diff options
Diffstat (limited to '')
26 files changed, 7586 insertions, 0 deletions
diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig new file mode 100644 index 000000000..3ca7de37d --- /dev/null +++ b/drivers/dma-buf/Kconfig @@ -0,0 +1,70 @@ +# SPDX-License-Identifier: GPL-2.0-only +menu "DMABUF options" + +config SYNC_FILE + bool "Explicit Synchronization Framework" + default n + select DMA_SHARED_BUFFER + help + The Sync File Framework adds explicit synchronization via + userspace. It enables send/receive 'struct dma_fence' objects to/from + userspace via Sync File fds for synchronization between drivers via + userspace components. It has been ported from Android. + + The first and main user for this is graphics in which a fence is + associated with a buffer. When a job is submitted to the GPU a fence + is attached to the buffer and is transferred via userspace, using Sync + Files fds, to the DRM driver for example. More details at + Documentation/driver-api/sync_file.rst. + +config SW_SYNC + bool "Sync File Validation Framework" + default n + depends on SYNC_FILE + depends on DEBUG_FS + help + A sync object driver that uses a 32bit counter to coordinate + synchronization. Useful when there is no hardware primitive backing + the synchronization. + + WARNING: improper use of this can result in deadlocking kernel + drivers from userspace. Intended for test and debug only. + +config UDMABUF + bool "userspace dmabuf misc driver" + default n + depends on DMA_SHARED_BUFFER + depends on MEMFD_CREATE || COMPILE_TEST + help + A driver to let userspace turn memfd regions into dma-bufs. + Qemu can use this to create host dmabufs for guest framebuffers. + +config DMABUF_MOVE_NOTIFY + bool "Move notify between drivers (EXPERIMENTAL)" + default n + depends on DMA_SHARED_BUFFER + help + Don't pin buffers if the dynamic DMA-buf interface is available on + both the exporter as well as the importer. This fixes a security + problem where userspace is able to pin unrestricted amounts of memory + through DMA-buf. + This is marked experimental because we don't yet have a consistent + execution context and memory management between drivers. + +config DMABUF_SELFTESTS + tristate "Selftests for the dma-buf interfaces" + default n + depends on DMA_SHARED_BUFFER + +menuconfig DMABUF_HEAPS + bool "DMA-BUF Userland Memory Heaps" + select DMA_SHARED_BUFFER + help + Choose this option to enable the DMA-BUF userland memory heaps. + This options creates per heap chardevs in /dev/dma_heap/ which + allows userspace to allocate dma-bufs that can be shared + between drivers. + +source "drivers/dma-buf/heaps/Kconfig" + +endmenu diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile new file mode 100644 index 000000000..995e05f60 --- /dev/null +++ b/drivers/dma-buf/Makefile @@ -0,0 +1,15 @@ +# 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 seqno-fence.o +obj-$(CONFIG_DMABUF_HEAPS) += dma-heap.o +obj-$(CONFIG_DMABUF_HEAPS) += heaps/ +obj-$(CONFIG_SYNC_FILE) += sync_file.o +obj-$(CONFIG_SW_SYNC) += sw_sync.o sync_debug.o +obj-$(CONFIG_UDMABUF) += udmabuf.o + +dmabuf_selftests-y := \ + selftest.o \ + st-dma-fence.o \ + st-dma-fence-chain.o + +obj-$(CONFIG_DMABUF_SELFTESTS) += dmabuf_selftests.o diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c new file mode 100644 index 000000000..93e9bf738 --- /dev/null +++ b/drivers/dma-buf/dma-buf.c @@ -0,0 +1,1422 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Framework for buffer objects that can be shared across devices/subsystems. + * + * Copyright(C) 2011 Linaro Limited. All rights reserved. + * Author: Sumit Semwal <sumit.semwal@ti.com> + * + * Many thanks to linaro-mm-sig list, and specially + * Arnd Bergmann <arnd@arndb.de>, Rob Clark <rob@ti.com> and + * Daniel Vetter <daniel@ffwll.ch> for their support in creation and + * refining of this idea. + */ + +#include <linux/fs.h> +#include <linux/slab.h> +#include <linux/dma-buf.h> +#include <linux/dma-fence.h> +#include <linux/anon_inodes.h> +#include <linux/export.h> +#include <linux/debugfs.h> +#include <linux/module.h> +#include <linux/seq_file.h> +#include <linux/poll.h> +#include <linux/dma-resv.h> +#include <linux/mm.h> +#include <linux/mount.h> +#include <linux/pseudo_fs.h> + +#include <uapi/linux/dma-buf.h> +#include <uapi/linux/magic.h> + +static inline int is_dma_buf_file(struct file *); + +struct dma_buf_list { + struct list_head head; + struct mutex lock; +}; + +static struct dma_buf_list db_list; + +static char *dmabuffs_dname(struct dentry *dentry, char *buffer, int buflen) +{ + struct dma_buf *dmabuf; + char name[DMA_BUF_NAME_LEN]; + size_t ret = 0; + + dmabuf = dentry->d_fsdata; + spin_lock(&dmabuf->name_lock); + if (dmabuf->name) + ret = strlcpy(name, dmabuf->name, DMA_BUF_NAME_LEN); + spin_unlock(&dmabuf->name_lock); + + return dynamic_dname(dentry, buffer, buflen, "/%s:%s", + dentry->d_name.name, ret > 0 ? name : ""); +} + +static void dma_buf_release(struct dentry *dentry) +{ + struct dma_buf *dmabuf; + + dmabuf = dentry->d_fsdata; + if (unlikely(!dmabuf)) + return; + + BUG_ON(dmabuf->vmapping_counter); + + /* + * Any fences that a dma-buf poll can wait on should be signaled + * before releasing dma-buf. This is the responsibility of each + * driver that uses the reservation objects. + * + * If you hit this BUG() it means someone dropped their ref to the + * dma-buf while still having pending operation to the buffer. + */ + BUG_ON(dmabuf->cb_shared.active || dmabuf->cb_excl.active); + + dmabuf->ops->release(dmabuf); + + if (dmabuf->resv == (struct dma_resv *)&dmabuf[1]) + dma_resv_fini(dmabuf->resv); + + WARN_ON(!list_empty(&dmabuf->attachments)); + module_put(dmabuf->owner); + kfree(dmabuf->name); + kfree(dmabuf); +} + +static int dma_buf_file_release(struct inode *inode, struct file *file) +{ + struct dma_buf *dmabuf; + + if (!is_dma_buf_file(file)) + return -EINVAL; + + dmabuf = file->private_data; + + mutex_lock(&db_list.lock); + list_del(&dmabuf->list_node); + mutex_unlock(&db_list.lock); + + return 0; +} + +static const struct dentry_operations dma_buf_dentry_ops = { + .d_dname = dmabuffs_dname, + .d_release = dma_buf_release, +}; + +static struct vfsmount *dma_buf_mnt; + +static int dma_buf_fs_init_context(struct fs_context *fc) +{ + struct pseudo_fs_context *ctx; + + ctx = init_pseudo(fc, DMA_BUF_MAGIC); + if (!ctx) + return -ENOMEM; + ctx->dops = &dma_buf_dentry_ops; + return 0; +} + +static struct file_system_type dma_buf_fs_type = { + .name = "dmabuf", + .init_fs_context = dma_buf_fs_init_context, + .kill_sb = kill_anon_super, +}; + +static int dma_buf_mmap_internal(struct file *file, struct vm_area_struct *vma) +{ + struct dma_buf *dmabuf; + + if (!is_dma_buf_file(file)) + return -EINVAL; + + dmabuf = file->private_data; + + /* check if buffer supports mmap */ + if (!dmabuf->ops->mmap) + return -EINVAL; + + /* check for overflowing the buffer's size */ + if (vma->vm_pgoff + vma_pages(vma) > + dmabuf->size >> PAGE_SHIFT) + return -EINVAL; + + return dmabuf->ops->mmap(dmabuf, vma); +} + +static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence) +{ + struct dma_buf *dmabuf; + loff_t base; + + if (!is_dma_buf_file(file)) + return -EBADF; + + dmabuf = file->private_data; + + /* only support discovering the end of the buffer, + but also allow SEEK_SET to maintain the idiomatic + SEEK_END(0), SEEK_CUR(0) pattern */ + if (whence == SEEK_END) + base = dmabuf->size; + else if (whence == SEEK_SET) + base = 0; + else + return -EINVAL; + + if (offset != 0) + return -EINVAL; + + return base + offset; +} + +/** + * DOC: implicit fence polling + * + * To support cross-device and cross-driver synchronization of buffer access + * implicit fences (represented internally in the kernel with &struct dma_fence) + * can be attached to a &dma_buf. The glue for that and a few related things are + * provided in the &dma_resv structure. + * + * Userspace can query the state of these implicitly tracked fences using poll() + * and related system calls: + * + * - Checking for EPOLLIN, i.e. read access, can be use to query the state of the + * most recent write or exclusive fence. + * + * - Checking for EPOLLOUT, i.e. write access, can be used to query the state of + * all attached fences, shared and exclusive ones. + * + * 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. + */ + +static void dma_buf_poll_cb(struct dma_fence *fence, struct dma_fence_cb *cb) +{ + struct dma_buf_poll_cb_t *dcb = (struct dma_buf_poll_cb_t *)cb; + unsigned long flags; + + spin_lock_irqsave(&dcb->poll->lock, flags); + wake_up_locked_poll(dcb->poll, dcb->active); + dcb->active = 0; + spin_unlock_irqrestore(&dcb->poll->lock, flags); +} + +static __poll_t dma_buf_poll(struct file *file, poll_table *poll) +{ + struct dma_buf *dmabuf; + struct dma_resv *resv; + struct dma_resv_list *fobj; + struct dma_fence *fence_excl; + __poll_t events; + unsigned shared_count, seq; + + dmabuf = file->private_data; + if (!dmabuf || !dmabuf->resv) + return EPOLLERR; + + resv = dmabuf->resv; + + poll_wait(file, &dmabuf->poll, poll); + + events = poll_requested_events(poll) & (EPOLLIN | EPOLLOUT); + if (!events) + return 0; + +retry: + seq = read_seqcount_begin(&resv->seq); + rcu_read_lock(); + + fobj = rcu_dereference(resv->fence); + if (fobj) + shared_count = fobj->shared_count; + else + shared_count = 0; + fence_excl = rcu_dereference(resv->fence_excl); + if (read_seqcount_retry(&resv->seq, seq)) { + rcu_read_unlock(); + goto retry; + } + + if (fence_excl && (!(events & EPOLLOUT) || shared_count == 0)) { + struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_excl; + __poll_t pevents = EPOLLIN; + + if (shared_count == 0) + pevents |= EPOLLOUT; + + spin_lock_irq(&dmabuf->poll.lock); + if (dcb->active) { + dcb->active |= pevents; + events &= ~pevents; + } else + dcb->active = pevents; + spin_unlock_irq(&dmabuf->poll.lock); + + if (events & pevents) { + if (!dma_fence_get_rcu(fence_excl)) { + /* force a recheck */ + events &= ~pevents; + dma_buf_poll_cb(NULL, &dcb->cb); + } else if (!dma_fence_add_callback(fence_excl, &dcb->cb, + dma_buf_poll_cb)) { + events &= ~pevents; + dma_fence_put(fence_excl); + } else { + /* + * No callback queued, wake up any additional + * waiters. + */ + dma_fence_put(fence_excl); + dma_buf_poll_cb(NULL, &dcb->cb); + } + } + } + + if ((events & EPOLLOUT) && shared_count > 0) { + struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_shared; + int i; + + /* Only queue a new callback if no event has fired yet */ + spin_lock_irq(&dmabuf->poll.lock); + if (dcb->active) + events &= ~EPOLLOUT; + else + dcb->active = EPOLLOUT; + spin_unlock_irq(&dmabuf->poll.lock); + + if (!(events & EPOLLOUT)) + goto out; + + for (i = 0; i < shared_count; ++i) { + struct dma_fence *fence = rcu_dereference(fobj->shared[i]); + + if (!dma_fence_get_rcu(fence)) { + /* + * fence refcount dropped to zero, this means + * that fobj has been freed + * + * call dma_buf_poll_cb and force a recheck! + */ + events &= ~EPOLLOUT; + dma_buf_poll_cb(NULL, &dcb->cb); + break; + } + if (!dma_fence_add_callback(fence, &dcb->cb, + dma_buf_poll_cb)) { + dma_fence_put(fence); + events &= ~EPOLLOUT; + break; + } + dma_fence_put(fence); + } + + /* No callback queued, wake up any additional waiters. */ + if (i == shared_count) + dma_buf_poll_cb(NULL, &dcb->cb); + } + +out: + rcu_read_unlock(); + return events; +} + +/** + * 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. + * + * @dmabuf: [in] dmabuf buffer that will be renamed. + * @buf: [in] A piece of userspace memory that contains the name of + * the dma-buf. + * + * Returns 0 on success. If the dma-buf buffer is already attached to + * devices, return -EBUSY. + * + */ +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: + dma_resv_unlock(dmabuf->resv); + return ret; +} + +static long dma_buf_ioctl(struct file *file, + unsigned int cmd, unsigned long arg) +{ + struct dma_buf *dmabuf; + struct dma_buf_sync sync; + enum dma_data_direction direction; + int ret; + + dmabuf = file->private_data; + + switch (cmd) { + case DMA_BUF_IOCTL_SYNC: + if (copy_from_user(&sync, (void __user *) arg, sizeof(sync))) + return -EFAULT; + + if (sync.flags & ~DMA_BUF_SYNC_VALID_FLAGS_MASK) + return -EINVAL; + + switch (sync.flags & DMA_BUF_SYNC_RW) { + case DMA_BUF_SYNC_READ: + direction = DMA_FROM_DEVICE; + break; + case DMA_BUF_SYNC_WRITE: + direction = DMA_TO_DEVICE; + break; + case DMA_BUF_SYNC_RW: + direction = DMA_BIDIRECTIONAL; + break; + default: + return -EINVAL; + } + + if (sync.flags & DMA_BUF_SYNC_END) + ret = dma_buf_end_cpu_access(dmabuf, direction); + else + ret = dma_buf_begin_cpu_access(dmabuf, direction); + + return ret; + + case DMA_BUF_SET_NAME_A: + case DMA_BUF_SET_NAME_B: + return dma_buf_set_name(dmabuf, (const char __user *)arg); + + default: + return -ENOTTY; + } +} + +static void dma_buf_show_fdinfo(struct seq_file *m, struct file *file) +{ + struct dma_buf *dmabuf = file->private_data; + + seq_printf(m, "size:\t%zu\n", dmabuf->size); + /* Don't count the temporary reference taken inside procfs seq_show */ + seq_printf(m, "count:\t%ld\n", file_count(dmabuf->file) - 1); + seq_printf(m, "exp_name:\t%s\n", dmabuf->exp_name); + spin_lock(&dmabuf->name_lock); + if (dmabuf->name) + seq_printf(m, "name:\t%s\n", dmabuf->name); + spin_unlock(&dmabuf->name_lock); +} + +static const struct file_operations dma_buf_fops = { + .release = dma_buf_file_release, + .mmap = dma_buf_mmap_internal, + .llseek = dma_buf_llseek, + .poll = dma_buf_poll, + .unlocked_ioctl = dma_buf_ioctl, + .compat_ioctl = compat_ptr_ioctl, + .show_fdinfo = dma_buf_show_fdinfo, +}; + +/* + * is_dma_buf_file - Check if struct file* is associated with dma_buf + */ +static inline int is_dma_buf_file(struct file *file) +{ + return file->f_op == &dma_buf_fops; +} + +static struct file *dma_buf_getfile(struct dma_buf *dmabuf, int flags) +{ + struct file *file; + struct inode *inode = alloc_anon_inode(dma_buf_mnt->mnt_sb); + + if (IS_ERR(inode)) + return ERR_CAST(inode); + + inode->i_size = dmabuf->size; + inode_set_bytes(inode, dmabuf->size); + + 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; + + return file; + +err_alloc_file: + iput(inode); + return file; +} + +/** + * DOC: dma buf device access + * + * For device DMA access to a shared DMA buffer the usual sequence of operations + * is fairly simple: + * + * 1. The exporter defines his exporter instance using + * DEFINE_DMA_BUF_EXPORT_INFO() and calls dma_buf_export() to wrap a private + * buffer object into a &dma_buf. It then exports that &dma_buf to userspace + * 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 + * dma_buf_get(). Then the buffer is attached to the device using + * dma_buf_attach(). + * + * Up to this stage the exporter is still free to migrate or reallocate the + * backing storage. + * + * 3. Once the buffer is attached to all devices userspace can initiate DMA + * access to the shared buffer. In the kernel this is done by calling + * dma_buf_map_attachment() and dma_buf_unmap_attachment(). + * + * 4. Once a driver is done with a shared buffer it needs to call + * dma_buf_detach() (after cleaning up any mappings) and then release the + * reference acquired with dma_buf_get by calling dma_buf_put(). + * + * For the detailed semantics exporters are expected to implement see + * &dma_buf_ops. + */ + +/** + * dma_buf_export - Creates a new dma_buf, and associates an anon file + * with this buffer, so it can be exported. + * Also connect the allocator specific data and ops to the buffer. + * Additionally, provide a name string for exporter; useful in debugging. + * + * @exp_info: [in] holds all the export related information provided + * by the exporter. see &struct dma_buf_export_info + * for further details. + * + * Returns, on success, a newly created dma_buf object, which wraps the + * supplied private data and operations for dma_buf_ops. On either missing + * ops, or error in allocating struct dma_buf, will return negative error. + * + * For most cases the easiest way to create @exp_info is through the + * %DEFINE_DMA_BUF_EXPORT_INFO macro. + */ +struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) +{ + struct dma_buf *dmabuf; + struct dma_resv *resv = exp_info->resv; + struct file *file; + size_t alloc_size = sizeof(struct dma_buf); + int ret; + + if (!exp_info->resv) + alloc_size += sizeof(struct dma_resv); + else + /* prevent &dma_buf[1] == dma_buf->resv */ + alloc_size += 1; + + if (WARN_ON(!exp_info->priv + || !exp_info->ops + || !exp_info->ops->map_dma_buf + || !exp_info->ops->unmap_dma_buf + || !exp_info->ops->release)) { + return ERR_PTR(-EINVAL); + } + + if (WARN_ON(exp_info->ops->cache_sgt_mapping && + (exp_info->ops->pin || exp_info->ops->unpin))) + return ERR_PTR(-EINVAL); + + if (WARN_ON(!exp_info->ops->pin != !exp_info->ops->unpin)) + return ERR_PTR(-EINVAL); + + if (!try_module_get(exp_info->owner)) + return ERR_PTR(-ENOENT); + + dmabuf = kzalloc(alloc_size, GFP_KERNEL); + if (!dmabuf) { + ret = -ENOMEM; + goto err_module; + } + + dmabuf->priv = exp_info->priv; + dmabuf->ops = exp_info->ops; + dmabuf->size = exp_info->size; + dmabuf->exp_name = exp_info->exp_name; + dmabuf->owner = exp_info->owner; + spin_lock_init(&dmabuf->name_lock); + init_waitqueue_head(&dmabuf->poll); + dmabuf->cb_excl.poll = dmabuf->cb_shared.poll = &dmabuf->poll; + dmabuf->cb_excl.active = dmabuf->cb_shared.active = 0; + + if (!resv) { + resv = (struct dma_resv *)&dmabuf[1]; + dma_resv_init(resv); + } + dmabuf->resv = resv; + + file = dma_buf_getfile(dmabuf, exp_info->flags); + if (IS_ERR(file)) { + ret = PTR_ERR(file); + goto err_dmabuf; + } + + file->f_mode |= FMODE_LSEEK; + dmabuf->file = file; + + mutex_init(&dmabuf->lock); + INIT_LIST_HEAD(&dmabuf->attachments); + + mutex_lock(&db_list.lock); + list_add(&dmabuf->list_node, &db_list.head); + mutex_unlock(&db_list.lock); + + return dmabuf; + +err_dmabuf: + kfree(dmabuf); +err_module: + module_put(exp_info->owner); + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(dma_buf_export); + +/** + * dma_buf_fd - returns a file descriptor for the given dma_buf + * @dmabuf: [in] pointer to dma_buf for which fd is required. + * @flags: [in] flags to give to fd + * + * On success, returns an associated 'fd'. Else, returns error. + */ +int dma_buf_fd(struct dma_buf *dmabuf, int flags) +{ + int fd; + + if (!dmabuf || !dmabuf->file) + return -EINVAL; + + fd = get_unused_fd_flags(flags); + if (fd < 0) + return fd; + + fd_install(fd, dmabuf->file); + + return fd; +} +EXPORT_SYMBOL_GPL(dma_buf_fd); + +/** + * dma_buf_get - returns the dma_buf structure related to an fd + * @fd: [in] fd associated with the dma_buf to be returned + * + * On success, returns the dma_buf structure associated with an fd; uses + * file's refcounting done by fget to increase refcount. returns ERR_PTR + * otherwise. + */ +struct dma_buf *dma_buf_get(int fd) +{ + struct file *file; + + file = fget(fd); + + if (!file) + return ERR_PTR(-EBADF); + + if (!is_dma_buf_file(file)) { + fput(file); + return ERR_PTR(-EINVAL); + } + + return file->private_data; +} +EXPORT_SYMBOL_GPL(dma_buf_get); + +/** + * dma_buf_put - decreases refcount of the buffer + * @dmabuf: [in] buffer to reduce refcount of + * + * Uses file's refcounting done implicitly by fput(). + * + * If, as a result of this call, the refcount becomes 0, the 'release' file + * operation related to this fd is called. It calls &dma_buf_ops.release vfunc + * in turn, and frees the memory allocated for dmabuf when exported. + */ +void dma_buf_put(struct dma_buf *dmabuf) +{ + if (WARN_ON(!dmabuf || !dmabuf->file)) + return; + + fput(dmabuf->file); +} +EXPORT_SYMBOL_GPL(dma_buf_put); + +/** + * dma_buf_dynamic_attach - Add the device to dma_buf's attachments list; optionally, + * calls attach() of dma_buf_ops to allow device-specific attach functionality + * @dmabuf: [in] buffer to attach device to. + * @dev: [in] device to be attached. + * @importer_ops: [in] importer operations for the attachment + * @importer_priv: [in] importer private pointer for the attachment + * + * Returns struct dma_buf_attachment pointer for this attachment. Attachments + * must be cleaned up by calling dma_buf_detach(). + * + * Returns: + * + * A pointer to newly created &dma_buf_attachment on success, or a negative + * error code wrapped into a pointer on failure. + * + * Note that this can fail if the backing storage of @dmabuf is in a place not + * accessible to @dev, and cannot be moved to a more suitable place. This is + * indicated with the error code -EBUSY. + */ +struct dma_buf_attachment * +dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev, + const struct dma_buf_attach_ops *importer_ops, + void *importer_priv) +{ + struct dma_buf_attachment *attach; + int ret; + + if (WARN_ON(!dmabuf || !dev)) + return ERR_PTR(-EINVAL); + + if (WARN_ON(importer_ops && !importer_ops->move_notify)) + return ERR_PTR(-EINVAL); + + attach = kzalloc(sizeof(*attach), GFP_KERNEL); + if (!attach) + return ERR_PTR(-ENOMEM); + + attach->dev = dev; + attach->dmabuf = dmabuf; + if (importer_ops) + attach->peer2peer = importer_ops->allow_peer2peer; + attach->importer_ops = importer_ops; + attach->importer_priv = importer_priv; + + if (dmabuf->ops->attach) { + ret = dmabuf->ops->attach(dmabuf, attach); + if (ret) + goto err_attach; + } + dma_resv_lock(dmabuf->resv, NULL); + list_add(&attach->node, &dmabuf->attachments); + dma_resv_unlock(dmabuf->resv); + + /* When either the importer or the exporter can't handle dynamic + * mappings we cache the mapping here to avoid issues with the + * reservation object lock. + */ + if (dma_buf_attachment_is_dynamic(attach) != + dma_buf_is_dynamic(dmabuf)) { + struct sg_table *sgt; + + if (dma_buf_is_dynamic(attach->dmabuf)) { + dma_resv_lock(attach->dmabuf->resv, NULL); + ret = dma_buf_pin(attach); + if (ret) + goto err_unlock; + } + + sgt = dmabuf->ops->map_dma_buf(attach, DMA_BIDIRECTIONAL); + if (!sgt) + sgt = ERR_PTR(-ENOMEM); + if (IS_ERR(sgt)) { + ret = PTR_ERR(sgt); + goto err_unpin; + } + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_resv_unlock(attach->dmabuf->resv); + attach->sgt = sgt; + attach->dir = DMA_BIDIRECTIONAL; + } + + return attach; + +err_attach: + kfree(attach); + return ERR_PTR(ret); + +err_unpin: + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_buf_unpin(attach); + +err_unlock: + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_resv_unlock(attach->dmabuf->resv); + + dma_buf_detach(dmabuf, attach); + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(dma_buf_dynamic_attach); + +/** + * dma_buf_attach - Wrapper for dma_buf_dynamic_attach + * @dmabuf: [in] buffer to attach device to. + * @dev: [in] device to be attached. + * + * Wrapper to call dma_buf_dynamic_attach() for drivers which still use a static + * mapping. + */ +struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, + struct device *dev) +{ + return dma_buf_dynamic_attach(dmabuf, dev, NULL, NULL); +} +EXPORT_SYMBOL_GPL(dma_buf_attach); + +/** + * dma_buf_detach - Remove the given attachment from dmabuf's attachments list; + * optionally calls detach() of dma_buf_ops for device-specific detach + * @dmabuf: [in] buffer to detach from. + * @attach: [in] attachment to be detached; is free'd after this call. + * + * Clean up a device attachment obtained by calling dma_buf_attach(). + */ +void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach) +{ + if (WARN_ON(!dmabuf || !attach)) + return; + + if (attach->sgt) { + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_resv_lock(attach->dmabuf->resv, NULL); + + dmabuf->ops->unmap_dma_buf(attach, attach->sgt, attach->dir); + + if (dma_buf_is_dynamic(attach->dmabuf)) { + dma_buf_unpin(attach); + dma_resv_unlock(attach->dmabuf->resv); + } + } + + dma_resv_lock(dmabuf->resv, NULL); + list_del(&attach->node); + dma_resv_unlock(dmabuf->resv); + if (dmabuf->ops->detach) + dmabuf->ops->detach(dmabuf, attach); + + kfree(attach); +} +EXPORT_SYMBOL_GPL(dma_buf_detach); + +/** + * dma_buf_pin - Lock down the DMA-buf + * + * @attach: [in] attachment which should be pinned + * + * Returns: + * 0 on success, negative error code on failure. + */ +int dma_buf_pin(struct dma_buf_attachment *attach) +{ + struct dma_buf *dmabuf = attach->dmabuf; + int ret = 0; + + dma_resv_assert_held(dmabuf->resv); + + if (dmabuf->ops->pin) + ret = dmabuf->ops->pin(attach); + + return ret; +} +EXPORT_SYMBOL_GPL(dma_buf_pin); + +/** + * dma_buf_unpin - Remove lock from DMA-buf + * + * @attach: [in] attachment which should be unpinned + */ +void dma_buf_unpin(struct dma_buf_attachment *attach) +{ + struct dma_buf *dmabuf = attach->dmabuf; + + dma_resv_assert_held(dmabuf->resv); + + if (dmabuf->ops->unpin) + dmabuf->ops->unpin(attach); +} +EXPORT_SYMBOL_GPL(dma_buf_unpin); + +/** + * dma_buf_map_attachment - Returns the scatterlist table of the attachment; + * mapped into _device_ address space. Is a wrapper for map_dma_buf() of the + * dma_buf_ops. + * @attach: [in] attachment whose scatterlist is to be returned + * @direction: [in] direction of DMA transfer + * + * Returns sg_table containing the scatterlist to be returned; returns ERR_PTR + * on error. May return -EINTR if it is interrupted by a signal. + * + * A mapping must be unmapped by using dma_buf_unmap_attachment(). Note that + * the underlying backing storage is pinned for as long as a mapping exists, + * therefore users/importers should not hold onto a mapping for undue amounts of + * time. + */ +struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach, + enum dma_data_direction direction) +{ + struct sg_table *sg_table; + int r; + + might_sleep(); + + if (WARN_ON(!attach || !attach->dmabuf)) + return ERR_PTR(-EINVAL); + + if (dma_buf_attachment_is_dynamic(attach)) + dma_resv_assert_held(attach->dmabuf->resv); + + if (attach->sgt) { + /* + * Two mappings with different directions for the same + * attachment are not allowed. + */ + if (attach->dir != direction && + attach->dir != DMA_BIDIRECTIONAL) + return ERR_PTR(-EBUSY); + + return attach->sgt; + } + + if (dma_buf_is_dynamic(attach->dmabuf)) { + dma_resv_assert_held(attach->dmabuf->resv); + if (!IS_ENABLED(CONFIG_DMABUF_MOVE_NOTIFY)) { + r = dma_buf_pin(attach); + if (r) + return ERR_PTR(r); + } + } + + sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction); + if (!sg_table) + sg_table = ERR_PTR(-ENOMEM); + + if (IS_ERR(sg_table) && dma_buf_is_dynamic(attach->dmabuf) && + !IS_ENABLED(CONFIG_DMABUF_MOVE_NOTIFY)) + dma_buf_unpin(attach); + + if (!IS_ERR(sg_table) && attach->dmabuf->ops->cache_sgt_mapping) { + attach->sgt = sg_table; + attach->dir = direction; + } + + return sg_table; +} +EXPORT_SYMBOL_GPL(dma_buf_map_attachment); + +/** + * dma_buf_unmap_attachment - unmaps and decreases usecount of the buffer;might + * deallocate the scatterlist associated. Is a wrapper for unmap_dma_buf() of + * dma_buf_ops. + * @attach: [in] attachment to unmap buffer from + * @sg_table: [in] scatterlist info of the buffer to unmap + * @direction: [in] direction of DMA transfer + * + * This unmaps a DMA mapping for @attached obtained by dma_buf_map_attachment(). + */ +void dma_buf_unmap_attachment(struct dma_buf_attachment *attach, + struct sg_table *sg_table, + enum dma_data_direction direction) +{ + might_sleep(); + + if (WARN_ON(!attach || !attach->dmabuf || !sg_table)) + return; + + if (dma_buf_attachment_is_dynamic(attach)) + dma_resv_assert_held(attach->dmabuf->resv); + + if (attach->sgt == sg_table) + return; + + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_resv_assert_held(attach->dmabuf->resv); + + attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, direction); + + if (dma_buf_is_dynamic(attach->dmabuf) && + !IS_ENABLED(CONFIG_DMABUF_MOVE_NOTIFY)) + dma_buf_unpin(attach); +} +EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment); + +/** + * dma_buf_move_notify - notify attachments that DMA-buf is moving + * + * @dmabuf: [in] buffer which is moving + * + * Informs all attachmenst that they need to destroy and recreated all their + * mappings. + */ +void dma_buf_move_notify(struct dma_buf *dmabuf) +{ + struct dma_buf_attachment *attach; + + dma_resv_assert_held(dmabuf->resv); + + list_for_each_entry(attach, &dmabuf->attachments, node) + if (attach->importer_ops) + attach->importer_ops->move_notify(attach); +} +EXPORT_SYMBOL_GPL(dma_buf_move_notify); + +/** + * DOC: cpu access + * + * There are mutliple reasons for supporting CPU access to a dma buffer object: + * + * - Fallback operations in the kernel, for example when a device is connected + * over USB and the kernel needs to shuffle the data around first before + * sending it away. Cache coherency is handled by braketing any transactions + * with calls to dma_buf_begin_cpu_access() and dma_buf_end_cpu_access() + * access. + * + * Since for most kernel internal dma-buf accesses need the entire buffer, a + * vmap interface is introduced. Note that on very old 32-bit architectures + * vmalloc space might be limited and result in vmap calls failing. + * + * Interfaces:: + * void \*dma_buf_vmap(struct dma_buf \*dmabuf) + * void dma_buf_vunmap(struct dma_buf \*dmabuf, void \*vaddr) + * + * The vmap call can fail if there is no vmap support in the exporter, or if + * it runs out of vmalloc space. Fallback to kmap should be implemented. Note + * that the dma-buf layer keeps a reference count for all vmap access and + * calls down into the exporter's vmap function only when no vmapping exists, + * and only unmaps it once. Protection against concurrent vmap/vunmap calls is + * provided by taking the dma_buf->lock mutex. + * + * - For full compatibility on the importer side with existing userspace + * interfaces, which might already support mmap'ing buffers. This is needed in + * many processing pipelines (e.g. feeding a software rendered image into a + * hardware pipeline, thumbnail creation, snapshots, ...). Also, Android's ION + * framework already supported this and for DMA buffer file descriptors to + * replace ION buffers mmap support was needed. + * + * There is no special interfaces, userspace simply calls mmap on the dma-buf + * fd. But like for CPU access there's a need to braket the actual access, + * which is handled by the ioctl (DMA_BUF_IOCTL_SYNC). Note that + * DMA_BUF_IOCTL_SYNC can fail with -EAGAIN or -EINTR, in which case it must + * be restarted. + * + * Some systems might need some sort of cache coherency management e.g. when + * CPU and GPU domains are being accessed through dma-buf at the same time. + * To circumvent this problem there are begin/end coherency markers, that + * forward directly to existing dma-buf device drivers vfunc hooks. Userspace + * can make use of those markers through the DMA_BUF_IOCTL_SYNC ioctl. The + * sequence would be used like following: + * + * - mmap dma-buf fd + * - for each drawing/upload cycle in CPU 1. SYNC_START ioctl, 2. read/write + * to mmap area 3. SYNC_END ioctl. This can be repeated as often as you + * want (with the new data being consumed by say the GPU or the scanout + * device) + * - munmap once you don't need the buffer any more + * + * For correctness and optimal performance, it is always required to use + * SYNC_START and SYNC_END before and after, respectively, when accessing the + * mapped address. Userspace cannot rely on coherent access, even when there + * are systems where it just works without calling these ioctls. + * + * - And as a CPU fallback in userspace processing pipelines. + * + * Similar to the motivation for kernel cpu access it is again important that + * the userspace code of a given importing subsystem can use the same + * interfaces with a imported dma-buf buffer object as with a native buffer + * object. This is especially important for drm where the userspace part of + * contemporary OpenGL, X, and other drivers is huge, and reworking them to + * use a different way to mmap a buffer rather invasive. + * + * The assumption in the current dma-buf interfaces is that redirecting the + * initial mmap is all that's needed. A survey of some of the existing + * subsystems shows that no driver seems to do any nefarious thing like + * syncing up with outstanding asynchronous processing on the device or + * allocating special resources at fault time. So hopefully this is good + * enough, since adding interfaces to intercept pagefaults and allow pte + * shootdowns would increase the complexity quite a bit. + * + * Interface:: + * int dma_buf_mmap(struct dma_buf \*, struct vm_area_struct \*, + * unsigned long); + * + * If the importing subsystem simply provides a special-purpose mmap call to + * set up a mapping in userspace, calling do_mmap with dma_buf->file will + * equally achieve that for a dma-buf object. + */ + +static int __dma_buf_begin_cpu_access(struct dma_buf *dmabuf, + enum dma_data_direction direction) +{ + bool write = (direction == DMA_BIDIRECTIONAL || + direction == DMA_TO_DEVICE); + struct dma_resv *resv = dmabuf->resv; + long ret; + + /* Wait on any implicit rendering fences */ + ret = dma_resv_wait_timeout_rcu(resv, write, true, + MAX_SCHEDULE_TIMEOUT); + if (ret < 0) + return ret; + + return 0; +} + +/** + * dma_buf_begin_cpu_access - Must be called before accessing a dma_buf from the + * cpu in the kernel context. Calls begin_cpu_access to allow exporter-specific + * preparations. Coherency is only guaranteed in the specified range for the + * specified access direction. + * @dmabuf: [in] buffer to prepare cpu access for. + * @direction: [in] length of range for cpu access. + * + * After the cpu access is complete the caller should call + * dma_buf_end_cpu_access(). Only when cpu access is braketed by both calls is + * it guaranteed to be coherent with other DMA access. + * + * Can return negative error values, returns 0 on success. + */ +int dma_buf_begin_cpu_access(struct dma_buf *dmabuf, + enum dma_data_direction direction) +{ + int ret = 0; + + if (WARN_ON(!dmabuf)) + return -EINVAL; + + if (dmabuf->ops->begin_cpu_access) + ret = dmabuf->ops->begin_cpu_access(dmabuf, direction); + + /* Ensure that all fences are waited upon - but we first allow + * the native handler the chance to do so more efficiently if it + * chooses. A double invocation here will be reasonably cheap no-op. + */ + if (ret == 0) + ret = __dma_buf_begin_cpu_access(dmabuf, direction); + + return ret; +} +EXPORT_SYMBOL_GPL(dma_buf_begin_cpu_access); + +/** + * dma_buf_end_cpu_access - Must be called after accessing a dma_buf from the + * cpu in the kernel context. Calls end_cpu_access to allow exporter-specific + * actions. Coherency is only guaranteed in the specified range for the + * specified access direction. + * @dmabuf: [in] buffer to complete cpu access for. + * @direction: [in] length of range for cpu access. + * + * This terminates CPU access started with dma_buf_begin_cpu_access(). + * + * Can return negative error values, returns 0 on success. + */ +int dma_buf_end_cpu_access(struct dma_buf *dmabuf, + enum dma_data_direction direction) +{ + int ret = 0; + + WARN_ON(!dmabuf); + + if (dmabuf->ops->end_cpu_access) + ret = dmabuf->ops->end_cpu_access(dmabuf, direction); + + return ret; +} +EXPORT_SYMBOL_GPL(dma_buf_end_cpu_access); + + +/** + * dma_buf_mmap - Setup up a userspace mmap with the given vma + * @dmabuf: [in] buffer that should back the vma + * @vma: [in] vma for the mmap + * @pgoff: [in] offset in pages where this mmap should start within the + * dma-buf buffer. + * + * This function adjusts the passed in vma so that it points at the file of the + * dma_buf operation. It also adjusts the starting pgoff and does bounds + * checking on the size of the vma. Then it calls the exporters mmap function to + * set up the mapping. + * + * Can return negative error values, returns 0 on success. + */ +int dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma, + unsigned long pgoff) +{ + struct file *oldfile; + int ret; + + if (WARN_ON(!dmabuf || !vma)) + return -EINVAL; + + /* check if buffer supports mmap */ + if (!dmabuf->ops->mmap) + return -EINVAL; + + /* check for offset overflow */ + if (pgoff + vma_pages(vma) < pgoff) + return -EOVERFLOW; + + /* check for overflowing the buffer's size */ + if (pgoff + vma_pages(vma) > + dmabuf->size >> PAGE_SHIFT) + return -EINVAL; + + /* readjust the vma */ + get_file(dmabuf->file); + oldfile = vma->vm_file; + vma->vm_file = dmabuf->file; + vma->vm_pgoff = pgoff; + + ret = dmabuf->ops->mmap(dmabuf, vma); + if (ret) { + /* restore old parameters on failure */ + vma->vm_file = oldfile; + fput(dmabuf->file); + } else { + if (oldfile) + fput(oldfile); + } + return ret; + +} +EXPORT_SYMBOL_GPL(dma_buf_mmap); + +/** + * dma_buf_vmap - Create virtual mapping for the buffer object into kernel + * address space. Same restrictions as for vmap and friends apply. + * @dmabuf: [in] buffer to vmap + * + * This call may fail due to lack of virtual mapping address space. + * These calls are optional in drivers. The intended use for them + * is for mapping objects linear in kernel space for high use objects. + * Please attempt to use kmap/kunmap before thinking about these interfaces. + * + * Returns NULL on error. + */ +void *dma_buf_vmap(struct dma_buf *dmabuf) +{ + void *ptr; + + if (WARN_ON(!dmabuf)) + return NULL; + + if (!dmabuf->ops->vmap) + return NULL; + + mutex_lock(&dmabuf->lock); + if (dmabuf->vmapping_counter) { + dmabuf->vmapping_counter++; + BUG_ON(!dmabuf->vmap_ptr); + ptr = dmabuf->vmap_ptr; + goto out_unlock; + } + + BUG_ON(dmabuf->vmap_ptr); + + ptr = dmabuf->ops->vmap(dmabuf); + if (WARN_ON_ONCE(IS_ERR(ptr))) + ptr = NULL; + if (!ptr) + goto out_unlock; + + dmabuf->vmap_ptr = ptr; + dmabuf->vmapping_counter = 1; + +out_unlock: + mutex_unlock(&dmabuf->lock); + return ptr; +} +EXPORT_SYMBOL_GPL(dma_buf_vmap); + +/** + * dma_buf_vunmap - Unmap a vmap obtained by dma_buf_vmap. + * @dmabuf: [in] buffer to vunmap + * @vaddr: [in] vmap to vunmap + */ +void dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr) +{ + if (WARN_ON(!dmabuf)) + return; + + BUG_ON(!dmabuf->vmap_ptr); + BUG_ON(dmabuf->vmapping_counter == 0); + BUG_ON(dmabuf->vmap_ptr != vaddr); + + mutex_lock(&dmabuf->lock); + if (--dmabuf->vmapping_counter == 0) { + if (dmabuf->ops->vunmap) + dmabuf->ops->vunmap(dmabuf, vaddr); + dmabuf->vmap_ptr = NULL; + } + mutex_unlock(&dmabuf->lock); +} +EXPORT_SYMBOL_GPL(dma_buf_vunmap); + +#ifdef CONFIG_DEBUG_FS +static int dma_buf_debug_show(struct seq_file *s, void *unused) +{ + int ret; + struct dma_buf *buf_obj; + struct dma_buf_attachment *attach_obj; + struct dma_resv *robj; + struct dma_resv_list *fobj; + struct dma_fence *fence; + unsigned seq; + int count = 0, attach_count, shared_count, i; + size_t size = 0; + + ret = mutex_lock_interruptible(&db_list.lock); + + if (ret) + return ret; + + seq_puts(s, "\nDma-buf Objects:\n"); + seq_printf(s, "%-8s\t%-8s\t%-8s\t%-8s\texp_name\t%-8s\n", + "size", "flags", "mode", "count", "ino"); + + list_for_each_entry(buf_obj, &db_list.head, list_node) { + + ret = dma_resv_lock_interruptible(buf_obj->resv, NULL); + if (ret) + goto error_unlock; + + seq_printf(s, "%08zu\t%08x\t%08x\t%08ld\t%s\t%08lu\t%s\n", + buf_obj->size, + buf_obj->file->f_flags, buf_obj->file->f_mode, + file_count(buf_obj->file), + buf_obj->exp_name, + file_inode(buf_obj->file)->i_ino, + buf_obj->name ?: ""); + + robj = buf_obj->resv; + while (true) { + seq = read_seqcount_begin(&robj->seq); + rcu_read_lock(); + fobj = rcu_dereference(robj->fence); + shared_count = fobj ? fobj->shared_count : 0; + fence = rcu_dereference(robj->fence_excl); + if (!read_seqcount_retry(&robj->seq, seq)) + break; + rcu_read_unlock(); + } + + if (fence) + seq_printf(s, "\tExclusive fence: %s %s %ssignalled\n", + fence->ops->get_driver_name(fence), + fence->ops->get_timeline_name(fence), + dma_fence_is_signaled(fence) ? "" : "un"); + for (i = 0; i < shared_count; i++) { + fence = rcu_dereference(fobj->shared[i]); + if (!dma_fence_get_rcu(fence)) + continue; + seq_printf(s, "\tShared fence: %s %s %ssignalled\n", + fence->ops->get_driver_name(fence), + fence->ops->get_timeline_name(fence), + dma_fence_is_signaled(fence) ? "" : "un"); + dma_fence_put(fence); + } + rcu_read_unlock(); + + seq_puts(s, "\tAttached Devices:\n"); + attach_count = 0; + + list_for_each_entry(attach_obj, &buf_obj->attachments, node) { + seq_printf(s, "\t%s\n", dev_name(attach_obj->dev)); + attach_count++; + } + dma_resv_unlock(buf_obj->resv); + + seq_printf(s, "Total %d devices attached\n\n", + attach_count); + + count++; + size += buf_obj->size; + } + + seq_printf(s, "\nTotal %d objects, %zu bytes\n", count, size); + + mutex_unlock(&db_list.lock); + return 0; + +error_unlock: + mutex_unlock(&db_list.lock); + return ret; +} + +DEFINE_SHOW_ATTRIBUTE(dma_buf_debug); + +static struct dentry *dma_buf_debugfs_dir; + +static int dma_buf_init_debugfs(void) +{ + struct dentry *d; + int err = 0; + + d = debugfs_create_dir("dma_buf", NULL); + if (IS_ERR(d)) + return PTR_ERR(d); + + dma_buf_debugfs_dir = d; + + d = debugfs_create_file("bufinfo", S_IRUGO, dma_buf_debugfs_dir, + NULL, &dma_buf_debug_fops); + if (IS_ERR(d)) { + pr_debug("dma_buf: debugfs: failed to create node bufinfo\n"); + debugfs_remove_recursive(dma_buf_debugfs_dir); + dma_buf_debugfs_dir = NULL; + err = PTR_ERR(d); + } + + return err; +} + +static void dma_buf_uninit_debugfs(void) +{ + debugfs_remove_recursive(dma_buf_debugfs_dir); +} +#else +static inline int dma_buf_init_debugfs(void) +{ + return 0; +} +static inline void dma_buf_uninit_debugfs(void) +{ +} +#endif + +static int __init dma_buf_init(void) +{ + dma_buf_mnt = kern_mount(&dma_buf_fs_type); + if (IS_ERR(dma_buf_mnt)) + return PTR_ERR(dma_buf_mnt); + + mutex_init(&db_list.lock); + INIT_LIST_HEAD(&db_list.head); + dma_buf_init_debugfs(); + return 0; +} +subsys_initcall(dma_buf_init); + +static void __exit dma_buf_deinit(void) +{ + dma_buf_uninit_debugfs(); + kern_unmount(dma_buf_mnt); +} +__exitcall(dma_buf_deinit); diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c new file mode 100644 index 000000000..3e07f961e --- /dev/null +++ b/drivers/dma-buf/dma-fence-array.c @@ -0,0 +1,207 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * dma-fence-array: aggregate fences to be waited together + * + * Copyright (C) 2016 Collabora Ltd + * Copyright (C) 2016 Advanced Micro Devices, Inc. + * Authors: + * Gustavo Padovan <gustavo@padovan.org> + * Christian König <christian.koenig@amd.com> + */ + +#include <linux/export.h> +#include <linux/slab.h> +#include <linux/dma-fence-array.h> + +#define PENDING_ERROR 1 + +static const char *dma_fence_array_get_driver_name(struct dma_fence *fence) +{ + return "dma_fence_array"; +} + +static const char *dma_fence_array_get_timeline_name(struct dma_fence *fence) +{ + return "unbound"; +} + +static void dma_fence_array_set_pending_error(struct dma_fence_array *array, + int error) +{ + /* + * Propagate the first error reported by any of our fences, but only + * before we ourselves are signaled. + */ + if (error) + cmpxchg(&array->base.error, PENDING_ERROR, error); +} + +static void dma_fence_array_clear_pending_error(struct dma_fence_array *array) +{ + /* Clear the error flag if not actually set. */ + cmpxchg(&array->base.error, PENDING_ERROR, 0); +} + +static void irq_dma_fence_array_work(struct irq_work *wrk) +{ + struct dma_fence_array *array = container_of(wrk, typeof(*array), work); + + dma_fence_array_clear_pending_error(array); + + dma_fence_signal(&array->base); + dma_fence_put(&array->base); +} + +static void dma_fence_array_cb_func(struct dma_fence *f, + struct dma_fence_cb *cb) +{ + struct dma_fence_array_cb *array_cb = + container_of(cb, struct dma_fence_array_cb, cb); + struct dma_fence_array *array = array_cb->array; + + dma_fence_array_set_pending_error(array, f->error); + + if (atomic_dec_and_test(&array->num_pending)) + irq_work_queue(&array->work); + else + dma_fence_put(&array->base); +} + +static bool dma_fence_array_enable_signaling(struct dma_fence *fence) +{ + struct dma_fence_array *array = to_dma_fence_array(fence); + struct dma_fence_array_cb *cb = (void *)(&array[1]); + unsigned i; + + for (i = 0; i < array->num_fences; ++i) { + cb[i].array = array; + /* + * As we may report that the fence is signaled before all + * callbacks are complete, we need to take an additional + * reference count on the array so that we do not free it too + * early. The core fence handling will only hold the reference + * until we signal the array as complete (but that is now + * insufficient). + */ + dma_fence_get(&array->base); + if (dma_fence_add_callback(array->fences[i], &cb[i].cb, + dma_fence_array_cb_func)) { + int error = array->fences[i]->error; + + dma_fence_array_set_pending_error(array, error); + dma_fence_put(&array->base); + if (atomic_dec_and_test(&array->num_pending)) { + dma_fence_array_clear_pending_error(array); + return false; + } + } + } + + return true; +} + +static bool dma_fence_array_signaled(struct dma_fence *fence) +{ + struct dma_fence_array *array = to_dma_fence_array(fence); + + 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) +{ + struct dma_fence_array *array = to_dma_fence_array(fence); + unsigned i; + + for (i = 0; i < array->num_fences; ++i) + dma_fence_put(array->fences[i]); + + kfree(array->fences); + dma_fence_free(fence); +} + +const struct dma_fence_ops dma_fence_array_ops = { + .get_driver_name = dma_fence_array_get_driver_name, + .get_timeline_name = dma_fence_array_get_timeline_name, + .enable_signaling = dma_fence_array_enable_signaling, + .signaled = dma_fence_array_signaled, + .release = dma_fence_array_release, +}; +EXPORT_SYMBOL(dma_fence_array_ops); + +/** + * dma_fence_array_create - Create a custom fence array + * @num_fences: [in] number of fences to add in the array + * @fences: [in] array containing the fences + * @context: [in] fence context to use + * @seqno: [in] sequence number to use + * @signal_on_any: [in] signal on any fence in the array + * + * Allocate a dma_fence_array object and initialize the base fence with + * dma_fence_init(). + * In case of error it returns NULL. + * + * The caller should allocate the fences array with num_fences size + * and fill it with the fences it wants to add to the object. Ownership of this + * array is taken and dma_fence_put() is used on each fence on release. + * + * If @signal_on_any is true the fence array signals if any fence in the array + * signals, otherwise it signals when all fences in the array signal. + */ +struct dma_fence_array *dma_fence_array_create(int num_fences, + struct dma_fence **fences, + u64 context, unsigned seqno, + bool signal_on_any) +{ + struct dma_fence_array *array; + size_t size = sizeof(*array); + + /* Allocate the callback structures behind the array. */ + size += num_fences * sizeof(struct dma_fence_array_cb); + array = kzalloc(size, GFP_KERNEL); + if (!array) + return NULL; + + spin_lock_init(&array->lock); + dma_fence_init(&array->base, &dma_fence_array_ops, &array->lock, + context, seqno); + init_irq_work(&array->work, irq_dma_fence_array_work); + + array->num_fences = num_fences; + atomic_set(&array->num_pending, signal_on_any ? 1 : num_fences); + array->fences = fences; + + array->base.error = PENDING_ERROR; + + return array; +} +EXPORT_SYMBOL(dma_fence_array_create); + +/** + * dma_fence_match_context - Check if all fences are from the given context + * @fence: [in] fence or fence array + * @context: [in] fence context to check all fences against + * + * Checks the provided fence or, for a fence array, all fences in the array + * against the given context. Returns false if any fence is from a different + * context. + */ +bool dma_fence_match_context(struct dma_fence *fence, u64 context) +{ + struct dma_fence_array *array = to_dma_fence_array(fence); + unsigned i; + + if (!dma_fence_is_array(fence)) + return fence->context == context; + + for (i = 0; i < array->num_fences; i++) { + if (array->fences[i]->context != context) + return false; + } + + return true; +} +EXPORT_SYMBOL(dma_fence_match_context); diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c new file mode 100644 index 000000000..7d129e68a --- /dev/null +++ b/drivers/dma-buf/dma-fence-chain.c @@ -0,0 +1,258 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * fence-chain: chain fences together in a timeline + * + * Copyright (C) 2018 Advanced Micro Devices, Inc. + * Authors: + * Christian König <christian.koenig@amd.com> + */ + +#include <linux/dma-fence-chain.h> + +static bool dma_fence_chain_enable_signaling(struct dma_fence *fence); + +/** + * dma_fence_chain_get_prev - use RCU to get a reference to the previous fence + * @chain: chain node to get the previous node from + * + * Use dma_fence_get_rcu_safe to get a reference to the previous fence of the + * chain node. + */ +static struct dma_fence *dma_fence_chain_get_prev(struct dma_fence_chain *chain) +{ + struct dma_fence *prev; + + rcu_read_lock(); + prev = dma_fence_get_rcu_safe(&chain->prev); + rcu_read_unlock(); + return prev; +} + +/** + * dma_fence_chain_walk - chain walking function + * @fence: current chain node + * + * Walk the chain to the next node. Returns the next fence or NULL if we are at + * the end of the chain. Garbage collects chain nodes which are already + * signaled. + */ +struct dma_fence *dma_fence_chain_walk(struct dma_fence *fence) +{ + struct dma_fence_chain *chain, *prev_chain; + struct dma_fence *prev, *replacement, *tmp; + + chain = to_dma_fence_chain(fence); + if (!chain) { + dma_fence_put(fence); + return NULL; + } + + while ((prev = dma_fence_chain_get_prev(chain))) { + + prev_chain = to_dma_fence_chain(prev); + if (prev_chain) { + if (!dma_fence_is_signaled(prev_chain->fence)) + break; + + replacement = dma_fence_chain_get_prev(prev_chain); + } else { + if (!dma_fence_is_signaled(prev)) + break; + + replacement = NULL; + } + + tmp = cmpxchg((struct dma_fence __force **)&chain->prev, + prev, replacement); + if (tmp == prev) + dma_fence_put(tmp); + else + dma_fence_put(replacement); + dma_fence_put(prev); + } + + dma_fence_put(fence); + return prev; +} +EXPORT_SYMBOL(dma_fence_chain_walk); + +/** + * dma_fence_chain_find_seqno - find fence chain node by seqno + * @pfence: pointer to the chain node where to start + * @seqno: the sequence number to search for + * + * Advance the fence pointer to the chain node which will signal this sequence + * number. If no sequence number is provided then this is a no-op. + * + * Returns EINVAL if the fence is not a chain node or the sequence number has + * not yet advanced far enough. + */ +int dma_fence_chain_find_seqno(struct dma_fence **pfence, uint64_t seqno) +{ + struct dma_fence_chain *chain; + + if (!seqno) + return 0; + + chain = to_dma_fence_chain(*pfence); + if (!chain || chain->base.seqno < seqno) + return -EINVAL; + + dma_fence_chain_for_each(*pfence, &chain->base) { + if ((*pfence)->context != chain->base.context || + to_dma_fence_chain(*pfence)->prev_seqno < seqno) + break; + } + dma_fence_put(&chain->base); + + return 0; +} +EXPORT_SYMBOL(dma_fence_chain_find_seqno); + +static const char *dma_fence_chain_get_driver_name(struct dma_fence *fence) +{ + return "dma_fence_chain"; +} + +static const char *dma_fence_chain_get_timeline_name(struct dma_fence *fence) +{ + return "unbound"; +} + +static void dma_fence_chain_irq_work(struct irq_work *work) +{ + struct dma_fence_chain *chain; + + chain = container_of(work, typeof(*chain), work); + + /* Try to rearm the callback */ + if (!dma_fence_chain_enable_signaling(&chain->base)) + /* Ok, we are done. No more unsignaled fences left */ + dma_fence_signal(&chain->base); + dma_fence_put(&chain->base); +} + +static void dma_fence_chain_cb(struct dma_fence *f, struct dma_fence_cb *cb) +{ + struct dma_fence_chain *chain; + + chain = container_of(cb, typeof(*chain), cb); + irq_work_queue(&chain->work); + dma_fence_put(f); +} + +static bool dma_fence_chain_enable_signaling(struct dma_fence *fence) +{ + struct dma_fence_chain *head = to_dma_fence_chain(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; + + dma_fence_get(f); + if (!dma_fence_add_callback(f, &head->cb, dma_fence_chain_cb)) { + dma_fence_put(fence); + return true; + } + dma_fence_put(f); + } + dma_fence_put(&head->base); + return false; +} + +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; + + if (!dma_fence_is_signaled(f)) { + dma_fence_put(fence); + return false; + } + } + + return true; +} + +static void dma_fence_chain_release(struct dma_fence *fence) +{ + struct dma_fence_chain *chain = to_dma_fence_chain(fence); + struct dma_fence *prev; + + /* Manually unlink the chain as much as possible to avoid recursion + * and potential stack overflow. + */ + while ((prev = rcu_dereference_protected(chain->prev, true))) { + struct dma_fence_chain *prev_chain; + + if (kref_read(&prev->refcount) > 1) + break; + + prev_chain = to_dma_fence_chain(prev); + if (!prev_chain) + break; + + /* No need for atomic operations since we hold the last + * reference to prev_chain. + */ + chain->prev = prev_chain->prev; + RCU_INIT_POINTER(prev_chain->prev, NULL); + dma_fence_put(prev); + } + dma_fence_put(prev); + + dma_fence_put(chain->fence); + dma_fence_free(fence); +} + +const struct dma_fence_ops dma_fence_chain_ops = { + .use_64bit_seqno = true, + .get_driver_name = dma_fence_chain_get_driver_name, + .get_timeline_name = dma_fence_chain_get_timeline_name, + .enable_signaling = dma_fence_chain_enable_signaling, + .signaled = dma_fence_chain_signaled, + .release = dma_fence_chain_release, +}; +EXPORT_SYMBOL(dma_fence_chain_ops); + +/** + * dma_fence_chain_init - initialize a fence chain + * @chain: the chain node to initialize + * @prev: the previous fence + * @fence: the current fence + * @seqno: the sequence number to use for the fence chain + * + * Initialize a new chain node and either start a new chain or add the node to + * the existing chain of the previous fence. + */ +void dma_fence_chain_init(struct dma_fence_chain *chain, + struct dma_fence *prev, + struct dma_fence *fence, + uint64_t seqno) +{ + struct dma_fence_chain *prev_chain = to_dma_fence_chain(prev); + uint64_t context; + + spin_lock_init(&chain->lock); + rcu_assign_pointer(chain->prev, prev); + chain->fence = fence; + chain->prev_seqno = 0; + init_irq_work(&chain->work, dma_fence_chain_irq_work); + + /* Try to reuse the context of the previous chain node. */ + if (prev_chain && __dma_fence_is_later(seqno, prev->seqno, prev->ops)) { + context = prev->context; + chain->prev_seqno = prev->seqno; + } else { + context = dma_fence_context_alloc(1); + /* Make sure that we always have a valid sequence number. */ + if (prev_chain) + seqno = max(prev->seqno, seqno); + } + + dma_fence_init(&chain->base, &dma_fence_chain_ops, + &chain->lock, context, seqno); +} +EXPORT_SYMBOL(dma_fence_chain_init); diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c new file mode 100644 index 000000000..7475e09b0 --- /dev/null +++ b/drivers/dma-buf/dma-fence.c @@ -0,0 +1,865 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Fence mechanism for dma-buf and to allow for asynchronous dma access + * + * Copyright (C) 2012 Canonical Ltd + * Copyright (C) 2012 Texas Instruments + * + * Authors: + * Rob Clark <robdclark@gmail.com> + * Maarten Lankhorst <maarten.lankhorst@canonical.com> + */ + +#include <linux/slab.h> +#include <linux/export.h> +#include <linux/atomic.h> +#include <linux/dma-fence.h> +#include <linux/sched/signal.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/dma_fence.h> + +EXPORT_TRACEPOINT_SYMBOL(dma_fence_emit); +EXPORT_TRACEPOINT_SYMBOL(dma_fence_enable_signal); +EXPORT_TRACEPOINT_SYMBOL(dma_fence_signaled); + +static DEFINE_SPINLOCK(dma_fence_stub_lock); +static struct dma_fence dma_fence_stub; + +/* + * fence context counter: each execution context should have its own + * fence context, this allows checking if fences belong to the same + * context or not. One device can have multiple separate contexts, + * and they're used if some engine can run independently of another. + */ +static atomic64_t dma_fence_context_counter = ATOMIC64_INIT(1); + +/** + * DOC: DMA fences overview + * + * DMA fences, represented by &struct dma_fence, are the kernel internal + * synchronization primitive for DMA operations like GPU rendering, video + * encoding/decoding, or displaying buffers on a screen. + * + * A fence is initialized using dma_fence_init() and completed using + * dma_fence_signal(). Fences are associated with a context, allocated through + * dma_fence_context_alloc(), and all fences on the same context are + * fully ordered. + * + * Since the purposes of fences is to facilitate cross-device and + * cross-application synchronization, there's multiple ways to use one: + * + * - Individual fences can be exposed as a &sync_file, accessed as a file + * descriptor from userspace, created by calling sync_file_create(). This is + * called explicit fencing, since userspace passes around explicit + * synchronization points. + * + * - Some subsystems also have their own explicit fencing primitives, like + * &drm_syncobj. Compared to &sync_file, a &drm_syncobj allows the underlying + * fence to be updated. + * + * - Then there's also implicit fencing, where the synchronization points are + * implicitly passed around as part of shared &dma_buf instances. Such + * implicit fences are stored in &struct dma_resv through the + * &dma_buf.resv pointer. + */ + +/** + * DOC: fence cross-driver contract + * + * Since &dma_fence provide a cross driver contract, all drivers must follow the + * same rules: + * + * * Fences must complete in a reasonable time. Fences which represent kernels + * and shaders submitted by userspace, which could run forever, must be backed + * up by timeout and gpu hang recovery code. Minimally that code must prevent + * further command submission and force complete all in-flight fences, e.g. + * when the driver or hardware do not support gpu reset, or if the gpu reset + * failed for some reason. Ideally the driver supports gpu recovery which only + * affects the offending userspace context, and no other userspace + * submissions. + * + * * Drivers may have different ideas of what completion within a reasonable + * time means. Some hang recovery code uses a fixed timeout, others a mix + * between observing forward progress and increasingly strict timeouts. + * Drivers should not try to second guess timeout handling of fences from + * other drivers. + * + * * To ensure there's no deadlocks of dma_fence_wait() against other locks + * drivers should annotate all code required to reach dma_fence_signal(), + * which completes the fences, with dma_fence_begin_signalling() and + * dma_fence_end_signalling(). + * + * * Drivers are allowed to call dma_fence_wait() while holding dma_resv_lock(). + * This means any code required for fence completion cannot acquire a + * &dma_resv lock. Note that this also pulls in the entire established + * locking hierarchy around dma_resv_lock() and dma_resv_unlock(). + * + * * Drivers are allowed to call dma_fence_wait() from their &shrinker + * callbacks. This means any code required for fence completion cannot + * allocate memory with GFP_KERNEL. + * + * * Drivers are allowed to call dma_fence_wait() from their &mmu_notifier + * respectively &mmu_interval_notifier callbacks. This means any code required + * for fence completeion cannot allocate memory with GFP_NOFS or GFP_NOIO. + * Only GFP_ATOMIC is permissible, which might fail. + * + * Note that only GPU drivers have a reasonable excuse for both requiring + * &mmu_interval_notifier and &shrinker callbacks at the same time as having to + * track asynchronous compute work using &dma_fence. No driver outside of + * drivers/gpu should ever call dma_fence_wait() in such contexts. + */ + +static const char *dma_fence_stub_get_name(struct dma_fence *fence) +{ + return "stub"; +} + +static const struct dma_fence_ops dma_fence_stub_ops = { + .get_driver_name = dma_fence_stub_get_name, + .get_timeline_name = dma_fence_stub_get_name, +}; + +/** + * dma_fence_get_stub - return a signaled fence + * + * Return a stub fence which is already signaled. + */ +struct dma_fence *dma_fence_get_stub(void) +{ + spin_lock(&dma_fence_stub_lock); + if (!dma_fence_stub.ops) { + dma_fence_init(&dma_fence_stub, + &dma_fence_stub_ops, + &dma_fence_stub_lock, + 0, 0); + dma_fence_signal_locked(&dma_fence_stub); + } + spin_unlock(&dma_fence_stub_lock); + + return dma_fence_get(&dma_fence_stub); +} +EXPORT_SYMBOL(dma_fence_get_stub); + +/** + * dma_fence_context_alloc - allocate an array of fence contexts + * @num: amount of contexts to allocate + * + * This function will return the first index of the number of fence contexts + * allocated. The fence context is used for setting &dma_fence.context to a + * unique number by passing the context to dma_fence_init(). + */ +u64 dma_fence_context_alloc(unsigned num) +{ + WARN_ON(!num); + return atomic64_fetch_add(num, &dma_fence_context_counter); +} +EXPORT_SYMBOL(dma_fence_context_alloc); + +/** + * DOC: fence signalling annotation + * + * Proving correctness of all the kernel code around &dma_fence through code + * review and testing is tricky for a few reasons: + * + * * It is a cross-driver contract, and therefore all drivers must follow the + * same rules for lock nesting order, calling contexts for various functions + * and anything else significant for in-kernel interfaces. But it is also + * impossible to test all drivers in a single machine, hence brute-force N vs. + * N testing of all combinations is impossible. Even just limiting to the + * possible combinations is infeasible. + * + * * There is an enormous amount of driver code involved. For render drivers + * there's the tail of command submission, after fences are published, + * scheduler code, interrupt and workers to process job completion, + * and timeout, gpu reset and gpu hang recovery code. Plus for integration + * with core mm with have &mmu_notifier, respectively &mmu_interval_notifier, + * and &shrinker. For modesetting drivers there's the commit tail functions + * between when fences for an atomic modeset are published, and when the + * corresponding vblank completes, including any interrupt processing and + * related workers. Auditing all that code, across all drivers, is not + * feasible. + * + * * Due to how many other subsystems are involved and the locking hierarchies + * this pulls in there is extremely thin wiggle-room for driver-specific + * differences. &dma_fence interacts with almost all of the core memory + * handling through page fault handlers via &dma_resv, dma_resv_lock() and + * dma_resv_unlock(). On the other side it also interacts through all + * allocation sites through &mmu_notifier and &shrinker. + * + * Furthermore lockdep does not handle cross-release dependencies, which means + * any deadlocks between dma_fence_wait() and dma_fence_signal() can't be caught + * at runtime with some quick testing. The simplest example is one thread + * waiting on a &dma_fence while holding a lock:: + * + * lock(A); + * dma_fence_wait(B); + * unlock(A); + * + * while the other thread is stuck trying to acquire the same lock, which + * prevents it from signalling the fence the previous thread is stuck waiting + * on:: + * + * lock(A); + * unlock(A); + * dma_fence_signal(B); + * + * By manually annotating all code relevant to signalling a &dma_fence we can + * teach lockdep about these dependencies, which also helps with the validation + * headache since now lockdep can check all the rules for us:: + * + * cookie = dma_fence_begin_signalling(); + * lock(A); + * unlock(A); + * dma_fence_signal(B); + * dma_fence_end_signalling(cookie); + * + * For using dma_fence_begin_signalling() and dma_fence_end_signalling() to + * annotate critical sections the following rules need to be observed: + * + * * All code necessary to complete a &dma_fence must be annotated, from the + * point where a fence is accessible to other threads, to the point where + * dma_fence_signal() is called. Un-annotated code can contain deadlock issues, + * and due to the very strict rules and many corner cases it is infeasible to + * catch these just with review or normal stress testing. + * + * * &struct dma_resv deserves a special note, since the readers are only + * protected by rcu. This means the signalling critical section starts as soon + * as the new fences are installed, even before dma_resv_unlock() is called. + * + * * The only exception are fast paths and opportunistic signalling code, which + * calls dma_fence_signal() purely as an optimization, but is not required to + * guarantee completion of a &dma_fence. The usual example is a wait IOCTL + * which calls dma_fence_signal(), while the mandatory completion path goes + * through a hardware interrupt and possible job completion worker. + * + * * To aid composability of code, the annotations can be freely nested, as long + * as the overall locking hierarchy is consistent. The annotations also work + * both in interrupt and process context. Due to implementation details this + * requires that callers pass an opaque cookie from + * dma_fence_begin_signalling() to dma_fence_end_signalling(). + * + * * Validation against the cross driver contract is implemented by priming + * lockdep with the relevant hierarchy at boot-up. This means even just + * testing with a single device is enough to validate a driver, at least as + * far as deadlocks with dma_fence_wait() against dma_fence_signal() are + * concerned. + */ +#ifdef CONFIG_LOCKDEP +static struct lockdep_map dma_fence_lockdep_map = { + .name = "dma_fence_map" +}; + +/** + * dma_fence_begin_signalling - begin a critical DMA fence signalling section + * + * Drivers should use this to annotate the beginning of any code section + * required to eventually complete &dma_fence by calling dma_fence_signal(). + * + * The end of these critical sections are annotated with + * dma_fence_end_signalling(). + * + * Returns: + * + * Opaque cookie needed by the implementation, which needs to be passed to + * dma_fence_end_signalling(). + */ +bool dma_fence_begin_signalling(void) +{ + /* explicitly nesting ... */ + if (lock_is_held_type(&dma_fence_lockdep_map, 1)) + return true; + + /* rely on might_sleep check for soft/hardirq locks */ + if (in_atomic()) + return true; + + /* ... and non-recursive readlock */ + lock_acquire(&dma_fence_lockdep_map, 0, 0, 1, 1, NULL, _RET_IP_); + + return false; +} +EXPORT_SYMBOL(dma_fence_begin_signalling); + +/** + * dma_fence_end_signalling - end a critical DMA fence signalling section + * @cookie: opaque cookie from dma_fence_begin_signalling() + * + * Closes a critical section annotation opened by dma_fence_begin_signalling(). + */ +void dma_fence_end_signalling(bool cookie) +{ + if (cookie) + return; + + lock_release(&dma_fence_lockdep_map, _RET_IP_); +} +EXPORT_SYMBOL(dma_fence_end_signalling); + +void __dma_fence_might_wait(void) +{ + bool tmp; + + tmp = lock_is_held_type(&dma_fence_lockdep_map, 1); + if (tmp) + lock_release(&dma_fence_lockdep_map, _THIS_IP_); + lock_map_acquire(&dma_fence_lockdep_map); + lock_map_release(&dma_fence_lockdep_map); + if (tmp) + lock_acquire(&dma_fence_lockdep_map, 0, 0, 1, 1, NULL, _THIS_IP_); +} +#endif + + +/** + * dma_fence_signal_locked - signal completion of a fence + * @fence: the fence to signal + * + * Signal completion for software callbacks on a fence, this will unblock + * dma_fence_wait() calls and run all the callbacks added with + * dma_fence_add_callback(). Can be called multiple times, but since a fence + * can only go from the unsignaled to the signaled state and not back, it will + * only be effective the first time. + * + * Unlike dma_fence_signal(), this function must be called with &dma_fence.lock + * held. + * + * Returns 0 on success and a negative error value when @fence has been + * signalled already. + */ +int dma_fence_signal_locked(struct dma_fence *fence) +{ + struct dma_fence_cb *cur, *tmp; + struct list_head cb_list; + + lockdep_assert_held(fence->lock); + + if (unlikely(test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, + &fence->flags))) + return -EINVAL; + + /* Stash the cb_list before replacing it with the timestamp */ + list_replace(&fence->cb_list, &cb_list); + + fence->timestamp = ktime_get(); + set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags); + trace_dma_fence_signaled(fence); + + list_for_each_entry_safe(cur, tmp, &cb_list, node) { + INIT_LIST_HEAD(&cur->node); + cur->func(fence, cur); + } + + return 0; +} +EXPORT_SYMBOL(dma_fence_signal_locked); + +/** + * dma_fence_signal - signal completion of a fence + * @fence: the fence to signal + * + * Signal completion for software callbacks on a fence, this will unblock + * dma_fence_wait() calls and run all the callbacks added with + * dma_fence_add_callback(). Can be called multiple times, but since a fence + * can only go from the unsignaled to the signaled state and not back, it will + * only be effective the first time. + * + * Returns 0 on success and a negative error value when @fence has been + * signalled already. + */ +int dma_fence_signal(struct dma_fence *fence) +{ + unsigned long flags; + int ret; + bool tmp; + + if (!fence) + return -EINVAL; + + tmp = dma_fence_begin_signalling(); + + spin_lock_irqsave(fence->lock, flags); + ret = dma_fence_signal_locked(fence); + spin_unlock_irqrestore(fence->lock, flags); + + dma_fence_end_signalling(tmp); + + return ret; +} +EXPORT_SYMBOL(dma_fence_signal); + +/** + * dma_fence_wait_timeout - sleep until the fence gets signaled + * or until timeout elapses + * @fence: the fence to wait on + * @intr: if true, do an interruptible wait + * @timeout: timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT + * + * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or the + * remaining timeout in jiffies on success. Other error values may be + * returned on custom implementations. + * + * Performs a synchronous wait on this fence. It is assumed the caller + * directly or indirectly (buf-mgr between reservation and committing) + * holds a reference to the fence, otherwise the fence might be + * freed before return, resulting in undefined behavior. + * + * See also dma_fence_wait() and dma_fence_wait_any_timeout(). + */ +signed long +dma_fence_wait_timeout(struct dma_fence *fence, bool intr, signed long timeout) +{ + signed long ret; + + if (WARN_ON(timeout < 0)) + return -EINVAL; + + might_sleep(); + + __dma_fence_might_wait(); + + trace_dma_fence_wait_start(fence); + if (fence->ops->wait) + ret = fence->ops->wait(fence, intr, timeout); + else + ret = dma_fence_default_wait(fence, intr, timeout); + trace_dma_fence_wait_end(fence); + return ret; +} +EXPORT_SYMBOL(dma_fence_wait_timeout); + +/** + * dma_fence_release - default relese function for fences + * @kref: &dma_fence.recfount + * + * This is the default release functions for &dma_fence. Drivers shouldn't call + * this directly, but instead call dma_fence_put(). + */ +void dma_fence_release(struct kref *kref) +{ + struct dma_fence *fence = + container_of(kref, struct dma_fence, refcount); + + trace_dma_fence_destroy(fence); + + if (WARN(!list_empty(&fence->cb_list) && + !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags), + "Fence %s:%s:%llx:%llx released with pending signals!\n", + fence->ops->get_driver_name(fence), + fence->ops->get_timeline_name(fence), + fence->context, fence->seqno)) { + unsigned long flags; + + /* + * Failed to signal before release, likely a refcounting issue. + * + * This should never happen, but if it does make sure that we + * don't leave chains dangling. We set the error flag first + * so that the callbacks know this signal is due to an error. + */ + spin_lock_irqsave(fence->lock, flags); + fence->error = -EDEADLK; + dma_fence_signal_locked(fence); + spin_unlock_irqrestore(fence->lock, flags); + } + + if (fence->ops->release) + fence->ops->release(fence); + else + dma_fence_free(fence); +} +EXPORT_SYMBOL(dma_fence_release); + +/** + * dma_fence_free - default release function for &dma_fence. + * @fence: fence to release + * + * This is the default implementation for &dma_fence_ops.release. It calls + * kfree_rcu() on @fence. + */ +void dma_fence_free(struct dma_fence *fence) +{ + kfree_rcu(fence, rcu); +} +EXPORT_SYMBOL(dma_fence_free); + +static bool __dma_fence_enable_signaling(struct dma_fence *fence) +{ + bool was_set; + + lockdep_assert_held(fence->lock); + + was_set = test_and_set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, + &fence->flags); + + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return false; + + if (!was_set && fence->ops->enable_signaling) { + trace_dma_fence_enable_signal(fence); + + if (!fence->ops->enable_signaling(fence)) { + dma_fence_signal_locked(fence); + return false; + } + } + + return true; +} + +/** + * dma_fence_enable_sw_signaling - enable signaling on fence + * @fence: the fence to enable + * + * This will request for sw signaling to be enabled, to make the fence + * complete as soon as possible. This calls &dma_fence_ops.enable_signaling + * internally. + */ +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); +} +EXPORT_SYMBOL(dma_fence_enable_sw_signaling); + +/** + * dma_fence_add_callback - add a callback to be called when the fence + * is signaled + * @fence: the fence to wait on + * @cb: the callback to register + * @func: the function to call + * + * @cb will be initialized by dma_fence_add_callback(), no initialization + * by the caller is required. Any number of callbacks can be registered + * to a fence, but a callback can only be registered to one fence at a time. + * + * Note that the callback can be called from an atomic context. If + * fence is already signaled, this function will return -ENOENT (and + * *not* call the callback). + * + * Add a software callback to the fence. Same restrictions apply to + * refcount as it does to dma_fence_wait(), however the caller doesn't need to + * keep a refcount to fence afterward dma_fence_add_callback() has returned: + * when software access is enabled, the creator of the fence is required to keep + * the fence alive until after it signals with dma_fence_signal(). The callback + * itself can be called from irq context. + * + * Returns 0 in case of success, -ENOENT if the fence is already signaled + * and -EINVAL in case of error. + */ +int dma_fence_add_callback(struct dma_fence *fence, struct dma_fence_cb *cb, + dma_fence_func_t func) +{ + unsigned long flags; + int ret = 0; + + if (WARN_ON(!fence || !func)) + return -EINVAL; + + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { + INIT_LIST_HEAD(&cb->node); + return -ENOENT; + } + + spin_lock_irqsave(fence->lock, flags); + + if (__dma_fence_enable_signaling(fence)) { + cb->func = func; + list_add_tail(&cb->node, &fence->cb_list); + } else { + INIT_LIST_HEAD(&cb->node); + ret = -ENOENT; + } + + spin_unlock_irqrestore(fence->lock, flags); + + return ret; +} +EXPORT_SYMBOL(dma_fence_add_callback); + +/** + * dma_fence_get_status - returns the status upon completion + * @fence: the dma_fence to query + * + * This wraps dma_fence_get_status_locked() to return the error status + * condition on a signaled fence. See dma_fence_get_status_locked() for more + * details. + * + * Returns 0 if the fence has not yet been signaled, 1 if the fence has + * been signaled without an error condition, or a negative error code + * if the fence has been completed in err. + */ +int dma_fence_get_status(struct dma_fence *fence) +{ + unsigned long flags; + int status; + + spin_lock_irqsave(fence->lock, flags); + status = dma_fence_get_status_locked(fence); + spin_unlock_irqrestore(fence->lock, flags); + + return status; +} +EXPORT_SYMBOL(dma_fence_get_status); + +/** + * dma_fence_remove_callback - remove a callback from the signaling list + * @fence: the fence to wait on + * @cb: the callback to remove + * + * Remove a previously queued callback from the fence. This function returns + * true if the callback is successfully removed, or false if the fence has + * already been signaled. + * + * *WARNING*: + * Cancelling a callback should only be done if you really know what you're + * doing, since deadlocks and race conditions could occur all too easily. For + * this reason, it should only ever be done on hardware lockup recovery, + * with a reference held to the fence. + * + * Behaviour is undefined if @cb has not been added to @fence using + * dma_fence_add_callback() beforehand. + */ +bool +dma_fence_remove_callback(struct dma_fence *fence, struct dma_fence_cb *cb) +{ + unsigned long flags; + bool ret; + + spin_lock_irqsave(fence->lock, flags); + + ret = !list_empty(&cb->node); + if (ret) + list_del_init(&cb->node); + + spin_unlock_irqrestore(fence->lock, flags); + + return ret; +} +EXPORT_SYMBOL(dma_fence_remove_callback); + +struct default_wait_cb { + struct dma_fence_cb base; + struct task_struct *task; +}; + +static void +dma_fence_default_wait_cb(struct dma_fence *fence, struct dma_fence_cb *cb) +{ + struct default_wait_cb *wait = + container_of(cb, struct default_wait_cb, base); + + wake_up_state(wait->task, TASK_NORMAL); +} + +/** + * dma_fence_default_wait - default sleep until the fence gets signaled + * or until timeout elapses + * @fence: the fence to wait on + * @intr: if true, do an interruptible wait + * @timeout: timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT + * + * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or the + * remaining timeout in jiffies on success. If timeout is zero the value one is + * returned if the fence is already signaled for consistency with other + * functions taking a jiffies timeout. + */ +signed long +dma_fence_default_wait(struct dma_fence *fence, bool intr, signed long timeout) +{ + struct default_wait_cb cb; + 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 (intr && signal_pending(current)) { + ret = -ERESTARTSYS; + goto out; + } + + if (!__dma_fence_enable_signaling(fence)) + goto out; + + if (!timeout) { + ret = 0; + goto out; + } + + cb.base.func = dma_fence_default_wait_cb; + cb.task = current; + list_add(&cb.base.node, &fence->cb_list); + + while (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags) && ret > 0) { + if (intr) + __set_current_state(TASK_INTERRUPTIBLE); + else + __set_current_state(TASK_UNINTERRUPTIBLE); + spin_unlock_irqrestore(fence->lock, flags); + + ret = schedule_timeout(ret); + + spin_lock_irqsave(fence->lock, flags); + if (ret > 0 && intr && signal_pending(current)) + ret = -ERESTARTSYS; + } + + if (!list_empty(&cb.base.node)) + list_del(&cb.base.node); + __set_current_state(TASK_RUNNING); + +out: + spin_unlock_irqrestore(fence->lock, flags); + return ret; +} +EXPORT_SYMBOL(dma_fence_default_wait); + +static bool +dma_fence_test_signaled_any(struct dma_fence **fences, uint32_t count, + uint32_t *idx) +{ + int i; + + for (i = 0; i < count; ++i) { + struct dma_fence *fence = fences[i]; + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { + if (idx) + *idx = i; + return true; + } + } + return false; +} + +/** + * dma_fence_wait_any_timeout - sleep until any fence gets signaled + * or until timeout elapses + * @fences: array of fences to wait on + * @count: number of fences to wait on + * @intr: if true, do an interruptible wait + * @timeout: timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT + * @idx: used to store the first signaled fence index, meaningful only on + * positive return + * + * Returns -EINVAL on custom fence wait implementation, -ERESTARTSYS if + * interrupted, 0 if the wait timed out, or the remaining timeout in jiffies + * on success. + * + * Synchronous waits for the first fence in the array to be signaled. The + * caller needs to hold a reference to all fences in the array, otherwise a + * fence might be freed before return, resulting in undefined behavior. + * + * See also dma_fence_wait() and dma_fence_wait_timeout(). + */ +signed long +dma_fence_wait_any_timeout(struct dma_fence **fences, uint32_t count, + bool intr, signed long timeout, uint32_t *idx) +{ + struct default_wait_cb *cb; + signed long ret = timeout; + unsigned i; + + if (WARN_ON(!fences || !count || timeout < 0)) + return -EINVAL; + + if (timeout == 0) { + for (i = 0; i < count; ++i) + if (dma_fence_is_signaled(fences[i])) { + if (idx) + *idx = i; + return 1; + } + + return 0; + } + + cb = kcalloc(count, sizeof(struct default_wait_cb), GFP_KERNEL); + if (cb == NULL) { + ret = -ENOMEM; + goto err_free_cb; + } + + for (i = 0; i < count; ++i) { + struct dma_fence *fence = fences[i]; + + cb[i].task = current; + if (dma_fence_add_callback(fence, &cb[i].base, + dma_fence_default_wait_cb)) { + /* This fence is already signaled */ + if (idx) + *idx = i; + goto fence_rm_cb; + } + } + + while (ret > 0) { + if (intr) + set_current_state(TASK_INTERRUPTIBLE); + else + set_current_state(TASK_UNINTERRUPTIBLE); + + if (dma_fence_test_signaled_any(fences, count, idx)) + break; + + ret = schedule_timeout(ret); + + if (ret > 0 && intr && signal_pending(current)) + ret = -ERESTARTSYS; + } + + __set_current_state(TASK_RUNNING); + +fence_rm_cb: + while (i-- > 0) + dma_fence_remove_callback(fences[i], &cb[i].base); + +err_free_cb: + kfree(cb); + + return ret; +} +EXPORT_SYMBOL(dma_fence_wait_any_timeout); + +/** + * dma_fence_init - Initialize a custom fence. + * @fence: the fence to initialize + * @ops: the dma_fence_ops for operations on this fence + * @lock: the irqsafe spinlock to use for locking this fence + * @context: the execution context this fence is run on + * @seqno: a linear increasing sequence number for this context + * + * Initializes an allocated fence, the caller doesn't have to keep its + * refcount after committing with this fence, but it will need to hold a + * refcount again if &dma_fence_ops.enable_signaling gets called. + * + * context and seqno are used for easy comparison between fences, allowing + * to check which fence is later by simply using dma_fence_later(). + */ +void +dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops, + spinlock_t *lock, u64 context, u64 seqno) +{ + BUG_ON(!lock); + BUG_ON(!ops || !ops->get_driver_name || !ops->get_timeline_name); + + kref_init(&fence->refcount); + fence->ops = ops; + INIT_LIST_HEAD(&fence->cb_list); + fence->lock = lock; + fence->context = context; + fence->seqno = seqno; + fence->flags = 0UL; + fence->error = 0; + + trace_dma_fence_init(fence); +} +EXPORT_SYMBOL(dma_fence_init); diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c new file mode 100644 index 000000000..dcbb023ac --- /dev/null +++ b/drivers/dma-buf/dma-heap.c @@ -0,0 +1,302 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Framework for userspace DMA-BUF allocations + * + * Copyright (C) 2011 Google, Inc. + * Copyright (C) 2019 Linaro Ltd. + */ + +#include <linux/cdev.h> +#include <linux/debugfs.h> +#include <linux/device.h> +#include <linux/dma-buf.h> +#include <linux/err.h> +#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> +#include <uapi/linux/dma-heap.h> + +#define DEVNAME "dma_heap" + +#define NUM_HEAP_MINORS 128 + +/** + * struct dma_heap - represents a dmabuf heap in the system + * @name: used for debugging/device-node name + * @ops: ops struct for this heap + * @heap_devt heap device node + * @list list head connecting to list of heaps + * @heap_cdev heap char device + * + * Represents a heap of memory from which buffers can be made. + */ +struct dma_heap { + const char *name; + const struct dma_heap_ops *ops; + void *priv; + dev_t heap_devt; + struct list_head list; + struct cdev heap_cdev; +}; + +static LIST_HEAD(heap_list); +static DEFINE_MUTEX(heap_list_lock); +static dev_t dma_heap_devt; +static struct class *dma_heap_class; +static DEFINE_XARRAY_ALLOC(dma_heap_minors); + +static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len, + unsigned int fd_flags, + unsigned int heap_flags) +{ + /* + * Allocations from all heaps have to begin + * and end on page boundaries. + */ + len = PAGE_ALIGN(len); + if (!len) + return -EINVAL; + + return heap->ops->allocate(heap, len, fd_flags, heap_flags); +} + +static int dma_heap_open(struct inode *inode, struct file *file) +{ + struct dma_heap *heap; + + heap = xa_load(&dma_heap_minors, iminor(inode)); + if (!heap) { + pr_err("dma_heap: minor %d unknown.\n", iminor(inode)); + return -ENODEV; + } + + /* instance data as context */ + file->private_data = heap; + nonseekable_open(inode, file); + + return 0; +} + +static long dma_heap_ioctl_allocate(struct file *file, void *data) +{ + struct dma_heap_allocation_data *heap_allocation = data; + struct dma_heap *heap = file->private_data; + int fd; + + if (heap_allocation->fd) + return -EINVAL; + + if (heap_allocation->fd_flags & ~DMA_HEAP_VALID_FD_FLAGS) + return -EINVAL; + + if (heap_allocation->heap_flags & ~DMA_HEAP_VALID_HEAP_FLAGS) + return -EINVAL; + + fd = dma_heap_buffer_alloc(heap, heap_allocation->len, + heap_allocation->fd_flags, + heap_allocation->heap_flags); + if (fd < 0) + return fd; + + heap_allocation->fd = fd; + + return 0; +} + +static unsigned int dma_heap_ioctl_cmds[] = { + DMA_HEAP_IOCTL_ALLOC, +}; + +static long dma_heap_ioctl(struct file *file, unsigned int ucmd, + unsigned long arg) +{ + char stack_kdata[128]; + char *kdata = stack_kdata; + unsigned int kcmd; + unsigned int in_size, out_size, drv_size, ksize; + int nr = _IOC_NR(ucmd); + int ret = 0; + + 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]; + + /* Figure out the delta between user cmd size and kernel cmd size */ + drv_size = _IOC_SIZE(kcmd); + out_size = _IOC_SIZE(ucmd); + in_size = out_size; + if ((ucmd & kcmd & IOC_IN) == 0) + in_size = 0; + if ((ucmd & kcmd & IOC_OUT) == 0) + out_size = 0; + ksize = max(max(in_size, out_size), drv_size); + + /* If necessary, allocate buffer for ioctl argument */ + if (ksize > sizeof(stack_kdata)) { + kdata = kmalloc(ksize, GFP_KERNEL); + if (!kdata) + return -ENOMEM; + } + + if (copy_from_user(kdata, (void __user *)arg, in_size) != 0) { + ret = -EFAULT; + goto err; + } + + /* zero out any difference between the kernel/user structure size */ + if (ksize > in_size) + memset(kdata + in_size, 0, ksize - in_size); + + switch (kcmd) { + case DMA_HEAP_IOCTL_ALLOC: + ret = dma_heap_ioctl_allocate(file, kdata); + break; + default: + ret = -ENOTTY; + goto err; + } + + if (copy_to_user((void __user *)arg, kdata, out_size) != 0) + ret = -EFAULT; +err: + if (kdata != stack_kdata) + kfree(kdata); + return ret; +} + +static const struct file_operations dma_heap_fops = { + .owner = THIS_MODULE, + .open = dma_heap_open, + .unlocked_ioctl = dma_heap_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = dma_heap_ioctl, +#endif +}; + +/** + * dma_heap_get_drvdata() - get per-subdriver data for the heap + * @heap: DMA-Heap to retrieve private data for + * + * Returns: + * The per-subdriver data for the heap. + */ +void *dma_heap_get_drvdata(struct dma_heap *heap) +{ + return heap->priv; +} + +struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) +{ + struct dma_heap *heap, *h, *err_ret; + struct device *dev_ret; + unsigned int minor; + int ret; + + if (!exp_info->name || !strcmp(exp_info->name, "")) { + pr_err("dma_heap: Cannot add heap without a name\n"); + return ERR_PTR(-EINVAL); + } + + if (!exp_info->ops || !exp_info->ops->allocate) { + pr_err("dma_heap: Cannot add heap with invalid ops struct\n"); + return ERR_PTR(-EINVAL); + } + + heap = kzalloc(sizeof(*heap), GFP_KERNEL); + if (!heap) + return ERR_PTR(-ENOMEM); + + heap->name = exp_info->name; + heap->ops = exp_info->ops; + heap->priv = exp_info->priv; + + /* Find unused minor number */ + ret = xa_alloc(&dma_heap_minors, &minor, heap, + XA_LIMIT(0, NUM_HEAP_MINORS - 1), GFP_KERNEL); + if (ret < 0) { + pr_err("dma_heap: Unable to get minor number for heap\n"); + err_ret = ERR_PTR(ret); + goto err0; + } + + /* Create device */ + heap->heap_devt = MKDEV(MAJOR(dma_heap_devt), minor); + + cdev_init(&heap->heap_cdev, &dma_heap_fops); + ret = cdev_add(&heap->heap_cdev, heap->heap_devt, 1); + if (ret < 0) { + pr_err("dma_heap: Unable to add char device\n"); + err_ret = ERR_PTR(ret); + goto err1; + } + + dev_ret = device_create(dma_heap_class, + NULL, + heap->heap_devt, + NULL, + heap->name); + if (IS_ERR(dev_ret)) { + pr_err("dma_heap: Unable to create device\n"); + err_ret = ERR_CAST(dev_ret); + goto err2; + } + + mutex_lock(&heap_list_lock); + /* check the name is unique */ + list_for_each_entry(h, &heap_list, list) { + if (!strcmp(h->name, exp_info->name)) { + mutex_unlock(&heap_list_lock); + pr_err("dma_heap: Already registered heap named %s\n", + exp_info->name); + err_ret = ERR_PTR(-EINVAL); + goto err3; + } + } + + /* Add heap to the list */ + list_add(&heap->list, &heap_list); + mutex_unlock(&heap_list_lock); + + return heap; + +err3: + device_destroy(dma_heap_class, heap->heap_devt); +err2: + cdev_del(&heap->heap_cdev); +err1: + xa_erase(&dma_heap_minors, minor); +err0: + kfree(heap); + return err_ret; +} + +static char *dma_heap_devnode(struct device *dev, umode_t *mode) +{ + return kasprintf(GFP_KERNEL, "dma_heap/%s", dev_name(dev)); +} + +static int dma_heap_init(void) +{ + int ret; + + ret = alloc_chrdev_region(&dma_heap_devt, 0, NUM_HEAP_MINORS, DEVNAME); + if (ret) + return ret; + + dma_heap_class = class_create(THIS_MODULE, DEVNAME); + if (IS_ERR(dma_heap_class)) { + unregister_chrdev_region(dma_heap_devt, NUM_HEAP_MINORS); + return PTR_ERR(dma_heap_class); + } + dma_heap_class->devnode = dma_heap_devnode; + + return 0; +} +subsys_initcall(dma_heap_init); diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c new file mode 100644 index 000000000..1187e5e80 --- /dev/null +++ b/drivers/dma-buf/dma-resv.c @@ -0,0 +1,683 @@ +/* + * Copyright (C) 2012-2014 Canonical Ltd (Maarten Lankhorst) + * + * Based on bo.c which bears the following copyright notice, + * but is dual licensed: + * + * Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA + * All Rights Reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + **************************************************************************/ +/* + * Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com> + */ + +#include <linux/dma-resv.h> +#include <linux/export.h> +#include <linux/mm.h> +#include <linux/sched/mm.h> +#include <linux/mmu_notifier.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. + */ + +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 + * + * Allocate a new dma_resv_list and make sure to correctly initialize + * shared_max. + */ +static struct dma_resv_list *dma_resv_list_alloc(unsigned int shared_max) +{ + struct dma_resv_list *list; + + list = kmalloc(offsetof(typeof(*list), shared[shared_max]), GFP_KERNEL); + if (!list) + return NULL; + + list->shared_max = (ksize(list) - offsetof(typeof(*list), shared)) / + sizeof(*list->shared); + + 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. + */ +static void dma_resv_list_free(struct dma_resv_list *list) +{ + unsigned int i; + + if (!list) + return; + + for (i = 0; i < list->shared_count; ++i) + dma_fence_put(rcu_dereference_protected(list->shared[i], true)); + + kfree_rcu(list, rcu); +} + +#if IS_ENABLED(CONFIG_LOCKDEP) +static int __init dma_resv_lockdep(void) +{ + struct mm_struct *mm = mm_alloc(); + struct ww_acquire_ctx ctx; + struct dma_resv obj; + struct address_space mapping; + int ret; + + if (!mm) + return -ENOMEM; + + dma_resv_init(&obj); + address_space_init_once(&mapping); + + mmap_read_lock(mm); + ww_acquire_init(&ctx, &reservation_ww_class); + ret = dma_resv_lock(&obj, &ctx); + if (ret == -EDEADLK) + dma_resv_lock_slow(&obj, &ctx); + fs_reclaim_acquire(GFP_KERNEL); + /* for unmap_mapping_range on trylocked buffer objects in shrinkers */ + i_mmap_lock_write(&mapping); + i_mmap_unlock_write(&mapping); +#ifdef CONFIG_MMU_NOTIFIER + lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); + __dma_fence_might_wait(); + lock_map_release(&__mmu_notifier_invalidate_range_start_map); +#else + __dma_fence_might_wait(); +#endif + fs_reclaim_release(GFP_KERNEL); + ww_mutex_unlock(&obj.lock); + ww_acquire_fini(&ctx); + mmap_read_unlock(mm); + + mmput(mm); + + return 0; +} +subsys_initcall(dma_resv_lockdep); +#endif + +/** + * dma_resv_init - initialize a reservation object + * @obj: the reservation object + */ +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); +} +EXPORT_SYMBOL(dma_resv_init); + +/** + * dma_resv_fini - destroys a reservation object + * @obj: the reservation object + */ +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); + ww_mutex_destroy(&obj->lock); +} +EXPORT_SYMBOL(dma_resv_fini); + +/** + * dma_resv_reserve_shared - Reserve space to add shared fences to + * a dma_resv. + * @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->lock held. + * + * RETURNS + * Zero for success, or -errno + */ +int dma_resv_reserve_shared(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_get_list(obj); + + if (old && old->shared_max) { + if ((old->shared_count + num_fences) <= old->shared_max) + return 0; + else + max = max(old->shared_count + num_fences, + old->shared_max * 2); + } else { + max = max(4ul, roundup_pow_of_two(num_fences)); + } + + new = dma_resv_list_alloc(max); + if (!new) + return -ENOMEM; + + /* + * no need to bump fence refcounts, rcu_read access + * requires the use of kref_get_unless_zero, and the + * 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) { + struct dma_fence *fence; + + fence = rcu_dereference_protected(old->shared[i], + dma_resv_held(obj)); + if (dma_fence_is_signaled(fence)) + RCU_INIT_POINTER(new->shared[--k], fence); + else + RCU_INIT_POINTER(new->shared[j++], fence); + } + new->shared_count = 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 + * 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); + + if (!old) + return 0; + + /* Drop the references to the signaled fences */ + for (i = k; i < max; ++i) { + struct dma_fence *fence; + + fence = rcu_dereference_protected(new->shared[i], + dma_resv_held(obj)); + dma_fence_put(fence); + } + kfree_rcu(old, rcu); + + return 0; +} +EXPORT_SYMBOL(dma_resv_reserve_shared); + +/** + * dma_resv_add_shared_fence - Add a fence to a shared slot + * @obj: the reservation object + * @fence: the shared fence to add + * + * Add a fence to a shared slot, obj->lock must be held, and + * dma_resv_reserve_shared() has been called. + */ +void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence) +{ + struct dma_resv_list *fobj; + struct dma_fence *old; + unsigned int i, count; + + dma_fence_get(fence); + + dma_resv_assert_held(obj); + + fobj = dma_resv_get_list(obj); + count = fobj->shared_count; + + write_seqcount_begin(&obj->seq); + + 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; + } + + BUG_ON(fobj->shared_count >= fobj->shared_max); + old = NULL; + 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); +} +EXPORT_SYMBOL(dma_resv_add_shared_fence); + +/** + * dma_resv_add_excl_fence - Add an exclusive fence. + * @obj: the reservation object + * @fence: the shared fence to add + * + * Add a fence to the exclusive slot. The obj->lock must be held. + */ +void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence) +{ + struct dma_fence *old_fence = dma_resv_get_excl(obj); + struct dma_resv_list *old; + u32 i = 0; + + dma_resv_assert_held(obj); + + old = dma_resv_get_list(obj); + if (old) + i = old->shared_count; + + if (fence) + dma_fence_get(fence); + + 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); + + /* 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); +} +EXPORT_SYMBOL(dma_resv_add_excl_fence); + +/** +* dma_resv_copy_fences - Copy all fences from src to dst. +* @dst: the destination reservation object +* @src: the source reservation object +* +* Copy all fences from src to dst. dst-lock must be held. +*/ +int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src) +{ + struct dma_resv_list *src_list, *dst_list; + struct dma_fence *old, *new; + unsigned i; + + dma_resv_assert_held(dst); + + rcu_read_lock(); + src_list = rcu_dereference(src->fence); + +retry: + if (src_list) { + unsigned shared_count = src_list->shared_count; + + rcu_read_unlock(); + + dst_list = dma_resv_list_alloc(shared_count); + if (!dst_list) + return -ENOMEM; + + rcu_read_lock(); + src_list = rcu_dereference(src->fence); + if (!src_list || src_list->shared_count > shared_count) { + kfree(dst_list); + goto retry; + } + + dst_list->shared_count = 0; + for (i = 0; i < src_list->shared_count; ++i) { + struct dma_fence *fence; + + fence = rcu_dereference(src_list->shared[i]); + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, + &fence->flags)) + continue; + + if (!dma_fence_get_rcu(fence)) { + dma_resv_list_free(dst_list); + src_list = rcu_dereference(src->fence); + goto retry; + } + + if (dma_fence_is_signaled(fence)) { + dma_fence_put(fence); + continue; + } + + rcu_assign_pointer(dst_list->shared[dst_list->shared_count++], fence); + } + } else { + dst_list = NULL; + } + + new = dma_fence_get_rcu_safe(&src->fence_excl); + rcu_read_unlock(); + + src_list = dma_resv_get_list(dst); + old = dma_resv_get_excl(dst); + + write_seqcount_begin(&dst->seq); + /* write_seqcount_begin provides the necessary memory barrier */ + RCU_INIT_POINTER(dst->fence_excl, new); + RCU_INIT_POINTER(dst->fence, dst_list); + write_seqcount_end(&dst->seq); + + dma_resv_list_free(src_list); + dma_fence_put(old); + + return 0; +} +EXPORT_SYMBOL(dma_resv_copy_fences); + +/** + * dma_resv_get_fences_rcu - Get an object's shared and exclusive + * fences without update side lock held + * @obj: the reservation object + * @pfence_excl: the returned exclusive fence (or NULL) + * @pshared_count: the number of shared fences returned + * @pshared: 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. + */ +int dma_resv_get_fences_rcu(struct dma_resv *obj, + struct dma_fence **pfence_excl, + unsigned *pshared_count, + struct dma_fence ***pshared) +{ + struct dma_fence **shared = NULL; + struct dma_fence *fence_excl; + unsigned int shared_count; + int ret = 1; + + do { + struct dma_resv_list *fobj; + unsigned int i, seq; + size_t sz = 0; + + shared_count = i = 0; + + rcu_read_lock(); + seq = read_seqcount_begin(&obj->seq); + + fence_excl = rcu_dereference(obj->fence_excl); + if (fence_excl && !dma_fence_get_rcu(fence_excl)) + goto unlock; + + fobj = rcu_dereference(obj->fence); + if (fobj) + sz += sizeof(*shared) * fobj->shared_max; + + if (!pfence_excl && fence_excl) + sz += sizeof(*shared); + + if (sz) { + struct dma_fence **nshared; + + nshared = krealloc(shared, sz, + GFP_NOWAIT | __GFP_NOWARN); + if (!nshared) { + rcu_read_unlock(); + + dma_fence_put(fence_excl); + fence_excl = NULL; + + nshared = krealloc(shared, sz, GFP_KERNEL); + if (nshared) { + shared = nshared; + continue; + } + + ret = -ENOMEM; + break; + } + shared = nshared; + shared_count = fobj ? fobj->shared_count : 0; + for (i = 0; i < shared_count; ++i) { + shared[i] = rcu_dereference(fobj->shared[i]); + if (!dma_fence_get_rcu(shared[i])) + break; + } + } + + if (i != shared_count || read_seqcount_retry(&obj->seq, seq)) { + while (i--) + dma_fence_put(shared[i]); + dma_fence_put(fence_excl); + goto unlock; + } + + ret = 0; +unlock: + rcu_read_unlock(); + } while (ret); + + if (pfence_excl) + *pfence_excl = fence_excl; + else if (fence_excl) + shared[shared_count++] = fence_excl; + + if (!shared_count) { + kfree(shared); + shared = NULL; + } + + *pshared_count = shared_count; + *pshared = shared; + return ret; +} +EXPORT_SYMBOL_GPL(dma_resv_get_fences_rcu); + +/** + * dma_resv_wait_timeout_rcu - Wait on reservation's objects + * shared and/or exclusive fences. + * @obj: the reservation object + * @wait_all: if true, wait on all fences, else wait on just exclusive fence + * @intr: if true, do interruptible wait + * @timeout: timeout value in jiffies or zero to return immediately + * + * RETURNS + * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or + * greater than zer on success. + */ +long dma_resv_wait_timeout_rcu(struct dma_resv *obj, + bool wait_all, bool intr, + unsigned long timeout) +{ + struct dma_fence *fence; + unsigned seq, shared_count; + long ret = timeout ? timeout : 1; + int i; + +retry: + shared_count = 0; + seq = read_seqcount_begin(&obj->seq); + rcu_read_lock(); + i = -1; + + fence = rcu_dereference(obj->fence_excl); + if (fence && !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { + if (!dma_fence_get_rcu(fence)) + goto unlock_retry; + + if (dma_fence_is_signaled(fence)) { + dma_fence_put(fence); + fence = NULL; + } + + } else { + fence = NULL; + } + + if (wait_all) { + struct dma_resv_list *fobj = rcu_dereference(obj->fence); + + if (fobj) + shared_count = fobj->shared_count; + + for (i = 0; !fence && i < shared_count; ++i) { + struct dma_fence *lfence = rcu_dereference(fobj->shared[i]); + + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, + &lfence->flags)) + continue; + + if (!dma_fence_get_rcu(lfence)) + goto unlock_retry; + + if (dma_fence_is_signaled(lfence)) { + dma_fence_put(lfence); + continue; + } + + fence = lfence; + break; + } + } + + rcu_read_unlock(); + if (fence) { + if (read_seqcount_retry(&obj->seq, seq)) { + dma_fence_put(fence); + goto retry; + } + + ret = dma_fence_wait_timeout(fence, intr, ret); + dma_fence_put(fence); + if (ret > 0 && wait_all && (i + 1 < shared_count)) + goto retry; + } + return ret; + +unlock_retry: + rcu_read_unlock(); + goto retry; +} +EXPORT_SYMBOL_GPL(dma_resv_wait_timeout_rcu); + + +static inline int dma_resv_test_signaled_single(struct dma_fence *passed_fence) +{ + struct dma_fence *fence, *lfence = passed_fence; + int ret = 1; + + if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &lfence->flags)) { + fence = dma_fence_get_rcu(lfence); + if (!fence) + return -1; + + ret = !!dma_fence_is_signaled(fence); + dma_fence_put(fence); + } + return ret; +} + +/** + * dma_resv_test_signaled_rcu - 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 + * + * RETURNS + * true if all fences signaled, else false + */ +bool dma_resv_test_signaled_rcu(struct dma_resv *obj, bool test_all) +{ + unsigned seq, shared_count; + int ret; + + rcu_read_lock(); +retry: + ret = true; + shared_count = 0; + seq = read_seqcount_begin(&obj->seq); + + if (test_all) { + unsigned i; + + struct dma_resv_list *fobj = rcu_dereference(obj->fence); + + if (fobj) + shared_count = fobj->shared_count; + + for (i = 0; i < shared_count; ++i) { + struct dma_fence *fence = rcu_dereference(fobj->shared[i]); + + ret = dma_resv_test_signaled_single(fence); + if (ret < 0) + goto retry; + else if (!ret) + break; + } + + if (read_seqcount_retry(&obj->seq, seq)) + goto retry; + } + + if (!shared_count) { + struct dma_fence *fence_excl = rcu_dereference(obj->fence_excl); + + if (fence_excl) { + ret = dma_resv_test_signaled_single(fence_excl); + if (ret < 0) + goto retry; + + if (read_seqcount_retry(&obj->seq, seq)) + goto retry; + } + } + + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(dma_resv_test_signaled_rcu); diff --git a/drivers/dma-buf/heaps/Kconfig b/drivers/dma-buf/heaps/Kconfig new file mode 100644 index 000000000..a5eef06c4 --- /dev/null +++ b/drivers/dma-buf/heaps/Kconfig @@ -0,0 +1,14 @@ +config DMABUF_HEAPS_SYSTEM + bool "DMA-BUF System Heap" + depends on DMABUF_HEAPS + help + Choose this option to enable the system dmabuf heap. The system heap + is backed by pages from the buddy allocator. If in doubt, say Y. + +config DMABUF_HEAPS_CMA + bool "DMA-BUF CMA Heap" + depends on DMABUF_HEAPS && DMA_CMA + help + Choose this option to enable dma-buf CMA heap. This heap is backed + by the Contiguous Memory Allocator (CMA). If your system has these + regions, you should say Y here. diff --git a/drivers/dma-buf/heaps/Makefile b/drivers/dma-buf/heaps/Makefile new file mode 100644 index 000000000..6e54cdec3 --- /dev/null +++ b/drivers/dma-buf/heaps/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-y += heap-helpers.o +obj-$(CONFIG_DMABUF_HEAPS_SYSTEM) += system_heap.o +obj-$(CONFIG_DMABUF_HEAPS_CMA) += cma_heap.o diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c new file mode 100644 index 000000000..e55384dc1 --- /dev/null +++ b/drivers/dma-buf/heaps/cma_heap.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DMABUF CMA heap exporter + * + * Copyright (C) 2012, 2019 Linaro Ltd. + * Author: <benjamin.gaignard@linaro.org> for ST-Ericsson. + */ + +#include <linux/cma.h> +#include <linux/device.h> +#include <linux/dma-buf.h> +#include <linux/dma-heap.h> +#include <linux/dma-map-ops.h> +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/highmem.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/scatterlist.h> +#include <linux/sched/signal.h> + +#include "heap-helpers.h" + +struct cma_heap { + struct dma_heap *heap; + struct cma *cma; +}; + +static void cma_heap_free(struct heap_helper_buffer *buffer) +{ + struct cma_heap *cma_heap = dma_heap_get_drvdata(buffer->heap); + unsigned long nr_pages = buffer->pagecount; + struct page *cma_pages = buffer->priv_virt; + + /* free page list */ + kfree(buffer->pages); + /* release memory */ + cma_release(cma_heap->cma, cma_pages, nr_pages); + kfree(buffer); +} + +/* dmabuf heap CMA operations functions */ +static int cma_heap_allocate(struct dma_heap *heap, + unsigned long len, + unsigned long fd_flags, + unsigned long heap_flags) +{ + struct cma_heap *cma_heap = dma_heap_get_drvdata(heap); + struct heap_helper_buffer *helper_buffer; + struct page *cma_pages; + size_t size = PAGE_ALIGN(len); + unsigned long nr_pages = size >> PAGE_SHIFT; + unsigned long align = get_order(size); + struct dma_buf *dmabuf; + int ret = -ENOMEM; + pgoff_t pg; + + if (align > CONFIG_CMA_ALIGNMENT) + align = CONFIG_CMA_ALIGNMENT; + + helper_buffer = kzalloc(sizeof(*helper_buffer), GFP_KERNEL); + if (!helper_buffer) + return -ENOMEM; + + init_heap_helper_buffer(helper_buffer, cma_heap_free); + helper_buffer->heap = heap; + helper_buffer->size = len; + + cma_pages = cma_alloc(cma_heap->cma, nr_pages, align, false); + if (!cma_pages) + goto free_buf; + + if (PageHighMem(cma_pages)) { + unsigned long nr_clear_pages = nr_pages; + struct page *page = cma_pages; + + while (nr_clear_pages > 0) { + void *vaddr = kmap_atomic(page); + + memset(vaddr, 0, PAGE_SIZE); + kunmap_atomic(vaddr); + /* + * Avoid wasting time zeroing memory if the process + * has been killed by by SIGKILL + */ + if (fatal_signal_pending(current)) + goto free_cma; + + page++; + nr_clear_pages--; + } + } else { + memset(page_address(cma_pages), 0, size); + } + + helper_buffer->pagecount = nr_pages; + helper_buffer->pages = kmalloc_array(helper_buffer->pagecount, + sizeof(*helper_buffer->pages), + GFP_KERNEL); + if (!helper_buffer->pages) { + ret = -ENOMEM; + goto free_cma; + } + + for (pg = 0; pg < helper_buffer->pagecount; pg++) + helper_buffer->pages[pg] = &cma_pages[pg]; + + /* create the dmabuf */ + dmabuf = heap_helper_export_dmabuf(helper_buffer, fd_flags); + if (IS_ERR(dmabuf)) { + ret = PTR_ERR(dmabuf); + goto free_pages; + } + + helper_buffer->dmabuf = dmabuf; + helper_buffer->priv_virt = cma_pages; + + ret = dma_buf_fd(dmabuf, fd_flags); + if (ret < 0) { + dma_buf_put(dmabuf); + /* just return, as put will call release and that will free */ + return ret; + } + + return ret; + +free_pages: + kfree(helper_buffer->pages); +free_cma: + cma_release(cma_heap->cma, cma_pages, nr_pages); +free_buf: + kfree(helper_buffer); + return ret; +} + +static const struct dma_heap_ops cma_heap_ops = { + .allocate = cma_heap_allocate, +}; + +static int __add_cma_heap(struct cma *cma, void *data) +{ + struct cma_heap *cma_heap; + struct dma_heap_export_info exp_info; + + cma_heap = kzalloc(sizeof(*cma_heap), GFP_KERNEL); + if (!cma_heap) + return -ENOMEM; + cma_heap->cma = cma; + + exp_info.name = cma_get_name(cma); + exp_info.ops = &cma_heap_ops; + exp_info.priv = cma_heap; + + cma_heap->heap = dma_heap_add(&exp_info); + if (IS_ERR(cma_heap->heap)) { + int ret = PTR_ERR(cma_heap->heap); + + kfree(cma_heap); + return ret; + } + + return 0; +} + +static int add_default_cma_heap(void) +{ + struct cma *default_cma = dev_get_cma_area(NULL); + int ret = 0; + + if (default_cma) + ret = __add_cma_heap(default_cma, NULL); + + return ret; +} +module_init(add_default_cma_heap); +MODULE_DESCRIPTION("DMA-BUF CMA Heap"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/dma-buf/heaps/heap-helpers.c b/drivers/dma-buf/heaps/heap-helpers.c new file mode 100644 index 000000000..d0696cf93 --- /dev/null +++ b/drivers/dma-buf/heaps/heap-helpers.c @@ -0,0 +1,270 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/device.h> +#include <linux/dma-buf.h> +#include <linux/err.h> +#include <linux/highmem.h> +#include <linux/idr.h> +#include <linux/list.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/vmalloc.h> +#include <uapi/linux/dma-heap.h> + +#include "heap-helpers.h" + +void init_heap_helper_buffer(struct heap_helper_buffer *buffer, + void (*free)(struct heap_helper_buffer *)) +{ + buffer->priv_virt = NULL; + mutex_init(&buffer->lock); + buffer->vmap_cnt = 0; + buffer->vaddr = NULL; + buffer->pagecount = 0; + buffer->pages = NULL; + INIT_LIST_HEAD(&buffer->attachments); + buffer->free = free; +} + +struct dma_buf *heap_helper_export_dmabuf(struct heap_helper_buffer *buffer, + int fd_flags) +{ + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); + + exp_info.ops = &heap_helper_ops; + exp_info.size = buffer->size; + exp_info.flags = fd_flags; + exp_info.priv = buffer; + + return dma_buf_export(&exp_info); +} + +static void *dma_heap_map_kernel(struct heap_helper_buffer *buffer) +{ + void *vaddr; + + vaddr = vmap(buffer->pages, buffer->pagecount, VM_MAP, PAGE_KERNEL); + if (!vaddr) + return ERR_PTR(-ENOMEM); + + return vaddr; +} + +static void dma_heap_buffer_destroy(struct heap_helper_buffer *buffer) +{ + if (buffer->vmap_cnt > 0) { + WARN(1, "%s: buffer still mapped in the kernel\n", __func__); + vunmap(buffer->vaddr); + } + + buffer->free(buffer); +} + +static void *dma_heap_buffer_vmap_get(struct heap_helper_buffer *buffer) +{ + void *vaddr; + + if (buffer->vmap_cnt) { + buffer->vmap_cnt++; + return buffer->vaddr; + } + vaddr = dma_heap_map_kernel(buffer); + if (IS_ERR(vaddr)) + return vaddr; + buffer->vaddr = vaddr; + buffer->vmap_cnt++; + return vaddr; +} + +static void dma_heap_buffer_vmap_put(struct heap_helper_buffer *buffer) +{ + if (!--buffer->vmap_cnt) { + vunmap(buffer->vaddr); + buffer->vaddr = NULL; + } +} + +struct dma_heaps_attachment { + struct device *dev; + struct sg_table table; + struct list_head list; +}; + +static int dma_heap_attach(struct dma_buf *dmabuf, + struct dma_buf_attachment *attachment) +{ + struct dma_heaps_attachment *a; + struct heap_helper_buffer *buffer = dmabuf->priv; + int ret; + + a = kzalloc(sizeof(*a), GFP_KERNEL); + if (!a) + return -ENOMEM; + + ret = sg_alloc_table_from_pages(&a->table, buffer->pages, + buffer->pagecount, 0, + buffer->pagecount << PAGE_SHIFT, + GFP_KERNEL); + if (ret) { + kfree(a); + return ret; + } + + a->dev = attachment->dev; + INIT_LIST_HEAD(&a->list); + + attachment->priv = a; + + mutex_lock(&buffer->lock); + list_add(&a->list, &buffer->attachments); + mutex_unlock(&buffer->lock); + + return 0; +} + +static void dma_heap_detach(struct dma_buf *dmabuf, + struct dma_buf_attachment *attachment) +{ + struct dma_heaps_attachment *a = attachment->priv; + struct heap_helper_buffer *buffer = dmabuf->priv; + + mutex_lock(&buffer->lock); + list_del(&a->list); + mutex_unlock(&buffer->lock); + + sg_free_table(&a->table); + kfree(a); +} + +static +struct sg_table *dma_heap_map_dma_buf(struct dma_buf_attachment *attachment, + enum dma_data_direction direction) +{ + struct dma_heaps_attachment *a = attachment->priv; + struct sg_table *table = &a->table; + int ret; + + ret = dma_map_sgtable(attachment->dev, table, direction, 0); + if (ret) + table = ERR_PTR(ret); + return table; +} + +static void dma_heap_unmap_dma_buf(struct dma_buf_attachment *attachment, + struct sg_table *table, + enum dma_data_direction direction) +{ + dma_unmap_sgtable(attachment->dev, table, direction, 0); +} + +static vm_fault_t dma_heap_vm_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct heap_helper_buffer *buffer = vma->vm_private_data; + + if (vmf->pgoff > buffer->pagecount) + return VM_FAULT_SIGBUS; + + vmf->page = buffer->pages[vmf->pgoff]; + get_page(vmf->page); + + return 0; +} + +static const struct vm_operations_struct dma_heap_vm_ops = { + .fault = dma_heap_vm_fault, +}; + +static int dma_heap_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma) +{ + struct heap_helper_buffer *buffer = dmabuf->priv; + + if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0) + return -EINVAL; + + vma->vm_ops = &dma_heap_vm_ops; + vma->vm_private_data = buffer; + + return 0; +} + +static void dma_heap_dma_buf_release(struct dma_buf *dmabuf) +{ + struct heap_helper_buffer *buffer = dmabuf->priv; + + dma_heap_buffer_destroy(buffer); +} + +static int dma_heap_dma_buf_begin_cpu_access(struct dma_buf *dmabuf, + enum dma_data_direction direction) +{ + struct heap_helper_buffer *buffer = dmabuf->priv; + struct dma_heaps_attachment *a; + int ret = 0; + + mutex_lock(&buffer->lock); + + if (buffer->vmap_cnt) + invalidate_kernel_vmap_range(buffer->vaddr, buffer->size); + + list_for_each_entry(a, &buffer->attachments, list) { + dma_sync_sg_for_cpu(a->dev, a->table.sgl, a->table.nents, + direction); + } + mutex_unlock(&buffer->lock); + + return ret; +} + +static int dma_heap_dma_buf_end_cpu_access(struct dma_buf *dmabuf, + enum dma_data_direction direction) +{ + struct heap_helper_buffer *buffer = dmabuf->priv; + struct dma_heaps_attachment *a; + + mutex_lock(&buffer->lock); + + if (buffer->vmap_cnt) + flush_kernel_vmap_range(buffer->vaddr, buffer->size); + + list_for_each_entry(a, &buffer->attachments, list) { + dma_sync_sg_for_device(a->dev, a->table.sgl, a->table.nents, + direction); + } + mutex_unlock(&buffer->lock); + + return 0; +} + +static void *dma_heap_dma_buf_vmap(struct dma_buf *dmabuf) +{ + struct heap_helper_buffer *buffer = dmabuf->priv; + void *vaddr; + + mutex_lock(&buffer->lock); + vaddr = dma_heap_buffer_vmap_get(buffer); + mutex_unlock(&buffer->lock); + + return vaddr; +} + +static void dma_heap_dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr) +{ + struct heap_helper_buffer *buffer = dmabuf->priv; + + mutex_lock(&buffer->lock); + dma_heap_buffer_vmap_put(buffer); + mutex_unlock(&buffer->lock); +} + +const struct dma_buf_ops heap_helper_ops = { + .map_dma_buf = dma_heap_map_dma_buf, + .unmap_dma_buf = dma_heap_unmap_dma_buf, + .mmap = dma_heap_mmap, + .release = dma_heap_dma_buf_release, + .attach = dma_heap_attach, + .detach = dma_heap_detach, + .begin_cpu_access = dma_heap_dma_buf_begin_cpu_access, + .end_cpu_access = dma_heap_dma_buf_end_cpu_access, + .vmap = dma_heap_dma_buf_vmap, + .vunmap = dma_heap_dma_buf_vunmap, +}; diff --git a/drivers/dma-buf/heaps/heap-helpers.h b/drivers/dma-buf/heaps/heap-helpers.h new file mode 100644 index 000000000..805d2df88 --- /dev/null +++ b/drivers/dma-buf/heaps/heap-helpers.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * DMABUF Heaps helper code + * + * Copyright (C) 2011 Google, Inc. + * Copyright (C) 2019 Linaro Ltd. + */ + +#ifndef _HEAP_HELPERS_H +#define _HEAP_HELPERS_H + +#include <linux/dma-heap.h> +#include <linux/list.h> + +/** + * struct heap_helper_buffer - helper buffer metadata + * @heap: back pointer to the heap the buffer came from + * @dmabuf: backing dma-buf for this buffer + * @size: size of the buffer + * @priv_virt pointer to heap specific private value + * @lock mutext to protect the data in this structure + * @vmap_cnt count of vmap references on the buffer + * @vaddr vmap'ed virtual address + * @pagecount number of pages in the buffer + * @pages list of page pointers + * @attachments list of device attachments + * + * @free heap callback to free the buffer + */ +struct heap_helper_buffer { + struct dma_heap *heap; + struct dma_buf *dmabuf; + size_t size; + + void *priv_virt; + struct mutex lock; + int vmap_cnt; + void *vaddr; + pgoff_t pagecount; + struct page **pages; + struct list_head attachments; + + void (*free)(struct heap_helper_buffer *buffer); +}; + +void init_heap_helper_buffer(struct heap_helper_buffer *buffer, + void (*free)(struct heap_helper_buffer *)); + +struct dma_buf *heap_helper_export_dmabuf(struct heap_helper_buffer *buffer, + int fd_flags); + +extern const struct dma_buf_ops heap_helper_ops; +#endif /* _HEAP_HELPERS_H */ diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c new file mode 100644 index 000000000..0bf688e3c --- /dev/null +++ b/drivers/dma-buf/heaps/system_heap.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DMABUF System heap exporter + * + * Copyright (C) 2011 Google, Inc. + * Copyright (C) 2019 Linaro Ltd. + */ + +#include <linux/dma-buf.h> +#include <linux/dma-mapping.h> +#include <linux/dma-heap.h> +#include <linux/err.h> +#include <linux/highmem.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/scatterlist.h> +#include <linux/slab.h> +#include <linux/sched/signal.h> +#include <asm/page.h> + +#include "heap-helpers.h" + +struct dma_heap *sys_heap; + +static void system_heap_free(struct heap_helper_buffer *buffer) +{ + pgoff_t pg; + + for (pg = 0; pg < buffer->pagecount; pg++) + __free_page(buffer->pages[pg]); + kfree(buffer->pages); + kfree(buffer); +} + +static int system_heap_allocate(struct dma_heap *heap, + unsigned long len, + unsigned long fd_flags, + unsigned long heap_flags) +{ + struct heap_helper_buffer *helper_buffer; + struct dma_buf *dmabuf; + int ret = -ENOMEM; + pgoff_t pg; + + helper_buffer = kzalloc(sizeof(*helper_buffer), GFP_KERNEL); + if (!helper_buffer) + return -ENOMEM; + + init_heap_helper_buffer(helper_buffer, system_heap_free); + helper_buffer->heap = heap; + helper_buffer->size = len; + + helper_buffer->pagecount = len / PAGE_SIZE; + helper_buffer->pages = kmalloc_array(helper_buffer->pagecount, + sizeof(*helper_buffer->pages), + GFP_KERNEL); + if (!helper_buffer->pages) { + ret = -ENOMEM; + goto err0; + } + + for (pg = 0; pg < helper_buffer->pagecount; pg++) { + /* + * Avoid trying to allocate memory if the process + * has been killed by by SIGKILL + */ + if (fatal_signal_pending(current)) + goto err1; + + helper_buffer->pages[pg] = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!helper_buffer->pages[pg]) + goto err1; + } + + /* create the dmabuf */ + dmabuf = heap_helper_export_dmabuf(helper_buffer, fd_flags); + if (IS_ERR(dmabuf)) { + ret = PTR_ERR(dmabuf); + goto err1; + } + + helper_buffer->dmabuf = dmabuf; + + ret = dma_buf_fd(dmabuf, fd_flags); + if (ret < 0) { + dma_buf_put(dmabuf); + /* just return, as put will call release and that will free */ + return ret; + } + + return ret; + +err1: + while (pg > 0) + __free_page(helper_buffer->pages[--pg]); + kfree(helper_buffer->pages); +err0: + kfree(helper_buffer); + + return ret; +} + +static const struct dma_heap_ops system_heap_ops = { + .allocate = system_heap_allocate, +}; + +static int system_heap_create(void) +{ + struct dma_heap_export_info exp_info; + int ret = 0; + + exp_info.name = "system"; + exp_info.ops = &system_heap_ops; + exp_info.priv = NULL; + + sys_heap = dma_heap_add(&exp_info); + if (IS_ERR(sys_heap)) + ret = PTR_ERR(sys_heap); + + return ret; +} +module_init(system_heap_create); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/dma-buf/selftest.c b/drivers/dma-buf/selftest.c new file mode 100644 index 000000000..c60b6944b --- /dev/null +++ b/drivers/dma-buf/selftest.c @@ -0,0 +1,167 @@ +/* SPDX-License-Identifier: MIT */ + +/* + * Copyright © 2019 Intel Corporation + */ + +#include <linux/compiler.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/sched/signal.h> +#include <linux/slab.h> + +#include "selftest.h" + +enum { +#define selftest(n, func) __idx_##n, +#include "selftests.h" +#undef selftest +}; + +#define selftest(n, f) [__idx_##n] = { .name = #n, .func = f }, +static struct selftest { + bool enabled; + const char *name; + int (*func)(void); +} selftests[] = { +#include "selftests.h" +}; +#undef selftest + +/* Embed the line number into the parameter name so that we can order tests */ +#define param(n) __PASTE(igt__, __PASTE(__PASTE(__LINE__, __), n)) +#define selftest_0(n, func, id) \ +module_param_named(id, selftests[__idx_##n].enabled, bool, 0400); +#define selftest(n, func) selftest_0(n, func, param(n)) +#include "selftests.h" +#undef selftest + +int __sanitycheck__(void) +{ + pr_debug("Hello World!\n"); + return 0; +} + +static char *__st_filter; + +static bool apply_subtest_filter(const char *caller, const char *name) +{ + char *filter, *sep, *tok; + bool result = true; + + filter = kstrdup(__st_filter, GFP_KERNEL); + for (sep = filter; (tok = strsep(&sep, ","));) { + bool allow = true; + char *sl; + + if (*tok == '!') { + allow = false; + tok++; + } + + if (*tok == '\0') + continue; + + sl = strchr(tok, '/'); + if (sl) { + *sl++ = '\0'; + if (strcmp(tok, caller)) { + if (allow) + result = false; + continue; + } + tok = sl; + } + + if (strcmp(tok, name)) { + if (allow) + result = false; + continue; + } + + result = allow; + break; + } + kfree(filter); + + return result; +} + +int +__subtests(const char *caller, const struct subtest *st, int count, void *data) +{ + int err; + + for (; count--; st++) { + cond_resched(); + if (signal_pending(current)) + return -EINTR; + + if (!apply_subtest_filter(caller, st->name)) + continue; + + pr_info("dma-buf: Running %s/%s\n", caller, st->name); + + err = st->func(data); + if (err && err != -EINTR) { + pr_err("dma-buf/%s: %s failed with error %d\n", + caller, st->name, err); + return err; + } + } + + return 0; +} + +static void set_default_test_all(struct selftest *st, unsigned long count) +{ + unsigned long i; + + for (i = 0; i < count; i++) + if (st[i].enabled) + return; + + for (i = 0; i < count; i++) + st[i].enabled = true; +} + +static int run_selftests(struct selftest *st, unsigned long count) +{ + int err = 0; + + set_default_test_all(st, count); + + /* Tests are listed in natural order in selftests.h */ + for (; count--; st++) { + if (!st->enabled) + continue; + + pr_info("dma-buf: Running %s\n", st->name); + err = st->func(); + if (err) + break; + } + + if (WARN(err > 0 || err == -ENOTTY, + "%s returned %d, conflicting with selftest's magic values!\n", + st->name, err)) + err = -1; + + return err; +} + +static int __init st_init(void) +{ + return run_selftests(selftests, ARRAY_SIZE(selftests)); +} + +static void __exit st_exit(void) +{ +} + +module_param_named(st_filter, __st_filter, charp, 0400); +module_init(st_init); +module_exit(st_exit); + +MODULE_DESCRIPTION("Self-test harness for dma-buf"); +MODULE_LICENSE("GPL and additional rights"); diff --git a/drivers/dma-buf/selftest.h b/drivers/dma-buf/selftest.h new file mode 100644 index 000000000..45793aff6 --- /dev/null +++ b/drivers/dma-buf/selftest.h @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: MIT + +/* + * Copyright © 2019 Intel Corporation + */ + +#ifndef __SELFTEST_H__ +#define __SELFTEST_H__ + +#include <linux/compiler.h> + +#define selftest(name, func) int func(void); +#include "selftests.h" +#undef selftest + +struct subtest { + int (*func)(void *data); + const char *name; +}; + +int __subtests(const char *caller, + const struct subtest *st, + int count, + void *data); +#define subtests(T, data) \ + __subtests(__func__, T, ARRAY_SIZE(T), data) + +#define SUBTEST(x) { x, #x } + +#endif /* __SELFTEST_H__ */ diff --git a/drivers/dma-buf/selftests.h b/drivers/dma-buf/selftests.h new file mode 100644 index 000000000..bc8cea67b --- /dev/null +++ b/drivers/dma-buf/selftests.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: MIT */ +/* List each unit test as selftest(name, function) + * + * The name is used as both an enum and expanded as subtest__name to create + * a module parameter. It must be unique and legal for a C identifier. + * + * The function should be of type int function(void). It may be conditionally + * compiled using #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST). + * + * Tests are executed in order by igt/dmabuf_selftest + */ +selftest(sanitycheck, __sanitycheck__) /* keep first (igt selfcheck) */ +selftest(dma_fence, dma_fence) +selftest(dma_fence_chain, dma_fence_chain) diff --git a/drivers/dma-buf/seqno-fence.c b/drivers/dma-buf/seqno-fence.c new file mode 100644 index 000000000..bfe14e94c --- /dev/null +++ b/drivers/dma-buf/seqno-fence.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * seqno-fence, using a dma-buf to synchronize fencing + * + * Copyright (C) 2012 Texas Instruments + * Copyright (C) 2012-2014 Canonical Ltd + * Authors: + * Rob Clark <robdclark@gmail.com> + * Maarten Lankhorst <maarten.lankhorst@canonical.com> + */ + +#include <linux/slab.h> +#include <linux/export.h> +#include <linux/seqno-fence.h> + +static const char *seqno_fence_get_driver_name(struct dma_fence *fence) +{ + struct seqno_fence *seqno_fence = to_seqno_fence(fence); + + return seqno_fence->ops->get_driver_name(fence); +} + +static const char *seqno_fence_get_timeline_name(struct dma_fence *fence) +{ + struct seqno_fence *seqno_fence = to_seqno_fence(fence); + + return seqno_fence->ops->get_timeline_name(fence); +} + +static bool seqno_enable_signaling(struct dma_fence *fence) +{ + struct seqno_fence *seqno_fence = to_seqno_fence(fence); + + return seqno_fence->ops->enable_signaling(fence); +} + +static bool seqno_signaled(struct dma_fence *fence) +{ + struct seqno_fence *seqno_fence = to_seqno_fence(fence); + + return seqno_fence->ops->signaled && seqno_fence->ops->signaled(fence); +} + +static void seqno_release(struct dma_fence *fence) +{ + struct seqno_fence *f = to_seqno_fence(fence); + + dma_buf_put(f->sync_buf); + if (f->ops->release) + f->ops->release(fence); + else + dma_fence_free(&f->base); +} + +static signed long seqno_wait(struct dma_fence *fence, bool intr, + signed long timeout) +{ + struct seqno_fence *f = to_seqno_fence(fence); + + return f->ops->wait(fence, intr, timeout); +} + +const struct dma_fence_ops seqno_fence_ops = { + .get_driver_name = seqno_fence_get_driver_name, + .get_timeline_name = seqno_fence_get_timeline_name, + .enable_signaling = seqno_enable_signaling, + .signaled = seqno_signaled, + .wait = seqno_wait, + .release = seqno_release, +}; +EXPORT_SYMBOL(seqno_fence_ops); diff --git a/drivers/dma-buf/st-dma-fence-chain.c b/drivers/dma-buf/st-dma-fence-chain.c new file mode 100644 index 000000000..9525f7f56 --- /dev/null +++ b/drivers/dma-buf/st-dma-fence-chain.c @@ -0,0 +1,714 @@ +// SPDX-License-Identifier: MIT + +/* + * Copyright © 2019 Intel Corporation + */ + +#include <linux/delay.h> +#include <linux/dma-fence.h> +#include <linux/dma-fence-chain.h> +#include <linux/kernel.h> +#include <linux/kthread.h> +#include <linux/mm.h> +#include <linux/sched/signal.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/random.h> + +#include "selftest.h" + +#define CHAIN_SZ (4 << 10) + +static struct kmem_cache *slab_fences; + +static inline struct mock_fence { + struct dma_fence base; + spinlock_t lock; +} *to_mock_fence(struct dma_fence *f) { + return container_of(f, struct mock_fence, base); +} + +static const char *mock_name(struct dma_fence *f) +{ + return "mock"; +} + +static void mock_fence_release(struct dma_fence *f) +{ + kmem_cache_free(slab_fences, to_mock_fence(f)); +} + +static const struct dma_fence_ops mock_ops = { + .get_driver_name = mock_name, + .get_timeline_name = mock_name, + .release = mock_fence_release, +}; + +static struct dma_fence *mock_fence(void) +{ + struct mock_fence *f; + + f = kmem_cache_alloc(slab_fences, GFP_KERNEL); + if (!f) + return NULL; + + spin_lock_init(&f->lock); + dma_fence_init(&f->base, &mock_ops, &f->lock, 0, 0); + + return &f->base; +} + +static inline struct mock_chain { + struct dma_fence_chain base; +} *to_mock_chain(struct dma_fence *f) { + return container_of(f, struct mock_chain, base.base); +} + +static struct dma_fence *mock_chain(struct dma_fence *prev, + struct dma_fence *fence, + u64 seqno) +{ + struct mock_chain *f; + + f = kmalloc(sizeof(*f), GFP_KERNEL); + if (!f) + return NULL; + + dma_fence_chain_init(&f->base, + dma_fence_get(prev), + dma_fence_get(fence), + seqno); + + return &f->base.base; +} + +static int sanitycheck(void *arg) +{ + struct dma_fence *f, *chain; + int err = 0; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + chain = mock_chain(NULL, f, 1); + if (!chain) + err = -ENOMEM; + + dma_fence_signal(f); + dma_fence_put(f); + + dma_fence_put(chain); + + return err; +} + +struct fence_chains { + unsigned int chain_length; + struct dma_fence **fences; + struct dma_fence **chains; + + struct dma_fence *tail; +}; + +static uint64_t seqno_inc(unsigned int i) +{ + return i + 1; +} + +static int fence_chains_init(struct fence_chains *fc, unsigned int count, + uint64_t (*seqno_fn)(unsigned int)) +{ + unsigned int i; + int err = 0; + + fc->chains = kvmalloc_array(count, sizeof(*fc->chains), + GFP_KERNEL | __GFP_ZERO); + if (!fc->chains) + return -ENOMEM; + + fc->fences = kvmalloc_array(count, sizeof(*fc->fences), + GFP_KERNEL | __GFP_ZERO); + if (!fc->fences) { + err = -ENOMEM; + goto err_chains; + } + + fc->tail = NULL; + for (i = 0; i < count; i++) { + fc->fences[i] = mock_fence(); + if (!fc->fences[i]) { + err = -ENOMEM; + goto unwind; + } + + fc->chains[i] = mock_chain(fc->tail, + fc->fences[i], + seqno_fn(i)); + if (!fc->chains[i]) { + err = -ENOMEM; + goto unwind; + } + + fc->tail = fc->chains[i]; + } + + fc->chain_length = i; + return 0; + +unwind: + for (i = 0; i < count; i++) { + dma_fence_put(fc->fences[i]); + dma_fence_put(fc->chains[i]); + } + kvfree(fc->fences); +err_chains: + kvfree(fc->chains); + return err; +} + +static void fence_chains_fini(struct fence_chains *fc) +{ + unsigned int i; + + for (i = 0; i < fc->chain_length; i++) { + dma_fence_signal(fc->fences[i]); + dma_fence_put(fc->fences[i]); + } + kvfree(fc->fences); + + for (i = 0; i < fc->chain_length; i++) + dma_fence_put(fc->chains[i]); + kvfree(fc->chains); +} + +static int find_seqno(void *arg) +{ + struct fence_chains fc; + struct dma_fence *fence; + int err; + int i; + + err = fence_chains_init(&fc, 64, seqno_inc); + if (err) + return err; + + fence = dma_fence_get(fc.tail); + err = dma_fence_chain_find_seqno(&fence, 0); + dma_fence_put(fence); + if (err) { + pr_err("Reported %d for find_seqno(0)!\n", err); + goto err; + } + + for (i = 0; i < fc.chain_length; i++) { + fence = dma_fence_get(fc.tail); + err = dma_fence_chain_find_seqno(&fence, i + 1); + dma_fence_put(fence); + if (err) { + pr_err("Reported %d for find_seqno(%d:%d)!\n", + err, fc.chain_length + 1, i + 1); + goto err; + } + if (fence != fc.chains[i]) { + pr_err("Incorrect fence reported by find_seqno(%d:%d)\n", + fc.chain_length + 1, i + 1); + err = -EINVAL; + goto err; + } + + dma_fence_get(fence); + err = dma_fence_chain_find_seqno(&fence, i + 1); + dma_fence_put(fence); + if (err) { + pr_err("Error reported for finding self\n"); + goto err; + } + if (fence != fc.chains[i]) { + pr_err("Incorrect fence reported by find self\n"); + err = -EINVAL; + goto err; + } + + dma_fence_get(fence); + err = dma_fence_chain_find_seqno(&fence, i + 2); + dma_fence_put(fence); + if (!err) { + pr_err("Error not reported for future fence: find_seqno(%d:%d)!\n", + i + 1, i + 2); + err = -EINVAL; + goto err; + } + + dma_fence_get(fence); + err = dma_fence_chain_find_seqno(&fence, i); + dma_fence_put(fence); + if (err) { + pr_err("Error reported for previous fence!\n"); + goto err; + } + if (i > 0 && fence != fc.chains[i - 1]) { + pr_err("Incorrect fence reported by find_seqno(%d:%d)\n", + i + 1, i); + err = -EINVAL; + goto err; + } + } + +err: + fence_chains_fini(&fc); + return err; +} + +static int find_signaled(void *arg) +{ + struct fence_chains fc; + struct dma_fence *fence; + int err; + + err = fence_chains_init(&fc, 2, seqno_inc); + if (err) + return err; + + dma_fence_signal(fc.fences[0]); + + fence = dma_fence_get(fc.tail); + err = dma_fence_chain_find_seqno(&fence, 1); + dma_fence_put(fence); + if (err) { + pr_err("Reported %d for find_seqno()!\n", err); + goto err; + } + + if (fence && fence != fc.chains[0]) { + pr_err("Incorrect chain-fence.seqno:%lld reported for completed seqno:1\n", + fence->seqno); + + dma_fence_get(fence); + err = dma_fence_chain_find_seqno(&fence, 1); + dma_fence_put(fence); + if (err) + pr_err("Reported %d for finding self!\n", err); + + err = -EINVAL; + } + +err: + fence_chains_fini(&fc); + return err; +} + +static int find_out_of_order(void *arg) +{ + struct fence_chains fc; + struct dma_fence *fence; + int err; + + err = fence_chains_init(&fc, 3, seqno_inc); + if (err) + return err; + + dma_fence_signal(fc.fences[1]); + + fence = dma_fence_get(fc.tail); + err = dma_fence_chain_find_seqno(&fence, 2); + dma_fence_put(fence); + if (err) { + pr_err("Reported %d for find_seqno()!\n", err); + goto err; + } + + /* + * We signaled the middle fence (2) of the 1-2-3 chain. The behavior + * of the dma-fence-chain is to make us wait for all the fences up to + * the point we want. Since fence 1 is still not signaled, this what + * we should get as fence to wait upon (fence 2 being garbage + * collected during the traversal of the chain). + */ + if (fence != fc.chains[0]) { + pr_err("Incorrect chain-fence.seqno:%lld reported for completed seqno:2\n", + fence ? fence->seqno : 0); + + err = -EINVAL; + } + +err: + fence_chains_fini(&fc); + return err; +} + +static uint64_t seqno_inc2(unsigned int i) +{ + return 2 * i + 2; +} + +static int find_gap(void *arg) +{ + struct fence_chains fc; + struct dma_fence *fence; + int err; + int i; + + err = fence_chains_init(&fc, 64, seqno_inc2); + if (err) + return err; + + for (i = 0; i < fc.chain_length; i++) { + fence = dma_fence_get(fc.tail); + err = dma_fence_chain_find_seqno(&fence, 2 * i + 1); + dma_fence_put(fence); + if (err) { + pr_err("Reported %d for find_seqno(%d:%d)!\n", + err, fc.chain_length + 1, 2 * i + 1); + goto err; + } + if (fence != fc.chains[i]) { + pr_err("Incorrect fence.seqno:%lld reported by find_seqno(%d:%d)\n", + fence->seqno, + fc.chain_length + 1, + 2 * i + 1); + err = -EINVAL; + goto err; + } + + dma_fence_get(fence); + err = dma_fence_chain_find_seqno(&fence, 2 * i + 2); + dma_fence_put(fence); + if (err) { + pr_err("Error reported for finding self\n"); + goto err; + } + if (fence != fc.chains[i]) { + pr_err("Incorrect fence reported by find self\n"); + err = -EINVAL; + goto err; + } + } + +err: + fence_chains_fini(&fc); + return err; +} + +struct find_race { + struct fence_chains fc; + atomic_t children; +}; + +static int __find_race(void *arg) +{ + struct find_race *data = arg; + int err = 0; + + while (!kthread_should_stop()) { + struct dma_fence *fence = dma_fence_get(data->fc.tail); + int seqno; + + seqno = prandom_u32_max(data->fc.chain_length) + 1; + + err = dma_fence_chain_find_seqno(&fence, seqno); + if (err) { + pr_err("Failed to find fence seqno:%d\n", + seqno); + dma_fence_put(fence); + break; + } + if (!fence) + goto signal; + + /* + * We can only find ourselves if we are on fence we were + * looking for. + */ + if (fence->seqno == seqno) { + err = dma_fence_chain_find_seqno(&fence, seqno); + if (err) { + pr_err("Reported an invalid fence for find-self:%d\n", + seqno); + dma_fence_put(fence); + break; + } + } + + dma_fence_put(fence); + +signal: + seqno = prandom_u32_max(data->fc.chain_length - 1); + dma_fence_signal(data->fc.fences[seqno]); + cond_resched(); + } + + if (atomic_dec_and_test(&data->children)) + wake_up_var(&data->children); + return err; +} + +static int find_race(void *arg) +{ + struct find_race data; + int ncpus = num_online_cpus(); + struct task_struct **threads; + unsigned long count; + int err; + int i; + + err = fence_chains_init(&data.fc, CHAIN_SZ, seqno_inc); + if (err) + return err; + + threads = kmalloc_array(ncpus, sizeof(*threads), GFP_KERNEL); + if (!threads) { + err = -ENOMEM; + goto err; + } + + atomic_set(&data.children, 0); + for (i = 0; i < ncpus; i++) { + threads[i] = kthread_run(__find_race, &data, "dmabuf/%d", i); + if (IS_ERR(threads[i])) { + ncpus = i; + break; + } + atomic_inc(&data.children); + get_task_struct(threads[i]); + } + + wait_var_event_timeout(&data.children, + !atomic_read(&data.children), + 5 * HZ); + + for (i = 0; i < ncpus; i++) { + int ret; + + ret = kthread_stop(threads[i]); + if (ret && !err) + err = ret; + put_task_struct(threads[i]); + } + kfree(threads); + + count = 0; + for (i = 0; i < data.fc.chain_length; i++) + if (dma_fence_is_signaled(data.fc.fences[i])) + count++; + pr_info("Completed %lu cycles\n", count); + +err: + fence_chains_fini(&data.fc); + return err; +} + +static int signal_forward(void *arg) +{ + struct fence_chains fc; + int err; + int i; + + err = fence_chains_init(&fc, 64, seqno_inc); + if (err) + return err; + + for (i = 0; i < fc.chain_length; i++) { + dma_fence_signal(fc.fences[i]); + + if (!dma_fence_is_signaled(fc.chains[i])) { + pr_err("chain[%d] not signaled!\n", i); + err = -EINVAL; + goto err; + } + + if (i + 1 < fc.chain_length && + dma_fence_is_signaled(fc.chains[i + 1])) { + pr_err("chain[%d] is signaled!\n", i); + err = -EINVAL; + goto err; + } + } + +err: + fence_chains_fini(&fc); + return err; +} + +static int signal_backward(void *arg) +{ + struct fence_chains fc; + int err; + int i; + + err = fence_chains_init(&fc, 64, seqno_inc); + if (err) + return err; + + for (i = fc.chain_length; i--; ) { + dma_fence_signal(fc.fences[i]); + + if (i > 0 && dma_fence_is_signaled(fc.chains[i])) { + pr_err("chain[%d] is signaled!\n", i); + err = -EINVAL; + goto err; + } + } + + for (i = 0; i < fc.chain_length; i++) { + if (!dma_fence_is_signaled(fc.chains[i])) { + pr_err("chain[%d] was not signaled!\n", i); + err = -EINVAL; + goto err; + } + } + +err: + fence_chains_fini(&fc); + return err; +} + +static int __wait_fence_chains(void *arg) +{ + struct fence_chains *fc = arg; + + if (dma_fence_wait(fc->tail, false)) + return -EIO; + + return 0; +} + +static int wait_forward(void *arg) +{ + struct fence_chains fc; + struct task_struct *tsk; + int err; + int i; + + err = fence_chains_init(&fc, CHAIN_SZ, seqno_inc); + if (err) + return err; + + tsk = kthread_run(__wait_fence_chains, &fc, "dmabuf/wait"); + if (IS_ERR(tsk)) { + err = PTR_ERR(tsk); + goto err; + } + get_task_struct(tsk); + yield_to(tsk, true); + + for (i = 0; i < fc.chain_length; i++) + dma_fence_signal(fc.fences[i]); + + err = kthread_stop(tsk); + put_task_struct(tsk); + +err: + fence_chains_fini(&fc); + return err; +} + +static int wait_backward(void *arg) +{ + struct fence_chains fc; + struct task_struct *tsk; + int err; + int i; + + err = fence_chains_init(&fc, CHAIN_SZ, seqno_inc); + if (err) + return err; + + tsk = kthread_run(__wait_fence_chains, &fc, "dmabuf/wait"); + if (IS_ERR(tsk)) { + err = PTR_ERR(tsk); + goto err; + } + get_task_struct(tsk); + yield_to(tsk, true); + + for (i = fc.chain_length; i--; ) + dma_fence_signal(fc.fences[i]); + + err = kthread_stop(tsk); + put_task_struct(tsk); + +err: + fence_chains_fini(&fc); + return err; +} + +static void randomise_fences(struct fence_chains *fc) +{ + unsigned int count = fc->chain_length; + + /* Fisher-Yates shuffle courtesy of Knuth */ + while (--count) { + unsigned int swp; + + swp = prandom_u32_max(count + 1); + if (swp == count) + continue; + + swap(fc->fences[count], fc->fences[swp]); + } +} + +static int wait_random(void *arg) +{ + struct fence_chains fc; + struct task_struct *tsk; + int err; + int i; + + err = fence_chains_init(&fc, CHAIN_SZ, seqno_inc); + if (err) + return err; + + randomise_fences(&fc); + + tsk = kthread_run(__wait_fence_chains, &fc, "dmabuf/wait"); + if (IS_ERR(tsk)) { + err = PTR_ERR(tsk); + goto err; + } + get_task_struct(tsk); + yield_to(tsk, true); + + for (i = 0; i < fc.chain_length; i++) + dma_fence_signal(fc.fences[i]); + + err = kthread_stop(tsk); + put_task_struct(tsk); + +err: + fence_chains_fini(&fc); + return err; +} + +int dma_fence_chain(void) +{ + static const struct subtest tests[] = { + SUBTEST(sanitycheck), + SUBTEST(find_seqno), + SUBTEST(find_signaled), + SUBTEST(find_out_of_order), + SUBTEST(find_gap), + SUBTEST(find_race), + SUBTEST(signal_forward), + SUBTEST(signal_backward), + SUBTEST(wait_forward), + SUBTEST(wait_backward), + SUBTEST(wait_random), + }; + int ret; + + pr_info("sizeof(dma_fence_chain)=%zu\n", + sizeof(struct dma_fence_chain)); + + slab_fences = KMEM_CACHE(mock_fence, + SLAB_TYPESAFE_BY_RCU | + SLAB_HWCACHE_ALIGN); + if (!slab_fences) + return -ENOMEM; + + ret = subtests(tests, NULL); + + kmem_cache_destroy(slab_fences); + return ret; +} diff --git a/drivers/dma-buf/st-dma-fence.c b/drivers/dma-buf/st-dma-fence.c new file mode 100644 index 000000000..e59306434 --- /dev/null +++ b/drivers/dma-buf/st-dma-fence.c @@ -0,0 +1,574 @@ +/* SPDX-License-Identifier: MIT */ + +/* + * Copyright © 2019 Intel Corporation + */ + +#include <linux/delay.h> +#include <linux/dma-fence.h> +#include <linux/kernel.h> +#include <linux/kthread.h> +#include <linux/sched/signal.h> +#include <linux/slab.h> +#include <linux/spinlock.h> + +#include "selftest.h" + +static struct kmem_cache *slab_fences; + +static struct mock_fence { + struct dma_fence base; + struct spinlock lock; +} *to_mock_fence(struct dma_fence *f) { + return container_of(f, struct mock_fence, base); +} + +static const char *mock_name(struct dma_fence *f) +{ + return "mock"; +} + +static void mock_fence_release(struct dma_fence *f) +{ + kmem_cache_free(slab_fences, to_mock_fence(f)); +} + +struct wait_cb { + struct dma_fence_cb cb; + struct task_struct *task; +}; + +static void mock_wakeup(struct dma_fence *f, struct dma_fence_cb *cb) +{ + wake_up_process(container_of(cb, struct wait_cb, cb)->task); +} + +static long mock_wait(struct dma_fence *f, bool intr, long timeout) +{ + const int state = intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE; + struct wait_cb cb = { .task = current }; + + if (dma_fence_add_callback(f, &cb.cb, mock_wakeup)) + return timeout; + + while (timeout) { + set_current_state(state); + + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &f->flags)) + break; + + if (signal_pending_state(state, current)) + break; + + timeout = schedule_timeout(timeout); + } + __set_current_state(TASK_RUNNING); + + if (!dma_fence_remove_callback(f, &cb.cb)) + return timeout; + + if (signal_pending_state(state, current)) + return -ERESTARTSYS; + + return -ETIME; +} + +static const struct dma_fence_ops mock_ops = { + .get_driver_name = mock_name, + .get_timeline_name = mock_name, + .wait = mock_wait, + .release = mock_fence_release, +}; + +static struct dma_fence *mock_fence(void) +{ + struct mock_fence *f; + + f = kmem_cache_alloc(slab_fences, GFP_KERNEL); + if (!f) + return NULL; + + spin_lock_init(&f->lock); + dma_fence_init(&f->base, &mock_ops, &f->lock, 0, 0); + + return &f->base; +} + +static int sanitycheck(void *arg) +{ + struct dma_fence *f; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + dma_fence_signal(f); + dma_fence_put(f); + + return 0; +} + +static int test_signaling(void *arg) +{ + struct dma_fence *f; + int err = -EINVAL; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + if (dma_fence_is_signaled(f)) { + pr_err("Fence unexpectedly signaled on creation\n"); + goto err_free; + } + + if (dma_fence_signal(f)) { + pr_err("Fence reported being already signaled\n"); + goto err_free; + } + + if (!dma_fence_is_signaled(f)) { + pr_err("Fence not reporting signaled\n"); + goto err_free; + } + + if (!dma_fence_signal(f)) { + pr_err("Fence reported not being already signaled\n"); + goto err_free; + } + + err = 0; +err_free: + dma_fence_put(f); + return err; +} + +struct simple_cb { + struct dma_fence_cb cb; + bool seen; +}; + +static void simple_callback(struct dma_fence *f, struct dma_fence_cb *cb) +{ + smp_store_mb(container_of(cb, struct simple_cb, cb)->seen, true); +} + +static int test_add_callback(void *arg) +{ + struct simple_cb cb = {}; + struct dma_fence *f; + int err = -EINVAL; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + if (dma_fence_add_callback(f, &cb.cb, simple_callback)) { + pr_err("Failed to add callback, fence already signaled!\n"); + goto err_free; + } + + dma_fence_signal(f); + if (!cb.seen) { + pr_err("Callback failed!\n"); + goto err_free; + } + + err = 0; +err_free: + dma_fence_put(f); + return err; +} + +static int test_late_add_callback(void *arg) +{ + struct simple_cb cb = {}; + struct dma_fence *f; + int err = -EINVAL; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + dma_fence_signal(f); + + if (!dma_fence_add_callback(f, &cb.cb, simple_callback)) { + pr_err("Added callback, but fence was already signaled!\n"); + goto err_free; + } + + dma_fence_signal(f); + if (cb.seen) { + pr_err("Callback called after failed attachment !\n"); + goto err_free; + } + + err = 0; +err_free: + dma_fence_put(f); + return err; +} + +static int test_rm_callback(void *arg) +{ + struct simple_cb cb = {}; + struct dma_fence *f; + int err = -EINVAL; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + if (dma_fence_add_callback(f, &cb.cb, simple_callback)) { + pr_err("Failed to add callback, fence already signaled!\n"); + goto err_free; + } + + if (!dma_fence_remove_callback(f, &cb.cb)) { + pr_err("Failed to remove callback!\n"); + goto err_free; + } + + dma_fence_signal(f); + if (cb.seen) { + pr_err("Callback still signaled after removal!\n"); + goto err_free; + } + + err = 0; +err_free: + dma_fence_put(f); + return err; +} + +static int test_late_rm_callback(void *arg) +{ + struct simple_cb cb = {}; + struct dma_fence *f; + int err = -EINVAL; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + if (dma_fence_add_callback(f, &cb.cb, simple_callback)) { + pr_err("Failed to add callback, fence already signaled!\n"); + goto err_free; + } + + dma_fence_signal(f); + if (!cb.seen) { + pr_err("Callback failed!\n"); + goto err_free; + } + + if (dma_fence_remove_callback(f, &cb.cb)) { + pr_err("Callback removal succeed after being executed!\n"); + goto err_free; + } + + err = 0; +err_free: + dma_fence_put(f); + return err; +} + +static int test_status(void *arg) +{ + struct dma_fence *f; + int err = -EINVAL; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + if (dma_fence_get_status(f)) { + pr_err("Fence unexpectedly has signaled status on creation\n"); + goto err_free; + } + + dma_fence_signal(f); + if (!dma_fence_get_status(f)) { + pr_err("Fence not reporting signaled status\n"); + goto err_free; + } + + err = 0; +err_free: + dma_fence_put(f); + return err; +} + +static int test_error(void *arg) +{ + struct dma_fence *f; + int err = -EINVAL; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + dma_fence_set_error(f, -EIO); + + if (dma_fence_get_status(f)) { + pr_err("Fence unexpectedly has error status before signal\n"); + goto err_free; + } + + dma_fence_signal(f); + if (dma_fence_get_status(f) != -EIO) { + pr_err("Fence not reporting error status, got %d\n", + dma_fence_get_status(f)); + goto err_free; + } + + err = 0; +err_free: + dma_fence_put(f); + return err; +} + +static int test_wait(void *arg) +{ + struct dma_fence *f; + int err = -EINVAL; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + if (dma_fence_wait_timeout(f, false, 0) != -ETIME) { + pr_err("Wait reported complete before being signaled\n"); + goto err_free; + } + + dma_fence_signal(f); + + if (dma_fence_wait_timeout(f, false, 0) != 0) { + pr_err("Wait reported incomplete after being signaled\n"); + goto err_free; + } + + err = 0; +err_free: + dma_fence_signal(f); + dma_fence_put(f); + return err; +} + +struct wait_timer { + struct timer_list timer; + struct dma_fence *f; +}; + +static void wait_timer(struct timer_list *timer) +{ + struct wait_timer *wt = from_timer(wt, timer, timer); + + dma_fence_signal(wt->f); +} + +static int test_wait_timeout(void *arg) +{ + struct wait_timer wt; + int err = -EINVAL; + + timer_setup_on_stack(&wt.timer, wait_timer, 0); + + wt.f = mock_fence(); + if (!wt.f) + return -ENOMEM; + + if (dma_fence_wait_timeout(wt.f, false, 1) != -ETIME) { + pr_err("Wait reported complete before being signaled\n"); + goto err_free; + } + + mod_timer(&wt.timer, jiffies + 1); + + if (dma_fence_wait_timeout(wt.f, false, 2) == -ETIME) { + if (timer_pending(&wt.timer)) { + pr_notice("Timer did not fire within the jiffie!\n"); + err = 0; /* not our fault! */ + } else { + pr_err("Wait reported incomplete after timeout\n"); + } + goto err_free; + } + + err = 0; +err_free: + del_timer_sync(&wt.timer); + destroy_timer_on_stack(&wt.timer); + dma_fence_signal(wt.f); + dma_fence_put(wt.f); + return err; +} + +static int test_stub(void *arg) +{ + struct dma_fence *f[64]; + int err = -EINVAL; + int i; + + for (i = 0; i < ARRAY_SIZE(f); i++) { + f[i] = dma_fence_get_stub(); + if (!dma_fence_is_signaled(f[i])) { + pr_err("Obtained unsignaled stub fence!\n"); + goto err; + } + } + + err = 0; +err: + while (i--) + dma_fence_put(f[i]); + return err; +} + +/* Now off to the races! */ + +struct race_thread { + struct dma_fence __rcu **fences; + struct task_struct *task; + bool before; + int id; +}; + +static void __wait_for_callbacks(struct dma_fence *f) +{ + spin_lock_irq(f->lock); + spin_unlock_irq(f->lock); +} + +static int thread_signal_callback(void *arg) +{ + const struct race_thread *t = arg; + unsigned long pass = 0; + unsigned long miss = 0; + int err = 0; + + while (!err && !kthread_should_stop()) { + struct dma_fence *f1, *f2; + struct simple_cb cb; + + f1 = mock_fence(); + if (!f1) { + err = -ENOMEM; + break; + } + + rcu_assign_pointer(t->fences[t->id], f1); + smp_wmb(); + + rcu_read_lock(); + do { + f2 = dma_fence_get_rcu_safe(&t->fences[!t->id]); + } while (!f2 && !kthread_should_stop()); + rcu_read_unlock(); + + if (t->before) + dma_fence_signal(f1); + + smp_store_mb(cb.seen, false); + if (!f2 || dma_fence_add_callback(f2, &cb.cb, simple_callback)) + miss++, cb.seen = true; + + if (!t->before) + dma_fence_signal(f1); + + if (!cb.seen) { + dma_fence_wait(f2, false); + __wait_for_callbacks(f2); + } + + if (!READ_ONCE(cb.seen)) { + pr_err("Callback not seen on thread %d, pass %lu (%lu misses), signaling %s add_callback; fence signaled? %s\n", + t->id, pass, miss, + t->before ? "before" : "after", + dma_fence_is_signaled(f2) ? "yes" : "no"); + err = -EINVAL; + } + + dma_fence_put(f2); + + rcu_assign_pointer(t->fences[t->id], NULL); + smp_wmb(); + + dma_fence_put(f1); + + pass++; + } + + pr_info("%s[%d] completed %lu passes, %lu misses\n", + __func__, t->id, pass, miss); + return err; +} + +static int race_signal_callback(void *arg) +{ + struct dma_fence __rcu *f[2] = {}; + int ret = 0; + int pass; + + for (pass = 0; !ret && pass <= 1; pass++) { + struct race_thread t[2]; + int i; + + for (i = 0; i < ARRAY_SIZE(t); i++) { + t[i].fences = f; + t[i].id = i; + t[i].before = pass; + t[i].task = kthread_run(thread_signal_callback, &t[i], + "dma-fence:%d", i); + get_task_struct(t[i].task); + } + + msleep(50); + + for (i = 0; i < ARRAY_SIZE(t); i++) { + int err; + + err = kthread_stop(t[i].task); + if (err && !ret) + ret = err; + + put_task_struct(t[i].task); + } + } + + return ret; +} + +int dma_fence(void) +{ + static const struct subtest tests[] = { + SUBTEST(sanitycheck), + SUBTEST(test_signaling), + SUBTEST(test_add_callback), + SUBTEST(test_late_add_callback), + SUBTEST(test_rm_callback), + SUBTEST(test_late_rm_callback), + SUBTEST(test_status), + SUBTEST(test_error), + SUBTEST(test_wait), + SUBTEST(test_wait_timeout), + SUBTEST(test_stub), + SUBTEST(race_signal_callback), + }; + int ret; + + pr_info("sizeof(dma_fence)=%zu\n", sizeof(struct dma_fence)); + + slab_fences = KMEM_CACHE(mock_fence, + SLAB_TYPESAFE_BY_RCU | + SLAB_HWCACHE_ALIGN); + if (!slab_fences) + return -ENOMEM; + + ret = subtests(tests, NULL); + + kmem_cache_destroy(slab_fences); + + return ret; +} diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c new file mode 100644 index 000000000..7f5ed1aa7 --- /dev/null +++ b/drivers/dma-buf/sw_sync.c @@ -0,0 +1,412 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Sync File validation framework + * + * Copyright (C) 2012 Google, Inc. + */ + +#include <linux/file.h> +#include <linux/fs.h> +#include <linux/uaccess.h> +#include <linux/slab.h> +#include <linux/sync_file.h> + +#include "sync_debug.h" + +#define CREATE_TRACE_POINTS +#include "sync_trace.h" + +/* + * SW SYNC validation framework + * + * A sync object driver that uses a 32bit counter to coordinate + * synchronization. Useful when there is no hardware primitive backing + * the synchronization. + * + * To start the framework just open: + * + * <debugfs>/sync/sw_sync + * + * That will create a sync timeline, all fences created under this timeline + * file descriptor will belong to the this timeline. + * + * The 'sw_sync' file can be opened many times as to create different + * timelines. + * + * Fences can be created with SW_SYNC_IOC_CREATE_FENCE ioctl with struct + * sw_sync_create_fence_data as parameter. + * + * To increment the timeline counter, SW_SYNC_IOC_INC ioctl should be used + * with the increment as u32. This will update the last signaled value + * from the timeline and signal any fence that has a seqno smaller or equal + * to it. + * + * struct sw_sync_create_fence_data + * @value: the seqno to initialise the fence with + * @name: the name of the new sync point + * @fence: return the fd of the new sync_file with the created fence + */ +struct sw_sync_create_fence_data { + __u32 value; + char name[32]; + __s32 fence; /* fd of new fence */ +}; + +#define SW_SYNC_IOC_MAGIC 'W' + +#define SW_SYNC_IOC_CREATE_FENCE _IOWR(SW_SYNC_IOC_MAGIC, 0,\ + struct sw_sync_create_fence_data) + +#define SW_SYNC_IOC_INC _IOW(SW_SYNC_IOC_MAGIC, 1, __u32) + +static const struct dma_fence_ops timeline_fence_ops; + +static inline struct sync_pt *dma_fence_to_sync_pt(struct dma_fence *fence) +{ + if (fence->ops != &timeline_fence_ops) + return NULL; + return container_of(fence, struct sync_pt, base); +} + +/** + * sync_timeline_create() - creates a sync object + * @name: sync_timeline name + * + * Creates a new sync_timeline. Returns the sync_timeline object or NULL in + * case of error. + */ +static struct sync_timeline *sync_timeline_create(const char *name) +{ + struct sync_timeline *obj; + + obj = kzalloc(sizeof(*obj), GFP_KERNEL); + if (!obj) + return NULL; + + kref_init(&obj->kref); + obj->context = dma_fence_context_alloc(1); + strlcpy(obj->name, name, sizeof(obj->name)); + + obj->pt_tree = RB_ROOT; + INIT_LIST_HEAD(&obj->pt_list); + spin_lock_init(&obj->lock); + + sync_timeline_debug_add(obj); + + return obj; +} + +static void sync_timeline_free(struct kref *kref) +{ + struct sync_timeline *obj = + container_of(kref, struct sync_timeline, kref); + + sync_timeline_debug_remove(obj); + + kfree(obj); +} + +static void sync_timeline_get(struct sync_timeline *obj) +{ + kref_get(&obj->kref); +} + +static void sync_timeline_put(struct sync_timeline *obj) +{ + kref_put(&obj->kref, sync_timeline_free); +} + +static const char *timeline_fence_get_driver_name(struct dma_fence *fence) +{ + return "sw_sync"; +} + +static const char *timeline_fence_get_timeline_name(struct dma_fence *fence) +{ + struct sync_timeline *parent = dma_fence_parent(fence); + + return parent->name; +} + +static void timeline_fence_release(struct dma_fence *fence) +{ + struct sync_pt *pt = dma_fence_to_sync_pt(fence); + struct sync_timeline *parent = dma_fence_parent(fence); + unsigned long flags; + + spin_lock_irqsave(fence->lock, flags); + if (!list_empty(&pt->link)) { + list_del(&pt->link); + rb_erase(&pt->node, &parent->pt_tree); + } + spin_unlock_irqrestore(fence->lock, flags); + + sync_timeline_put(parent); + dma_fence_free(fence); +} + +static bool timeline_fence_signaled(struct dma_fence *fence) +{ + struct sync_timeline *parent = dma_fence_parent(fence); + + return !__dma_fence_is_later(fence->seqno, parent->value, fence->ops); +} + +static bool timeline_fence_enable_signaling(struct dma_fence *fence) +{ + return true; +} + +static void timeline_fence_value_str(struct dma_fence *fence, + char *str, int size) +{ + snprintf(str, size, "%lld", fence->seqno); +} + +static void timeline_fence_timeline_value_str(struct dma_fence *fence, + char *str, int size) +{ + struct sync_timeline *parent = dma_fence_parent(fence); + + snprintf(str, size, "%d", parent->value); +} + +static const struct dma_fence_ops timeline_fence_ops = { + .get_driver_name = timeline_fence_get_driver_name, + .get_timeline_name = timeline_fence_get_timeline_name, + .enable_signaling = timeline_fence_enable_signaling, + .signaled = timeline_fence_signaled, + .release = timeline_fence_release, + .fence_value_str = timeline_fence_value_str, + .timeline_value_str = timeline_fence_timeline_value_str, +}; + +/** + * sync_timeline_signal() - signal a status change on a sync_timeline + * @obj: sync_timeline to signal + * @inc: num to increment on timeline->value + * + * A sync implementation should call this any time one of it's fences + * has signaled or has an error condition. + */ +static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc) +{ + LIST_HEAD(signalled); + struct sync_pt *pt, *next; + + trace_sync_timeline(obj); + + spin_lock_irq(&obj->lock); + + obj->value += inc; + + list_for_each_entry_safe(pt, next, &obj->pt_list, link) { + if (!timeline_fence_signaled(&pt->base)) + break; + + dma_fence_get(&pt->base); + + list_move_tail(&pt->link, &signalled); + rb_erase(&pt->node, &obj->pt_tree); + + dma_fence_signal_locked(&pt->base); + } + + spin_unlock_irq(&obj->lock); + + list_for_each_entry_safe(pt, next, &signalled, link) { + list_del_init(&pt->link); + dma_fence_put(&pt->base); + } +} + +/** + * sync_pt_create() - creates a sync pt + * @obj: parent sync_timeline + * @value: value of the fence + * + * Creates a new sync_pt (fence) as a child of @parent. @size bytes will be + * allocated allowing for implementation specific data to be kept after + * the generic sync_timeline struct. Returns the sync_pt object or + * NULL in case of error. + */ +static struct sync_pt *sync_pt_create(struct sync_timeline *obj, + unsigned int value) +{ + struct sync_pt *pt; + + pt = kzalloc(sizeof(*pt), GFP_KERNEL); + if (!pt) + return NULL; + + sync_timeline_get(obj); + dma_fence_init(&pt->base, &timeline_fence_ops, &obj->lock, + obj->context, value); + INIT_LIST_HEAD(&pt->link); + + spin_lock_irq(&obj->lock); + if (!dma_fence_is_signaled_locked(&pt->base)) { + struct rb_node **p = &obj->pt_tree.rb_node; + struct rb_node *parent = NULL; + + while (*p) { + struct sync_pt *other; + int cmp; + + parent = *p; + other = rb_entry(parent, typeof(*pt), node); + cmp = value - other->base.seqno; + if (cmp > 0) { + p = &parent->rb_right; + } else if (cmp < 0) { + p = &parent->rb_left; + } else { + if (dma_fence_get_rcu(&other->base)) { + sync_timeline_put(obj); + kfree(pt); + pt = other; + goto unlock; + } + p = &parent->rb_left; + } + } + rb_link_node(&pt->node, parent, p); + rb_insert_color(&pt->node, &obj->pt_tree); + + parent = rb_next(&pt->node); + list_add_tail(&pt->link, + parent ? &rb_entry(parent, typeof(*pt), node)->link : &obj->pt_list); + } +unlock: + spin_unlock_irq(&obj->lock); + + return pt; +} + +/* + * *WARNING* + * + * improper use of this can result in deadlocking kernel drivers from userspace. + */ + +/* opening sw_sync create a new sync obj */ +static int sw_sync_debugfs_open(struct inode *inode, struct file *file) +{ + struct sync_timeline *obj; + char task_comm[TASK_COMM_LEN]; + + get_task_comm(task_comm, current); + + obj = sync_timeline_create(task_comm); + if (!obj) + return -ENOMEM; + + file->private_data = obj; + + return 0; +} + +static int sw_sync_debugfs_release(struct inode *inode, struct file *file) +{ + struct sync_timeline *obj = file->private_data; + struct sync_pt *pt, *next; + + spin_lock_irq(&obj->lock); + + list_for_each_entry_safe(pt, next, &obj->pt_list, link) { + dma_fence_set_error(&pt->base, -ENOENT); + dma_fence_signal_locked(&pt->base); + } + + spin_unlock_irq(&obj->lock); + + sync_timeline_put(obj); + return 0; +} + +static long sw_sync_ioctl_create_fence(struct sync_timeline *obj, + unsigned long arg) +{ + int fd = get_unused_fd_flags(O_CLOEXEC); + int err; + struct sync_pt *pt; + struct sync_file *sync_file; + struct sw_sync_create_fence_data data; + + if (fd < 0) + return fd; + + if (copy_from_user(&data, (void __user *)arg, sizeof(data))) { + err = -EFAULT; + goto err; + } + + pt = sync_pt_create(obj, data.value); + if (!pt) { + err = -ENOMEM; + goto err; + } + + sync_file = sync_file_create(&pt->base); + dma_fence_put(&pt->base); + if (!sync_file) { + err = -ENOMEM; + goto err; + } + + data.fence = fd; + if (copy_to_user((void __user *)arg, &data, sizeof(data))) { + fput(sync_file->file); + err = -EFAULT; + goto err; + } + + fd_install(fd, sync_file->file); + + return 0; + +err: + put_unused_fd(fd); + return err; +} + +static long sw_sync_ioctl_inc(struct sync_timeline *obj, unsigned long arg) +{ + u32 value; + + if (copy_from_user(&value, (void __user *)arg, sizeof(value))) + return -EFAULT; + + while (value > INT_MAX) { + sync_timeline_signal(obj, INT_MAX); + value -= INT_MAX; + } + + sync_timeline_signal(obj, value); + + return 0; +} + +static long sw_sync_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct sync_timeline *obj = file->private_data; + + switch (cmd) { + case SW_SYNC_IOC_CREATE_FENCE: + return sw_sync_ioctl_create_fence(obj, arg); + + case SW_SYNC_IOC_INC: + return sw_sync_ioctl_inc(obj, arg); + + default: + return -ENOTTY; + } +} + +const struct file_operations sw_sync_debugfs_fops = { + .open = sw_sync_debugfs_open, + .release = sw_sync_debugfs_release, + .unlocked_ioctl = sw_sync_ioctl, + .compat_ioctl = compat_ptr_ioctl, +}; diff --git a/drivers/dma-buf/sync_debug.c b/drivers/dma-buf/sync_debug.c new file mode 100644 index 000000000..101394f16 --- /dev/null +++ b/drivers/dma-buf/sync_debug.c @@ -0,0 +1,190 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Sync File validation framework and debug information + * + * Copyright (C) 2012 Google, Inc. + */ + +#include <linux/debugfs.h> +#include "sync_debug.h" + +static struct dentry *dbgfs; + +static LIST_HEAD(sync_timeline_list_head); +static DEFINE_SPINLOCK(sync_timeline_list_lock); +static LIST_HEAD(sync_file_list_head); +static DEFINE_SPINLOCK(sync_file_list_lock); + +void sync_timeline_debug_add(struct sync_timeline *obj) +{ + unsigned long flags; + + spin_lock_irqsave(&sync_timeline_list_lock, flags); + list_add_tail(&obj->sync_timeline_list, &sync_timeline_list_head); + spin_unlock_irqrestore(&sync_timeline_list_lock, flags); +} + +void sync_timeline_debug_remove(struct sync_timeline *obj) +{ + unsigned long flags; + + spin_lock_irqsave(&sync_timeline_list_lock, flags); + list_del(&obj->sync_timeline_list); + spin_unlock_irqrestore(&sync_timeline_list_lock, flags); +} + +void sync_file_debug_add(struct sync_file *sync_file) +{ + unsigned long flags; + + spin_lock_irqsave(&sync_file_list_lock, flags); + list_add_tail(&sync_file->sync_file_list, &sync_file_list_head); + spin_unlock_irqrestore(&sync_file_list_lock, flags); +} + +void sync_file_debug_remove(struct sync_file *sync_file) +{ + unsigned long flags; + + spin_lock_irqsave(&sync_file_list_lock, flags); + list_del(&sync_file->sync_file_list); + spin_unlock_irqrestore(&sync_file_list_lock, flags); +} + +static const char *sync_status_str(int status) +{ + if (status < 0) + return "error"; + + if (status > 0) + return "signaled"; + + return "active"; +} + +static void sync_print_fence(struct seq_file *s, + struct dma_fence *fence, bool show) +{ + struct sync_timeline *parent = dma_fence_parent(fence); + int status; + + status = dma_fence_get_status_locked(fence); + + seq_printf(s, " %s%sfence %s", + show ? parent->name : "", + show ? "_" : "", + sync_status_str(status)); + + if (test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags)) { + struct timespec64 ts64 = + ktime_to_timespec64(fence->timestamp); + + seq_printf(s, "@%lld.%09ld", (s64)ts64.tv_sec, ts64.tv_nsec); + } + + if (fence->ops->timeline_value_str && + fence->ops->fence_value_str) { + char value[64]; + bool success; + + fence->ops->fence_value_str(fence, value, sizeof(value)); + success = strlen(value); + + if (success) { + seq_printf(s, ": %s", value); + + fence->ops->timeline_value_str(fence, value, + sizeof(value)); + + if (strlen(value)) + seq_printf(s, " / %s", value); + } + } + + seq_putc(s, '\n'); +} + +static void sync_print_obj(struct seq_file *s, struct sync_timeline *obj) +{ + struct list_head *pos; + + seq_printf(s, "%s: %d\n", obj->name, obj->value); + + spin_lock_irq(&obj->lock); + list_for_each(pos, &obj->pt_list) { + struct sync_pt *pt = container_of(pos, struct sync_pt, link); + sync_print_fence(s, &pt->base, false); + } + spin_unlock_irq(&obj->lock); +} + +static void sync_print_sync_file(struct seq_file *s, + struct sync_file *sync_file) +{ + char buf[128]; + int i; + + seq_printf(s, "[%p] %s: %s\n", sync_file, + sync_file_get_name(sync_file, buf, sizeof(buf)), + sync_status_str(dma_fence_get_status(sync_file->fence))); + + if (dma_fence_is_array(sync_file->fence)) { + struct dma_fence_array *array = to_dma_fence_array(sync_file->fence); + + for (i = 0; i < array->num_fences; ++i) + sync_print_fence(s, array->fences[i], true); + } else { + sync_print_fence(s, sync_file->fence, true); + } +} + +static int sync_info_debugfs_show(struct seq_file *s, void *unused) +{ + struct list_head *pos; + + seq_puts(s, "objs:\n--------------\n"); + + spin_lock_irq(&sync_timeline_list_lock); + list_for_each(pos, &sync_timeline_list_head) { + struct sync_timeline *obj = + container_of(pos, struct sync_timeline, + sync_timeline_list); + + sync_print_obj(s, obj); + seq_putc(s, '\n'); + } + spin_unlock_irq(&sync_timeline_list_lock); + + seq_puts(s, "fences:\n--------------\n"); + + spin_lock_irq(&sync_file_list_lock); + list_for_each(pos, &sync_file_list_head) { + struct sync_file *sync_file = + container_of(pos, struct sync_file, sync_file_list); + + sync_print_sync_file(s, sync_file); + seq_putc(s, '\n'); + } + spin_unlock_irq(&sync_file_list_lock); + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(sync_info_debugfs); + +static __init int sync_debugfs_init(void) +{ + dbgfs = debugfs_create_dir("sync", NULL); + + /* + * The debugfs files won't ever get removed and thus, there is + * no need to protect it against removal races. The use of + * debugfs_create_file_unsafe() is actually safe here. + */ + debugfs_create_file_unsafe("info", 0444, dbgfs, NULL, + &sync_info_debugfs_fops); + debugfs_create_file_unsafe("sw_sync", 0644, dbgfs, NULL, + &sw_sync_debugfs_fops); + + return 0; +} +late_initcall(sync_debugfs_init); diff --git a/drivers/dma-buf/sync_debug.h b/drivers/dma-buf/sync_debug.h new file mode 100644 index 000000000..6176e52ba --- /dev/null +++ b/drivers/dma-buf/sync_debug.h @@ -0,0 +1,72 @@ +/* + * Sync File validation framework and debug infomation + * + * Copyright (C) 2012 Google, Inc. + * + * 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. + * + */ + +#ifndef _LINUX_SYNC_H +#define _LINUX_SYNC_H + +#include <linux/list.h> +#include <linux/rbtree.h> +#include <linux/spinlock.h> +#include <linux/dma-fence.h> + +#include <linux/sync_file.h> +#include <uapi/linux/sync_file.h> + +/** + * struct sync_timeline - sync object + * @kref: reference count on fence. + * @name: name of the sync_timeline. Useful for debugging + * @lock: lock protecting @pt_list and @value + * @pt_tree: rbtree of active (unsignaled/errored) sync_pts + * @pt_list: list of active (unsignaled/errored) sync_pts + * @sync_timeline_list: membership in global sync_timeline_list + */ +struct sync_timeline { + struct kref kref; + char name[32]; + + /* protected by lock */ + u64 context; + int value; + + struct rb_root pt_tree; + struct list_head pt_list; + spinlock_t lock; + + struct list_head sync_timeline_list; +}; + +static inline struct sync_timeline *dma_fence_parent(struct dma_fence *fence) +{ + return container_of(fence->lock, struct sync_timeline, lock); +} + +/** + * struct sync_pt - sync_pt object + * @base: base fence object + * @link: link on the sync timeline's list + * @node: node in the sync timeline's tree + */ +struct sync_pt { + struct dma_fence base; + struct list_head link; + struct rb_node node; +}; + +extern const struct file_operations sw_sync_debugfs_fops; + +void sync_timeline_debug_add(struct sync_timeline *obj); +void sync_timeline_debug_remove(struct sync_timeline *obj); +void sync_file_debug_add(struct sync_file *fence); +void sync_file_debug_remove(struct sync_file *fence); + +#endif /* _LINUX_SYNC_H */ diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c new file mode 100644 index 000000000..f0c822952 --- /dev/null +++ b/drivers/dma-buf/sync_file.c @@ -0,0 +1,485 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * drivers/dma-buf/sync_file.c + * + * Copyright (C) 2012 Google, Inc. + */ + +#include <linux/export.h> +#include <linux/file.h> +#include <linux/fs.h> +#include <linux/kernel.h> +#include <linux/poll.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/anon_inodes.h> +#include <linux/sync_file.h> +#include <uapi/linux/sync_file.h> + +static const struct file_operations sync_file_fops; + +static struct sync_file *sync_file_alloc(void) +{ + struct sync_file *sync_file; + + sync_file = kzalloc(sizeof(*sync_file), GFP_KERNEL); + if (!sync_file) + return NULL; + + sync_file->file = anon_inode_getfile("sync_file", &sync_file_fops, + sync_file, 0); + if (IS_ERR(sync_file->file)) + goto err; + + init_waitqueue_head(&sync_file->wq); + + INIT_LIST_HEAD(&sync_file->cb.node); + + return sync_file; + +err: + kfree(sync_file); + return NULL; +} + +static void fence_check_cb_func(struct dma_fence *f, struct dma_fence_cb *cb) +{ + struct sync_file *sync_file; + + sync_file = container_of(cb, struct sync_file, cb); + + wake_up_all(&sync_file->wq); +} + +/** + * sync_file_create() - creates a sync file + * @fence: fence to add to the sync_fence + * + * Creates a sync_file containg @fence. This function acquires and additional + * reference of @fence for the newly-created &sync_file, if it succeeds. The + * sync_file can be released with fput(sync_file->file). Returns the + * sync_file or NULL in case of error. + */ +struct sync_file *sync_file_create(struct dma_fence *fence) +{ + struct sync_file *sync_file; + + sync_file = sync_file_alloc(); + if (!sync_file) + return NULL; + + sync_file->fence = dma_fence_get(fence); + + return sync_file; +} +EXPORT_SYMBOL(sync_file_create); + +static struct sync_file *sync_file_fdget(int fd) +{ + struct file *file = fget(fd); + + if (!file) + return NULL; + + if (file->f_op != &sync_file_fops) + goto err; + + return file->private_data; + +err: + fput(file); + return NULL; +} + +/** + * sync_file_get_fence - get the fence related to the sync_file fd + * @fd: sync_file fd to get the fence from + * + * Ensures @fd references a valid sync_file and returns a fence that + * represents all fence in the sync_file. On error NULL is returned. + */ +struct dma_fence *sync_file_get_fence(int fd) +{ + struct sync_file *sync_file; + struct dma_fence *fence; + + sync_file = sync_file_fdget(fd); + if (!sync_file) + return NULL; + + fence = dma_fence_get(sync_file->fence); + fput(sync_file->file); + + return fence; +} +EXPORT_SYMBOL(sync_file_get_fence); + +/** + * sync_file_get_name - get the name of the sync_file + * @sync_file: sync_file to get the fence from + * @buf: destination buffer to copy sync_file name into + * @len: available size of destination buffer. + * + * Each sync_file may have a name assigned either by the user (when merging + * sync_files together) or created from the fence it contains. In the latter + * case construction of the name is deferred until use, and so requires + * sync_file_get_name(). + * + * Returns: a string representing the name. + */ +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); + } else { + struct dma_fence *fence = sync_file->fence; + + snprintf(buf, len, "%s-%s%llu-%lld", + fence->ops->get_driver_name(fence), + fence->ops->get_timeline_name(fence), + fence->context, + fence->seqno); + } + + 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 + * @a: sync_file a + * @b: sync_file b + * + * Creates a new sync_file which contains copies of all the fences in both + * @a and @b. @a and @b remain valid, independent sync_file. Returns the + * new merged sync_file or NULL in case of error. + */ +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; + + 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(fences, i * sizeof(*fences), + GFP_KERNEL); + if (!nfences) + goto err; + + fences = nfences; + } + + if (sync_file_set_fence(sync_file, fences, i) < 0) + goto err; + + strlcpy(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) +{ + struct sync_file *sync_file = file->private_data; + + if (test_bit(POLL_ENABLED, &sync_file->flags)) + dma_fence_remove_callback(sync_file->fence, &sync_file->cb); + dma_fence_put(sync_file->fence); + kfree(sync_file); + + return 0; +} + +static __poll_t sync_file_poll(struct file *file, poll_table *wait) +{ + struct sync_file *sync_file = file->private_data; + + poll_wait(file, &sync_file->wq, wait); + + if (list_empty(&sync_file->cb.node) && + !test_and_set_bit(POLL_ENABLED, &sync_file->flags)) { + if (dma_fence_add_callback(sync_file->fence, &sync_file->cb, + fence_check_cb_func) < 0) + wake_up_all(&sync_file->wq); + } + + return dma_fence_is_signaled(sync_file->fence) ? EPOLLIN : 0; +} + +static long sync_file_ioctl_merge(struct sync_file *sync_file, + unsigned long arg) +{ + int fd = get_unused_fd_flags(O_CLOEXEC); + int err; + struct sync_file *fence2, *fence3; + struct sync_merge_data data; + + if (fd < 0) + return fd; + + if (copy_from_user(&data, (void __user *)arg, sizeof(data))) { + err = -EFAULT; + goto err_put_fd; + } + + if (data.flags || data.pad) { + err = -EINVAL; + goto err_put_fd; + } + + fence2 = sync_file_fdget(data.fd2); + if (!fence2) { + err = -ENOENT; + goto err_put_fd; + } + + data.name[sizeof(data.name) - 1] = '\0'; + fence3 = sync_file_merge(data.name, sync_file, fence2); + if (!fence3) { + err = -ENOMEM; + goto err_put_fence2; + } + + data.fence = fd; + if (copy_to_user((void __user *)arg, &data, sizeof(data))) { + err = -EFAULT; + goto err_put_fence3; + } + + fd_install(fd, fence3->file); + fput(fence2->file); + return 0; + +err_put_fence3: + fput(fence3->file); + +err_put_fence2: + fput(fence2->file); + +err_put_fd: + put_unused_fd(fd); + return err; +} + +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), + sizeof(info->obj_name)); + strlcpy(info->driver_name, fence->ops->get_driver_name(fence), + sizeof(info->driver_name)); + + info->status = dma_fence_get_status(fence); + while (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags) && + !test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags)) + cpu_relax(); + info->timestamp_ns = + test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags) ? + ktime_to_ns(fence->timestamp) : + ktime_set(0, 0); + + return info->status; +} + +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; + __u32 size; + int num_fences, ret, i; + + if (copy_from_user(&info, (void __user *)arg, sizeof(info))) + return -EFAULT; + + if (info.flags || info.pad) + return -EINVAL; + + fences = get_fences(sync_file, &num_fences); + + /* + * Passing num_fences = 0 means that userspace doesn't want to + * retrieve any sync_fence_info. If num_fences = 0 we skip filling + * sync_fence_info and return the actual number of fences on + * info->num_fences. + */ + if (!info.num_fences) { + info.status = dma_fence_get_status(sync_file->fence); + goto no_fences; + } else { + info.status = 1; + } + + if (info.num_fences < num_fences) + return -EINVAL; + + size = num_fences * sizeof(*fence_info); + fence_info = kzalloc(size, GFP_KERNEL); + if (!fence_info) + return -ENOMEM; + + for (i = 0; i < num_fences; i++) { + int status = sync_fill_fence_info(fences[i], &fence_info[i]); + info.status = info.status <= 0 ? info.status : status; + } + + if (copy_to_user(u64_to_user_ptr(info.sync_fence_info), fence_info, + size)) { + ret = -EFAULT; + goto out; + } + +no_fences: + sync_file_get_name(sync_file, info.name, sizeof(info.name)); + info.num_fences = num_fences; + + if (copy_to_user((void __user *)arg, &info, sizeof(info))) + ret = -EFAULT; + else + ret = 0; + +out: + kfree(fence_info); + + return ret; +} + +static long sync_file_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct sync_file *sync_file = file->private_data; + + switch (cmd) { + case SYNC_IOC_MERGE: + return sync_file_ioctl_merge(sync_file, arg); + + case SYNC_IOC_FILE_INFO: + return sync_file_ioctl_fence_info(sync_file, arg); + + default: + return -ENOTTY; + } +} + +static const struct file_operations sync_file_fops = { + .release = sync_file_release, + .poll = sync_file_poll, + .unlocked_ioctl = sync_file_ioctl, + .compat_ioctl = compat_ptr_ioctl, +}; diff --git a/drivers/dma-buf/sync_trace.h b/drivers/dma-buf/sync_trace.h new file mode 100644 index 000000000..06e468a21 --- /dev/null +++ b/drivers/dma-buf/sync_trace.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_INCLUDE_PATH ../../drivers/dma-buf +#define TRACE_SYSTEM sync_trace + +#if !defined(_TRACE_SYNC_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_SYNC_H + +#include "sync_debug.h" +#include <linux/tracepoint.h> + +TRACE_EVENT(sync_timeline, + TP_PROTO(struct sync_timeline *timeline), + + TP_ARGS(timeline), + + TP_STRUCT__entry( + __string(name, timeline->name) + __field(u32, value) + ), + + TP_fast_assign( + __assign_str(name, timeline->name); + __entry->value = timeline->value; + ), + + TP_printk("name=%s value=%d", __get_str(name), __entry->value) +); + +#endif /* if !defined(_TRACE_SYNC_H) || defined(TRACE_HEADER_MULTI_READ) */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c new file mode 100644 index 000000000..e359c5c6c --- /dev/null +++ b/drivers/dma-buf/udmabuf.c @@ -0,0 +1,361 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/cred.h> +#include <linux/device.h> +#include <linux/dma-buf.h> +#include <linux/highmem.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/memfd.h> +#include <linux/miscdevice.h> +#include <linux/module.h> +#include <linux/shmem_fs.h> +#include <linux/slab.h> +#include <linux/udmabuf.h> + +static const u32 list_limit = 1024; /* udmabuf_create_list->count limit */ +static const size_t size_limit_mb = 64; /* total dmabuf size, in megabytes */ + +struct udmabuf { + pgoff_t pagecount; + struct page **pages; + struct sg_table *sg; + struct miscdevice *device; +}; + +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; + + if (pgoff >= ubuf->pagecount) + return VM_FAULT_SIGBUS; + vmf->page = ubuf->pages[pgoff]; + get_page(vmf->page); + return 0; +} + +static const struct vm_operations_struct udmabuf_vm_ops = { + .fault = udmabuf_vm_fault, +}; + +static int mmap_udmabuf(struct dma_buf *buf, struct vm_area_struct *vma) +{ + struct udmabuf *ubuf = buf->priv; + + if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0) + return -EINVAL; + + vma->vm_ops = &udmabuf_vm_ops; + vma->vm_private_data = ubuf; + return 0; +} + +static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf, + enum dma_data_direction direction) +{ + struct udmabuf *ubuf = buf->priv; + struct sg_table *sg; + int ret; + + sg = kzalloc(sizeof(*sg), GFP_KERNEL); + if (!sg) + return ERR_PTR(-ENOMEM); + ret = sg_alloc_table_from_pages(sg, ubuf->pages, ubuf->pagecount, + 0, ubuf->pagecount << PAGE_SHIFT, + GFP_KERNEL); + if (ret < 0) + goto err; + ret = dma_map_sgtable(dev, sg, direction, 0); + if (ret < 0) + goto err; + return sg; + +err: + sg_free_table(sg); + kfree(sg); + return ERR_PTR(ret); +} + +static void put_sg_table(struct device *dev, struct sg_table *sg, + enum dma_data_direction direction) +{ + dma_unmap_sgtable(dev, sg, direction, 0); + sg_free_table(sg); + kfree(sg); +} + +static struct sg_table *map_udmabuf(struct dma_buf_attachment *at, + enum dma_data_direction direction) +{ + return get_sg_table(at->dev, at->dmabuf, direction); +} + +static void unmap_udmabuf(struct dma_buf_attachment *at, + struct sg_table *sg, + enum dma_data_direction direction) +{ + return put_sg_table(at->dev, sg, direction); +} + +static void release_udmabuf(struct dma_buf *buf) +{ + struct udmabuf *ubuf = buf->priv; + struct device *dev = ubuf->device->this_device; + pgoff_t pg; + + if (ubuf->sg) + put_sg_table(dev, ubuf->sg, DMA_BIDIRECTIONAL); + + for (pg = 0; pg < ubuf->pagecount; pg++) + put_page(ubuf->pages[pg]); + kfree(ubuf->pages); + kfree(ubuf); +} + +static int begin_cpu_udmabuf(struct dma_buf *buf, + enum dma_data_direction direction) +{ + 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)) { + ret = PTR_ERR(ubuf->sg); + ubuf->sg = NULL; + } + } else { + dma_sync_sg_for_cpu(dev, ubuf->sg->sgl, ubuf->sg->nents, + direction); + } + + return ret; +} + +static int end_cpu_udmabuf(struct dma_buf *buf, + enum dma_data_direction direction) +{ + struct udmabuf *ubuf = buf->priv; + struct device *dev = ubuf->device->this_device; + + if (!ubuf->sg) + return -EINVAL; + + dma_sync_sg_for_device(dev, ubuf->sg->sgl, ubuf->sg->nents, direction); + return 0; +} + +static const struct dma_buf_ops udmabuf_ops = { + .cache_sgt_mapping = true, + .map_dma_buf = map_udmabuf, + .unmap_dma_buf = unmap_udmabuf, + .release = release_udmabuf, + .mmap = mmap_udmabuf, + .begin_cpu_access = begin_cpu_udmabuf, + .end_cpu_access = end_cpu_udmabuf, +}; + +#define SEALS_WANTED (F_SEAL_SHRINK) +#define SEALS_DENIED (F_SEAL_WRITE) + +static long udmabuf_create(struct miscdevice *device, + struct udmabuf_create_list *head, + struct udmabuf_create_item *list) +{ + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); + struct file *memfd = NULL; + struct udmabuf *ubuf; + struct dma_buf *buf; + pgoff_t pgoff, pgcnt, pgidx, pgbuf = 0, pglimit; + struct page *page; + int seals, ret = -EINVAL; + u32 i, flags; + + ubuf = kzalloc(sizeof(*ubuf), GFP_KERNEL); + if (!ubuf) + return -ENOMEM; + + pglimit = (size_limit_mb * 1024 * 1024) >> PAGE_SHIFT; + for (i = 0; i < head->count; i++) { + if (!IS_ALIGNED(list[i].offset, PAGE_SIZE)) + goto err; + if (!IS_ALIGNED(list[i].size, PAGE_SIZE)) + goto err; + ubuf->pagecount += list[i].size >> PAGE_SHIFT; + 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) { + ret = -ENOMEM; + goto err; + } + + pgbuf = 0; + for (i = 0; i < head->count; i++) { + ret = -EBADFD; + memfd = fget(list[i].memfd); + if (!memfd) + goto err; + if (!shmem_mapping(file_inode(memfd)->i_mapping)) + goto err; + seals = memfd_fcntl(memfd, F_GET_SEALS, 0); + if (seals == -EINVAL) + goto err; + ret = -EINVAL; + if ((seals & SEALS_WANTED) != SEALS_WANTED || + (seals & SEALS_DENIED) != 0) + goto err; + pgoff = list[i].offset >> PAGE_SHIFT; + pgcnt = list[i].size >> PAGE_SHIFT; + for (pgidx = 0; pgidx < pgcnt; pgidx++) { + page = shmem_read_mapping_page( + file_inode(memfd)->i_mapping, pgoff + pgidx); + if (IS_ERR(page)) { + ret = PTR_ERR(page); + goto err; + } + ubuf->pages[pgbuf++] = page; + } + fput(memfd); + memfd = NULL; + } + + exp_info.ops = &udmabuf_ops; + exp_info.size = ubuf->pagecount << PAGE_SHIFT; + exp_info.priv = ubuf; + exp_info.flags = O_RDWR; + + ubuf->device = device; + buf = dma_buf_export(&exp_info); + if (IS_ERR(buf)) { + ret = PTR_ERR(buf); + goto err; + } + + flags = 0; + if (head->flags & UDMABUF_FLAGS_CLOEXEC) + flags |= O_CLOEXEC; + return dma_buf_fd(buf, flags); + +err: + while (pgbuf > 0) + put_page(ubuf->pages[--pgbuf]); + if (memfd) + fput(memfd); + kfree(ubuf->pages); + kfree(ubuf); + return ret; +} + +static long udmabuf_ioctl_create(struct file *filp, unsigned long arg) +{ + struct udmabuf_create create; + struct udmabuf_create_list head; + struct udmabuf_create_item list; + + if (copy_from_user(&create, (void __user *)arg, + sizeof(create))) + return -EFAULT; + + head.flags = create.flags; + head.count = 1; + list.memfd = create.memfd; + list.offset = create.offset; + list.size = create.size; + + return udmabuf_create(filp->private_data, &head, &list); +} + +static long udmabuf_ioctl_create_list(struct file *filp, unsigned long arg) +{ + struct udmabuf_create_list head; + struct udmabuf_create_item *list; + int ret = -EINVAL; + u32 lsize; + + if (copy_from_user(&head, (void __user *)arg, sizeof(head))) + return -EFAULT; + if (head.count > list_limit) + return -EINVAL; + lsize = sizeof(struct udmabuf_create_item) * head.count; + list = memdup_user((void __user *)(arg + sizeof(head)), lsize); + if (IS_ERR(list)) + return PTR_ERR(list); + + ret = udmabuf_create(filp->private_data, &head, list); + kfree(list); + return ret; +} + +static long udmabuf_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + long ret; + + switch (ioctl) { + case UDMABUF_CREATE: + ret = udmabuf_ioctl_create(filp, arg); + break; + case UDMABUF_CREATE_LIST: + ret = udmabuf_ioctl_create_list(filp, arg); + break; + default: + ret = -ENOTTY; + break; + } + return ret; +} + +static const struct file_operations udmabuf_fops = { + .owner = THIS_MODULE, + .unlocked_ioctl = udmabuf_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = udmabuf_ioctl, +#endif +}; + +static struct miscdevice udmabuf_misc = { + .minor = MISC_DYNAMIC_MINOR, + .name = "udmabuf", + .fops = &udmabuf_fops, +}; + +static int __init udmabuf_dev_init(void) +{ + 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) +{ + misc_deregister(&udmabuf_misc); +} + +module_init(udmabuf_dev_init) +module_exit(udmabuf_dev_exit) + +MODULE_AUTHOR("Gerd Hoffmann <kraxel@redhat.com>"); +MODULE_LICENSE("GPL v2"); |