); EXPORT_SYMBOL(reservation_ww_class); -/** - * dma_resv_list_alloc - allocate fence list - * @shared_max: number of fences we need space for - * +/* Mask for the lower fence pointer bits */ +#define DMA_RESV_LIST_MASK 0x3 + +struct dma_resv_list { + struct rcu_head rcu; + u32 num_fences, max_fences; + struct dma_fence __rcu *table[]; +}; + +/* Extract the fence and usage flags from an RCU protected entry in the list. */ +static void dma_resv_list_entry(struct dma_resv_list *list, unsigned int index, + struct dma_resv *resv, struct dma_fence **fence, + enum dma_resv_usage *usage) +{ + long tmp; + + tmp = (long)rcu_dereference_check(list->table[index], + resv ? dma_resv_held(resv) : true); + *fence = (struct dma_fence *)(tmp & ~DMA_RESV_LIST_MASK); + if (usage) + *usage = tmp & DMA_RESV_LIST_MASK; +} + +/* Set the fence and usage flags at the specific index in the list. */ +static void dma_resv_list_set(struct dma_resv_list *list, + unsigned int index, + struct dma_fence *fence, + enum dma_resv_usage usage) +{ + long tmp = ((long)fence) | usage; + + RCU_INIT_POINTER(list->table[index], (struct dma_fence *)tmp); +} + +/* * Allocate a new dma_resv_list and make sure to correctly initialize - * shared_max. + * max_fences. */ -static struct dma_resv_list *dma_resv_list_alloc(unsigned int shared_max) +static struct dma_resv_list *dma_resv_list_alloc(unsigned int max_fences) { struct dma_resv_list *list; - list = kmalloc(struct_size(list, shared, shared_max), GFP_KERNEL); + list = kmalloc(struct_size(list, table, max_fences), GFP_KERNEL); if (!list) return NULL; - list->shared_max = (ksize(list) - offsetof(typeof(*list), shared)) / - sizeof(*list->shared); + list->max_fences = (ksize(list) - offsetof(typeof(*list), table)) / + sizeof(*list->table); return list; } -/** - * dma_resv_list_free - free fence list - * @list: list to free - * - * Free a dma_resv_list and make sure to drop all references. - */ +/* Free a dma_resv_list and make sure to drop all references. */ static void dma_resv_list_free(struct dma_resv_list *list) { unsigned int i; @@ -89,9 +117,12 @@ static void dma_resv_list_free(struct dma_resv_list *list) if (!list) return; - for (i = 0; i < list->shared_count; ++i) - dma_fence_put(rcu_dereference_protected(list->shared[i], true)); + for (i = 0; i < list->num_fences; ++i) { + struct dma_fence *fence; + dma_resv_list_entry(list, i, NULL, &fence, NULL); + dma_fence_put(fence); + } kfree_rcu(list, rcu); } @@ -102,10 +133,8 @@ static void dma_resv_list_free(struct dma_resv_list *list) void dma_resv_init(struct dma_resv *obj) { ww_mutex_init(&obj->lock, &reservation_ww_class); - seqcount_ww_mutex_init(&obj->seq, &obj->lock); - RCU_INIT_POINTER(obj->fence, NULL); - RCU_INIT_POINTER(obj->fence_excl, NULL); + RCU_INIT_POINTER(obj->fences, NULL); } EXPORT_SYMBOL(dma_resv_init); @@ -115,51 +144,48 @@ EXPORT_SYMBOL(dma_resv_init); */ void dma_resv_fini(struct dma_resv *obj) { - struct dma_resv_list *fobj; - struct dma_fence *excl; - /* * This object should be dead and all references must have * been released to it, so no need to be protected with rcu. */ - excl = rcu_dereference_protected(obj->fence_excl, 1); - if (excl) - dma_fence_put(excl); - - fobj = rcu_dereference_protected(obj->fence, 1); - dma_resv_list_free(fobj); + dma_resv_list_free(rcu_dereference_protected(obj->fences, true)); ww_mutex_destroy(&obj->lock); } EXPORT_SYMBOL(dma_resv_fini); +/* Dereference the fences while ensuring RCU rules */ +static inline struct dma_resv_list *dma_resv_fences_list(struct dma_resv *obj) +{ + return rcu_dereference_check(obj->fences, dma_resv_held(obj)); +} + /** - * dma_resv_reserve_shared - Reserve space to add shared fences to - * a dma_resv. + * dma_resv_reserve_fences - Reserve space to add fences to a dma_resv object. * @obj: reservation object * @num_fences: number of fences we want to add * - * Should be called before dma_resv_add_shared_fence(). Must - * be called with @obj locked through dma_resv_lock(). + * Should be called before dma_resv_add_fence(). Must be called with @obj + * locked through dma_resv_lock(). * * Note that the preallocated slots need to be re-reserved if @obj is unlocked - * at any time before calling dma_resv_add_shared_fence(). This is validated - * when CONFIG_DEBUG_MUTEXES is enabled. + * at any time before calling dma_resv_add_fence(). This is validated when + * CONFIG_DEBUG_MUTEXES is enabled. * * RETURNS * Zero for success, or -errno */ -int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences) +int dma_resv_reserve_fences(struct dma_resv *obj, unsigned int num_fences) { struct dma_resv_list *old, *new; unsigned int i, j, k, max; dma_resv_assert_held(obj); - old = dma_resv_shared_list(obj); - if (old && old->shared_max) { - if ((old->shared_count + num_fences) <= old->shared_max) + old = dma_resv_fences_list(obj); + if (old && old->max_fences) { + if ((old->num_fences + num_fences) <= old->max_fences) return 0; - max = max(old->shared_count + num_fences, old->shared_max * 2); + max = max(old->num_fences + num_fences, old->max_fences * 2); } else { max = max(4ul, roundup_pow_of_two(num_fences)); } @@ -174,27 +200,27 @@ int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences) * references from the old struct are carried over to * the new. */ - for (i = 0, j = 0, k = max; i < (old ? old->shared_count : 0); ++i) { + for (i = 0, j = 0, k = max; i < (old ? old->num_fences : 0); ++i) { + enum dma_resv_usage usage; struct dma_fence *fence; - fence = rcu_dereference_protected(old->shared[i], - dma_resv_held(obj)); + dma_resv_list_entry(old, i, obj, &fence, &usage); if (dma_fence_is_signaled(fence)) - RCU_INIT_POINTER(new->shared[--k], fence); + RCU_INIT_POINTER(new->table[--k], fence); else - RCU_INIT_POINTER(new->shared[j++], fence); + dma_resv_list_set(new, j++, fence, usage); } - new->shared_count = j; + new->num_fences = j; /* * We are not changing the effective set of fences here so can * merely update the pointer to the new array; both existing * readers and new readers will see exactly the same set of - * active (unsignaled) shared fences. Individual fences and the + * active (unsignaled) fences. Individual fences and the * old array are protected by RCU and so will not vanish under * the gaze of the rcu_read_lock() readers. */ - rcu_assign_pointer(obj->fence, new); + rcu_assign_pointer(obj->fences, new); if (!old) return 0; @@ -203,7 +229,7 @@ int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences) for (i = k; i < max; ++i) { struct dma_fence *fence; - fence = rcu_dereference_protected(new->shared[i], + fence = rcu_dereference_protected(new->table[i], dma_resv_held(obj)); dma_fence_put(fence); } @@ -211,41 +237,43 @@ int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences) return 0; } -EXPORT_SYMBOL(dma_resv_reserve_shared); +EXPORT_SYMBOL(dma_resv_reserve_fences); #ifdef CONFIG_DEBUG_MUTEXES /** - * dma_resv_reset_shared_max - reset shared fences for debugging + * dma_resv_reset_max_fences - reset fences for debugging * @obj: the dma_resv object to reset * - * Reset the number of pre-reserved shared slots to test that drivers do - * correct slot allocation using dma_resv_reserve_shared(). See also - * &dma_resv_list.shared_max. + * Reset the number of pre-reserved fence slots to test that drivers do + * correct slot allocation using dma_resv_reserve_fences(). See also + * &dma_resv_list.max_fences. */ -void dma_resv_reset_shared_max(struct dma_resv *obj) +void dma_resv_reset_max_fences(struct dma_resv *obj) { - struct dma_resv_list *fences = dma_resv_shared_list(obj); + struct dma_resv_list *fences = dma_resv_fences_list(obj); dma_resv_assert_held(obj); - /* Test shared fence slot reservation */ + /* Test fence slot reservation */ if (fences) - fences->shared_max = fences->shared_count; + fences->max_fences = fences->num_fences; } -EXPORT_SYMBOL(dma_resv_reset_shared_max); +EXPORT_SYMBOL(dma_resv_reset_max_fences); #endif /** - * dma_resv_add_shared_fence - Add a fence to a shared slot + * dma_resv_add_fence - Add a fence to the dma_resv obj * @obj: the reservation object - * @fence: the shared fence to add + * @fence: the fence to add + * @usage: how the fence is used, see enum dma_resv_usage * - * Add a fence to a shared slot, @obj must be locked with dma_resv_lock(), and - * dma_resv_reserve_shared() has been called. + * Add a fence to a slot, @obj must be locked with dma_resv_lock(), and + * dma_resv_reserve_fences() has been called. * * See also &dma_resv.fence for a discussion of the semantics. */ -void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence) +void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence, + enum dma_resv_usage usage) { struct dma_resv_list *fobj; struct dma_fence *old; @@ -255,130 +283,111 @@ void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence) dma_resv_assert_held(obj); - fobj = dma_resv_shared_list(obj); - count = fobj->shared_count; + /* Drivers should not add containers here, instead add each fence + * individually. + */ + WARN_ON(dma_fence_is_container(fence)); - write_seqcount_begin(&obj->seq); + fobj = dma_resv_fences_list(obj); + count = fobj->num_fences; for (i = 0; i < count; ++i) { - - old = rcu_dereference_protected(fobj->shared[i], - dma_resv_held(obj)); - if (old->context == fence->context || - dma_fence_is_signaled(old)) - goto replace; + enum dma_resv_usage old_usage; + + dma_resv_list_entry(fobj, i, obj, &old, &old_usage); + if ((old->context == fence->context && old_usage >= usage && + dma_fence_is_later(fence, old)) || + dma_fence_is_signaled(old)) { + dma_resv_list_set(fobj, i, fence, usage); + dma_fence_put(old); + return; + } } - BUG_ON(fobj->shared_count >= fobj->shared_max); - old = NULL; + BUG_ON(fobj->num_fences >= fobj->max_fences); count++; -replace: - RCU_INIT_POINTER(fobj->shared[i], fence); - /* pointer update must be visible before we extend the shared_count */ - smp_store_mb(fobj->shared_count, count); - - write_seqcount_end(&obj->seq); - dma_fence_put(old); + dma_resv_list_set(fobj, i, fence, usage); + /* pointer update must be visible before we extend the num_fences */ + smp_store_mb(fobj->num_fences, count); } -EXPORT_SYMBOL(dma_resv_add_shared_fence); +EXPORT_SYMBOL(dma_resv_add_fence); /** - * dma_resv_add_excl_fence - Add an exclusive fence. + * dma_resv_replace_fences - replace fences in the dma_resv obj * @obj: the reservation object - * @fence: the exclusive fence to add + * @context: the context of the fences to replace + * @replacement: the new fence to use instead + * @usage: how the new fence is used, see enum dma_resv_usage + * + * Replace fences with a specified context with a new fence. Only valid if the + * operation represented by the original fence has no longer access to the + * resources represented by the dma_resv object when the new fence completes. * - * Add a fence to the exclusive slot. @obj must be locked with dma_resv_lock(). - * Note that this function replaces all fences attached to @obj, see also - * &dma_resv.fence_excl for a discussion of the semantics. + * And example for using this is replacing a preemption fence with a page table + * update fence which makes the resource inaccessible. */ -void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence) +void dma_resv_replace_fences(struct dma_resv *obj, uint64_t context, + struct dma_fence *replacement, + enum dma_resv_usage usage) { - struct dma_fence *old_fence = dma_resv_excl_fence(obj); - struct dma_resv_list *old; - u32 i = 0; + struct dma_resv_list *list; + unsigned int i; dma_resv_assert_held(obj); - old = dma_resv_shared_list(obj); - if (old) - i = old->shared_count; - - if (fence) - dma_fence_get(fence); + list = dma_resv_fences_list(obj); + for (i = 0; list && i < list->num_fences; ++i) { + struct dma_fence *old; - write_seqcount_begin(&obj->seq); - /* write_seqcount_begin provides the necessary memory barrier */ - RCU_INIT_POINTER(obj->fence_excl, fence); - if (old) - old->shared_count = 0; - write_seqcount_end(&obj->seq); + dma_resv_list_entry(list, i, obj, &old, NULL); + if (old->context != context) + continue; - /* inplace update, no shared fences */ - while (i--) - dma_fence_put(rcu_dereference_protected(old->shared[i], - dma_resv_held(obj))); - - dma_fence_put(old_fence); + dma_resv_list_set(list, i, dma_fence_get(replacement), usage); + dma_fence_put(old); + } } -EXPORT_SYMBOL(dma_resv_add_excl_fence); +EXPORT_SYMBOL(dma_resv_replace_fences); -/** - * dma_resv_iter_restart_unlocked - restart the unlocked iterator - * @cursor: The dma_resv_iter object to restart - * - * Restart the unlocked iteration by initializing the cursor object. - */ +/* Restart the unlocked iteration by initializing the cursor object. */ static void dma_resv_iter_restart_unlocked(struct dma_resv_iter *cursor) { - cursor->seq = read_seqcount_begin(&cursor->obj->seq); - cursor->index = -1; - cursor->shared_count = 0; - if (cursor->all_fences) { - cursor->fences = dma_resv_shared_list(cursor->obj); - if (cursor->fences) - cursor->shared_count = cursor->fences->shared_count; - } else { - cursor->fences = NULL; - } + cursor->index = 0; + cursor->num_fences = 0; + cursor->fences = dma_resv_fences_list(cursor->obj); + if (cursor->fences) + cursor->num_fences = cursor->fences->num_fences; cursor->is_restarted = true; } -/** - * dma_resv_iter_walk_unlocked - walk over fences in a dma_resv obj - * @cursor: cursor to record the current position - * - * Return all the fences in the dma_resv object which are not yet signaled. - * The returned fence has an extra local reference so will stay alive. - * If a concurrent modify is detected the whole iteration is started over again. - */ +/* Walk to the next not signaled fence and grab a reference to it */ static void dma_resv_iter_walk_unlocked(struct dma_resv_iter *cursor) { - struct dma_resv *obj = cursor->obj; + if (!cursor->fences) + return; do { /* Drop the reference from the previous round */ dma_fence_put(cursor->fence); - if (cursor->index == -1) { - cursor->fence = dma_resv_excl_fence(obj); - cursor->index++; - if (!cursor->fence) - continue; - - } else if (!cursor->fences || - cursor->index >= cursor->shared_count) { + if (cursor->index >= cursor->num_fences) { cursor->fence = NULL; break; - } else { - struct dma_resv_list *fences = cursor->fences; - unsigned int idx = cursor->index++; - - cursor->fence = rcu_dereference(fences->shared[idx]); } + + dma_resv_list_entry(cursor->fences, cursor->index++, + cursor->obj, &cursor->fence, + &cursor->fence_usage); cursor->fence = dma_fence_get_rcu(cursor->fence); - if (!cursor->fence || !dma_fence_is_signaled(cursor->fence)) + if (!cursor->fence) { + dma_resv_iter_restart_unlocked(cursor); + continue; + } + + if (!dma_fence_is_signaled(cursor->fence) && + cursor->usage >= cursor->fence_usage) break; } while (true); } @@ -387,6 +396,12 @@ static void dma_resv_iter_walk_unlocked(struct dma_resv_iter *cursor) * dma_resv_iter_first_unlocked - first fence in an unlocked dma_resv obj. * @cursor: the cursor with the current position * + * Subsequent fences are iterated with dma_resv_iter_next_unlocked(). + * + * Beware that the iterator can be restarted. Code which accumulates statistics + * or similar needs to check for this with dma_resv_iter_is_restarted(). For + * this reason prefer the locked dma_resv_iter_first() whenver possible. + * * Returns the first fence from an unlocked dma_resv obj. */ struct dma_fence *dma_resv_iter_first_unlocked(struct dma_resv_iter *cursor) @@ -395,7 +410,7 @@ struct dma_fence *dma_resv_iter_first_unlocked(struct dma_resv_iter *cursor) do { dma_resv_iter_restart_unlocked(cursor); dma_resv_iter_walk_unlocked(cursor); - } while (read_seqcount_retry(&cursor->obj->seq, cursor->seq)); + } while (dma_resv_fences_list(cursor->obj) != cursor->fences); rcu_read_unlock(); return cursor->fence; @@ -406,6 +421,10 @@ EXPORT_SYMBOL(dma_resv_iter_first_unlocked); * dma_resv_iter_next_unlocked - next fence in an unlocked dma_resv obj. * @cursor: the cursor with the current position * + * Beware that the iterator can be restarted. Code which accumulates statistics + * or similar needs to check for this with dma_resv_iter_is_restarted(). For + * this reason prefer the locked dma_resv_iter_next() whenver possible. + * * Returns the next fence from an unlocked dma_resv obj. */ struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor) @@ -414,13 +433,13 @@ struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor) rcu_read_lock(); cursor->is_restarted = false; - restart = read_seqcount_retry(&cursor->obj->seq, cursor->seq); + restart = dma_resv_fences_list(cursor->obj) != cursor->fences; do { if (restart) dma_resv_iter_restart_unlocked(cursor); dma_resv_iter_walk_unlocked(cursor); restart = true; - } while (read_seqcount_retry(&cursor->obj->seq, cursor->seq)); + } while (dma_resv_fences_list(cursor->obj) != cursor->fences); rcu_read_unlock(); return cursor->fence; @@ -431,6 +450,8 @@ EXPORT_SYMBOL(dma_resv_iter_next_unlocked); * dma_resv_iter_first - first fence from a locked dma_resv object * @cursor: cursor to record the current position * + * Subsequent fences are iterated with dma_resv_iter_next_unlocked(). + * * Return the first fence in the dma_resv object while holding the * &dma_resv.lock. */ @@ -441,15 +462,9 @@ struct dma_fence *dma_resv_iter_first(struct dma_resv_iter *cursor) dma_resv_assert_held(cursor->obj); cursor->index = 0; - if (cursor->all_fences) - cursor->fences = dma_resv_shared_list(cursor->obj); - else - cursor->fences = NULL; - - fence = dma_resv_excl_fence(cursor->obj); - if (!fence) - fence = dma_resv_iter_next(cursor); + cursor->fences = dma_resv_fences_list(cursor->obj); + fence = dma_resv_iter_next(cursor); cursor->is_restarted = true; return fence; } @@ -464,17 +479,22 @@ EXPORT_SYMBOL_GPL(dma_resv_iter_first); */ struct dma_fence *dma_resv_iter_next(struct dma_resv_iter *cursor) { - unsigned int idx; + struct dma_fence *fence; dma_resv_assert_held(cursor->obj); cursor->is_restarted = false; - if (!cursor->fences || cursor->index >= cursor->fences->shared_count) - return NULL; - idx = cursor->index++; - return rcu_dereference_protected(cursor->fences->shared[idx], - dma_resv_held(cursor->obj)); + do { + if (!cursor->fences || + cursor->index >= cursor->fences->num_fences) + return NULL; + + dma_resv_list_entry(cursor->fences, cursor->index++, + cursor->obj, &fence, &cursor->fence_usage); + } while (cursor->fence_usage > cursor->usage); + + return fence; } EXPORT_SYMBOL_GPL(dma_resv_iter_next); @@ -489,110 +509,81 @@ int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src) { struct dma_resv_iter cursor; struct dma_resv_list *list; - struct dma_fence *f, *excl; + struct dma_fence *f; dma_resv_assert_held(dst); list = NULL; - excl = NULL; - dma_resv_iter_begin(&cursor, src, true); + dma_resv_iter_begin(&cursor, src, DMA_RESV_USAGE_BOOKKEEP); dma_resv_for_each_fence_unlocked(&cursor, f) { if (dma_resv_iter_is_restarted(&cursor)) { dma_resv_list_free(list); - dma_fence_put(excl); - - if (cursor.shared_count) { - list = dma_resv_list_alloc(cursor.shared_count); - if (!list) { - dma_resv_iter_end(&cursor); - return -ENOMEM; - } - list->shared_count = 0; - - } else { - list = NULL; + list = dma_resv_list_alloc(cursor.num_fences); + if (!list) { + dma_resv_iter_end(&cursor); + return -ENOMEM; } - excl = NULL; + list->num_fences = 0; } dma_fence_get(f); - if (dma_resv_iter_is_exclusive(&cursor)) - excl = f; - else - RCU_INIT_POINTER(list->shared[list->shared_count++], f); + dma_resv_list_set(list, list->num_fences++, f, + dma_resv_iter_usage(&cursor)); } dma_resv_iter_end(&cursor); - write_seqcount_begin(&dst->seq); - excl = rcu_replace_pointer(dst->fence_excl, excl, dma_resv_held(dst)); - list = rcu_replace_pointer(dst->fence, list, dma_resv_held(dst)); - write_seqcount_end(&dst->seq); - + list = rcu_replace_pointer(dst->fences, list, dma_resv_held(dst)); dma_resv_list_free(list); - dma_fence_put(excl); - return 0; } EXPORT_SYMBOL(dma_resv_copy_fences); /** - * dma_resv_get_fences - Get an object's shared and exclusive + * dma_resv_get_fences - Get an object's fences * fences without update side lock held * @obj: the reservation object - * @fence_excl: the returned exclusive fence (or NULL) - * @shared_count: the number of shared fences returned - * @shared: the array of shared fence ptrs returned (array is krealloc'd to - * the required size, and must be freed by caller) - * - * Retrieve all fences from the reservation object. If the pointer for the - * exclusive fence is not specified the fence is put into the array of the - * shared fences as well. Returns either zero or -ENOMEM. + * @usage: controls which fences to include, see enum dma_resv_usage. + * @num_fences: the number of fences returned + * @fences: the array of fence ptrs returned (array is krealloc'd to the + * required size, and must be freed by caller) + * + * Retrieve all fences from the reservation object. + * Returns either zero or -ENOMEM. */ -int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **fence_excl, - unsigned int *shared_count, struct dma_fence ***shared) +int dma_resv_get_fences(struct dma_resv *obj, enum dma_resv_usage usage, + unsigned int *num_fences, struct dma_fence ***fences) { struct dma_resv_iter cursor; struct dma_fence *fence; - *shared_count = 0; - *shared = NULL; + *num_fences = 0; + *fences = NULL; - if (fence_excl) - *fence_excl = NULL; - - dma_resv_iter_begin(&cursor, obj, true); + dma_resv_iter_begin(&cursor, obj, usage); dma_resv_for_each_fence_unlocked(&cursor, fence) { if (dma_resv_iter_is_restarted(&cursor)) { unsigned int count; - while (*shared_count) - dma_fence_put((*shared)[--(*shared_count)]); - - if (fence_excl) - dma_fence_put(*fence_excl); + while (*num_fences) + dma_fence_put((*fences)[--(*num_fences)]); - count = cursor.shared_count; - count += fence_excl ? 0 : 1; + count = cursor.num_fences + 1; /* Eventually re-allocate the array */ - *shared = krealloc_array(*shared, count, + *fences = krealloc_array(*fences, count, sizeof(void *), GFP_KERNEL); - if (count && !*shared) { + if (count && !*fences) { dma_resv_iter_end(&cursor); return -ENOMEM; } } - dma_fence_get(fence); - if (dma_resv_iter_is_exclusive(&cursor) && fence_excl) - *fence_excl = fence; - else - (*shared)[(*shared_count)++] = fence; + (*fences)[(*num_fences)++] = dma_fence_get(fence); } dma_resv_iter_end(&cursor); @@ -601,10 +592,62 @@ int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **fence_excl, EXPORT_SYMBOL_GPL(dma_resv_get_fences); /** - * dma_resv_wait_timeout - Wait on reservation's objects - * shared and/or exclusive fences. + * dma_resv_get_singleton - Get a single fence for all the fences * @obj: the reservation object - * @wait_all: if true, wait on all fences, else wait on just exclusive fence + * @usage: controls which fences to include, see enum dma_resv_usage. + * @fence: the resulting fence + * + * Get a single fence representing all the fences inside the resv object. + * Returns either 0 for success or -ENOMEM. + * + * Warning: This can't be used like this when adding the fence back to the resv + * object since that can lead to stack corruption when finalizing the + * dma_fence_array. + * + * Returns 0 on success and negative error values on failure. + */ +int dma_resv_get_singleton(struct dma_resv *obj, enum dma_resv_usage usage, + struct dma_fence **fence) +{ + struct dma_fence_array *array; + struct dma_fence **fences; + unsigned count; + int r; + + r = dma_resv_get_fences(obj, usage, &count, &fences); + if (r) + return r; + + if (count == 0) { + *fence = NULL; + return 0; + } + + if (count == 1) { + *fence = fences[0]; + kfree(fences); + return 0; + } + + array = dma_fence_array_create(count, fences, + dma_fence_context_alloc(1), + 1, false); + if (!array) { + while (count--) + dma_fence_put(fences[count]); + kfree(fences); + return -ENOMEM; + } + + *fence = &array->base; + return 0; +} +EXPORT_SYMBOL_GPL(dma_resv_get_singleton); + +/** + * dma_resv_wait_timeout - Wait on reservation's objects fences + * @obj: the reservation object + * @usage: controls which fences to include, see enum dma_resv_usage. * @intr: if true, do interruptible wait * @timeout: timeout value in jiffies or zero to return immediately * @@ -614,14 +657,14 @@ EXPORT_SYMBOL_GPL(dma_resv_get_fences); * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or * greater than zer on success. */ -long dma_resv_wait_timeout(struct dma_resv *obj, bool wait_all, bool intr, - unsigned long timeout) +long dma_resv_wait_timeout(struct dma_resv *obj, enum dma_resv_usage usage, + bool intr, unsigned long timeout) { long ret = timeout ? timeout : 1; struct dma_resv_iter cursor; struct dma_fence *fence; - dma_resv_iter_begin(&cursor, obj, wait_all); + dma_resv_iter_begin(&cursor, obj, usage); dma_resv_for_each_fence_unlocked(&cursor, fence) { ret = dma_fence_wait_timeout(fence, intr, ret); @@ -641,8 +684,7 @@ EXPORT_SYMBOL_GPL(dma_resv_wait_timeout); * dma_resv_test_signaled - Test if a reservation object's fences have been * signaled. * @obj: the reservation object - * @test_all: if true, test all fences, otherwise only test the exclusive - * fence + * @usage: controls which fences to include, see enum dma_resv_usage. * * Callers are not required to hold specific locks, but maybe hold * dma_resv_lock() already. @@ -651,12 +693,12 @@ EXPORT_SYMBOL_GPL(dma_resv_wait_timeout); * * True if all fences signaled, else false. */ -bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all) +bool dma_resv_test_signaled(struct dma_resv *obj, enum dma_resv_usage usage) { struct dma_resv_iter cursor; struct dma_fence *fence; - dma_resv_iter_begin(&cursor, obj, test_all); + dma_resv_iter_begin(&cursor, obj, usage); dma_resv_for_each_fence_unlocked(&cursor, fence) { dma_resv_iter_end(&cursor); return false; @@ -666,6 +708,28 @@ bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all) } EXPORT_SYMBOL_GPL(dma_resv_test_signaled); +/** + * dma_resv_describe - Dump description of the resv object into seq_file + * @obj: the reservation object + * @seq: the seq_file to dump the description into + * + * Dump a textual description of the fences inside an dma_resv object into the + * seq_file. + */ +void dma_resv_describe(struct dma_resv *obj, struct seq_file *seq) +{ + static const char *usage[] = { "kernel", "write", "read", "bookkeep" }; + struct dma_resv_iter cursor; + struct dma_fence *fence; + + dma_resv_for_each_fence(&cursor, obj, DMA_RESV_USAGE_READ, fence) { + seq_printf(seq, "\t%s fence:", + usage[dma_resv_iter_usage(&cursor)]); + dma_fence_describe(fence, seq); + } +} +EXPORT_SYMBOL_GPL(dma_resv_describe); + #if IS_ENABLED(CONFIG_LOCKDEP) static int __init dma_resv_lockdep(void) { diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c index 0c05b79870f9..28fb04eccdd0 100644 --- a/drivers/dma-buf/heaps/cma_heap.c +++ b/drivers/dma-buf/heaps/cma_heap.c @@ -124,10 +124,11 @@ static int cma_heap_dma_buf_begin_cpu_access(struct dma_buf *dmabuf, struct cma_heap_buffer *buffer = dmabuf->priv; struct dma_heap_attachment *a; + mutex_lock(&buffer->lock); + if (buffer->vmap_cnt) invalidate_kernel_vmap_range(buffer->vaddr, buffer->len); - mutex_lock(&buffer->lock); list_for_each_entry(a, &buffer->attachments, list) { if (!a->mapped) continue; @@ -144,10 +145,11 @@ static int cma_heap_dma_buf_end_cpu_access(struct dma_buf *dmabuf, struct cma_heap_buffer *buffer = dmabuf->priv; struct dma_heap_attachment *a; + mutex_lock(&buffer->lock); + if (buffer->vmap_cnt) flush_kernel_vmap_range(buffer->vaddr, buffer->len); - mutex_lock(&buffer->lock); list_for_each_entry(a, &buffer->attachments, list) { if (!a->mapped) continue; @@ -200,7 +202,7 @@ static void *cma_heap_do_vmap(struct cma_heap_buffer *buffer) return vaddr; } -static int cma_heap_vmap(struct dma_buf *dmabuf, struct dma_buf_map *map) +static int cma_heap_vmap(struct dma_buf *dmabuf, struct iosys_map *map) { struct cma_heap_buffer *buffer = dmabuf->priv; void *vaddr; @@ -209,7 +211,7 @@ static int cma_heap_vmap(struct dma_buf *dmabuf, struct dma_buf_map *map) mutex_lock(&buffer->lock); if (buffer->vmap_cnt) { buffer->vmap_cnt++; - dma_buf_map_set_vaddr(map, buffer->vaddr); + iosys_map_set_vaddr(map, buffer->vaddr); goto out; } @@ -220,14 +222,14 @@ static int cma_heap_vmap(struct dma_buf *dmabuf, struct dma_buf_map *map) } buffer->vaddr = vaddr; buffer->vmap_cnt++; - dma_buf_map_set_vaddr(map, buffer->vaddr); + iosys_map_set_vaddr(map, buffer->vaddr); out: mutex_unlock(&buffer->lock); return ret; } -static void cma_heap_vunmap(struct dma_buf *dmabuf, struct dma_buf_map *map) +static void cma_heap_vunmap(struct dma_buf *dmabuf, struct iosys_map *map) { struct cma_heap_buffer *buffer = dmabuf->priv; @@ -237,7 +239,7 @@ static void cma_heap_vunmap(struct dma_buf *dmabuf, struct dma_buf_map *map) buffer->vaddr = NULL; } mutex_unlock(&buffer->lock); - dma_buf_map_clear(map); + iosys_map_clear(map); } static void cma_heap_dma_buf_release(struct dma_buf *dmabuf) diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c index ab7fd896d2c4..fcf836ba9c1f 100644 --- a/drivers/dma-buf/heaps/system_heap.c +++ b/drivers/dma-buf/heaps/system_heap.c @@ -241,7 +241,7 @@ static void *system_heap_do_vmap(struct system_heap_buffer *buffer) return vaddr; } -static int system_heap_vmap(struct dma_buf *dmabuf, struct dma_buf_map *map) +static int system_heap_vmap(struct dma_buf *dmabuf, struct iosys_map *map) { struct system_heap_buffer *buffer = dmabuf->priv; void *vaddr; @@ -250,7 +250,7 @@ static int system_heap_vmap(struct dma_buf *dmabuf, struct dma_buf_map *map) mutex_lock(&buffer->lock); if (buffer->vmap_cnt) { buffer->vmap_cnt++; - dma_buf_map_set_vaddr(map, buffer->vaddr); + iosys_map_set_vaddr(map, buffer->vaddr); goto out; } @@ -262,14 +262,14 @@ static int system_heap_vmap(struct dma_buf *dmabuf, struct dma_buf_map *map) buffer->vaddr = vaddr; buffer->vmap_cnt++; - dma_buf_map_set_vaddr(map, buffer->vaddr); + iosys_map_set_vaddr(map, buffer->vaddr); out: mutex_unlock(&buffer->lock); return ret; } -static void system_heap_vunmap(struct dma_buf *dmabuf, struct dma_buf_map *map) +static void system_heap_vunmap(struct dma_buf *dmabuf, struct iosys_map *map) { struct system_heap_buffer *buffer = dmabuf->priv; @@ -279,7 +279,7 @@ static void system_heap_vunmap(struct dma_buf *dmabuf, struct dma_buf_map *map) buffer->vaddr = NULL; } mutex_unlock(&buffer->lock); - dma_buf_map_clear(map); + iosys_map_clear(map); } static void system_heap_dma_buf_release(struct dma_buf *dmabuf) diff --git a/drivers/dma-buf/selftests.h b/drivers/dma-buf/selftests.h index bc8cea67bf1e..851965867d9c 100644 --- a/drivers/dma-buf/selftests.h +++ b/drivers/dma-buf/selftests.h @@ -12,3 +12,5 @@ selftest(sanitycheck, __sanitycheck__) /* keep first (igt selfcheck) */ selftest(dma_fence, dma_fence) selftest(dma_fence_chain, dma_fence_chain) +selftest(dma_fence_unwrap, dma_fence_unwrap) +selftest(dma_resv, dma_resv) diff --git a/drivers/dma-buf/st-dma-fence-chain.c b/drivers/dma-buf/st-dma-fence-chain.c index 8ce1ea59d31b..0a9b099d0518 100644 --- a/drivers/dma-buf/st-dma-fence-chain.c +++ b/drivers/dma-buf/st-dma-fence-chain.c @@ -87,6 +87,8 @@ static int sanitycheck(void *arg) if (!chain) err = -ENOMEM; + dma_fence_enable_sw_signaling(chain); + dma_fence_signal(f); dma_fence_put(f); @@ -143,6 +145,8 @@ static int fence_chains_init(struct fence_chains *fc, unsigned int count, } fc->tail = fc->chains[i]; + + dma_fence_enable_sw_signaling(fc->chains[i]); } fc->chain_length = i; diff --git a/drivers/dma-buf/st-dma-fence-unwrap.c b/drivers/dma-buf/st-dma-fence-unwrap.c new file mode 100644 index 000000000000..f0cee984b6c7 --- /dev/null +++ b/drivers/dma-buf/st-dma-fence-unwrap.c @@ -0,0 +1,382 @@ +// SPDX-License-Identifier: MIT + +/* + * Copyright (C) 2022 Advanced Micro Devices, Inc. + */ + +#include <linux/dma-fence.h> +#include <linux/dma-fence-array.h> +#include <linux/dma-fence-chain.h> +#include <linux/dma-fence-unwrap.h> + +#include "selftest.h" + +#define CHAIN_SZ (4 << 10) + +struct mock_fence { + struct dma_fence base; + spinlock_t lock; +}; + +static const char *mock_name(struct dma_fence *f) +{ + return "mock"; +} + +static const struct dma_fence_ops mock_ops = { + .get_driver_name = mock_name, + .get_timeline_name = mock_name, +}; + +static struct dma_fence *mock_fence(void) +{ + struct mock_fence *f; + + f = kmalloc(sizeof(*f), GFP_KERNEL); + if (!f) + return NULL; + + spin_lock_init(&f->lock); + dma_fence_init(&f->base, &mock_ops, &f->lock, + dma_fence_context_alloc(1), 1); + + return &f->base; +} + +static struct dma_fence *mock_array(unsigned int num_fences, ...) +{ + struct dma_fence_array *array; + struct dma_fence **fences; + va_list valist; + int i; + + fences = kcalloc(num_fences, sizeof(*fences), GFP_KERNEL); + if (!fences) + goto error_put; + + va_start(valist, num_fences); + for (i = 0; i < num_fences; ++i) + fences[i] = va_arg(valist, typeof(*fences)); + va_end(valist); + + array = dma_fence_array_create(num_fences, fences, + dma_fence_context_alloc(1), + 1, false); + if (!array) + goto error_free; + return &array->base; + +error_free: + kfree(fences); + +error_put: + va_start(valist, num_fences); + for (i = 0; i < num_fences; ++i) + dma_fence_put(va_arg(valist, typeof(*fences))); + va_end(valist); + return NULL; +} + +static struct dma_fence *mock_chain(struct dma_fence *prev, + struct dma_fence *fence) +{ + struct dma_fence_chain *f; + + f = dma_fence_chain_alloc(); + if (!f) { + dma_fence_put(prev); + dma_fence_put(fence); + return NULL; + } + + dma_fence_chain_init(f, prev, fence, 1); + return &f->base; +} + +static int sanitycheck(void *arg) +{ + struct dma_fence *f, *chain, *array; + int err = 0; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f); + + array = mock_array(1, f); + if (!array) + return -ENOMEM; + + chain = mock_chain(NULL, array); + if (!chain) + return -ENOMEM; + + dma_fence_put(chain); + return err; +} + +static int unwrap_array(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *array; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f1); + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + dma_fence_enable_sw_signaling(f2); + + array = mock_array(2, f1, f2); + if (!array) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, array) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_put(array); + return err; +} + +static int unwrap_chain(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *chain; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f1); + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + dma_fence_enable_sw_signaling(f2); + + chain = mock_chain(f1, f2); + if (!chain) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, chain) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_put(chain); + return err; +} + +static int unwrap_chain_array(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *array, *chain; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f1); + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + dma_fence_enable_sw_signaling(f2); + + array = mock_array(2, f1, f2); + if (!array) + return -ENOMEM; + + chain = mock_chain(NULL, array); + if (!chain) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, chain) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_put(chain); + return err; +} + +static int unwrap_merge(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *f3; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f1); + + f2 = mock_fence(); + if (!f2) { + err = -ENOMEM; + goto error_put_f1; + } + + dma_fence_enable_sw_signaling(f2); + + f3 = dma_fence_unwrap_merge(f1, f2); + if (!f3) { + err = -ENOMEM; + goto error_put_f2; + } + + dma_fence_unwrap_for_each(fence, &iter, f3) { + if (fence == f1) { + dma_fence_put(f1); + f1 = NULL; + } else if (fence == f2) { + dma_fence_put(f2); + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_put(f3); +error_put_f2: + dma_fence_put(f2); +error_put_f1: + dma_fence_put(f1); + return err; +} + +static int unwrap_merge_complex(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *f3, *f4, *f5; + struct dma_fence_unwrap iter; + int err = -ENOMEM; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f1); + + f2 = mock_fence(); + if (!f2) + goto error_put_f1; + + dma_fence_enable_sw_signaling(f2); + + f3 = dma_fence_unwrap_merge(f1, f2); + if (!f3) + goto error_put_f2; + + /* The resulting array has the fences in reverse */ + f4 = dma_fence_unwrap_merge(f2, f1); + if (!f4) + goto error_put_f3; + + /* Signaled fences should be filtered, the two arrays merged. */ + f5 = dma_fence_unwrap_merge(f3, f4, dma_fence_get_stub()); + if (!f5) + goto error_put_f4; + + err = 0; + dma_fence_unwrap_for_each(fence, &iter, f5) { + if (fence == f1) { + dma_fence_put(f1); + f1 = NULL; + } else if (fence == f2) { + dma_fence_put(f2); + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_put(f5); +error_put_f4: + dma_fence_put(f4); +error_put_f3: + dma_fence_put(f3); +error_put_f2: + dma_fence_put(f2); +error_put_f1: + dma_fence_put(f1); + return err; +} + +int dma_fence_unwrap(void) +{ + static const struct subtest tests[] = { + SUBTEST(sanitycheck), + SUBTEST(unwrap_array), + SUBTEST(unwrap_chain), + SUBTEST(unwrap_chain_array), + SUBTEST(unwrap_merge), + SUBTEST(unwrap_merge_complex), + }; + + return subtests(tests, NULL); +} diff --git a/drivers/dma-buf/st-dma-fence.c b/drivers/dma-buf/st-dma-fence.c index c8a12d7ad71a..fb6e0a6ae2c9 100644 --- a/drivers/dma-buf/st-dma-fence.c +++ b/drivers/dma-buf/st-dma-fence.c @@ -102,6 +102,8 @@ static int sanitycheck(void *arg) if (!f) return -ENOMEM; + dma_fence_enable_sw_signaling(f); + dma_fence_signal(f); dma_fence_put(f); @@ -117,6 +119,8 @@ static int test_signaling(void *arg) if (!f) return -ENOMEM; + dma_fence_enable_sw_signaling(f); + if (dma_fence_is_signaled(f)) { pr_err("Fence unexpectedly signaled on creation\n"); goto err_free; @@ -190,6 +194,8 @@ static int test_late_add_callback(void *arg) if (!f) return -ENOMEM; + dma_fence_enable_sw_signaling(f); + dma_fence_signal(f); if (!dma_fence_add_callback(f, &cb.cb, simple_callback)) { @@ -282,6 +288,8 @@ static int test_status(void *arg) if (!f) return -ENOMEM; + dma_fence_enable_sw_signaling(f); + if (dma_fence_get_status(f)) { pr_err("Fence unexpectedly has signaled status on creation\n"); goto err_free; @@ -308,6 +316,8 @@ static int test_error(void *arg) if (!f) return -ENOMEM; + dma_fence_enable_sw_signaling(f); + dma_fence_set_error(f, -EIO); if (dma_fence_get_status(f)) { @@ -337,6 +347,8 @@ static int test_wait(void *arg) if (!f) return -ENOMEM; + dma_fence_enable_sw_signaling(f); + if (dma_fence_wait_timeout(f, false, 0) != -ETIME) { pr_err("Wait reported complete before being signaled\n"); goto err_free; @@ -379,6 +391,8 @@ static int test_wait_timeout(void *arg) if (!wt.f) return -ENOMEM; + dma_fence_enable_sw_signaling(wt.f); + if (dma_fence_wait_timeout(wt.f, false, 1) != -ETIME) { pr_err("Wait reported complete before being signaled\n"); goto err_free; @@ -458,6 +472,8 @@ static int thread_signal_callback(void *arg) break; } + dma_fence_enable_sw_signaling(f1); + rcu_assign_pointer(t->fences[t->id], f1); smp_wmb(); diff --git a/drivers/dma-buf/st-dma-resv.c b/drivers/dma-buf/st-dma-resv.c new file mode 100644 index 000000000000..15dbea1462ed --- /dev/null +++ b/drivers/dma-buf/st-dma-resv.c @@ -0,0 +1,316 @@ +/* SPDX-License-Identifier: MIT */ + +/* +* Copyright © 2019 Intel Corporation +* Copyright © 2021 Advanced Micro Devices, Inc. +*/ + +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/dma-resv.h> + +#include "selftest.h" + +static struct spinlock fence_lock; + +static const char *fence_name(struct dma_fence *f) +{ + return "selftest"; +} + +static const struct dma_fence_ops fence_ops = { + .get_driver_name = fence_name, + .get_timeline_name = fence_name, +}; + +static struct dma_fence *alloc_fence(void) +{ + struct dma_fence *f; + + f = kmalloc(sizeof(*f), GFP_KERNEL); + if (!f) + return NULL; + + dma_fence_init(f, &fence_ops, &fence_lock, 0, 0); + return f; +} + +static int sanitycheck(void *arg) +{ + struct dma_resv resv; + struct dma_fence *f; + int r; + + f = alloc_fence(); + if (!f) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f); + + dma_fence_signal(f); + dma_fence_put(f); + + dma_resv_init(&resv); + r = dma_resv_lock(&resv, NULL); + if (r) + pr_err("Resv locking failed\n"); + else + dma_resv_unlock(&resv); + dma_resv_fini(&resv); + return r; +} + +static int test_signaling(void *arg) +{ + enum dma_resv_usage usage = (unsigned long)arg; + struct dma_resv resv; + struct dma_fence *f; + int r; + + f = alloc_fence(); + if (!f) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f); + + dma_resv_init(&resv); + r = dma_resv_lock(&resv, NULL); + if (r) { + pr_err("Resv locking failed\n"); + goto err_free; + } + + r = dma_resv_reserve_fences(&resv, 1); + if (r) { + pr_err("Resv shared slot allocation failed\n"); + goto err_unlock; + } + + dma_resv_add_fence(&resv, f, usage); + if (dma_resv_test_signaled(&resv, usage)) { + pr_err("Resv unexpectedly signaled\n"); + r = -EINVAL; + goto err_unlock; + } + dma_fence_signal(f); + if (!dma_resv_test_signaled(&resv, usage)) { + pr_err("Resv not reporting signaled\n"); + r = -EINVAL; + goto err_unlock; + } +err_unlock: + dma_resv_unlock(&resv); +err_free: + dma_resv_fini(&resv); + dma_fence_put(f); + return r; +} + +static int test_for_each(void *arg) +{ + enum dma_resv_usage usage = (unsigned long)arg; + struct dma_resv_iter cursor; + struct dma_fence *f, *fence; + struct dma_resv resv; + int r; + + f = alloc_fence(); + if (!f) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f); + + dma_resv_init(&resv); + r = dma_resv_lock(&resv, NULL); + if (r) { + pr_err("Resv locking failed\n"); + goto err_free; + } + + r = dma_resv_reserve_fences(&resv, 1); + if (r) { + pr_err("Resv shared slot allocation failed\n"); + goto err_unlock; + } + + dma_resv_add_fence(&resv, f, usage); + + r = -ENOENT; + dma_resv_for_each_fence(&cursor, &resv, usage, fence) { + if (!r) { + pr_err("More than one fence found\n"); + r = -EINVAL; + goto err_unlock; + } + if (f != fence) { + pr_err("Unexpected fence\n"); + r = -EINVAL; + goto err_unlock; + } + if (dma_resv_iter_usage(&cursor) != usage) { + pr_err("Unexpected fence usage\n"); + r = -EINVAL; + goto err_unlock; + } + r = 0; + } + if (r) { + pr_err("No fence found\n"); + goto err_unlock; + } + dma_fence_signal(f); +err_unlock: + dma_resv_unlock(&resv); +err_free: + dma_resv_fini(&resv); + dma_fence_put(f); + return r; +} + +static int test_for_each_unlocked(void *arg) +{ + enum dma_resv_usage usage = (unsigned long)arg; + struct dma_resv_iter cursor; + struct dma_fence *f, *fence; + struct dma_resv resv; + int r; + + f = alloc_fence(); + if (!f) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f); + + dma_resv_init(&resv); + r = dma_resv_lock(&resv, NULL); + if (r) { + pr_err("Resv locking failed\n"); + goto err_free; + } + + r = dma_resv_reserve_fences(&resv, 1); + if (r) { + pr_err("Resv shared slot allocation failed\n"); + dma_resv_unlock(&resv); + goto err_free; + } + + dma_resv_add_fence(&resv, f, usage); + dma_resv_unlock(&resv); + + r = -ENOENT; + dma_resv_iter_begin(&cursor, &resv, usage); + dma_resv_for_each_fence_unlocked(&cursor, fence) { + if (!r) { + pr_err("More than one fence found\n"); + r = -EINVAL; + goto err_iter_end; + } + if (!dma_resv_iter_is_restarted(&cursor)) { + pr_err("No restart flag\n"); + goto err_iter_end; + } + if (f != fence) { + pr_err("Unexpected fence\n"); + r = -EINVAL; + goto err_iter_end; + } + if (dma_resv_iter_usage(&cursor) != usage) { + pr_err("Unexpected fence usage\n"); + r = -EINVAL; + goto err_iter_end; + } + + /* We use r as state here */ + if (r == -ENOENT) { + r = -EINVAL; + /* That should trigger an restart */ + cursor.fences = (void*)~0; + } else if (r == -EINVAL) { + r = 0; + } + } + if (r) + pr_err("No fence found\n"); +err_iter_end: + dma_resv_iter_end(&cursor); + dma_fence_signal(f); +err_free: + dma_resv_fini(&resv); + dma_fence_put(f); + return r; +} + +static int test_get_fences(void *arg) +{ + enum dma_resv_usage usage = (unsigned long)arg; + struct dma_fence *f, **fences = NULL; + struct dma_resv resv; + int r, i; + + f = alloc_fence(); + if (!f) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f); + + dma_resv_init(&resv); + r = dma_resv_lock(&resv, NULL); + if (r) { + pr_err("Resv locking failed\n"); + goto err_resv; + } + + r = dma_resv_reserve_fences(&resv, 1); + if (r) { + pr_err("Resv shared slot allocation failed\n"); + dma_resv_unlock(&resv); + goto err_resv; + } + + dma_resv_add_fence(&resv, f, usage); + dma_resv_unlock(&resv); + + r = dma_resv_get_fences(&resv, usage, &i, &fences); + if (r) { + pr_err("get_fences failed\n"); + goto err_free; + } + + if (i != 1 || fences[0] != f) { + pr_err("get_fences returned unexpected fence\n"); + goto err_free; + } + + dma_fence_signal(f); +err_free: + while (i--) + dma_fence_put(fences[i]); + kfree(fences); +err_resv: + dma_resv_fini(&resv); + dma_fence_put(f); + return r; +} + +int dma_resv(void) +{ + static const struct subtest tests[] = { + SUBTEST(sanitycheck), + SUBTEST(test_signaling), + SUBTEST(test_for_each), + SUBTEST(test_for_each_unlocked), + SUBTEST(test_get_fences), + }; + enum dma_resv_usage usage; + int r; + + spin_lock_init(&fence_lock); + for (usage = DMA_RESV_USAGE_KERNEL; usage <= DMA_RESV_USAGE_BOOKKEEP; + ++usage) { + r = subtests(tests, (void *)(unsigned long)usage); + if (r) + return r; + } + return 0; +} diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index 394e6e1e9686..af57799c86ce 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -5,6 +5,7 @@ * Copyright (C) 2012 Google, Inc. */ +#include <linux/dma-fence-unwrap.h> #include <linux/export.h> #include <linux/file.h> #include <linux/fs.h> @@ -131,7 +132,7 @@ EXPORT_SYMBOL(sync_file_get_fence); char *sync_file_get_name(struct sync_file *sync_file, char *buf, int len) { if (sync_file->user_name[0]) { - strlcpy(buf, sync_file->user_name, len); + strscpy(buf, sync_file->user_name, len); } else { struct dma_fence *fence = sync_file->fence; @@ -145,58 +146,6 @@ char *sync_file_get_name(struct sync_file *sync_file, char *buf, int len) return buf; } -static int sync_file_set_fence(struct sync_file *sync_file, - struct dma_fence **fences, int num_fences) -{ - struct dma_fence_array *array; - - /* - * The reference for the fences in the new sync_file and held - * in add_fence() during the merge procedure, so for num_fences == 1 - * we already own a new reference to the fence. For num_fence > 1 - * we own the reference of the dma_fence_array creation. - */ - if (num_fences == 1) { - sync_file->fence = fences[0]; - kfree(fences); - } else { - array = dma_fence_array_create(num_fences, fences, - dma_fence_context_alloc(1), - 1, false); - if (!array) - return -ENOMEM; - - sync_file->fence = &array->base; - } - - return 0; -} - -static struct dma_fence **get_fences(struct sync_file *sync_file, - int *num_fences) -{ - if (dma_fence_is_array(sync_file->fence)) { - struct dma_fence_array *array = to_dma_fence_array(sync_file->fence); - - *num_fences = array->num_fences; - return array->fences; - } - - *num_fences = 1; - return &sync_file->fence; -} - -static void add_fence(struct dma_fence **fences, - int *i, struct dma_fence *fence) -{ - fences[*i] = fence; - - if (!dma_fence_is_signaled(fence)) { - dma_fence_get(fence); - (*i)++; - } -} - /** * sync_file_merge() - merge two sync_files * @name: name of new fence @@ -211,85 +160,20 @@ static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, struct sync_file *b) { struct sync_file *sync_file; - struct dma_fence **fences = NULL, **nfences, **a_fences, **b_fences; - int i = 0, i_a, i_b, num_fences, a_num_fences, b_num_fences; + struct dma_fence *fence; sync_file = sync_file_alloc(); if (!sync_file) return NULL; - a_fences = get_fences(a, &a_num_fences); - b_fences = get_fences(b, &b_num_fences); - if (a_num_fences > INT_MAX - b_num_fences) - goto err; - - num_fences = a_num_fences + b_num_fences; - - fences = kcalloc(num_fences, sizeof(*fences), GFP_KERNEL); - if (!fences) - goto err; - - /* - * Assume sync_file a and b are both ordered and have no - * duplicates with the same context. - * - * If a sync_file can only be created with sync_file_merge - * and sync_file_create, this is a reasonable assumption. - */ - for (i_a = i_b = 0; i_a < a_num_fences && i_b < b_num_fences; ) { - struct dma_fence *pt_a = a_fences[i_a]; - struct dma_fence *pt_b = b_fences[i_b]; - - if (pt_a->context < pt_b->context) { - add_fence(fences, &i, pt_a); - - i_a++; - } else if (pt_a->context > pt_b->context) { - add_fence(fences, &i, pt_b); - - i_b++; - } else { - if (__dma_fence_is_later(pt_a->seqno, pt_b->seqno, - pt_a->ops)) - add_fence(fences, &i, pt_a); - else - add_fence(fences, &i, pt_b); - - i_a++; - i_b++; - } - } - - for (; i_a < a_num_fences; i_a++) - add_fence(fences, &i, a_fences[i_a]); - - for (; i_b < b_num_fences; i_b++) - add_fence(fences, &i, b_fences[i_b]); - - if (i == 0) - fences[i++] = dma_fence_get(a_fences[0]); - - if (num_fences > i) { - nfences = krealloc_array(fences, i, sizeof(*fences), GFP_KERNEL); - if (!nfences) - goto err; - - fences = nfences; + fence = dma_fence_unwrap_merge(a->fence, b->fence); + if (!fence) { + fput(sync_file->file); + return NULL; } - - if (sync_file_set_fence(sync_file, fences, i) < 0) - goto err; - - strlcpy(sync_file->user_name, name, sizeof(sync_file->user_name)); + sync_file->fence = fence; + strscpy(sync_file->user_name, name, sizeof(sync_file->user_name)); return sync_file; - -err: - while (i) - dma_fence_put(fences[--i]); - kfree(fences); - fput(sync_file->file); - return NULL; - } static int sync_file_release(struct inode *inode, struct file *file) @@ -378,9 +262,9 @@ err_put_fd: static int sync_fill_fence_info(struct dma_fence *fence, struct sync_fence_info *info) { - strlcpy(info->obj_name, fence->ops->get_timeline_name(fence), + strscpy(info->obj_name, fence->ops->get_timeline_name(fence), sizeof(info->obj_name)); - strlcpy(info->driver_name, fence->ops->get_driver_name(fence), + strscpy(info->driver_name, fence->ops->get_driver_name(fence), sizeof(info->driver_name)); info->status = dma_fence_get_status(fence); @@ -398,11 +282,13 @@ static int sync_fill_fence_info(struct dma_fence *fence, static long sync_file_ioctl_fence_info(struct sync_file *sync_file, unsigned long arg) { - struct sync_file_info info; struct sync_fence_info *fence_info = NULL; - struct dma_fence **fences; + struct dma_fence_unwrap iter; + struct sync_file_info info; + unsigned int num_fences; + struct dma_fence *fence; + int ret; __u32 size; - int num_fences, ret, i; if (copy_from_user(&info, (void __user *)arg, sizeof(info))) return -EFAULT; @@ -410,7 +296,9 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, if (info.flags || info.pad) return -EINVAL; - fences = get_fences(sync_file, &num_fences); + num_fences = 0; + dma_fence_unwrap_for_each(fence, &iter, sync_file->fence) + ++num_fences; /* * Passing num_fences = 0 means that userspace doesn't want to @@ -433,8 +321,11 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, if (!fence_info) return -ENOMEM; - for (i = 0; i < num_fences; i++) { - int status = sync_fill_fence_info(fences[i], &fence_info[i]); + num_fences = 0; + dma_fence_unwrap_for_each(fence, &iter, sync_file->fence) { + int status; + + status = sync_fill_fence_info(fence, &fence_info[num_fences++]); info.status = info.status <= 0 ? info.status : status; } diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index c57a609db75b..2bcdb935a3ac 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -32,8 +32,11 @@ static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct udmabuf *ubuf = vma->vm_private_data; + pgoff_t pgoff = vmf->pgoff; - vmf->page = ubuf->pages[vmf->pgoff]; + if (pgoff >= ubuf->pagecount) + return VM_FAULT_SIGBUS; + vmf->page = ubuf->pages[pgoff]; get_page(vmf->page); return 0; } @@ -121,17 +124,20 @@ static int begin_cpu_udmabuf(struct dma_buf *buf, { struct udmabuf *ubuf = buf->priv; struct device *dev = ubuf->device->this_device; + int ret = 0; if (!ubuf->sg) { ubuf->sg = get_sg_table(dev, buf, direction); - if (IS_ERR(ubuf->sg)) - return PTR_ERR(ubuf->sg); + if (IS_ERR(ubuf->sg)) { + ret = PTR_ERR(ubuf->sg); + ubuf->sg = NULL; + } } else { dma_sync_sg_for_cpu(dev, ubuf->sg->sgl, ubuf->sg->nents, direction); } - return 0; + return ret; } static int end_cpu_udmabuf(struct dma_buf *buf, @@ -190,6 +196,10 @@ static long udmabuf_create(struct miscdevice *device, if (ubuf->pagecount > pglimit) goto err; } + + if (!ubuf->pagecount) + goto err; + ubuf->pages = kmalloc_array(ubuf->pagecount, sizeof(*ubuf->pages), GFP_KERNEL); if (!ubuf->pages) { @@ -203,7 +213,7 @@ static long udmabuf_create(struct miscdevice *device, memfd = fget(list[i].memfd); if (!memfd) goto err; - mapping = file_inode(memfd)->i_mapping; + mapping = memfd->f_mapping; if (!shmem_mapping(mapping) && !is_file_hugepages(memfd)) goto err; seals = memfd_fcntl(memfd, F_GET_SEALS, 0); @@ -361,7 +371,23 @@ static struct miscdevice udmabuf_misc = { static int __init udmabuf_dev_init(void) { - return misc_register(&udmabuf_misc); + int ret; + + ret = misc_register(&udmabuf_misc); + if (ret < 0) { + pr_err("Could not initialize udmabuf device\n"); + return ret; + } + + ret = dma_coerce_mask_and_coherent(udmabuf_misc.this_device, + DMA_BIT_MASK(64)); + if (ret < 0) { + pr_err("Could not setup DMA mask for udmabuf device\n"); + misc_deregister(&udmabuf_misc); + return ret; + } + + return 0; } static void __exit udmabuf_dev_exit(void) |