diff options
Diffstat (limited to 'drivers/dma-buf')
31 files changed, 7870 insertions, 1633 deletions
diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig index 2e5a0faa2cb1..b46eb8a552d7 100644 --- a/drivers/dma-buf/Kconfig +++ b/drivers/dma-buf/Kconfig @@ -1,12 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0-only 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 + help + The Sync File Framework adds explicit synchronization via userspace. It enables send/receive 'struct dma_fence' objects to/from userspace via Sync File fds for synchronization between drivers via userspace components. It has been ported from Android. @@ -15,14 +15,14 @@ config SYNC_FILE 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. + Documentation/driver-api/sync_file.rst. config SW_SYNC bool "Sync File Validation Framework" default n depends on SYNC_FILE depends on DEBUG_FS - ---help--- + help A sync object driver that uses a 32bit counter to coordinate synchronization. Useful when there is no hardware primitive backing the synchronization. @@ -35,8 +35,61 @@ config UDMABUF default n depends on DMA_SHARED_BUFFER depends on MEMFD_CREATE || COMPILE_TEST + depends on MMU help A driver to let userspace turn memfd regions into dma-bufs. Qemu can use this to create host dmabufs for guest framebuffers. +config DMABUF_MOVE_NOTIFY + bool "Move notify between drivers (EXPERIMENTAL)" + default n + depends on DMA_SHARED_BUFFER + help + Don't pin buffers if the dynamic DMA-buf interface is available on + both the exporter as well as the importer. This fixes a security + problem where userspace is able to pin unrestricted amounts of memory + through DMA-buf. + This is marked experimental because we don't yet have a consistent + execution context and memory management between drivers. + +config DMABUF_DEBUG + bool "DMA-BUF debug checks" + depends on DMA_SHARED_BUFFER + default y if DMA_API_DEBUG + help + This option enables additional checks for DMA-BUF importers and + exporters. Specifically it validates that importers do not peek at the + underlying struct page when they import a buffer. + +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. + +menuconfig DMABUF_SYSFS_STATS + bool "DMA-BUF sysfs statistics (DEPRECATED)" + depends on DMA_SHARED_BUFFER + help + Choose this option to enable DMA-BUF sysfs statistics + in location /sys/kernel/dmabuf/buffers. + + /sys/kernel/dmabuf/buffers/<inode_number> will contain + statistics for the DMA-BUF with the unique inode number + <inode_number>. + + This option is deprecated and should sooner or later be removed. + Android is the only user of this and it turned out that this resulted + in quite some performance problems. + +source "drivers/dma-buf/heaps/Kconfig" + endmenu diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile index 0913a6ccab5a..2008fb7481b3 100644 --- a/drivers/dma-buf/Makefile +++ b/drivers/dma-buf/Makefile @@ -1,4 +1,18 @@ -obj-y := dma-buf.o dma-fence.o dma-fence-array.o reservation.o seqno-fence.o +# SPDX-License-Identifier: GPL-2.0-only +obj-y := dma-buf.o dma-fence.o dma-fence-array.o dma-fence-chain.o \ + dma-fence-unwrap.o dma-resv.o dma-buf-mapping.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-$(CONFIG_UDMABUF) += udmabuf.o +obj-$(CONFIG_DMABUF_SYSFS_STATS) += dma-buf-sysfs-stats.o + +dmabuf_selftests-y := \ + selftest.o \ + st-dma-fence.o \ + st-dma-fence-chain.o \ + st-dma-fence-unwrap.o \ + st-dma-resv.o + +obj-$(CONFIG_DMABUF_SELFTESTS) += dmabuf_selftests.o diff --git a/drivers/dma-buf/dma-buf-mapping.c b/drivers/dma-buf/dma-buf-mapping.c new file mode 100644 index 000000000000..b7352e609fbd --- /dev/null +++ b/drivers/dma-buf/dma-buf-mapping.c @@ -0,0 +1,248 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * DMA BUF Mapping Helpers + * + */ +#include <linux/dma-buf-mapping.h> +#include <linux/dma-resv.h> + +static struct scatterlist *fill_sg_entry(struct scatterlist *sgl, size_t length, + dma_addr_t addr) +{ + unsigned int len, nents; + int i; + + nents = DIV_ROUND_UP(length, UINT_MAX); + for (i = 0; i < nents; i++) { + len = min_t(size_t, length, UINT_MAX); + length -= len; + /* + * DMABUF abuses scatterlist to create a scatterlist + * that does not have any CPU list, only the DMA list. + * Always set the page related values to NULL to ensure + * importers can't use it. The phys_addr based DMA API + * does not require the CPU list for mapping or unmapping. + */ + sg_set_page(sgl, NULL, 0, 0); + sg_dma_address(sgl) = addr + (dma_addr_t)i * UINT_MAX; + sg_dma_len(sgl) = len; + sgl = sg_next(sgl); + } + + return sgl; +} + +static unsigned int calc_sg_nents(struct dma_iova_state *state, + struct dma_buf_phys_vec *phys_vec, + size_t nr_ranges, size_t size) +{ + unsigned int nents = 0; + size_t i; + + if (!state || !dma_use_iova(state)) { + for (i = 0; i < nr_ranges; i++) + nents += DIV_ROUND_UP(phys_vec[i].len, UINT_MAX); + } else { + /* + * In IOVA case, there is only one SG entry which spans + * for whole IOVA address space, but we need to make sure + * that it fits sg->length, maybe we need more. + */ + nents = DIV_ROUND_UP(size, UINT_MAX); + } + + return nents; +} + +/** + * struct dma_buf_dma - holds DMA mapping information + * @sgt: Scatter-gather table + * @state: DMA IOVA state relevant in IOMMU-based DMA + * @size: Total size of DMA transfer + */ +struct dma_buf_dma { + struct sg_table sgt; + struct dma_iova_state *state; + size_t size; +}; + +/** + * dma_buf_phys_vec_to_sgt - Returns the scatterlist table of the attachment + * from arrays of physical vectors. This funciton is intended for MMIO memory + * only. + * @attach: [in] attachment whose scatterlist is to be returned + * @provider: [in] p2pdma provider + * @phys_vec: [in] array of physical vectors + * @nr_ranges: [in] number of entries in phys_vec array + * @size: [in] total size of phys_vec + * @dir: [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. + * + * On success, the DMA addresses and lengths in the returned scatterlist are + * PAGE_SIZE aligned. + * + * A mapping must be unmapped by using dma_buf_free_sgt(). + * + * NOTE: This function is intended for exporters. If direct traffic routing is + * mandatory exporter should call routing pci_p2pdma_map_type() before calling + * this function. + */ +struct sg_table *dma_buf_phys_vec_to_sgt(struct dma_buf_attachment *attach, + struct p2pdma_provider *provider, + struct dma_buf_phys_vec *phys_vec, + size_t nr_ranges, size_t size, + enum dma_data_direction dir) +{ + unsigned int nents, mapped_len = 0; + struct dma_buf_dma *dma; + struct scatterlist *sgl; + dma_addr_t addr; + size_t i; + int ret; + + dma_resv_assert_held(attach->dmabuf->resv); + + if (WARN_ON(!attach || !attach->dmabuf || !provider)) + /* This function is supposed to work on MMIO memory only */ + return ERR_PTR(-EINVAL); + + dma = kzalloc(sizeof(*dma), GFP_KERNEL); + if (!dma) + return ERR_PTR(-ENOMEM); + + switch (pci_p2pdma_map_type(provider, attach->dev)) { + case PCI_P2PDMA_MAP_BUS_ADDR: + /* + * There is no need in IOVA at all for this flow. + */ + break; + case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE: + dma->state = kzalloc(sizeof(*dma->state), GFP_KERNEL); + if (!dma->state) { + ret = -ENOMEM; + goto err_free_dma; + } + + dma_iova_try_alloc(attach->dev, dma->state, 0, size); + break; + default: + ret = -EINVAL; + goto err_free_dma; + } + + nents = calc_sg_nents(dma->state, phys_vec, nr_ranges, size); + ret = sg_alloc_table(&dma->sgt, nents, GFP_KERNEL | __GFP_ZERO); + if (ret) + goto err_free_state; + + sgl = dma->sgt.sgl; + + for (i = 0; i < nr_ranges; i++) { + if (!dma->state) { + addr = pci_p2pdma_bus_addr_map(provider, + phys_vec[i].paddr); + } else if (dma_use_iova(dma->state)) { + ret = dma_iova_link(attach->dev, dma->state, + phys_vec[i].paddr, 0, + phys_vec[i].len, dir, + DMA_ATTR_MMIO); + if (ret) + goto err_unmap_dma; + + mapped_len += phys_vec[i].len; + } else { + addr = dma_map_phys(attach->dev, phys_vec[i].paddr, + phys_vec[i].len, dir, + DMA_ATTR_MMIO); + ret = dma_mapping_error(attach->dev, addr); + if (ret) + goto err_unmap_dma; + } + + if (!dma->state || !dma_use_iova(dma->state)) + sgl = fill_sg_entry(sgl, phys_vec[i].len, addr); + } + + if (dma->state && dma_use_iova(dma->state)) { + WARN_ON_ONCE(mapped_len != size); + ret = dma_iova_sync(attach->dev, dma->state, 0, mapped_len); + if (ret) + goto err_unmap_dma; + + sgl = fill_sg_entry(sgl, mapped_len, dma->state->addr); + } + + dma->size = size; + + /* + * No CPU list included — set orig_nents = 0 so others can detect + * this via SG table (use nents only). + */ + dma->sgt.orig_nents = 0; + + + /* + * SGL must be NULL to indicate that SGL is the last one + * and we allocated correct number of entries in sg_alloc_table() + */ + WARN_ON_ONCE(sgl); + return &dma->sgt; + +err_unmap_dma: + if (!i || !dma->state) { + ; /* Do nothing */ + } else if (dma_use_iova(dma->state)) { + dma_iova_destroy(attach->dev, dma->state, mapped_len, dir, + DMA_ATTR_MMIO); + } else { + for_each_sgtable_dma_sg(&dma->sgt, sgl, i) + dma_unmap_phys(attach->dev, sg_dma_address(sgl), + sg_dma_len(sgl), dir, DMA_ATTR_MMIO); + } + sg_free_table(&dma->sgt); +err_free_state: + kfree(dma->state); +err_free_dma: + kfree(dma); + return ERR_PTR(ret); +} +EXPORT_SYMBOL_NS_GPL(dma_buf_phys_vec_to_sgt, "DMA_BUF"); + +/** + * dma_buf_free_sgt- unmaps the buffer + * @attach: [in] attachment to unmap buffer from + * @sgt: [in] scatterlist info of the buffer to unmap + * @dir: [in] direction of DMA transfer + * + * This unmaps a DMA mapping for @attached obtained + * by dma_buf_phys_vec_to_sgt(). + */ +void dma_buf_free_sgt(struct dma_buf_attachment *attach, struct sg_table *sgt, + enum dma_data_direction dir) +{ + struct dma_buf_dma *dma = container_of(sgt, struct dma_buf_dma, sgt); + int i; + + dma_resv_assert_held(attach->dmabuf->resv); + + if (!dma->state) { + ; /* Do nothing */ + } else if (dma_use_iova(dma->state)) { + dma_iova_destroy(attach->dev, dma->state, dma->size, dir, + DMA_ATTR_MMIO); + } else { + struct scatterlist *sgl; + + for_each_sgtable_dma_sg(sgt, sgl, i) + dma_unmap_phys(attach->dev, sg_dma_address(sgl), + sg_dma_len(sgl), dir, DMA_ATTR_MMIO); + } + + sg_free_table(sgt); + kfree(dma->state); + kfree(dma); + +} +EXPORT_SYMBOL_NS_GPL(dma_buf_free_sgt, "DMA_BUF"); diff --git a/drivers/dma-buf/dma-buf-sysfs-stats.c b/drivers/dma-buf/dma-buf-sysfs-stats.c new file mode 100644 index 000000000000..b5b62e40ccc1 --- /dev/null +++ b/drivers/dma-buf/dma-buf-sysfs-stats.c @@ -0,0 +1,202 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * DMA-BUF sysfs statistics. + * + * Copyright (C) 2021 Google LLC. + */ + +#include <linux/dma-buf.h> +#include <linux/dma-resv.h> +#include <linux/kobject.h> +#include <linux/printk.h> +#include <linux/slab.h> +#include <linux/sysfs.h> + +#include "dma-buf-sysfs-stats.h" + +#define to_dma_buf_entry_from_kobj(x) container_of(x, struct dma_buf_sysfs_entry, kobj) + +/** + * DOC: overview + * + * ``/sys/kernel/debug/dma_buf/bufinfo`` provides an overview of every DMA-BUF + * in the system. However, since debugfs is not safe to be mounted in + * production, procfs and sysfs can be used to gather DMA-BUF statistics on + * production systems. + * + * The ``/proc/<pid>/fdinfo/<fd>`` files in procfs can be used to gather + * information about DMA-BUF fds. Detailed documentation about the interface + * is present in Documentation/filesystems/proc.rst. + * + * Unfortunately, the existing procfs interfaces can only provide information + * about the DMA-BUFs for which processes hold fds or have the buffers mmapped + * into their address space. This necessitated the creation of the DMA-BUF sysfs + * statistics interface to provide per-buffer information on production systems. + * + * The interface at ``/sys/kernel/dmabuf/buffers`` exposes information about + * every DMA-BUF when ``CONFIG_DMABUF_SYSFS_STATS`` is enabled. + * + * The following stats are exposed by the interface: + * + * * ``/sys/kernel/dmabuf/buffers/<inode_number>/exporter_name`` + * * ``/sys/kernel/dmabuf/buffers/<inode_number>/size`` + * + * The information in the interface can also be used to derive per-exporter + * statistics. The data from the interface can be gathered on error conditions + * or other important events to provide a snapshot of DMA-BUF usage. + * It can also be collected periodically by telemetry to monitor various metrics. + * + * Detailed documentation about the interface is present in + * Documentation/ABI/testing/sysfs-kernel-dmabuf-buffers. + */ + +struct dma_buf_stats_attribute { + struct attribute attr; + ssize_t (*show)(struct dma_buf *dmabuf, + struct dma_buf_stats_attribute *attr, char *buf); +}; +#define to_dma_buf_stats_attr(x) container_of(x, struct dma_buf_stats_attribute, attr) + +static ssize_t dma_buf_stats_attribute_show(struct kobject *kobj, + struct attribute *attr, + char *buf) +{ + struct dma_buf_stats_attribute *attribute; + struct dma_buf_sysfs_entry *sysfs_entry; + struct dma_buf *dmabuf; + + attribute = to_dma_buf_stats_attr(attr); + sysfs_entry = to_dma_buf_entry_from_kobj(kobj); + dmabuf = sysfs_entry->dmabuf; + + if (!dmabuf || !attribute->show) + return -EIO; + + return attribute->show(dmabuf, attribute, buf); +} + +static const struct sysfs_ops dma_buf_stats_sysfs_ops = { + .show = dma_buf_stats_attribute_show, +}; + +static ssize_t exporter_name_show(struct dma_buf *dmabuf, + struct dma_buf_stats_attribute *attr, + char *buf) +{ + return sysfs_emit(buf, "%s\n", dmabuf->exp_name); +} + +static ssize_t size_show(struct dma_buf *dmabuf, + struct dma_buf_stats_attribute *attr, + char *buf) +{ + return sysfs_emit(buf, "%zu\n", dmabuf->size); +} + +static struct dma_buf_stats_attribute exporter_name_attribute = + __ATTR_RO(exporter_name); +static struct dma_buf_stats_attribute size_attribute = __ATTR_RO(size); + +static struct attribute *dma_buf_stats_default_attrs[] = { + &exporter_name_attribute.attr, + &size_attribute.attr, + NULL, +}; +ATTRIBUTE_GROUPS(dma_buf_stats_default); + +static void dma_buf_sysfs_release(struct kobject *kobj) +{ + struct dma_buf_sysfs_entry *sysfs_entry; + + sysfs_entry = to_dma_buf_entry_from_kobj(kobj); + kfree(sysfs_entry); +} + +static const struct kobj_type dma_buf_ktype = { + .sysfs_ops = &dma_buf_stats_sysfs_ops, + .release = dma_buf_sysfs_release, + .default_groups = dma_buf_stats_default_groups, +}; + +void dma_buf_stats_teardown(struct dma_buf *dmabuf) +{ + struct dma_buf_sysfs_entry *sysfs_entry; + + sysfs_entry = dmabuf->sysfs_entry; + if (!sysfs_entry) + return; + + kobject_del(&sysfs_entry->kobj); + kobject_put(&sysfs_entry->kobj); +} + + +/* Statistics files do not need to send uevents. */ +static int dmabuf_sysfs_uevent_filter(const struct kobject *kobj) +{ + return 0; +} + +static const struct kset_uevent_ops dmabuf_sysfs_no_uevent_ops = { + .filter = dmabuf_sysfs_uevent_filter, +}; + +static struct kset *dma_buf_stats_kset; +static struct kset *dma_buf_per_buffer_stats_kset; +int dma_buf_init_sysfs_statistics(void) +{ + dma_buf_stats_kset = kset_create_and_add("dmabuf", + &dmabuf_sysfs_no_uevent_ops, + kernel_kobj); + if (!dma_buf_stats_kset) + return -ENOMEM; + + dma_buf_per_buffer_stats_kset = kset_create_and_add("buffers", + &dmabuf_sysfs_no_uevent_ops, + &dma_buf_stats_kset->kobj); + if (!dma_buf_per_buffer_stats_kset) { + kset_unregister(dma_buf_stats_kset); + return -ENOMEM; + } + + return 0; +} + +void dma_buf_uninit_sysfs_statistics(void) +{ + kset_unregister(dma_buf_per_buffer_stats_kset); + kset_unregister(dma_buf_stats_kset); +} + +int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file) +{ + struct dma_buf_sysfs_entry *sysfs_entry; + int ret; + + if (!dmabuf->exp_name) { + pr_err("exporter name must not be empty if stats needed\n"); + return -EINVAL; + } + + sysfs_entry = kzalloc(sizeof(struct dma_buf_sysfs_entry), GFP_KERNEL); + if (!sysfs_entry) + return -ENOMEM; + + sysfs_entry->kobj.kset = dma_buf_per_buffer_stats_kset; + sysfs_entry->dmabuf = dmabuf; + + dmabuf->sysfs_entry = sysfs_entry; + + /* create the directory for buffer stats */ + ret = kobject_init_and_add(&sysfs_entry->kobj, &dma_buf_ktype, NULL, + "%lu", file_inode(file)->i_ino); + if (ret) + goto err_sysfs_dmabuf; + + return 0; + +err_sysfs_dmabuf: + kobject_put(&sysfs_entry->kobj); + dmabuf->sysfs_entry = NULL; + return ret; +} diff --git a/drivers/dma-buf/dma-buf-sysfs-stats.h b/drivers/dma-buf/dma-buf-sysfs-stats.h new file mode 100644 index 000000000000..7a8a995b75ba --- /dev/null +++ b/drivers/dma-buf/dma-buf-sysfs-stats.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * DMA-BUF sysfs statistics. + * + * Copyright (C) 2021 Google LLC. + */ + +#ifndef _DMA_BUF_SYSFS_STATS_H +#define _DMA_BUF_SYSFS_STATS_H + +#ifdef CONFIG_DMABUF_SYSFS_STATS + +int dma_buf_init_sysfs_statistics(void); +void dma_buf_uninit_sysfs_statistics(void); + +int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file); + +void dma_buf_stats_teardown(struct dma_buf *dmabuf); +#else + +static inline int dma_buf_init_sysfs_statistics(void) +{ + return 0; +} + +static inline void dma_buf_uninit_sysfs_statistics(void) {} + +static inline int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file) +{ + return 0; +} + +static inline void dma_buf_stats_teardown(struct dma_buf *dmabuf) {} +#endif +#endif // _DMA_BUF_SYSFS_STATS_H diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 02f7f9a89979..edaa9e4ee4ae 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Framework for buffer objects that can be shared across devices/subsystems. * @@ -8,79 +9,199 @@ * 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/dma-fence-unwrap.h> #include <linux/anon_inodes.h> #include <linux/export.h> #include <linux/debugfs.h> +#include <linux/list.h> #include <linux/module.h> +#include <linux/mutex.h> #include <linux/seq_file.h> +#include <linux/sync_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> #include <uapi/linux/dma-buf.h> +#include <uapi/linux/magic.h> + +#include "dma-buf-sysfs-stats.h" static inline int is_dma_buf_file(struct file *); -struct dma_buf_list { - struct list_head head; - struct mutex lock; -}; +static DEFINE_MUTEX(dmabuf_list_mutex); +static LIST_HEAD(dmabuf_list); + +static void __dma_buf_list_add(struct dma_buf *dmabuf) +{ + mutex_lock(&dmabuf_list_mutex); + list_add(&dmabuf->list_node, &dmabuf_list); + mutex_unlock(&dmabuf_list_mutex); +} -static struct dma_buf_list db_list; +static void __dma_buf_list_del(struct dma_buf *dmabuf) +{ + if (!dmabuf) + return; -static int dma_buf_release(struct inode *inode, struct file *file) + mutex_lock(&dmabuf_list_mutex); + list_del(&dmabuf->list_node); + mutex_unlock(&dmabuf_list_mutex); +} + +/** + * dma_buf_iter_begin - begin iteration through global list of all DMA buffers + * + * Returns the first buffer in the global list of DMA-bufs that's not in the + * process of being destroyed. Increments that buffer's reference count to + * prevent buffer destruction. Callers must release the reference, either by + * continuing iteration with dma_buf_iter_next(), or with dma_buf_put(). + * + * Return: + * * First buffer from global list, with refcount elevated + * * NULL if no active buffers are present + */ +struct dma_buf *dma_buf_iter_begin(void) +{ + struct dma_buf *ret = NULL, *dmabuf; + + /* + * The list mutex does not protect a dmabuf's refcount, so it can be + * zeroed while we are iterating. We cannot call get_dma_buf() since the + * caller may not already own a reference to the buffer. + */ + mutex_lock(&dmabuf_list_mutex); + list_for_each_entry(dmabuf, &dmabuf_list, list_node) { + if (file_ref_get(&dmabuf->file->f_ref)) { + ret = dmabuf; + break; + } + } + mutex_unlock(&dmabuf_list_mutex); + return ret; +} + +/** + * dma_buf_iter_next - continue iteration through global list of all DMA buffers + * @dmabuf: [in] pointer to dma_buf + * + * Decrements the reference count on the provided buffer. Returns the next + * buffer from the remainder of the global list of DMA-bufs with its reference + * count incremented. Callers must release the reference, either by continuing + * iteration with dma_buf_iter_next(), or with dma_buf_put(). + * + * Return: + * * Next buffer from global list, with refcount elevated + * * NULL if no additional active buffers are present + */ +struct dma_buf *dma_buf_iter_next(struct dma_buf *dmabuf) +{ + struct dma_buf *ret = NULL; + + /* + * The list mutex does not protect a dmabuf's refcount, so it can be + * zeroed while we are iterating. We cannot call get_dma_buf() since the + * caller may not already own a reference to the buffer. + */ + mutex_lock(&dmabuf_list_mutex); + dma_buf_put(dmabuf); + list_for_each_entry_continue(dmabuf, &dmabuf_list, list_node) { + if (file_ref_get(&dmabuf->file->f_ref)) { + ret = dmabuf; + break; + } + } + mutex_unlock(&dmabuf_list_mutex); + return ret; +} + +static char *dmabuffs_dname(struct dentry *dentry, char *buffer, int buflen) { struct dma_buf *dmabuf; + char name[DMA_BUF_NAME_LEN]; + ssize_t ret = 0; - if (!is_dma_buf_file(file)) - return -EINVAL; + dmabuf = dentry->d_fsdata; + spin_lock(&dmabuf->name_lock); + if (dmabuf->name) + ret = strscpy(name, dmabuf->name, sizeof(name)); + spin_unlock(&dmabuf->name_lock); - dmabuf = file->private_data; + return dynamic_dname(buffer, buflen, "/%s:%s", + dentry->d_name.name, ret > 0 ? name : ""); +} + +static void dma_buf_release(struct dentry *dentry) +{ + struct dma_buf *dmabuf; + + dmabuf = dentry->d_fsdata; + if (unlikely(!dmabuf)) + return; BUG_ON(dmabuf->vmapping_counter); /* - * Any fences that a dma-buf poll can wait on should be signaled - * before releasing dma-buf. This is the responsibility of each - * driver that uses the reservation objects. - * - * If you hit this BUG() it means someone dropped their ref to the - * dma-buf while still having pending operation to the buffer. + * If you hit this BUG() it could mean: + * * There's a file reference imbalance in dma_buf_poll / dma_buf_poll_cb or somewhere else + * * dmabuf->cb_in/out.active are non-0 despite no pending fence callback */ - BUG_ON(dmabuf->cb_shared.active || dmabuf->cb_excl.active); + BUG_ON(dmabuf->cb_in.active || dmabuf->cb_out.active); + dma_buf_stats_teardown(dmabuf); 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); + if (dmabuf->resv == (struct dma_resv *)&dmabuf[1]) + dma_resv_fini(dmabuf->resv); + WARN_ON(!list_empty(&dmabuf->attachments)); module_put(dmabuf->owner); + kfree(dmabuf->name); kfree(dmabuf); +} + +static int dma_buf_file_release(struct inode *inode, struct file *file) +{ + if (!is_dma_buf_file(file)) + return -EINVAL; + + __dma_buf_list_del(file->private_data); + + return 0; +} + +static const struct dentry_operations dma_buf_dentry_ops = { + .d_dname = dmabuffs_dname, + .d_release = dma_buf_release, +}; + +static struct vfsmount *dma_buf_mnt; + +static int dma_buf_fs_init_context(struct fs_context *fc) +{ + struct pseudo_fs_context *ctx; + + ctx = init_pseudo(fc, DMA_BUF_MAGIC); + if (!ctx) + return -ENOMEM; + ctx->dops = &dma_buf_dentry_ops; return 0; } +static struct file_system_type dma_buf_fs_type = { + .name = "dmabuf", + .init_fs_context = dma_buf_fs_init_context, + .kill_sb = kill_anon_super, +}; + static int dma_buf_mmap_internal(struct file *file, struct vm_area_struct *vma) { struct dma_buf *dmabuf; @@ -90,6 +211,10 @@ static int dma_buf_mmap_internal(struct file *file, struct vm_area_struct *vma) dmabuf = file->private_data; + /* check if buffer supports mmap */ + if (!dmabuf->ops->mmap) + return -EINVAL; + /* check for overflowing the buffer's size */ if (vma->vm_pgoff + vma_pages(vma) > dmabuf->size >> PAGE_SHIFT) @@ -109,8 +234,9 @@ static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence) 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 */ + * 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) @@ -125,12 +251,12 @@ static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence) } /** - * DOC: fence polling + * DOC: implicit 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. + * implicit fences (represented internally in the kernel with &struct dma_fence) + * can be attached to a &dma_buf. The glue for that and a few related things are + * provided in the &dma_resv structure. * * Userspace can query the state of these implicitly tracked fences using poll() * and related system calls: @@ -144,27 +270,50 @@ static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence) * Note that this only signals the completion of the respective fences, i.e. the * DMA transfers are complete. Cache flushing and any other necessary * preparations before CPU access can begin still need to happen. + * + * As an alternative to poll(), the set of fences on DMA buffer can be + * exported as a &sync_file using &dma_buf_sync_file_export. */ static void dma_buf_poll_cb(struct dma_fence *fence, struct dma_fence_cb *cb) { struct dma_buf_poll_cb_t *dcb = (struct dma_buf_poll_cb_t *)cb; + struct dma_buf *dmabuf = container_of(dcb->poll, struct dma_buf, poll); 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); + dma_fence_put(fence); + /* Paired with get_file in dma_buf_poll */ + fput(dmabuf->file); +} + +static bool dma_buf_poll_add_cb(struct dma_resv *resv, bool write, + struct dma_buf_poll_cb_t *dcb) +{ + struct dma_resv_iter cursor; + struct dma_fence *fence; + int r; + + dma_resv_for_each_fence(&cursor, resv, dma_resv_usage_rw(write), + fence) { + dma_fence_get(fence); + r = dma_fence_add_callback(fence, &dcb->cb, dma_buf_poll_cb); + if (!r) + return true; + dma_fence_put(fence); + } + + return false; } 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; + struct dma_resv *resv; __poll_t events; - unsigned shared_count, seq; dmabuf = file->private_data; if (!dmabuf || !dmabuf->resv) @@ -178,104 +327,191 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll) 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; + dma_resv_lock(resv, NULL); - if (shared_count == 0) - pevents |= EPOLLOUT; + if (events & EPOLLOUT) { + struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_out; + /* Check that callback isn't busy */ spin_lock_irq(&dmabuf->poll.lock); - if (dcb->active) { - dcb->active |= pevents; - events &= ~pevents; - } else - dcb->active = pevents; + if (dcb->active) + events &= ~EPOLLOUT; + else + dcb->active = EPOLLOUT; 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); + if (events & EPOLLOUT) { + /* Paired with fput in dma_buf_poll_cb */ + get_file(dmabuf->file); + + if (!dma_buf_poll_add_cb(resv, true, dcb)) + /* No callback queued, wake up any other waiters */ dma_buf_poll_cb(NULL, &dcb->cb); - } + else + events &= ~EPOLLOUT; } } - if ((events & EPOLLOUT) && shared_count > 0) { - struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_shared; - int i; + if (events & EPOLLIN) { + struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_in; - /* Only queue a new callback if no event has fired yet */ + /* Check that callback isn't busy */ spin_lock_irq(&dmabuf->poll.lock); if (dcb->active) - events &= ~EPOLLOUT; + events &= ~EPOLLIN; else - dcb->active = EPOLLOUT; + dcb->active = EPOLLIN; 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 (events & EPOLLIN) { + /* Paired with fput in dma_buf_poll_cb */ + get_file(dmabuf->file); - 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; + if (!dma_buf_poll_add_cb(resv, false, dcb)) + /* No callback queued, wake up any other waiters */ 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); + else + events &= ~EPOLLIN; } - - /* No callback queued, wake up any additional waiters. */ - if (i == shared_count) - dma_buf_poll_cb(NULL, &dcb->cb); } -out: - rcu_read_unlock(); + dma_resv_unlock(resv); return events; } +/** + * dma_buf_set_name - Set a name to a specific dma_buf to track the usage. + * It could support changing the name of the dma-buf if the same + * piece of memory is used for multiple purpose between different devices. + * + * @dmabuf: [in] dmabuf buffer that will be renamed. + * @buf: [in] A piece of userspace memory that contains the name of + * the dma-buf. + * + * Returns 0 on success. If the dma-buf buffer is already attached to + * devices, return -EBUSY. + * + */ +static long dma_buf_set_name(struct dma_buf *dmabuf, const char __user *buf) +{ + char *name = strndup_user(buf, DMA_BUF_NAME_LEN); + + if (IS_ERR(name)) + return PTR_ERR(name); + + spin_lock(&dmabuf->name_lock); + kfree(dmabuf->name); + dmabuf->name = name; + spin_unlock(&dmabuf->name_lock); + + return 0; +} + +#if IS_ENABLED(CONFIG_SYNC_FILE) +static long dma_buf_export_sync_file(struct dma_buf *dmabuf, + void __user *user_data) +{ + struct dma_buf_export_sync_file arg; + enum dma_resv_usage usage; + struct dma_fence *fence = NULL; + struct sync_file *sync_file; + int fd, ret; + + if (copy_from_user(&arg, user_data, sizeof(arg))) + return -EFAULT; + + if (arg.flags & ~DMA_BUF_SYNC_RW) + return -EINVAL; + + if ((arg.flags & DMA_BUF_SYNC_RW) == 0) + return -EINVAL; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) + return fd; + + usage = dma_resv_usage_rw(arg.flags & DMA_BUF_SYNC_WRITE); + ret = dma_resv_get_singleton(dmabuf->resv, usage, &fence); + if (ret) + goto err_put_fd; + + if (!fence) + fence = dma_fence_get_stub(); + + sync_file = sync_file_create(fence); + + dma_fence_put(fence); + + if (!sync_file) { + ret = -ENOMEM; + goto err_put_fd; + } + + arg.fd = fd; + if (copy_to_user(user_data, &arg, sizeof(arg))) { + ret = -EFAULT; + goto err_put_file; + } + + fd_install(fd, sync_file->file); + + return 0; + +err_put_file: + fput(sync_file->file); +err_put_fd: + put_unused_fd(fd); + return ret; +} + +static long dma_buf_import_sync_file(struct dma_buf *dmabuf, + const void __user *user_data) +{ + struct dma_buf_import_sync_file arg; + struct dma_fence *fence, *f; + enum dma_resv_usage usage; + struct dma_fence_unwrap iter; + unsigned int num_fences; + int ret = 0; + + if (copy_from_user(&arg, user_data, sizeof(arg))) + return -EFAULT; + + if (arg.flags & ~DMA_BUF_SYNC_RW) + return -EINVAL; + + if ((arg.flags & DMA_BUF_SYNC_RW) == 0) + return -EINVAL; + + fence = sync_file_get_fence(arg.fd); + if (!fence) + return -EINVAL; + + usage = (arg.flags & DMA_BUF_SYNC_WRITE) ? DMA_RESV_USAGE_WRITE : + DMA_RESV_USAGE_READ; + + num_fences = 0; + dma_fence_unwrap_for_each(f, &iter, fence) + ++num_fences; + + if (num_fences > 0) { + dma_resv_lock(dmabuf->resv, NULL); + + ret = dma_resv_reserve_fences(dmabuf->resv, num_fences); + if (!ret) { + dma_fence_unwrap_for_each(f, &iter, fence) + dma_resv_add_fence(dmabuf->resv, f, usage); + } + + dma_resv_unlock(dmabuf->resv); + } + + dma_fence_put(fence); + + return ret; +} +#endif + static long dma_buf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -314,20 +550,45 @@ static long dma_buf_ioctl(struct file *file, ret = dma_buf_begin_cpu_access(dmabuf, direction); return ret; + + case DMA_BUF_SET_NAME_A: + case DMA_BUF_SET_NAME_B: + return dma_buf_set_name(dmabuf, (const char __user *)arg); + +#if IS_ENABLED(CONFIG_SYNC_FILE) + case DMA_BUF_IOCTL_EXPORT_SYNC_FILE: + return dma_buf_export_sync_file(dmabuf, (void __user *)arg); + case DMA_BUF_IOCTL_IMPORT_SYNC_FILE: + return dma_buf_import_sync_file(dmabuf, (const void __user *)arg); +#endif + default: return -ENOTTY; } } +static void dma_buf_show_fdinfo(struct seq_file *m, struct file *file) +{ + struct dma_buf *dmabuf = file->private_data; + + seq_printf(m, "size:\t%zu\n", dmabuf->size); + /* Don't count the temporary reference taken inside procfs seq_show */ + seq_printf(m, "count:\t%ld\n", file_count(dmabuf->file) - 1); + seq_printf(m, "exp_name:\t%s\n", dmabuf->exp_name); + spin_lock(&dmabuf->name_lock); + if (dmabuf->name) + seq_printf(m, "name:\t%s\n", dmabuf->name); + spin_unlock(&dmabuf->name_lock); +} + static const struct file_operations dma_buf_fops = { - .release = dma_buf_release, + .release = dma_buf_file_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 + .compat_ioctl = compat_ptr_ioctl, + .show_fdinfo = dma_buf_show_fdinfo, }; /* @@ -338,6 +599,38 @@ static inline int is_dma_buf_file(struct file *file) return file->f_op == &dma_buf_fops; } +static struct file *dma_buf_getfile(size_t size, int flags) +{ + static atomic64_t dmabuf_inode = ATOMIC64_INIT(0); + struct inode *inode = alloc_anon_inode(dma_buf_mnt->mnt_sb); + struct file *file; + + if (IS_ERR(inode)) + return ERR_CAST(inode); + + inode->i_size = size; + inode_set_bytes(inode, size); + + /* + * The ->i_ino acquired from get_next_ino() is not unique thus + * not suitable for using it as dentry name by dmabuf stats. + * Override ->i_ino with the unique and dmabuffs specific + * value. + */ + inode->i_ino = atomic64_inc_return(&dmabuf_inode); + flags &= O_ACCMODE | O_NONBLOCK; + file = alloc_file_pseudo(inode, dma_buf_mnt, "dmabuf", + flags, &dma_buf_fops); + if (IS_ERR(file)) + goto err_alloc_file; + + return file; + +err_alloc_file: + iput(inode); + return file; +} + /** * DOC: dma buf device access * @@ -350,7 +643,7 @@ static inline int is_dma_buf_file(struct file *file) * as a file descriptor by calling dma_buf_fd(). * * 2. Userspace passes this file-descriptors to all drivers it wants this buffer - * to share with: First the filedescriptor is converted to a &dma_buf using + * to share with: First the file descriptor is converted to a &dma_buf using * dma_buf_get(). Then the buffer is attached to the device using * dma_buf_attach(). * @@ -363,7 +656,7 @@ static inline int is_dma_buf_file(struct file *file) * * 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(). + * reference acquired with dma_buf_get() by calling dma_buf_put(). * * For the detailed semantics exporters are expected to implement see * &dma_buf_ops. @@ -379,9 +672,10 @@ static inline int is_dma_buf_file(struct file *file) * 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. + * Returns, on success, a newly created struct dma_buf object, which wraps the + * supplied private data and operations for struct 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. @@ -389,33 +683,38 @@ static inline int is_dma_buf_file(struct file *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); - else - /* prevent &dma_buf[1] == dma_buf->resv */ - alloc_size += 1; + if (WARN_ON(!exp_info->priv || !exp_info->ops + || !exp_info->ops->map_dma_buf + || !exp_info->ops->unmap_dma_buf + || !exp_info->ops->release)) + return ERR_PTR(-EINVAL); - if (WARN_ON(!exp_info->priv - || !exp_info->ops - || !exp_info->ops->map_dma_buf - || !exp_info->ops->unmap_dma_buf - || !exp_info->ops->release - || !exp_info->ops->mmap)) { + if (WARN_ON(!exp_info->ops->pin != !exp_info->ops->unpin)) return ERR_PTR(-EINVAL); - } if (!try_module_get(exp_info->owner)) return ERR_PTR(-ENOENT); + file = dma_buf_getfile(exp_info->size, exp_info->flags); + if (IS_ERR(file)) { + ret = PTR_ERR(file); + goto err_module; + } + + if (!exp_info->resv) + alloc_size += sizeof(struct dma_resv); + else + /* prevent &dma_buf[1] == dma_buf->resv */ + alloc_size += 1; dmabuf = kzalloc(alloc_size, GFP_KERNEL); if (!dmabuf) { ret = -ENOMEM; - goto err_module; + goto err_file; } dmabuf->priv = exp_info->priv; @@ -423,45 +722,45 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) dmabuf->size = exp_info->size; dmabuf->exp_name = exp_info->exp_name; dmabuf->owner = exp_info->owner; + spin_lock_init(&dmabuf->name_lock); init_waitqueue_head(&dmabuf->poll); - dmabuf->cb_excl.poll = dmabuf->cb_shared.poll = &dmabuf->poll; - dmabuf->cb_excl.active = dmabuf->cb_shared.active = 0; + dmabuf->cb_in.poll = dmabuf->cb_out.poll = &dmabuf->poll; + dmabuf->cb_in.active = dmabuf->cb_out.active = 0; + INIT_LIST_HEAD(&dmabuf->attachments); if (!resv) { - resv = (struct reservation_object *)&dmabuf[1]; - reservation_object_init(resv); + dmabuf->resv = (struct dma_resv *)&dmabuf[1]; + dma_resv_init(dmabuf->resv); + } else { + dmabuf->resv = resv; } - dmabuf->resv = resv; - file = anon_inode_getfile("dmabuf", &dma_buf_fops, dmabuf, - exp_info->flags); - if (IS_ERR(file)) { - ret = PTR_ERR(file); + ret = dma_buf_stats_setup(dmabuf, file); + if (ret) goto err_dmabuf; - } - file->f_mode |= FMODE_LSEEK; + file->private_data = dmabuf; + file->f_path.dentry->d_fsdata = dmabuf; 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); + __dma_buf_list_add(dmabuf); return dmabuf; err_dmabuf: + if (!resv) + dma_resv_fini(dmabuf->resv); kfree(dmabuf); +err_file: + fput(file); err_module: module_put(exp_info->owner); return ERR_PTR(ret); } -EXPORT_SYMBOL_GPL(dma_buf_export); +EXPORT_SYMBOL_NS_GPL(dma_buf_export, "DMA_BUF"); /** - * dma_buf_fd - returns a file descriptor for the given dma_buf + * dma_buf_fd - returns a file descriptor for the given struct dma_buf * @dmabuf: [in] pointer to dma_buf for which fd is required. * @flags: [in] flags to give to fd * @@ -469,26 +768,18 @@ EXPORT_SYMBOL_GPL(dma_buf_export); */ 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; + return FD_ADD(flags, dmabuf->file); } -EXPORT_SYMBOL_GPL(dma_buf_fd); +EXPORT_SYMBOL_NS_GPL(dma_buf_fd, "DMA_BUF"); /** - * dma_buf_get - returns the dma_buf structure related to an fd - * @fd: [in] fd associated with the dma_buf to be returned + * dma_buf_get - returns the struct dma_buf related to an fd + * @fd: [in] fd associated with the struct dma_buf to be returned * - * On success, returns the dma_buf structure associated with an fd; uses + * On success, returns the struct dma_buf associated with an fd; uses * file's refcounting done by fget to increase refcount. returns ERR_PTR * otherwise. */ @@ -508,7 +799,7 @@ struct dma_buf *dma_buf_get(int fd) return file->private_data; } -EXPORT_SYMBOL_GPL(dma_buf_get); +EXPORT_SYMBOL_NS_GPL(dma_buf_get, "DMA_BUF"); /** * dma_buf_put - decreases refcount of the buffer @@ -527,17 +818,116 @@ void dma_buf_put(struct dma_buf *dmabuf) fput(dmabuf->file); } -EXPORT_SYMBOL_GPL(dma_buf_put); +EXPORT_SYMBOL_NS_GPL(dma_buf_put, "DMA_BUF"); + +static void mangle_sg_table(struct sg_table *sg_table) +{ +#ifdef CONFIG_DMABUF_DEBUG + int i; + struct scatterlist *sg; + + /* To catch abuse of the underlying struct page by importers mix + * up the bits, but take care to preserve the low SG_ bits to + * not corrupt the sgt. The mixing is undone on unmap + * before passing the sgt back to the exporter. + */ + for_each_sgtable_sg(sg_table, sg, i) + sg->page_link ^= ~0xffUL; +#endif + +} + +static inline bool +dma_buf_attachment_is_dynamic(struct dma_buf_attachment *attach) +{ + return !!attach->importer_ops; +} + +static bool +dma_buf_pin_on_map(struct dma_buf_attachment *attach) +{ + return attach->dmabuf->ops->pin && + (!dma_buf_attachment_is_dynamic(attach) || + !IS_ENABLED(CONFIG_DMABUF_MOVE_NOTIFY)); +} /** - * 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. + * DOC: locking convention + * + * In order to avoid deadlock situations between dma-buf exports and importers, + * all dma-buf API users must follow the common dma-buf locking convention. + * + * Convention for importers + * + * 1. Importers must hold the dma-buf reservation lock when calling these + * functions: + * + * - dma_buf_pin() + * - dma_buf_unpin() + * - dma_buf_map_attachment() + * - dma_buf_unmap_attachment() + * - dma_buf_vmap() + * - dma_buf_vunmap() + * + * 2. Importers must not hold the dma-buf reservation lock when calling these + * functions: + * + * - dma_buf_attach() + * - dma_buf_dynamic_attach() + * - dma_buf_detach() + * - dma_buf_export() + * - dma_buf_fd() + * - dma_buf_get() + * - dma_buf_put() + * - dma_buf_mmap() + * - dma_buf_begin_cpu_access() + * - dma_buf_end_cpu_access() + * - dma_buf_map_attachment_unlocked() + * - dma_buf_unmap_attachment_unlocked() + * - dma_buf_vmap_unlocked() + * - dma_buf_vunmap_unlocked() + * + * Convention for exporters + * + * 1. These &dma_buf_ops callbacks are invoked with unlocked dma-buf + * reservation and exporter can take the lock: + * + * - &dma_buf_ops.attach() + * - &dma_buf_ops.detach() + * - &dma_buf_ops.release() + * - &dma_buf_ops.begin_cpu_access() + * - &dma_buf_ops.end_cpu_access() + * - &dma_buf_ops.mmap() + * + * 2. These &dma_buf_ops callbacks are invoked with locked dma-buf + * reservation and exporter can't take the lock: + * + * - &dma_buf_ops.pin() + * - &dma_buf_ops.unpin() + * - &dma_buf_ops.map_dma_buf() + * - &dma_buf_ops.unmap_dma_buf() + * - &dma_buf_ops.vmap() + * - &dma_buf_ops.vunmap() + * + * 3. Exporters must hold the dma-buf reservation lock when calling these + * functions: + * + * - dma_buf_move_notify() + */ + +/** + * dma_buf_dynamic_attach - Add the device to dma_buf's attachments list + * @dmabuf: [in] buffer to attach device to. + * @dev: [in] device to be attached. + * @importer_ops: [in] importer operations for the attachment + * @importer_priv: [in] importer private pointer for the attachment * * Returns struct dma_buf_attachment pointer for this attachment. Attachments * must be cleaned up by calling dma_buf_detach(). * + * Optionally this calls &dma_buf_ops.attach to allow device-specific attach + * functionality. + * * Returns: * * A pointer to newly created &dma_buf_attachment on success, or a negative @@ -547,8 +937,10 @@ 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, + const struct dma_buf_attach_ops *importer_ops, + void *importer_priv) { struct dma_buf_attachment *attach; int ret; @@ -556,54 +948,127 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, if (WARN_ON(!dmabuf || !dev)) return ERR_PTR(-EINVAL); + if (WARN_ON(importer_ops && !importer_ops->move_notify)) + return ERR_PTR(-EINVAL); + attach = kzalloc(sizeof(*attach), GFP_KERNEL); if (!attach) return ERR_PTR(-ENOMEM); attach->dev = dev; attach->dmabuf = dmabuf; - - mutex_lock(&dmabuf->lock); + if (importer_ops) + attach->peer2peer = importer_ops->allow_peer2peer; + attach->importer_ops = importer_ops; + attach->importer_priv = importer_priv; if (dmabuf->ops->attach) { ret = dmabuf->ops->attach(dmabuf, attach); if (ret) goto err_attach; } + dma_resv_lock(dmabuf->resv, NULL); list_add(&attach->node, &dmabuf->attachments); + dma_resv_unlock(dmabuf->resv); - mutex_unlock(&dmabuf->lock); return attach; err_attach: kfree(attach); - mutex_unlock(&dmabuf->lock); return ERR_PTR(ret); } -EXPORT_SYMBOL_GPL(dma_buf_attach); +EXPORT_SYMBOL_NS_GPL(dma_buf_dynamic_attach, "DMA_BUF"); + +/** + * dma_buf_attach - Wrapper for dma_buf_dynamic_attach + * @dmabuf: [in] buffer to attach device to. + * @dev: [in] device to be attached. + * + * Wrapper to call dma_buf_dynamic_attach() for drivers which still use a static + * mapping. + */ +struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, + struct device *dev) +{ + return dma_buf_dynamic_attach(dmabuf, dev, NULL, NULL); +} +EXPORT_SYMBOL_NS_GPL(dma_buf_attach, "DMA_BUF"); /** - * dma_buf_detach - Remove the given attachment from dmabuf's attachments list; - * optionally calls detach() of dma_buf_ops for device-specific detach + * dma_buf_detach - Remove the given attachment from dmabuf's attachments list * @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(). + * + * Optionally this calls &dma_buf_ops.detach for device-specific detach. */ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach) { - if (WARN_ON(!dmabuf || !attach)) + if (WARN_ON(!dmabuf || !attach || dmabuf != attach->dmabuf)) return; - mutex_lock(&dmabuf->lock); + 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); +EXPORT_SYMBOL_NS_GPL(dma_buf_detach, "DMA_BUF"); + +/** + * dma_buf_pin - Lock down the DMA-buf + * @attach: [in] attachment which should be pinned + * + * Only dynamic importers (who set up @attach with dma_buf_dynamic_attach()) may + * call this, and only for limited use cases like scanout and not for temporary + * pin operations. It is not permitted to allow userspace to pin arbitrary + * amounts of buffers through this interface. + * + * Buffers must be unpinned by calling dma_buf_unpin(). + * + * Returns: + * 0 on success, negative error code on failure. + */ +int dma_buf_pin(struct dma_buf_attachment *attach) +{ + struct dma_buf *dmabuf = attach->dmabuf; + int ret = 0; + + WARN_ON(!attach->importer_ops); + + dma_resv_assert_held(dmabuf->resv); + + if (dmabuf->ops->pin) + ret = dmabuf->ops->pin(attach); + + return ret; +} +EXPORT_SYMBOL_NS_GPL(dma_buf_pin, "DMA_BUF"); + +/** + * dma_buf_unpin - Unpin a DMA-buf + * @attach: [in] attachment which should be unpinned + * + * This unpins a buffer pinned by dma_buf_pin() and allows the exporter to move + * any mapping of @attach again and inform the importer through + * &dma_buf_attach_ops.move_notify. + */ +void dma_buf_unpin(struct dma_buf_attachment *attach) +{ + struct dma_buf *dmabuf = attach->dmabuf; + + WARN_ON(!attach->importer_ops); + + dma_resv_assert_held(dmabuf->resv); + + if (dmabuf->ops->unpin) + dmabuf->ops->unpin(attach); +} +EXPORT_SYMBOL_NS_GPL(dma_buf_unpin, "DMA_BUF"); /** * dma_buf_map_attachment - Returns the scatterlist table of the attachment; @@ -615,28 +1080,117 @@ EXPORT_SYMBOL_GPL(dma_buf_detach); * Returns sg_table containing the scatterlist to be returned; returns ERR_PTR * on error. May return -EINTR if it is interrupted by a signal. * + * On success, the DMA addresses and lengths in the returned scatterlist are + * PAGE_SIZE aligned. + * * 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. + * + * Important: Dynamic importers must wait for the exclusive fence of the struct + * dma_resv attached to the DMA-BUF first. */ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach, enum dma_data_direction direction) { struct sg_table *sg_table; + signed long ret; might_sleep(); if (WARN_ON(!attach || !attach->dmabuf)) return ERR_PTR(-EINVAL); + dma_resv_assert_held(attach->dmabuf->resv); + + if (dma_buf_pin_on_map(attach)) { + ret = attach->dmabuf->ops->pin(attach); + /* + * Catch exporters making buffers inaccessible even when + * attachments preventing that exist. + */ + WARN_ON_ONCE(ret == -EBUSY); + if (ret) + return ERR_PTR(ret); + } + sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction); if (!sg_table) sg_table = ERR_PTR(-ENOMEM); + if (IS_ERR(sg_table)) + goto error_unpin; + + /* + * Importers with static attachments don't wait for fences. + */ + if (!dma_buf_attachment_is_dynamic(attach)) { + ret = dma_resv_wait_timeout(attach->dmabuf->resv, + DMA_RESV_USAGE_KERNEL, true, + MAX_SCHEDULE_TIMEOUT); + if (ret < 0) + goto error_unmap; + } + mangle_sg_table(sg_table); + +#ifdef CONFIG_DMA_API_DEBUG + { + struct scatterlist *sg; + u64 addr; + int len; + int i; + + for_each_sgtable_dma_sg(sg_table, sg, i) { + addr = sg_dma_address(sg); + len = sg_dma_len(sg); + if (!PAGE_ALIGNED(addr) || !PAGE_ALIGNED(len)) { + pr_debug("%s: addr %llx or len %x is not page aligned!\n", + __func__, addr, len); + } + } + } +#endif /* CONFIG_DMA_API_DEBUG */ + return sg_table; + +error_unmap: + attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, direction); + sg_table = ERR_PTR(ret); + +error_unpin: + if (dma_buf_pin_on_map(attach)) + attach->dmabuf->ops->unpin(attach); return sg_table; } -EXPORT_SYMBOL_GPL(dma_buf_map_attachment); +EXPORT_SYMBOL_NS_GPL(dma_buf_map_attachment, "DMA_BUF"); + +/** + * dma_buf_map_attachment_unlocked - 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 + * + * Unlocked variant of dma_buf_map_attachment(). + */ +struct sg_table * +dma_buf_map_attachment_unlocked(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); + + dma_resv_lock(attach->dmabuf->resv, NULL); + sg_table = dma_buf_map_attachment(attach, direction); + dma_resv_unlock(attach->dmabuf->resv); + + return sg_table; +} +EXPORT_SYMBOL_NS_GPL(dma_buf_map_attachment_unlocked, "DMA_BUF"); /** * dma_buf_unmap_attachment - unmaps and decreases usecount of the buffer;might @@ -657,56 +1211,88 @@ void dma_buf_unmap_attachment(struct dma_buf_attachment *attach, if (WARN_ON(!attach || !attach->dmabuf || !sg_table)) return; - attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, - direction); + dma_resv_assert_held(attach->dmabuf->resv); + + mangle_sg_table(sg_table); + attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, direction); + + if (dma_buf_pin_on_map(attach)) + attach->dmabuf->ops->unpin(attach); +} +EXPORT_SYMBOL_NS_GPL(dma_buf_unmap_attachment, "DMA_BUF"); + +/** + * dma_buf_unmap_attachment_unlocked - 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 + * + * Unlocked variant of dma_buf_unmap_attachment(). + */ +void dma_buf_unmap_attachment_unlocked(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; + + dma_resv_lock(attach->dmabuf->resv, NULL); + dma_buf_unmap_attachment(attach, sg_table, direction); + dma_resv_unlock(attach->dmabuf->resv); } -EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment); +EXPORT_SYMBOL_NS_GPL(dma_buf_unmap_attachment_unlocked, "DMA_BUF"); + +/** + * dma_buf_move_notify - notify attachments that DMA-buf is moving + * + * @dmabuf: [in] buffer which is moving + * + * Informs all attachments that they need to destroy and recreate all their + * mappings. + */ +void dma_buf_move_notify(struct dma_buf *dmabuf) +{ + struct dma_buf_attachment *attach; + + dma_resv_assert_held(dmabuf->resv); + + list_for_each_entry(attach, &dmabuf->attachments, node) + if (attach->importer_ops) + attach->importer_ops->move_notify(attach); +} +EXPORT_SYMBOL_NS_GPL(dma_buf_move_notify, "DMA_BUF"); /** * DOC: cpu access * - * There are mutliple reasons for supporting CPU access to a dma buffer object: + * There are multiple 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 + * sending it away. Cache coherency is handled by bracketing 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. + * 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_kmap(struct dma_buf \*, unsigned long); - * void dma_buf_kunmap(struct dma_buf \*, unsigned long, void \*); + * Interfaces: * - * Implementing the functions is optional for exporters and for importers all - * the restrictions of using kmap apply. + * .. code-block:: c * - * 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) + * void *dma_buf_vmap(struct dma_buf *dmabuf, struct iosys_map *map) + * void dma_buf_vunmap(struct dma_buf *dmabuf, struct iosys_map *map) * * The vmap call can fail if there is no vmap support in the exporter, or if - * it runs out of vmalloc space. 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. + * it runs out of vmalloc space. 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 @@ -716,7 +1302,7 @@ EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment); * 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, + * fd. But like for CPU access there's a need to bracket 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. @@ -757,12 +1343,14 @@ EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment); * 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); + * Interface: + * + * .. code-block:: c + * + * 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 + * set up a mapping in userspace, calling do_mmap with &dma_buf.file will * equally achieve that for a dma-buf object. */ @@ -771,12 +1359,12 @@ 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, - MAX_SCHEDULE_TIMEOUT); + ret = dma_resv_wait_timeout(resv, dma_resv_usage_rw(write), + true, MAX_SCHEDULE_TIMEOUT); if (ret < 0) return ret; @@ -789,12 +1377,17 @@ static int __dma_buf_begin_cpu_access(struct dma_buf *dmabuf, * 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. + * @direction: [in] direction of 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 + * dma_buf_end_cpu_access(). Only when cpu access is bracketed by both calls is * it guaranteed to be coherent with other DMA access. * + * This function will also wait for any DMA transactions tracked through + * implicit synchronization in &dma_buf.resv. For DMA transactions with explicit + * synchronization this function will only ensure cache coherency, callers must + * ensure synchronization with such DMA transactions on their own. + * * Can return negative error values, returns 0 on success. */ int dma_buf_begin_cpu_access(struct dma_buf *dmabuf, @@ -805,6 +1398,8 @@ int dma_buf_begin_cpu_access(struct dma_buf *dmabuf, if (WARN_ON(!dmabuf)) return -EINVAL; + might_lock(&dmabuf->resv->lock.base); + if (dmabuf->ops->begin_cpu_access) ret = dmabuf->ops->begin_cpu_access(dmabuf, direction); @@ -817,7 +1412,7 @@ int dma_buf_begin_cpu_access(struct dma_buf *dmabuf, return ret; } -EXPORT_SYMBOL_GPL(dma_buf_begin_cpu_access); +EXPORT_SYMBOL_NS_GPL(dma_buf_begin_cpu_access, "DMA_BUF"); /** * dma_buf_end_cpu_access - Must be called after accessing a dma_buf from the @@ -825,7 +1420,7 @@ EXPORT_SYMBOL_GPL(dma_buf_begin_cpu_access); * 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. + * @direction: [in] direction of access. * * This terminates CPU access started with dma_buf_begin_cpu_access(). * @@ -838,49 +1433,14 @@ int dma_buf_end_cpu_access(struct dma_buf *dmabuf, WARN_ON(!dmabuf); + might_lock(&dmabuf->resv->lock.base); + 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); +EXPORT_SYMBOL_NS_GPL(dma_buf_end_cpu_access, "DMA_BUF"); /** @@ -900,12 +1460,13 @@ EXPORT_SYMBOL_GPL(dma_buf_kunmap); int dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma, unsigned long pgoff) { - struct file *oldfile; - int ret; - if (WARN_ON(!dmabuf || !vma)) return -EINVAL; + /* check if buffer supports mmap */ + if (!dmabuf->ops->mmap) + return -EINVAL; + /* check for offset overflow */ if (pgoff + vma_pages(vma) < pgoff) return -EOVERFLOW; @@ -916,160 +1477,169 @@ int dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma, return -EINVAL; /* readjust the vma */ - get_file(dmabuf->file); - oldfile = vma->vm_file; - vma->vm_file = dmabuf->file; + vma_set_file(vma, 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; - + return dmabuf->ops->mmap(dmabuf, vma); } -EXPORT_SYMBOL_GPL(dma_buf_mmap); +EXPORT_SYMBOL_NS_GPL(dma_buf_mmap, "DMA_BUF"); /** * 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 + * @map: [out] returns the vmap pointer * * 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. + * To ensure coherency users must call dma_buf_begin_cpu_access() and + * dma_buf_end_cpu_access() around any cpu access performed through this + * mapping. + * + * Returns 0 on success, or a negative errno code otherwise. */ -void *dma_buf_vmap(struct dma_buf *dmabuf) +int dma_buf_vmap(struct dma_buf *dmabuf, struct iosys_map *map) { - void *ptr; + struct iosys_map ptr; + int ret; + + iosys_map_clear(map); if (WARN_ON(!dmabuf)) - return NULL; + return -EINVAL; + + dma_resv_assert_held(dmabuf->resv); if (!dmabuf->ops->vmap) - return NULL; + return -EINVAL; - 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(iosys_map_is_null(&dmabuf->vmap_ptr)); + *map = dmabuf->vmap_ptr; + return 0; } - BUG_ON(dmabuf->vmap_ptr); + BUG_ON(iosys_map_is_set(&dmabuf->vmap_ptr)); - ptr = dmabuf->ops->vmap(dmabuf); - if (WARN_ON_ONCE(IS_ERR(ptr))) - ptr = NULL; - if (!ptr) - goto out_unlock; + ret = dmabuf->ops->vmap(dmabuf, &ptr); + if (WARN_ON_ONCE(ret)) + return ret; dmabuf->vmap_ptr = ptr; dmabuf->vmapping_counter = 1; -out_unlock: - mutex_unlock(&dmabuf->lock); - return ptr; + *map = dmabuf->vmap_ptr; + + return 0; } -EXPORT_SYMBOL_GPL(dma_buf_vmap); +EXPORT_SYMBOL_NS_GPL(dma_buf_vmap, "DMA_BUF"); + +/** + * dma_buf_vmap_unlocked - Create virtual mapping for the buffer object into kernel + * address space. Same restrictions as for vmap and friends apply. + * @dmabuf: [in] buffer to vmap + * @map: [out] returns the vmap pointer + * + * Unlocked version of dma_buf_vmap() + * + * Returns 0 on success, or a negative errno code otherwise. + */ +int dma_buf_vmap_unlocked(struct dma_buf *dmabuf, struct iosys_map *map) +{ + int ret; + + iosys_map_clear(map); + + if (WARN_ON(!dmabuf)) + return -EINVAL; + + dma_resv_lock(dmabuf->resv, NULL); + ret = dma_buf_vmap(dmabuf, map); + dma_resv_unlock(dmabuf->resv); + + return ret; +} +EXPORT_SYMBOL_NS_GPL(dma_buf_vmap_unlocked, "DMA_BUF"); /** * dma_buf_vunmap - Unmap a vmap obtained by dma_buf_vmap. * @dmabuf: [in] buffer to vunmap - * @vaddr: [in] vmap to vunmap + * @map: [in] vmap pointer to vunmap */ -void dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr) +void dma_buf_vunmap(struct dma_buf *dmabuf, struct iosys_map *map) { if (WARN_ON(!dmabuf)) return; - BUG_ON(!dmabuf->vmap_ptr); + dma_resv_assert_held(dmabuf->resv); + + BUG_ON(iosys_map_is_null(&dmabuf->vmap_ptr)); BUG_ON(dmabuf->vmapping_counter == 0); - BUG_ON(dmabuf->vmap_ptr != vaddr); + BUG_ON(!iosys_map_is_equal(&dmabuf->vmap_ptr, map)); - mutex_lock(&dmabuf->lock); if (--dmabuf->vmapping_counter == 0) { if (dmabuf->ops->vunmap) - dmabuf->ops->vunmap(dmabuf, vaddr); - dmabuf->vmap_ptr = NULL; + dmabuf->ops->vunmap(dmabuf, map); + iosys_map_clear(&dmabuf->vmap_ptr); } - mutex_unlock(&dmabuf->lock); } -EXPORT_SYMBOL_GPL(dma_buf_vunmap); +EXPORT_SYMBOL_NS_GPL(dma_buf_vunmap, "DMA_BUF"); + +/** + * dma_buf_vunmap_unlocked - Unmap a vmap obtained by dma_buf_vmap. + * @dmabuf: [in] buffer to vunmap + * @map: [in] vmap pointer to vunmap + */ +void dma_buf_vunmap_unlocked(struct dma_buf *dmabuf, struct iosys_map *map) +{ + if (WARN_ON(!dmabuf)) + return; + + dma_resv_lock(dmabuf->resv, NULL); + dma_buf_vunmap(dmabuf, map); + dma_resv_unlock(dmabuf->resv); +} +EXPORT_SYMBOL_NS_GPL(dma_buf_vunmap_unlocked, "DMA_BUF"); #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; + int count = 0, attach_count; size_t size = 0; + int ret; - ret = mutex_lock_interruptible(&db_list.lock); + ret = mutex_lock_interruptible(&dmabuf_list_mutex); 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"); + seq_printf(s, "%-8s\t%-8s\t%-8s\t%-8s\texp_name\t%-8s\tname\n", + "size", "flags", "mode", "count", "ino"); - list_for_each_entry(buf_obj, &db_list.head, list_node) { - ret = mutex_lock_interruptible(&buf_obj->lock); + list_for_each_entry(buf_obj, &dmabuf_list, list_node) { - 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\n", + + spin_lock(&buf_obj->name_lock); + seq_printf(s, "%08zu\t%08x\t%08x\t%08ld\t%s\t%08lu\t%s\n", buf_obj->size, buf_obj->file->f_flags, buf_obj->file->f_mode, file_count(buf_obj->file), - buf_obj->exp_name); - - 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(); - } + buf_obj->exp_name, + file_inode(buf_obj->file)->i_ino, + buf_obj->name ?: "<none>"); + spin_unlock(&buf_obj->name_lock); - 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"); - } - rcu_read_unlock(); + dma_resv_describe(buf_obj->resv, s); seq_puts(s, "\tAttached Devices:\n"); attach_count = 0; @@ -1078,32 +1648,26 @@ 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); + mutex_unlock(&dmabuf_list_mutex); return 0; -} -static int dma_buf_debug_open(struct inode *inode, struct file *file) -{ - return single_open(file, dma_buf_debug_show, NULL); +error_unlock: + mutex_unlock(&dmabuf_list_mutex); + return ret; } -static const struct file_operations dma_buf_debug_fops = { - .open = dma_buf_debug_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(dma_buf_debug); static struct dentry *dma_buf_debugfs_dir; @@ -1118,7 +1682,7 @@ static int dma_buf_init_debugfs(void) dma_buf_debugfs_dir = d; - d = debugfs_create_file("bufinfo", S_IRUGO, dma_buf_debugfs_dir, + d = debugfs_create_file("bufinfo", 0444, dma_buf_debugfs_dir, NULL, &dma_buf_debug_fops); if (IS_ERR(d)) { pr_debug("dma_buf: debugfs: failed to create node bufinfo\n"); @@ -1146,8 +1710,16 @@ static inline void dma_buf_uninit_debugfs(void) static int __init dma_buf_init(void) { - mutex_init(&db_list.lock); - INIT_LIST_HEAD(&db_list.head); + int ret; + + ret = dma_buf_init_sysfs_statistics(); + if (ret) + return ret; + + dma_buf_mnt = kern_mount(&dma_buf_fs_type); + if (IS_ERR(dma_buf_mnt)) + return PTR_ERR(dma_buf_mnt); + dma_buf_init_debugfs(); return 0; } @@ -1156,5 +1728,7 @@ subsys_initcall(dma_buf_init); static void __exit dma_buf_deinit(void) { dma_buf_uninit_debugfs(); + kern_unmount(dma_buf_mnt); + dma_buf_uninit_sysfs_statistics(); } __exitcall(dma_buf_deinit); diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c index a8c254497251..6657d4b30af9 100644 --- a/drivers/dma-buf/dma-fence-array.c +++ b/drivers/dma-buf/dma-fence-array.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * dma-fence-array: aggregate fences to be waited together * @@ -6,21 +7,14 @@ * 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> +#define PENDING_ERROR 1 + static const char *dma_fence_array_get_driver_name(struct dma_fence *fence) { return "dma_fence_array"; @@ -31,10 +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); } @@ -46,6 +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 @@ -55,7 +70,7 @@ static void dma_fence_array_cb_func(struct dma_fence *f, 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]); + struct dma_fence_array_cb *cb = array->callbacks; unsigned i; for (i = 0; i < array->num_fences; ++i) { @@ -71,9 +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; + } } } @@ -83,8 +103,38 @@ static bool dma_fence_array_enable_signaling(struct dma_fence *fence) static bool dma_fence_array_signaled(struct dma_fence *fence) { struct dma_fence_array *array = to_dma_fence_array(fence); + int num_pending; + unsigned int i; + + /* + * We need to read num_pending before checking the enable_signal bit + * to avoid racing with the enable_signaling() implementation, which + * might decrement the counter, and cause a partial check. + * atomic_read_acquire() pairs with atomic_dec_and_test() in + * dma_fence_array_enable_signaling() + * + * The !--num_pending check is here to account for the any_signaled case + * if we race with enable_signaling(), that means the !num_pending check + * in the is_signalling_enabled branch might be outdated (num_pending + * might have been decremented), but that's fine. The user will get the + * right value when testing again later. + */ + num_pending = atomic_read_acquire(&array->num_pending); + if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &array->base.flags)) { + if (num_pending <= 0) + goto signal; + return false; + } + + for (i = 0; i < array->num_fences; ++i) { + if (dma_fence_is_signaled(array->fences[i]) && !--num_pending) + goto signal; + } + return false; - return atomic_read(&array->num_pending) <= 0; +signal: + dma_fence_array_clear_pending_error(array); + return true; } static void dma_fence_array_release(struct dma_fence *fence) @@ -99,16 +149,88 @@ static void dma_fence_array_release(struct dma_fence *fence) dma_fence_free(fence); } +static void dma_fence_array_set_deadline(struct dma_fence *fence, + ktime_t deadline) +{ + struct dma_fence_array *array = to_dma_fence_array(fence); + unsigned i; + + for (i = 0; i < array->num_fences; ++i) + dma_fence_set_deadline(array->fences[i], deadline); +} + 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, + .set_deadline = dma_fence_array_set_deadline, }; EXPORT_SYMBOL(dma_fence_array_ops); /** + * dma_fence_array_alloc - Allocate a custom fence array + * @num_fences: [in] number of fences to add in the array + * + * Return dma fence array on success, NULL on failure + */ +struct dma_fence_array *dma_fence_array_alloc(int num_fences) +{ + struct dma_fence_array *array; + + return kzalloc(struct_size(array, callbacks, num_fences), GFP_KERNEL); +} +EXPORT_SYMBOL(dma_fence_array_alloc); + +/** + * dma_fence_array_init - Init a custom fence array + * @array: [in] dma fence array to arm + * @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 + * + * Implementation of @dma_fence_array_create without allocation. Useful to init + * a preallocated dma fence array in the path of reclaim or dma fence signaling. + */ +void dma_fence_array_init(struct dma_fence_array *array, + int num_fences, struct dma_fence **fences, + u64 context, unsigned seqno, + bool signal_on_any) +{ + WARN_ON(!num_fences || !fences); + + array->num_fences = num_fences; + + 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); + + atomic_set(&array->num_pending, signal_on_any ? 1 : num_fences); + array->fences = fences; + + array->base.error = PENDING_ERROR; + + /* + * dma_fence_array objects should never contain any other fence + * containers or otherwise we run into recursion and potential kernel + * stack overflow on operations on the dma_fence_array. + * + * The correct way of handling this is to flatten out the array by the + * caller instead. + * + * Enforce this here by checking that we don't create a dma_fence_array + * with any container inside. + */ + while (num_fences--) + WARN_ON(dma_fence_is_container(fences[num_fences])); +} +EXPORT_SYMBOL(dma_fence_array_init); + +/** * 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 @@ -133,22 +255,13 @@ struct dma_fence_array *dma_fence_array_create(int num_fences, 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); + array = dma_fence_array_alloc(num_fences); 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; + dma_fence_array_init(array, num_fences, fences, + context, seqno, signal_on_any); return array; } @@ -179,3 +292,33 @@ bool dma_fence_match_context(struct dma_fence *fence, u64 context) return true; } EXPORT_SYMBOL(dma_fence_match_context); + +struct dma_fence *dma_fence_array_first(struct dma_fence *head) +{ + struct dma_fence_array *array; + + if (!head) + return NULL; + + array = to_dma_fence_array(head); + if (!array) + return head; + + if (!array->num_fences) + return NULL; + + return array->fences[0]; +} +EXPORT_SYMBOL(dma_fence_array_first); + +struct dma_fence *dma_fence_array_next(struct dma_fence *head, + unsigned int index) +{ + struct dma_fence_array *array = to_dma_fence_array(head); + + if (!array || index >= array->num_fences) + return NULL; + + return array->fences[index]; +} +EXPORT_SYMBOL(dma_fence_array_next); diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c new file mode 100644 index 000000000000..a8a90acf4f34 --- /dev/null +++ b/drivers/dma-buf/dma-fence-chain.c @@ -0,0 +1,276 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * fence-chain: chain fences together in a timeline + * + * Copyright (C) 2018 Advanced Micro Devices, Inc. + * Authors: + * Christian König <christian.koenig@amd.com> + */ + +#include <linux/dma-fence-chain.h> + +static bool dma_fence_chain_enable_signaling(struct dma_fence *fence); + +/** + * dma_fence_chain_get_prev - use RCU to get a reference to the previous fence + * @chain: chain node to get the previous node from + * + * Use dma_fence_get_rcu_safe to get a reference to the previous fence of the + * chain node. + */ +static struct dma_fence *dma_fence_chain_get_prev(struct dma_fence_chain *chain) +{ + struct dma_fence *prev; + + rcu_read_lock(); + prev = dma_fence_get_rcu_safe(&chain->prev); + rcu_read_unlock(); + return prev; +} + +/** + * dma_fence_chain_walk - chain walking function + * @fence: current chain node + * + * Walk the chain to the next node. Returns the next fence or NULL if we are at + * the end of the chain. Garbage collects chain nodes which are already + * signaled. + */ +struct dma_fence *dma_fence_chain_walk(struct dma_fence *fence) +{ + struct dma_fence_chain *chain, *prev_chain; + struct dma_fence *prev, *replacement, *tmp; + + chain = to_dma_fence_chain(fence); + if (!chain) { + dma_fence_put(fence); + return NULL; + } + + while ((prev = dma_fence_chain_get_prev(chain))) { + + prev_chain = to_dma_fence_chain(prev); + if (prev_chain) { + if (!dma_fence_is_signaled(prev_chain->fence)) + break; + + replacement = dma_fence_chain_get_prev(prev_chain); + } else { + if (!dma_fence_is_signaled(prev)) + break; + + replacement = NULL; + } + + tmp = unrcu_pointer(cmpxchg(&chain->prev, RCU_INITIALIZER(prev), + RCU_INITIALIZER(replacement))); + if (tmp == prev) + dma_fence_put(tmp); + else + dma_fence_put(replacement); + dma_fence_put(prev); + } + + dma_fence_put(fence); + return prev; +} +EXPORT_SYMBOL(dma_fence_chain_walk); + +/** + * dma_fence_chain_find_seqno - find fence chain node by seqno + * @pfence: pointer to the chain node where to start + * @seqno: the sequence number to search for + * + * Advance the fence pointer to the chain node which will signal this sequence + * number. If no sequence number is provided then this is a no-op. + * + * Returns EINVAL if the fence is not a chain node or the sequence number has + * not yet advanced far enough. + */ +int dma_fence_chain_find_seqno(struct dma_fence **pfence, uint64_t seqno) +{ + struct dma_fence_chain *chain; + + if (!seqno) + return 0; + + chain = to_dma_fence_chain(*pfence); + if (!chain || chain->base.seqno < seqno) + return -EINVAL; + + dma_fence_chain_for_each(*pfence, &chain->base) { + if ((*pfence)->context != chain->base.context || + to_dma_fence_chain(*pfence)->prev_seqno < seqno) + break; + } + dma_fence_put(&chain->base); + + return 0; +} +EXPORT_SYMBOL(dma_fence_chain_find_seqno); + +static const char *dma_fence_chain_get_driver_name(struct dma_fence *fence) +{ + return "dma_fence_chain"; +} + +static const char *dma_fence_chain_get_timeline_name(struct dma_fence *fence) +{ + return "unbound"; +} + +static void dma_fence_chain_irq_work(struct irq_work *work) +{ + struct dma_fence_chain *chain; + + chain = container_of(work, typeof(*chain), work); + + /* Try to rearm the callback */ + if (!dma_fence_chain_enable_signaling(&chain->base)) + /* Ok, we are done. No more unsignaled fences left */ + dma_fence_signal(&chain->base); + dma_fence_put(&chain->base); +} + +static void dma_fence_chain_cb(struct dma_fence *f, struct dma_fence_cb *cb) +{ + struct dma_fence_chain *chain; + + chain = container_of(cb, typeof(*chain), cb); + init_irq_work(&chain->work, dma_fence_chain_irq_work); + irq_work_queue(&chain->work); + dma_fence_put(f); +} + +static bool dma_fence_chain_enable_signaling(struct dma_fence *fence) +{ + struct dma_fence_chain *head = to_dma_fence_chain(fence); + + dma_fence_get(&head->base); + dma_fence_chain_for_each(fence, &head->base) { + struct dma_fence *f = dma_fence_chain_contained(fence); + + dma_fence_get(f); + if (!dma_fence_add_callback(f, &head->cb, dma_fence_chain_cb)) { + dma_fence_put(fence); + return true; + } + dma_fence_put(f); + } + dma_fence_put(&head->base); + return false; +} + +static bool dma_fence_chain_signaled(struct dma_fence *fence) +{ + dma_fence_chain_for_each(fence, fence) { + struct dma_fence *f = dma_fence_chain_contained(fence); + + if (!dma_fence_is_signaled(f)) { + dma_fence_put(fence); + return false; + } + } + + return true; +} + +static void dma_fence_chain_release(struct dma_fence *fence) +{ + struct dma_fence_chain *chain = to_dma_fence_chain(fence); + struct dma_fence *prev; + + /* Manually unlink the chain as much as possible to avoid recursion + * and potential stack overflow. + */ + while ((prev = rcu_dereference_protected(chain->prev, true))) { + struct dma_fence_chain *prev_chain; + + if (kref_read(&prev->refcount) > 1) + break; + + prev_chain = to_dma_fence_chain(prev); + if (!prev_chain) + break; + + /* No need for atomic operations since we hold the last + * reference to prev_chain. + */ + chain->prev = prev_chain->prev; + RCU_INIT_POINTER(prev_chain->prev, NULL); + dma_fence_put(prev); + } + dma_fence_put(prev); + + dma_fence_put(chain->fence); + dma_fence_free(fence); +} + + +static void dma_fence_chain_set_deadline(struct dma_fence *fence, + ktime_t deadline) +{ + dma_fence_chain_for_each(fence, fence) { + struct dma_fence *f = dma_fence_chain_contained(fence); + + dma_fence_set_deadline(f, deadline); + } +} + +const struct dma_fence_ops dma_fence_chain_ops = { + .get_driver_name = dma_fence_chain_get_driver_name, + .get_timeline_name = dma_fence_chain_get_timeline_name, + .enable_signaling = dma_fence_chain_enable_signaling, + .signaled = dma_fence_chain_signaled, + .release = dma_fence_chain_release, + .set_deadline = dma_fence_chain_set_deadline, +}; +EXPORT_SYMBOL(dma_fence_chain_ops); + +/** + * dma_fence_chain_init - initialize a fence chain + * @chain: the chain node to initialize + * @prev: the previous fence + * @fence: the current fence + * @seqno: the sequence number to use for the fence chain + * + * Initialize a new chain node and either start a new chain or add the node to + * the existing chain of the previous fence. + */ +void dma_fence_chain_init(struct dma_fence_chain *chain, + struct dma_fence *prev, + struct dma_fence *fence, + uint64_t seqno) +{ + struct dma_fence_chain *prev_chain = to_dma_fence_chain(prev); + uint64_t context; + + spin_lock_init(&chain->lock); + rcu_assign_pointer(chain->prev, prev); + chain->fence = fence; + chain->prev_seqno = 0; + + /* Try to reuse the context of the previous chain node. */ + if (prev_chain && __dma_fence_is_later(prev, seqno, prev->seqno)) { + context = prev->context; + chain->prev_seqno = prev->seqno; + } else { + context = dma_fence_context_alloc(1); + /* Make sure that we always have a valid sequence number. */ + if (prev_chain) + seqno = max(prev->seqno, seqno); + } + + dma_fence_init64(&chain->base, &dma_fence_chain_ops, &chain->lock, + context, seqno); + + /* + * Chaining dma_fence_chain container together is only allowed through + * the prev fence and not through the contained fence. + * + * The correct way of handling this is to flatten out the fence + * structure into a dma_fence_array by the caller instead. + */ + WARN_ON(dma_fence_is_chain(fence)); +} +EXPORT_SYMBOL(dma_fence_chain_init); diff --git a/drivers/dma-buf/dma-fence-unwrap.c b/drivers/dma-buf/dma-fence-unwrap.c new file mode 100644 index 000000000000..a495d8a6c2e3 --- /dev/null +++ b/drivers/dma-buf/dma-fence-unwrap.c @@ -0,0 +1,204 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * dma-fence-util: misc functions for dma_fence objects + * + * Copyright (C) 2022 Advanced Micro Devices, Inc. + * Authors: + * Christian König <christian.koenig@amd.com> + */ + +#include <linux/dma-fence.h> +#include <linux/dma-fence-array.h> +#include <linux/dma-fence-chain.h> +#include <linux/dma-fence-unwrap.h> +#include <linux/slab.h> +#include <linux/sort.h> + +/* Internal helper to start new array iteration, don't use directly */ +static struct dma_fence * +__dma_fence_unwrap_array(struct dma_fence_unwrap *cursor) +{ + cursor->array = dma_fence_chain_contained(cursor->chain); + cursor->index = 0; + return dma_fence_array_first(cursor->array); +} + +/** + * dma_fence_unwrap_first - return the first fence from fence containers + * @head: the entrypoint into the containers + * @cursor: current position inside the containers + * + * Unwraps potential dma_fence_chain/dma_fence_array containers and return the + * first fence. + */ +struct dma_fence *dma_fence_unwrap_first(struct dma_fence *head, + struct dma_fence_unwrap *cursor) +{ + cursor->chain = dma_fence_get(head); + return __dma_fence_unwrap_array(cursor); +} +EXPORT_SYMBOL_GPL(dma_fence_unwrap_first); + +/** + * dma_fence_unwrap_next - return the next fence from a fence containers + * @cursor: current position inside the containers + * + * Continue unwrapping the dma_fence_chain/dma_fence_array containers and return + * the next fence from them. + */ +struct dma_fence *dma_fence_unwrap_next(struct dma_fence_unwrap *cursor) +{ + struct dma_fence *tmp; + + ++cursor->index; + tmp = dma_fence_array_next(cursor->array, cursor->index); + if (tmp) + return tmp; + + cursor->chain = dma_fence_chain_walk(cursor->chain); + return __dma_fence_unwrap_array(cursor); +} +EXPORT_SYMBOL_GPL(dma_fence_unwrap_next); + + +static int fence_cmp(const void *_a, const void *_b) +{ + struct dma_fence *a = *(struct dma_fence **)_a; + struct dma_fence *b = *(struct dma_fence **)_b; + + if (a->context < b->context) + return -1; + else if (a->context > b->context) + return 1; + + if (dma_fence_is_later(b, a)) + return 1; + else if (dma_fence_is_later(a, b)) + return -1; + + return 0; +} + +/** + * dma_fence_dedup_array - Sort and deduplicate an array of dma_fence pointers + * @fences: Array of dma_fence pointers to be deduplicated + * @num_fences: Number of entries in the @fences array + * + * Sorts the input array by context, then removes duplicate + * fences with the same context, keeping only the most recent one. + * + * The array is modified in-place and unreferenced duplicate fences are released + * via dma_fence_put(). The function returns the new number of fences after + * deduplication. + * + * Return: Number of unique fences remaining in the array. + */ +int dma_fence_dedup_array(struct dma_fence **fences, int num_fences) +{ + int i, j; + + sort(fences, num_fences, sizeof(*fences), fence_cmp, NULL); + + /* + * Only keep the most recent fence for each context. + */ + j = 0; + for (i = 1; i < num_fences; i++) { + if (fences[i]->context == fences[j]->context) + dma_fence_put(fences[i]); + else + fences[++j] = fences[i]; + } + + return ++j; +} +EXPORT_SYMBOL_GPL(dma_fence_dedup_array); + +/* Implementation for the dma_fence_merge() marco, don't use directly */ +struct dma_fence *__dma_fence_unwrap_merge(unsigned int num_fences, + struct dma_fence **fences, + struct dma_fence_unwrap *iter) +{ + struct dma_fence *tmp, *unsignaled = NULL, **array; + struct dma_fence_array *result; + ktime_t timestamp; + int i, count; + + count = 0; + timestamp = ns_to_ktime(0); + for (i = 0; i < num_fences; ++i) { + dma_fence_unwrap_for_each(tmp, &iter[i], fences[i]) { + if (!dma_fence_is_signaled(tmp)) { + dma_fence_put(unsignaled); + unsignaled = dma_fence_get(tmp); + ++count; + } else { + ktime_t t = dma_fence_timestamp(tmp); + + if (ktime_after(t, timestamp)) + timestamp = t; + } + } + } + + /* + * If we couldn't find a pending fence just return a private signaled + * fence with the timestamp of the last signaled one. + * + * Or if there was a single unsignaled fence left we can return it + * directly and early since that is a major path on many workloads. + */ + if (count == 0) + return dma_fence_allocate_private_stub(timestamp); + else if (count == 1) + return unsignaled; + + dma_fence_put(unsignaled); + + array = kmalloc_array(count, sizeof(*array), GFP_KERNEL); + if (!array) + return NULL; + + count = 0; + for (i = 0; i < num_fences; ++i) { + dma_fence_unwrap_for_each(tmp, &iter[i], fences[i]) { + if (!dma_fence_is_signaled(tmp)) { + array[count++] = dma_fence_get(tmp); + } else { + ktime_t t = dma_fence_timestamp(tmp); + + if (ktime_after(t, timestamp)) + timestamp = t; + } + } + } + + if (count == 0 || count == 1) + goto return_fastpath; + + count = dma_fence_dedup_array(array, count); + + if (count > 1) { + result = dma_fence_array_create(count, array, + dma_fence_context_alloc(1), + 1, false); + if (!result) { + for (i = 0; i < count; i++) + dma_fence_put(array[i]); + tmp = NULL; + goto return_tmp; + } + return &result->base; + } + +return_fastpath: + if (count == 0) + tmp = dma_fence_allocate_private_stub(timestamp); + else + tmp = array[0]; + +return_tmp: + kfree(array); + return tmp; +} +EXPORT_SYMBOL_GPL(__dma_fence_unwrap_merge); diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 136ec04d683f..b4f5c8635276 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Fence mechanism for dma-buf and to allow for asynchronous dma access * @@ -7,15 +8,6 @@ * 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> @@ -23,12 +15,14 @@ #include <linux/atomic.h> #include <linux/dma-fence.h> #include <linux/sched/signal.h> +#include <linux/seq_file.h> #define CREATE_TRACE_POINTS #include <trace/events/dma_fence.h> EXPORT_TRACEPOINT_SYMBOL(dma_fence_emit); EXPORT_TRACEPOINT_SYMBOL(dma_fence_enable_signal); +EXPORT_TRACEPOINT_SYMBOL(dma_fence_signaled); static DEFINE_SPINLOCK(dma_fence_stub_lock); static struct dma_fence dma_fence_stub; @@ -67,10 +61,56 @@ 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. */ +/** + * DOC: fence cross-driver contract + * + * Since &dma_fence provide a cross driver contract, all drivers must follow the + * same rules: + * + * * Fences must complete in a reasonable time. Fences which represent kernels + * and shaders submitted by userspace, which could run forever, must be backed + * up by timeout and gpu hang recovery code. Minimally that code must prevent + * further command submission and force complete all in-flight fences, e.g. + * when the driver or hardware do not support gpu reset, or if the gpu reset + * failed for some reason. Ideally the driver supports gpu recovery which only + * affects the offending userspace context, and no other userspace + * submissions. + * + * * Drivers may have different ideas of what completion within a reasonable + * time means. Some hang recovery code uses a fixed timeout, others a mix + * between observing forward progress and increasingly strict timeouts. + * Drivers should not try to second guess timeout handling of fences from + * other drivers. + * + * * To ensure there's no deadlocks of dma_fence_wait() against other locks + * drivers should annotate all code required to reach dma_fence_signal(), + * which completes the fences, with dma_fence_begin_signalling() and + * dma_fence_end_signalling(). + * + * * Drivers are allowed to call dma_fence_wait() while holding dma_resv_lock(). + * This means any code required for fence completion cannot acquire a + * &dma_resv lock. Note that this also pulls in the entire established + * locking hierarchy around dma_resv_lock() and dma_resv_unlock(). + * + * * Drivers are allowed to call dma_fence_wait() from their &shrinker + * callbacks. This means any code required for fence completion cannot + * allocate memory with GFP_KERNEL. + * + * * Drivers are allowed to call dma_fence_wait() from their &mmu_notifier + * respectively &mmu_interval_notifier callbacks. This means any code required + * for fence completion cannot allocate memory with GFP_NOFS or GFP_NOIO. + * Only GFP_ATOMIC is permissible, which might fail. + * + * Note that only GPU drivers have a reasonable excuse for both requiring + * &mmu_interval_notifier and &shrinker callbacks at the same time as having to + * track asynchronous compute work using &dma_fence. No driver outside of + * drivers/gpu should ever call dma_fence_wait() in such contexts. + */ + static const char *dma_fence_stub_get_name(struct dma_fence *fence) { return "stub"; @@ -81,28 +121,60 @@ static const struct dma_fence_ops dma_fence_stub_ops = { .get_timeline_name = dma_fence_stub_get_name, }; +static int __init dma_fence_init_stub(void) +{ + dma_fence_init(&dma_fence_stub, &dma_fence_stub_ops, + &dma_fence_stub_lock, 0, 0); + + set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, + &dma_fence_stub.flags); + + dma_fence_signal(&dma_fence_stub); + return 0; +} +subsys_initcall(dma_fence_init_stub); + /** * dma_fence_get_stub - return a signaled fence * - * Return a stub fence which is already signaled. + * Return a stub fence which is already signaled. The fence's timestamp + * corresponds to the initialisation time of the linux kernel. */ struct dma_fence *dma_fence_get_stub(void) { - spin_lock(&dma_fence_stub_lock); - if (!dma_fence_stub.ops) { - dma_fence_init(&dma_fence_stub, - &dma_fence_stub_ops, - &dma_fence_stub_lock, - 0, 0); - dma_fence_signal_locked(&dma_fence_stub); - } - spin_unlock(&dma_fence_stub_lock); - return dma_fence_get(&dma_fence_stub); } EXPORT_SYMBOL(dma_fence_get_stub); /** + * dma_fence_allocate_private_stub - return a private, signaled fence + * @timestamp: timestamp when the fence was signaled + * + * Return a newly allocated and signaled stub fence. + */ +struct dma_fence *dma_fence_allocate_private_stub(ktime_t timestamp) +{ + struct dma_fence *fence; + + fence = kzalloc(sizeof(*fence), GFP_KERNEL); + if (fence == NULL) + return NULL; + + dma_fence_init(fence, + &dma_fence_stub_ops, + &dma_fence_stub_lock, + 0, 0); + + set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, + &fence->flags); + + dma_fence_signal_timestamp(fence, timestamp); + + return fence; +} +EXPORT_SYMBOL(dma_fence_allocate_private_stub); + +/** * dma_fence_context_alloc - allocate an array of fence contexts * @num: amount of contexts to allocate * @@ -113,55 +185,262 @@ EXPORT_SYMBOL(dma_fence_get_stub); u64 dma_fence_context_alloc(unsigned num) { WARN_ON(!num); - return atomic64_add_return(num, &dma_fence_context_counter) - num; + return atomic64_fetch_add(num, &dma_fence_context_counter); } EXPORT_SYMBOL(dma_fence_context_alloc); /** - * dma_fence_signal_locked - signal completion of a fence + * DOC: fence signalling annotation + * + * Proving correctness of all the kernel code around &dma_fence through code + * review and testing is tricky for a few reasons: + * + * * It is a cross-driver contract, and therefore all drivers must follow the + * same rules for lock nesting order, calling contexts for various functions + * and anything else significant for in-kernel interfaces. But it is also + * impossible to test all drivers in a single machine, hence brute-force N vs. + * N testing of all combinations is impossible. Even just limiting to the + * possible combinations is infeasible. + * + * * There is an enormous amount of driver code involved. For render drivers + * there's the tail of command submission, after fences are published, + * scheduler code, interrupt and workers to process job completion, + * and timeout, gpu reset and gpu hang recovery code. Plus for integration + * with core mm with have &mmu_notifier, respectively &mmu_interval_notifier, + * and &shrinker. For modesetting drivers there's the commit tail functions + * between when fences for an atomic modeset are published, and when the + * corresponding vblank completes, including any interrupt processing and + * related workers. Auditing all that code, across all drivers, is not + * feasible. + * + * * Due to how many other subsystems are involved and the locking hierarchies + * this pulls in there is extremely thin wiggle-room for driver-specific + * differences. &dma_fence interacts with almost all of the core memory + * handling through page fault handlers via &dma_resv, dma_resv_lock() and + * dma_resv_unlock(). On the other side it also interacts through all + * allocation sites through &mmu_notifier and &shrinker. + * + * Furthermore lockdep does not handle cross-release dependencies, which means + * any deadlocks between dma_fence_wait() and dma_fence_signal() can't be caught + * at runtime with some quick testing. The simplest example is one thread + * waiting on a &dma_fence while holding a lock:: + * + * lock(A); + * dma_fence_wait(B); + * unlock(A); + * + * while the other thread is stuck trying to acquire the same lock, which + * prevents it from signalling the fence the previous thread is stuck waiting + * on:: + * + * lock(A); + * unlock(A); + * dma_fence_signal(B); + * + * By manually annotating all code relevant to signalling a &dma_fence we can + * teach lockdep about these dependencies, which also helps with the validation + * headache since now lockdep can check all the rules for us:: + * + * cookie = dma_fence_begin_signalling(); + * lock(A); + * unlock(A); + * dma_fence_signal(B); + * dma_fence_end_signalling(cookie); + * + * For using dma_fence_begin_signalling() and dma_fence_end_signalling() to + * annotate critical sections the following rules need to be observed: + * + * * All code necessary to complete a &dma_fence must be annotated, from the + * point where a fence is accessible to other threads, to the point where + * dma_fence_signal() is called. Un-annotated code can contain deadlock issues, + * and due to the very strict rules and many corner cases it is infeasible to + * catch these just with review or normal stress testing. + * + * * &struct dma_resv deserves a special note, since the readers are only + * protected by rcu. This means the signalling critical section starts as soon + * as the new fences are installed, even before dma_resv_unlock() is called. + * + * * The only exception are fast paths and opportunistic signalling code, which + * calls dma_fence_signal() purely as an optimization, but is not required to + * guarantee completion of a &dma_fence. The usual example is a wait IOCTL + * which calls dma_fence_signal(), while the mandatory completion path goes + * through a hardware interrupt and possible job completion worker. + * + * * To aid composability of code, the annotations can be freely nested, as long + * as the overall locking hierarchy is consistent. The annotations also work + * both in interrupt and process context. Due to implementation details this + * requires that callers pass an opaque cookie from + * dma_fence_begin_signalling() to dma_fence_end_signalling(). + * + * * Validation against the cross driver contract is implemented by priming + * lockdep with the relevant hierarchy at boot-up. This means even just + * testing with a single device is enough to validate a driver, at least as + * far as deadlocks with dma_fence_wait() against dma_fence_signal() are + * concerned. + */ +#ifdef CONFIG_LOCKDEP +static struct lockdep_map dma_fence_lockdep_map = { + .name = "dma_fence_map" +}; + +/** + * dma_fence_begin_signalling - begin a critical DMA fence signalling section + * + * Drivers should use this to annotate the beginning of any code section + * required to eventually complete &dma_fence by calling dma_fence_signal(). + * + * The end of these critical sections are annotated with + * dma_fence_end_signalling(). + * + * Returns: + * + * Opaque cookie needed by the implementation, which needs to be passed to + * dma_fence_end_signalling(). + */ +bool dma_fence_begin_signalling(void) +{ + /* explicitly nesting ... */ + if (lock_is_held_type(&dma_fence_lockdep_map, 1)) + return true; + + /* rely on might_sleep check for soft/hardirq locks */ + if (in_atomic()) + return true; + + /* ... and non-recursive successful read_trylock */ + lock_acquire(&dma_fence_lockdep_map, 0, 1, 1, 1, NULL, _RET_IP_); + + return false; +} +EXPORT_SYMBOL(dma_fence_begin_signalling); + +/** + * dma_fence_end_signalling - end a critical DMA fence signalling section + * @cookie: opaque cookie from dma_fence_begin_signalling() + * + * Closes a critical section annotation opened by dma_fence_begin_signalling(). + */ +void dma_fence_end_signalling(bool cookie) +{ + if (cookie) + return; + + lock_release(&dma_fence_lockdep_map, _RET_IP_); +} +EXPORT_SYMBOL(dma_fence_end_signalling); + +void __dma_fence_might_wait(void) +{ + bool tmp; + + tmp = lock_is_held_type(&dma_fence_lockdep_map, 1); + if (tmp) + lock_release(&dma_fence_lockdep_map, _THIS_IP_); + lock_map_acquire(&dma_fence_lockdep_map); + lock_map_release(&dma_fence_lockdep_map); + if (tmp) + lock_acquire(&dma_fence_lockdep_map, 0, 1, 1, 1, NULL, _THIS_IP_); +} +#endif + + +/** + * dma_fence_signal_timestamp_locked - signal completion of a fence * @fence: the fence to signal + * @timestamp: fence signal timestamp in kernel's CLOCK_MONOTONIC time domain * * 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. + * only be effective the first time. Set the timestamp provided as the fence + * signal timestamp. * - * Unlike dma_fence_signal(), this function must be called with &dma_fence.lock - * held. + * Unlike dma_fence_signal_timestamp(), 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) +int dma_fence_signal_timestamp_locked(struct dma_fence *fence, + ktime_t timestamp) { 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 = timestamp; + 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 0; +} +EXPORT_SYMBOL(dma_fence_signal_timestamp_locked); + +/** + * dma_fence_signal_timestamp - signal completion of a fence + * @fence: the fence to signal + * @timestamp: fence signal timestamp in kernel's CLOCK_MONOTONIC time domain + * + * 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. Set the timestamp provided as the fence + * signal timestamp. + * + * Returns 0 on success and a negative error value when @fence has been + * signalled already. + */ +int dma_fence_signal_timestamp(struct dma_fence *fence, ktime_t timestamp) +{ + unsigned long flags; + int ret; + + if (WARN_ON(!fence)) + return -EINVAL; + + spin_lock_irqsave(fence->lock, flags); + ret = dma_fence_signal_timestamp_locked(fence, timestamp); + spin_unlock_irqrestore(fence->lock, flags); + return ret; } +EXPORT_SYMBOL(dma_fence_signal_timestamp); + +/** + * 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) +{ + return dma_fence_signal_timestamp_locked(fence, ktime_get()); +} EXPORT_SYMBOL(dma_fence_signal_locked); /** @@ -180,28 +459,21 @@ EXPORT_SYMBOL(dma_fence_signal_locked); int dma_fence_signal(struct dma_fence *fence) { unsigned long flags; + int ret; + bool tmp; - if (!fence) + if (WARN_ON(!fence)) return -EINVAL; - if (test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) - return -EINVAL; + tmp = dma_fence_begin_signalling(); - fence->timestamp = ktime_get(); - set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags); - trace_dma_fence_signaled(fence); + spin_lock_irqsave(fence->lock, flags); + ret = dma_fence_signal_timestamp_locked(fence, ktime_get()); + spin_unlock_irqrestore(fence->lock, flags); - if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags)) { - struct dma_fence_cb *cur, *tmp; + dma_fence_end_signalling(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; + return ret; } EXPORT_SYMBOL(dma_fence_signal); @@ -231,18 +503,32 @@ dma_fence_wait_timeout(struct dma_fence *fence, bool intr, signed long timeout) if (WARN_ON(timeout < 0)) return -EINVAL; - trace_dma_fence_wait_start(fence); + might_sleep(); + + __dma_fence_might_wait(); + + dma_fence_enable_sw_signaling(fence); + + if (trace_dma_fence_wait_start_enabled()) { + rcu_read_lock(); + trace_dma_fence_wait_start(fence); + rcu_read_unlock(); + } 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); + if (trace_dma_fence_wait_end_enabled()) { + rcu_read_lock(); + trace_dma_fence_wait_end(fence); + rcu_read_unlock(); + } return ret; } EXPORT_SYMBOL(dma_fence_wait_timeout); /** - * dma_fence_release - default relese function for fences + * dma_fence_release - default release function for fences * @kref: &dma_fence.recfount * * This is the default release functions for &dma_fence. Drivers shouldn't call @@ -253,10 +539,37 @@ void dma_fence_release(struct kref *kref) struct dma_fence *fence = container_of(kref, struct dma_fence, refcount); + rcu_read_lock(); trace_dma_fence_destroy(fence); - /* Failed to signal before release, could be a refcounting issue */ - WARN_ON(!list_empty(&fence->cb_list)); + if (!list_empty(&fence->cb_list) && + !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { + const char __rcu *timeline; + const char __rcu *driver; + unsigned long flags; + + driver = dma_fence_driver_name(fence); + timeline = dma_fence_timeline_name(fence); + + WARN(1, + "Fence %s:%s:%llx:%llx released with pending signals!\n", + rcu_dereference(driver), rcu_dereference(timeline), + fence->context, fence->seqno); + + /* + * Failed to signal before release, likely a refcounting issue. + * + * This should never happen, but if it does make sure that we + * don't leave chains dangling. We set the error flag first + * so that the callbacks know this signal is due to an error. + */ + spin_lock_irqsave(fence->lock, flags); + fence->error = -EDEADLK; + dma_fence_signal_locked(fence); + spin_unlock_irqrestore(fence->lock, flags); + } + + rcu_read_unlock(); if (fence->ops->release) fence->ops->release(fence); @@ -278,6 +591,30 @@ 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 @@ -290,19 +627,9 @@ 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); - - 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); @@ -313,20 +640,17 @@ EXPORT_SYMBOL(dma_fence_enable_sw_signaling); * @cb: the callback to register * @func: the function to call * + * Add a software callback to the fence. The caller should keep a reference to + * the fence. + * * @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 + * 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. + * Note that the callback can be called from an atomic context or irq context. * * Returns 0 in case of success, -ENOENT if the fence is already signaled * and -EINVAL in case of error. @@ -336,7 +660,6 @@ 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; @@ -348,25 +671,14 @@ 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; @@ -466,31 +778,15 @@ 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; spin_lock_irqsave(fence->lock, flags); - if (intr && signal_pending(current)) { - ret = -ERESTARTSYS; - 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)) 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 (intr && signal_pending(current)) { + ret = -ERESTARTSYS; + goto out; } if (!timeout) { @@ -633,6 +929,114 @@ err_free_cb: EXPORT_SYMBOL(dma_fence_wait_any_timeout); /** + * DOC: deadline hints + * + * In an ideal world, it would be possible to pipeline a workload sufficiently + * that a utilization based device frequency governor could arrive at a minimum + * frequency that meets the requirements of the use-case, in order to minimize + * power consumption. But in the real world there are many workloads which + * defy this ideal. For example, but not limited to: + * + * * Workloads that ping-pong between device and CPU, with alternating periods + * of CPU waiting for device, and device waiting on CPU. This can result in + * devfreq and cpufreq seeing idle time in their respective domains and in + * result reduce frequency. + * + * * Workloads that interact with a periodic time based deadline, such as double + * buffered GPU rendering vs vblank sync'd page flipping. In this scenario, + * missing a vblank deadline results in an *increase* in idle time on the GPU + * (since it has to wait an additional vblank period), sending a signal to + * the GPU's devfreq to reduce frequency, when in fact the opposite is what is + * needed. + * + * To this end, deadline hint(s) can be set on a &dma_fence via &dma_fence_set_deadline + * (or indirectly via userspace facing ioctls like &sync_set_deadline). + * The deadline hint provides a way for the waiting driver, or userspace, to + * convey an appropriate sense of urgency to the signaling driver. + * + * A deadline hint is given in absolute ktime (CLOCK_MONOTONIC for userspace + * facing APIs). The time could either be some point in the future (such as + * the vblank based deadline for page-flipping, or the start of a compositor's + * composition cycle), or the current time to indicate an immediate deadline + * hint (Ie. forward progress cannot be made until this fence is signaled). + * + * Multiple deadlines may be set on a given fence, even in parallel. See the + * documentation for &dma_fence_ops.set_deadline. + * + * The deadline hint is just that, a hint. The driver that created the fence + * may react by increasing frequency, making different scheduling choices, etc. + * Or doing nothing at all. + */ + +/** + * dma_fence_set_deadline - set desired fence-wait deadline hint + * @fence: the fence that is to be waited on + * @deadline: the time by which the waiter hopes for the fence to be + * signaled + * + * Give the fence signaler a hint about an upcoming deadline, such as + * vblank, by which point the waiter would prefer the fence to be + * signaled by. This is intended to give feedback to the fence signaler + * to aid in power management decisions, such as boosting GPU frequency + * if a periodic vblank deadline is approaching but the fence is not + * yet signaled.. + */ +void dma_fence_set_deadline(struct dma_fence *fence, ktime_t deadline) +{ + if (fence->ops->set_deadline && !dma_fence_is_signaled(fence)) + fence->ops->set_deadline(fence, deadline); +} +EXPORT_SYMBOL(dma_fence_set_deadline); + +/** + * dma_fence_describe - Dump fence description into seq_file + * @fence: the fence to describe + * @seq: the seq_file to put the textual description into + * + * Dump a textual description of the fence and it's state into the seq_file. + */ +void dma_fence_describe(struct dma_fence *fence, struct seq_file *seq) +{ + const char __rcu *timeline = ""; + const char __rcu *driver = ""; + const char *signaled = ""; + + rcu_read_lock(); + + if (!dma_fence_is_signaled(fence)) { + timeline = dma_fence_timeline_name(fence); + driver = dma_fence_driver_name(fence); + signaled = "un"; + } + + seq_printf(seq, "%llu:%llu %s %s %ssignalled\n", + fence->context, fence->seqno, timeline, driver, + signaled); + + rcu_read_unlock(); +} +EXPORT_SYMBOL(dma_fence_describe); + +static void +__dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops, + spinlock_t *lock, u64 context, u64 seqno, unsigned long flags) +{ + 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 = flags; + fence->error = 0; + + trace_dma_fence_init(fence); +} + +/** * dma_fence_init - Initialize a custom fence. * @fence: the fence to initialize * @ops: the dma_fence_ops for operations on this fence @@ -649,20 +1053,96 @@ EXPORT_SYMBOL(dma_fence_wait_any_timeout); */ void dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops, - spinlock_t *lock, u64 context, unsigned seqno) + spinlock_t *lock, u64 context, u64 seqno) { - BUG_ON(!lock); - BUG_ON(!ops || !ops->get_driver_name || !ops->get_timeline_name); + __dma_fence_init(fence, ops, lock, context, seqno, 0UL); +} +EXPORT_SYMBOL(dma_fence_init); - 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; +/** + * dma_fence_init64 - Initialize a custom fence with 64-bit seqno support. + * @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_init64(struct dma_fence *fence, const struct dma_fence_ops *ops, + spinlock_t *lock, u64 context, u64 seqno) +{ + __dma_fence_init(fence, ops, lock, context, seqno, + BIT(DMA_FENCE_FLAG_SEQNO64_BIT)); +} +EXPORT_SYMBOL(dma_fence_init64); - trace_dma_fence_init(fence); +/** + * dma_fence_driver_name - Access the driver name + * @fence: the fence to query + * + * Returns a driver name backing the dma-fence implementation. + * + * IMPORTANT CONSIDERATION: + * Dma-fence contract stipulates that access to driver provided data (data not + * directly embedded into the object itself), such as the &dma_fence.lock and + * memory potentially accessed by the &dma_fence.ops functions, is forbidden + * after the fence has been signalled. Drivers are allowed to free that data, + * and some do. + * + * To allow safe access drivers are mandated to guarantee a RCU grace period + * between signalling the fence and freeing said data. + * + * As such access to the driver name is only valid inside a RCU locked section. + * The pointer MUST be both queried and USED ONLY WITHIN a SINGLE block guarded + * by the &rcu_read_lock and &rcu_read_unlock pair. + */ +const char __rcu *dma_fence_driver_name(struct dma_fence *fence) +{ + RCU_LOCKDEP_WARN(!rcu_read_lock_held(), + "RCU protection is required for safe access to returned string"); + + if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return fence->ops->get_driver_name(fence); + else + return "detached-driver"; } -EXPORT_SYMBOL(dma_fence_init); +EXPORT_SYMBOL(dma_fence_driver_name); + +/** + * dma_fence_timeline_name - Access the timeline name + * @fence: the fence to query + * + * Returns a timeline name provided by the dma-fence implementation. + * + * IMPORTANT CONSIDERATION: + * Dma-fence contract stipulates that access to driver provided data (data not + * directly embedded into the object itself), such as the &dma_fence.lock and + * memory potentially accessed by the &dma_fence.ops functions, is forbidden + * after the fence has been signalled. Drivers are allowed to free that data, + * and some do. + * + * To allow safe access drivers are mandated to guarantee a RCU grace period + * between signalling the fence and freeing said data. + * + * As such access to the driver name is only valid inside a RCU locked section. + * The pointer MUST be both queried and USED ONLY WITHIN a SINGLE block guarded + * by the &rcu_read_lock and &rcu_read_unlock pair. + */ +const char __rcu *dma_fence_timeline_name(struct dma_fence *fence) +{ + RCU_LOCKDEP_WARN(!rcu_read_lock_held(), + "RCU protection is required for safe access to returned string"); + + if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return fence->ops->get_timeline_name(fence); + else + return "signaled-timeline"; +} +EXPORT_SYMBOL(dma_fence_timeline_name); diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c new file mode 100644 index 000000000000..8ab49924f8b7 --- /dev/null +++ b/drivers/dma-buf/dma-heap.c @@ -0,0 +1,333 @@ +// 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/device.h> +#include <linux/dma-buf.h> +#include <linux/dma-heap.h> +#include <linux/err.h> +#include <linux/export.h> +#include <linux/list.h> +#include <linux/nospec.h> +#include <linux/syscalls.h> +#include <linux/uaccess.h> +#include <linux/xarray.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 + * @priv: private data 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, + u32 fd_flags, + u64 heap_flags) +{ + struct dma_buf *dmabuf; + int fd; + + /* + * Allocations from all heaps have to begin + * and end on page boundaries. + */ + len = PAGE_ALIGN(len); + if (!len) + return -EINVAL; + + dmabuf = heap->ops->allocate(heap, len, fd_flags, heap_flags); + if (IS_ERR(dmabuf)) + return PTR_ERR(dmabuf); + + fd = dma_buf_fd(dmabuf, fd_flags); + if (fd < 0) { + dma_buf_put(dmabuf); + /* just return, as put will call release and that will free */ + } + return fd; +} + +static int dma_heap_open(struct inode *inode, struct file *file) +{ + struct dma_heap *heap; + + heap = xa_load(&dma_heap_minors, iminor(inode)); + if (!heap) { + pr_err("dma_heap: minor %d unknown.\n", iminor(inode)); + return -ENODEV; + } + + /* instance data as context */ + file->private_data = heap; + nonseekable_open(inode, file); + + return 0; +} + +static long dma_heap_ioctl_allocate(struct file *file, void *data) +{ + struct dma_heap_allocation_data *heap_allocation = data; + struct dma_heap *heap = file->private_data; + int fd; + + if (heap_allocation->fd) + return -EINVAL; + + if (heap_allocation->fd_flags & ~DMA_HEAP_VALID_FD_FLAGS) + return -EINVAL; + + if (heap_allocation->heap_flags & ~DMA_HEAP_VALID_HEAP_FLAGS) + return -EINVAL; + + fd = dma_heap_buffer_alloc(heap, heap_allocation->len, + heap_allocation->fd_flags, + heap_allocation->heap_flags); + if (fd < 0) + return fd; + + heap_allocation->fd = fd; + + return 0; +} + +static unsigned int dma_heap_ioctl_cmds[] = { + DMA_HEAP_IOCTL_ALLOC, +}; + +static long dma_heap_ioctl(struct file *file, unsigned int ucmd, + unsigned long arg) +{ + char stack_kdata[128]; + char *kdata = stack_kdata; + unsigned int kcmd; + unsigned int in_size, out_size, drv_size, ksize; + int nr = _IOC_NR(ucmd); + int ret = 0; + + if (nr >= ARRAY_SIZE(dma_heap_ioctl_cmds)) + return -EINVAL; + + nr = array_index_nospec(nr, ARRAY_SIZE(dma_heap_ioctl_cmds)); + /* Get the kernel ioctl cmd that matches */ + kcmd = dma_heap_ioctl_cmds[nr]; + + /* Figure out the delta between user cmd size and kernel cmd size */ + drv_size = _IOC_SIZE(kcmd); + out_size = _IOC_SIZE(ucmd); + in_size = out_size; + if ((ucmd & kcmd & IOC_IN) == 0) + in_size = 0; + if ((ucmd & kcmd & IOC_OUT) == 0) + out_size = 0; + ksize = max(max(in_size, out_size), drv_size); + + /* If necessary, allocate buffer for ioctl argument */ + if (ksize > sizeof(stack_kdata)) { + kdata = kmalloc(ksize, GFP_KERNEL); + if (!kdata) + return -ENOMEM; + } + + if (copy_from_user(kdata, (void __user *)arg, in_size) != 0) { + ret = -EFAULT; + goto err; + } + + /* zero out any difference between the kernel/user structure size */ + if (ksize > in_size) + memset(kdata + in_size, 0, ksize - in_size); + + switch (kcmd) { + case DMA_HEAP_IOCTL_ALLOC: + ret = dma_heap_ioctl_allocate(file, kdata); + break; + default: + ret = -ENOTTY; + goto err; + } + + if (copy_to_user((void __user *)arg, kdata, out_size) != 0) + ret = -EFAULT; +err: + if (kdata != stack_kdata) + kfree(kdata); + return ret; +} + +static const struct file_operations dma_heap_fops = { + .owner = THIS_MODULE, + .open = dma_heap_open, + .unlocked_ioctl = dma_heap_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = dma_heap_ioctl, +#endif +}; + +/** + * dma_heap_get_drvdata - get per-heap driver data + * @heap: DMA-Heap to retrieve private data for + * + * Returns: + * The per-heap data for the heap. + */ +void *dma_heap_get_drvdata(struct dma_heap *heap) +{ + return heap->priv; +} +EXPORT_SYMBOL_NS_GPL(dma_heap_get_drvdata, "DMA_BUF_HEAP"); + +/** + * dma_heap_get_name - get heap name + * @heap: DMA-Heap to retrieve the name of + * + * Returns: + * The char* for the heap name. + */ +const char *dma_heap_get_name(struct dma_heap *heap) +{ + return heap->name; +} +EXPORT_SYMBOL_NS_GPL(dma_heap_get_name, "DMA_BUF_HEAP"); + +/** + * dma_heap_add - adds a heap to dmabuf heaps + * @exp_info: information needed to register this heap + */ +struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) +{ + struct dma_heap *heap, *h, *err_ret; + struct device *dev_ret; + unsigned int minor; + int ret; + + if (!exp_info->name || !strcmp(exp_info->name, "")) { + pr_err("dma_heap: Cannot add heap without a name\n"); + return ERR_PTR(-EINVAL); + } + + if (!exp_info->ops || !exp_info->ops->allocate) { + pr_err("dma_heap: Cannot add heap with invalid ops struct\n"); + return ERR_PTR(-EINVAL); + } + + heap = kzalloc(sizeof(*heap), GFP_KERNEL); + if (!heap) + return ERR_PTR(-ENOMEM); + + heap->name = exp_info->name; + heap->ops = exp_info->ops; + heap->priv = exp_info->priv; + + /* Find unused minor number */ + ret = xa_alloc(&dma_heap_minors, &minor, heap, + XA_LIMIT(0, NUM_HEAP_MINORS - 1), GFP_KERNEL); + if (ret < 0) { + pr_err("dma_heap: Unable to get minor number for heap\n"); + err_ret = ERR_PTR(ret); + goto err0; + } + + /* Create device */ + heap->heap_devt = MKDEV(MAJOR(dma_heap_devt), minor); + + cdev_init(&heap->heap_cdev, &dma_heap_fops); + ret = cdev_add(&heap->heap_cdev, heap->heap_devt, 1); + if (ret < 0) { + pr_err("dma_heap: Unable to add char device\n"); + err_ret = ERR_PTR(ret); + goto err1; + } + + dev_ret = device_create(dma_heap_class, + NULL, + heap->heap_devt, + NULL, + heap->name); + if (IS_ERR(dev_ret)) { + pr_err("dma_heap: Unable to create device\n"); + err_ret = ERR_CAST(dev_ret); + goto err2; + } + + mutex_lock(&heap_list_lock); + /* check the name is unique */ + list_for_each_entry(h, &heap_list, list) { + if (!strcmp(h->name, exp_info->name)) { + mutex_unlock(&heap_list_lock); + pr_err("dma_heap: Already registered heap named %s\n", + exp_info->name); + err_ret = ERR_PTR(-EINVAL); + goto err3; + } + } + + /* Add heap to the list */ + list_add(&heap->list, &heap_list); + mutex_unlock(&heap_list_lock); + + return heap; + +err3: + device_destroy(dma_heap_class, heap->heap_devt); +err2: + cdev_del(&heap->heap_cdev); +err1: + xa_erase(&dma_heap_minors, minor); +err0: + kfree(heap); + return err_ret; +} +EXPORT_SYMBOL_NS_GPL(dma_heap_add, "DMA_BUF_HEAP"); + +static char *dma_heap_devnode(const 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(DEVNAME); + if (IS_ERR(dma_heap_class)) { + unregister_chrdev_region(dma_heap_devt, NUM_HEAP_MINORS); + return PTR_ERR(dma_heap_class); + } + dma_heap_class->devnode = dma_heap_devnode; + + return 0; +} +subsys_initcall(dma_heap_init); diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c new file mode 100644 index 000000000000..bea3e9858aca --- /dev/null +++ b/drivers/dma-buf/dma-resv.c @@ -0,0 +1,816 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright (C) 2012-2014 Canonical Ltd (Maarten Lankhorst) + * + * Based on bo.c which bears the following copyright notice, + * but is dual licensed: + * + * Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA + * All Rights Reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + **************************************************************************/ +/* + * Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com> + */ + +#include <linux/dma-resv.h> +#include <linux/dma-fence-array.h> +#include <linux/export.h> +#include <linux/mm.h> +#include <linux/sched/mm.h> +#include <linux/mmu_notifier.h> +#include <linux/seq_file.h> + +/** + * DOC: Reservation Object Overview + * + * The reservation object provides a mechanism to manage a container of + * dma_fence object associated with a resource. A reservation object + * can have any number of fences attaches to it. Each fence carries an usage + * parameter determining how the operation represented by the fence is using the + * resource. The RCU mechanism is used to protect read access to fences from + * locked write-side updates. + * + * See struct dma_resv for more details. + */ + +DEFINE_WD_CLASS(reservation_ww_class); +EXPORT_SYMBOL(reservation_ww_class); + +/* Mask for the lower fence pointer bits */ +#define DMA_RESV_LIST_MASK 0x3 + +struct dma_resv_list { + struct rcu_head rcu; + u32 num_fences, max_fences; + struct dma_fence __rcu *table[]; +}; + +/* Extract the fence and usage flags from an RCU protected entry in the list. */ +static void dma_resv_list_entry(struct dma_resv_list *list, unsigned int index, + struct dma_resv *resv, struct dma_fence **fence, + enum dma_resv_usage *usage) +{ + long tmp; + + tmp = (long)rcu_dereference_check(list->table[index], + resv ? dma_resv_held(resv) : true); + *fence = (struct dma_fence *)(tmp & ~DMA_RESV_LIST_MASK); + if (usage) + *usage = tmp & DMA_RESV_LIST_MASK; +} + +/* Set the fence and usage flags at the specific index in the list. */ +static void dma_resv_list_set(struct dma_resv_list *list, + unsigned int index, + struct dma_fence *fence, + enum dma_resv_usage usage) +{ + long tmp = ((long)fence) | usage; + + RCU_INIT_POINTER(list->table[index], (struct dma_fence *)tmp); +} + +/* + * Allocate a new dma_resv_list and make sure to correctly initialize + * max_fences. + */ +static struct dma_resv_list *dma_resv_list_alloc(unsigned int max_fences) +{ + struct dma_resv_list *list; + size_t size; + + /* Round up to the next kmalloc bucket size. */ + size = kmalloc_size_roundup(struct_size(list, table, max_fences)); + + list = kmalloc(size, GFP_KERNEL); + if (!list) + return NULL; + + /* Given the resulting bucket size, recalculated max_fences. */ + list->max_fences = (size - offsetof(typeof(*list), table)) / + sizeof(*list->table); + + return list; +} + +/* 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->num_fences; ++i) { + struct dma_fence *fence; + + dma_resv_list_entry(list, i, NULL, &fence, NULL); + dma_fence_put(fence); + } + kfree_rcu(list, rcu); +} + +/** + * 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); + + RCU_INIT_POINTER(obj->fences, 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) +{ + /* + * This object should be dead and all references must have + * been released to it, so no need to be protected with rcu. + */ + dma_resv_list_free(rcu_dereference_protected(obj->fences, true)); + ww_mutex_destroy(&obj->lock); +} +EXPORT_SYMBOL(dma_resv_fini); + +/* Dereference the fences while ensuring RCU rules */ +static inline struct dma_resv_list *dma_resv_fences_list(struct dma_resv *obj) +{ + return rcu_dereference_check(obj->fences, dma_resv_held(obj)); +} + +/** + * dma_resv_reserve_fences - Reserve space to add fences to a dma_resv object. + * @obj: reservation object + * @num_fences: number of fences we want to add + * + * Should be called before dma_resv_add_fence(). Must be called with @obj + * locked through dma_resv_lock(). + * + * Note that the preallocated slots need to be re-reserved if @obj is unlocked + * at any time before calling dma_resv_add_fence(). This is validated when + * CONFIG_DEBUG_MUTEXES is enabled. + * + * RETURNS + * Zero for success, or -errno + */ +int dma_resv_reserve_fences(struct dma_resv *obj, unsigned int num_fences) +{ + struct dma_resv_list *old, *new; + unsigned int i, j, k, max; + + dma_resv_assert_held(obj); + + /* Driver and component code should never call this function with + * num_fences=0. If they do it usually points to bugs when calculating + * the number of needed fences dynamically. + */ + if (WARN_ON(!num_fences)) + return -EINVAL; + + old = dma_resv_fences_list(obj); + if (old && old->max_fences) { + if ((old->num_fences + num_fences) <= old->max_fences) + return 0; + max = max(old->num_fences + num_fences, old->max_fences * 2); + } else { + max = max(4ul, roundup_pow_of_two(num_fences)); + } + + new = dma_resv_list_alloc(max); + if (!new) + return -ENOMEM; + + /* + * no need to bump fence refcounts, rcu_read access + * requires the use of kref_get_unless_zero, and the + * references from the old struct are carried over to + * the new. + */ + for (i = 0, j = 0, k = max; i < (old ? old->num_fences : 0); ++i) { + enum dma_resv_usage usage; + struct dma_fence *fence; + + dma_resv_list_entry(old, i, obj, &fence, &usage); + if (dma_fence_is_signaled(fence)) + RCU_INIT_POINTER(new->table[--k], fence); + else + dma_resv_list_set(new, j++, fence, usage); + } + new->num_fences = j; + + /* + * We are not changing the effective set of fences here so can + * merely update the pointer to the new array; both existing + * readers and new readers will see exactly the same set of + * active (unsignaled) fences. Individual fences and the + * old array are protected by RCU and so will not vanish under + * the gaze of the rcu_read_lock() readers. + */ + rcu_assign_pointer(obj->fences, new); + + if (!old) + return 0; + + /* Drop the references to the signaled fences */ + for (i = k; i < max; ++i) { + struct dma_fence *fence; + + fence = rcu_dereference_protected(new->table[i], + dma_resv_held(obj)); + dma_fence_put(fence); + } + kfree_rcu(old, rcu); + + return 0; +} +EXPORT_SYMBOL(dma_resv_reserve_fences); + +#ifdef CONFIG_DEBUG_MUTEXES +/** + * dma_resv_reset_max_fences - reset fences for debugging + * @obj: the dma_resv object to reset + * + * Reset the number of pre-reserved fence slots to test that drivers do + * correct slot allocation using dma_resv_reserve_fences(). See also + * &dma_resv_list.max_fences. + */ +void dma_resv_reset_max_fences(struct dma_resv *obj) +{ + struct dma_resv_list *fences = dma_resv_fences_list(obj); + + dma_resv_assert_held(obj); + + /* Test fence slot reservation */ + if (fences) + fences->max_fences = fences->num_fences; +} +EXPORT_SYMBOL(dma_resv_reset_max_fences); +#endif + +/** + * dma_resv_add_fence - Add a fence to the dma_resv obj + * @obj: the reservation object + * @fence: the fence to add + * @usage: how the fence is used, see enum dma_resv_usage + * + * Add a fence to a slot, @obj must be locked with dma_resv_lock(), and + * dma_resv_reserve_fences() has been called. + * + * See also &dma_resv.fence for a discussion of the semantics. + */ +void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence, + enum dma_resv_usage usage) +{ + struct dma_resv_list *fobj; + struct dma_fence *old; + unsigned int i, count; + + dma_fence_get(fence); + + dma_resv_assert_held(obj); + + /* Drivers should not add containers here, instead add each fence + * individually. + */ + WARN_ON(dma_fence_is_container(fence)); + + fobj = dma_resv_fences_list(obj); + count = fobj->num_fences; + + for (i = 0; i < count; ++i) { + enum dma_resv_usage old_usage; + + dma_resv_list_entry(fobj, i, obj, &old, &old_usage); + if ((old->context == fence->context && old_usage >= usage && + dma_fence_is_later_or_same(fence, old)) || + dma_fence_is_signaled(old)) { + dma_resv_list_set(fobj, i, fence, usage); + dma_fence_put(old); + return; + } + } + + BUG_ON(fobj->num_fences >= fobj->max_fences); + count++; + + dma_resv_list_set(fobj, i, fence, usage); + /* fence update must be visible before we extend the num_fences */ + smp_wmb(); + fobj->num_fences = count; +} +EXPORT_SYMBOL(dma_resv_add_fence); + +/** + * dma_resv_replace_fences - replace fences in the dma_resv obj + * @obj: the reservation object + * @context: the context of the fences to replace + * @replacement: the new fence to use instead + * @usage: how the new fence is used, see enum dma_resv_usage + * + * Replace fences with a specified context with a new fence. Only valid if the + * operation represented by the original fence has no longer access to the + * resources represented by the dma_resv object when the new fence completes. + * + * And example for using this is replacing a preemption fence with a page table + * update fence which makes the resource inaccessible. + */ +void dma_resv_replace_fences(struct dma_resv *obj, uint64_t context, + struct dma_fence *replacement, + enum dma_resv_usage usage) +{ + struct dma_resv_list *list; + unsigned int i; + + dma_resv_assert_held(obj); + + list = dma_resv_fences_list(obj); + for (i = 0; list && i < list->num_fences; ++i) { + struct dma_fence *old; + + dma_resv_list_entry(list, i, obj, &old, NULL); + if (old->context != context) + continue; + + dma_resv_list_set(list, i, dma_fence_get(replacement), usage); + dma_fence_put(old); + } +} +EXPORT_SYMBOL(dma_resv_replace_fences); + +/* Restart the unlocked iteration by initializing the cursor object. */ +static void dma_resv_iter_restart_unlocked(struct dma_resv_iter *cursor) +{ + cursor->index = 0; + cursor->num_fences = 0; + cursor->fences = dma_resv_fences_list(cursor->obj); + if (cursor->fences) + cursor->num_fences = cursor->fences->num_fences; + cursor->is_restarted = true; +} + +/* Walk to the next not signaled fence and grab a reference to it */ +static void dma_resv_iter_walk_unlocked(struct dma_resv_iter *cursor) +{ + if (!cursor->fences) + return; + + do { + /* Drop the reference from the previous round */ + dma_fence_put(cursor->fence); + + if (cursor->index >= cursor->num_fences) { + cursor->fence = NULL; + break; + + } + + dma_resv_list_entry(cursor->fences, cursor->index++, + cursor->obj, &cursor->fence, + &cursor->fence_usage); + cursor->fence = dma_fence_get_rcu(cursor->fence); + if (!cursor->fence) { + dma_resv_iter_restart_unlocked(cursor); + continue; + } + + if (!dma_fence_is_signaled(cursor->fence) && + cursor->usage >= cursor->fence_usage) + break; + } while (true); +} + +/** + * dma_resv_iter_first_unlocked - first fence in an unlocked dma_resv obj. + * @cursor: the cursor with the current position + * + * Subsequent fences are iterated with dma_resv_iter_next_unlocked(). + * + * Beware that the iterator can be restarted. Code which accumulates statistics + * or similar needs to check for this with dma_resv_iter_is_restarted(). For + * this reason prefer the locked dma_resv_iter_first() whenever possible. + * + * Returns the first fence from an unlocked dma_resv obj. + */ +struct dma_fence *dma_resv_iter_first_unlocked(struct dma_resv_iter *cursor) +{ + rcu_read_lock(); + do { + dma_resv_iter_restart_unlocked(cursor); + dma_resv_iter_walk_unlocked(cursor); + } while (dma_resv_fences_list(cursor->obj) != cursor->fences); + rcu_read_unlock(); + + return cursor->fence; +} +EXPORT_SYMBOL(dma_resv_iter_first_unlocked); + +/** + * dma_resv_iter_next_unlocked - next fence in an unlocked dma_resv obj. + * @cursor: the cursor with the current position + * + * Beware that the iterator can be restarted. Code which accumulates statistics + * or similar needs to check for this with dma_resv_iter_is_restarted(). For + * this reason prefer the locked dma_resv_iter_next() whenever possible. + * + * Returns the next fence from an unlocked dma_resv obj. + */ +struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor) +{ + bool restart; + + rcu_read_lock(); + cursor->is_restarted = false; + restart = dma_resv_fences_list(cursor->obj) != cursor->fences; + do { + if (restart) + dma_resv_iter_restart_unlocked(cursor); + dma_resv_iter_walk_unlocked(cursor); + restart = true; + } while (dma_resv_fences_list(cursor->obj) != cursor->fences); + rcu_read_unlock(); + + return cursor->fence; +} +EXPORT_SYMBOL(dma_resv_iter_next_unlocked); + +/** + * dma_resv_iter_first - first fence from a locked dma_resv object + * @cursor: cursor to record the current position + * + * Subsequent fences are iterated with dma_resv_iter_next_unlocked(). + * + * Return the first fence in the dma_resv object while holding the + * &dma_resv.lock. + */ +struct dma_fence *dma_resv_iter_first(struct dma_resv_iter *cursor) +{ + struct dma_fence *fence; + + dma_resv_assert_held(cursor->obj); + + cursor->index = 0; + cursor->fences = dma_resv_fences_list(cursor->obj); + + fence = dma_resv_iter_next(cursor); + cursor->is_restarted = true; + return fence; +} +EXPORT_SYMBOL_GPL(dma_resv_iter_first); + +/** + * dma_resv_iter_next - next fence from a locked dma_resv object + * @cursor: cursor to record the current position + * + * Return the next fences from the dma_resv object while holding the + * &dma_resv.lock. + */ +struct dma_fence *dma_resv_iter_next(struct dma_resv_iter *cursor) +{ + struct dma_fence *fence; + + dma_resv_assert_held(cursor->obj); + + cursor->is_restarted = false; + + do { + if (!cursor->fences || + cursor->index >= cursor->fences->num_fences) + return NULL; + + dma_resv_list_entry(cursor->fences, cursor->index++, + cursor->obj, &fence, &cursor->fence_usage); + } while (cursor->fence_usage > cursor->usage); + + return fence; +} +EXPORT_SYMBOL_GPL(dma_resv_iter_next); + +/** + * dma_resv_copy_fences - Copy all fences from src to dst. + * @dst: the destination reservation object + * @src: the source reservation object + * + * Copy all fences from src to dst. dst-lock must be held. + */ +int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src) +{ + struct dma_resv_iter cursor; + struct dma_resv_list *list; + struct dma_fence *f; + + dma_resv_assert_held(dst); + + list = NULL; + + dma_resv_iter_begin(&cursor, src, DMA_RESV_USAGE_BOOKKEEP); + dma_resv_for_each_fence_unlocked(&cursor, f) { + + if (dma_resv_iter_is_restarted(&cursor)) { + dma_resv_list_free(list); + + list = dma_resv_list_alloc(cursor.num_fences); + if (!list) { + dma_resv_iter_end(&cursor); + return -ENOMEM; + } + list->num_fences = 0; + } + + dma_fence_get(f); + dma_resv_list_set(list, list->num_fences++, f, + dma_resv_iter_usage(&cursor)); + } + dma_resv_iter_end(&cursor); + + list = rcu_replace_pointer(dst->fences, list, dma_resv_held(dst)); + dma_resv_list_free(list); + return 0; +} +EXPORT_SYMBOL(dma_resv_copy_fences); + +/** + * dma_resv_get_fences - Get an object's fences + * fences without update side lock held + * @obj: the reservation object + * @usage: controls which fences to include, see enum dma_resv_usage. + * @num_fences: the number of fences returned + * @fences: the array of fence ptrs returned (array is krealloc'd to the + * required size, and must be freed by caller) + * + * Retrieve all fences from the reservation object. + * Returns either zero or -ENOMEM. + */ +int dma_resv_get_fences(struct dma_resv *obj, enum dma_resv_usage usage, + unsigned int *num_fences, struct dma_fence ***fences) +{ + struct dma_resv_iter cursor; + struct dma_fence *fence; + + *num_fences = 0; + *fences = NULL; + + dma_resv_iter_begin(&cursor, obj, usage); + dma_resv_for_each_fence_unlocked(&cursor, fence) { + + if (dma_resv_iter_is_restarted(&cursor)) { + struct dma_fence **new_fences; + unsigned int count; + + while (*num_fences) + dma_fence_put((*fences)[--(*num_fences)]); + + count = cursor.num_fences + 1; + + /* Eventually re-allocate the array */ + new_fences = krealloc_array(*fences, count, + sizeof(void *), + GFP_KERNEL); + if (count && !new_fences) { + kfree(*fences); + *fences = NULL; + *num_fences = 0; + dma_resv_iter_end(&cursor); + return -ENOMEM; + } + *fences = new_fences; + } + + (*fences)[(*num_fences)++] = dma_fence_get(fence); + } + dma_resv_iter_end(&cursor); + + return 0; +} +EXPORT_SYMBOL_GPL(dma_resv_get_fences); + +/** + * dma_resv_get_singleton - Get a single fence for all the fences + * @obj: the reservation object + * @usage: controls which fences to include, see enum dma_resv_usage. + * @fence: the resulting fence + * + * Get a single fence representing all the fences inside the resv object. + * Returns either 0 for success or -ENOMEM. + * + * Warning: This can't be used like this when adding the fence back to the resv + * object since that can lead to stack corruption when finalizing the + * dma_fence_array. + * + * Returns 0 on success and negative error values on failure. + */ +int dma_resv_get_singleton(struct dma_resv *obj, enum dma_resv_usage usage, + struct dma_fence **fence) +{ + struct dma_fence_array *array; + struct dma_fence **fences; + unsigned count; + int r; + + r = dma_resv_get_fences(obj, usage, &count, &fences); + if (r) + return r; + + if (count == 0) { + *fence = NULL; + return 0; + } + + if (count == 1) { + *fence = fences[0]; + kfree(fences); + return 0; + } + + array = dma_fence_array_create(count, fences, + dma_fence_context_alloc(1), + 1, false); + if (!array) { + while (count--) + dma_fence_put(fences[count]); + kfree(fences); + return -ENOMEM; + } + + *fence = &array->base; + return 0; +} +EXPORT_SYMBOL_GPL(dma_resv_get_singleton); + +/** + * dma_resv_wait_timeout - Wait on reservation's objects fences + * @obj: the reservation object + * @usage: controls which fences to include, see enum dma_resv_usage. + * @intr: if true, do interruptible wait + * @timeout: timeout value in jiffies or zero to return immediately + * + * Callers are not required to hold specific locks, but maybe hold + * dma_resv_lock() already + * RETURNS + * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or + * greater than zero on success. + */ +long dma_resv_wait_timeout(struct dma_resv *obj, enum dma_resv_usage usage, + bool intr, unsigned long timeout) +{ + long ret = timeout ? timeout : 1; + struct dma_resv_iter cursor; + struct dma_fence *fence; + + dma_resv_iter_begin(&cursor, obj, usage); + dma_resv_for_each_fence_unlocked(&cursor, fence) { + + ret = dma_fence_wait_timeout(fence, intr, timeout); + if (ret <= 0) + break; + + /* Even for zero timeout the return value is 1 */ + if (timeout) + timeout = ret; + } + dma_resv_iter_end(&cursor); + + return ret; +} +EXPORT_SYMBOL_GPL(dma_resv_wait_timeout); + +/** + * dma_resv_set_deadline - Set a deadline on reservation's objects fences + * @obj: the reservation object + * @usage: controls which fences to include, see enum dma_resv_usage. + * @deadline: the requested deadline (MONOTONIC) + * + * May be called without holding the dma_resv lock. Sets @deadline on + * all fences filtered by @usage. + */ +void dma_resv_set_deadline(struct dma_resv *obj, enum dma_resv_usage usage, + ktime_t deadline) +{ + struct dma_resv_iter cursor; + struct dma_fence *fence; + + dma_resv_iter_begin(&cursor, obj, usage); + dma_resv_for_each_fence_unlocked(&cursor, fence) { + dma_fence_set_deadline(fence, deadline); + } + dma_resv_iter_end(&cursor); +} +EXPORT_SYMBOL_GPL(dma_resv_set_deadline); + +/** + * dma_resv_test_signaled - Test if a reservation object's fences have been + * signaled. + * @obj: the reservation object + * @usage: controls which fences to include, see enum dma_resv_usage. + * + * Callers are not required to hold specific locks, but maybe hold + * dma_resv_lock() already. + * + * RETURNS + * + * True if all fences signaled, else false. + */ +bool dma_resv_test_signaled(struct dma_resv *obj, enum dma_resv_usage usage) +{ + struct dma_resv_iter cursor; + struct dma_fence *fence; + + dma_resv_iter_begin(&cursor, obj, usage); + dma_resv_for_each_fence_unlocked(&cursor, fence) { + dma_resv_iter_end(&cursor); + return false; + } + dma_resv_iter_end(&cursor); + return true; +} +EXPORT_SYMBOL_GPL(dma_resv_test_signaled); + +/** + * dma_resv_describe - Dump description of the resv object into seq_file + * @obj: the reservation object + * @seq: the seq_file to dump the description into + * + * Dump a textual description of the fences inside an dma_resv object into the + * seq_file. + */ +void dma_resv_describe(struct dma_resv *obj, struct seq_file *seq) +{ + static const char *usage[] = { "kernel", "write", "read", "bookkeep" }; + struct dma_resv_iter cursor; + struct dma_fence *fence; + + dma_resv_for_each_fence(&cursor, obj, DMA_RESV_USAGE_READ, fence) { + seq_printf(seq, "\t%s fence:", + usage[dma_resv_iter_usage(&cursor)]); + dma_fence_describe(fence, seq); + } +} +EXPORT_SYMBOL_GPL(dma_resv_describe); + +#if IS_ENABLED(CONFIG_LOCKDEP) +static int __init dma_resv_lockdep(void) +{ + struct mm_struct *mm = mm_alloc(); + struct ww_acquire_ctx ctx; + struct dma_resv obj; + struct address_space mapping; + int ret; + + if (!mm) + return -ENOMEM; + + dma_resv_init(&obj); + address_space_init_once(&mapping); + + mmap_read_lock(mm); + ww_acquire_init(&ctx, &reservation_ww_class); + ret = dma_resv_lock(&obj, &ctx); + if (ret == -EDEADLK) + dma_resv_lock_slow(&obj, &ctx); + fs_reclaim_acquire(GFP_KERNEL); + /* for unmap_mapping_range on trylocked buffer objects in shrinkers */ + i_mmap_lock_write(&mapping); + i_mmap_unlock_write(&mapping); +#ifdef CONFIG_MMU_NOTIFIER + lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); + __dma_fence_might_wait(); + lock_map_release(&__mmu_notifier_invalidate_range_start_map); +#else + __dma_fence_might_wait(); +#endif + fs_reclaim_release(GFP_KERNEL); + ww_mutex_unlock(&obj.lock); + ww_acquire_fini(&ctx); + mmap_read_unlock(mm); + + mmput(mm); + + return 0; +} +subsys_initcall(dma_resv_lockdep); +#endif 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..974467791032 --- /dev/null +++ b/drivers/dma-buf/heaps/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +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..42f88193eab9 --- /dev/null +++ b/drivers/dma-buf/heaps/cma_heap.c @@ -0,0 +1,440 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DMABUF CMA heap exporter + * + * Copyright (C) 2012, 2019, 2020 Linaro Ltd. + * Author: <benjamin.gaignard@linaro.org> for ST-Ericsson. + * + * Also utilizing parts of Andrew Davis' SRAM heap: + * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com/ + * Andrew F. Davis <afd@ti.com> + */ + +#define pr_fmt(fmt) "cma_heap: " fmt + +#include <linux/cma.h> +#include <linux/dma-buf.h> +#include <linux/dma-buf/heaps/cma.h> +#include <linux/dma-heap.h> +#include <linux/dma-map-ops.h> +#include <linux/err.h> +#include <linux/highmem.h> +#include <linux/io.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_reserved_mem.h> +#include <linux/scatterlist.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> + +#define DEFAULT_CMA_NAME "default_cma_region" + +static struct cma *dma_areas[MAX_CMA_AREAS] __initdata; +static unsigned int dma_areas_num __initdata; + +int __init dma_heap_cma_register_heap(struct cma *cma) +{ + if (dma_areas_num >= ARRAY_SIZE(dma_areas)) + return -EINVAL; + + dma_areas[dma_areas_num++] = cma; + + return 0; +} + +struct cma_heap { + struct dma_heap *heap; + struct cma *cma; +}; + +struct cma_heap_buffer { + struct cma_heap *heap; + struct list_head attachments; + struct mutex lock; + unsigned long len; + struct page *cma_pages; + struct page **pages; + pgoff_t pagecount; + int vmap_cnt; + void *vaddr; +}; + +struct dma_heap_attachment { + struct device *dev; + struct sg_table table; + struct list_head list; + bool mapped; +}; + +static int cma_heap_attach(struct dma_buf *dmabuf, + struct dma_buf_attachment *attachment) +{ + struct cma_heap_buffer *buffer = dmabuf->priv; + struct dma_heap_attachment *a; + 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); + a->mapped = false; + + attachment->priv = a; + + mutex_lock(&buffer->lock); + list_add(&a->list, &buffer->attachments); + mutex_unlock(&buffer->lock); + + return 0; +} + +static void cma_heap_detach(struct dma_buf *dmabuf, + struct dma_buf_attachment *attachment) +{ + struct cma_heap_buffer *buffer = dmabuf->priv; + struct dma_heap_attachment *a = attachment->priv; + + mutex_lock(&buffer->lock); + list_del(&a->list); + mutex_unlock(&buffer->lock); + + sg_free_table(&a->table); + kfree(a); +} + +static struct sg_table *cma_heap_map_dma_buf(struct dma_buf_attachment *attachment, + enum dma_data_direction direction) +{ + struct dma_heap_attachment *a = attachment->priv; + struct sg_table *table = &a->table; + int ret; + + ret = dma_map_sgtable(attachment->dev, table, direction, 0); + if (ret) + return ERR_PTR(-ENOMEM); + a->mapped = true; + return table; +} + +static void cma_heap_unmap_dma_buf(struct dma_buf_attachment *attachment, + struct sg_table *table, + enum dma_data_direction direction) +{ + struct dma_heap_attachment *a = attachment->priv; + + a->mapped = false; + dma_unmap_sgtable(attachment->dev, table, direction, 0); +} + +static int cma_heap_dma_buf_begin_cpu_access(struct dma_buf *dmabuf, + enum dma_data_direction direction) +{ + struct cma_heap_buffer *buffer = dmabuf->priv; + struct dma_heap_attachment *a; + + mutex_lock(&buffer->lock); + + if (buffer->vmap_cnt) + invalidate_kernel_vmap_range(buffer->vaddr, buffer->len); + + list_for_each_entry(a, &buffer->attachments, list) { + if (!a->mapped) + continue; + dma_sync_sgtable_for_cpu(a->dev, &a->table, direction); + } + mutex_unlock(&buffer->lock); + + return 0; +} + +static int cma_heap_dma_buf_end_cpu_access(struct dma_buf *dmabuf, + enum dma_data_direction direction) +{ + struct cma_heap_buffer *buffer = dmabuf->priv; + struct dma_heap_attachment *a; + + mutex_lock(&buffer->lock); + + if (buffer->vmap_cnt) + flush_kernel_vmap_range(buffer->vaddr, buffer->len); + + list_for_each_entry(a, &buffer->attachments, list) { + if (!a->mapped) + continue; + dma_sync_sgtable_for_device(a->dev, &a->table, direction); + } + mutex_unlock(&buffer->lock); + + return 0; +} + +static vm_fault_t cma_heap_vm_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct cma_heap_buffer *buffer = vma->vm_private_data; + + if (vmf->pgoff >= buffer->pagecount) + return VM_FAULT_SIGBUS; + + return vmf_insert_pfn(vma, vmf->address, page_to_pfn(buffer->pages[vmf->pgoff])); +} + +static const struct vm_operations_struct dma_heap_vm_ops = { + .fault = cma_heap_vm_fault, +}; + +static int cma_heap_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma) +{ + struct cma_heap_buffer *buffer = dmabuf->priv; + + if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0) + return -EINVAL; + + vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP); + + vma->vm_ops = &dma_heap_vm_ops; + vma->vm_private_data = buffer; + + return 0; +} + +static void *cma_heap_do_vmap(struct cma_heap_buffer *buffer) +{ + void *vaddr; + + vaddr = vmap(buffer->pages, buffer->pagecount, VM_MAP, PAGE_KERNEL); + if (!vaddr) + return ERR_PTR(-ENOMEM); + + return vaddr; +} + +static int cma_heap_vmap(struct dma_buf *dmabuf, struct iosys_map *map) +{ + struct cma_heap_buffer *buffer = dmabuf->priv; + void *vaddr; + int ret = 0; + + mutex_lock(&buffer->lock); + if (buffer->vmap_cnt) { + buffer->vmap_cnt++; + iosys_map_set_vaddr(map, buffer->vaddr); + goto out; + } + + vaddr = cma_heap_do_vmap(buffer); + if (IS_ERR(vaddr)) { + ret = PTR_ERR(vaddr); + goto out; + } + buffer->vaddr = vaddr; + buffer->vmap_cnt++; + iosys_map_set_vaddr(map, buffer->vaddr); +out: + mutex_unlock(&buffer->lock); + + return ret; +} + +static void cma_heap_vunmap(struct dma_buf *dmabuf, struct iosys_map *map) +{ + struct cma_heap_buffer *buffer = dmabuf->priv; + + mutex_lock(&buffer->lock); + if (!--buffer->vmap_cnt) { + vunmap(buffer->vaddr); + buffer->vaddr = NULL; + } + mutex_unlock(&buffer->lock); + iosys_map_clear(map); +} + +static void cma_heap_dma_buf_release(struct dma_buf *dmabuf) +{ + struct cma_heap_buffer *buffer = dmabuf->priv; + struct cma_heap *cma_heap = buffer->heap; + + if (buffer->vmap_cnt > 0) { + WARN(1, "%s: buffer still mapped in the kernel\n", __func__); + vunmap(buffer->vaddr); + buffer->vaddr = NULL; + } + + /* free page list */ + kfree(buffer->pages); + /* release memory */ + cma_release(cma_heap->cma, buffer->cma_pages, buffer->pagecount); + kfree(buffer); +} + +static const struct dma_buf_ops cma_heap_buf_ops = { + .attach = cma_heap_attach, + .detach = cma_heap_detach, + .map_dma_buf = cma_heap_map_dma_buf, + .unmap_dma_buf = cma_heap_unmap_dma_buf, + .begin_cpu_access = cma_heap_dma_buf_begin_cpu_access, + .end_cpu_access = cma_heap_dma_buf_end_cpu_access, + .mmap = cma_heap_mmap, + .vmap = cma_heap_vmap, + .vunmap = cma_heap_vunmap, + .release = cma_heap_dma_buf_release, +}; + +static struct dma_buf *cma_heap_allocate(struct dma_heap *heap, + unsigned long len, + u32 fd_flags, + u64 heap_flags) +{ + struct cma_heap *cma_heap = dma_heap_get_drvdata(heap); + struct cma_heap_buffer *buffer; + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); + size_t size = PAGE_ALIGN(len); + pgoff_t pagecount = size >> PAGE_SHIFT; + unsigned long align = get_order(size); + struct page *cma_pages; + struct dma_buf *dmabuf; + int ret = -ENOMEM; + pgoff_t pg; + + buffer = kzalloc(sizeof(*buffer), GFP_KERNEL); + if (!buffer) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&buffer->attachments); + mutex_init(&buffer->lock); + buffer->len = size; + + if (align > CONFIG_CMA_ALIGNMENT) + align = CONFIG_CMA_ALIGNMENT; + + cma_pages = cma_alloc(cma_heap->cma, pagecount, align, false); + if (!cma_pages) + goto free_buffer; + + /* Clear the cma pages */ + if (PageHighMem(cma_pages)) { + unsigned long nr_clear_pages = pagecount; + struct page *page = cma_pages; + + while (nr_clear_pages > 0) { + void *vaddr = kmap_local_page(page); + + memset(vaddr, 0, PAGE_SIZE); + kunmap_local(vaddr); + /* + * Avoid wasting time zeroing memory if the process + * has been killed by SIGKILL. + */ + if (fatal_signal_pending(current)) + goto free_cma; + page++; + nr_clear_pages--; + } + } else { + memset(page_address(cma_pages), 0, size); + } + + buffer->pages = kmalloc_array(pagecount, sizeof(*buffer->pages), GFP_KERNEL); + if (!buffer->pages) { + ret = -ENOMEM; + goto free_cma; + } + + for (pg = 0; pg < pagecount; pg++) + buffer->pages[pg] = &cma_pages[pg]; + + buffer->cma_pages = cma_pages; + buffer->heap = cma_heap; + buffer->pagecount = pagecount; + + /* create the dmabuf */ + exp_info.exp_name = dma_heap_get_name(heap); + exp_info.ops = &cma_heap_buf_ops; + exp_info.size = buffer->len; + exp_info.flags = fd_flags; + exp_info.priv = buffer; + dmabuf = dma_buf_export(&exp_info); + if (IS_ERR(dmabuf)) { + ret = PTR_ERR(dmabuf); + goto free_pages; + } + return dmabuf; + +free_pages: + kfree(buffer->pages); +free_cma: + cma_release(cma_heap->cma, cma_pages, pagecount); +free_buffer: + kfree(buffer); + + return ERR_PTR(ret); +} + +static const struct dma_heap_ops cma_heap_ops = { + .allocate = cma_heap_allocate, +}; + +static int __init __add_cma_heap(struct cma *cma, const char *name) +{ + struct dma_heap_export_info exp_info; + struct cma_heap *cma_heap; + + cma_heap = kzalloc(sizeof(*cma_heap), GFP_KERNEL); + if (!cma_heap) + return -ENOMEM; + cma_heap->cma = cma; + + exp_info.name = name; + 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 __init add_cma_heaps(void) +{ + struct cma *default_cma = dev_get_cma_area(NULL); + unsigned int i; + int ret; + + if (default_cma) { + ret = __add_cma_heap(default_cma, DEFAULT_CMA_NAME); + if (ret) + return ret; + } + + for (i = 0; i < dma_areas_num; i++) { + struct cma *cma = dma_areas[i]; + + ret = __add_cma_heap(cma, cma_get_name(cma)); + if (ret) { + pr_warn("Failed to add CMA heap %s", cma_get_name(cma)); + continue; + } + + } + + return 0; +} +module_init(add_cma_heaps); +MODULE_DESCRIPTION("DMA-BUF CMA Heap"); diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c new file mode 100644 index 000000000000..4c782fe33fd4 --- /dev/null +++ b/drivers/dma-buf/heaps/system_heap.c @@ -0,0 +1,443 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DMABUF System heap exporter + * + * Copyright (C) 2011 Google, Inc. + * Copyright (C) 2019, 2020 Linaro Ltd. + * + * Portions based off of Andrew Davis' SRAM heap: + * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com/ + * Andrew F. Davis <afd@ti.com> + */ + +#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/vmalloc.h> + +struct system_heap_buffer { + struct dma_heap *heap; + struct list_head attachments; + struct mutex lock; + unsigned long len; + struct sg_table sg_table; + int vmap_cnt; + void *vaddr; +}; + +struct dma_heap_attachment { + struct device *dev; + struct sg_table table; + struct list_head list; + bool mapped; +}; + +#define LOW_ORDER_GFP (GFP_HIGHUSER | __GFP_ZERO) +#define HIGH_ORDER_GFP (((GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN \ + | __GFP_NORETRY) & ~__GFP_RECLAIM) \ + | __GFP_COMP) +static gfp_t order_flags[] = {HIGH_ORDER_GFP, HIGH_ORDER_GFP, LOW_ORDER_GFP}; +/* + * The selection of the orders used for allocation (1MB, 64K, 4K) is designed + * to match with the sizes often found in IOMMUs. Using order 4 pages instead + * of order 0 pages can significantly improve the performance of many IOMMUs + * by reducing TLB pressure and time spent updating page tables. + */ +static const unsigned int orders[] = {8, 4, 0}; +#define NUM_ORDERS ARRAY_SIZE(orders) + +static int dup_sg_table(struct sg_table *from, struct sg_table *to) +{ + struct scatterlist *sg, *new_sg; + int ret, i; + + ret = sg_alloc_table(to, from->orig_nents, GFP_KERNEL); + if (ret) + return ret; + + new_sg = to->sgl; + for_each_sgtable_sg(from, sg, i) { + sg_set_page(new_sg, sg_page(sg), sg->length, sg->offset); + new_sg = sg_next(new_sg); + } + + return 0; +} + +static int system_heap_attach(struct dma_buf *dmabuf, + struct dma_buf_attachment *attachment) +{ + struct system_heap_buffer *buffer = dmabuf->priv; + struct dma_heap_attachment *a; + int ret; + + a = kzalloc(sizeof(*a), GFP_KERNEL); + if (!a) + return -ENOMEM; + + ret = dup_sg_table(&buffer->sg_table, &a->table); + if (ret) { + kfree(a); + return ret; + } + + a->dev = attachment->dev; + INIT_LIST_HEAD(&a->list); + a->mapped = false; + + attachment->priv = a; + + mutex_lock(&buffer->lock); + list_add(&a->list, &buffer->attachments); + mutex_unlock(&buffer->lock); + + return 0; +} + +static void system_heap_detach(struct dma_buf *dmabuf, + struct dma_buf_attachment *attachment) +{ + struct system_heap_buffer *buffer = dmabuf->priv; + struct dma_heap_attachment *a = attachment->priv; + + mutex_lock(&buffer->lock); + list_del(&a->list); + mutex_unlock(&buffer->lock); + + sg_free_table(&a->table); + kfree(a); +} + +static struct sg_table *system_heap_map_dma_buf(struct dma_buf_attachment *attachment, + enum dma_data_direction direction) +{ + struct dma_heap_attachment *a = attachment->priv; + struct sg_table *table = &a->table; + int ret; + + ret = dma_map_sgtable(attachment->dev, table, direction, 0); + if (ret) + return ERR_PTR(ret); + + a->mapped = true; + return table; +} + +static void system_heap_unmap_dma_buf(struct dma_buf_attachment *attachment, + struct sg_table *table, + enum dma_data_direction direction) +{ + struct dma_heap_attachment *a = attachment->priv; + + a->mapped = false; + dma_unmap_sgtable(attachment->dev, table, direction, 0); +} + +static int system_heap_dma_buf_begin_cpu_access(struct dma_buf *dmabuf, + enum dma_data_direction direction) +{ + struct system_heap_buffer *buffer = dmabuf->priv; + struct dma_heap_attachment *a; + + mutex_lock(&buffer->lock); + + if (buffer->vmap_cnt) + invalidate_kernel_vmap_range(buffer->vaddr, buffer->len); + + list_for_each_entry(a, &buffer->attachments, list) { + if (!a->mapped) + continue; + dma_sync_sgtable_for_cpu(a->dev, &a->table, direction); + } + mutex_unlock(&buffer->lock); + + return 0; +} + +static int system_heap_dma_buf_end_cpu_access(struct dma_buf *dmabuf, + enum dma_data_direction direction) +{ + struct system_heap_buffer *buffer = dmabuf->priv; + struct dma_heap_attachment *a; + + mutex_lock(&buffer->lock); + + if (buffer->vmap_cnt) + flush_kernel_vmap_range(buffer->vaddr, buffer->len); + + list_for_each_entry(a, &buffer->attachments, list) { + if (!a->mapped) + continue; + dma_sync_sgtable_for_device(a->dev, &a->table, direction); + } + mutex_unlock(&buffer->lock); + + return 0; +} + +static int system_heap_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma) +{ + struct system_heap_buffer *buffer = dmabuf->priv; + struct sg_table *table = &buffer->sg_table; + unsigned long addr = vma->vm_start; + unsigned long pgoff = vma->vm_pgoff; + struct scatterlist *sg; + int i, ret; + + for_each_sgtable_sg(table, sg, i) { + unsigned long n = sg->length >> PAGE_SHIFT; + + if (pgoff < n) + break; + pgoff -= n; + } + + for (; sg && addr < vma->vm_end; sg = sg_next(sg)) { + unsigned long n = (sg->length >> PAGE_SHIFT) - pgoff; + struct page *page = sg_page(sg) + pgoff; + unsigned long size = n << PAGE_SHIFT; + + if (addr + size > vma->vm_end) + size = vma->vm_end - addr; + + ret = remap_pfn_range(vma, addr, page_to_pfn(page), + size, vma->vm_page_prot); + if (ret) + return ret; + + addr += size; + pgoff = 0; + } + + return 0; +} + +static void *system_heap_do_vmap(struct system_heap_buffer *buffer) +{ + struct sg_table *table = &buffer->sg_table; + int npages = PAGE_ALIGN(buffer->len) / PAGE_SIZE; + struct page **pages = vmalloc(sizeof(struct page *) * npages); + struct page **tmp = pages; + struct sg_page_iter piter; + void *vaddr; + + if (!pages) + return ERR_PTR(-ENOMEM); + + for_each_sgtable_page(table, &piter, 0) { + WARN_ON(tmp - pages >= npages); + *tmp++ = sg_page_iter_page(&piter); + } + + vaddr = vmap(pages, npages, VM_MAP, PAGE_KERNEL); + vfree(pages); + + if (!vaddr) + return ERR_PTR(-ENOMEM); + + return vaddr; +} + +static int system_heap_vmap(struct dma_buf *dmabuf, struct iosys_map *map) +{ + struct system_heap_buffer *buffer = dmabuf->priv; + void *vaddr; + int ret = 0; + + mutex_lock(&buffer->lock); + if (buffer->vmap_cnt) { + buffer->vmap_cnt++; + iosys_map_set_vaddr(map, buffer->vaddr); + goto out; + } + + vaddr = system_heap_do_vmap(buffer); + if (IS_ERR(vaddr)) { + ret = PTR_ERR(vaddr); + goto out; + } + + buffer->vaddr = vaddr; + buffer->vmap_cnt++; + iosys_map_set_vaddr(map, buffer->vaddr); +out: + mutex_unlock(&buffer->lock); + + return ret; +} + +static void system_heap_vunmap(struct dma_buf *dmabuf, struct iosys_map *map) +{ + struct system_heap_buffer *buffer = dmabuf->priv; + + mutex_lock(&buffer->lock); + if (!--buffer->vmap_cnt) { + vunmap(buffer->vaddr); + buffer->vaddr = NULL; + } + mutex_unlock(&buffer->lock); + iosys_map_clear(map); +} + +static void system_heap_dma_buf_release(struct dma_buf *dmabuf) +{ + struct system_heap_buffer *buffer = dmabuf->priv; + struct sg_table *table; + struct scatterlist *sg; + int i; + + table = &buffer->sg_table; + for_each_sgtable_sg(table, sg, i) { + struct page *page = sg_page(sg); + + __free_pages(page, compound_order(page)); + } + sg_free_table(table); + kfree(buffer); +} + +static const struct dma_buf_ops system_heap_buf_ops = { + .attach = system_heap_attach, + .detach = system_heap_detach, + .map_dma_buf = system_heap_map_dma_buf, + .unmap_dma_buf = system_heap_unmap_dma_buf, + .begin_cpu_access = system_heap_dma_buf_begin_cpu_access, + .end_cpu_access = system_heap_dma_buf_end_cpu_access, + .mmap = system_heap_mmap, + .vmap = system_heap_vmap, + .vunmap = system_heap_vunmap, + .release = system_heap_dma_buf_release, +}; + +static struct page *alloc_largest_available(unsigned long size, + unsigned int max_order) +{ + struct page *page; + int i; + + for (i = 0; i < NUM_ORDERS; i++) { + if (size < (PAGE_SIZE << orders[i])) + continue; + if (max_order < orders[i]) + continue; + + page = alloc_pages(order_flags[i], orders[i]); + if (!page) + continue; + return page; + } + return NULL; +} + +static struct dma_buf *system_heap_allocate(struct dma_heap *heap, + unsigned long len, + u32 fd_flags, + u64 heap_flags) +{ + struct system_heap_buffer *buffer; + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); + unsigned long size_remaining = len; + unsigned int max_order = orders[0]; + struct dma_buf *dmabuf; + struct sg_table *table; + struct scatterlist *sg; + struct list_head pages; + struct page *page, *tmp_page; + int i, ret = -ENOMEM; + + buffer = kzalloc(sizeof(*buffer), GFP_KERNEL); + if (!buffer) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&buffer->attachments); + mutex_init(&buffer->lock); + buffer->heap = heap; + buffer->len = len; + + INIT_LIST_HEAD(&pages); + i = 0; + while (size_remaining > 0) { + /* + * Avoid trying to allocate memory if the process + * has been killed by SIGKILL + */ + if (fatal_signal_pending(current)) { + ret = -EINTR; + goto free_buffer; + } + + page = alloc_largest_available(size_remaining, max_order); + if (!page) + goto free_buffer; + + list_add_tail(&page->lru, &pages); + size_remaining -= page_size(page); + max_order = compound_order(page); + i++; + } + + table = &buffer->sg_table; + if (sg_alloc_table(table, i, GFP_KERNEL)) + goto free_buffer; + + sg = table->sgl; + list_for_each_entry_safe(page, tmp_page, &pages, lru) { + sg_set_page(sg, page, page_size(page), 0); + sg = sg_next(sg); + list_del(&page->lru); + } + + /* create the dmabuf */ + exp_info.exp_name = dma_heap_get_name(heap); + exp_info.ops = &system_heap_buf_ops; + exp_info.size = buffer->len; + exp_info.flags = fd_flags; + exp_info.priv = buffer; + dmabuf = dma_buf_export(&exp_info); + if (IS_ERR(dmabuf)) { + ret = PTR_ERR(dmabuf); + goto free_pages; + } + return dmabuf; + +free_pages: + for_each_sgtable_sg(table, sg, i) { + struct page *p = sg_page(sg); + + __free_pages(p, compound_order(p)); + } + sg_free_table(table); +free_buffer: + list_for_each_entry_safe(page, tmp_page, &pages, lru) + __free_pages(page, compound_order(page)); + kfree(buffer); + + return ERR_PTR(ret); +} + +static const struct dma_heap_ops system_heap_ops = { + .allocate = system_heap_allocate, +}; + +static int __init system_heap_create(void) +{ + struct dma_heap_export_info exp_info; + struct dma_heap *sys_heap; + + 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)) + return PTR_ERR(sys_heap); + + return 0; +} +module_init(system_heap_create); diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c deleted file mode 100644 index c1618335ca99..000000000000 --- a/drivers/dma-buf/reservation.c +++ /dev/null @@ -1,579 +0,0 @@ -/* - * 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 shared fences to - * a reservation_object. - * @obj: reservation object - * @num_fences: number of fences we want to add - * - * 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, - unsigned int num_fences) -{ - struct reservation_object_list *old, *new; - unsigned int i, j, k, max; - - old = reservation_object_get_list(obj); - - if (old && old->shared_max) { - if ((old->shared_count + num_fences) <= old->shared_max) - return 0; - else - max = max(old->shared_count + num_fences, - old->shared_max * 2); - } else { - max = 4; - } - - new = kmalloc(offsetof(typeof(*new), shared[max]), GFP_KERNEL); - if (!new) - return -ENOMEM; - - /* - * no need to bump fence refcounts, rcu_read access - * requires the use of kref_get_unless_zero, and the - * references from the old struct are carried over to - * the new. - */ - for (i = 0, j = 0, k = max; i < (old ? old->shared_count : 0); ++i) { - struct dma_fence *fence; - - fence = rcu_dereference_protected(old->shared[i], - reservation_object_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 - */ - RCU_INIT_POINTER(obj->fence, new); - write_seqcount_end(&obj->seq); - preempt_enable(); - - if (!old) - return 0; - - /* Drop the references to the signaled fences */ - for (i = k; i < new->shared_max; ++i) { - struct dma_fence *fence; - - fence = rcu_dereference_protected(new->shared[i], - reservation_object_held(obj)); - dma_fence_put(fence); - } - kfree_rcu(old, rcu); - - return 0; -} -EXPORT_SYMBOL(reservation_object_reserve_shared); - -/** - * 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 *fobj; - unsigned int i, count; - - dma_fence_get(fence); - - fobj = reservation_object_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); - goto replace; - } - } - - BUG_ON(fobj->shared_count >= fobj->shared_max); - count++; - -replace: - RCU_INIT_POINTER(fobj->shared[i], fence); - /* pointer update must be visible before we extend the shared_count */ - smp_store_mb(fobj->shared_count, count); - - write_seqcount_end(&obj->seq); - preempt_enable(); -} -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(); - - 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(); - 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/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..851965867d9c --- /dev/null +++ b/drivers/dma-buf/selftests.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: MIT */ +/* List each unit test as selftest(name, function) + * + * The name is used as both an enum and expanded as subtest__name to create + * a module parameter. It must be unique and legal for a C identifier. + * + * The function should be of type int function(void). It may be conditionally + * compiled using #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST). + * + * Tests are executed in order by igt/dmabuf_selftest + */ +selftest(sanitycheck, __sanitycheck__) /* keep first (igt selfcheck) */ +selftest(dma_fence, dma_fence) +selftest(dma_fence_chain, dma_fence_chain) +selftest(dma_fence_unwrap, dma_fence_unwrap) +selftest(dma_resv, dma_resv) diff --git a/drivers/dma-buf/seqno-fence.c b/drivers/dma-buf/seqno-fence.c deleted file mode 100644 index f47112a64763..000000000000 --- a/drivers/dma-buf/seqno-fence.c +++ /dev/null @@ -1,79 +0,0 @@ -/* - * 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/st-dma-fence-chain.c b/drivers/dma-buf/st-dma-fence-chain.c new file mode 100644 index 000000000000..ed4b323886e4 --- /dev/null +++ b/drivers/dma-buf/st-dma-fence-chain.c @@ -0,0 +1,706 @@ +// SPDX-License-Identifier: MIT + +/* + * Copyright © 2019 Intel Corporation + */ + +#include <linux/delay.h> +#include <linux/dma-fence.h> +#include <linux/dma-fence-chain.h> +#include <linux/kernel.h> +#include <linux/kthread.h> +#include <linux/mm.h> +#include <linux/sched/signal.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/random.h> + +#include "selftest.h" + +#define CHAIN_SZ (4 << 10) + +static struct kmem_cache *slab_fences; + +static inline struct mock_fence { + struct dma_fence base; + spinlock_t lock; +} *to_mock_fence(struct dma_fence *f) { + return container_of(f, struct mock_fence, base); +} + +static const char *mock_name(struct dma_fence *f) +{ + return "mock"; +} + +static void mock_fence_release(struct dma_fence *f) +{ + kmem_cache_free(slab_fences, to_mock_fence(f)); +} + +static const struct dma_fence_ops mock_ops = { + .get_driver_name = mock_name, + .get_timeline_name = mock_name, + .release = mock_fence_release, +}; + +static struct dma_fence *mock_fence(void) +{ + struct mock_fence *f; + + f = kmem_cache_alloc(slab_fences, GFP_KERNEL); + if (!f) + return NULL; + + spin_lock_init(&f->lock); + dma_fence_init(&f->base, &mock_ops, &f->lock, 0, 0); + + return &f->base; +} + +static struct dma_fence *mock_chain(struct dma_fence *prev, + struct dma_fence *fence, + u64 seqno) +{ + struct dma_fence_chain *f; + + f = dma_fence_chain_alloc(); + if (!f) + return NULL; + + dma_fence_chain_init(f, dma_fence_get(prev), dma_fence_get(fence), + seqno); + + return &f->base; +} + +static int sanitycheck(void *arg) +{ + struct dma_fence *f, *chain; + int err = 0; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + chain = mock_chain(NULL, f, 1); + if (chain) + dma_fence_enable_sw_signaling(chain); + else + err = -ENOMEM; + + dma_fence_signal(f); + dma_fence_put(f); + + dma_fence_put(chain); + + return err; +} + +struct fence_chains { + unsigned int chain_length; + struct dma_fence **fences; + struct dma_fence **chains; + + struct dma_fence *tail; +}; + +static uint64_t seqno_inc(unsigned int i) +{ + return i + 1; +} + +static int fence_chains_init(struct fence_chains *fc, unsigned int count, + uint64_t (*seqno_fn)(unsigned int)) +{ + unsigned int i; + int err = 0; + + fc->chains = kvmalloc_array(count, sizeof(*fc->chains), + GFP_KERNEL | __GFP_ZERO); + if (!fc->chains) + return -ENOMEM; + + fc->fences = kvmalloc_array(count, sizeof(*fc->fences), + GFP_KERNEL | __GFP_ZERO); + if (!fc->fences) { + err = -ENOMEM; + goto err_chains; + } + + fc->tail = NULL; + for (i = 0; i < count; i++) { + fc->fences[i] = mock_fence(); + if (!fc->fences[i]) { + err = -ENOMEM; + goto unwind; + } + + fc->chains[i] = mock_chain(fc->tail, + fc->fences[i], + seqno_fn(i)); + if (!fc->chains[i]) { + err = -ENOMEM; + goto unwind; + } + + fc->tail = fc->chains[i]; + + dma_fence_enable_sw_signaling(fc->chains[i]); + } + + fc->chain_length = i; + return 0; + +unwind: + for (i = 0; i < count; i++) { + dma_fence_put(fc->fences[i]); + dma_fence_put(fc->chains[i]); + } + kvfree(fc->fences); +err_chains: + kvfree(fc->chains); + return err; +} + +static void fence_chains_fini(struct fence_chains *fc) +{ + unsigned int i; + + for (i = 0; i < fc->chain_length; i++) { + dma_fence_signal(fc->fences[i]); + dma_fence_put(fc->fences[i]); + } + kvfree(fc->fences); + + for (i = 0; i < fc->chain_length; i++) + dma_fence_put(fc->chains[i]); + kvfree(fc->chains); +} + +static int find_seqno(void *arg) +{ + struct fence_chains fc; + struct dma_fence *fence; + int err; + int i; + + err = fence_chains_init(&fc, 64, seqno_inc); + if (err) + return err; + + fence = dma_fence_get(fc.tail); + err = dma_fence_chain_find_seqno(&fence, 0); + dma_fence_put(fence); + if (err) { + pr_err("Reported %d for find_seqno(0)!\n", err); + goto err; + } + + for (i = 0; i < fc.chain_length; i++) { + fence = dma_fence_get(fc.tail); + err = dma_fence_chain_find_seqno(&fence, i + 1); + dma_fence_put(fence); + if (err) { + pr_err("Reported %d for find_seqno(%d:%d)!\n", + err, fc.chain_length + 1, i + 1); + goto err; + } + if (fence != fc.chains[i]) { + pr_err("Incorrect fence reported by find_seqno(%d:%d)\n", + fc.chain_length + 1, i + 1); + err = -EINVAL; + goto err; + } + + dma_fence_get(fence); + err = dma_fence_chain_find_seqno(&fence, i + 1); + dma_fence_put(fence); + if (err) { + pr_err("Error reported for finding self\n"); + goto err; + } + if (fence != fc.chains[i]) { + pr_err("Incorrect fence reported by find self\n"); + err = -EINVAL; + goto err; + } + + dma_fence_get(fence); + err = dma_fence_chain_find_seqno(&fence, i + 2); + dma_fence_put(fence); + if (!err) { + pr_err("Error not reported for future fence: find_seqno(%d:%d)!\n", + i + 1, i + 2); + err = -EINVAL; + goto err; + } + + dma_fence_get(fence); + err = dma_fence_chain_find_seqno(&fence, i); + dma_fence_put(fence); + if (err) { + pr_err("Error reported for previous fence!\n"); + goto err; + } + if (i > 0 && fence != fc.chains[i - 1]) { + pr_err("Incorrect fence reported by find_seqno(%d:%d)\n", + i + 1, i); + err = -EINVAL; + goto err; + } + } + +err: + fence_chains_fini(&fc); + return err; +} + +static int find_signaled(void *arg) +{ + struct fence_chains fc; + struct dma_fence *fence; + int err; + + err = fence_chains_init(&fc, 2, seqno_inc); + if (err) + return err; + + dma_fence_signal(fc.fences[0]); + + fence = dma_fence_get(fc.tail); + err = dma_fence_chain_find_seqno(&fence, 1); + dma_fence_put(fence); + if (err) { + pr_err("Reported %d for find_seqno()!\n", err); + goto err; + } + + if (fence && fence != fc.chains[0]) { + pr_err("Incorrect chain-fence.seqno:%lld reported for completed seqno:1\n", + fence->seqno); + + dma_fence_get(fence); + err = dma_fence_chain_find_seqno(&fence, 1); + dma_fence_put(fence); + if (err) + pr_err("Reported %d for finding self!\n", err); + + err = -EINVAL; + } + +err: + fence_chains_fini(&fc); + return err; +} + +static int find_out_of_order(void *arg) +{ + struct fence_chains fc; + struct dma_fence *fence; + int err; + + err = fence_chains_init(&fc, 3, seqno_inc); + if (err) + return err; + + dma_fence_signal(fc.fences[1]); + + fence = dma_fence_get(fc.tail); + err = dma_fence_chain_find_seqno(&fence, 2); + dma_fence_put(fence); + if (err) { + pr_err("Reported %d for find_seqno()!\n", err); + goto err; + } + + /* + * We signaled the middle fence (2) of the 1-2-3 chain. The behavior + * of the dma-fence-chain is to make us wait for all the fences up to + * the point we want. Since fence 1 is still not signaled, this what + * we should get as fence to wait upon (fence 2 being garbage + * collected during the traversal of the chain). + */ + if (fence != fc.chains[0]) { + pr_err("Incorrect chain-fence.seqno:%lld reported for completed seqno:2\n", + fence ? fence->seqno : 0); + + err = -EINVAL; + } + +err: + fence_chains_fini(&fc); + return err; +} + +static uint64_t seqno_inc2(unsigned int i) +{ + return 2 * i + 2; +} + +static int find_gap(void *arg) +{ + struct fence_chains fc; + struct dma_fence *fence; + int err; + int i; + + err = fence_chains_init(&fc, 64, seqno_inc2); + if (err) + return err; + + for (i = 0; i < fc.chain_length; i++) { + fence = dma_fence_get(fc.tail); + err = dma_fence_chain_find_seqno(&fence, 2 * i + 1); + dma_fence_put(fence); + if (err) { + pr_err("Reported %d for find_seqno(%d:%d)!\n", + err, fc.chain_length + 1, 2 * i + 1); + goto err; + } + if (fence != fc.chains[i]) { + pr_err("Incorrect fence.seqno:%lld reported by find_seqno(%d:%d)\n", + fence->seqno, + fc.chain_length + 1, + 2 * i + 1); + err = -EINVAL; + goto err; + } + + dma_fence_get(fence); + err = dma_fence_chain_find_seqno(&fence, 2 * i + 2); + dma_fence_put(fence); + if (err) { + pr_err("Error reported for finding self\n"); + goto err; + } + if (fence != fc.chains[i]) { + pr_err("Incorrect fence reported by find self\n"); + err = -EINVAL; + goto err; + } + } + +err: + fence_chains_fini(&fc); + return err; +} + +struct find_race { + struct fence_chains fc; + atomic_t children; +}; + +static int __find_race(void *arg) +{ + struct find_race *data = arg; + int err = 0; + + while (!kthread_should_stop()) { + struct dma_fence *fence = dma_fence_get(data->fc.tail); + int seqno; + + seqno = get_random_u32_inclusive(1, data->fc.chain_length); + + err = dma_fence_chain_find_seqno(&fence, seqno); + if (err) { + pr_err("Failed to find fence seqno:%d\n", + seqno); + dma_fence_put(fence); + break; + } + if (!fence) + goto signal; + + /* + * We can only find ourselves if we are on fence we were + * looking for. + */ + if (fence->seqno == seqno) { + err = dma_fence_chain_find_seqno(&fence, seqno); + if (err) { + pr_err("Reported an invalid fence for find-self:%d\n", + seqno); + dma_fence_put(fence); + break; + } + } + + dma_fence_put(fence); + +signal: + seqno = get_random_u32_below(data->fc.chain_length - 1); + dma_fence_signal(data->fc.fences[seqno]); + cond_resched(); + } + + if (atomic_dec_and_test(&data->children)) + wake_up_var(&data->children); + return err; +} + +static int find_race(void *arg) +{ + struct find_race data; + int ncpus = num_online_cpus(); + struct task_struct **threads; + unsigned long count; + int err; + int i; + + err = fence_chains_init(&data.fc, CHAIN_SZ, seqno_inc); + if (err) + return err; + + threads = kmalloc_array(ncpus, sizeof(*threads), GFP_KERNEL); + if (!threads) { + err = -ENOMEM; + goto err; + } + + atomic_set(&data.children, 0); + for (i = 0; i < ncpus; i++) { + threads[i] = kthread_run(__find_race, &data, "dmabuf/%d", i); + if (IS_ERR(threads[i])) { + ncpus = i; + break; + } + atomic_inc(&data.children); + get_task_struct(threads[i]); + } + + wait_var_event_timeout(&data.children, + !atomic_read(&data.children), + 5 * HZ); + + for (i = 0; i < ncpus; i++) { + int ret; + + ret = kthread_stop_put(threads[i]); + if (ret && !err) + err = ret; + } + kfree(threads); + + count = 0; + for (i = 0; i < data.fc.chain_length; i++) + if (dma_fence_is_signaled(data.fc.fences[i])) + count++; + pr_info("Completed %lu cycles\n", count); + +err: + fence_chains_fini(&data.fc); + return err; +} + +static int signal_forward(void *arg) +{ + struct fence_chains fc; + int err; + int i; + + err = fence_chains_init(&fc, 64, seqno_inc); + if (err) + return err; + + for (i = 0; i < fc.chain_length; i++) { + dma_fence_signal(fc.fences[i]); + + if (!dma_fence_is_signaled(fc.chains[i])) { + pr_err("chain[%d] not signaled!\n", i); + err = -EINVAL; + goto err; + } + + if (i + 1 < fc.chain_length && + dma_fence_is_signaled(fc.chains[i + 1])) { + pr_err("chain[%d] is signaled!\n", i); + err = -EINVAL; + goto err; + } + } + +err: + fence_chains_fini(&fc); + return err; +} + +static int signal_backward(void *arg) +{ + struct fence_chains fc; + int err; + int i; + + err = fence_chains_init(&fc, 64, seqno_inc); + if (err) + return err; + + for (i = fc.chain_length; i--; ) { + dma_fence_signal(fc.fences[i]); + + if (i > 0 && dma_fence_is_signaled(fc.chains[i])) { + pr_err("chain[%d] is signaled!\n", i); + err = -EINVAL; + goto err; + } + } + + for (i = 0; i < fc.chain_length; i++) { + if (!dma_fence_is_signaled(fc.chains[i])) { + pr_err("chain[%d] was not signaled!\n", i); + err = -EINVAL; + goto err; + } + } + +err: + fence_chains_fini(&fc); + return err; +} + +static int __wait_fence_chains(void *arg) +{ + struct fence_chains *fc = arg; + + if (dma_fence_wait(fc->tail, false)) + return -EIO; + + return 0; +} + +static int wait_forward(void *arg) +{ + struct fence_chains fc; + struct task_struct *tsk; + int err; + int i; + + err = fence_chains_init(&fc, CHAIN_SZ, seqno_inc); + if (err) + return err; + + tsk = kthread_run(__wait_fence_chains, &fc, "dmabuf/wait"); + if (IS_ERR(tsk)) { + err = PTR_ERR(tsk); + goto err; + } + get_task_struct(tsk); + yield_to(tsk, true); + + for (i = 0; i < fc.chain_length; i++) + dma_fence_signal(fc.fences[i]); + + err = kthread_stop_put(tsk); + +err: + fence_chains_fini(&fc); + return err; +} + +static int wait_backward(void *arg) +{ + struct fence_chains fc; + struct task_struct *tsk; + int err; + int i; + + err = fence_chains_init(&fc, CHAIN_SZ, seqno_inc); + if (err) + return err; + + tsk = kthread_run(__wait_fence_chains, &fc, "dmabuf/wait"); + if (IS_ERR(tsk)) { + err = PTR_ERR(tsk); + goto err; + } + get_task_struct(tsk); + yield_to(tsk, true); + + for (i = fc.chain_length; i--; ) + dma_fence_signal(fc.fences[i]); + + err = kthread_stop_put(tsk); + +err: + fence_chains_fini(&fc); + return err; +} + +static void randomise_fences(struct fence_chains *fc) +{ + unsigned int count = fc->chain_length; + + /* Fisher-Yates shuffle courtesy of Knuth */ + while (--count) { + unsigned int swp; + + swp = get_random_u32_below(count + 1); + if (swp == count) + continue; + + swap(fc->fences[count], fc->fences[swp]); + } +} + +static int wait_random(void *arg) +{ + struct fence_chains fc; + struct task_struct *tsk; + int err; + int i; + + err = fence_chains_init(&fc, CHAIN_SZ, seqno_inc); + if (err) + return err; + + randomise_fences(&fc); + + tsk = kthread_run(__wait_fence_chains, &fc, "dmabuf/wait"); + if (IS_ERR(tsk)) { + err = PTR_ERR(tsk); + goto err; + } + get_task_struct(tsk); + yield_to(tsk, true); + + for (i = 0; i < fc.chain_length; i++) + dma_fence_signal(fc.fences[i]); + + err = kthread_stop_put(tsk); + +err: + fence_chains_fini(&fc); + return err; +} + +int dma_fence_chain(void) +{ + static const struct subtest tests[] = { + SUBTEST(sanitycheck), + SUBTEST(find_seqno), + SUBTEST(find_signaled), + SUBTEST(find_out_of_order), + SUBTEST(find_gap), + SUBTEST(find_race), + SUBTEST(signal_forward), + SUBTEST(signal_backward), + SUBTEST(wait_forward), + SUBTEST(wait_backward), + SUBTEST(wait_random), + }; + int ret; + + pr_info("sizeof(dma_fence_chain)=%zu\n", + sizeof(struct dma_fence_chain)); + + slab_fences = KMEM_CACHE(mock_fence, + SLAB_TYPESAFE_BY_RCU | + SLAB_HWCACHE_ALIGN); + if (!slab_fences) + return -ENOMEM; + + ret = subtests(tests, NULL); + + kmem_cache_destroy(slab_fences); + return ret; +} diff --git a/drivers/dma-buf/st-dma-fence-unwrap.c b/drivers/dma-buf/st-dma-fence-unwrap.c new file mode 100644 index 000000000000..a3be888ae2e8 --- /dev/null +++ b/drivers/dma-buf/st-dma-fence-unwrap.c @@ -0,0 +1,642 @@ +// SPDX-License-Identifier: MIT + +/* + * Copyright (C) 2022 Advanced Micro Devices, Inc. + */ + +#include <linux/dma-fence.h> +#include <linux/dma-fence-array.h> +#include <linux/dma-fence-chain.h> +#include <linux/dma-fence-unwrap.h> + +#include "selftest.h" + +#define CHAIN_SZ (4 << 10) + +struct mock_fence { + struct dma_fence base; + spinlock_t lock; +}; + +static const char *mock_name(struct dma_fence *f) +{ + return "mock"; +} + +static const struct dma_fence_ops mock_ops = { + .get_driver_name = mock_name, + .get_timeline_name = mock_name, +}; + +static struct dma_fence *__mock_fence(u64 context, u64 seqno) +{ + struct mock_fence *f; + + f = kmalloc(sizeof(*f), GFP_KERNEL); + if (!f) + return NULL; + + spin_lock_init(&f->lock); + dma_fence_init(&f->base, &mock_ops, &f->lock, context, seqno); + + return &f->base; +} + +static struct dma_fence *mock_fence(void) +{ + return __mock_fence(dma_fence_context_alloc(1), 1); +} + +static struct dma_fence *mock_array(unsigned int num_fences, ...) +{ + struct dma_fence_array *array; + struct dma_fence **fences; + va_list valist; + int i; + + fences = kcalloc(num_fences, sizeof(*fences), GFP_KERNEL); + if (!fences) + goto error_put; + + va_start(valist, num_fences); + for (i = 0; i < num_fences; ++i) + fences[i] = va_arg(valist, typeof(*fences)); + va_end(valist); + + array = dma_fence_array_create(num_fences, fences, + dma_fence_context_alloc(1), + 1, false); + if (!array) + goto error_free; + return &array->base; + +error_free: + kfree(fences); + +error_put: + va_start(valist, num_fences); + for (i = 0; i < num_fences; ++i) + dma_fence_put(va_arg(valist, typeof(*fences))); + va_end(valist); + return NULL; +} + +static struct dma_fence *mock_chain(struct dma_fence *prev, + struct dma_fence *fence) +{ + struct dma_fence_chain *f; + + f = dma_fence_chain_alloc(); + if (!f) { + dma_fence_put(prev); + dma_fence_put(fence); + return NULL; + } + + dma_fence_chain_init(f, prev, fence, 1); + return &f->base; +} + +static int sanitycheck(void *arg) +{ + struct dma_fence *f, *chain, *array; + int err = 0; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f); + + array = mock_array(1, f); + if (!array) + return -ENOMEM; + + chain = mock_chain(NULL, array); + if (!chain) + return -ENOMEM; + + dma_fence_put(chain); + return err; +} + +static int unwrap_array(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *array; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f1); + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + dma_fence_enable_sw_signaling(f2); + + array = mock_array(2, f1, f2); + if (!array) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, array) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_put(array); + return err; +} + +static int unwrap_chain(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *chain; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f1); + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + dma_fence_enable_sw_signaling(f2); + + chain = mock_chain(f1, f2); + if (!chain) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, chain) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_put(chain); + return err; +} + +static int unwrap_chain_array(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *array, *chain; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f1); + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + dma_fence_enable_sw_signaling(f2); + + array = mock_array(2, f1, f2); + if (!array) + return -ENOMEM; + + chain = mock_chain(NULL, array); + if (!chain) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, chain) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_put(chain); + return err; +} + +static int unwrap_merge(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *f3; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f1); + + f2 = mock_fence(); + if (!f2) { + err = -ENOMEM; + goto error_put_f1; + } + + dma_fence_enable_sw_signaling(f2); + + f3 = dma_fence_unwrap_merge(f1, f2); + if (!f3) { + err = -ENOMEM; + goto error_put_f2; + } + + dma_fence_unwrap_for_each(fence, &iter, f3) { + if (fence == f1) { + dma_fence_put(f1); + f1 = NULL; + } else if (fence == f2) { + dma_fence_put(f2); + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_put(f3); +error_put_f2: + dma_fence_put(f2); +error_put_f1: + dma_fence_put(f1); + return err; +} + +static int unwrap_merge_duplicate(void *arg) +{ + struct dma_fence *fence, *f1, *f2; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f1); + + f2 = dma_fence_unwrap_merge(f1, f1); + if (!f2) { + err = -ENOMEM; + goto error_put_f1; + } + + dma_fence_unwrap_for_each(fence, &iter, f2) { + if (fence == f1) { + dma_fence_put(f1); + f1 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_put(f2); +error_put_f1: + dma_fence_put(f1); + return err; +} + +static int unwrap_merge_seqno(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *f3, *f4; + struct dma_fence_unwrap iter; + int err = 0; + u64 ctx[2]; + + ctx[0] = dma_fence_context_alloc(1); + ctx[1] = dma_fence_context_alloc(1); + + f1 = __mock_fence(ctx[1], 1); + if (!f1) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f1); + + f2 = __mock_fence(ctx[1], 2); + if (!f2) { + err = -ENOMEM; + goto error_put_f1; + } + + dma_fence_enable_sw_signaling(f2); + + f3 = __mock_fence(ctx[0], 1); + if (!f3) { + err = -ENOMEM; + goto error_put_f2; + } + + dma_fence_enable_sw_signaling(f3); + + f4 = dma_fence_unwrap_merge(f1, f2, f3); + if (!f4) { + err = -ENOMEM; + goto error_put_f3; + } + + dma_fence_unwrap_for_each(fence, &iter, f4) { + if (fence == f3 && f2) { + dma_fence_put(f3); + f3 = NULL; + } else if (fence == f2 && !f3) { + dma_fence_put(f2); + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f2 || f3) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_put(f4); +error_put_f3: + dma_fence_put(f3); +error_put_f2: + dma_fence_put(f2); +error_put_f1: + dma_fence_put(f1); + return err; +} + +static int unwrap_merge_order(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *a1, *a2, *c1, *c2; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f1); + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + dma_fence_enable_sw_signaling(f2); + + a1 = mock_array(2, f1, f2); + if (!a1) + return -ENOMEM; + + c1 = mock_chain(NULL, dma_fence_get(f1)); + if (!c1) + goto error_put_a1; + + c2 = mock_chain(c1, dma_fence_get(f2)); + if (!c2) + goto error_put_a1; + + /* + * The fences in the chain are the same as in a1 but in oposite order, + * the dma_fence_merge() function should be able to handle that. + */ + a2 = dma_fence_unwrap_merge(a1, c2); + + dma_fence_unwrap_for_each(fence, &iter, a2) { + if (fence == f1) { + f1 = NULL; + if (!f2) + pr_err("Unexpected order!\n"); + } else if (fence == f2) { + f2 = NULL; + if (f1) + pr_err("Unexpected order!\n"); + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_put(a2); + return err; + +error_put_a1: + dma_fence_put(a1); + return -ENOMEM; +} + +static int unwrap_merge_complex(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *f3, *f4, *f5; + struct dma_fence_unwrap iter; + int err = -ENOMEM; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f1); + + f2 = mock_fence(); + if (!f2) + goto error_put_f1; + + dma_fence_enable_sw_signaling(f2); + + f3 = dma_fence_unwrap_merge(f1, f2); + if (!f3) + goto error_put_f2; + + /* The resulting array has the fences in reverse */ + f4 = mock_array(2, dma_fence_get(f2), dma_fence_get(f1)); + if (!f4) + goto error_put_f3; + + /* Signaled fences should be filtered, the two arrays merged. */ + f5 = dma_fence_unwrap_merge(f3, f4, dma_fence_get_stub()); + if (!f5) + goto error_put_f4; + + err = 0; + dma_fence_unwrap_for_each(fence, &iter, f5) { + if (fence == f1) { + dma_fence_put(f1); + f1 = NULL; + } else if (fence == f2) { + dma_fence_put(f2); + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_put(f5); +error_put_f4: + dma_fence_put(f4); +error_put_f3: + dma_fence_put(f3); +error_put_f2: + dma_fence_put(f2); +error_put_f1: + dma_fence_put(f1); + return err; +} + +static int unwrap_merge_complex_seqno(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *f3, *f4, *f5, *f6, *f7; + struct dma_fence_unwrap iter; + int err = -ENOMEM; + u64 ctx[2]; + + ctx[0] = dma_fence_context_alloc(1); + ctx[1] = dma_fence_context_alloc(1); + + f1 = __mock_fence(ctx[0], 2); + if (!f1) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f1); + + f2 = __mock_fence(ctx[1], 1); + if (!f2) + goto error_put_f1; + + dma_fence_enable_sw_signaling(f2); + + f3 = __mock_fence(ctx[0], 1); + if (!f3) + goto error_put_f2; + + dma_fence_enable_sw_signaling(f3); + + f4 = __mock_fence(ctx[1], 2); + if (!f4) + goto error_put_f3; + + dma_fence_enable_sw_signaling(f4); + + f5 = mock_array(2, dma_fence_get(f1), dma_fence_get(f2)); + if (!f5) + goto error_put_f4; + + f6 = mock_array(2, dma_fence_get(f3), dma_fence_get(f4)); + if (!f6) + goto error_put_f5; + + f7 = dma_fence_unwrap_merge(f5, f6); + if (!f7) + goto error_put_f6; + + err = 0; + dma_fence_unwrap_for_each(fence, &iter, f7) { + if (fence == f1 && f4) { + dma_fence_put(f1); + f1 = NULL; + } else if (fence == f4 && !f1) { + dma_fence_put(f4); + f4 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f4) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_put(f7); +error_put_f6: + dma_fence_put(f6); +error_put_f5: + dma_fence_put(f5); +error_put_f4: + dma_fence_put(f4); +error_put_f3: + dma_fence_put(f3); +error_put_f2: + dma_fence_put(f2); +error_put_f1: + dma_fence_put(f1); + return err; +} + +int dma_fence_unwrap(void) +{ + static const struct subtest tests[] = { + SUBTEST(sanitycheck), + SUBTEST(unwrap_array), + SUBTEST(unwrap_chain), + SUBTEST(unwrap_chain_array), + SUBTEST(unwrap_merge), + SUBTEST(unwrap_merge_duplicate), + SUBTEST(unwrap_merge_seqno), + SUBTEST(unwrap_merge_order), + SUBTEST(unwrap_merge_complex), + SUBTEST(unwrap_merge_complex_seqno), + }; + + return subtests(tests, NULL); +} diff --git a/drivers/dma-buf/st-dma-fence.c b/drivers/dma-buf/st-dma-fence.c new file mode 100644 index 000000000000..27a36045410b --- /dev/null +++ b/drivers/dma-buf/st-dma-fence.c @@ -0,0 +1,597 @@ +/* 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_enable_sw_signaling(f); + + 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; + + dma_fence_enable_sw_signaling(f); + + 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_enable_sw_signaling(f); + + 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; + + dma_fence_enable_sw_signaling(f); + + if (dma_fence_get_status(f)) { + pr_err("Fence unexpectedly has signaled status on creation\n"); + goto err_free; + } + + 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_enable_sw_signaling(f); + + 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; + + dma_fence_enable_sw_signaling(f); + + if (dma_fence_wait_timeout(f, false, 0) != -ETIME) { + pr_err("Wait reported complete before being signaled\n"); + goto err_free; + } + + 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 = timer_container_of(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; + + dma_fence_enable_sw_signaling(wt.f); + + if (dma_fence_wait_timeout(wt.f, false, 1) != -ETIME) { + pr_err("Wait reported complete before being signaled\n"); + goto err_free; + } + + 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 jiffy!\n"); + err = 0; /* not our fault! */ + } else { + pr_err("Wait reported incomplete after timeout\n"); + } + goto err_free; + } + + err = 0; +err_free: + timer_delete_sync(&wt.timer); + timer_destroy_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; + } + + dma_fence_enable_sw_signaling(f1); + + 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); + if (IS_ERR(t[i].task)) { + ret = PTR_ERR(t[i].task); + while (--i >= 0) + kthread_stop_put(t[i].task); + return ret; + } + get_task_struct(t[i].task); + } + + msleep(50); + + for (i = 0; i < ARRAY_SIZE(t); i++) { + int err; + + err = kthread_stop_put(t[i].task); + if (err && !ret) + ret = err; + } + } + + 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/st-dma-resv.c b/drivers/dma-buf/st-dma-resv.c new file mode 100644 index 000000000000..15dbea1462ed --- /dev/null +++ b/drivers/dma-buf/st-dma-resv.c @@ -0,0 +1,316 @@ +/* SPDX-License-Identifier: MIT */ + +/* +* Copyright © 2019 Intel Corporation +* Copyright © 2021 Advanced Micro Devices, Inc. +*/ + +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/dma-resv.h> + +#include "selftest.h" + +static struct spinlock fence_lock; + +static const char *fence_name(struct dma_fence *f) +{ + return "selftest"; +} + +static const struct dma_fence_ops fence_ops = { + .get_driver_name = fence_name, + .get_timeline_name = fence_name, +}; + +static struct dma_fence *alloc_fence(void) +{ + struct dma_fence *f; + + f = kmalloc(sizeof(*f), GFP_KERNEL); + if (!f) + return NULL; + + dma_fence_init(f, &fence_ops, &fence_lock, 0, 0); + return f; +} + +static int sanitycheck(void *arg) +{ + struct dma_resv resv; + struct dma_fence *f; + int r; + + f = alloc_fence(); + if (!f) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f); + + dma_fence_signal(f); + dma_fence_put(f); + + dma_resv_init(&resv); + r = dma_resv_lock(&resv, NULL); + if (r) + pr_err("Resv locking failed\n"); + else + dma_resv_unlock(&resv); + dma_resv_fini(&resv); + return r; +} + +static int test_signaling(void *arg) +{ + enum dma_resv_usage usage = (unsigned long)arg; + struct dma_resv resv; + struct dma_fence *f; + int r; + + f = alloc_fence(); + if (!f) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f); + + dma_resv_init(&resv); + r = dma_resv_lock(&resv, NULL); + if (r) { + pr_err("Resv locking failed\n"); + goto err_free; + } + + r = dma_resv_reserve_fences(&resv, 1); + if (r) { + pr_err("Resv shared slot allocation failed\n"); + goto err_unlock; + } + + dma_resv_add_fence(&resv, f, usage); + if (dma_resv_test_signaled(&resv, usage)) { + pr_err("Resv unexpectedly signaled\n"); + r = -EINVAL; + goto err_unlock; + } + dma_fence_signal(f); + if (!dma_resv_test_signaled(&resv, usage)) { + pr_err("Resv not reporting signaled\n"); + r = -EINVAL; + goto err_unlock; + } +err_unlock: + dma_resv_unlock(&resv); +err_free: + dma_resv_fini(&resv); + dma_fence_put(f); + return r; +} + +static int test_for_each(void *arg) +{ + enum dma_resv_usage usage = (unsigned long)arg; + struct dma_resv_iter cursor; + struct dma_fence *f, *fence; + struct dma_resv resv; + int r; + + f = alloc_fence(); + if (!f) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f); + + dma_resv_init(&resv); + r = dma_resv_lock(&resv, NULL); + if (r) { + pr_err("Resv locking failed\n"); + goto err_free; + } + + r = dma_resv_reserve_fences(&resv, 1); + if (r) { + pr_err("Resv shared slot allocation failed\n"); + goto err_unlock; + } + + dma_resv_add_fence(&resv, f, usage); + + r = -ENOENT; + dma_resv_for_each_fence(&cursor, &resv, usage, fence) { + if (!r) { + pr_err("More than one fence found\n"); + r = -EINVAL; + goto err_unlock; + } + if (f != fence) { + pr_err("Unexpected fence\n"); + r = -EINVAL; + goto err_unlock; + } + if (dma_resv_iter_usage(&cursor) != usage) { + pr_err("Unexpected fence usage\n"); + r = -EINVAL; + goto err_unlock; + } + r = 0; + } + if (r) { + pr_err("No fence found\n"); + goto err_unlock; + } + dma_fence_signal(f); +err_unlock: + dma_resv_unlock(&resv); +err_free: + dma_resv_fini(&resv); + dma_fence_put(f); + return r; +} + +static int test_for_each_unlocked(void *arg) +{ + enum dma_resv_usage usage = (unsigned long)arg; + struct dma_resv_iter cursor; + struct dma_fence *f, *fence; + struct dma_resv resv; + int r; + + f = alloc_fence(); + if (!f) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f); + + dma_resv_init(&resv); + r = dma_resv_lock(&resv, NULL); + if (r) { + pr_err("Resv locking failed\n"); + goto err_free; + } + + r = dma_resv_reserve_fences(&resv, 1); + if (r) { + pr_err("Resv shared slot allocation failed\n"); + dma_resv_unlock(&resv); + goto err_free; + } + + dma_resv_add_fence(&resv, f, usage); + dma_resv_unlock(&resv); + + r = -ENOENT; + dma_resv_iter_begin(&cursor, &resv, usage); + dma_resv_for_each_fence_unlocked(&cursor, fence) { + if (!r) { + pr_err("More than one fence found\n"); + r = -EINVAL; + goto err_iter_end; + } + if (!dma_resv_iter_is_restarted(&cursor)) { + pr_err("No restart flag\n"); + goto err_iter_end; + } + if (f != fence) { + pr_err("Unexpected fence\n"); + r = -EINVAL; + goto err_iter_end; + } + if (dma_resv_iter_usage(&cursor) != usage) { + pr_err("Unexpected fence usage\n"); + r = -EINVAL; + goto err_iter_end; + } + + /* We use r as state here */ + if (r == -ENOENT) { + r = -EINVAL; + /* That should trigger an restart */ + cursor.fences = (void*)~0; + } else if (r == -EINVAL) { + r = 0; + } + } + if (r) + pr_err("No fence found\n"); +err_iter_end: + dma_resv_iter_end(&cursor); + dma_fence_signal(f); +err_free: + dma_resv_fini(&resv); + dma_fence_put(f); + return r; +} + +static int test_get_fences(void *arg) +{ + enum dma_resv_usage usage = (unsigned long)arg; + struct dma_fence *f, **fences = NULL; + struct dma_resv resv; + int r, i; + + f = alloc_fence(); + if (!f) + return -ENOMEM; + + dma_fence_enable_sw_signaling(f); + + dma_resv_init(&resv); + r = dma_resv_lock(&resv, NULL); + if (r) { + pr_err("Resv locking failed\n"); + goto err_resv; + } + + r = dma_resv_reserve_fences(&resv, 1); + if (r) { + pr_err("Resv shared slot allocation failed\n"); + dma_resv_unlock(&resv); + goto err_resv; + } + + dma_resv_add_fence(&resv, f, usage); + dma_resv_unlock(&resv); + + r = dma_resv_get_fences(&resv, usage, &i, &fences); + if (r) { + pr_err("get_fences failed\n"); + goto err_free; + } + + if (i != 1 || fences[0] != f) { + pr_err("get_fences returned unexpected fence\n"); + goto err_free; + } + + dma_fence_signal(f); +err_free: + while (i--) + dma_fence_put(fences[i]); + kfree(fences); +err_resv: + dma_resv_fini(&resv); + dma_fence_put(f); + return r; +} + +int dma_resv(void) +{ + static const struct subtest tests[] = { + SUBTEST(sanitycheck), + SUBTEST(test_signaling), + SUBTEST(test_for_each), + SUBTEST(test_for_each_unlocked), + SUBTEST(test_get_fences), + }; + enum dma_resv_usage usage; + int r; + + spin_lock_init(&fence_lock); + for (usage = DMA_RESV_USAGE_KERNEL; usage <= DMA_RESV_USAGE_BOOKKEEP; + ++usage) { + r = subtests(tests, (void *)(unsigned long)usage); + if (r) + return r; + } + return 0; +} diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c index 53c1d6d36a64..6f09d13be6b6 100644 --- a/drivers/dma-buf/sw_sync.c +++ b/drivers/dma-buf/sw_sync.c @@ -1,22 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * 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/panic.h> #include <linux/slab.h> #include <linux/sync_file.h> @@ -61,12 +53,33 @@ struct sw_sync_create_fence_data { __s32 fence; /* fd of new fence */ }; +/** + * struct sw_sync_get_deadline - get the deadline hint of a sw_sync fence + * @deadline_ns: absolute time of the deadline + * @pad: must be zero + * @fence_fd: the sw_sync fence fd (in) + * + * Return the earliest deadline set on the fence. The timebase for the + * deadline is CLOCK_MONOTONIC (same as vblank). If there is no deadline + * set on the fence, this ioctl will return -ENOENT. + */ +struct sw_sync_get_deadline { + __u64 deadline_ns; + __u32 pad; + __s32 fence_fd; +}; + #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) +#define SW_SYNC_GET_DEADLINE _IOWR(SW_SYNC_IOC_MAGIC, 2, \ + struct sw_sync_get_deadline) + + +#define SW_SYNC_HAS_DEADLINE_BIT DMA_FENCE_FLAG_USER_BITS static const struct dma_fence_ops timeline_fence_ops; @@ -94,7 +107,7 @@ static struct sync_timeline *sync_timeline_create(const char *name) kref_init(&obj->kref); obj->context = dma_fence_context_alloc(1); - strlcpy(obj->name, name, sizeof(obj->name)); + strscpy(obj->name, name, sizeof(obj->name)); obj->pt_tree = RB_ROOT; INIT_LIST_HEAD(&obj->pt_list); @@ -141,17 +154,14 @@ 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); @@ -161,36 +171,31 @@ 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; + return !__dma_fence_is_later(fence, fence->seqno, parent->value); } -static void timeline_fence_value_str(struct dma_fence *fence, - char *str, int size) +static void timeline_fence_set_deadline(struct dma_fence *fence, ktime_t deadline) { - 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); + struct sync_pt *pt = dma_fence_to_sync_pt(fence); + unsigned long flags; + + spin_lock_irqsave(fence->lock, flags); + if (test_bit(SW_SYNC_HAS_DEADLINE_BIT, &fence->flags)) { + if (ktime_before(deadline, pt->deadline)) + pt->deadline = deadline; + } else { + pt->deadline = deadline; + __set_bit(SW_SYNC_HAS_DEADLINE_BIT, &fence->flags); + } + spin_unlock_irqrestore(fence->lock, flags); } 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, + .set_deadline = timeline_fence_set_deadline, }; /** @@ -203,6 +208,7 @@ static const struct dma_fence_ops timeline_fence_ops = { */ static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc) { + LIST_HEAD(signalled); struct sync_pt *pt, *next; trace_sync_timeline(obj); @@ -215,21 +221,20 @@ static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc) if (!timeline_fence_signaled(&pt->base)) break; - list_del_init(&pt->link); + dma_fence_get(&pt->base); + + list_move_tail(&pt->link, &signalled); 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); + + list_for_each_entry_safe(pt, next, &signalled, link) { + list_del_init(&pt->link); + dma_fence_put(&pt->base); + } } /** @@ -274,7 +279,8 @@ 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; } @@ -344,6 +350,9 @@ static long sw_sync_ioctl_create_fence(struct sync_timeline *obj, struct sync_file *sync_file; struct sw_sync_create_fence_data data; + /* SW sync fence are inherently unsafe and can deadlock the kernel */ + add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK); + if (fd < 0) return fd; @@ -398,6 +407,56 @@ static long sw_sync_ioctl_inc(struct sync_timeline *obj, unsigned long arg) return 0; } +static int sw_sync_ioctl_get_deadline(struct sync_timeline *obj, unsigned long arg) +{ + struct sw_sync_get_deadline data; + struct dma_fence *fence; + unsigned long flags; + struct sync_pt *pt; + int ret = 0; + + if (copy_from_user(&data, (void __user *)arg, sizeof(data))) + return -EFAULT; + + if (data.deadline_ns || data.pad) + return -EINVAL; + + fence = sync_file_get_fence(data.fence_fd); + if (!fence) + return -EINVAL; + + pt = dma_fence_to_sync_pt(fence); + if (!pt) { + ret = -EINVAL; + goto put_fence; + } + + spin_lock_irqsave(fence->lock, flags); + if (!test_bit(SW_SYNC_HAS_DEADLINE_BIT, &fence->flags)) { + ret = -ENOENT; + goto unlock; + } + data.deadline_ns = ktime_to_ns(pt->deadline); + spin_unlock_irqrestore(fence->lock, flags); + + dma_fence_put(fence); + + if (ret) + return ret; + + if (copy_to_user((void __user *)arg, &data, sizeof(data))) + return -EFAULT; + + return 0; + +unlock: + spin_unlock_irqrestore(fence->lock, flags); +put_fence: + dma_fence_put(fence); + + return ret; +} + static long sw_sync_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -410,6 +469,9 @@ static long sw_sync_ioctl(struct file *file, unsigned int cmd, case SW_SYNC_IOC_INC: return sw_sync_ioctl_inc(obj, arg); + case SW_SYNC_GET_DEADLINE: + return sw_sync_ioctl_get_deadline(obj, arg); + default: return -ENOTTY; } @@ -419,5 +481,5 @@ 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_debug.c b/drivers/dma-buf/sync_debug.c index c4c8ecb24aa9..9e5d662cd4e8 100644 --- a/drivers/dma-buf/sync_debug.c +++ b/drivers/dma-buf/sync_debug.c @@ -1,17 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * 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> @@ -21,8 +12,6 @@ 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) { @@ -42,24 +31,6 @@ void sync_timeline_debug_remove(struct sync_timeline *obj) 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) @@ -88,28 +59,11 @@ static void sync_print_fence(struct seq_file *s, 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_printf(s, "@%ptSp", &ts64); } + seq_printf(s, ": %lld", fence->seqno); + seq_printf(s, " / %d", parent->value); seq_putc(s, '\n'); } @@ -119,35 +73,15 @@ static void sync_print_obj(struct seq_file *s, struct sync_timeline *obj) seq_printf(s, "%s: %d\n", obj->name, obj->value); - spin_lock_irq(&obj->lock); + spin_lock(&obj->lock); /* Caller already disabled IRQ. */ 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); + spin_unlock(&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) +static int sync_info_debugfs_show(struct seq_file *s, void *unused) { struct list_head *pos; @@ -166,29 +100,10 @@ static int sync_debugfs_show(struct seq_file *s, void *unused) 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, -}; +DEFINE_SHOW_ATTRIBUTE(sync_info_debugfs); static __init int sync_debugfs_init(void) { @@ -207,29 +122,3 @@ static __init int sync_debugfs_init(void) 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 index 05e33f937ad0..02af347293d0 100644 --- a/drivers/dma-buf/sync_debug.h +++ b/drivers/dma-buf/sync_debug.h @@ -55,19 +55,18 @@ static inline struct sync_timeline *dma_fence_parent(struct dma_fence *fence) * @base: base fence object * @link: link on the sync timeline's list * @node: node in the sync timeline's tree + * @deadline: the earliest fence deadline hint */ struct sync_pt { struct dma_fence base; struct list_head link; struct rb_node node; + ktime_t deadline; }; 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 index 35dd06479867..747e377fb954 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -1,19 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * 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/dma-fence-unwrap.h> #include <linux/export.h> #include <linux/file.h> #include <linux/fs.h> @@ -140,72 +132,26 @@ EXPORT_SYMBOL(sync_file_get_fence); char *sync_file_get_name(struct sync_file *sync_file, char *buf, int len) { if (sync_file->user_name[0]) { - strlcpy(buf, sync_file->user_name, len); + strscpy(buf, sync_file->user_name, len); } else { struct dma_fence *fence = sync_file->fence; - - snprintf(buf, len, "%s-%s%llu-%d", - fence->ops->get_driver_name(fence), - fence->ops->get_timeline_name(fence), + const char __rcu *timeline; + const char __rcu *driver; + + rcu_read_lock(); + driver = dma_fence_driver_name(fence); + timeline = dma_fence_timeline_name(fence); + snprintf(buf, len, "%s-%s%llu-%lld", + rcu_dereference(driver), + rcu_dereference(timeline), fence->context, fence->seqno); + rcu_read_unlock(); } 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 @@ -220,84 +166,20 @@ static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, struct sync_file *b) { struct sync_file *sync_file; - struct dma_fence **fences, **nfences, **a_fences, **b_fences; - int i, i_a, i_b, num_fences, a_num_fences, b_num_fences; + struct dma_fence *fence; sync_file = sync_file_alloc(); if (!sync_file) return NULL; - a_fences = get_fences(a, &a_num_fences); - b_fences = get_fences(b, &b_num_fences); - if (a_num_fences > INT_MAX - b_num_fences) + fence = dma_fence_unwrap_merge(a->fence, b->fence); + if (!fence) { + fput(sync_file->file); return NULL; - - 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 = 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) { - kfree(fences); - goto err; - } - - strlcpy(sync_file->user_name, name, sizeof(sync_file->user_name)); + sync_file->fence = fence; + strscpy(sync_file->user_name, name, sizeof(sync_file->user_name)); return sync_file; - -err: - fput(sync_file->file); - return NULL; - } static int sync_file_release(struct inode *inode, struct file *file) @@ -386,19 +268,26 @@ err_put_fd: static int sync_fill_fence_info(struct dma_fence *fence, struct sync_fence_info *info) { - strlcpy(info->obj_name, fence->ops->get_timeline_name(fence), + const char __rcu *timeline; + const char __rcu *driver; + + rcu_read_lock(); + + driver = dma_fence_driver_name(fence); + timeline = dma_fence_timeline_name(fence); + + strscpy(info->obj_name, rcu_dereference(timeline), sizeof(info->obj_name)); - strlcpy(info->driver_name, fence->ops->get_driver_name(fence), + strscpy(info->driver_name, rcu_dereference(driver), 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); + dma_fence_is_signaled(fence) ? + ktime_to_ns(dma_fence_timestamp(fence)) : + ktime_set(0, 0); + + rcu_read_unlock(); return info->status; } @@ -406,11 +295,13 @@ static int sync_fill_fence_info(struct dma_fence *fence, static long sync_file_ioctl_fence_info(struct sync_file *sync_file, unsigned long arg) { - struct sync_file_info info; struct sync_fence_info *fence_info = NULL; - struct dma_fence **fences; + struct dma_fence_unwrap iter; + struct sync_file_info info; + unsigned int num_fences; + struct dma_fence *fence; + int ret; __u32 size; - int num_fences, ret, i; if (copy_from_user(&info, (void __user *)arg, sizeof(info))) return -EFAULT; @@ -418,7 +309,9 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, if (info.flags || info.pad) return -EINVAL; - fences = get_fences(sync_file, &num_fences); + num_fences = 0; + dma_fence_unwrap_for_each(fence, &iter, sync_file->fence) + ++num_fences; /* * Passing num_fences = 0 means that userspace doesn't want to @@ -427,7 +320,7 @@ 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; @@ -441,8 +334,11 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, if (!fence_info) return -ENOMEM; - for (i = 0; i < num_fences; i++) { - int status = sync_fill_fence_info(fences[i], &fence_info[i]); + num_fences = 0; + dma_fence_unwrap_for_each(fence, &iter, sync_file->fence) { + int status; + + status = sync_fill_fence_info(fence, &fence_info[num_fences++]); info.status = info.status <= 0 ? info.status : status; } @@ -467,6 +363,22 @@ out: return ret; } +static int sync_file_ioctl_set_deadline(struct sync_file *sync_file, + unsigned long arg) +{ + struct sync_set_deadline ts; + + if (copy_from_user(&ts, (void __user *)arg, sizeof(ts))) + return -EFAULT; + + if (ts.pad) + return -EINVAL; + + dma_fence_set_deadline(sync_file->fence, ns_to_ktime(ts.deadline_ns)); + + return 0; +} + static long sync_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -479,6 +391,9 @@ static long sync_file_ioctl(struct file *file, unsigned int cmd, case SYNC_IOC_FILE_INFO: return sync_file_ioctl_fence_info(sync_file, arg); + case SYNC_IOC_SET_DEADLINE: + return sync_file_ioctl_set_deadline(sync_file, arg); + default: return -ENOTTY; } @@ -488,5 +403,5 @@ 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/sync_trace.h b/drivers/dma-buf/sync_trace.h index 06e468a218ff..d71dcf954b8d 100644 --- a/drivers/dma-buf/sync_trace.h +++ b/drivers/dma-buf/sync_trace.h @@ -20,7 +20,7 @@ TRACE_EVENT(sync_timeline, ), TP_fast_assign( - __assign_str(name, timeline->name); + __assign_str(name); __entry->value = timeline->value; ), diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index cd57747286f2..40399c26e6be 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -2,6 +2,7 @@ #include <linux/cred.h> #include <linux/device.h> #include <linux/dma-buf.h> +#include <linux/dma-resv.h> #include <linux/highmem.h> #include <linux/init.h> #include <linux/kernel.h> @@ -9,25 +10,83 @@ #include <linux/miscdevice.h> #include <linux/module.h> #include <linux/shmem_fs.h> +#include <linux/hugetlb.h> #include <linux/slab.h> #include <linux/udmabuf.h> +#include <linux/vmalloc.h> +#include <linux/iosys-map.h> -static const u32 list_limit = 1024; /* udmabuf_create_list->count limit */ -static const size_t size_limit_mb = 64; /* total dmabuf size, in megabytes */ +static int list_limit = 1024; +module_param(list_limit, int, 0644); +MODULE_PARM_DESC(list_limit, "udmabuf_create_list->count limit. Default is 1024."); + +static int size_limit_mb = 64; +module_param(size_limit_mb, int, 0644); +MODULE_PARM_DESC(size_limit_mb, "Max size of a dmabuf, in megabytes. Default is 64."); struct udmabuf { pgoff_t pagecount; - struct page **pages; + struct folio **folios; + + /** + * Unlike folios, pinned_folios is only used for unpin. + * So, nr_pinned is not the same to pagecount, the pinned_folios + * only set each folio which already pinned when udmabuf_create. + * Note that, since a folio may be pinned multiple times, each folio + * can be added to pinned_folios multiple times, depending on how many + * times the folio has been pinned when create. + */ + pgoff_t nr_pinned; + struct folio **pinned_folios; + + struct sg_table *sg; + struct miscdevice *device; + pgoff_t *offsets; }; static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct udmabuf *ubuf = vma->vm_private_data; + pgoff_t pgoff = vmf->pgoff; + unsigned long addr, pfn; + vm_fault_t ret; + + if (pgoff >= ubuf->pagecount) + return VM_FAULT_SIGBUS; + + pfn = folio_pfn(ubuf->folios[pgoff]); + pfn += ubuf->offsets[pgoff] >> PAGE_SHIFT; + + ret = vmf_insert_pfn(vma, vmf->address, pfn); + if (ret & VM_FAULT_ERROR) + return ret; + + /* pre fault */ + pgoff = vma->vm_pgoff; + addr = vma->vm_start; + + for (; addr < vma->vm_end; pgoff++, addr += PAGE_SIZE) { + if (addr == vmf->address) + continue; + + if (WARN_ON(pgoff >= ubuf->pagecount)) + break; + + pfn = folio_pfn(ubuf->folios[pgoff]); + pfn += ubuf->offsets[pgoff] >> PAGE_SHIFT; + + /** + * If the below vmf_insert_pfn() fails, we do not return an + * error here during this pre-fault step. However, an error + * will be returned if the failure occurs when the addr is + * truly accessed. + */ + if (vmf_insert_pfn(vma, addr, pfn) & VM_FAULT_ERROR) + break; + } - vmf->page = ubuf->pages[vmf->pgoff]; - get_page(vmf->page); - return 0; + return ret; } static const struct vm_operations_struct udmabuf_vm_ops = { @@ -43,167 +102,368 @@ static int mmap_udmabuf(struct dma_buf *buf, struct vm_area_struct *vma) vma->vm_ops = &udmabuf_vm_ops; vma->vm_private_data = ubuf; + vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP); return 0; } -static struct sg_table *map_udmabuf(struct dma_buf_attachment *at, - enum dma_data_direction direction) +static int vmap_udmabuf(struct dma_buf *buf, struct iosys_map *map) { - struct udmabuf *ubuf = at->dmabuf->priv; + struct udmabuf *ubuf = buf->priv; + struct page **pages; + void *vaddr; + pgoff_t pg; + + dma_resv_assert_held(buf->resv); + + pages = kvmalloc_array(ubuf->pagecount, sizeof(*pages), GFP_KERNEL); + if (!pages) + return -ENOMEM; + + for (pg = 0; pg < ubuf->pagecount; pg++) + pages[pg] = folio_page(ubuf->folios[pg], + ubuf->offsets[pg] >> PAGE_SHIFT); + + vaddr = vm_map_ram(pages, ubuf->pagecount, -1); + kvfree(pages); + if (!vaddr) + return -EINVAL; + + iosys_map_set_vaddr(map, vaddr); + return 0; +} + +static void vunmap_udmabuf(struct dma_buf *buf, struct iosys_map *map) +{ + struct udmabuf *ubuf = buf->priv; + + dma_resv_assert_held(buf->resv); + + vm_unmap_ram(map->vaddr, ubuf->pagecount); +} + +static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf, + enum dma_data_direction direction) +{ + struct udmabuf *ubuf = buf->priv; struct sg_table *sg; + struct scatterlist *sgl; + unsigned int i = 0; int ret; sg = kzalloc(sizeof(*sg), GFP_KERNEL); if (!sg) return ERR_PTR(-ENOMEM); - ret = sg_alloc_table_from_pages(sg, ubuf->pages, ubuf->pagecount, - 0, ubuf->pagecount << PAGE_SHIFT, - GFP_KERNEL); + + ret = sg_alloc_table(sg, ubuf->pagecount, GFP_KERNEL); if (ret < 0) - goto err; - if (!dma_map_sg(at->dev, sg->sgl, sg->nents, direction)) { - ret = -EINVAL; - goto err; - } + goto err_alloc; + + for_each_sg(sg->sgl, sgl, ubuf->pagecount, i) + sg_set_folio(sgl, ubuf->folios[i], PAGE_SIZE, + ubuf->offsets[i]); + + ret = dma_map_sgtable(dev, sg, direction, 0); + if (ret < 0) + goto err_map; return sg; -err: +err_map: sg_free_table(sg); +err_alloc: kfree(sg); return ERR_PTR(ret); } +static void put_sg_table(struct device *dev, struct sg_table *sg, + enum dma_data_direction direction) +{ + dma_unmap_sgtable(dev, sg, direction, 0); + sg_free_table(sg); + kfree(sg); +} + +static struct sg_table *map_udmabuf(struct dma_buf_attachment *at, + enum dma_data_direction direction) +{ + return get_sg_table(at->dev, at->dmabuf, direction); +} + static void unmap_udmabuf(struct dma_buf_attachment *at, struct sg_table *sg, enum dma_data_direction direction) { - sg_free_table(sg); - kfree(sg); + return put_sg_table(at->dev, sg, direction); +} + +static void unpin_all_folios(struct udmabuf *ubuf) +{ + pgoff_t i; + + for (i = 0; i < ubuf->nr_pinned; ++i) + unpin_folio(ubuf->pinned_folios[i]); + + kvfree(ubuf->pinned_folios); +} + +static __always_inline int init_udmabuf(struct udmabuf *ubuf, pgoff_t pgcnt) +{ + ubuf->folios = kvmalloc_array(pgcnt, sizeof(*ubuf->folios), GFP_KERNEL); + if (!ubuf->folios) + return -ENOMEM; + + ubuf->offsets = kvcalloc(pgcnt, sizeof(*ubuf->offsets), GFP_KERNEL); + if (!ubuf->offsets) + return -ENOMEM; + + ubuf->pinned_folios = kvmalloc_array(pgcnt, + sizeof(*ubuf->pinned_folios), + GFP_KERNEL); + if (!ubuf->pinned_folios) + return -ENOMEM; + + return 0; +} + +static __always_inline void deinit_udmabuf(struct udmabuf *ubuf) +{ + unpin_all_folios(ubuf); + kvfree(ubuf->offsets); + kvfree(ubuf->folios); } static void release_udmabuf(struct dma_buf *buf) { struct udmabuf *ubuf = buf->priv; - pgoff_t pg; + struct device *dev = ubuf->device->this_device; - for (pg = 0; pg < ubuf->pagecount; pg++) - put_page(ubuf->pages[pg]); - kfree(ubuf->pages); + if (ubuf->sg) + put_sg_table(dev, ubuf->sg, DMA_BIDIRECTIONAL); + + deinit_udmabuf(ubuf); 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; + int ret = 0; + + if (!ubuf->sg) { + ubuf->sg = get_sg_table(dev, buf, direction); + if (IS_ERR(ubuf->sg)) { + ret = PTR_ERR(ubuf->sg); + ubuf->sg = NULL; + } + } else { + dma_sync_sgtable_for_cpu(dev, ubuf->sg, direction); + } - return kmap(page); + return ret; } -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_sgtable_for_device(dev, ubuf->sg, 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, + .map_dma_buf = map_udmabuf, + .unmap_dma_buf = unmap_udmabuf, + .release = release_udmabuf, + .mmap = mmap_udmabuf, + .vmap = vmap_udmabuf, + .vunmap = vunmap_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) +#define SEALS_DENIED (F_SEAL_WRITE|F_SEAL_FUTURE_WRITE) + +static int check_memfd_seals(struct file *memfd) +{ + int seals; + + if (!shmem_file(memfd) && !is_file_hugepages(memfd)) + return -EBADFD; + + seals = memfd_fcntl(memfd, F_GET_SEALS, 0); + if (seals == -EINVAL) + return -EBADFD; + + if ((seals & SEALS_WANTED) != SEALS_WANTED || + (seals & SEALS_DENIED) != 0) + return -EINVAL; -static long udmabuf_create(const struct udmabuf_create_list *head, - const struct udmabuf_create_item *list) + return 0; +} + +static struct dma_buf *export_udmabuf(struct udmabuf *ubuf, + struct miscdevice *device) { DEFINE_DMA_BUF_EXPORT_INFO(exp_info); - struct file *memfd = NULL; + + ubuf->device = device; + exp_info.ops = &udmabuf_ops; + exp_info.size = ubuf->pagecount << PAGE_SHIFT; + exp_info.priv = ubuf; + exp_info.flags = O_RDWR; + + return dma_buf_export(&exp_info); +} + +static long udmabuf_pin_folios(struct udmabuf *ubuf, struct file *memfd, + loff_t start, loff_t size, struct folio **folios) +{ + pgoff_t nr_pinned = ubuf->nr_pinned; + pgoff_t upgcnt = ubuf->pagecount; + u32 cur_folio, cur_pgcnt; + pgoff_t pgoff, pgcnt; + long nr_folios; + loff_t end; + + pgcnt = size >> PAGE_SHIFT; + end = start + (pgcnt << PAGE_SHIFT) - 1; + nr_folios = memfd_pin_folios(memfd, start, end, folios, pgcnt, &pgoff); + if (nr_folios <= 0) + return nr_folios ? nr_folios : -EINVAL; + + cur_pgcnt = 0; + for (cur_folio = 0; cur_folio < nr_folios; ++cur_folio) { + pgoff_t subpgoff = pgoff; + size_t fsize = folio_size(folios[cur_folio]); + + ubuf->pinned_folios[nr_pinned++] = folios[cur_folio]; + + for (; subpgoff < fsize; subpgoff += PAGE_SIZE) { + ubuf->folios[upgcnt] = folios[cur_folio]; + ubuf->offsets[upgcnt] = subpgoff; + ++upgcnt; + + if (++cur_pgcnt >= pgcnt) + goto end; + } + + /** + * In a given range, only the first subpage of the first folio + * has an offset, that is returned by memfd_pin_folios(). + * The first subpages of other folios (in the range) have an + * offset of 0. + */ + pgoff = 0; + } +end: + ubuf->pagecount = upgcnt; + ubuf->nr_pinned = nr_pinned; + return 0; +} + +static long udmabuf_create(struct miscdevice *device, + struct udmabuf_create_list *head, + struct udmabuf_create_item *list) +{ + unsigned long max_nr_folios = 0; + struct folio **folios = NULL; + pgoff_t pgcnt = 0, pglimit; struct udmabuf *ubuf; - struct dma_buf *buf; - pgoff_t pgoff, pgcnt, pgidx, pgbuf = 0, pglimit; - struct page *page; - int seals, ret = -EINVAL; + struct dma_buf *dmabuf; + long ret = -EINVAL; u32 i, flags; ubuf = kzalloc(sizeof(*ubuf), GFP_KERNEL); if (!ubuf) return -ENOMEM; - pglimit = (size_limit_mb * 1024 * 1024) >> PAGE_SHIFT; + pglimit = ((u64)size_limit_mb * 1024 * 1024) >> PAGE_SHIFT; for (i = 0; i < head->count; i++) { - if (!IS_ALIGNED(list[i].offset, PAGE_SIZE)) - goto err; - if (!IS_ALIGNED(list[i].size, PAGE_SIZE)) - goto err; - ubuf->pagecount += list[i].size >> PAGE_SHIFT; - if (ubuf->pagecount > pglimit) - goto err; + pgoff_t subpgcnt; + + if (!PAGE_ALIGNED(list[i].offset)) + goto err_noinit; + if (!PAGE_ALIGNED(list[i].size)) + goto err_noinit; + + subpgcnt = list[i].size >> PAGE_SHIFT; + pgcnt += subpgcnt; + if (pgcnt > pglimit) + goto err_noinit; + + max_nr_folios = max_t(unsigned long, subpgcnt, max_nr_folios); } - ubuf->pages = kmalloc_array(ubuf->pagecount, sizeof(*ubuf->pages), - GFP_KERNEL); - if (!ubuf->pages) { + + if (!pgcnt) + goto err_noinit; + + ret = init_udmabuf(ubuf, pgcnt); + if (ret) + goto err; + + folios = kvmalloc_array(max_nr_folios, sizeof(*folios), GFP_KERNEL); + if (!folios) { ret = -ENOMEM; goto err; } - pgbuf = 0; for (i = 0; i < head->count; i++) { - ret = -EBADFD; - memfd = fget(list[i].memfd); - if (!memfd) - goto err; - if (!shmem_mapping(file_inode(memfd)->i_mapping)) - goto err; - seals = memfd_fcntl(memfd, F_GET_SEALS, 0); - if (seals == -EINVAL) - goto err; - ret = -EINVAL; - if ((seals & SEALS_WANTED) != SEALS_WANTED || - (seals & SEALS_DENIED) != 0) + struct file *memfd = fget(list[i].memfd); + + if (!memfd) { + ret = -EBADFD; goto err; - pgoff = list[i].offset >> PAGE_SHIFT; - pgcnt = list[i].size >> PAGE_SHIFT; - for (pgidx = 0; pgidx < pgcnt; pgidx++) { - page = shmem_read_mapping_page( - file_inode(memfd)->i_mapping, pgoff + pgidx); - if (IS_ERR(page)) { - ret = PTR_ERR(page); - goto err; - } - ubuf->pages[pgbuf++] = page; } + + /* + * Take the inode lock to protect against concurrent + * memfd_add_seals(), which takes this lock in write mode. + */ + inode_lock_shared(file_inode(memfd)); + ret = check_memfd_seals(memfd); + if (ret) + goto out_unlock; + + ret = udmabuf_pin_folios(ubuf, memfd, list[i].offset, + list[i].size, folios); +out_unlock: + inode_unlock_shared(file_inode(memfd)); fput(memfd); - memfd = NULL; + if (ret) + goto err; } - exp_info.ops = &udmabuf_ops; - exp_info.size = ubuf->pagecount << PAGE_SHIFT; - exp_info.priv = ubuf; - exp_info.flags = O_RDWR; - - buf = dma_buf_export(&exp_info); - if (IS_ERR(buf)) { - ret = PTR_ERR(buf); + flags = head->flags & UDMABUF_FLAGS_CLOEXEC ? O_CLOEXEC : 0; + dmabuf = export_udmabuf(ubuf, device); + if (IS_ERR(dmabuf)) { + ret = PTR_ERR(dmabuf); goto err; } + /* + * Ownership of ubuf is held by the dmabuf from here. + * If the following dma_buf_fd() fails, dma_buf_put() cleans up both the + * dmabuf and the ubuf (through udmabuf_ops.release). + */ + + ret = dma_buf_fd(dmabuf, flags); + if (ret < 0) + dma_buf_put(dmabuf); - flags = 0; - if (head->flags & UDMABUF_FLAGS_CLOEXEC) - flags |= O_CLOEXEC; - return dma_buf_fd(buf, flags); + kvfree(folios); + return ret; err: - while (pgbuf > 0) - put_page(ubuf->pages[--pgbuf]); - if (memfd) - fput(memfd); - kfree(ubuf->pages); + deinit_udmabuf(ubuf); +err_noinit: kfree(ubuf); + kvfree(folios); return ret; } @@ -223,7 +483,7 @@ 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) @@ -242,7 +502,7 @@ 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; } @@ -269,6 +529,9 @@ static long udmabuf_ioctl(struct file *filp, unsigned int ioctl, static const struct file_operations udmabuf_fops = { .owner = THIS_MODULE, .unlocked_ioctl = udmabuf_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = udmabuf_ioctl, +#endif }; static struct miscdevice udmabuf_misc = { @@ -279,7 +542,23 @@ static struct miscdevice udmabuf_misc = { static int __init udmabuf_dev_init(void) { - return misc_register(&udmabuf_misc); + int ret; + + ret = misc_register(&udmabuf_misc); + if (ret < 0) { + pr_err("Could not initialize udmabuf device\n"); + return ret; + } + + ret = dma_coerce_mask_and_coherent(udmabuf_misc.this_device, + DMA_BIT_MASK(64)); + if (ret < 0) { + pr_err("Could not setup DMA mask for udmabuf device\n"); + misc_deregister(&udmabuf_misc); + return ret; + } + + return 0; } static void __exit udmabuf_dev_exit(void) @@ -291,4 +570,3 @@ module_init(udmabuf_dev_init) module_exit(udmabuf_dev_exit) MODULE_AUTHOR("Gerd Hoffmann <kraxel@redhat.com>"); -MODULE_LICENSE("GPL v2"); |