diff options
Diffstat (limited to 'drivers/dma-buf')
-rw-r--r-- | drivers/dma-buf/Kconfig | 16 | ||||
-rw-r--r-- | drivers/dma-buf/Makefile | 10 | ||||
-rw-r--r-- | drivers/dma-buf/dma-buf.c | 215 | ||||
-rw-r--r-- | drivers/dma-buf/dma-fence-array.c | 32 | ||||
-rw-r--r-- | drivers/dma-buf/dma-fence-chain.c | 24 | ||||
-rw-r--r-- | drivers/dma-buf/dma-fence.c | 133 | ||||
-rw-r--r-- | drivers/dma-buf/dma-heap.c | 298 | ||||
-rw-r--r-- | drivers/dma-buf/dma-resv.c (renamed from drivers/dma-buf/reservation.c) | 283 | ||||
-rw-r--r-- | drivers/dma-buf/heaps/Kconfig | 14 | ||||
-rw-r--r-- | drivers/dma-buf/heaps/Makefile | 4 | ||||
-rw-r--r-- | drivers/dma-buf/heaps/cma_heap.c | 177 | ||||
-rw-r--r-- | drivers/dma-buf/heaps/heap-helpers.c | 271 | ||||
-rw-r--r-- | drivers/dma-buf/heaps/heap-helpers.h | 53 | ||||
-rw-r--r-- | drivers/dma-buf/heaps/system_heap.c | 123 | ||||
-rw-r--r-- | drivers/dma-buf/selftest.c | 167 | ||||
-rw-r--r-- | drivers/dma-buf/selftest.h | 30 | ||||
-rw-r--r-- | drivers/dma-buf/selftests.h | 13 | ||||
-rw-r--r-- | drivers/dma-buf/st-dma-fence.c | 574 | ||||
-rw-r--r-- | drivers/dma-buf/sw_sync.c | 18 | ||||
-rw-r--r-- | drivers/dma-buf/sync_file.c | 6 | ||||
-rw-r--r-- | drivers/dma-buf/udmabuf.c | 84 |
21 files changed, 2230 insertions, 315 deletions
diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig index b6a9c2f1bc41..0613bb7770f5 100644 --- a/drivers/dma-buf/Kconfig +++ b/drivers/dma-buf/Kconfig @@ -39,4 +39,20 @@ config UDMABUF A driver to let userspace turn memfd regions into dma-bufs. Qemu can use this to create host dmabufs for guest framebuffers. +config DMABUF_SELFTESTS + tristate "Selftests for the dma-buf interfaces" + default n + depends on DMA_SHARED_BUFFER + +menuconfig DMABUF_HEAPS + bool "DMA-BUF Userland Memory Heaps" + select DMA_SHARED_BUFFER + help + Choose this option to enable the DMA-BUF userland memory heaps. + This options creates per heap chardevs in /dev/dma_heap/ which + allows userspace to allocate dma-bufs that can be shared + between drivers. + +source "drivers/dma-buf/heaps/Kconfig" + endmenu diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile index e8c7310cb800..9c190026bfab 100644 --- a/drivers/dma-buf/Makefile +++ b/drivers/dma-buf/Makefile @@ -1,6 +1,14 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y := dma-buf.o dma-fence.o dma-fence-array.o dma-fence-chain.o \ - reservation.o seqno-fence.o + dma-resv.o seqno-fence.o +obj-$(CONFIG_DMABUF_HEAPS) += dma-heap.o +obj-$(CONFIG_DMABUF_HEAPS) += heaps/ obj-$(CONFIG_SYNC_FILE) += sync_file.o obj-$(CONFIG_SW_SYNC) += sw_sync.o sync_debug.o obj-$(CONFIG_UDMABUF) += udmabuf.o + +dmabuf_selftests-y := \ + selftest.o \ + st-dma-fence.o + +obj-$(CONFIG_DMABUF_SELFTESTS) += dmabuf_selftests.o diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index f45bfb29ef96..d4097856c86b 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -21,7 +21,7 @@ #include <linux/module.h> #include <linux/seq_file.h> #include <linux/poll.h> -#include <linux/reservation.h> +#include <linux/dma-resv.h> #include <linux/mm.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> @@ -45,10 +45,10 @@ static char *dmabuffs_dname(struct dentry *dentry, char *buffer, int buflen) size_t ret = 0; dmabuf = dentry->d_fsdata; - mutex_lock(&dmabuf->lock); + dma_resv_lock(dmabuf->resv, NULL); if (dmabuf->name) ret = strlcpy(name, dmabuf->name, DMA_BUF_NAME_LEN); - mutex_unlock(&dmabuf->lock); + dma_resv_unlock(dmabuf->resv); return dynamic_dname(dentry, buffer, buflen, "/%s:%s", dentry->d_name.name, ret > 0 ? name : ""); @@ -104,8 +104,8 @@ static int dma_buf_release(struct inode *inode, struct file *file) list_del(&dmabuf->list_node); mutex_unlock(&db_list.lock); - if (dmabuf->resv == (struct reservation_object *)&dmabuf[1]) - reservation_object_fini(dmabuf->resv); + if (dmabuf->resv == (struct dma_resv *)&dmabuf[1]) + dma_resv_fini(dmabuf->resv); module_put(dmabuf->owner); kfree(dmabuf); @@ -165,7 +165,7 @@ static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence) * 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. + * provided in the &dma_resv structure. * * Userspace can query the state of these implicitly tracked fences using poll() * and related system calls: @@ -195,8 +195,8 @@ static void dma_buf_poll_cb(struct dma_fence *fence, struct dma_fence_cb *cb) 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_resv *resv; + struct dma_resv_list *fobj; struct dma_fence *fence_excl; __poll_t events; unsigned shared_count, seq; @@ -334,7 +334,7 @@ static long dma_buf_set_name(struct dma_buf *dmabuf, const char __user *buf) if (IS_ERR(name)) return PTR_ERR(name); - mutex_lock(&dmabuf->lock); + dma_resv_lock(dmabuf->resv, NULL); if (!list_empty(&dmabuf->attachments)) { ret = -EBUSY; kfree(name); @@ -344,7 +344,7 @@ static long dma_buf_set_name(struct dma_buf *dmabuf, const char __user *buf) dmabuf->name = name; out_unlock: - mutex_unlock(&dmabuf->lock); + dma_resv_unlock(dmabuf->resv); return ret; } @@ -403,10 +403,10 @@ static void dma_buf_show_fdinfo(struct seq_file *m, struct file *file) /* Don't count the temporary reference taken inside procfs seq_show */ seq_printf(m, "count:\t%ld\n", file_count(dmabuf->file) - 1); seq_printf(m, "exp_name:\t%s\n", dmabuf->exp_name); - mutex_lock(&dmabuf->lock); + dma_resv_lock(dmabuf->resv, NULL); if (dmabuf->name) seq_printf(m, "name:\t%s\n", dmabuf->name); - mutex_unlock(&dmabuf->lock); + dma_resv_unlock(dmabuf->resv); } static const struct file_operations dma_buf_fops = { @@ -415,9 +415,7 @@ static const struct file_operations dma_buf_fops = { .llseek = dma_buf_llseek, .poll = dma_buf_poll, .unlocked_ioctl = dma_buf_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = dma_buf_ioctl, -#endif + .compat_ioctl = compat_ptr_ioctl, .show_fdinfo = dma_buf_show_fdinfo, }; @@ -506,13 +504,13 @@ err_alloc_file: 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 dma_resv *resv = exp_info->resv; struct file *file; size_t alloc_size = sizeof(struct dma_buf); int ret; if (!exp_info->resv) - alloc_size += sizeof(struct reservation_object); + alloc_size += sizeof(struct dma_resv); else /* prevent &dma_buf[1] == dma_buf->resv */ alloc_size += 1; @@ -525,6 +523,10 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) return ERR_PTR(-EINVAL); } + if (WARN_ON(exp_info->ops->cache_sgt_mapping && + exp_info->ops->dynamic_mapping)) + return ERR_PTR(-EINVAL); + if (!try_module_get(exp_info->owner)) return ERR_PTR(-ENOENT); @@ -544,8 +546,8 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) dmabuf->cb_excl.active = dmabuf->cb_shared.active = 0; if (!resv) { - resv = (struct reservation_object *)&dmabuf[1]; - reservation_object_init(resv); + resv = (struct dma_resv *)&dmabuf[1]; + dma_resv_init(resv); } dmabuf->resv = resv; @@ -645,10 +647,11 @@ void dma_buf_put(struct dma_buf *dmabuf) EXPORT_SYMBOL_GPL(dma_buf_put); /** - * dma_buf_attach - Add the device to dma_buf's attachments list; optionally, + * dma_buf_dynamic_attach - Add the device to dma_buf's attachments list; optionally, * calls attach() of dma_buf_ops to allow device-specific attach functionality - * @dmabuf: [in] buffer to attach device to. - * @dev: [in] device to be attached. + * @dmabuf: [in] buffer to attach device to. + * @dev: [in] device to be attached. + * @dynamic_mapping: [in] calling convention for map/unmap * * Returns struct dma_buf_attachment pointer for this attachment. Attachments * must be cleaned up by calling dma_buf_detach(). @@ -662,8 +665,9 @@ EXPORT_SYMBOL_GPL(dma_buf_put); * 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 * +dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev, + bool dynamic_mapping) { struct dma_buf_attachment *attach; int ret; @@ -677,25 +681,69 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, attach->dev = dev; attach->dmabuf = dmabuf; - - mutex_lock(&dmabuf->lock); + attach->dynamic_mapping = dynamic_mapping; if (dmabuf->ops->attach) { ret = dmabuf->ops->attach(dmabuf, attach); if (ret) goto err_attach; } + dma_resv_lock(dmabuf->resv, NULL); list_add(&attach->node, &dmabuf->attachments); + dma_resv_unlock(dmabuf->resv); - mutex_unlock(&dmabuf->lock); + /* When either the importer or the exporter can't handle dynamic + * mappings we cache the mapping here to avoid issues with the + * reservation object lock. + */ + if (dma_buf_attachment_is_dynamic(attach) != + dma_buf_is_dynamic(dmabuf)) { + struct sg_table *sgt; + + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_resv_lock(attach->dmabuf->resv, NULL); + + sgt = dmabuf->ops->map_dma_buf(attach, DMA_BIDIRECTIONAL); + if (!sgt) + sgt = ERR_PTR(-ENOMEM); + if (IS_ERR(sgt)) { + ret = PTR_ERR(sgt); + goto err_unlock; + } + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_resv_unlock(attach->dmabuf->resv); + attach->sgt = sgt; + attach->dir = DMA_BIDIRECTIONAL; + } return attach; err_attach: kfree(attach); - mutex_unlock(&dmabuf->lock); + return ERR_PTR(ret); + +err_unlock: + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_resv_unlock(attach->dmabuf->resv); + + dma_buf_detach(dmabuf, attach); return ERR_PTR(ret); } +EXPORT_SYMBOL_GPL(dma_buf_dynamic_attach); + +/** + * dma_buf_attach - Wrapper for dma_buf_dynamic_attach + * @dmabuf: [in] buffer to attach device to. + * @dev: [in] device to be attached. + * + * Wrapper to call dma_buf_dynamic_attach() for drivers which still use a static + * mapping. + */ +struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, + struct device *dev) +{ + return dma_buf_dynamic_attach(dmabuf, dev, false); +} EXPORT_SYMBOL_GPL(dma_buf_attach); /** @@ -711,15 +759,22 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach) if (WARN_ON(!dmabuf || !attach)) return; - if (attach->sgt) + if (attach->sgt) { + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_resv_lock(attach->dmabuf->resv, NULL); + dmabuf->ops->unmap_dma_buf(attach, attach->sgt, attach->dir); - mutex_lock(&dmabuf->lock); + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_resv_unlock(attach->dmabuf->resv); + } + + dma_resv_lock(dmabuf->resv, NULL); list_del(&attach->node); + dma_resv_unlock(dmabuf->resv); if (dmabuf->ops->detach) dmabuf->ops->detach(dmabuf, attach); - mutex_unlock(&dmabuf->lock); kfree(attach); } EXPORT_SYMBOL_GPL(dma_buf_detach); @@ -749,6 +804,9 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach, if (WARN_ON(!attach || !attach->dmabuf)) return ERR_PTR(-EINVAL); + if (dma_buf_attachment_is_dynamic(attach)) + dma_resv_assert_held(attach->dmabuf->resv); + if (attach->sgt) { /* * Two mappings with different directions for the same @@ -761,6 +819,9 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach, return attach->sgt; } + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_resv_assert_held(attach->dmabuf->resv); + sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction); if (!sg_table) sg_table = ERR_PTR(-ENOMEM); @@ -793,9 +854,15 @@ void dma_buf_unmap_attachment(struct dma_buf_attachment *attach, if (WARN_ON(!attach || !attach->dmabuf || !sg_table)) return; + if (dma_buf_attachment_is_dynamic(attach)) + dma_resv_assert_held(attach->dmabuf->resv); + if (attach->sgt == sg_table) return; + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_resv_assert_held(attach->dmabuf->resv); + attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, direction); } EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment); @@ -811,29 +878,9 @@ EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment); * 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. + * Since for most kernel internal dma-buf accesses need the entire buffer, a + * vmap interface is introduced. Note that on very old 32-bit architectures + * vmalloc space might be limited and result in vmap calls failing. * * Interfaces:: * void \*dma_buf_vmap(struct dma_buf \*dmabuf) @@ -909,11 +956,11 @@ static int __dma_buf_begin_cpu_access(struct dma_buf *dmabuf, { bool write = (direction == DMA_BIDIRECTIONAL || direction == DMA_TO_DEVICE); - struct reservation_object *resv = dmabuf->resv; + struct dma_resv *resv = dmabuf->resv; long ret; /* Wait on any implicit rendering fences */ - ret = reservation_object_wait_timeout_rcu(resv, write, true, + ret = dma_resv_wait_timeout_rcu(resv, write, true, MAX_SCHEDULE_TIMEOUT); if (ret < 0) return ret; @@ -983,43 +1030,6 @@ int dma_buf_end_cpu_access(struct dma_buf *dmabuf, } 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 @@ -1154,8 +1164,8 @@ 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_resv *robj; + struct dma_resv_list *fobj; struct dma_fence *fence; unsigned seq; int count = 0, attach_count, shared_count, i; @@ -1171,13 +1181,10 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused) "size", "flags", "mode", "count", "ino"); 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; - } + ret = dma_resv_lock_interruptible(buf_obj->resv, NULL); + if (ret) + goto error_unlock; seq_printf(s, "%08zu\t%08x\t%08x\t%08ld\t%s\t%08lu\t%s\n", buf_obj->size, @@ -1223,19 +1230,23 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused) seq_printf(s, "\t%s\n", dev_name(attach_obj->dev)); attach_count++; } + dma_resv_unlock(buf_obj->resv); seq_printf(s, "Total %d devices attached\n\n", attach_count); count++; size += buf_obj->size; - mutex_unlock(&buf_obj->lock); } seq_printf(s, "\nTotal %d objects, %zu bytes\n", count, size); mutex_unlock(&db_list.lock); return 0; + +error_unlock: + mutex_unlock(&db_list.lock); + return ret; } DEFINE_SHOW_ATTRIBUTE(dma_buf_debug); diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c index 12c6f64c0bc2..d3fbd950be94 100644 --- a/drivers/dma-buf/dma-fence-array.c +++ b/drivers/dma-buf/dma-fence-array.c @@ -13,6 +13,8 @@ #include <linux/slab.h> #include <linux/dma-fence-array.h> +#define PENDING_ERROR 1 + static const char *dma_fence_array_get_driver_name(struct dma_fence *fence) { return "dma_fence_array"; @@ -23,10 +25,29 @@ static const char *dma_fence_array_get_timeline_name(struct dma_fence *fence) return "unbound"; } +static void dma_fence_array_set_pending_error(struct dma_fence_array *array, + int error) +{ + /* + * Propagate the first error reported by any of our fences, but only + * before we ourselves are signaled. + */ + if (error) + cmpxchg(&array->base.error, PENDING_ERROR, error); +} + +static void dma_fence_array_clear_pending_error(struct dma_fence_array *array) +{ + /* Clear the error flag if not actually set. */ + cmpxchg(&array->base.error, PENDING_ERROR, 0); +} + static void irq_dma_fence_array_work(struct irq_work *wrk) { struct dma_fence_array *array = container_of(wrk, typeof(*array), work); + dma_fence_array_clear_pending_error(array); + dma_fence_signal(&array->base); dma_fence_put(&array->base); } @@ -38,6 +59,8 @@ static void dma_fence_array_cb_func(struct dma_fence *f, container_of(cb, struct dma_fence_array_cb, cb); struct dma_fence_array *array = array_cb->array; + dma_fence_array_set_pending_error(array, f->error); + if (atomic_dec_and_test(&array->num_pending)) irq_work_queue(&array->work); else @@ -63,9 +86,14 @@ static bool dma_fence_array_enable_signaling(struct dma_fence *fence) dma_fence_get(&array->base); if (dma_fence_add_callback(array->fences[i], &cb[i].cb, dma_fence_array_cb_func)) { + int error = array->fences[i]->error; + + dma_fence_array_set_pending_error(array, error); dma_fence_put(&array->base); - if (atomic_dec_and_test(&array->num_pending)) + if (atomic_dec_and_test(&array->num_pending)) { + dma_fence_array_clear_pending_error(array); return false; + } } } @@ -142,6 +170,8 @@ struct dma_fence_array *dma_fence_array_create(int num_fences, atomic_set(&array->num_pending, signal_on_any ? 1 : num_fences); array->fences = fences; + array->base.error = PENDING_ERROR; + return array; } EXPORT_SYMBOL(dma_fence_array_create); diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c index b5089f64be2a..44a741677d25 100644 --- a/drivers/dma-buf/dma-fence-chain.c +++ b/drivers/dma-buf/dma-fence-chain.c @@ -178,8 +178,30 @@ static bool dma_fence_chain_signaled(struct dma_fence *fence) static void dma_fence_chain_release(struct dma_fence *fence) { struct dma_fence_chain *chain = to_dma_fence_chain(fence); + struct dma_fence *prev; + + /* Manually unlink the chain as much as possible to avoid recursion + * and potential stack overflow. + */ + while ((prev = rcu_dereference_protected(chain->prev, true))) { + struct dma_fence_chain *prev_chain; + + if (kref_read(&prev->refcount) > 1) + break; + + prev_chain = to_dma_fence_chain(prev); + if (!prev_chain) + break; + + /* No need for atomic operations since we hold the last + * reference to prev_chain. + */ + chain->prev = prev_chain->prev; + RCU_INIT_POINTER(prev_chain->prev, NULL); + dma_fence_put(prev); + } + dma_fence_put(prev); - dma_fence_put(rcu_dereference_protected(chain->prev, true)); dma_fence_put(chain->fence); dma_fence_free(fence); } diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 59ac96ec7ba8..052a41e2451c 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -60,7 +60,7 @@ static atomic64_t dma_fence_context_counter = ATOMIC64_INIT(1); * * - 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 + * implicit fences are stored in &struct dma_resv through the * &dma_buf.resv pointer. */ @@ -129,31 +129,27 @@ EXPORT_SYMBOL(dma_fence_context_alloc); int dma_fence_signal_locked(struct dma_fence *fence) { struct dma_fence_cb *cur, *tmp; - int ret = 0; + struct list_head cb_list; lockdep_assert_held(fence->lock); - if (WARN_ON(!fence)) + if (unlikely(test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, + &fence->flags))) return -EINVAL; - if (test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { - ret = -EINVAL; + /* Stash the cb_list before replacing it with the timestamp */ + list_replace(&fence->cb_list, &cb_list); - /* - * 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); - } + 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); + list_for_each_entry_safe(cur, tmp, &cb_list, node) { + INIT_LIST_HEAD(&cur->node); cur->func(fence, cur); } - return ret; + + return 0; } EXPORT_SYMBOL(dma_fence_signal_locked); @@ -173,28 +169,16 @@ EXPORT_SYMBOL(dma_fence_signal_locked); int dma_fence_signal(struct dma_fence *fence) { unsigned long flags; + int ret; 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); + ret = dma_fence_signal_locked(fence); + spin_unlock_irqrestore(fence->lock, flags); - 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; + return ret; } EXPORT_SYMBOL(dma_fence_signal); @@ -248,7 +232,8 @@ void dma_fence_release(struct kref *kref) trace_dma_fence_destroy(fence); - if (WARN(!list_empty(&fence->cb_list), + if (WARN(!list_empty(&fence->cb_list) && + !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags), "Fence %s:%s:%llx:%llx released with pending signals!\n", fence->ops->get_driver_name(fence), fence->ops->get_timeline_name(fence), @@ -288,6 +273,30 @@ void dma_fence_free(struct dma_fence *fence) } 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 @@ -300,19 +309,12 @@ void dma_fence_enable_sw_signaling(struct dma_fence *fence) { unsigned long flags; - if (!test_and_set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, - &fence->flags) && - !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags) && - fence->ops->enable_signaling) { - trace_dma_fence_enable_signal(fence); - - spin_lock_irqsave(fence->lock, flags); - - if (!fence->ops->enable_signaling(fence)) - dma_fence_signal_locked(fence); + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return; - spin_unlock_irqrestore(fence->lock, flags); - } + spin_lock_irqsave(fence->lock, flags); + __dma_fence_enable_signaling(fence); + spin_unlock_irqrestore(fence->lock, flags); } EXPORT_SYMBOL(dma_fence_enable_sw_signaling); @@ -346,7 +348,6 @@ int dma_fence_add_callback(struct dma_fence *fence, struct dma_fence_cb *cb, { unsigned long flags; int ret = 0; - bool was_set; if (WARN_ON(!fence || !func)) return -EINVAL; @@ -358,25 +359,14 @@ int dma_fence_add_callback(struct dma_fence *fence, struct dma_fence_cb *cb, spin_lock_irqsave(fence->lock, flags); - was_set = test_and_set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, - &fence->flags); - - if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) - ret = -ENOENT; - else if (!was_set && fence->ops->enable_signaling) { - trace_dma_fence_enable_signal(fence); - - if (!fence->ops->enable_signaling(fence)) { - dma_fence_signal_locked(fence); - ret = -ENOENT; - } - } - - if (!ret) { + if (__dma_fence_enable_signaling(fence)) { cb->func = func; list_add_tail(&cb->node, &fence->cb_list); - } else + } else { INIT_LIST_HEAD(&cb->node); + ret = -ENOENT; + } + spin_unlock_irqrestore(fence->lock, flags); return ret; @@ -476,7 +466,6 @@ 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; - bool was_set; if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) return ret; @@ -488,21 +477,9 @@ dma_fence_default_wait(struct dma_fence *fence, bool intr, signed long timeout) goto out; } - was_set = test_and_set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, - &fence->flags); - - if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + if (!__dma_fence_enable_signaling(fence)) goto out; - if (!was_set && fence->ops->enable_signaling) { - trace_dma_fence_enable_signal(fence); - - if (!fence->ops->enable_signaling(fence)) { - dma_fence_signal_locked(fence); - goto out; - } - } - if (!timeout) { ret = 0; goto out; diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c new file mode 100644 index 000000000000..afd22c9dbdcf --- /dev/null +++ b/drivers/dma-buf/dma-heap.c @@ -0,0 +1,298 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Framework for userspace DMA-BUF allocations + * + * Copyright (C) 2011 Google, Inc. + * Copyright (C) 2019 Linaro Ltd. + */ + +#include <linux/cdev.h> +#include <linux/debugfs.h> +#include <linux/device.h> +#include <linux/dma-buf.h> +#include <linux/err.h> +#include <linux/xarray.h> +#include <linux/list.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/syscalls.h> +#include <linux/dma-heap.h> +#include <uapi/linux/dma-heap.h> + +#define DEVNAME "dma_heap" + +#define NUM_HEAP_MINORS 128 + +/** + * struct dma_heap - represents a dmabuf heap in the system + * @name: used for debugging/device-node name + * @ops: ops struct for this heap + * @heap_devt heap device node + * @list list head connecting to list of heaps + * @heap_cdev heap char device + * + * Represents a heap of memory from which buffers can be made. + */ +struct dma_heap { + const char *name; + const struct dma_heap_ops *ops; + void *priv; + dev_t heap_devt; + struct list_head list; + struct cdev heap_cdev; +}; + +static LIST_HEAD(heap_list); +static DEFINE_MUTEX(heap_list_lock); +static dev_t dma_heap_devt; +static struct class *dma_heap_class; +static DEFINE_XARRAY_ALLOC(dma_heap_minors); + +static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len, + unsigned int fd_flags, + unsigned int heap_flags) +{ + /* + * Allocations from all heaps have to begin + * and end on page boundaries. + */ + len = PAGE_ALIGN(len); + if (!len) + return -EINVAL; + + return heap->ops->allocate(heap, len, fd_flags, heap_flags); +} + +static int dma_heap_open(struct inode *inode, struct file *file) +{ + struct dma_heap *heap; + + heap = xa_load(&dma_heap_minors, iminor(inode)); + if (!heap) { + pr_err("dma_heap: minor %d unknown.\n", iminor(inode)); + return -ENODEV; + } + + /* instance data as context */ + file->private_data = heap; + nonseekable_open(inode, file); + + return 0; +} + +static long dma_heap_ioctl_allocate(struct file *file, void *data) +{ + struct dma_heap_allocation_data *heap_allocation = data; + struct dma_heap *heap = file->private_data; + int fd; + + if (heap_allocation->fd) + return -EINVAL; + + if (heap_allocation->fd_flags & ~DMA_HEAP_VALID_FD_FLAGS) + return -EINVAL; + + if (heap_allocation->heap_flags & ~DMA_HEAP_VALID_HEAP_FLAGS) + return -EINVAL; + + fd = dma_heap_buffer_alloc(heap, heap_allocation->len, + heap_allocation->fd_flags, + heap_allocation->heap_flags); + if (fd < 0) + return fd; + + heap_allocation->fd = fd; + + return 0; +} + +static unsigned int dma_heap_ioctl_cmds[] = { + DMA_HEAP_IOCTL_ALLOC, +}; + +static long dma_heap_ioctl(struct file *file, unsigned int ucmd, + unsigned long arg) +{ + char stack_kdata[128]; + char *kdata = stack_kdata; + unsigned int kcmd; + unsigned int in_size, out_size, drv_size, ksize; + int nr = _IOC_NR(ucmd); + int ret = 0; + + if (nr >= ARRAY_SIZE(dma_heap_ioctl_cmds)) + return -EINVAL; + + /* Get the kernel ioctl cmd that matches */ + kcmd = dma_heap_ioctl_cmds[nr]; + + /* Figure out the delta between user cmd size and kernel cmd size */ + drv_size = _IOC_SIZE(kcmd); + out_size = _IOC_SIZE(ucmd); + in_size = out_size; + if ((ucmd & kcmd & IOC_IN) == 0) + in_size = 0; + if ((ucmd & kcmd & IOC_OUT) == 0) + out_size = 0; + ksize = max(max(in_size, out_size), drv_size); + + /* If necessary, allocate buffer for ioctl argument */ + if (ksize > sizeof(stack_kdata)) { + kdata = kmalloc(ksize, GFP_KERNEL); + if (!kdata) + return -ENOMEM; + } + + if (copy_from_user(kdata, (void __user *)arg, in_size) != 0) { + ret = -EFAULT; + goto err; + } + + /* zero out any difference between the kernel/user structure size */ + if (ksize > in_size) + memset(kdata + in_size, 0, ksize - in_size); + + switch (kcmd) { + case DMA_HEAP_IOCTL_ALLOC: + ret = dma_heap_ioctl_allocate(file, kdata); + break; + default: + ret = -ENOTTY; + goto err; + } + + if (copy_to_user((void __user *)arg, kdata, out_size) != 0) + ret = -EFAULT; +err: + if (kdata != stack_kdata) + kfree(kdata); + return ret; +} + +static const struct file_operations dma_heap_fops = { + .owner = THIS_MODULE, + .open = dma_heap_open, + .unlocked_ioctl = dma_heap_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = dma_heap_ioctl, +#endif +}; + +/** + * dma_heap_get_drvdata() - get per-subdriver data for the heap + * @heap: DMA-Heap to retrieve private data for + * + * Returns: + * The per-subdriver data for the heap. + */ +void *dma_heap_get_drvdata(struct dma_heap *heap) +{ + return heap->priv; +} + +struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) +{ + struct dma_heap *heap, *h, *err_ret; + struct device *dev_ret; + unsigned int minor; + int ret; + + if (!exp_info->name || !strcmp(exp_info->name, "")) { + pr_err("dma_heap: Cannot add heap without a name\n"); + return ERR_PTR(-EINVAL); + } + + if (!exp_info->ops || !exp_info->ops->allocate) { + pr_err("dma_heap: Cannot add heap with invalid ops struct\n"); + return ERR_PTR(-EINVAL); + } + + /* check the name is unique */ + mutex_lock(&heap_list_lock); + list_for_each_entry(h, &heap_list, list) { + if (!strcmp(h->name, exp_info->name)) { + mutex_unlock(&heap_list_lock); + pr_err("dma_heap: Already registered heap named %s\n", + exp_info->name); + return ERR_PTR(-EINVAL); + } + } + mutex_unlock(&heap_list_lock); + + heap = kzalloc(sizeof(*heap), GFP_KERNEL); + if (!heap) + return ERR_PTR(-ENOMEM); + + heap->name = exp_info->name; + heap->ops = exp_info->ops; + heap->priv = exp_info->priv; + + /* Find unused minor number */ + ret = xa_alloc(&dma_heap_minors, &minor, heap, + XA_LIMIT(0, NUM_HEAP_MINORS - 1), GFP_KERNEL); + if (ret < 0) { + pr_err("dma_heap: Unable to get minor number for heap\n"); + err_ret = ERR_PTR(ret); + goto err0; + } + + /* Create device */ + heap->heap_devt = MKDEV(MAJOR(dma_heap_devt), minor); + + cdev_init(&heap->heap_cdev, &dma_heap_fops); + ret = cdev_add(&heap->heap_cdev, heap->heap_devt, 1); + if (ret < 0) { + pr_err("dma_heap: Unable to add char device\n"); + err_ret = ERR_PTR(ret); + goto err1; + } + + dev_ret = device_create(dma_heap_class, + NULL, + heap->heap_devt, + NULL, + heap->name); + if (IS_ERR(dev_ret)) { + pr_err("dma_heap: Unable to create device\n"); + err_ret = ERR_CAST(dev_ret); + goto err2; + } + /* Add heap to the list */ + mutex_lock(&heap_list_lock); + list_add(&heap->list, &heap_list); + mutex_unlock(&heap_list_lock); + + return heap; + +err2: + cdev_del(&heap->heap_cdev); +err1: + xa_erase(&dma_heap_minors, minor); +err0: + kfree(heap); + return err_ret; +} + +static char *dma_heap_devnode(struct device *dev, umode_t *mode) +{ + return kasprintf(GFP_KERNEL, "dma_heap/%s", dev_name(dev)); +} + +static int dma_heap_init(void) +{ + int ret; + + ret = alloc_chrdev_region(&dma_heap_devt, 0, NUM_HEAP_MINORS, DEVNAME); + if (ret) + return ret; + + dma_heap_class = class_create(THIS_MODULE, DEVNAME); + if (IS_ERR(dma_heap_class)) { + unregister_chrdev_region(dma_heap_devt, NUM_HEAP_MINORS); + return PTR_ERR(dma_heap_class); + } + dma_heap_class->devnode = dma_heap_devnode; + + return 0; +} +subsys_initcall(dma_heap_init); diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/dma-resv.c index 4447e13d1e89..4264e64788c4 100644 --- a/drivers/dma-buf/reservation.c +++ b/drivers/dma-buf/dma-resv.c @@ -32,8 +32,9 @@ * Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com> */ -#include <linux/reservation.h> +#include <linux/dma-resv.h> #include <linux/export.h> +#include <linux/sched/mm.h> /** * DOC: Reservation Object Overview @@ -56,26 +57,134 @@ const char reservation_seqcount_string[] = "reservation_seqcount"; EXPORT_SYMBOL(reservation_seqcount_string); /** - * reservation_object_reserve_shared - Reserve space to add shared fences to - * a reservation_object. + * dma_resv_list_alloc - allocate fence list + * @shared_max: number of fences we need space for + * + * Allocate a new dma_resv_list and make sure to correctly initialize + * shared_max. + */ +static struct dma_resv_list *dma_resv_list_alloc(unsigned int shared_max) +{ + struct dma_resv_list *list; + + list = kmalloc(offsetof(typeof(*list), shared[shared_max]), GFP_KERNEL); + if (!list) + return NULL; + + list->shared_max = (ksize(list) - offsetof(typeof(*list), shared)) / + sizeof(*list->shared); + + return list; +} + +/** + * dma_resv_list_free - free fence list + * @list: list to free + * + * Free a dma_resv_list and make sure to drop all references. + */ +static void dma_resv_list_free(struct dma_resv_list *list) +{ + unsigned int i; + + if (!list) + return; + + for (i = 0; i < list->shared_count; ++i) + dma_fence_put(rcu_dereference_protected(list->shared[i], true)); + + kfree_rcu(list, rcu); +} + +#if IS_ENABLED(CONFIG_LOCKDEP) +static int __init dma_resv_lockdep(void) +{ + struct mm_struct *mm = mm_alloc(); + struct ww_acquire_ctx ctx; + struct dma_resv obj; + int ret; + + if (!mm) + return -ENOMEM; + + dma_resv_init(&obj); + + down_read(&mm->mmap_sem); + ww_acquire_init(&ctx, &reservation_ww_class); + ret = dma_resv_lock(&obj, &ctx); + if (ret == -EDEADLK) + dma_resv_lock_slow(&obj, &ctx); + fs_reclaim_acquire(GFP_KERNEL); + fs_reclaim_release(GFP_KERNEL); + ww_mutex_unlock(&obj.lock); + ww_acquire_fini(&ctx); + up_read(&mm->mmap_sem); + + mmput(mm); + + return 0; +} +subsys_initcall(dma_resv_lockdep); +#endif + +/** + * dma_resv_init - initialize a reservation object + * @obj: the reservation object + */ +void dma_resv_init(struct dma_resv *obj) +{ + ww_mutex_init(&obj->lock, &reservation_ww_class); + + __seqcount_init(&obj->seq, reservation_seqcount_string, + &reservation_seqcount_class); + RCU_INIT_POINTER(obj->fence, NULL); + RCU_INIT_POINTER(obj->fence_excl, NULL); +} +EXPORT_SYMBOL(dma_resv_init); + +/** + * dma_resv_fini - destroys a reservation object + * @obj: the reservation object + */ +void dma_resv_fini(struct dma_resv *obj) +{ + struct dma_resv_list *fobj; + struct dma_fence *excl; + + /* + * This object should be dead and all references must have + * been released to it, so no need to be protected with rcu. + */ + excl = rcu_dereference_protected(obj->fence_excl, 1); + if (excl) + dma_fence_put(excl); + + fobj = rcu_dereference_protected(obj->fence, 1); + dma_resv_list_free(fobj); + ww_mutex_destroy(&obj->lock); +} +EXPORT_SYMBOL(dma_resv_fini); + +/** + * dma_resv_reserve_shared - Reserve space to add shared fences to + * a dma_resv. * @obj: reservation object * @num_fences: number of fences we want to add * - * Should be called before reservation_object_add_shared_fence(). Must + * Should be called before dma_resv_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, - unsigned int num_fences) +int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences) { - struct reservation_object_list *old, *new; + struct dma_resv_list *old, *new; unsigned int i, j, k, max; - reservation_object_assert_held(obj); + dma_resv_assert_held(obj); - old = reservation_object_get_list(obj); + old = dma_resv_get_list(obj); if (old && old->shared_max) { if ((old->shared_count + num_fences) <= old->shared_max) @@ -87,7 +196,7 @@ int reservation_object_reserve_shared(struct reservation_object *obj, max = 4; } - new = kmalloc(offsetof(typeof(*new), shared[max]), GFP_KERNEL); + new = dma_resv_list_alloc(max); if (!new) return -ENOMEM; @@ -101,79 +210,76 @@ int reservation_object_reserve_shared(struct reservation_object *obj, struct dma_fence *fence; fence = rcu_dereference_protected(old->shared[i], - reservation_object_held(obj)); + dma_resv_held(obj)); if (dma_fence_is_signaled(fence)) RCU_INIT_POINTER(new->shared[--k], fence); else RCU_INIT_POINTER(new->shared[j++], fence); } new->shared_count = j; - new->shared_max = max; - preempt_disable(); - write_seqcount_begin(&obj->seq); /* - * RCU_INIT_POINTER can be used here, - * seqcount provides the necessary barriers + * We are not changing the effective set of fences here so can + * merely update the pointer to the new array; both existing + * readers and new readers will see exactly the same set of + * active (unsignaled) shared fences. Individual fences and the + * old array are protected by RCU and so will not vanish under + * the gaze of the rcu_read_lock() readers. */ - RCU_INIT_POINTER(obj->fence, new); - write_seqcount_end(&obj->seq); - preempt_enable(); + rcu_assign_pointer(obj->fence, new); if (!old) return 0; /* Drop the references to the signaled fences */ - for (i = k; i < new->shared_max; ++i) { + for (i = k; i < max; ++i) { struct dma_fence *fence; fence = rcu_dereference_protected(new->shared[i], - reservation_object_held(obj)); + dma_resv_held(obj)); dma_fence_put(fence); } kfree_rcu(old, rcu); return 0; } -EXPORT_SYMBOL(reservation_object_reserve_shared); +EXPORT_SYMBOL(dma_resv_reserve_shared); /** - * reservation_object_add_shared_fence - Add a fence to a shared slot + * dma_resv_add_shared_fence - Add a fence to a shared slot * @obj: the reservation object * @fence: the shared fence to add * * Add a fence to a shared slot, obj->lock must be held, and - * reservation_object_reserve_shared() has been called. + * dma_resv_reserve_shared() has been called. */ -void reservation_object_add_shared_fence(struct reservation_object *obj, - struct dma_fence *fence) +void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence) { - struct reservation_object_list *fobj; + struct dma_resv_list *fobj; + struct dma_fence *old; unsigned int i, count; dma_fence_get(fence); - reservation_object_assert_held(obj); + dma_resv_assert_held(obj); - fobj = reservation_object_get_list(obj); + fobj = dma_resv_get_list(obj); count = fobj->shared_count; preempt_disable(); write_seqcount_begin(&obj->seq); for (i = 0; i < 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 || - dma_fence_is_signaled(old_fence)) { - dma_fence_put(old_fence); + old = rcu_dereference_protected(fobj->shared[i], + dma_resv_held(obj)); + if (old->context == fence->context || + dma_fence_is_signaled(old)) goto replace; - } } BUG_ON(fobj->shared_count >= fobj->shared_max); + old = NULL; count++; replace: @@ -183,26 +289,26 @@ replace: write_seqcount_end(&obj->seq); preempt_enable(); + dma_fence_put(old); } -EXPORT_SYMBOL(reservation_object_add_shared_fence); +EXPORT_SYMBOL(dma_resv_add_shared_fence); /** - * reservation_object_add_excl_fence - Add an exclusive fence. + * dma_resv_add_excl_fence - Add an exclusive fence. * @obj: the reservation object * @fence: the shared fence to add * * Add a fence to the exclusive slot. The obj->lock must be held. */ -void reservation_object_add_excl_fence(struct reservation_object *obj, - struct dma_fence *fence) +void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence) { - struct dma_fence *old_fence = reservation_object_get_excl(obj); - struct reservation_object_list *old; + struct dma_fence *old_fence = dma_resv_get_excl(obj); + struct dma_resv_list *old; u32 i = 0; - reservation_object_assert_held(obj); + dma_resv_assert_held(obj); - old = reservation_object_get_list(obj); + old = dma_resv_get_list(obj); if (old) i = old->shared_count; @@ -221,28 +327,26 @@ void reservation_object_add_excl_fence(struct reservation_object *obj, /* inplace update, no shared fences */ while (i--) dma_fence_put(rcu_dereference_protected(old->shared[i], - reservation_object_held(obj))); + dma_resv_held(obj))); dma_fence_put(old_fence); } -EXPORT_SYMBOL(reservation_object_add_excl_fence); +EXPORT_SYMBOL(dma_resv_add_excl_fence); /** -* reservation_object_copy_fences - Copy all fences from src to dst. +* dma_resv_copy_fences - Copy all fences from src to dst. * @dst: the destination reservation object * @src: the source reservation object * * Copy all fences from src to dst. dst-lock must be held. */ -int reservation_object_copy_fences(struct reservation_object *dst, - struct reservation_object *src) +int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src) { - struct reservation_object_list *src_list, *dst_list; + struct dma_resv_list *src_list, *dst_list; struct dma_fence *old, *new; - size_t size; unsigned i; - reservation_object_assert_held(dst); + dma_resv_assert_held(dst); rcu_read_lock(); src_list = rcu_dereference(src->fence); @@ -251,10 +355,9 @@ 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); + dst_list = dma_resv_list_alloc(shared_count); if (!dst_list) return -ENOMEM; @@ -266,7 +369,6 @@ 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; @@ -276,7 +378,7 @@ retry: continue; if (!dma_fence_get_rcu(fence)) { - kfree(dst_list); + dma_resv_list_free(dst_list); src_list = rcu_dereference(src->fence); goto retry; } @@ -295,8 +397,8 @@ retry: new = dma_fence_get_rcu_safe(&src->fence_excl); rcu_read_unlock(); - src_list = reservation_object_get_list(dst); - old = reservation_object_get_excl(dst); + src_list = dma_resv_get_list(dst); + old = dma_resv_get_excl(dst); preempt_disable(); write_seqcount_begin(&dst->seq); @@ -306,16 +408,15 @@ retry: write_seqcount_end(&dst->seq); preempt_enable(); - if (src_list) - kfree_rcu(src_list, rcu); + dma_resv_list_free(src_list); dma_fence_put(old); return 0; } -EXPORT_SYMBOL(reservation_object_copy_fences); +EXPORT_SYMBOL(dma_resv_copy_fences); /** - * reservation_object_get_fences_rcu - Get an object's shared and exclusive + * dma_resv_get_fences_rcu - Get an object's shared and exclusive * fences without update side lock held * @obj: the reservation object * @pfence_excl: the returned exclusive fence (or NULL) @@ -327,10 +428,10 @@ EXPORT_SYMBOL(reservation_object_copy_fences); * 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) +int dma_resv_get_fences_rcu(struct dma_resv *obj, + struct dma_fence **pfence_excl, + unsigned *pshared_count, + struct dma_fence ***pshared) { struct dma_fence **shared = NULL; struct dma_fence *fence_excl; @@ -338,7 +439,7 @@ int reservation_object_get_fences_rcu(struct reservation_object *obj, int ret = 1; do { - struct reservation_object_list *fobj; + struct dma_resv_list *fobj; unsigned int i, seq; size_t sz = 0; @@ -385,13 +486,6 @@ int reservation_object_get_fences_rcu(struct reservation_object *obj, 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)) { @@ -406,6 +500,11 @@ unlock: rcu_read_unlock(); } while (ret); + if (pfence_excl) + *pfence_excl = fence_excl; + else if (fence_excl) + shared[shared_count++] = fence_excl; + if (!shared_count) { kfree(shared); shared = NULL; @@ -413,15 +512,12 @@ unlock: *pshared_count = shared_count; *pshared = shared; - if (pfence_excl) - *pfence_excl = fence_excl; - return ret; } -EXPORT_SYMBOL_GPL(reservation_object_get_fences_rcu); +EXPORT_SYMBOL_GPL(dma_resv_get_fences_rcu); /** - * reservation_object_wait_timeout_rcu - Wait on reservation's objects + * dma_resv_wait_timeout_rcu - Wait on reservation's objects * shared and/or exclusive fences. * @obj: the reservation object * @wait_all: if true, wait on all fences, else wait on just exclusive fence @@ -432,9 +528,9 @@ EXPORT_SYMBOL_GPL(reservation_object_get_fences_rcu); * 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) +long dma_resv_wait_timeout_rcu(struct dma_resv *obj, + bool wait_all, bool intr, + unsigned long timeout) { struct dma_fence *fence; unsigned seq, shared_count; @@ -462,8 +558,7 @@ retry: } if (wait_all) { - struct reservation_object_list *fobj = - rcu_dereference(obj->fence); + struct dma_resv_list *fobj = rcu_dereference(obj->fence); if (fobj) shared_count = fobj->shared_count; @@ -506,11 +601,10 @@ unlock_retry: rcu_read_unlock(); goto retry; } -EXPORT_SYMBOL_GPL(reservation_object_wait_timeout_rcu); +EXPORT_SYMBOL_GPL(dma_resv_wait_timeout_rcu); -static inline int -reservation_object_test_signaled_single(struct dma_fence *passed_fence) +static inline int dma_resv_test_signaled_single(struct dma_fence *passed_fence) { struct dma_fence *fence, *lfence = passed_fence; int ret = 1; @@ -527,7 +621,7 @@ reservation_object_test_signaled_single(struct dma_fence *passed_fence) } /** - * reservation_object_test_signaled_rcu - Test if a reservation object's + * dma_resv_test_signaled_rcu - Test if a reservation object's * fences have been signaled. * @obj: the reservation object * @test_all: if true, test all fences, otherwise only test the exclusive @@ -536,8 +630,7 @@ reservation_object_test_signaled_single(struct dma_fence *passed_fence) * RETURNS * true if all fences signaled, else false */ -bool reservation_object_test_signaled_rcu(struct reservation_object *obj, - bool test_all) +bool dma_resv_test_signaled_rcu(struct dma_resv *obj, bool test_all) { unsigned seq, shared_count; int ret; @@ -551,8 +644,7 @@ retry: if (test_all) { unsigned i; - struct reservation_object_list *fobj = - rcu_dereference(obj->fence); + struct dma_resv_list *fobj = rcu_dereference(obj->fence); if (fobj) shared_count = fobj->shared_count; @@ -560,7 +652,7 @@ retry: for (i = 0; i < shared_count; ++i) { struct dma_fence *fence = rcu_dereference(fobj->shared[i]); - ret = reservation_object_test_signaled_single(fence); + ret = dma_resv_test_signaled_single(fence); if (ret < 0) goto retry; else if (!ret) @@ -575,8 +667,7 @@ retry: struct dma_fence *fence_excl = rcu_dereference(obj->fence_excl); if (fence_excl) { - ret = reservation_object_test_signaled_single( - fence_excl); + ret = dma_resv_test_signaled_single(fence_excl); if (ret < 0) goto retry; @@ -588,4 +679,4 @@ retry: rcu_read_unlock(); return ret; } -EXPORT_SYMBOL_GPL(reservation_object_test_signaled_rcu); +EXPORT_SYMBOL_GPL(dma_resv_test_signaled_rcu); diff --git a/drivers/dma-buf/heaps/Kconfig b/drivers/dma-buf/heaps/Kconfig new file mode 100644 index 000000000000..a5eef06c4226 --- /dev/null +++ b/drivers/dma-buf/heaps/Kconfig @@ -0,0 +1,14 @@ +config DMABUF_HEAPS_SYSTEM + bool "DMA-BUF System Heap" + depends on DMABUF_HEAPS + help + Choose this option to enable the system dmabuf heap. The system heap + is backed by pages from the buddy allocator. If in doubt, say Y. + +config DMABUF_HEAPS_CMA + bool "DMA-BUF CMA Heap" + depends on DMABUF_HEAPS && DMA_CMA + help + Choose this option to enable dma-buf CMA heap. This heap is backed + by the Contiguous Memory Allocator (CMA). If your system has these + regions, you should say Y here. diff --git a/drivers/dma-buf/heaps/Makefile b/drivers/dma-buf/heaps/Makefile new file mode 100644 index 000000000000..6e54cdec3da0 --- /dev/null +++ b/drivers/dma-buf/heaps/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-y += heap-helpers.o +obj-$(CONFIG_DMABUF_HEAPS_SYSTEM) += system_heap.o +obj-$(CONFIG_DMABUF_HEAPS_CMA) += cma_heap.o diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c new file mode 100644 index 000000000000..626cf7fd033a --- /dev/null +++ b/drivers/dma-buf/heaps/cma_heap.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DMABUF CMA heap exporter + * + * Copyright (C) 2012, 2019 Linaro Ltd. + * Author: <benjamin.gaignard@linaro.org> for ST-Ericsson. + */ + +#include <linux/cma.h> +#include <linux/device.h> +#include <linux/dma-buf.h> +#include <linux/dma-heap.h> +#include <linux/dma-contiguous.h> +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/highmem.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/scatterlist.h> +#include <linux/sched/signal.h> + +#include "heap-helpers.h" + +struct cma_heap { + struct dma_heap *heap; + struct cma *cma; +}; + +static void cma_heap_free(struct heap_helper_buffer *buffer) +{ + struct cma_heap *cma_heap = dma_heap_get_drvdata(buffer->heap); + unsigned long nr_pages = buffer->pagecount; + struct page *cma_pages = buffer->priv_virt; + + /* free page list */ + kfree(buffer->pages); + /* release memory */ + cma_release(cma_heap->cma, cma_pages, nr_pages); + kfree(buffer); +} + +/* dmabuf heap CMA operations functions */ +static int cma_heap_allocate(struct dma_heap *heap, + unsigned long len, + unsigned long fd_flags, + unsigned long heap_flags) +{ + struct cma_heap *cma_heap = dma_heap_get_drvdata(heap); + struct heap_helper_buffer *helper_buffer; + struct page *cma_pages; + size_t size = PAGE_ALIGN(len); + unsigned long nr_pages = size >> PAGE_SHIFT; + unsigned long align = get_order(size); + struct dma_buf *dmabuf; + int ret = -ENOMEM; + pgoff_t pg; + + if (align > CONFIG_CMA_ALIGNMENT) + align = CONFIG_CMA_ALIGNMENT; + + helper_buffer = kzalloc(sizeof(*helper_buffer), GFP_KERNEL); + if (!helper_buffer) + return -ENOMEM; + + init_heap_helper_buffer(helper_buffer, cma_heap_free); + helper_buffer->heap = heap; + helper_buffer->size = len; + + cma_pages = cma_alloc(cma_heap->cma, nr_pages, align, false); + if (!cma_pages) + goto free_buf; + + if (PageHighMem(cma_pages)) { + unsigned long nr_clear_pages = nr_pages; + struct page *page = cma_pages; + + while (nr_clear_pages > 0) { + void *vaddr = kmap_atomic(page); + + memset(vaddr, 0, PAGE_SIZE); + kunmap_atomic(vaddr); + /* + * Avoid wasting time zeroing memory if the process + * has been killed by by SIGKILL + */ + if (fatal_signal_pending(current)) + goto free_cma; + + page++; + nr_clear_pages--; + } + } else { + memset(page_address(cma_pages), 0, size); + } + + helper_buffer->pagecount = nr_pages; + helper_buffer->pages = kmalloc_array(helper_buffer->pagecount, + sizeof(*helper_buffer->pages), + GFP_KERNEL); + if (!helper_buffer->pages) { + ret = -ENOMEM; + goto free_cma; + } + + for (pg = 0; pg < helper_buffer->pagecount; pg++) + helper_buffer->pages[pg] = &cma_pages[pg]; + + /* create the dmabuf */ + dmabuf = heap_helper_export_dmabuf(helper_buffer, fd_flags); + if (IS_ERR(dmabuf)) { + ret = PTR_ERR(dmabuf); + goto free_pages; + } + + helper_buffer->dmabuf = dmabuf; + helper_buffer->priv_virt = cma_pages; + + ret = dma_buf_fd(dmabuf, fd_flags); + if (ret < 0) { + dma_buf_put(dmabuf); + /* just return, as put will call release and that will free */ + return ret; + } + + return ret; + +free_pages: + kfree(helper_buffer->pages); +free_cma: + cma_release(cma_heap->cma, cma_pages, nr_pages); +free_buf: + kfree(helper_buffer); + return ret; +} + +static const struct dma_heap_ops cma_heap_ops = { + .allocate = cma_heap_allocate, +}; + +static int __add_cma_heap(struct cma *cma, void *data) +{ + struct cma_heap *cma_heap; + struct dma_heap_export_info exp_info; + + cma_heap = kzalloc(sizeof(*cma_heap), GFP_KERNEL); + if (!cma_heap) + return -ENOMEM; + cma_heap->cma = cma; + + exp_info.name = cma_get_name(cma); + exp_info.ops = &cma_heap_ops; + exp_info.priv = cma_heap; + + cma_heap->heap = dma_heap_add(&exp_info); + if (IS_ERR(cma_heap->heap)) { + int ret = PTR_ERR(cma_heap->heap); + + kfree(cma_heap); + return ret; + } + + return 0; +} + +static int add_default_cma_heap(void) +{ + struct cma *default_cma = dev_get_cma_area(NULL); + int ret = 0; + + if (default_cma) + ret = __add_cma_heap(default_cma, NULL); + + return ret; +} +module_init(add_default_cma_heap); +MODULE_DESCRIPTION("DMA-BUF CMA Heap"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/dma-buf/heaps/heap-helpers.c b/drivers/dma-buf/heaps/heap-helpers.c new file mode 100644 index 000000000000..9f964ca3f59c --- /dev/null +++ b/drivers/dma-buf/heaps/heap-helpers.c @@ -0,0 +1,271 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/device.h> +#include <linux/dma-buf.h> +#include <linux/err.h> +#include <linux/highmem.h> +#include <linux/idr.h> +#include <linux/list.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/vmalloc.h> +#include <uapi/linux/dma-heap.h> + +#include "heap-helpers.h" + +void init_heap_helper_buffer(struct heap_helper_buffer *buffer, + void (*free)(struct heap_helper_buffer *)) +{ + buffer->priv_virt = NULL; + mutex_init(&buffer->lock); + buffer->vmap_cnt = 0; + buffer->vaddr = NULL; + buffer->pagecount = 0; + buffer->pages = NULL; + INIT_LIST_HEAD(&buffer->attachments); + buffer->free = free; +} + +struct dma_buf *heap_helper_export_dmabuf(struct heap_helper_buffer *buffer, + int fd_flags) +{ + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); + + exp_info.ops = &heap_helper_ops; + exp_info.size = buffer->size; + exp_info.flags = fd_flags; + exp_info.priv = buffer; + + return dma_buf_export(&exp_info); +} + +static void *dma_heap_map_kernel(struct heap_helper_buffer *buffer) +{ + void *vaddr; + + vaddr = vmap(buffer->pages, buffer->pagecount, VM_MAP, PAGE_KERNEL); + if (!vaddr) + return ERR_PTR(-ENOMEM); + + return vaddr; +} + +static void dma_heap_buffer_destroy(struct heap_helper_buffer *buffer) +{ + if (buffer->vmap_cnt > 0) { + WARN(1, "%s: buffer still mapped in the kernel\n", __func__); + vunmap(buffer->vaddr); + } + + buffer->free(buffer); +} + +static void *dma_heap_buffer_vmap_get(struct heap_helper_buffer *buffer) +{ + void *vaddr; + + if (buffer->vmap_cnt) { + buffer->vmap_cnt++; + return buffer->vaddr; + } + vaddr = dma_heap_map_kernel(buffer); + if (IS_ERR(vaddr)) + return vaddr; + buffer->vaddr = vaddr; + buffer->vmap_cnt++; + return vaddr; +} + +static void dma_heap_buffer_vmap_put(struct heap_helper_buffer *buffer) +{ + if (!--buffer->vmap_cnt) { + vunmap(buffer->vaddr); + buffer->vaddr = NULL; + } +} + +struct dma_heaps_attachment { + struct device *dev; + struct sg_table table; + struct list_head list; +}; + +static int dma_heap_attach(struct dma_buf *dmabuf, + struct dma_buf_attachment *attachment) +{ + struct dma_heaps_attachment *a; + struct heap_helper_buffer *buffer = dmabuf->priv; + int ret; + + a = kzalloc(sizeof(*a), GFP_KERNEL); + if (!a) + return -ENOMEM; + + ret = sg_alloc_table_from_pages(&a->table, buffer->pages, + buffer->pagecount, 0, + buffer->pagecount << PAGE_SHIFT, + GFP_KERNEL); + if (ret) { + kfree(a); + return ret; + } + + a->dev = attachment->dev; + INIT_LIST_HEAD(&a->list); + + attachment->priv = a; + + mutex_lock(&buffer->lock); + list_add(&a->list, &buffer->attachments); + mutex_unlock(&buffer->lock); + + return 0; +} + +static void dma_heap_detach(struct dma_buf *dmabuf, + struct dma_buf_attachment *attachment) +{ + struct dma_heaps_attachment *a = attachment->priv; + struct heap_helper_buffer *buffer = dmabuf->priv; + + mutex_lock(&buffer->lock); + list_del(&a->list); + mutex_unlock(&buffer->lock); + + sg_free_table(&a->table); + kfree(a); +} + +static +struct sg_table *dma_heap_map_dma_buf(struct dma_buf_attachment *attachment, + enum dma_data_direction direction) +{ + struct dma_heaps_attachment *a = attachment->priv; + struct sg_table *table; + + table = &a->table; + + if (!dma_map_sg(attachment->dev, table->sgl, table->nents, + direction)) + table = ERR_PTR(-ENOMEM); + return table; +} + +static void dma_heap_unmap_dma_buf(struct dma_buf_attachment *attachment, + struct sg_table *table, + enum dma_data_direction direction) +{ + dma_unmap_sg(attachment->dev, table->sgl, table->nents, direction); +} + +static vm_fault_t dma_heap_vm_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct heap_helper_buffer *buffer = vma->vm_private_data; + + if (vmf->pgoff > buffer->pagecount) + return VM_FAULT_SIGBUS; + + vmf->page = buffer->pages[vmf->pgoff]; + get_page(vmf->page); + + return 0; +} + +static const struct vm_operations_struct dma_heap_vm_ops = { + .fault = dma_heap_vm_fault, +}; + +static int dma_heap_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma) +{ + struct heap_helper_buffer *buffer = dmabuf->priv; + + if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0) + return -EINVAL; + + vma->vm_ops = &dma_heap_vm_ops; + vma->vm_private_data = buffer; + + return 0; +} + +static void dma_heap_dma_buf_release(struct dma_buf *dmabuf) +{ + struct heap_helper_buffer *buffer = dmabuf->priv; + + dma_heap_buffer_destroy(buffer); +} + +static int dma_heap_dma_buf_begin_cpu_access(struct dma_buf *dmabuf, + enum dma_data_direction direction) +{ + struct heap_helper_buffer *buffer = dmabuf->priv; + struct dma_heaps_attachment *a; + int ret = 0; + + mutex_lock(&buffer->lock); + + if (buffer->vmap_cnt) + invalidate_kernel_vmap_range(buffer->vaddr, buffer->size); + + list_for_each_entry(a, &buffer->attachments, list) { + dma_sync_sg_for_cpu(a->dev, a->table.sgl, a->table.nents, + direction); + } + mutex_unlock(&buffer->lock); + + return ret; +} + +static int dma_heap_dma_buf_end_cpu_access(struct dma_buf *dmabuf, + enum dma_data_direction direction) +{ + struct heap_helper_buffer *buffer = dmabuf->priv; + struct dma_heaps_attachment *a; + + mutex_lock(&buffer->lock); + + if (buffer->vmap_cnt) + flush_kernel_vmap_range(buffer->vaddr, buffer->size); + + list_for_each_entry(a, &buffer->attachments, list) { + dma_sync_sg_for_device(a->dev, a->table.sgl, a->table.nents, + direction); + } + mutex_unlock(&buffer->lock); + + return 0; +} + +static void *dma_heap_dma_buf_vmap(struct dma_buf *dmabuf) +{ + struct heap_helper_buffer *buffer = dmabuf->priv; + void *vaddr; + + mutex_lock(&buffer->lock); + vaddr = dma_heap_buffer_vmap_get(buffer); + mutex_unlock(&buffer->lock); + + return vaddr; +} + +static void dma_heap_dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr) +{ + struct heap_helper_buffer *buffer = dmabuf->priv; + + mutex_lock(&buffer->lock); + dma_heap_buffer_vmap_put(buffer); + mutex_unlock(&buffer->lock); +} + +const struct dma_buf_ops heap_helper_ops = { + .map_dma_buf = dma_heap_map_dma_buf, + .unmap_dma_buf = dma_heap_unmap_dma_buf, + .mmap = dma_heap_mmap, + .release = dma_heap_dma_buf_release, + .attach = dma_heap_attach, + .detach = dma_heap_detach, + .begin_cpu_access = dma_heap_dma_buf_begin_cpu_access, + .end_cpu_access = dma_heap_dma_buf_end_cpu_access, + .vmap = dma_heap_dma_buf_vmap, + .vunmap = dma_heap_dma_buf_vunmap, +}; diff --git a/drivers/dma-buf/heaps/heap-helpers.h b/drivers/dma-buf/heaps/heap-helpers.h new file mode 100644 index 000000000000..805d2df88024 --- /dev/null +++ b/drivers/dma-buf/heaps/heap-helpers.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * DMABUF Heaps helper code + * + * Copyright (C) 2011 Google, Inc. + * Copyright (C) 2019 Linaro Ltd. + */ + +#ifndef _HEAP_HELPERS_H +#define _HEAP_HELPERS_H + +#include <linux/dma-heap.h> +#include <linux/list.h> + +/** + * struct heap_helper_buffer - helper buffer metadata + * @heap: back pointer to the heap the buffer came from + * @dmabuf: backing dma-buf for this buffer + * @size: size of the buffer + * @priv_virt pointer to heap specific private value + * @lock mutext to protect the data in this structure + * @vmap_cnt count of vmap references on the buffer + * @vaddr vmap'ed virtual address + * @pagecount number of pages in the buffer + * @pages list of page pointers + * @attachments list of device attachments + * + * @free heap callback to free the buffer + */ +struct heap_helper_buffer { + struct dma_heap *heap; + struct dma_buf *dmabuf; + size_t size; + + void *priv_virt; + struct mutex lock; + int vmap_cnt; + void *vaddr; + pgoff_t pagecount; + struct page **pages; + struct list_head attachments; + + void (*free)(struct heap_helper_buffer *buffer); +}; + +void init_heap_helper_buffer(struct heap_helper_buffer *buffer, + void (*free)(struct heap_helper_buffer *)); + +struct dma_buf *heap_helper_export_dmabuf(struct heap_helper_buffer *buffer, + int fd_flags); + +extern const struct dma_buf_ops heap_helper_ops; +#endif /* _HEAP_HELPERS_H */ diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c new file mode 100644 index 000000000000..0bf688e3c023 --- /dev/null +++ b/drivers/dma-buf/heaps/system_heap.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DMABUF System heap exporter + * + * Copyright (C) 2011 Google, Inc. + * Copyright (C) 2019 Linaro Ltd. + */ + +#include <linux/dma-buf.h> +#include <linux/dma-mapping.h> +#include <linux/dma-heap.h> +#include <linux/err.h> +#include <linux/highmem.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/scatterlist.h> +#include <linux/slab.h> +#include <linux/sched/signal.h> +#include <asm/page.h> + +#include "heap-helpers.h" + +struct dma_heap *sys_heap; + +static void system_heap_free(struct heap_helper_buffer *buffer) +{ + pgoff_t pg; + + for (pg = 0; pg < buffer->pagecount; pg++) + __free_page(buffer->pages[pg]); + kfree(buffer->pages); + kfree(buffer); +} + +static int system_heap_allocate(struct dma_heap *heap, + unsigned long len, + unsigned long fd_flags, + unsigned long heap_flags) +{ + struct heap_helper_buffer *helper_buffer; + struct dma_buf *dmabuf; + int ret = -ENOMEM; + pgoff_t pg; + + helper_buffer = kzalloc(sizeof(*helper_buffer), GFP_KERNEL); + if (!helper_buffer) + return -ENOMEM; + + init_heap_helper_buffer(helper_buffer, system_heap_free); + helper_buffer->heap = heap; + helper_buffer->size = len; + + helper_buffer->pagecount = len / PAGE_SIZE; + helper_buffer->pages = kmalloc_array(helper_buffer->pagecount, + sizeof(*helper_buffer->pages), + GFP_KERNEL); + if (!helper_buffer->pages) { + ret = -ENOMEM; + goto err0; + } + + for (pg = 0; pg < helper_buffer->pagecount; pg++) { + /* + * Avoid trying to allocate memory if the process + * has been killed by by SIGKILL + */ + if (fatal_signal_pending(current)) + goto err1; + + helper_buffer->pages[pg] = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!helper_buffer->pages[pg]) + goto err1; + } + + /* create the dmabuf */ + dmabuf = heap_helper_export_dmabuf(helper_buffer, fd_flags); + if (IS_ERR(dmabuf)) { + ret = PTR_ERR(dmabuf); + goto err1; + } + + helper_buffer->dmabuf = dmabuf; + + ret = dma_buf_fd(dmabuf, fd_flags); + if (ret < 0) { + dma_buf_put(dmabuf); + /* just return, as put will call release and that will free */ + return ret; + } + + return ret; + +err1: + while (pg > 0) + __free_page(helper_buffer->pages[--pg]); + kfree(helper_buffer->pages); +err0: + kfree(helper_buffer); + + return ret; +} + +static const struct dma_heap_ops system_heap_ops = { + .allocate = system_heap_allocate, +}; + +static int system_heap_create(void) +{ + struct dma_heap_export_info exp_info; + int ret = 0; + + exp_info.name = "system"; + exp_info.ops = &system_heap_ops; + exp_info.priv = NULL; + + sys_heap = dma_heap_add(&exp_info); + if (IS_ERR(sys_heap)) + ret = PTR_ERR(sys_heap); + + return ret; +} +module_init(system_heap_create); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/dma-buf/selftest.c b/drivers/dma-buf/selftest.c new file mode 100644 index 000000000000..c60b6944b4bd --- /dev/null +++ b/drivers/dma-buf/selftest.c @@ -0,0 +1,167 @@ +/* SPDX-License-Identifier: MIT */ + +/* + * Copyright © 2019 Intel Corporation + */ + +#include <linux/compiler.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/sched/signal.h> +#include <linux/slab.h> + +#include "selftest.h" + +enum { +#define selftest(n, func) __idx_##n, +#include "selftests.h" +#undef selftest +}; + +#define selftest(n, f) [__idx_##n] = { .name = #n, .func = f }, +static struct selftest { + bool enabled; + const char *name; + int (*func)(void); +} selftests[] = { +#include "selftests.h" +}; +#undef selftest + +/* Embed the line number into the parameter name so that we can order tests */ +#define param(n) __PASTE(igt__, __PASTE(__PASTE(__LINE__, __), n)) +#define selftest_0(n, func, id) \ +module_param_named(id, selftests[__idx_##n].enabled, bool, 0400); +#define selftest(n, func) selftest_0(n, func, param(n)) +#include "selftests.h" +#undef selftest + +int __sanitycheck__(void) +{ + pr_debug("Hello World!\n"); + return 0; +} + +static char *__st_filter; + +static bool apply_subtest_filter(const char *caller, const char *name) +{ + char *filter, *sep, *tok; + bool result = true; + + filter = kstrdup(__st_filter, GFP_KERNEL); + for (sep = filter; (tok = strsep(&sep, ","));) { + bool allow = true; + char *sl; + + if (*tok == '!') { + allow = false; + tok++; + } + + if (*tok == '\0') + continue; + + sl = strchr(tok, '/'); + if (sl) { + *sl++ = '\0'; + if (strcmp(tok, caller)) { + if (allow) + result = false; + continue; + } + tok = sl; + } + + if (strcmp(tok, name)) { + if (allow) + result = false; + continue; + } + + result = allow; + break; + } + kfree(filter); + + return result; +} + +int +__subtests(const char *caller, const struct subtest *st, int count, void *data) +{ + int err; + + for (; count--; st++) { + cond_resched(); + if (signal_pending(current)) + return -EINTR; + + if (!apply_subtest_filter(caller, st->name)) + continue; + + pr_info("dma-buf: Running %s/%s\n", caller, st->name); + + err = st->func(data); + if (err && err != -EINTR) { + pr_err("dma-buf/%s: %s failed with error %d\n", + caller, st->name, err); + return err; + } + } + + return 0; +} + +static void set_default_test_all(struct selftest *st, unsigned long count) +{ + unsigned long i; + + for (i = 0; i < count; i++) + if (st[i].enabled) + return; + + for (i = 0; i < count; i++) + st[i].enabled = true; +} + +static int run_selftests(struct selftest *st, unsigned long count) +{ + int err = 0; + + set_default_test_all(st, count); + + /* Tests are listed in natural order in selftests.h */ + for (; count--; st++) { + if (!st->enabled) + continue; + + pr_info("dma-buf: Running %s\n", st->name); + err = st->func(); + if (err) + break; + } + + if (WARN(err > 0 || err == -ENOTTY, + "%s returned %d, conflicting with selftest's magic values!\n", + st->name, err)) + err = -1; + + return err; +} + +static int __init st_init(void) +{ + return run_selftests(selftests, ARRAY_SIZE(selftests)); +} + +static void __exit st_exit(void) +{ +} + +module_param_named(st_filter, __st_filter, charp, 0400); +module_init(st_init); +module_exit(st_exit); + +MODULE_DESCRIPTION("Self-test harness for dma-buf"); +MODULE_LICENSE("GPL and additional rights"); diff --git a/drivers/dma-buf/selftest.h b/drivers/dma-buf/selftest.h new file mode 100644 index 000000000000..45793aff6142 --- /dev/null +++ b/drivers/dma-buf/selftest.h @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: MIT + +/* + * Copyright © 2019 Intel Corporation + */ + +#ifndef __SELFTEST_H__ +#define __SELFTEST_H__ + +#include <linux/compiler.h> + +#define selftest(name, func) int func(void); +#include "selftests.h" +#undef selftest + +struct subtest { + int (*func)(void *data); + const char *name; +}; + +int __subtests(const char *caller, + const struct subtest *st, + int count, + void *data); +#define subtests(T, data) \ + __subtests(__func__, T, ARRAY_SIZE(T), data) + +#define SUBTEST(x) { x, #x } + +#endif /* __SELFTEST_H__ */ diff --git a/drivers/dma-buf/selftests.h b/drivers/dma-buf/selftests.h new file mode 100644 index 000000000000..5320386f02e5 --- /dev/null +++ b/drivers/dma-buf/selftests.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: MIT */ +/* List each unit test as selftest(name, function) + * + * The name is used as both an enum and expanded as subtest__name to create + * a module parameter. It must be unique and legal for a C identifier. + * + * The function should be of type int function(void). It may be conditionally + * compiled using #if IS_ENABLED(DRM_I915_SELFTEST). + * + * Tests are executed in order by igt/dmabuf_selftest + */ +selftest(sanitycheck, __sanitycheck__) /* keep first (igt selfcheck) */ +selftest(dma_fence, dma_fence) diff --git a/drivers/dma-buf/st-dma-fence.c b/drivers/dma-buf/st-dma-fence.c new file mode 100644 index 000000000000..e593064341c8 --- /dev/null +++ b/drivers/dma-buf/st-dma-fence.c @@ -0,0 +1,574 @@ +/* SPDX-License-Identifier: MIT */ + +/* + * Copyright © 2019 Intel Corporation + */ + +#include <linux/delay.h> +#include <linux/dma-fence.h> +#include <linux/kernel.h> +#include <linux/kthread.h> +#include <linux/sched/signal.h> +#include <linux/slab.h> +#include <linux/spinlock.h> + +#include "selftest.h" + +static struct kmem_cache *slab_fences; + +static struct mock_fence { + struct dma_fence base; + struct spinlock lock; +} *to_mock_fence(struct dma_fence *f) { + return container_of(f, struct mock_fence, base); +} + +static const char *mock_name(struct dma_fence *f) +{ + return "mock"; +} + +static void mock_fence_release(struct dma_fence *f) +{ + kmem_cache_free(slab_fences, to_mock_fence(f)); +} + +struct wait_cb { + struct dma_fence_cb cb; + struct task_struct *task; +}; + +static void mock_wakeup(struct dma_fence *f, struct dma_fence_cb *cb) +{ + wake_up_process(container_of(cb, struct wait_cb, cb)->task); +} + +static long mock_wait(struct dma_fence *f, bool intr, long timeout) +{ + const int state = intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE; + struct wait_cb cb = { .task = current }; + + if (dma_fence_add_callback(f, &cb.cb, mock_wakeup)) + return timeout; + + while (timeout) { + set_current_state(state); + + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &f->flags)) + break; + + if (signal_pending_state(state, current)) + break; + + timeout = schedule_timeout(timeout); + } + __set_current_state(TASK_RUNNING); + + if (!dma_fence_remove_callback(f, &cb.cb)) + return timeout; + + if (signal_pending_state(state, current)) + return -ERESTARTSYS; + + return -ETIME; +} + +static const struct dma_fence_ops mock_ops = { + .get_driver_name = mock_name, + .get_timeline_name = mock_name, + .wait = mock_wait, + .release = mock_fence_release, +}; + +static struct dma_fence *mock_fence(void) +{ + struct mock_fence *f; + + f = kmem_cache_alloc(slab_fences, GFP_KERNEL); + if (!f) + return NULL; + + spin_lock_init(&f->lock); + dma_fence_init(&f->base, &mock_ops, &f->lock, 0, 0); + + return &f->base; +} + +static int sanitycheck(void *arg) +{ + struct dma_fence *f; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + dma_fence_signal(f); + dma_fence_put(f); + + return 0; +} + +static int test_signaling(void *arg) +{ + struct dma_fence *f; + int err = -EINVAL; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + if (dma_fence_is_signaled(f)) { + pr_err("Fence unexpectedly signaled on creation\n"); + goto err_free; + } + + if (dma_fence_signal(f)) { + pr_err("Fence reported being already signaled\n"); + goto err_free; + } + + if (!dma_fence_is_signaled(f)) { + pr_err("Fence not reporting signaled\n"); + goto err_free; + } + + if (!dma_fence_signal(f)) { + pr_err("Fence reported not being already signaled\n"); + goto err_free; + } + + err = 0; +err_free: + dma_fence_put(f); + return err; +} + +struct simple_cb { + struct dma_fence_cb cb; + bool seen; +}; + +static void simple_callback(struct dma_fence *f, struct dma_fence_cb *cb) +{ + smp_store_mb(container_of(cb, struct simple_cb, cb)->seen, true); +} + +static int test_add_callback(void *arg) +{ + struct simple_cb cb = {}; + struct dma_fence *f; + int err = -EINVAL; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + if (dma_fence_add_callback(f, &cb.cb, simple_callback)) { + pr_err("Failed to add callback, fence already signaled!\n"); + goto err_free; + } + + dma_fence_signal(f); + if (!cb.seen) { + pr_err("Callback failed!\n"); + goto err_free; + } + + err = 0; +err_free: + dma_fence_put(f); + return err; +} + +static int test_late_add_callback(void *arg) +{ + struct simple_cb cb = {}; + struct dma_fence *f; + int err = -EINVAL; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + dma_fence_signal(f); + + if (!dma_fence_add_callback(f, &cb.cb, simple_callback)) { + pr_err("Added callback, but fence was already signaled!\n"); + goto err_free; + } + + dma_fence_signal(f); + if (cb.seen) { + pr_err("Callback called after failed attachment !\n"); + goto err_free; + } + + err = 0; +err_free: + dma_fence_put(f); + return err; +} + +static int test_rm_callback(void *arg) +{ + struct simple_cb cb = {}; + struct dma_fence *f; + int err = -EINVAL; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + if (dma_fence_add_callback(f, &cb.cb, simple_callback)) { + pr_err("Failed to add callback, fence already signaled!\n"); + goto err_free; + } + + if (!dma_fence_remove_callback(f, &cb.cb)) { + pr_err("Failed to remove callback!\n"); + goto err_free; + } + + dma_fence_signal(f); + if (cb.seen) { + pr_err("Callback still signaled after removal!\n"); + goto err_free; + } + + err = 0; +err_free: + dma_fence_put(f); + return err; +} + +static int test_late_rm_callback(void *arg) +{ + struct simple_cb cb = {}; + struct dma_fence *f; + int err = -EINVAL; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + if (dma_fence_add_callback(f, &cb.cb, simple_callback)) { + pr_err("Failed to add callback, fence already signaled!\n"); + goto err_free; + } + + dma_fence_signal(f); + if (!cb.seen) { + pr_err("Callback failed!\n"); + goto err_free; + } + + if (dma_fence_remove_callback(f, &cb.cb)) { + pr_err("Callback removal succeed after being executed!\n"); + goto err_free; + } + + err = 0; +err_free: + dma_fence_put(f); + return err; +} + +static int test_status(void *arg) +{ + struct dma_fence *f; + int err = -EINVAL; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + if (dma_fence_get_status(f)) { + pr_err("Fence unexpectedly has signaled status on creation\n"); + goto err_free; + } + + dma_fence_signal(f); + if (!dma_fence_get_status(f)) { + pr_err("Fence not reporting signaled status\n"); + goto err_free; + } + + err = 0; +err_free: + dma_fence_put(f); + return err; +} + +static int test_error(void *arg) +{ + struct dma_fence *f; + int err = -EINVAL; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + dma_fence_set_error(f, -EIO); + + if (dma_fence_get_status(f)) { + pr_err("Fence unexpectedly has error status before signal\n"); + goto err_free; + } + + dma_fence_signal(f); + if (dma_fence_get_status(f) != -EIO) { + pr_err("Fence not reporting error status, got %d\n", + dma_fence_get_status(f)); + goto err_free; + } + + err = 0; +err_free: + dma_fence_put(f); + return err; +} + +static int test_wait(void *arg) +{ + struct dma_fence *f; + int err = -EINVAL; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + if (dma_fence_wait_timeout(f, false, 0) != -ETIME) { + pr_err("Wait reported complete before being signaled\n"); + goto err_free; + } + + dma_fence_signal(f); + + if (dma_fence_wait_timeout(f, false, 0) != 0) { + pr_err("Wait reported incomplete after being signaled\n"); + goto err_free; + } + + err = 0; +err_free: + dma_fence_signal(f); + dma_fence_put(f); + return err; +} + +struct wait_timer { + struct timer_list timer; + struct dma_fence *f; +}; + +static void wait_timer(struct timer_list *timer) +{ + struct wait_timer *wt = from_timer(wt, timer, timer); + + dma_fence_signal(wt->f); +} + +static int test_wait_timeout(void *arg) +{ + struct wait_timer wt; + int err = -EINVAL; + + timer_setup_on_stack(&wt.timer, wait_timer, 0); + + wt.f = mock_fence(); + if (!wt.f) + return -ENOMEM; + + if (dma_fence_wait_timeout(wt.f, false, 1) != -ETIME) { + pr_err("Wait reported complete before being signaled\n"); + goto err_free; + } + + mod_timer(&wt.timer, jiffies + 1); + + if (dma_fence_wait_timeout(wt.f, false, 2) == -ETIME) { + if (timer_pending(&wt.timer)) { + pr_notice("Timer did not fire within the jiffie!\n"); + err = 0; /* not our fault! */ + } else { + pr_err("Wait reported incomplete after timeout\n"); + } + goto err_free; + } + + err = 0; +err_free: + del_timer_sync(&wt.timer); + destroy_timer_on_stack(&wt.timer); + dma_fence_signal(wt.f); + dma_fence_put(wt.f); + return err; +} + +static int test_stub(void *arg) +{ + struct dma_fence *f[64]; + int err = -EINVAL; + int i; + + for (i = 0; i < ARRAY_SIZE(f); i++) { + f[i] = dma_fence_get_stub(); + if (!dma_fence_is_signaled(f[i])) { + pr_err("Obtained unsignaled stub fence!\n"); + goto err; + } + } + + err = 0; +err: + while (i--) + dma_fence_put(f[i]); + return err; +} + +/* Now off to the races! */ + +struct race_thread { + struct dma_fence __rcu **fences; + struct task_struct *task; + bool before; + int id; +}; + +static void __wait_for_callbacks(struct dma_fence *f) +{ + spin_lock_irq(f->lock); + spin_unlock_irq(f->lock); +} + +static int thread_signal_callback(void *arg) +{ + const struct race_thread *t = arg; + unsigned long pass = 0; + unsigned long miss = 0; + int err = 0; + + while (!err && !kthread_should_stop()) { + struct dma_fence *f1, *f2; + struct simple_cb cb; + + f1 = mock_fence(); + if (!f1) { + err = -ENOMEM; + break; + } + + rcu_assign_pointer(t->fences[t->id], f1); + smp_wmb(); + + rcu_read_lock(); + do { + f2 = dma_fence_get_rcu_safe(&t->fences[!t->id]); + } while (!f2 && !kthread_should_stop()); + rcu_read_unlock(); + + if (t->before) + dma_fence_signal(f1); + + smp_store_mb(cb.seen, false); + if (!f2 || dma_fence_add_callback(f2, &cb.cb, simple_callback)) + miss++, cb.seen = true; + + if (!t->before) + dma_fence_signal(f1); + + if (!cb.seen) { + dma_fence_wait(f2, false); + __wait_for_callbacks(f2); + } + + if (!READ_ONCE(cb.seen)) { + pr_err("Callback not seen on thread %d, pass %lu (%lu misses), signaling %s add_callback; fence signaled? %s\n", + t->id, pass, miss, + t->before ? "before" : "after", + dma_fence_is_signaled(f2) ? "yes" : "no"); + err = -EINVAL; + } + + dma_fence_put(f2); + + rcu_assign_pointer(t->fences[t->id], NULL); + smp_wmb(); + + dma_fence_put(f1); + + pass++; + } + + pr_info("%s[%d] completed %lu passes, %lu misses\n", + __func__, t->id, pass, miss); + return err; +} + +static int race_signal_callback(void *arg) +{ + struct dma_fence __rcu *f[2] = {}; + int ret = 0; + int pass; + + for (pass = 0; !ret && pass <= 1; pass++) { + struct race_thread t[2]; + int i; + + for (i = 0; i < ARRAY_SIZE(t); i++) { + t[i].fences = f; + t[i].id = i; + t[i].before = pass; + t[i].task = kthread_run(thread_signal_callback, &t[i], + "dma-fence:%d", i); + get_task_struct(t[i].task); + } + + msleep(50); + + for (i = 0; i < ARRAY_SIZE(t); i++) { + int err; + + err = kthread_stop(t[i].task); + if (err && !ret) + ret = err; + + put_task_struct(t[i].task); + } + } + + return ret; +} + +int dma_fence(void) +{ + static const struct subtest tests[] = { + SUBTEST(sanitycheck), + SUBTEST(test_signaling), + SUBTEST(test_add_callback), + SUBTEST(test_late_add_callback), + SUBTEST(test_rm_callback), + SUBTEST(test_late_rm_callback), + SUBTEST(test_status), + SUBTEST(test_error), + SUBTEST(test_wait), + SUBTEST(test_wait_timeout), + SUBTEST(test_stub), + SUBTEST(race_signal_callback), + }; + int ret; + + pr_info("sizeof(dma_fence)=%zu\n", sizeof(struct dma_fence)); + + slab_fences = KMEM_CACHE(mock_fence, + SLAB_TYPESAFE_BY_RCU | + SLAB_HWCACHE_ALIGN); + if (!slab_fences) + return -ENOMEM; + + ret = subtests(tests, NULL); + + kmem_cache_destroy(slab_fences); + + return ret; +} diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c index 051f6c2873c7..348b3a9170fa 100644 --- a/drivers/dma-buf/sw_sync.c +++ b/drivers/dma-buf/sw_sync.c @@ -132,17 +132,14 @@ 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)) { - 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); + 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); @@ -265,7 +262,8 @@ static struct sync_pt *sync_pt_create(struct sync_timeline *obj, p = &parent->rb_left; } else { if (dma_fence_get_rcu(&other->base)) { - dma_fence_put(&pt->base); + sync_timeline_put(obj); + kfree(pt); pt = other; goto unlock; } @@ -410,5 +408,5 @@ 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, + .compat_ioctl = compat_ptr_ioctl, }; diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index ee4d1a96d779..5a5a1da01a00 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -221,7 +221,7 @@ static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, 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) - return NULL; + goto err; num_fences = a_num_fences + b_num_fences; @@ -419,7 +419,7 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, * info->num_fences. */ if (!info.num_fences) { - info.status = dma_fence_is_signaled(sync_file->fence); + info.status = dma_fence_get_status(sync_file->fence); goto no_fences; } else { info.status = 1; @@ -480,5 +480,5 @@ 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, + .compat_ioctl = compat_ptr_ioctl, }; diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index 9635897458a0..acb26c627d27 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -18,6 +18,8 @@ static const size_t size_limit_mb = 64; /* total dmabuf size, in megabytes */ struct udmabuf { pgoff_t pagecount; struct page **pages; + struct sg_table *sg; + struct miscdevice *device; }; static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf) @@ -46,10 +48,10 @@ static int mmap_udmabuf(struct dma_buf *buf, struct vm_area_struct *vma) return 0; } -static struct sg_table *map_udmabuf(struct dma_buf_attachment *at, - enum dma_data_direction direction) +static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf, + enum dma_data_direction direction) { - struct udmabuf *ubuf = at->dmabuf->priv; + struct udmabuf *ubuf = buf->priv; struct sg_table *sg; int ret; @@ -61,7 +63,7 @@ static struct sg_table *map_udmabuf(struct dma_buf_attachment *at, GFP_KERNEL); if (ret < 0) goto err; - if (!dma_map_sg(at->dev, sg->sgl, sg->nents, direction)) { + if (!dma_map_sg(dev, sg->sgl, sg->nents, direction)) { ret = -EINVAL; goto err; } @@ -73,54 +75,89 @@ err: return ERR_PTR(ret); } +static void put_sg_table(struct device *dev, struct sg_table *sg, + enum dma_data_direction direction) +{ + dma_unmap_sg(dev, sg->sgl, sg->nents, direction); + sg_free_table(sg); + kfree(sg); +} + +static struct sg_table *map_udmabuf(struct dma_buf_attachment *at, + enum dma_data_direction direction) +{ + return get_sg_table(at->dev, at->dmabuf, direction); +} + static void unmap_udmabuf(struct dma_buf_attachment *at, struct sg_table *sg, enum dma_data_direction direction) { - dma_unmap_sg(at->dev, sg->sgl, sg->nents, direction); - sg_free_table(sg); - kfree(sg); + return put_sg_table(at->dev, sg, direction); } static void release_udmabuf(struct dma_buf *buf) { struct udmabuf *ubuf = buf->priv; + struct device *dev = ubuf->device->this_device; pgoff_t pg; + if (ubuf->sg) + put_sg_table(dev, ubuf->sg, DMA_BIDIRECTIONAL); + for (pg = 0; pg < ubuf->pagecount; pg++) put_page(ubuf->pages[pg]); kfree(ubuf->pages); kfree(ubuf); } -static void *kmap_udmabuf(struct dma_buf *buf, unsigned long page_num) +static int begin_cpu_udmabuf(struct dma_buf *buf, + enum dma_data_direction direction) { struct udmabuf *ubuf = buf->priv; - struct page *page = ubuf->pages[page_num]; + struct device *dev = ubuf->device->this_device; + + if (!ubuf->sg) { + ubuf->sg = get_sg_table(dev, buf, direction); + if (IS_ERR(ubuf->sg)) + return PTR_ERR(ubuf->sg); + } else { + dma_sync_sg_for_cpu(dev, ubuf->sg->sgl, ubuf->sg->nents, + direction); + } - return kmap(page); + return 0; } -static void kunmap_udmabuf(struct dma_buf *buf, unsigned long page_num, - void *vaddr) +static int end_cpu_udmabuf(struct dma_buf *buf, + enum dma_data_direction direction) { - kunmap(vaddr); + struct udmabuf *ubuf = buf->priv; + struct device *dev = ubuf->device->this_device; + + if (!ubuf->sg) + return -EINVAL; + + dma_sync_sg_for_device(dev, ubuf->sg->sgl, ubuf->sg->nents, direction); + return 0; } static const struct dma_buf_ops udmabuf_ops = { - .map_dma_buf = map_udmabuf, - .unmap_dma_buf = unmap_udmabuf, - .release = release_udmabuf, - .map = kmap_udmabuf, - .unmap = kunmap_udmabuf, - .mmap = mmap_udmabuf, + .cache_sgt_mapping = true, + .map_dma_buf = map_udmabuf, + .unmap_dma_buf = unmap_udmabuf, + .release = release_udmabuf, + .mmap = mmap_udmabuf, + .begin_cpu_access = begin_cpu_udmabuf, + .end_cpu_access = end_cpu_udmabuf, }; #define SEALS_WANTED (F_SEAL_SHRINK) #define SEALS_DENIED (F_SEAL_WRITE) -static long udmabuf_create(const struct udmabuf_create_list *head, - const struct udmabuf_create_item *list) +static long udmabuf_create(struct miscdevice *device, + struct udmabuf_create_list *head, + struct udmabuf_create_item *list) { DEFINE_DMA_BUF_EXPORT_INFO(exp_info); struct file *memfd = NULL; @@ -187,6 +224,7 @@ static long udmabuf_create(const struct udmabuf_create_list *head, exp_info.priv = ubuf; exp_info.flags = O_RDWR; + ubuf->device = device; buf = dma_buf_export(&exp_info); if (IS_ERR(buf)) { ret = PTR_ERR(buf); @@ -224,7 +262,7 @@ static long udmabuf_ioctl_create(struct file *filp, unsigned long arg) list.offset = create.offset; list.size = create.size; - return udmabuf_create(&head, &list); + return udmabuf_create(filp->private_data, &head, &list); } static long udmabuf_ioctl_create_list(struct file *filp, unsigned long arg) @@ -243,7 +281,7 @@ static long udmabuf_ioctl_create_list(struct file *filp, unsigned long arg) if (IS_ERR(list)) return PTR_ERR(list); - ret = udmabuf_create(&head, list); + ret = udmabuf_create(filp->private_data, &head, list); kfree(list); return ret; } |