summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2005-03-13Command DMA optimizations:Felix Kuehling
- don't waste DMA memory when small command buffers are flushed - minimized padding with noops - slightly simplified faked DMA flushing
2005-03-08Fix for bug 2673 from Egbert Eich - memset the versionDave Airlie
2005-03-07Tracked down random lockups related to command DMA that occurred in Quake3Felix Kuehling
after ~5min: buffer aging was subtly broken. Part of this may have also affected vertex DMA buffer aging and client-side texture heap aging, though with less fatal consequences. Bumped minor version and driver date.
2005-03-07minor pointer cast typoDave Airlie
2005-03-06Added support for command DMA on Savage4-based hardware. UnfortunatelyFelix Kuehling
command and vertex DMA don't work at the same time. Command DMA performance is superior and works with all vertex formats. Bumped minor version and driver date.
2005-03-04add some idct type 3 packets for referenceDave Airlie
2005-02-23Use wrap counter to extend 16-bit hardware event tags to 32-bit logicalFelix Kuehling
event counters in the SAVAGE_EVENT_EMIT/WAIT ioctls. This is needed for reliable client-side texture heap aging. Slightly simplified DMA buffer aging while at it. Bumped minor version and driver date.
2005-02-20Fix VIA K8M800 PCI ID.Thomas Hellstrom
2005-02-19Fix a couple of gcc warnings in DRM_INFOs.Eric Anholt
2005-02-19Merge r1.26 from FreeBSD: Now that mem(4) is a kernel module, we need toEric Anholt
depend on it.
2005-02-18fd.o bug #2576: Add support for ATI RN50/ES1000. (ATI Technologies Inc.)Michel Daenzer
2005-02-18Bug #2567: Fix reversed memset arguments. (David Krause)Adam Jackson
2005-02-15Run depmod after installing new modulesKeith Whitwell
2005-02-14Use fuword32 for DRM_GET_USER_UNCHECKED when available. May help on 64-bitEric Anholt
platforms. Submitted by: Jung-uk Kim, jkim at niksun dot com
2005-02-14Use the proper API to get PCI vendor/device number for a dev.Eric Anholt
PR: ports/76879 Submitted by: Alex, lesha at intercaf dot ru.
2005-02-14Initialize kbuf to NULL to quiet the compiler about uninit variablesEric Anholt
(wasn't an issue). Don't forget to free kbuf if the copyin fails.
2005-02-13Fixed Futex release bug. Bumped driver date and patchlevel.Thomas Hellstrom
2005-02-13Fix bad copy'n'pastage of copyrights -- don't disclaim anything for VAEric Anholt
Linux or PI in my copyrights when I should be doing it for myself.
2005-02-13Add the first bits necessary for a port of savage to FreeBSD. More toEric Anholt
follow later.
2005-02-10add support for texture micro tiling for radeon/r200. Add support for cubeRoland Scheidegger
maps for r100. (Stephane Marchesin's port of the core version).
2005-02-10add support for texture micro tiling on radeon/r200. Add support for r100Roland Scheidegger
cube maps (since it also requires a version bump) at the same time.
2005-02-10Stephane's port of Eric's race fixKeith Whitwell
2005-02-08fix incorrect PCI id for ATI radeonRoland Scheidegger
2005-02-08Close a race which could allow for privilege escalation by users with DRIEric Anholt
privileges on Radeon hardware. Essentially, a malicious program could submit a packet containing an offset (possibly in main memory) to be rendered from/to, while a separate thread switched that offset in userspace rapidly between a valid value and an invalid one. radeon_check_and_fixup_offset() would pull the offset in from user space, check it, and spit it back out to user space to be copied in later by the emit code. It would sometimes catch the bad value, but sometimes the malicious program could modify it after the check and get an invalid offset rendered from/to. Fix this by allocating a temporary buffer and copying the data in at once. While here, make the cliprects stuff not do the VERIFYAREA_READ and COPY_FROM_USER_UNCHECKED gymnastics, avoiding a lock order reversal on FreeBSD. Performance impact is negligible -- no difference on r200 to ~1% improvement on rv200 in quake3 tests (P4 1Ghz, demofour at 1024x768, n=4 or 5).
2005-02-07Invalid bound check of driver defined ioctls in drm_ioctlDave Airlie
Bug 2489 Reporter: Aapo Tahkola <aet@rasterburn.org>
2005-02-07Cast user data to correct type in radeon_surface_free's copyin.Roland Scheidegger
2005-02-07change DRIVER_ to CORE_ makes things look nicer, also change it so theDave Airlie
driver name is marked on resource allocations
2005-02-07fix agp detection on linuxDave Airlie
2005-02-07Restore a debugging message to DRM_DEBUG instead of DRM_ERROR.Eric Anholt
2005-02-07Remove some annoying trailing whitespace.Eric Anholt
2005-02-05- Implement drm_initmap, and extend it with the resource number to helpEric Anholt
FreeBSD. Add drm_get_resource_{start|len} so linux-specific stuff doesn't need to be in shared code. - Fix mach64 build by using __DECONST to work around passing a const pointer to useracc, which is unfortunately not marked const. - Get rid of a lot of maplist code by not having dev->maplist be a pointer, and by sticking the link entries directly in drm_local_map_t rather than having a separate structure for the linked list. - Factor out map uninit and removal into its own routine, rather than duplicating in both drm_takedown() and drm_rmmap(). - Hook up more driver functions, and correct FreeBSD-specific bits of radeon_cp.c, making radeon work. - Baby steps towards using bus_space as we should.
2005-02-03Via driver: Add missing drm_poll function to via driver in core.Thomas Hellstrom
2005-02-03Declare r128_do_cleanup_pageflip static since it's only used here and itsEric Anholt
prototype went away.
2005-02-03Cast user data to correct type in radeon_surface_free's copyin.Eric Anholt
2005-02-01momentary revert. libdrm build may be broken now, but no one uses it yet...Adam Jackson
2005-02-01cleanup patch from Adrian Bunk <bunk@stusta.de>Dave Airlie
2005-02-01make functions static in i915, remove unused functionsDave Airlie
2005-02-01update i830 similiar to the kernel, add staticsDave Airlie
2005-02-01make more functions static in i810 and fix pageflip cleanupDave Airlie
2005-01-30Final pass of libdrm.so work:Adam Jackson
- Add $(DESTDIR) for distributors doing package creation - Remove OS-specific include path from build - Add /usr/include/drm for driver-kernel API - Install all of shared-core/*.h in /usr/include/drm - Rename xf86drm.h to libdrm.h since we're not X biased anymore - Include backwards compat for xf86drm.h name, with a warning - Fix libdrm source to account for drm.h living in /usr/include/drm
2005-01-29fix radeon drvDave Airlie
2005-01-27Fixed multiple devices DMA bug. Fixed PCI path FIRE command detectionThomas Hellstrom
2005-01-27fix incorrect PCI id for ATI radeonDave Airlie
2005-01-26(Stephane Marchesin,me) Add radeon framebuffer tiling support to radeonRoland Scheidegger
drm. Add new ioctls to manage surfaces which cover the tiled areas
2005-01-26replace magic number with macro constant RADEON_ZBLOCK16Roland Scheidegger
2005-01-24use libdrm after it was updatedDave Airlie
2005-01-24hopefully fix drm_core setversion ioctl... pointed out by Eric on ircDave Airlie
2005-01-22Add drm.h to the install target.Adam Jackson
2005-01-20Removed one bogus Savage3D PCI ID. Corrected another one. RestoredFelix Kuehling
numerical ordering.
2005-01-20Add a Savage3D PCI IDAdam Jackson