linux/drivers/gpu/drm
Chris Wilson 39b4d07aa3 drm: Hold the mutex when dropping the last GEM reference (v2)
In order to be fully threadsafe we need to check that the drm_gem_object
refcount is still 0 after acquiring the mutex in order to call the free
function. Otherwise, we may encounter scenarios like:

Thread A:                                        Thread B:
drm_gem_close
unreference_unlocked
kref_put                                         mutex_lock
...                                              i915_gem_evict
...                                              kref_get -> BUG
...                                              i915_gem_unbind
...                                              kref_put
...                                              i915_gem_object_free
...                                              mutex_unlock
mutex_lock
i915_gem_object_free -> BUG
i915_gem_object_unbind
kfree
mutex_unlock

Note that no driver is currently using the free_unlocked vfunc and it is
scheduled for removal, hasten that process.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=30454
Reported-and-Tested-by: Magnus Kessler <Magnus.Kessler@gmx.net>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: stable@kernel.org
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-10-01 21:08:45 +10:00
..
i2c drm/i2c/ch7006: Don't use POWER_LEVEL_FULL_POWER_OFF on early chip versions. 2010-08-09 15:16:23 +10:00
i810 drm: i810/i830: fix locked ioctl variant 2010-09-30 12:45:09 +10:00
i830 drm: i810/i830: fix locked ioctl variant 2010-09-30 12:45:09 +10:00
i915 drm/gem: handlecount isn't really a kref so don't make it one. 2010-10-01 09:17:44 +10:00
mga drm: block userspace under allocating buffer and having drivers overwrite it (v2) 2010-08-17 14:52:25 +10:00
nouveau drm/gem: handlecount isn't really a kref so don't make it one. 2010-10-01 09:17:44 +10:00
r128 drm: block userspace under allocating buffer and having drivers overwrite it (v2) 2010-08-17 14:52:25 +10:00
radeon drm/gem: handlecount isn't really a kref so don't make it one. 2010-10-01 09:17:44 +10:00
savage Merge branch 'drm-core-next' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6 2010-08-23 18:28:03 -07:00
sis drm: block userspace under allocating buffer and having drivers overwrite it (v2) 2010-08-17 14:52:25 +10:00
tdfx
ttm drm: ttm sparse fixes. 2010-09-24 10:09:08 +10:00
via drm: block userspace under allocating buffer and having drivers overwrite it (v2) 2010-08-17 14:52:25 +10:00
vmwgfx drm: Use a nondestructive mode for output detect when polling (v2) 2010-09-14 20:38:48 +10:00
ati_pcigart.c drm/radeon: Fix pci_map_page() error checking 2010-08-12 09:38:29 +10:00
drm_agpsupport.c
drm_auth.c drivers/gpu/drm: Use kzalloc 2010-05-18 15:57:05 +10:00
drm_buffer.c drm: fix trivial coding errors 2010-09-24 10:10:23 +10:00
drm_bufs.c DRM: Replace kmalloc/memset combos with kzalloc 2010-08-12 09:12:30 +10:00
drm_cache.c
drm_context.c
drm_crtc_helper.c drm: Use a nondestructive mode for output detect when polling (v2) 2010-09-14 20:38:48 +10:00
drm_crtc.c drm: expand gamma_set 2010-08-10 10:47:00 +10:00
drm_debugfs.c
drm_dma.c drivers/gpu/drm: Use kzalloc 2010-05-18 15:57:05 +10:00
drm_dp_i2c_helper.c
drm_drawable.c
drm_drv.c drm: block userspace under allocating buffer and having drivers overwrite it (v2) 2010-08-17 14:52:25 +10:00
drm_edid_modes.h drm/edid: Split mode lists out to their own header for readability 2010-08-10 10:47:00 +10:00
drm_edid.c Merge branch 'drm-core-next' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6 2010-08-12 09:21:39 -07:00
drm_encoder_slave.c drm/kms: Simplify setup of the initial I2C encoder config. 2010-08-05 09:37:45 +10:00
drm_fb_helper.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input 2010-08-28 13:55:31 -07:00
drm_fops.c Merge remote branch 'nouveau/for-airlied' of /ssd/git/drm-nouveau-next into drm-fixes 2010-08-27 09:09:46 +10:00
drm_gem.c drm: Hold the mutex when dropping the last GEM reference (v2) 2010-10-01 21:08:45 +10:00
drm_global.c drm: move ttm global code to core drm 2010-08-04 09:46:06 +10:00
drm_hashtab.c
drm_info.c drm/gem: handlecount isn't really a kref so don't make it one. 2010-10-01 09:17:44 +10:00
drm_ioc32.c
drm_ioctl.c drm: Fix support for PCI domains 2010-08-10 08:20:20 +10:00
drm_irq.c Merge branch 'drm-tracepoints' into drm-testing 2010-07-07 18:38:44 +10:00
drm_lock.c drm: fix regression in drm locking since BKL removal. 2010-08-27 09:10:28 +10:00
drm_memory.c drivers/gpu/drm/drm_memory.c: fix check for end of loop 2010-04-28 18:41:51 +10:00
drm_mm.c drm: mm: fix range restricted allocations 2010-08-27 09:10:16 +10:00
drm_modes.c drm/modes: Fix CVT-R modeline generation 2010-08-27 09:10:33 +10:00
drm_pci.c drm: fix race between driver loading and userspace open. 2010-09-14 20:39:04 +10:00
drm_platform.c drm: fix race between driver loading and userspace open. 2010-09-14 20:39:04 +10:00
drm_proc.c
drm_scatter.c
drm_sman.c
drm_stub.c drm: Free devname along with master->unique 2010-08-02 10:14:30 +10:00
drm_sysfs.c drm: Use a nondestructive mode for output detect when polling 2010-09-13 20:29:11 +10:00
drm_trace_points.c drm: add vblank event trace point 2010-07-02 14:02:44 +10:00
drm_trace.h drm: add per-event vblank event trace points 2010-07-02 14:03:24 +10:00
drm_vm.c drm: Prune GEM vma entries 2010-09-28 09:14:34 +10:00
Kconfig drm/radeon/kms: add support for internal thermal sensors (v3) 2010-08-02 10:00:00 +10:00
Makefile drm: move ttm global code to core drm 2010-08-04 09:46:06 +10:00
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