Switch branches/tags
Nothing to show
Commits on Jan 4, 2011
  1. pscnv: install the nv04/c0_pushbuf.h headers

    Christoph Bumiller committed Jan 4, 2011
  2. pscnv: fix nouveau_grobj_autobind pushbuf commands

    Christoph Bumiller committed Jan 4, 2011
  3. pscnv: import split pushbuf headers from nouveau

    Christoph Bumiller committed Dec 22, 2010
  4. Merge remote branch 'fdo/master'

    Christoph Bumiller committed Jan 4, 2011
    Not really conflicts, something went wrong.
Commits on Dec 21, 2010
  1. nouveau: fix up reloc_emit() to accept NULL target buffer

    skeggsb committed Dec 20, 2010
    The nvc0 gallium drivers passes NULL here to indicate to the memory manager
    that a buffer is being used, but without creating an actual reloc.
    Signed-off-by: Ben Skeggs <>
  2. nouveau: split pushbuf macros specific to nv04-nv50 out, and add nvc0

    skeggsb committed Dec 20, 2010
    Signed-off-by: Ben Skeggs <>
  3. nouveau: nvc0 drm has no concept of "notifier block"

    skeggsb committed Dec 8, 2010
    Signed-off-by: Ben Skeggs <>
Commits on Dec 19, 2010
  1. intel: Export CONSTANT_BUFFER addressing mode

    ickle committed Dec 19, 2010
    Signed-off-by: Chris Wilson <>
Commits on Dec 10, 2010
  1. configure: Bump version to 2.4.23

    ickle committed Dec 10, 2010
    To export new kernel API for Intel's 2010Q4 release.
    Signed-off-by: Chris Wilson <>
  2. tests: Update for ENOENT returns from unknown handles

    ickle committed Dec 10, 2010
    Signed-off-by: Chris Wilson <>
Commits on Dec 8, 2010
  1. pscnv: use bits ff00 for memory storage type on nvc0 as well

    Christoph Bumiller committed Dec 8, 2010

    Christoph Bumiller committed Dec 8, 2010
Commits on Dec 7, 2010
  1. intel: Reorder need_fence vs fenced_command to avoid fences on gen4

    ickle committed Dec 7, 2010
    gen4+ hardware doesn't use fences for GPU access and the older kernel
    doesn't expect userspace to make such a mistake. So don't.
    Signed-off-by: Chris Wilson <>
  2. drm: don't do the create the node ourselves if we have udev.

    Dave Airlie committed Dec 7, 2010
    this can remove nodes it shouldn't, let udev run the show.
    this is needed for reliably GPU switch.
    Signed-off-by: Dave Airlie <>
Commits on Dec 3, 2010
  1. intel: If the command is fenced inform the kernel

    ickle committed Dec 3, 2010
    ... but only account for a fenced used if the object is tiled.
    Signed-off-by: Chris Wilson <>
Commits on Dec 2, 2010
Commits on Nov 25, 2010
  1. intel: Add a forward declaration of struct drm_clip_rect

    ickle committed Nov 25, 2010
    ... so that intel_bufmgr.h can be compiled standalone.
    Signed-off-by: Chris Wilson <>
Commits on Nov 22, 2010
  1. intel: Compute in-aperture size for relaxed fenced objects

    ickle committed Nov 22, 2010
    For relaxed fencing the object may only consume the small set of active
    pages, but still requires a fence region once bound into the aperture.
    This is the size we need to use when computing the maximum possible
    aperture space that could be used by a single batchbuffer and so avoid
    hitting ENOSPC.
    Reported-by: Daniel Vetter <>
    Signed-off-by: Chris Wilson <>
  2. nouveau: Add implicit pushbuf flush before gpuobj destruction.

    curro committed Nov 20, 2010
    It makes sure that GPU object destruction is executed in order with
    respect to the previous FIFO commands.
    Signed-off-by: Francisco Jerez <>
    Acked-by: Ben Skeggs <>
Commits on Nov 9, 2010
  1. intel: Fix drm_intel_gem_bo_wait_rendering to wait for read-only usag…

    anholt committed Nov 9, 2010
    …e too.
    Both the consumers of this API (sync objects and client throttling)
    were expecting this behavior.  The kernel used to actually behave the
    desired (but incorrect) way for us anyway, but that got fixed a while
Commits on Nov 7, 2010
  1. intel: initialize bufmgr.bo_mrb_exec unconditionally

    Albert Damen committed with ickle Nov 7, 2010
    If bufmgr.bo_mrb_exec is not set, drm_intel_bo_mrb_exec returns ENODEV
    even though drm_intel_gem_bo_mrb_exec2 will work fine for the RENDER ring.
    Fixes xf86-video-intel after commit 'add BLT ring support' (5bed685f76)
    with kernels without BSD or BLT ring support (2.6.34 and before).
    Signed-off-by: Albert Damen <>
    Signed-off-by: Chris Wilson <>
Commits on Nov 2, 2010
  1. intel: Drop silly asserts on mappings present at unmap time.

    anholt committed Nov 2, 2010
    The intent of these was to catch mismatched map/unmap.  What it
    actually did was check whether there was ever a mapping of that type
    (including in a previous life of the buffer through the userland BO
    cache), not whether they were mismatched.  We don't even actually want
    to catch mismatched map/unmap, unless we also do refcounting, since at
    one point Mesa would do map/map/use/unmap/unmap.  Just remove this
    code instead.
  2. intel: Remove gratuitous assert on bo_reference.

    anholt committed Nov 2, 2010
    This couldn't be triggered except by overflow, since there's an assert
    in unreference to catch the usual failure of over-unreferencing.
  3. pscnv: s/libdrm_nouveau/libdrm_pscnv in

    Christoph Bumiller committed Nov 2, 2010
  4. pscnv: increase spin count on fence wait

    Christoph Bumiller committed Nov 2, 2010
  5. nvc0: add an IB call marker into the trace file

    Christoph Bumiller committed Nov 2, 2010
  6. pscnv: silence IB PUT debug message

    Christoph Bumiller committed Nov 2, 2010
  7. pscnv: add pushbuf_size param to nouveau_channel_alloc

    Christoph Bumiller committed Oct 30, 2010
    Regain API compatiblity.
  8. pscnv: use NOUVEAU_BO_TILE_SCANOUT like nouveau

    Christoph Bumiller committed Oct 30, 2010
  9. Reestablish compatibility with fdo libdrm.

    Christoph Bumiller committed Oct 30, 2010
Commits on Nov 1, 2010
  1. intel: Remove stale comment.

    anholt committed Sep 20, 2010
Commits on Oct 31, 2010
  1. nouveau: Avoid unnecessary call to CPU_FINI.

    curro committed Oct 31, 2010
    nouveau_bo_unmap called the CPU_FINI IOCTL even if it was a NOSYNC
    mapping. It caused no harmful effects (actually CPU_FINI is a no-op on
    recent enough kernels) besides the precious CPU cycles being wasted.
    Signed-off-by: Francisco Jerez <>
Commits on Oct 29, 2010
  1. intel: enable relaxed fence allocation for i915

    ickle committed Oct 29, 2010
    The kernel has always allowed userspace to underallocate objects
    supplied for fencing. However, the kernel only allocated the object size
    for the fence in the GTT and so caused tiling corruption. More recently
    the kernel does allocate the full fence region in the GTT for an
    under-sized object and so advertises that clients may finally make use
    of this feature. The biggest benefit is for texture-heavy GL games on
    i945 such as World of Padman which go from needing over 1GiB of RAM to
    play to fitting in the GTT!
    Signed-off-by: Chris Wilson <>
Commits on Oct 27, 2010
  1. s/drmStrdup/strdup/

    nwnk committed Oct 27, 2010
    _DRM_MALLOC hasn't been a relevant concern since we split libdrm out
    from xserver.
    Signed-off-by: Adam Jackson <>