diff options
Diffstat (limited to 'drivers/dma-buf')
| -rw-r--r-- | drivers/dma-buf/Kconfig | 33 | ||||
| -rw-r--r-- | drivers/dma-buf/Makefile | 3 | ||||
| -rw-r--r-- | drivers/dma-buf/dma-buf.c | 1162 | ||||
| -rw-r--r-- | drivers/dma-buf/dma-fence-array.c | 181 | ||||
| -rw-r--r-- | drivers/dma-buf/dma-fence.c | 626 | ||||
| -rw-r--r-- | drivers/dma-buf/reservation.c | 642 | ||||
| -rw-r--r-- | drivers/dma-buf/seqno-fence.c | 79 | ||||
| -rw-r--r-- | drivers/dma-buf/sw_sync.c | 421 | ||||
| -rw-r--r-- | drivers/dma-buf/sync_debug.c | 235 | ||||
| -rw-r--r-- | drivers/dma-buf/sync_debug.h | 73 | ||||
| -rw-r--r-- | drivers/dma-buf/sync_file.c | 493 | ||||
| -rw-r--r-- | drivers/dma-buf/sync_trace.h | 33 |
12 files changed, 3981 insertions, 0 deletions
diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig new file mode 100644 index 000000000..ed3b785ba --- /dev/null +++ b/drivers/dma-buf/Kconfig @@ -0,0 +1,33 @@ +menu "DMABUF options" + +config SYNC_FILE + bool "Explicit Synchronization Framework" + default n + select ANON_INODES + select DMA_SHARED_BUFFER + ---help--- + The Sync File Framework adds explicit syncronization 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/sync_file.txt. + +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. + +endmenu diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile new file mode 100644 index 000000000..c33bf8863 --- /dev/null +++ b/drivers/dma-buf/Makefile @@ -0,0 +1,3 @@ +obj-y := dma-buf.o dma-fence.o dma-fence-array.o reservation.o seqno-fence.o +obj-$(CONFIG_SYNC_FILE) += sync_file.o +obj-$(CONFIG_SW_SYNC) += sw_sync.o sync_debug.o diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c new file mode 100644 index 000000000..69842145c --- /dev/null +++ b/drivers/dma-buf/dma-buf.c @@ -0,0 +1,1162 @@ +/* + * 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. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/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/reservation.h> +#include <linux/mm.h> + +#include <uapi/linux/dma-buf.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 int dma_buf_release(struct inode *inode, struct file *file) +{ + struct dma_buf *dmabuf; + + if (!is_dma_buf_file(file)) + return -EINVAL; + + dmabuf = file->private_data; + + 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); + + mutex_lock(&db_list.lock); + list_del(&dmabuf->list_node); + mutex_unlock(&db_list.lock); + + if (dmabuf->resv == (struct reservation_object *)&dmabuf[1]) + reservation_object_fini(dmabuf->resv); + + module_put(dmabuf->owner); + kfree(dmabuf); + return 0; +} + +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 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: fence polling + * + * To support cross-device and cross-driver synchronization of buffer access + * implicit fences (represented internally in the kernel with &struct fence) can + * be attached to a &dma_buf. The glue for that and a few related things are + * provided in the &reservation_object 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 reservation_object *resv; + struct reservation_object_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; +} + +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; + default: + return -ENOTTY; + } +} + +static const struct file_operations dma_buf_fops = { + .release = dma_buf_release, + .mmap = dma_buf_mmap_internal, + .llseek = dma_buf_llseek, + .poll = dma_buf_poll, + .unlocked_ioctl = dma_buf_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = dma_buf_ioctl, +#endif +}; + +/* + * 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; +} + +/** + * 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 reservation_object *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 reservation_object); + 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 + || !exp_info->ops->map + || !exp_info->ops->mmap)) { + 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; + 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 reservation_object *)&dmabuf[1]; + reservation_object_init(resv); + } + dmabuf->resv = resv; + + file = anon_inode_getfile("dmabuf", &dma_buf_fops, 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_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. + * + * 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_attach(struct dma_buf *dmabuf, + struct device *dev) +{ + struct dma_buf_attachment *attach; + int ret; + + if (WARN_ON(!dmabuf || !dev)) + return ERR_PTR(-EINVAL); + + attach = kzalloc(sizeof(*attach), GFP_KERNEL); + if (!attach) + return ERR_PTR(-ENOMEM); + + attach->dev = dev; + attach->dmabuf = dmabuf; + + mutex_lock(&dmabuf->lock); + + if (dmabuf->ops->attach) { + ret = dmabuf->ops->attach(dmabuf, attach); + if (ret) + goto err_attach; + } + list_add(&attach->node, &dmabuf->attachments); + + mutex_unlock(&dmabuf->lock); + return attach; + +err_attach: + kfree(attach); + mutex_unlock(&dmabuf->lock); + return ERR_PTR(ret); +} +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; + + mutex_lock(&dmabuf->lock); + list_del(&attach->node); + if (dmabuf->ops->detach) + dmabuf->ops->detach(dmabuf, attach); + + mutex_unlock(&dmabuf->lock); + kfree(attach); +} +EXPORT_SYMBOL_GPL(dma_buf_detach); + +/** + * 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; + + might_sleep(); + + if (WARN_ON(!attach || !attach->dmabuf)) + return ERR_PTR(-EINVAL); + + sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction); + if (!sg_table) + sg_table = ERR_PTR(-ENOMEM); + + 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; + + attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, + direction); +} +EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment); + +/** + * 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. + * + * To support dma_buf objects residing in highmem cpu access is page-based + * using an api similar to kmap. Accessing a dma_buf is done in aligned chunks + * of PAGE_SIZE size. Before accessing a chunk it needs to be mapped, which + * returns a pointer in kernel virtual address space. Afterwards the chunk + * needs to be unmapped again. There is no limit on how often a given chunk + * can be mapped and unmapped, i.e. the importer does not need to call + * begin_cpu_access again before mapping the same chunk again. + * + * Interfaces:: + * void \*dma_buf_kmap(struct dma_buf \*, unsigned long); + * void dma_buf_kunmap(struct dma_buf \*, unsigned long, void \*); + * + * Implementing the functions is optional for exporters and for importers all + * the restrictions of using kmap apply. + * + * dma_buf kmap calls outside of the range specified in begin_cpu_access are + * undefined. If the range is not PAGE_SIZE aligned, kmap needs to succeed on + * the partial chunks at the beginning and end but may return stale or bogus + * data outside of the range (in these partial chunks). + * + * For some cases the overhead of kmap can be too high, a vmap interface + * is introduced. This interface should be used very carefully, as vmalloc + * space is a limited resources on many architectures. + * + * 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 reservation_object *resv = dmabuf->resv; + long ret; + + /* Wait on any implicit rendering fences */ + ret = reservation_object_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_kmap - Map a page of the buffer object into kernel address space. The + * same restrictions as for kmap and friends apply. + * @dmabuf: [in] buffer to map page from. + * @page_num: [in] page in PAGE_SIZE units to map. + * + * This call must always succeed, any necessary preparations that might fail + * need to be done in begin_cpu_access. + */ +void *dma_buf_kmap(struct dma_buf *dmabuf, unsigned long page_num) +{ + WARN_ON(!dmabuf); + + if (!dmabuf->ops->map) + return NULL; + return dmabuf->ops->map(dmabuf, page_num); +} +EXPORT_SYMBOL_GPL(dma_buf_kmap); + +/** + * dma_buf_kunmap - Unmap a page obtained by dma_buf_kmap. + * @dmabuf: [in] buffer to unmap page from. + * @page_num: [in] page in PAGE_SIZE units to unmap. + * @vaddr: [in] kernel space pointer obtained from dma_buf_kmap. + * + * This call must always succeed. + */ +void dma_buf_kunmap(struct dma_buf *dmabuf, unsigned long page_num, + void *vaddr) +{ + WARN_ON(!dmabuf); + + if (dmabuf->ops->unmap) + dmabuf->ops->unmap(dmabuf, page_num, vaddr); +} +EXPORT_SYMBOL_GPL(dma_buf_kunmap); + + +/** + * 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 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 reservation_object *robj; + struct reservation_object_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\n", + "size", "flags", "mode", "count"); + + list_for_each_entry(buf_obj, &db_list.head, list_node) { + ret = mutex_lock_interruptible(&buf_obj->lock); + + if (ret) { + seq_puts(s, + "\tERROR locking buffer object: skipping\n"); + continue; + } + + seq_printf(s, "%08zu\t%08x\t%08x\t%08ld\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); + + 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++; + } + + seq_printf(s, "Total %d devices attached\n\n", + attach_count); + + count++; + size += buf_obj->size; + mutex_unlock(&buf_obj->lock); + } + + seq_printf(s, "\nTotal %d objects, %zu bytes\n", count, size); + + mutex_unlock(&db_list.lock); + return 0; +} + +static int dma_buf_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, dma_buf_debug_show, NULL); +} + +static const struct file_operations dma_buf_debug_fops = { + .open = dma_buf_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +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) +{ + 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(); +} +__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..a8c254497 --- /dev/null +++ b/drivers/dma-buf/dma-fence-array.c @@ -0,0 +1,181 @@ +/* + * 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> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/export.h> +#include <linux/slab.h> +#include <linux/dma-fence-array.h> + +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 irq_dma_fence_array_work(struct irq_work *wrk) +{ + struct dma_fence_array *array = container_of(wrk, typeof(*array), work); + + 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; + + 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)) { + dma_fence_put(&array->base); + if (atomic_dec_and_test(&array->num_pending)) + return false; + } + } + + return true; +} + +static bool dma_fence_array_signaled(struct dma_fence *fence) +{ + struct dma_fence_array *array = to_dma_fence_array(fence); + + return atomic_read(&array->num_pending) <= 0; +} + +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; + + 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.c b/drivers/dma-buf/dma-fence.c new file mode 100644 index 000000000..8586cc05d --- /dev/null +++ b/drivers/dma-buf/dma-fence.c @@ -0,0 +1,626 @@ +/* + * 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> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#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); + +/* + * 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(0); + +/** + * 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 reservation_object through the + * &dma_buf.resv pointer. + */ + +/** + * 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_add_return(num, &dma_fence_context_counter) - num; +} +EXPORT_SYMBOL(dma_fence_context_alloc); + +/** + * 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; + int ret = 0; + + lockdep_assert_held(fence->lock); + + if (WARN_ON(!fence)) + return -EINVAL; + + if (test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { + ret = -EINVAL; + + /* + * we might have raced with the unlocked dma_fence_signal, + * still run through all callbacks + */ + } else { + 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, &fence->cb_list, node) { + list_del_init(&cur->node); + cur->func(fence, cur); + } + return ret; +} +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; + + if (!fence) + return -EINVAL; + + if (test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return -EINVAL; + + fence->timestamp = ktime_get(); + set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags); + trace_dma_fence_signaled(fence); + + if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags)) { + struct dma_fence_cb *cur, *tmp; + + spin_lock_irqsave(fence->lock, flags); + list_for_each_entry_safe(cur, tmp, &fence->cb_list, node) { + list_del_init(&cur->node); + cur->func(fence, cur); + } + spin_unlock_irqrestore(fence->lock, flags); + } + return 0; +} +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; + + 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); + + /* Failed to signal before release, could be a refcounting issue */ + WARN_ON(!list_empty(&fence->cb_list)); + + 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, unsigned 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/reservation.c b/drivers/dma-buf/reservation.c new file mode 100644 index 000000000..49ab09468 --- /dev/null +++ b/drivers/dma-buf/reservation.c @@ -0,0 +1,642 @@ +/* + * 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/reservation.h> +#include <linux/export.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); + +struct lock_class_key reservation_seqcount_class; +EXPORT_SYMBOL(reservation_seqcount_class); + +const char reservation_seqcount_string[] = "reservation_seqcount"; +EXPORT_SYMBOL(reservation_seqcount_string); + +/** + * reservation_object_reserve_shared - Reserve space to add a shared + * fence to a reservation_object. + * @obj: reservation object + * + * Should be called before reservation_object_add_shared_fence(). Must + * be called with obj->lock held. + * + * RETURNS + * Zero for success, or -errno + */ +int reservation_object_reserve_shared(struct reservation_object *obj) +{ + struct reservation_object_list *fobj, *old; + u32 max; + + old = reservation_object_get_list(obj); + + if (old && old->shared_max) { + if (old->shared_count < old->shared_max) { + /* perform an in-place update */ + kfree(obj->staged); + obj->staged = NULL; + return 0; + } else + max = old->shared_max * 2; + } else + max = 4; + + /* + * resize obj->staged or allocate if it doesn't exist, + * noop if already correct size + */ + fobj = krealloc(obj->staged, offsetof(typeof(*fobj), shared[max]), + GFP_KERNEL); + if (!fobj) + return -ENOMEM; + + obj->staged = fobj; + fobj->shared_max = max; + return 0; +} +EXPORT_SYMBOL(reservation_object_reserve_shared); + +static void +reservation_object_add_shared_inplace(struct reservation_object *obj, + struct reservation_object_list *fobj, + struct dma_fence *fence) +{ + struct dma_fence *signaled = NULL; + u32 i, signaled_idx; + + dma_fence_get(fence); + + preempt_disable(); + write_seqcount_begin(&obj->seq); + + for (i = 0; i < fobj->shared_count; ++i) { + struct dma_fence *old_fence; + + old_fence = rcu_dereference_protected(fobj->shared[i], + reservation_object_held(obj)); + + if (old_fence->context == fence->context) { + /* memory barrier is added by write_seqcount_begin */ + RCU_INIT_POINTER(fobj->shared[i], fence); + write_seqcount_end(&obj->seq); + preempt_enable(); + + dma_fence_put(old_fence); + return; + } + + if (!signaled && dma_fence_is_signaled(old_fence)) { + signaled = old_fence; + signaled_idx = i; + } + } + + /* + * memory barrier is added by write_seqcount_begin, + * fobj->shared_count is protected by this lock too + */ + if (signaled) { + RCU_INIT_POINTER(fobj->shared[signaled_idx], fence); + } else { + BUG_ON(fobj->shared_count >= fobj->shared_max); + RCU_INIT_POINTER(fobj->shared[fobj->shared_count], fence); + fobj->shared_count++; + } + + write_seqcount_end(&obj->seq); + preempt_enable(); + + dma_fence_put(signaled); +} + +static void +reservation_object_add_shared_replace(struct reservation_object *obj, + struct reservation_object_list *old, + struct reservation_object_list *fobj, + struct dma_fence *fence) +{ + unsigned i, j, k; + + dma_fence_get(fence); + + if (!old) { + RCU_INIT_POINTER(fobj->shared[0], fence); + fobj->shared_count = 1; + goto done; + } + + /* + * 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 = fobj->shared_max; i < old->shared_count; ++i) { + struct dma_fence *check; + + check = rcu_dereference_protected(old->shared[i], + reservation_object_held(obj)); + + if (check->context == fence->context || + dma_fence_is_signaled(check)) + RCU_INIT_POINTER(fobj->shared[--k], check); + else + RCU_INIT_POINTER(fobj->shared[j++], check); + } + fobj->shared_count = j; + RCU_INIT_POINTER(fobj->shared[fobj->shared_count], fence); + fobj->shared_count++; + +done: + preempt_disable(); + write_seqcount_begin(&obj->seq); + /* + * RCU_INIT_POINTER can be used here, + * seqcount provides the necessary barriers + */ + RCU_INIT_POINTER(obj->fence, fobj); + write_seqcount_end(&obj->seq); + preempt_enable(); + + if (!old) + return; + + /* Drop the references to the signaled fences */ + for (i = k; i < fobj->shared_max; ++i) { + struct dma_fence *f; + + f = rcu_dereference_protected(fobj->shared[i], + reservation_object_held(obj)); + dma_fence_put(f); + } + kfree_rcu(old, rcu); +} + +/** + * reservation_object_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 + * reservation_object_reserve_shared() has been called. + */ +void reservation_object_add_shared_fence(struct reservation_object *obj, + struct dma_fence *fence) +{ + struct reservation_object_list *old, *fobj = obj->staged; + + old = reservation_object_get_list(obj); + obj->staged = NULL; + + if (!fobj) + reservation_object_add_shared_inplace(obj, old, fence); + else + reservation_object_add_shared_replace(obj, old, fobj, fence); +} +EXPORT_SYMBOL(reservation_object_add_shared_fence); + +/** + * reservation_object_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 reservation_object_add_excl_fence(struct reservation_object *obj, + struct dma_fence *fence) +{ + struct dma_fence *old_fence = reservation_object_get_excl(obj); + struct reservation_object_list *old; + u32 i = 0; + + old = reservation_object_get_list(obj); + if (old) + i = old->shared_count; + + if (fence) + dma_fence_get(fence); + + preempt_disable(); + 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); + preempt_enable(); + + /* inplace update, no shared fences */ + while (i--) + dma_fence_put(rcu_dereference_protected(old->shared[i], + reservation_object_held(obj))); + + dma_fence_put(old_fence); +} +EXPORT_SYMBOL(reservation_object_add_excl_fence); + +/** +* reservation_object_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 reservation_object_copy_fences(struct reservation_object *dst, + struct reservation_object *src) +{ + struct reservation_object_list *src_list, *dst_list; + struct dma_fence *old, *new; + size_t size; + unsigned i; + + rcu_read_lock(); + src_list = rcu_dereference(src->fence); + +retry: + if (src_list) { + unsigned shared_count = src_list->shared_count; + + size = offsetof(typeof(*src_list), shared[shared_count]); + rcu_read_unlock(); + + dst_list = kmalloc(size, GFP_KERNEL); + 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; + dst_list->shared_max = shared_count; + 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)) { + kfree(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(); + + kfree(dst->staged); + dst->staged = NULL; + + src_list = reservation_object_get_list(dst); + old = reservation_object_get_excl(dst); + + preempt_disable(); + 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); + preempt_enable(); + + if (src_list) + kfree_rcu(src_list, rcu); + dma_fence_put(old); + + return 0; +} +EXPORT_SYMBOL(reservation_object_copy_fences); + +/** + * reservation_object_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 reservation_object_get_fences_rcu(struct reservation_object *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 reservation_object_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 (!pfence_excl && fence_excl) { + shared[i] = fence_excl; + fence_excl = NULL; + ++i; + ++shared_count; + } + } + + 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 (!shared_count) { + kfree(shared); + shared = NULL; + } + + *pshared_count = shared_count; + *pshared = shared; + if (pfence_excl) + *pfence_excl = fence_excl; + + return ret; +} +EXPORT_SYMBOL_GPL(reservation_object_get_fences_rcu); + +/** + * reservation_object_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 reservation_object_wait_timeout_rcu(struct reservation_object *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 reservation_object_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(reservation_object_wait_timeout_rcu); + + +static inline int +reservation_object_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; +} + +/** + * reservation_object_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 reservation_object_test_signaled_rcu(struct reservation_object *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 reservation_object_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 = reservation_object_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 = reservation_object_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(reservation_object_test_signaled_rcu); diff --git a/drivers/dma-buf/seqno-fence.c b/drivers/dma-buf/seqno-fence.c new file mode 100644 index 000000000..f47112a64 --- /dev/null +++ b/drivers/dma-buf/seqno-fence.c @@ -0,0 +1,79 @@ +/* + * 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> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#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/sw_sync.c b/drivers/dma-buf/sw_sync.c new file mode 100644 index 000000000..81ba4eb34 --- /dev/null +++ b/drivers/dma-buf/sw_sync.c @@ -0,0 +1,421 @@ +/* + * Sync File validation framework + * + * Copyright (C) 2012 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * 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. + * + */ + +#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); +} + +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, "%d", 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) +{ + 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; + + list_del_init(&pt->link); + rb_erase(&pt->node, &obj->pt_tree); + + /* + * A signal callback may release the last reference to this + * fence, causing it to be freed. That operation has to be + * last to avoid a use after free inside this loop, and must + * be after we remove the fence from the timeline in order to + * prevent deadlocking on timeline->lock inside + * timeline_fence_release(). + */ + dma_fence_signal_locked(&pt->base); + } + + spin_unlock_irq(&obj->lock); +} + +/** + * 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 = sw_sync_ioctl, +}; diff --git a/drivers/dma-buf/sync_debug.c b/drivers/dma-buf/sync_debug.c new file mode 100644 index 000000000..c4c8ecb24 --- /dev/null +++ b/drivers/dma-buf/sync_debug.c @@ -0,0 +1,235 @@ +/* + * Sync File validation framework and debug information + * + * Copyright (C) 2012 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * 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. + * + */ + +#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_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; +} + +static int sync_info_debugfs_open(struct inode *inode, struct file *file) +{ + return single_open(file, sync_debugfs_show, inode->i_private); +} + +static const struct file_operations sync_info_debugfs_fops = { + .open = sync_info_debugfs_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +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); + +#define DUMP_CHUNK 256 +static char sync_dump_buf[64 * 1024]; +void sync_dump(void) +{ + struct seq_file s = { + .buf = sync_dump_buf, + .size = sizeof(sync_dump_buf) - 1, + }; + int i; + + sync_debugfs_show(&s, NULL); + + for (i = 0; i < s.count; i += DUMP_CHUNK) { + if ((s.count - i) > DUMP_CHUNK) { + char c = s.buf[i + DUMP_CHUNK]; + + s.buf[i + DUMP_CHUNK] = 0; + pr_cont("%s", s.buf + i); + s.buf[i + DUMP_CHUNK] = c; + } else { + s.buf[s.count] = 0; + pr_cont("%s", s.buf + i); + } + } +} diff --git a/drivers/dma-buf/sync_debug.h b/drivers/dma-buf/sync_debug.h new file mode 100644 index 000000000..05e33f937 --- /dev/null +++ b/drivers/dma-buf/sync_debug.h @@ -0,0 +1,73 @@ +/* + * 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); +void sync_dump(void); + +#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..b0d2563cd --- /dev/null +++ b/drivers/dma-buf/sync_file.c @@ -0,0 +1,493 @@ +/* + * drivers/dma-buf/sync_file.c + * + * Copyright (C) 2012 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * 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. + * + */ + +#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-%d", + 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 (pt_a->seqno - pt_b->seqno <= INT_MAX) + 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_is_signaled(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 = sync_file_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> |