Daniel Vetter | 868c97a | 2016-12-09 19:53:05 +0100 | [diff] [blame] | 1 | Buffer Sharing and Synchronization |
| 2 | ================================== |
| 3 | |
| 4 | The dma-buf subsystem provides the framework for sharing buffers for |
| 5 | hardware (DMA) access across multiple device drivers and subsystems, and |
| 6 | for synchronizing asynchronous hardware access. |
| 7 | |
| 8 | This is used, for example, by drm "prime" multi-GPU support, but is of |
| 9 | course not limited to GPU use cases. |
| 10 | |
| 11 | The three main components of this are: (1) dma-buf, representing a |
| 12 | sg_table and exposed to userspace as a file descriptor to allow passing |
| 13 | between devices, (2) fence, which provides a mechanism to signal when |
| 14 | one device as finished access, and (3) reservation, which manages the |
| 15 | shared or exclusive fence(s) associated with the buffer. |
| 16 | |
| 17 | Shared DMA Buffers |
| 18 | ------------------ |
| 19 | |
Daniel Vetter | 2904a8c | 2016-12-09 19:53:07 +0100 | [diff] [blame] | 20 | This document serves as a guide to device-driver writers on what is the dma-buf |
| 21 | buffer sharing API, how to use it for exporting and using shared buffers. |
| 22 | |
| 23 | Any device driver which wishes to be a part of DMA buffer sharing, can do so as |
| 24 | either the 'exporter' of buffers, or the 'user' or 'importer' of buffers. |
| 25 | |
| 26 | Say a driver A wants to use buffers created by driver B, then we call B as the |
| 27 | exporter, and A as buffer-user/importer. |
| 28 | |
| 29 | The exporter |
| 30 | |
| 31 | - implements and manages operations in :c:type:`struct dma_buf_ops |
| 32 | <dma_buf_ops>` for the buffer, |
| 33 | - allows other users to share the buffer by using dma_buf sharing APIs, |
| 34 | - manages the details of buffer allocation, wrapped int a :c:type:`struct |
| 35 | dma_buf <dma_buf>`, |
| 36 | - decides about the actual backing storage where this allocation happens, |
| 37 | - and takes care of any migration of scatterlist - for all (shared) users of |
| 38 | this buffer. |
| 39 | |
| 40 | The buffer-user |
| 41 | |
| 42 | - is one of (many) sharing users of the buffer. |
| 43 | - doesn't need to worry about how the buffer is allocated, or where. |
| 44 | - and needs a mechanism to get access to the scatterlist that makes up this |
| 45 | buffer in memory, mapped into its own address space, so it can access the |
| 46 | same area of memory. This interface is provided by :c:type:`struct |
| 47 | dma_buf_attachment <dma_buf_attachment>`. |
| 48 | |
Daniel Vetter | e7e21c7 | 2016-12-09 22:50:55 +0100 | [diff] [blame] | 49 | Any exporters or users of the dma-buf buffer sharing framework must have a |
| 50 | 'select DMA_SHARED_BUFFER' in their respective Kconfigs. |
| 51 | |
| 52 | Userspace Interface Notes |
| 53 | ~~~~~~~~~~~~~~~~~~~~~~~~~ |
| 54 | |
| 55 | Mostly a DMA buffer file descriptor is simply an opaque object for userspace, |
| 56 | and hence the generic interface exposed is very minimal. There's a few things to |
| 57 | consider though: |
| 58 | |
| 59 | - Since kernel 3.12 the dma-buf FD supports the llseek system call, but only |
| 60 | with offset=0 and whence=SEEK_END|SEEK_SET. SEEK_SET is supported to allow |
| 61 | the usual size discover pattern size = SEEK_END(0); SEEK_SET(0). Every other |
| 62 | llseek operation will report -EINVAL. |
| 63 | |
| 64 | If llseek on dma-buf FDs isn't support the kernel will report -ESPIPE for all |
| 65 | cases. Userspace can use this to detect support for discovering the dma-buf |
| 66 | size using llseek. |
| 67 | |
| 68 | - In order to avoid fd leaks on exec, the FD_CLOEXEC flag must be set |
| 69 | on the file descriptor. This is not just a resource leak, but a |
| 70 | potential security hole. It could give the newly exec'd application |
| 71 | access to buffers, via the leaked fd, to which it should otherwise |
| 72 | not be permitted access. |
| 73 | |
| 74 | The problem with doing this via a separate fcntl() call, versus doing it |
| 75 | atomically when the fd is created, is that this is inherently racy in a |
| 76 | multi-threaded app[3]. The issue is made worse when it is library code |
| 77 | opening/creating the file descriptor, as the application may not even be |
| 78 | aware of the fd's. |
| 79 | |
| 80 | To avoid this problem, userspace must have a way to request O_CLOEXEC |
| 81 | flag be set when the dma-buf fd is created. So any API provided by |
| 82 | the exporting driver to create a dmabuf fd must provide a way to let |
| 83 | userspace control setting of O_CLOEXEC flag passed in to dma_buf_fd(). |
| 84 | |
| 85 | - Memory mapping the contents of the DMA buffer is also supported. See the |
| 86 | discussion below on `CPU Access to DMA Buffer Objects`_ for the full details. |
| 87 | |
| 88 | - The DMA buffer FD is also pollable, see `Fence Poll Support`_ below for |
| 89 | details. |
| 90 | |
Daniel Vetter | 2904a8c | 2016-12-09 19:53:07 +0100 | [diff] [blame] | 91 | Basic Operation and Device DMA Access |
| 92 | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ |
| 93 | |
| 94 | .. kernel-doc:: drivers/dma-buf/dma-buf.c |
| 95 | :doc: dma buf device access |
| 96 | |
Daniel Vetter | 0959a16 | 2016-12-09 19:53:08 +0100 | [diff] [blame] | 97 | CPU Access to DMA Buffer Objects |
| 98 | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ |
| 99 | |
| 100 | .. kernel-doc:: drivers/dma-buf/dma-buf.c |
| 101 | :doc: cpu access |
| 102 | |
Daniel Vetter | e7e21c7 | 2016-12-09 22:50:55 +0100 | [diff] [blame] | 103 | Fence Poll Support |
| 104 | ~~~~~~~~~~~~~~~~~~ |
| 105 | |
| 106 | .. kernel-doc:: drivers/dma-buf/dma-buf.c |
| 107 | :doc: fence polling |
| 108 | |
Daniel Vetter | 2904a8c | 2016-12-09 19:53:07 +0100 | [diff] [blame] | 109 | Kernel Functions and Structures Reference |
| 110 | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ |
| 111 | |
Daniel Vetter | 868c97a | 2016-12-09 19:53:05 +0100 | [diff] [blame] | 112 | .. kernel-doc:: drivers/dma-buf/dma-buf.c |
| 113 | :export: |
| 114 | |
| 115 | .. kernel-doc:: include/linux/dma-buf.h |
| 116 | :internal: |
| 117 | |
| 118 | Reservation Objects |
| 119 | ------------------- |
| 120 | |
| 121 | .. kernel-doc:: drivers/dma-buf/reservation.c |
| 122 | :doc: Reservation Object Overview |
| 123 | |
| 124 | .. kernel-doc:: drivers/dma-buf/reservation.c |
| 125 | :export: |
| 126 | |
| 127 | .. kernel-doc:: include/linux/reservation.h |
| 128 | :internal: |
| 129 | |
| 130 | DMA Fences |
| 131 | ---------- |
| 132 | |
| 133 | .. kernel-doc:: drivers/dma-buf/dma-fence.c |
| 134 | :export: |
| 135 | |
| 136 | .. kernel-doc:: include/linux/dma-fence.h |
| 137 | :internal: |
| 138 | |
| 139 | Seqno Hardware Fences |
| 140 | ~~~~~~~~~~~~~~~~~~~~~ |
| 141 | |
Daniel Vetter | 868c97a | 2016-12-09 19:53:05 +0100 | [diff] [blame] | 142 | .. kernel-doc:: include/linux/seqno-fence.h |
| 143 | :internal: |
| 144 | |
| 145 | DMA Fence Array |
| 146 | ~~~~~~~~~~~~~~~ |
| 147 | |
| 148 | .. kernel-doc:: drivers/dma-buf/dma-fence-array.c |
| 149 | :export: |
| 150 | |
| 151 | .. kernel-doc:: include/linux/dma-fence-array.h |
| 152 | :internal: |
| 153 | |
| 154 | DMA Fence uABI/Sync File |
| 155 | ~~~~~~~~~~~~~~~~~~~~~~~~ |
| 156 | |
| 157 | .. kernel-doc:: drivers/dma-buf/sync_file.c |
| 158 | :export: |
| 159 | |
| 160 | .. kernel-doc:: include/linux/sync_file.h |
| 161 | :internal: |
| 162 | |