diff options
Diffstat (limited to 'linux-core')
| -rw-r--r-- | linux-core/drm-gem.txt | 799 | ||||
| -rw-r--r-- | linux-core/drmP.h | 10 | ||||
| -rw-r--r-- | linux-core/drm_drv.c | 6 | ||||
| -rw-r--r-- | linux-core/drm_gem.c | 20 | ||||
| -rw-r--r-- | linux-core/i915_gem.c | 13 |
5 files changed, 823 insertions, 25 deletions
diff --git a/linux-core/drm-gem.txt b/linux-core/drm-gem.txt new file mode 100644 index 00000000..8f95c206 --- /dev/null +++ b/linux-core/drm-gem.txt @@ -0,0 +1,799 @@ + The Graphics Execution Manager + Part of the Direct Rendering Manager + ============================== + + Keith Packard <keithp@keithp.com> + Eric Anholt <eric@anholt.net> + 2008-5-9 + +Contents: + + 1. GEM Overview + 2. API overview and conventions + 3. Object Creation/Destruction + 4. Reading/writing contents + 5. Mapping objects to userspace + 6. Memory Domains + 7. Execution (Intel specific) + 8. Other misc Intel-specific functions + +1. Graphics Execution Manager Overview + +Gem is designed to manage graphics memory, control access to the graphics +device execution context and handle the essentially NUMA environment unique +to modern graphics hardware. Gem allows multiple applications to share +graphics device resources without the need to constantly reload the entire +graphics card. Data may be shared between multiple applications with gem +ensuring that the correct memory synchronization occurs. + +Graphics data can consume arbitrary amounts of memory, with 3D applications +constructing ever larger sets of textures and vertices. With graphics cards +memory space growing larger every year, and graphics APIs growing more +complex, we can no longer insist that each application save a complete copy +of their graphics state so that the card can be re-initialized from user +space at each context switch. Ensuring that graphics data remains persistent +across context switches allows applications significant new functionality +while also improving performance for existing APIs. + +Modern linux desktops include significant 3D rendering as a fundemental +component of the desktop image construction process. 2D and 3D applications +paint their content to offscreen storage and the central 'compositing +manager' constructs the final screen image from those window contents. This +means that pixel image data from these applications must move within reach +of the compositing manager and used as source operands for screen image +rendering operations. + +Gem provides simple mechanisms to manage graphics data and control execution +flow within the linux operating system. Using many existing kernel +subsystems, it does this with a modest amount of code. + +2. API Overview and Conventions + +All APIs here are defined in terms of ioctls appplied to the DRM file +descriptor. To create and manipulate objects, an applications must be +'authorized' using the DRI or DRI2 protocols with the X server. To relax +that, we will need to implement some better access control mechanisms within +the hardware portion of the driver to prevent inappropriate +cross-application data access. + +Any DRM driver which does not support GEM will return -ENODEV for all of +these ioctls. Invalid object handles return -EINVAL. Invalid object names +return -ENOENT. Other errors are as documented in the specific API below. + +To avoid the need to translate ioctl contents on mixed-size systems (with +32-bit user space running on a 64-bit kernel), the ioctl data structures +contain explicitly sized objects, using 64-bits for all size and pointer +data and 32-bits for identifiers. In addition, the 64-bit objects are all +carefully aligned on 64-bit boundaries. Because of this, all pointers in the +ioctl data structures are passed as uint64_t values. Suitable casts will +be necessary. + +One significant operation which is explicitly left out of this API is object +locking. Applications are expected to perform locking of shared objects +outside of the GEM api. This kind of locking is not necessary to safely +manipulate the graphics engine, and with multiple objects interacting in +unknown ways, per-object locking would likely introduce all kinds of +lock-order issues. Punting this to the application seems like the only +sensible plan. Given that DRM already offers a global lock on the hardware, +this doesn't change the current situation. + +3. Object Creation and Destruction + +Gem provides explicit memory management primitives. System pages are +allocated when the object is created, either as the fundemental storage for +hardware where system memory is used by the graphics processor directly, or +as backing store for graphics-processor resident memory. + +Objects are referenced from user space using handles. These are, for all +intents and purposes, equivalent to file descriptors. We could simply use +file descriptors were it not for the small limit (1024) of file descriptors +available to applications, and for the fact that the X server (a rather +significant user of this API) uses 'select' and has a limited maximum file +descriptor for that operation. Given the ability to allocate more file +descriptors, and given the ability to place these 'higher' in the file +descriptor space, we'd love to simply use file descriptors. + +Objects may be published with a name so that other applications can access +them. The name remains valid as long as the object exists. Right now, our +DRI APIs use 32-bit integer names, so that's what we expose here + + A. Creation + + struct drm_gem_create { + /** + * Requested size for the object. + * + * The (page-aligned) allocated size for the object + * will be returned. + */ + uint64_t size; + /** + * Returned handle for the object. + * + * Object handles are nonzero. + */ + uint32_t handle; + uint32_t pad; + }; + + /* usage */ + create.size = 16384; + ret = ioctl (fd, DRM_IOCTL_GEM_CREATE, &create); + if (ret == 0) + return create.handle; + + Note that the size is rounded up to a page boundary, and that + the rounded-up size is returned in 'size'. No name is assigned to + this object, making it local to this process. + + If insufficient memory is availabe, -ENOMEM will be returned. + + B. Closing + + struct drm_gem_close { + /** Handle of the object to be closed. */ + uint32_t handle; + uint32_t pad; + }; + + + /* usage */ + close.handle = <handle>; + ret = ioctl (fd, DRM_IOCTL_GEM_CLOSE, &close); + + This call makes the specified handle invalid, and if no other + applications are using the object, any necessary graphics hardware + synchronization is performed and the resources used by the object + released. + + C. Naming + + struct drm_gem_flink { + /** Handle for the object being named */ + uint32_t handle; + + /** Returned global name */ + uint32_t name; + }; + + /* usage */ + flink.handle = <handle>; + ret = ioctl (fd, DRM_IOCTL_GEM_FLINK, &flink); + if (ret == 0) + return flink.name; + + Flink creates a name for the object and returns it to the + application. This name can be used by other applications to gain + access to the same object. + + D. Opening by name + + struct drm_gem_open { + /** Name of object being opened */ + uint32_t name; + + /** Returned handle for the object */ + uint32_t handle; + + /** Returned size of the object */ + uint64_t size; + }; + + /* usage */ + open.name = <name>; + ret = ioctl (fd, DRM_IOCTL_GEM_OPEN, &open); + if (ret == 0) { + *sizep = open.size; + return open.handle; + } + + Open accesses an existing object and returns a handle for it. If the + object doesn't exist, -ENOENT is returned. The size of the object is + also returned. This handle has all the same capabilities as the + handle used to create the object. In particular, the object is not + destroyed until all handles are closed. + +4. Basic read/write operations + +By default, gem objects are not mapped to the applications address space, +getting data in and out of them is done with I/O operations instead. This +allows the data to reside in otherwise unmapped pages, including pages in +video memory on an attached discrete graphics card. In addition, using +explicit I/O operations allows better control over cache contents, as +graphics devices are generally not cache coherent with the CPU, mapping +pages used for graphics into an application address space requires the use +of expensive cache flushing operations. Providing direct control over +graphics data access ensures that data are handled in the most efficient +possible fashion. + + A. Reading + + struct drm_gem_pread { + /** Handle for the object being read. */ + uint32_t handle; + uint32_t pad; + /** Offset into the object to read from */ + uint64_t offset; + /** Length of data to read */ + uint64_t size; + /** Pointer to write the data into. */ + uint64_t data_ptr; /* void * */ + }; + + This copies data into the specified object at the specified + position. Any necessary graphics device synchronization and + flushing will be done automatically. + + struct drm_gem_pwrite { + /** Handle for the object being written to. */ + uint32_t handle; + uint32_t pad; + /** Offset into the object to write to */ + uint64_t offset; + /** Length of data to write */ + uint64_t size; + /** Pointer to read the data from. */ + uint64_t data_ptr; /* void * */ + }; + + This copies data out of the specified object into the + waiting user memory. Again, device synchronization will + be handled by the kernel to ensure user space sees a + consistent view of the graphics device. + +5. Mapping objects to user space + +For most objects, reading/writing is the preferred interaction mode. +However, when the CPU is involved in rendering to cover deficiencies in +hardware support for particular operations, the CPU will want to directly +access the relevant objects. + +Because mmap is fairly heavyweight, we allow applications to retain maps to +objects persistently and then update how they're using the memory through a +separate interface. Applications which fail to use this separate interface +may exhibit unpredictable behaviour as memory consistency will not be +preserved. + + A. Mapping + + struct drm_gem_mmap { + /** Handle for the object being mapped. */ + uint32_t handle; + uint32_t pad; + /** Offset in the object to map. */ + uint64_t offset; + /** + * Length of data to map. + * + * The value will be page-aligned. + */ + uint64_t size; + /** Returned pointer the data was mapped at */ + uint64_t addr_ptr; /* void * */ + }; + + /* usage */ + mmap.handle = <handle>; + mmap.offset = <offset>; + mmap.size = <size>; + ret = ioctl (fd, DRM_IOCTL_GEM_MMAP, &mmap); + if (ret == 0) + return (void *) (uintptr_t) mmap.addr_ptr; + + + B. Unmapping + + munmap (addr, length); + + Nothing strange here, just use the normal munmap syscall. + +6. Memory Domains + +Graphics devices remain a strong bastion of non cache-coherent memory. As a +result, accessing data through one functional unit will end up loading that +cache with data which then needs to be manually synchronized when that data +is used with another functional unit. + +Tracking where data are resident is done by identifying how functional units +deal with caches. Each cache is labeled as a separate memory domain. Then, +each sequence of operations is expected to load data into various read +domains and leave data in at most one write domain. Gem tracks the read and +write memory domains of each object and performs the necessary +synchronization operations when objects move from one domain set to another. + +For example, if operation 'A' constructs an image that is immediately used +by operation 'B', then when the read domain for 'B' is not the same as the +write domain for 'A', then the write domain must be flushed, and the read +domain invalidated. If these two operations are both executed in the same +command queue, then the flush operation can go inbetween them in the same +queue, avoiding any kind of CPU-based synchronization and leaving the GPU to +do the work itself. + +6.1 Memory Domains (GPU-independent) + + * DRM_GEM_DOMAIN_CPU. + + Objects in this domain are using caches which are connected to the CPU. + Moving objects from non-CPU domains into the CPU domain can involve waiting + for the GPU to finish with operations using this object. Moving objects + from this domain to a GPU domain can involve flushing CPU caches and chipset + buffers. + +6.1 GPU-independent memory domain ioctl + +This ioctl is independent of the GPU in use. So far, no use other than +synchronizing objects to the CPU domain have been found; if that turns out +to be generally true, this ioctl may be simplified further. + + A. Explicit domain control + + struct drm_gem_set_domain { + /** Handle for the object */ + uint32_t handle; + + /** New read domains */ + uint32_t read_domains; + + /** New write domain */ + uint32_t write_domain; + }; + + /* usage */ + set_domain.handle = <handle>; + set_domain.read_domains = <read_domains>; + set_domain.write_domain = <write_domain>; + ret = ioctl (fd, DRM_IOCTL_GEM_SET_DOMAIN, &set_domain); + + When the application wants to explicitly manage memory domains for + an object, it can use this function. Usually, this is only used + when the application wants to synchronize object contents between + the GPU and CPU-based application rendering. In that case, + the <read_domains> would be set to DRM_GEM_DOMAIN_CPU, and if the + application were going to write to the object, the <write_domain> + would also be set to DRM_GEM_DOMAIN_CPU. After the call, gem + guarantees that all previous rendering operations involving this + object are complete. The application is then free to access the + object through the address returned by the mmap call. Afterwards, + when the application again uses the object through the GPU, any + necessary CPU flushing will occur and the object will be correctly + synchronized with the GPU. + +7. Execution (Intel specific) + +Managing the command buffers is inherently chip-specific, so the core of gem +doesn't have any intrinsic functions. Rather, execution is left to the +device-specific portions of the driver. + +The Intel DRM_I915_GEM_EXECBUFFER ioctl takes a list of gem objects, all of +which are mapped to the graphics device. The last object in the list is the +command buffer. + +7.1. Relocations + +Command buffers often refer to other objects, and to allow the kernel driver +to move objects around, a sequence of relocations is associated with each +object. Device-specific relocation operations are used to place the +target-object relative value into the object. + +The Intel driver has a single relocation type: + + struct drm_i915_gem_relocation_entry { + /* + * Handle of the buffer being pointed to by this + * relocation entry. + /* + * It's appealing to make this be an index into the + * mm_validate_entry list to refer to the buffer, but + * handle lookup should be O(1) anyway, and prevents + * O(n) search in userland to find what that index is. + + */ + uint32_t target_handle; + + /** + * Value to be added to the offset of the target + * buffer to make up the relocation entry. + */ + uint32_t delta; + + /** + * Offset in the buffer the relocation entry will be + * written into + */ + uint64_t offset; + + /** + * Offset value of the target buffer that the + * relocation entry was last written as. + * + * If the buffer has the same offset as last time, we + * can skip syncing and writing the relocation. This + * value is written back out by the execbuffer ioctl + * when the relocation is written. + */ + uint64_t presumed_offset; + + /** + * Target memory domains read by this operation. + */ + uint32_t read_domains; + + /* + * Target memory domains written by this operation. + * + * Note that only one domain may be written by the + * whole execbuffer operation, so that where there are + * conflicts, the application will get -EINVAL back. + */ + uint32_t write_domain; + }; + + 'target_handle', the handle to the target object. This object must + be one of the objects listed in the execbuffer request or + bad things will happen. The kernel doesn't check for this. + + 'offset' is where, in the source object, the relocation data + are written. Each relocation value is a 32-bit value consisting + of the location of the target object in the GPU memory space plus + the 'delta' value included in the relocation. + + 'presumed_offset' is where user-space believes the target object + lies in GPU memory space. If this value matches where the object + actually is, then no relocation data are written, the kernel + assumes that user space has set up data in the source object + using this presumption. This offers a fairly important optimization + as writing relocation data requires mapping of the source object + into the kernel memory space. + + 'read_domains' and 'write_domains' list the usage by the source + object of the target object. The kernel unions all of the domain + information from all relocations in the execbuffer request. No more + than one write_domain is allowed, otherwise an EINVAL error is + returned. read_domains must contain write_domain. This domain + information is used to synchronize buffer contents as described + above in the section on domains. + +7.1.1 Memory Domains (Intel specific) + +The Intel GPU has several internal caches which are not coherent and hence +require explicit synchronization. Memory domains provide the necessary data +to synchronize what is needed while leaving other cache contents intact. + + * DRM_GEM_DOMAIN_I915_RENDER. + The GPU 3D and 2D rendering operations use a unified rendering cache, so + operations doing 3D painting and 2D blts will use this domain + + * DRM_GEM_DOMAIN_I915_SAMPLER + Textures are loaded by the sampler through a separate cache, so + any texture reading will use this domain. Note that the sampler + and renderer use different caches, so moving an object from render target + to texture source will require a domain transfer. + + * DRM_GEM_DOMAIN_I915_COMMAND + The command buffer doesn't have an explicit cache (although it does + read ahead quite a bit), so this domain just indicates that the object + needs to be flushed to the GPU. + + * DRM_GEM_DOMAIN_I915_INSTRUCTION + Fragment programs on Gen3 and all of the programs on later + chips use an instruction cache to speed program execution. It must be + explicitly flushed when new programs are written to memory by the CPU. + + * DRM_GEM_DOMAIN_I915_VERTEX + Vertex data uses two different vertex caches, but they're + both flushed with the same instruction. + +7.2 Execution object list (Intel specific) + + struct drm_i915_gem_exec_object { + /** + * User's handle for a buffer to be bound into the GTT + * for this operation. + */ + uint32_t handle; + + /** + * List of relocations to be performed on this buffer + */ + uint32_t relocation_count; + /* struct drm_i915_gem_relocation_entry *relocs */ + uint64_t relocs_ptr; + + /** + * Required alignment in graphics aperture + */ + uint64_t alignment; + + /** + * Returned value of the updated offset of the object, + * for future presumed_offset writes. + */ + uint64_t offset; + }; + + Each object involved in a particular execution operation must be + listed using one of these structures. + + 'handle' references the object. + + 'relocs_ptr' is a user-mode pointer to a array of 'relocation_count' + drm_i915_gem_relocation_entry structs (see above) that + define the relocations necessary in this buffer. Note that all + relocations must reference other exec_object structures in the same + execbuffer ioctl and that those other buffers must come earlier in + the exec_object array. In other words, the dependencies mapped by the + exec_object relocations must form a directed acyclic graph. + + 'alignment' is the byte alignment necessary for this buffer. Each + object has specific alignment requirements, as the kernel doesn't + know what each object is being used for, those requirements must be + provided by user mode. If an object is used in two different ways, + it's quite possible that the alignment requirements will differ. + + 'offset' is a return value, receiving the location of the object + during this execbuffer operation. The application should use this + as the presumed offset in future operations; if the object does not + move, then kernel need not write relocation data. + +7.3 Execbuffer ioctl (Intel specific) + + struct drm_i915_gem_execbuffer { + /** + * List of buffers to be validated wit their + * relocations to be performend on them. + * + * These buffers must be listed in an order such that + * all relocations a buffer is performing refer to + * buffers that have already appeared in the validate + * list. + */ + /* struct drm_i915_gem_validate_entry *buffers */ + uint64_t buffers_ptr; + uint32_t buffer_count; + + /** + * Offset in the batchbuffer to start execution from. + */ + uint32_t batch_start_offset; + + /** + * Bytes used in batchbuffer from batch_start_offset + */ + uint32_t batch_len; + uint32_t DR1; + uint32_t DR4; + uint32_t num_cliprects; + uint64_t cliprects_ptr; /* struct drm_clip_rect *cliprects */ + }; + + + 'buffers_ptr' is a user-mode pointer to an array of 'buffer_count' + drm_i915_gem_exec_object structures which contains the complete set + of objects required for this execbuffer operation. The last entry in + this array, the 'batch buffer', is the buffer of commands which will + be linked to the ring and executed. + + 'batch_start_offset' is the byte offset within the batch buffer which + contains the first command to execute. So far, we haven't found a + reason to use anything other than '0' here, but the thought was that + some space might be allocated for additional initialization which + could be skipped in some cases. This must be a multiple of 4. + + 'batch_len' is the length, in bytes, of the data to be executed + (i.e., the amount of data after batch_start_offset). This must + be a multiple of 4. + + 'num_cliprects' and 'cliprects_ptr' reference an array of + drm_clip_rect structures that is num_cliprects long. The entire + batch buffer will be executed multiple times, once for each + rectangle in this list. If num_cliprects is 0, then no clipping + rectangle will be set. + + 'DR1' and 'DR4' are portions of the 3DSTATE_DRAWING_RECTANGLE + command which will be queued when this operation is clipped + (num_cliprects != 0). + + DR1 bit definition + 31 Fast Scissor Clip Disable (debug only). + Disables a hardware optimization that + improves performance. This should have + no visible effect, other than reducing + performance + + 30 Depth Buffer Coordinate Offset Disable. + This disables the addition of the + depth buffer offset bits which are used + to change the location of the depth buffer + relative to the front buffer. + + 27:26 X Dither Offset. Specifies the X pixel + offset to use when accessing the dither table + + 25:24 Y Dither Offset. Specifies the Y pixel + offset to use when accessing the dither + table. + + DR4 bit definition + 31:16 Drawing Rectangle Origin Y. Specifies the Y + origin of coordinates relative to the + draw buffer. + + 15:0 Drawing Rectangle Origin X. Specifies the X + origin of coordinates relative to the + draw buffer. + + As you can see, these two fields are necessary for correctly + offsetting drawing within a buffer which contains multiple surfaces. + Note that DR1 is only used on Gen3 and earlier hardware and that + newer hardware sticks the dither offset elsewhere. + +7.3.1 Detailed Execution Description + + Execution of a single batch buffer requires several preparatory + steps to make the objects visible to the graphics engine and resolve + relocations to account for their current addresses. + + A. Mapping and Relocation + + Each exec_object structure in the array is examined in turn. + + If the object is not already bound to the GTT, it is assigned a + location in the graphics address space. If no space is available in + the GTT, some other object will be evicted. This may require waiting + for previous execbuffer requests to complete before that object can + be unmapped. With the location assigned, the pages for the object + are pinned in memory using find_or_create_page and the GTT entries + updated to point at the relevant pages using drm_agp_bind_pages. + + Then the array of relocations is traversed. Each relocation record + looks up the target object and, if the presumed offset does not + match the current offset (remember that this buffer has already been + assigned an address as it must have been mapped earlier), the + relocation value is computed using the current offset. If the + object is currently in use by the graphics engine, writing the data + out must be preceeded by a delay while the object is still busy. + Once it is idle, then the page containing the relocation is mapped + by the CPU and the updated relocation data written out. + + The read_domains and write_domain entries in each relocation are + used to compute the new read_domains and write_domain values for the + target buffers. The actual execution of the domain changes must wait + until all of the exec_object entries have been evaluated as the + complete set of domain information will not be available until then. + + B. Memory Domain Resolution + + After all of the new memory domain data has been pulled out of the + relocations and computed for each object, the list of objects is + again traversed and the new memory domains compared against the + current memory domains. There are two basic operations involved here: + + * Flushing the current write domain. If the new read domains + are not equal to the current write domain, then the current + write domain must be flushed. Otherwise, reads will not see data + present in the write domain cache. In addition, any new read domains + other than the current write domain must be invalidated to ensure + that the flushed data are re-read into their caches. + + * Invaliding new read domains. Any domains which were not currently + used for this object must be invalidated as old objects which + were mapped at the same location may have stale data in the new + domain caches. + + If the CPU cache is being invalidated and some GPU cache is being + flushed, then we'll have to wait for rendering to complete so that + any pending GPU writes will be complete before we flush the GPU + cache. + + If the CPU cache is being flushed, then we use 'clflush' to get data + written from the CPU. + + Because the GPU caches cannot be partially flushed or invalidated, + we don't actually flush them during this traversal stage. Rather, we + gather the invalidate and flush bits up in the device structure. + + Once all of the object domain changes have been evaluated, then the + gathered invalidate and flush bits are examined. For any GPU flush + operations, we emit a single MI_FLUSH command that performs all of + the necessary flushes. We then look to see if the CPU cache was + flushed. If so, we use the chipset flush magic (writing to a special + page) to get the data out of the chipset and into memory. + + C. Queuing Batch Buffer to the Ring + + With all of the objects resident in graphics memory space, and all + of the caches prepared with appropriate data, the batch buffer + object can be queued to the ring. If there are clip rectangles, then + the buffer is queued once per rectangle, with suitable clipping + inserted into the ring just before the batch buffer. + + D. Creating an IRQ Cookie + + Right after the batch buffer is placed in the ring, a request to + generate an IRQ is added to the ring along with a command to write a + marker into memory. When the IRQ fires, the driver can look at the + memory location to see where in the ring the GPU has passed. This + magic cookie value is stored in each object used in this execbuffer + command; it is used whereever you saw 'wait for rendering' above in + this document. + + E. Writing back the new object offsets + + So that the application has a better idea what to use for + 'presumed_offset' values later, the current object offsets are + written back to the exec_object structures. + + +8. Other misc Intel-specific functions. + +To complete the driver, a few other functions were necessary. + +8.1 Initialization from the X server + +As the X server is currently responsible for apportioning memory between 2D +and 3D, it must tell the kernel which region of the GTT aperture is +available for 3D objects to be mapped into. + + struct drm_i915_gem_init { + /** + * Beginning offset in the GTT to be managed by the + * DRM memory manager. + */ + uint64_t gtt_start; + /** + * Ending offset in the GTT to be managed by the DRM + * memory manager. + */ + uint64_t gtt_end; + }; + /* usage */ + init.gtt_start = <gtt_start>; + init.gtt_end = <gtt_end>; + ret = ioctl (fd, DRM_IOCTL_I915_GEM_INIT, &init); + + The GTT aperture between gtt_start and gtt_end will be used to map + objects. This also tells the kernel that the ring can be used, + pulling the ring addresses from the device registers. + +8.2 Pinning objects in the GTT + +For scan-out buffers and the current shared depth and back buffers, we need +to have them always available in the GTT, at least for now. Pinning means to +lock their pages in memory along with keeping them at a fixed offset in the +graphics aperture. These operations are available only to root. + + struct drm_i915_gem_pin { + /** Handle of the buffer to be pinned. */ + uint32_t handle; + uint32_t pad; + + /** alignment required within the aperture */ + uint64_t alignment; + + /** Returned GTT offset of the buffer. */ + uint64_t offset; + }; + + /* usage */ + pin.handle = <handle>; + pin.alignment = <alignment>; + ret = ioctl (fd, DRM_IOCTL_I915_GEM_PIN, &pin); + if (ret == 0) + return pin.offset; + + Pinning an object ensures that it will not be evicted from the GTT + or moved. It will stay resident until destroyed or unpinned. + + struct drm_i915_gem_unpin { + /** Handle of the buffer to be unpinned. */ + uint32_t handle; + uint32_t pad; + }; + + /* usage */ + unpin.handle = <handle>; + ret = ioctl (fd, DRM_IOCTL_I915_GEM_UNPIN, &unpin); + + Unpinning an object makes it possible to evict this object from the + GTT. It doesn't ensure that it will be evicted, just that it may. + diff --git a/linux-core/drmP.h b/linux-core/drmP.h index 11688cdd..419b4be3 100644 --- a/linux-core/drmP.h +++ b/linux-core/drmP.h @@ -1394,18 +1394,18 @@ static inline void drm_gem_object_handle_unreference (struct drm_gem_object *obj struct drm_gem_object * drm_gem_object_lookup(struct drm_device *dev, struct drm_file *filp, int handle); -int drm_gem_alloc_ioctl(struct drm_device *dev, void *data, +int drm_gem_create_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv); +int drm_gem_close_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); -int drm_gem_unreference_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv); int drm_gem_pread_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); int drm_gem_pwrite_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); int drm_gem_mmap_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); -int drm_gem_name_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv); +int drm_gem_flink_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv); int drm_gem_open_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); int drm_gem_set_domain_ioctl(struct drm_device *dev, void *data, diff --git a/linux-core/drm_drv.c b/linux-core/drm_drv.c index 16c38dbe..edc1f057 100644 --- a/linux-core/drm_drv.c +++ b/linux-core/drm_drv.c @@ -151,12 +151,12 @@ static struct drm_ioctl_desc drm_ioctls[] = { DRM_IOCTL_DEF(DRM_IOCTL_MM_INFO, drm_mm_info_ioctl, 0), - DRM_IOCTL_DEF(DRM_IOCTL_GEM_ALLOC, drm_gem_alloc_ioctl, 0), - DRM_IOCTL_DEF(DRM_IOCTL_GEM_UNREFERENCE, drm_gem_unreference_ioctl, 0), + DRM_IOCTL_DEF(DRM_IOCTL_GEM_CREATE, drm_gem_create_ioctl, 0), + DRM_IOCTL_DEF(DRM_IOCTL_GEM_CLOSE, drm_gem_close_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_GEM_PREAD, drm_gem_pread_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_GEM_PWRITE, drm_gem_pwrite_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_GEM_MMAP, drm_gem_mmap_ioctl, 0), - DRM_IOCTL_DEF(DRM_IOCTL_GEM_NAME, drm_gem_name_ioctl, DRM_AUTH), + DRM_IOCTL_DEF(DRM_IOCTL_GEM_FLINK, drm_gem_flink_ioctl, DRM_AUTH), DRM_IOCTL_DEF(DRM_IOCTL_GEM_OPEN, drm_gem_open_ioctl, DRM_AUTH), DRM_IOCTL_DEF(DRM_IOCTL_GEM_SET_DOMAIN, drm_gem_set_domain_ioctl, DRM_AUTH), }; diff --git a/linux-core/drm_gem.c b/linux-core/drm_gem.c index c85265ad..6c462921 100644 --- a/linux-core/drm_gem.c +++ b/linux-core/drm_gem.c @@ -204,13 +204,13 @@ drm_gem_object_lookup(struct drm_device *dev, struct drm_file *filp, EXPORT_SYMBOL(drm_gem_object_lookup); /** - * Allocates a new mm object and returns a handle to it. + * Creates a new mm object and returns a handle to it. */ int -drm_gem_alloc_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv) +drm_gem_create_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) { - struct drm_gem_alloc *args = data; + struct drm_gem_create *args = data; struct drm_gem_object *obj; int handle, ret; @@ -239,10 +239,10 @@ drm_gem_alloc_ioctl(struct drm_device *dev, void *data, * Releases the handle to an mm object. */ int -drm_gem_unreference_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv) +drm_gem_close_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) { - struct drm_gem_unreference *args = data; + struct drm_gem_close *args = data; int ret; if (!(dev->driver->driver_features & DRIVER_GEM)) @@ -376,10 +376,10 @@ drm_gem_pwrite_ioctl(struct drm_device *dev, void *data, * is freed, the name goes away. */ int -drm_gem_name_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv) +drm_gem_flink_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) { - struct drm_gem_name *args = data; + struct drm_gem_flink *args = data; struct drm_gem_object *obj; int ret; diff --git a/linux-core/i915_gem.c b/linux-core/i915_gem.c index 37a4e503..0cacc65b 100644 --- a/linux-core/i915_gem.c +++ b/linux-core/i915_gem.c @@ -577,7 +577,7 @@ i915_gem_dev_set_domain(struct drm_device *dev) static int i915_gem_reloc_and_validate_object(struct drm_gem_object *obj, struct drm_file *file_priv, - struct drm_i915_gem_validate_entry *entry) + struct drm_i915_gem_exec_object *entry) { struct drm_device *dev = obj->dev; struct drm_i915_gem_relocation_entry reloc; @@ -594,7 +594,7 @@ i915_gem_reloc_and_validate_object(struct drm_gem_object *obj, return -ENOMEM; } - entry->buffer_offset = obj_priv->gtt_offset; + entry->offset = obj_priv->gtt_offset; relocs = (struct drm_i915_gem_relocation_entry __user *) (uintptr_t) entry->relocs_ptr; @@ -809,7 +809,7 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, { drm_i915_private_t *dev_priv = dev->dev_private; struct drm_i915_gem_execbuffer *args = data; - struct drm_i915_gem_validate_entry *validate_list; + struct drm_i915_gem_exec_object *validate_list; struct drm_gem_object **object_list; struct drm_gem_object *batch_obj; int ret, i; @@ -849,11 +849,10 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, /* Look up object handles and perform the relocations */ for (i = 0; i < args->buffer_count; i++) { object_list[i] = drm_gem_object_lookup(dev, file_priv, - validate_list[i]. - buffer_handle); + validate_list[i].handle); if (object_list[i] == NULL) { DRM_ERROR("Invalid object handle %d at index %d\n", - validate_list[i].buffer_handle, i); + validate_list[i].handle, i); ret = -EINVAL; goto err; } @@ -897,7 +896,7 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, /* Flush/invalidate caches and chipset buffer */ i915_gem_dev_set_domain(dev); - exec_offset = validate_list[args->buffer_count - 1].buffer_offset; + exec_offset = validate_list[args->buffer_count - 1].offset; #if WATCH_EXEC i915_gem_dump_object(object_list[args->buffer_count - 1], |