summaryrefslogtreecommitdiff
path: root/libdrm/intel/intel_bufmgr_gem.c
AgeCommit message (Collapse)Author
2009-03-26libdrm/intel: support GTT maps correctlyJesse Barnes
libdrm has some support for GTT mapping already, but there are bugs with it (no surprise since it hasn't been used much). In fixing 20803, I found that sharing bo_gem->virtual was a bad idea, since a previously mapped object might not end up getting GTT mapped, leading to corruption. So this patch splits the fields according to use, taking care to unmap both at free time (but preserving the map caching). There's still a risk we might run out of mappings (there's a sysctl tunable for max number of mappings per process, defaulted to 64k or so it looks like) but at least GTT maps will work with these changes (and some others for fixing PAT breakage in the kernel). Reviewed-by: Eric Anholt <eric@anholt.net> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-27intel: Update reloc_tree_size of the first buffer when we count the tree size.Eric Anholt
This helps avoid the n^2 performance cost of counting tree size when we get a lot of relocations into our batch buffer. rgb10text on keithp's laptop went from 136k glyphs/sec to 234k glyphs/sec.
2009-02-21intel: Add a new bufmgr alloc function to get BOs ready for rendering to.Eric Anholt
This avoids using the oldest BO in the BO cache and waiting for it to be idle before we turn around and render to it with the GPU. Thanks to Chris Wilson for pointing out how silly we were being.
2009-02-15intel: Clear ioctl parameter outvalues and pads that confuse valgrind.Eric Anholt
The minor CPU cost here is probably outweighed by bothering us with noise in the tool.
2009-01-27intel: don't count fences on 965 and later, as they don't use them.Eric Anholt
2009-01-27intel: Fix under-counting of fences registers required in check_aperture.Eric Anholt
2009-01-27intel: libdrm support for fence management in execbufJesse Barnes
This patch tries to use the available fence count to figure out whether a given batch can succeed or not (just like the aperture check). Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org> Signed-off-by: Eric Anholt <eric@anholt.net>
2009-01-14intel: Retry pin ioctl on -EINTR.Eric Anholt
2008-12-17intel: Cache tiling/swizzle state in user mode. Reset tiling on reuse.Keith Packard
Remember tiling mode values provided by appplications, and record tiling mode when creating a buffer from another application. This eliminates any need to ask the kernel for tiling values and also makes reused buffers get the right tiling. Signed-off-by: Keith Packard <keithp@keithp.com>
2008-12-17intel: Debug output %u vs uint64_t warning fixKeith Packard
Signed-off-by: Keith Packard <keithp@keithp.com>
2008-12-17intel: return error status from drm_intel_gem_bo_mapKeith Packard
Applications may actually care if the mapping operation failed, so when it happens, return an error indication. errno is probably trashed by fprintf though. Signed-off-by: Keith Packard <keithp@keithp.com>
2008-12-17intel: Dump out memory usage information when the kernel fails to pinKeith Packard
The execbuffer ioctl returns ENOMEM when it fails to pin all of the buffers in the GTT. This is usually caused by the DRM client attempting to use too much memory in a single request. Dumping out the requested and available memory values should help point out failures in the DRM code to catch over commitments of this form. Signed-off-by: Keith Packard <keithp@keithp.com>
2008-12-17libdrm: add mode setting filesJesse Barnes
Add mode setting files to libdrm, including xf86drmMode.* and the new drm_mode.h header. Also add a couple of tests to sanity check the kernel interfaces and update code to support them.
2008-12-14intel: don't skip set_domain on mapping of shared buffers.Eric Anholt
2008-12-14intel: don't let named buffers into the BO cache.Eric Anholt
We wouldn't want some remaining 3D rendering to scribble on our batchbuffer.
2008-12-14intel: Remove the mapped flag, which is adequately covered by bo_gem->virtual.Eric Anholt
2008-12-10Revert "Merge branch 'modesetting-gem'"Jesse Barnes
This reverts commit 6656db10551bbb8770dd945b6d81d5138521f208. We really just want the libdrm and ioctl bits, not all the driver stuff.
2008-12-03Merge branch 'master' into modesetting-gemJesse Barnes
2008-12-02intel: Add a function for setting (GTT,GTT) domain, for use by UXA.Eric Anholt
This function can also serve the role that the bo_wait_rendering did, when write_enable is unset.
2008-11-19libdrm_intel: fix merge errorJesse Barnes
don't take the lock twice
2008-11-13Merge branch 'master' into modesetting-gemJesse Barnes
Conflicts: libdrm/Makefile.am libdrm/intel/intel_bufmgr.h libdrm/intel/intel_bufmgr_fake.c libdrm/intel/intel_bufmgr_gem.c shared-core/drm.h shared-core/i915_dma.c shared-core/i915_irq.c shared-core/radeon_cp.c shared-core/radeon_drv.h
2008-11-13libdrm_intel: fix warnings on 64 bitJesse Barnes
Cast a couple of %llx args to unsigned long long.
2008-11-13libdrm: add support for i915 GTT mapping ioctlJesse Barnes
Add a drm_intel_gem_bo_map_gtt() function for mapping a buffer object through the aperture rather than directly to its CPU cacheable memory.
2008-11-07intel: Restart on interrupt of bo_wait_rendering instead of complaining.Eric Anholt
2008-10-30intel: Rename dri_ and intel_ symbols to drm_intel_.Eric Anholt
I wanted to avoid doing this, as it's a bunch of churn, but there was a conflict between the dri_ symbols in libdrm and the symbols that were in Mesa in 7.2, which broke Mesa 7.2 AIGLX when the 2D driver had loaded new libdrm symbols. The new naming was recommended by cworth for giving the code a unique prefix identifying where the code lives. Additionally, take the opportunity to fix up two API mistakes: emit_reloc's arguments were in a nonsensical order, and set_tiling lacked the stride argument that the kernel will want to use soon. API compatibility with released code is maintained using #defines.
2008-10-28intel: Add dri_bufmgr_check_aperture support for bufmgr_gem.Eric Anholt
This relies on a new kernel ioctl to get the available aperture size. In order to provide reasonable performance from dri_bufmgr_check_aperture, we now require that once a buffer has been used as the target of a relocation, it gets no further relocations added to it. This cuts the cost of check_aperture from 10% to 1% in the 3D driver with no code changes, but slightly complicates our plans for the 2D driver.
2008-10-16intel: ioctl is not defined to return -errnoKeith Packard
Don't count on ioctl returning -errno; use errno directly. Signed-off-by: Keith Packard <keithp@keithp.com> Signed-off-by: Eric Anholt <eric@anholt.net>
2008-10-17intel: Protect bufmgr objects with a pthread mutex.Eric Anholt
We want to be able to use the bufmgr from multiple threads for GL, and thus we need to protect the internal structures. The pthread-stubs package is used so that programs not linked against pthreads get weak symbols to stubs and don't eat most of the cost.
2008-10-14intel: Add interface for getting tiling mode of a bo.Eric Anholt
2008-10-09intel: Protect bufmgr objects with a pthread mutex.Eric Anholt
We want to be able to use the bufmgr from multiple threads for GL, and thus we need to protect the internal structures. The pthread-stubs package is used so that programs not linked against pthreads get weak symbols to stubs and don't eat most of the cost.
2008-09-30intel bufmgr: reinstate buffer handle trackingJesse Barnes
We need a way of getting at the underlying handle for use with mode setting. We can either export it in the dri_bo object or provide a new callback to get it.
2008-09-30Merge remote branch 'origin/master' into modesetting-gemDave Airlie
Conflicts: libdrm/Makefile.am libdrm/dri_bufmgr.h linux-core/drm_irq.c linux-core/drm_sysfs.c linux-core/drm_ttm.c shared-core/i915_dma.c shared-core/i915_irq.c shared-core/nouveau_drv.h shared-core/radeon_cp.c
2008-09-23intel: Do strerror on errno, not on the -1 return value from ioctl.Eric Anholt
2008-09-10intel: don't forget to include config.h in bufmgr code.Eric Anholt
Thanks to airlied for catching this.
2008-09-10intel: move drm calls to exec buffers to libdrm_intel.Eric Anholt
This avoids duplicating the effort in 3 places. Also, added emit/wait fence callbacks back in bufmgr_fake since we need it for non-drm 2d. Sigh.
2008-09-10Move intel libdrm stuff to libdrm_intel.soEric Anholt
dri_bufmgr.h is replaced by intel_bufmgr.h, and several functions are renamed, though the structures and many functions remain dri_bufmgr_* and dri_bo_*
2008-08-26[intel_bufmgr_gem] Remember global name when creating buffer from name.Kristian Høgsberg
2008-08-13Merge branch 'master' into modesetting-gemJesse Barnes
Conflicts: libdrm/Makefile.am libdrm/xf86drm.h shared-core/i915_dma.c shared-core/i915_irq.c
2008-08-12[intel_bufmgr_gem] Fix flink buffer name caching (#17085, #17092).Kristian Høgsberg
Store the global name in global_name, don't overwrite the gem_handle.
2008-08-12Export a generic dri_bo handle for use by clientsJesse Barnes
We'll need something like this (either a handle field or a dri_bo_get_handle function) for kernel mode setting to get at the handles.
2008-08-08Fix compile warning from check_aperture change.Eric Anholt
2008-08-08Replace the check_aperture API with one we can make thread-safe.Eric Anholt
While the bufmgr isn't thread-safe at the moment, we need it to be for shared objects between contexts.
2008-08-07Make flink save the kernel-assigned name and return it instead of creating ↵Keith Packard
another name
2008-08-04Expose pin/unpin/set_tiling/flink APIsKeith Packard
2008-06-24[intel-gem] Use I915_GEM_DOMAIN_GTT in dri_gem_bo_wait_rendering.Keith Packard
I915_GEM_DOMAIN_CPU is very expensive to wait for -- it generally requires clflushing the frame buffer.
2008-06-20[intel-gem] Add DRM_IOCTL_I915_GEM_SW_FINISH to flag CPU writesKeith Packard
When a software fallback has completed, usermode must notify the kernel so that any scanout buffers can be synchronized. This ioctl should be called whenever a fallback completes to flush CPU and chipset caches.
2008-06-13[gem] Catch -EINTR from blocking ioctls and restart them.Eric Anholt
Thanks to Thomas Hellstrom for catching the issue, no thanks to the kernel developer who authoritatively told me that they would get restarted on their own.
2008-06-11[gem] Move potentially device-specific ioctls to the intel driver.Eric Anholt
This is the create (may want location flags), pread/pwrite/mmap (performance tuning hints), and set_domain (will 32 bits be enough for everyone?) ioctls. Left in the generic set are just flink/open/close. The 2D driver must be updated for this change, and API but not ABI is broken for 3D. The driver version is bumped to mark this.
2008-06-06[gem] Don't forget to munmap in the non-bo-reuse object-freeing case.Eric Anholt
2008-06-06[libdrm/intel] Eliminate extra dri_gem_bo_bucket_entry structureKeith Packard
Place the buffer reuse links right into the dri_bo_gem object.