diff options
| -rw-r--r-- | Documentation/dma-buf-sharing.txt | 120 | ||||
| -rw-r--r-- | drivers/base/dma-buf.c | 165 | ||||
| -rw-r--r-- | include/linux/dma-buf.h | 97 |
3 files changed, 345 insertions, 37 deletions
diff --git a/Documentation/dma-buf-sharing.txt b/Documentation/dma-buf-sharing.txt index 225f96d..3bbd5c5 100644 --- a/Documentation/dma-buf-sharing.txt +++ b/Documentation/dma-buf-sharing.txt @@ -32,8 +32,12 @@ The buffer-user *IMPORTANT*: [see https://lkml.org/lkml/2011/12/20/211 for more details] For this first version, A buffer shared using the dma_buf sharing API: - *may* be exported to user space using "mmap" *ONLY* by exporter, outside of - this framework. -- may be used *ONLY* by importers that do not need CPU access to the buffer. + this framework. +- with this new iteration of the dma-buf api cpu access from the kernel has been + enable, see below for the details. + +dma-buf operations for device dma only +-------------------------------------- The dma_buf buffer sharing API usage contains the following steps: @@ -219,10 +223,120 @@ NOTES: If the exporter chooses not to allow an attach() operation once a map_dma_buf() API has been called, it simply returns an error. -Miscellaneous notes: +Kernel cpu access to a dma-buf buffer object +-------------------------------------------- + +The motivation to allow cpu access from the kernel to a dma-buf object from the +importers side are: +- fallback operations, e.g. if the devices is connected to a usb bus and the + kernel needs to shuffle the data around first before sending it away. +- full transparency for existing users on the importer side, i.e. userspace + should not notice the difference between a normal object from that subsystem + and an imported one backed by a dma-buf. This is really important for drm + opengl drivers that expect to still use all the existing upload/download + paths. + +Access to a dma_buf from the kernel context involves three steps: + +1. Prepare access, which invalidate any necessary caches and make the object + available for cpu access. +2. Access the object page-by-page with the dma_buf map apis +3. Finish access, which will flush any necessary cpu caches and free reserved + resources. + +1. Prepare access + + Before an importer can access a dma_buf object with the cpu from the kernel + context, it needs to notify the exporter of the access that is about to + happen. + + Interface: + int dma_buf_begin_cpu_access(struct dma_buf *dmabuf, + size_t start, size_t len, + enum dma_data_direction direction) + + This allows the exporter to ensure that the memory is actually available for + cpu access - the exporter might need to allocate or swap-in and pin the + backing storage. The exporter also needs to ensure that cpu access is + coherent for the given range and access direction. The range and access + direction can be used by the exporter to optimize the cache flushing, i.e. + access outside of the range or with a different direction (read instead of + write) might return stale or even bogus data (e.g. when the exporter needs to + copy the data to temporary storage). + + This step might fail, e.g. in oom conditions. + +2. Accessing the buffer + + To support dma_buf objects residing in highmem cpu access is page-based using + an api similar to kmap. Accessing a dma_buf is done in aligned chunks of + PAGE_SIZE size. Before accessing a chunk it needs to be mapped, which returns + a pointer in kernel virtual address space. Afterwards the chunk needs to be + unmapped again. There is no limit on how often a given chunk can be mapped + and unmapped, i.e. the importer does not need to call begin_cpu_access again + before mapping the same chunk again. + + Interfaces: + void *dma_buf_kmap(struct dma_buf *, unsigned long); + void dma_buf_kunmap(struct dma_buf *, unsigned long, void *); + + There are also atomic variants of these interfaces. Like for kmap they + facilitate non-blocking fast-paths. Neither the importer nor the exporter (in + the callback) is allowed to block when using these. + + Interfaces: + void *dma_buf_kmap_atomic(struct dma_buf *, unsigned long); + void dma_buf_kunmap_atomic(struct dma_buf *, unsigned long, void *); + + For importers all the restrictions of using kmap apply, like the limited + supply of kmap_atomic slots. Hence an importer shall only hold onto at most 2 + atomic dma_buf kmaps at the same time (in any given process context). + + 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). + + Note that these calls need to always succeed. The exporter needs to complete + any preparations that might fail in begin_cpu_access. + +3. Finish access + + When the importer is done accessing the range specified in begin_cpu_access, + it needs to announce this to the exporter (to facilitate cache flushing and + unpinning of any pinned resources). The result of of any dma_buf kmap calls + after end_cpu_access is undefined. + + Interface: + void dma_buf_end_cpu_access(struct dma_buf *dma_buf, + size_t start, size_t len, + enum dma_data_direction dir); + + +Miscellaneous notes +------------------- + - Any exporters or users of the dma-buf buffer sharing framework must have a 'select DMA_SHARED_BUFFER' in their respective Kconfigs. +- In order to avoid fd leaks on exec, the FD_CLOEXEC flag must be set + on the file descriptor. This is not just a resource leak, but a + potential security hole. It could give the newly exec'd application + access to buffers, via the leaked fd, to which it should otherwise + not be permitted access. + + The problem with doing this via a separate fcntl() call, versus doing it + atomically when the fd is created, is that this is inherently racy in a + multi-threaded app[3]. The issue is made worse when it is library code + opening/creating the file descriptor, as the application may not even be + aware of the fd's. + + To avoid this problem, userspace must have a way to request O_CLOEXEC + flag be set when the dma-buf fd is created. So any API provided by + the exporting driver to create a dmabuf fd must provide a way to let + userspace control setting of O_CLOEXEC flag passed in to dma_buf_fd(). + References: [1] struct dma_buf_ops in include/linux/dma-buf.h [2] All interfaces mentioned above defined in include/linux/dma-buf.h +[3] https://lwn.net/Articles/236486/ diff --git a/drivers/base/dma-buf.c b/drivers/base/dma-buf.c index e38ad24..07cbbc6 100644 --- a/drivers/base/dma-buf.c +++ b/drivers/base/dma-buf.c @@ -71,7 +71,7 @@ static inline int is_dma_buf_file(struct file *file) * ops, or error in allocating struct dma_buf, will return negative error. * */ -struct dma_buf *dma_buf_export(void *priv, struct dma_buf_ops *ops, +struct dma_buf *dma_buf_export(void *priv, const struct dma_buf_ops *ops, size_t size, int flags) { struct dma_buf *dmabuf; @@ -80,7 +80,9 @@ struct dma_buf *dma_buf_export(void *priv, struct dma_buf_ops *ops, if (WARN_ON(!priv || !ops || !ops->map_dma_buf || !ops->unmap_dma_buf - || !ops->release)) { + || !ops->release + || !ops->kmap_atomic + || !ops->kmap)) { return ERR_PTR(-EINVAL); } @@ -107,17 +109,18 @@ EXPORT_SYMBOL_GPL(dma_buf_export); /** * dma_buf_fd - returns a file descriptor for the given dma_buf * @dmabuf: [in] pointer to dma_buf for which fd is required. + * @flags: [in] flags to give to fd * * On success, returns an associated 'fd'. Else, returns error. */ -int dma_buf_fd(struct dma_buf *dmabuf) +int dma_buf_fd(struct dma_buf *dmabuf, int flags) { int error, fd; if (!dmabuf || !dmabuf->file) return -EINVAL; - error = get_unused_fd(); + error = get_unused_fd_flags(flags); if (error < 0) return error; fd = error; @@ -185,17 +188,18 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach; int ret; - if (WARN_ON(!dmabuf || !dev || !dmabuf->ops)) + if (WARN_ON(!dmabuf || !dev)) return ERR_PTR(-EINVAL); attach = kzalloc(sizeof(struct dma_buf_attachment), GFP_KERNEL); if (attach == NULL) - goto err_alloc; - - mutex_lock(&dmabuf->lock); + return ERR_PTR(-ENOMEM); attach->dev = dev; attach->dmabuf = dmabuf; + + mutex_lock(&dmabuf->lock); + if (dmabuf->ops->attach) { ret = dmabuf->ops->attach(dmabuf, dev, attach); if (ret) @@ -206,8 +210,6 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, mutex_unlock(&dmabuf->lock); return attach; -err_alloc: - return ERR_PTR(-ENOMEM); err_attach: kfree(attach); mutex_unlock(&dmabuf->lock); @@ -224,7 +226,7 @@ EXPORT_SYMBOL_GPL(dma_buf_attach); */ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach) { - if (WARN_ON(!dmabuf || !attach || !dmabuf->ops)) + if (WARN_ON(!dmabuf || !attach)) return; mutex_lock(&dmabuf->lock); @@ -255,13 +257,10 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach, might_sleep(); - if (WARN_ON(!attach || !attach->dmabuf || !attach->dmabuf->ops)) + if (WARN_ON(!attach || !attach->dmabuf)) return ERR_PTR(-EINVAL); - mutex_lock(&attach->dmabuf->lock); - if (attach->dmabuf->ops->map_dma_buf) - sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction); - mutex_unlock(&attach->dmabuf->lock); + sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction); return sg_table; } @@ -273,19 +272,137 @@ EXPORT_SYMBOL_GPL(dma_buf_map_attachment); * 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 * */ void dma_buf_unmap_attachment(struct dma_buf_attachment *attach, - struct sg_table *sg_table) + struct sg_table *sg_table, + enum dma_data_direction direction) { - if (WARN_ON(!attach || !attach->dmabuf || !sg_table - || !attach->dmabuf->ops)) + if (WARN_ON(!attach || !attach->dmabuf || !sg_table)) return; - mutex_lock(&attach->dmabuf->lock); - if (attach->dmabuf->ops->unmap_dma_buf) - attach->dmabuf->ops->unmap_dma_buf(attach, sg_table); - mutex_unlock(&attach->dmabuf->lock); - + attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, + direction); } EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment); + + +/** + * dma_buf_begin_cpu_access - Must be called before accessing a dma_buf from the + * cpu in the kernel context. Calls begin_cpu_access to allow exporter-specific + * preparations. Coherency is only guaranteed in the specified range for the + * specified access direction. + * @dma_buf: [in] buffer to prepare cpu access for. + * @start: [in] start of range for cpu access. + * @len: [in] length of range for cpu access. + * @direction: [in] length of range for cpu access. + * + * Can return negative error values, returns 0 on success. + */ +int dma_buf_begin_cpu_access(struct dma_buf *dmabuf, size_t start, size_t len, + enum dma_data_direction direction) +{ + int ret = 0; + + if (WARN_ON(!dmabuf)) + return -EINVAL; + + if (dmabuf->ops->begin_cpu_access) + ret = dmabuf->ops->begin_cpu_access(dmabuf, start, len, direction); + + return ret; +} +EXPORT_SYMBOL_GPL(dma_buf_begin_cpu_access); + +/** + * dma_buf_end_cpu_access - Must be called after accessing a dma_buf from the + * cpu in the kernel context. Calls end_cpu_access to allow exporter-specific + * actions. Coherency is only guaranteed in the specified range for the + * specified access direction. + * @dma_buf: [in] buffer to complete cpu access for. + * @start: [in] start of range for cpu access. + * @len: [in] length of range for cpu access. + * @direction: [in] length of range for cpu access. + * + * This call must always succeed. + */ +void dma_buf_end_cpu_access(struct dma_buf *dmabuf, size_t start, size_t len, + enum dma_data_direction direction) +{ + WARN_ON(!dmabuf); + + if (dmabuf->ops->end_cpu_access) + dmabuf->ops->end_cpu_access(dmabuf, start, len, direction); +} +EXPORT_SYMBOL_GPL(dma_buf_end_cpu_access); + +/** + * dma_buf_kmap_atomic - Map a page of the buffer object into kernel address + * space. The same restrictions as for kmap_atomic and friends apply. + * @dma_buf: [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_atomic(struct dma_buf *dmabuf, unsigned long page_num) +{ + WARN_ON(!dmabuf); + + return dmabuf->ops->kmap_atomic(dmabuf, page_num); +} +EXPORT_SYMBOL_GPL(dma_buf_kmap_atomic); + +/** + * dma_buf_kunmap_atomic - Unmap a page obtained by dma_buf_kmap_atomic. + * @dma_buf: [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_atomic. + * + * This call must always succeed. + */ +void dma_buf_kunmap_atomic(struct dma_buf *dmabuf, unsigned long page_num, + void *vaddr) +{ + WARN_ON(!dmabuf); + + if (dmabuf->ops->kunmap_atomic) + dmabuf->ops->kunmap_atomic(dmabuf, page_num, vaddr); +} +EXPORT_SYMBOL_GPL(dma_buf_kunmap_atomic); + +/** + * dma_buf_kmap - Map a page of the buffer object into kernel address space. The + * same restrictions as for kmap and friends apply. + * @dma_buf: [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); + + return dmabuf->ops->kmap(dmabuf, page_num); +} +EXPORT_SYMBOL_GPL(dma_buf_kmap); + +/** + * dma_buf_kunmap - Unmap a page obtained by dma_buf_kmap. + * @dma_buf: [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->kunmap) + dmabuf->ops->kunmap(dmabuf, page_num, vaddr); +} +EXPORT_SYMBOL_GPL(dma_buf_kunmap); diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 887dcd4..3efbfc2 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -29,6 +29,7 @@ #include <linux/scatterlist.h> #include <linux/list.h> #include <linux/dma-mapping.h> +#include <linux/fs.h> struct device; struct dma_buf; @@ -49,6 +50,17 @@ struct dma_buf_attachment; * @unmap_dma_buf: decreases usecount of buffer, might deallocate scatter * pages. * @release: release this buffer; to be called after the last dma_buf_put. + * @begin_cpu_access: [optional] called before cpu access to invalidate cpu + * caches and allocate backing storage (if not yet done) + * respectively pin the objet into memory. + * @end_cpu_access: [optional] called after cpu access to flush cashes. + * @kmap_atomic: maps a page from the buffer into kernel address + * space, users may not block until the subsequent unmap call. + * This callback must not sleep. + * @kunmap_atomic: [optional] unmaps a atomically mapped page from the buffer. + * This Callback must not sleep. + * @kmap: maps a page from the buffer into kernel address space. + * @kunmap: [optional] unmaps a page from the buffer. */ struct dma_buf_ops { int (*attach)(struct dma_buf *, struct device *, @@ -63,7 +75,8 @@ struct dma_buf_ops { struct sg_table * (*map_dma_buf)(struct dma_buf_attachment *, enum dma_data_direction); void (*unmap_dma_buf)(struct dma_buf_attachment *, - struct sg_table *); + struct sg_table *, + enum dma_data_direction); /* TODO: Add try_map_dma_buf version, to return immed with -EBUSY * if the call would block. */ @@ -71,6 +84,14 @@ struct dma_buf_ops { /* after final dma_buf_put() */ void (*release)(struct dma_buf *); + int (*begin_cpu_access)(struct dma_buf *, size_t, size_t, + enum dma_data_direction); + void (*end_cpu_access)(struct dma_buf *, size_t, size_t, + enum dma_data_direction); + void *(*kmap_atomic)(struct dma_buf *, unsigned long); + void (*kunmap_atomic)(struct dma_buf *, unsigned long, void *); + void *(*kmap)(struct dma_buf *, unsigned long); + void (*kunmap)(struct dma_buf *, unsigned long, void *); }; /** @@ -86,7 +107,7 @@ struct dma_buf { struct file *file; struct list_head attachments; const struct dma_buf_ops *ops; - /* mutex to serialize list manipulation and other ops */ + /* mutex to serialize list manipulation and attach/detach */ struct mutex lock; void *priv; }; @@ -109,20 +130,43 @@ struct dma_buf_attachment { void *priv; }; +/** + * get_dma_buf - convenience wrapper for get_file. + * @dmabuf: [in] pointer to dma_buf + * + * Increments the reference count on the dma-buf, needed in case of drivers + * that either need to create additional references to the dmabuf on the + * kernel side. For example, an exporter that needs to keep a dmabuf ptr + * so that subsequent exports don't create a new dmabuf. + */ +static inline void get_dma_buf(struct dma_buf *dmabuf) +{ + get_file(dmabuf->file); +} + #ifdef CONFIG_DMA_SHARED_BUFFER struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, struct device *dev); void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *dmabuf_attach); -struct dma_buf *dma_buf_export(void *priv, struct dma_buf_ops *ops, - size_t size, int flags); -int dma_buf_fd(struct dma_buf *dmabuf); +struct dma_buf *dma_buf_export(void *priv, const struct dma_buf_ops *ops, + size_t size, int flags); +int dma_buf_fd(struct dma_buf *dmabuf, int flags); struct dma_buf *dma_buf_get(int fd); void dma_buf_put(struct dma_buf *dmabuf); struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *, enum dma_data_direction); -void dma_buf_unmap_attachment(struct dma_buf_attachment *, struct sg_table *); +void dma_buf_unmap_attachment(struct dma_buf_attachment *, struct sg_table *, + enum dma_data_direction); +int dma_buf_begin_cpu_access(struct dma_buf *dma_buf, size_t start, size_t len, + enum dma_data_direction dir); +void dma_buf_end_cpu_access(struct dma_buf *dma_buf, size_t start, size_t len, + enum dma_data_direction dir); +void *dma_buf_kmap_atomic(struct dma_buf *, unsigned long); +void dma_buf_kunmap_atomic(struct dma_buf *, unsigned long, void *); +void *dma_buf_kmap(struct dma_buf *, unsigned long); +void dma_buf_kunmap(struct dma_buf *, unsigned long, void *); #else static inline struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, @@ -138,13 +182,13 @@ static inline void dma_buf_detach(struct dma_buf *dmabuf, } static inline struct dma_buf *dma_buf_export(void *priv, - struct dma_buf_ops *ops, - size_t size, int flags) + const struct dma_buf_ops *ops, + size_t size, int flags) { return ERR_PTR(-ENODEV); } -static inline int dma_buf_fd(struct dma_buf *dmabuf) +static inline int dma_buf_fd(struct dma_buf *dmabuf, int flags) { return -ENODEV; } @@ -166,11 +210,44 @@ static inline struct sg_table *dma_buf_map_attachment( } static inline void dma_buf_unmap_attachment(struct dma_buf_attachment *attach, - struct sg_table *sg) + struct sg_table *sg, enum dma_data_direction dir) { return; } +static inline int dma_buf_begin_cpu_access(struct dma_buf *dmabuf, + size_t start, size_t len, + enum dma_data_direction dir) +{ + return -ENODEV; +} + +static inline void dma_buf_end_cpu_access(struct dma_buf *dmabuf, + size_t start, size_t len, + enum dma_data_direction dir) +{ +} + +static inline void *dma_buf_kmap_atomic(struct dma_buf *dmabuf, + unsigned long pnum) +{ + return NULL; +} + +static inline void dma_buf_kunmap_atomic(struct dma_buf *dmabuf, + unsigned long pnum, void *vaddr) +{ +} + +static inline void *dma_buf_kmap(struct dma_buf *dmabuf, unsigned long pnum) +{ + return NULL; +} + +static inline void dma_buf_kunmap(struct dma_buf *dmabuf, + unsigned long pnum, void *vaddr) +{ +} #endif /* CONFIG_DMA_SHARED_BUFFER */ #endif /* __DMA_BUF_H__ */ |
