iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
linux/drivers/gpu/drm
History
Daniel Vetter de2b998552 drm/i915: don't return a spurious -EIO from intel_ring_begin 
The issue with this check is that it results in userspace receiving an
-EIO while the gpu reset hasn't completed, resulting in fallback to sw
rendering or worse.

Now there's also a stern comment in intel_ring_wait_seqno saying that
intel_ring_begin should not return -EAGAIN, ever, because some callers
can't handle that. But after an audit of the callsites I don't see any
issues. I guess the last problematic spot disappeared with the removal
of the pipelined fencing code.

So do the right thing and call check_wedge, which should properly
decide whether an -EAGAIN or -EIO is appropriate if wedged is set.

Note that the early check for a wedged gpu before touching the ring is
rather important (and it took me quite some time of acting like the
densest doofus to figure that out): If we don't do that and the gpu
died for good, not having been resurrect by the reset code, userspace
can merrily fill up the entire ring until it notices that something is
amiss.

Allowing userspace to emit more render, despite that we know that it
will fail can't lead to anything good (and by experience can lead to
all sorts of havoc, including angering the OOM gods and hard-hanging
the hw for good).

v2: Fix EAGAIN mispell, noticed by Chris Wilson.

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2012-07-05 10:03:45 +02:00
..
ast
drm: update ast/cirrus/mgag200 for change in TTM api
2012-05-23 14:08:41 +01:00
cirrus
drm/cirrus: kick out conflicting framebuffers earlier
2012-06-01 11:11:09 +01:00
exynos
drm/exynos: fixed blending for hdmi graphic layer
2012-06-05 13:25:18 +09:00
gma500
drm: Constify drm_mode_config_funcs pointer
2012-05-22 10:35:07 +01:00
i2c
drm: add convenience function to create an range property
2012-02-09 10:15:25 +00:00
i810
i810: switch to vm_mmap()
2012-05-30 21:04:54 -04:00
i915
drm/i915: don't return a spurious -EIO from intel_ring_begin
2012-07-05 10:03:45 +02:00
mga
drm: move pci bus master enable into driver.
2012-02-16 18:31:07 +00:00
mgag200
drm/mgag200: kick off conflicting framebuffers earlier.
2012-06-01 11:12:39 +01:00
nouveau
nouveau: add vmap support to nouveau prime support
2012-05-31 14:14:00 +01:00
r128
drm: move pci bus master enable into driver.
2012-02-16 18:31:07 +00:00
radeon
drm/radeon: SI tiling fixes for display
2012-06-20 19:55:56 +01:00
savage
drm: checking the wrong variable in savage_do_init_bci()
2012-05-17 11:42:27 +01:00
sis
drm sis: initialize object_idr
2012-06-16 11:18:53 +01:00
tdfx
drm: Make the per-driver file_operations struct const
2011-11-11 11:14:47 +00:00
ttm
drm/ttm: Fix buffer object metadata accounting regression v2
2012-06-12 15:57:47 +01:00
udl
drm/udl: only bind to the video devices on the hub.
2012-06-16 11:09:58 +01:00
via
drm via: initialize object_idr
2012-06-16 11:18:38 +01:00
vmwgfx
drm/vmwgfx: Fix nasty write past alloced memory area
2012-06-01 17:00:20 +01:00
ati_pcigart.c
…
drm_agpsupport.c
…
drm_auth.c
drm: Fix authentication kernel crash
2012-01-25 09:27:45 +00:00
drm_buffer.c
…
drm_bufs.c
VM: add "vm_mmap()" helper function
2012-04-20 17:29:13 -07:00
drm_cache.c
Merge branch 'drm-intel-next' of git://people.freedesktop.org/~danvet/drm-intel into drm-core-next
2012-04-12 10:27:01 +01:00
drm_context.c
drm: Unify and fix idr error handling
2012-04-24 09:50:20 +01:00
drm_crtc_helper.c
drm: Don't initialize local ret variable when not needed
2012-05-22 10:32:58 +01:00
drm_crtc.c
drm: Use stdint types for consistency
2012-05-29 11:07:09 +01:00
drm_debugfs.c
drm: serialize access to list of debugfs files
2011-11-11 11:05:19 +00:00
drm_dma.c
…
drm_dp_i2c_helper.c
…
drm_drv.c
drm: add generic ioctls to get/set properties on any object
2012-05-17 11:11:22 +01:00
drm_edid_load.c
drm: Don't initialize local ret variable when not needed
2012-05-22 10:32:58 +01:00
drm_edid_modes.h
drm: replace open-coded ARRAY_SIZE with macro
2012-04-20 13:12:16 +01:00
drm_edid.c
drm/edid: don't return stack garbage from supports_rb
2012-06-21 09:34:13 +01:00
drm_encoder_slave.c
…
drm_fb_helper.c
drm: Make the CRTC gamma_set operation optional
2012-05-22 10:35:15 +01:00
drm_fops.c
drm: Releasing FBs before releasing GEM objects during drm_release
2012-04-19 14:40:41 +01:00
drm_gem.c
drm/prime: add exported buffers to current fprivs imported buffer list (v2)
2012-05-23 10:46:03 +01:00
drm_global.c
…
drm_hashtab.c
…
drm_info.c
…
drm_ioc32.c
drivers/gpu/drm/drm_ioc32.c: initialize all fields
2012-02-03 09:47:32 +00:00
drm_ioctl.c
drm/prime: expose capability flags for userspace.
2012-05-18 11:12:16 +01:00
drm_irq.c
drm: Don't initialize local ret variable when not needed
2012-05-22 10:32:58 +01:00
drm_lock.c
drm: Don't initialize local ret variable when not needed
2012-05-22 10:32:58 +01:00
drm_memory.c
drm: remove unused code
2012-02-29 10:18:29 +00:00
drm_mm.c
…
drm_modes.c
drm: Add drm_mode_copy()
2012-03-15 09:52:51 +00:00
drm_pci.c
drm: move pci bus master enable into driver.
2012-02-16 18:31:07 +00:00
drm_platform.c
drm: cope with platformdev->id == -1
2012-03-07 14:03:40 +00:00
drm_prime.c
drm/prime: add exported buffers to current fprivs imported buffer list (v2)
2012-05-23 10:46:03 +01:00
drm_proc.c
…
drm_scatter.c
…
drm_stub.c
drm: Don't initialize local ret variable when not needed
2012-05-22 10:32:58 +01:00
drm_sysfs.c
drm: Miscellaneous typo fixes and documentation updates
2012-05-22 10:34:33 +01:00
drm_trace_points.c
…
drm_trace.h
…
drm_usb.c
drm/usb: fix module license on drm/usb layer.
2012-04-19 09:33:32 +01:00
drm_vm.c
drm: pass dev to drm_vm_{open,close}_locked()
2012-05-11 17:37:46 +01:00
Kconfig
drm/kms: driver for virtual cirrus under qemu
2012-05-17 11:02:24 +01:00
Makefile
drm/kms: driver for virtual cirrus under qemu
2012-05-17 11:02:24 +01:00
README.drm
…

README.drm 

************************************************************
* For the very latest on DRI development, please see:      *
*     http://dri.freedesktop.org/                          *
************************************************************

The Direct Rendering Manager (drm) is a device-independent kernel-level
device driver that provides support for the XFree86 Direct Rendering
Infrastructure (DRI).

The DRM supports the Direct Rendering Infrastructure (DRI) in four major
ways:

    1. The DRM provides synchronized access to the graphics hardware via
       the use of an optimized two-tiered lock.

    2. The DRM enforces the DRI security policy for access to the graphics
       hardware by only allowing authenticated X11 clients access to
       restricted regions of memory.

    3. The DRM provides a generic DMA engine, complete with multiple
       queues and the ability to detect the need for an OpenGL context
       switch.

    4. The DRM is extensible via the use of small device-specific modules
       that rely extensively on the API exported by the DRM module.


Documentation on the DRI is available from:
    http://dri.freedesktop.org/wiki/Documentation
    http://sourceforge.net/project/showfiles.php?group_id=387
    http://dri.sourceforge.net/doc/

For specific information about kernel-level support, see:

    The Direct Rendering Manager, Kernel Support for the Direct Rendering
    Infrastructure
    http://dri.sourceforge.net/doc/drm_low_level.html

    Hardware Locking for the Direct Rendering Infrastructure
    http://dri.sourceforge.net/doc/hardware_locking_low_level.html

    A Security Analysis of the Direct Rendering Infrastructure
    http://dri.sourceforge.net/doc/security_low_level.html