linux

mirror of https://github.com/torvalds/linux.git synced 2024-12-22 10:56:40 +00:00

History

Daniel Vetter 93927ca52a drm/i915: Revert shrinker changes from "Track unbound pages" This partially reverts commit `6c085a728c` Author: Chris Wilson <chris@chris-wilson.co.uk> Date: Mon Aug 20 11:40:46 2012 +0200 drm/i915: Track unbound pages Closer inspection of that patch revealed a bunch of unrelated changes in the shrinker: - The shrinker count is now in pages instead of objects. - For counting the shrinkable objects the old code only looked at the inactive list, the new code looks at all bounds objects (including pinned ones). That is obviously in addition to the new unbound list. - The shrinker cound is no longer scaled with sysctl_vfs_cache_pressure. Note though that with the default tuning value of vfs_cache_pressue = 100 this doesn't affect the shrinker behaviour. - When actually shrinking objects, the old code first dropped purgeable objects, then normal (inactive) objects. Only then did it, in a last-ditch effort idle the gpu and evict everything. The new code omits the intermediate step of evicting normal inactive objects. Safe for the first change, which seems benign, and the shrinker count scaling, which is a bit a different story, the endresult of all these changes is that the shrinker is _much_ more likely to fall back to the last-ditch resort of idling the gpu and evicting everything. The old code could only do that if something else evicted lots of objects meanwhile (since without any other changes the nr_to_scan will be smaller than the object count). Reverting the vfs_cache_pressure behaviour itself is a bit bogus: Only dentry/inode object caches should scale their shrinker counts with vfs_cache_pressure. Originally I've had that change reverted, too. But Chris Wilson insisted that it's too bogus and shouldn't again see the light of day. Hence revert all these other changes and restore the old shrinker behaviour, with the minor adjustment that we now first scan the unbound list, then the inactive list for each object category (purgeable or normal). A similar patch has been tested by a few people affected by the gen4/5 hangs which started to appear in 3.7, which some people bisected to the "drm/i915: Track unbound pages" commit. But just disabling the unbound logic alone didn't change things at all. Note that this patch doesn't fix the referenced bugs, it only hides the underlying bug(s) well enough to restore pre-3.7 behaviour. The key to achieve that is to massively reduce the likelyhood of going into a full gpu stall and evicting everything. v2: Reword commit message a bit, taking Chris Wilson's comment into account. v3: On Chris Wilson's insistency, do not reinstate the rather bogus vfs_cache_pressure change. Tested-by: Greg KH <gregkh@linuxfoundation.org> Tested-by: Dave Kleikamp <dave.kleikamp@oracle.com> References: https://bugs.freedesktop.org/show_bug.cgi?id=55984 References: https://bugs.freedesktop.org/show_bug.cgi?id=57122 References: https://bugs.freedesktop.org/show_bug.cgi?id=56916 References: https://bugs.freedesktop.org/show_bug.cgi?id=57136 Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: stable@vger.kernel.org Acked-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>		2013-01-10 18:02:44 +01:00
..
ast	drm/ttm: remove no_wait_reserve, v3	2012-12-10 20:21:30 +10:00
cirrus	drm/ttm: remove no_wait_reserve, v3	2012-12-10 20:21:30 +10:00
exynos	drm/exynos: add gsc ipp driver	2012-12-15 02:40:00 +09:00
gma500	drm/gma500: drm_connector_property -> drm_object_property	2012-11-30 10:20:11 -06:00
i2c	drm/i2c: drm_connector_property -> drm_object_property	2012-11-30 10:20:12 -06:00
i810
i915	drm/i915: Revert shrinker changes from "Track unbound pages"	2013-01-10 18:02:44 +01:00
mga
mgag200	drm/ttm: remove no_wait_reserve, v3	2012-12-10 20:21:30 +10:00
nouveau	drm/nve0/graph: fix fuc, and enable acceleration on all known chipsets	2012-12-23 22:59:32 +10:00
r128
radeon	Merge branch 'drm-fixes-3.8' of git://people.freedesktop.org/~agd5f/linux into drm-next	2012-12-30 13:02:48 +10:00
savage
shmobile	drm/shmob: drm_connector_property -> drm_object_property	2012-11-30 10:20:11 -06:00
sis
tdfx
tegra	Revert "drm: tegra: protect DC register access with mutex"	2012-12-30 21:58:20 +10:00
ttm	drm/ttm: fix delayed ttm_bo_cleanup_refs_and_unlock delayed handling	2012-12-20 07:46:20 +10:00
udl	drm/udl: drm_connector_property -> drm_object_property	2012-11-30 10:20:11 -06:00
via
vmwgfx	drm/ttm: remove no_wait_reserve, v3	2012-12-10 20:21:30 +10:00
ati_pcigart.c
drm_agpsupport.c
drm_auth.c
drm_buffer.c
drm_bufs.c
drm_cache.c
drm_context.c
drm_crtc_helper.c	drm/doc: integrate crtc helper api into docbook	2012-11-28 20:19:58 +10:00
drm_crtc.c	drm: remove legacy drm_connector_property fxns	2012-11-30 10:30:48 -06:00
drm_debugfs.c
drm_dma.c
drm_dp_helper.c	drm/doc: add new dp helpers into drm DocBook	2012-11-28 20:26:53 +10:00
drm_drv.c
drm_edid_load.c
drm_edid_modes.h
drm_edid.c	Merge branch 'drm-intel-fixes' of git://people.freedesktop.org/~danvet/drm-intel into drm-next	2012-12-16 06:05:03 +00:00
drm_encoder_slave.c
drm_fb_cma_helper.c
drm_fb_helper.c	drm: remove legacy drm_connector_property fxns	2012-11-30 10:30:48 -06:00
drm_fops.c	drm: set dev_mapping before calling drm_open_helper	2012-11-07 10:51:15 +10:00
drm_gem_cma_helper.c
drm_gem.c
drm_global.c
drm_hashtab.c	drm: Add a hash-tab rcu-safe API	2012-11-28 18:36:05 +10:00
drm_info.c
drm_ioc32.c
drm_ioctl.c	drm: add support for monotonic vblank timestamps	2012-11-20 16:06:16 +10:00
drm_irq.c	drm: hold event_lock while accessing vblank_event_list	2012-11-29 03:30:34 -08:00
drm_lock.c
drm_memory.c
drm_mm.c	drm: Only evict the blocks required to create the requested hole	2013-01-08 11:52:02 +01:00
drm_modes.c
drm_pci.c	drm/pci: add missing variable initialization	2012-11-29 18:20:31 +10:00
drm_platform.c
drm_prime.c
drm_proc.c
drm_scatter.c
drm_stub.c	drm: add support for monotonic vblank timestamps	2012-11-20 16:06:16 +10:00
drm_sysfs.c	drm: remove legacy drm_connector_property fxns	2012-11-30 10:30:48 -06:00
drm_trace_points.c
drm_trace.h
drm_usb.c
drm_vm.c
Kconfig	drm: Add NVIDIA Tegra20 support	2012-11-20 15:43:41 +10:00
Makefile	drm: only build ati_pcigart if PCI enabled	2012-11-28 20:12:29 +10:00
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