aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/gpu
Commit message (Collapse)AuthorAgeFilesLines
* Merge branch 'drm-linus' of ↵Linus Torvalds2010-02-235-76/+210
|\ | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6 * 'drm-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6: drm/vmwgfx: Fix queries if no dma buffer thrashing is occuring. drm/nv50: fix vram ptes on IGPs to point at stolen system memory drm/nv50: fix instmem binding on IGPs to point at stolen system memory drm/nv50: improve vram page table construction drm/nv50: more efficient clearing of gpu page table entries drm/nv50: make nv50_mem_vm_{bind,unbind} operate only on vram drm/nouveau: Fix up pre-nv17 analog load detection.
| * drm/vmwgfx: Fix queries if no dma buffer thrashing is occuring.Thomas Hellstrom2010-02-231-16/+92
| | | | | | | | | | | | | | Intercept query commands and apply relocations to their guest pointers. Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
| * Merge remote branch 'nouveau/for-airlied' of ../drm-nouveau-next into drm-linusDave Airlie2010-02-234-60/+118
| |\ | | | | | | | | | | | | | | | | | | | | | | | | | | | * 'nouveau/for-airlied' of ../drm-nouveau-next: drm/nv50: fix vram ptes on IGPs to point at stolen system memory drm/nv50: fix instmem binding on IGPs to point at stolen system memory drm/nv50: improve vram page table construction drm/nv50: more efficient clearing of gpu page table entries drm/nv50: make nv50_mem_vm_{bind,unbind} operate only on vram drm/nouveau: Fix up pre-nv17 analog load detection.
| | * drm/nv50: fix vram ptes on IGPs to point at stolen system memoryBen Skeggs2010-02-231-1/+7
| | | | | | | | | | | | Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
| | * drm/nv50: fix instmem binding on IGPs to point at stolen system memoryBen Skeggs2010-02-232-18/+41
| | | | | | | | | | | | | | | | | | | | | | | | | | | This also modifies the unused PRAMIN PT entries to be all zeroes, can't really recall why I used 9/0 initially, just that it didn't work for some reason. It was likely masking a bug elsewhere that's since been fixed. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
| | * drm/nv50: improve vram page table constructionBen Skeggs2010-02-231-11/+33
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This commit changes nouveau to construct PTEs which look very much like the ones the binary driver creates. I presume that filling multiple PTEs identically with length flags and the physical address of the start of a block of VRAM is a hint to the memory controller that it need not perform additional page table lookups for that range of addresses. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
| | * drm/nv50: more efficient clearing of gpu page table entriesBen Skeggs2010-02-231-24/+44
| | | | | | | | | | | | Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
| | * drm/nv50: make nv50_mem_vm_{bind,unbind} operate only on vramBen Skeggs2010-02-231-30/+13
| | | | | | | | | | | | | | | | | | GART is handled elsewhere, no reason to have the code for it here too. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
| | * drm/nouveau: Fix up pre-nv17 analog load detection.Francisco Jerez2010-02-231-1/+5
| | | | | | | | | | | | | | | Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
* | | i915 / PM: Fix hibernate regression caused by suspend/resume splittingRafael J. Wysocki2010-02-221-21/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Commit 84b79f8d2882b0a84330c04839ed4d3cefd2ff77 (drm/i915: Fix crash while aborting hibernation) attempted to fix a regression introduced by commit cbda12d77ea590082edb6d30bd342a67ebc459e0 (drm/i915: implement new pm ops for i915), but it went too far trying to split the freeze/suspend and resume/thaw parts of the code. As a result, it introduced another regression, which only is visible on some systems. Fix the problem by merging i915_drm_suspend() with i915_drm_freeze() and moving some code from i915_resume() into i915_drm_thaw(), so that intel_opregion_free() and intel_opregion_init() are also executed in the freeze and thaw code paths, respectively. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Reported-and-tested-by: Pedro Ribeiro <pedrib@gmail.com> Tested-by: Tino Keitel <tino.keitel@tikei.de> Acked-by: Eric Anholt <eric@anholt.net> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* | | Merge branch 'drm-linus' of ↵Linus Torvalds2010-02-198-18/+39
|\ \ \ | |/ / | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6 * 'drm-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6: drm/radeon: bump the UMS driver version number to indicate rv740 fix drm/radeon/kms: free fence IB if it wasn't emited at IB free time drm/ttm: fix caching problem on non-PAT systems. drm/radeon/rv740: fix backend setup drm/radeon/kms: fix shared ddc detection drm/radeon/kms/rs600: add connector quirk vgaarb: fix "target=default" passing
| * | drm/radeon: bump the UMS driver version number to indicate rv740 fixDave Airlie2010-02-201-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | This lets UMS userspace know the rv740 fix is in. For KMS we can consider the kernel release to be the v2.0.0 release so we don't need the bump there. Signed-off-by: Dave Airlie <airlied@redhat.com>
| * | drm/radeon/kms: free fence IB if it wasn't emited at IB free timeJerome Glisse2010-02-201-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | If at IB free time fence wasn't emited that means the IB wasn't scheduled because an error occured somewhere, thus we can free then fence and mark the IB as free. Signed-off-by: Jerome Glisse <jglisse@redhat.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
| * | drm/ttm: fix caching problem on non-PAT systems.Francisco Jerez2010-02-201-7/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | http://bugzilla.kernel.org/show_bug.cgi?id=15328 This fixes a serious regression on AGP/non-PAT systems, where pages were ending up in the wrong state and slowing down the whole system. [airlied: taken this from the bug as the other option is to revert the change which caused it]. Tested-by: John W. Linville (in bug). Signed-off-by: Dave Airlie <airlied@redhat.com>
| * | drm/radeon/rv740: fix backend setupAlex Deucher2010-02-202-6/+12
| | | | | | | | | | | | | | | | | | | | | | | | | | | This patch fixes occlusion queries and rendering errors on rv740 boards. Hardcoding the backend map is not an optimal solution, but a better fix is being worked on. Signed-off-by: Alex Deucher <alexdeucher@gmail.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
| * | drm/radeon/kms: fix shared ddc detectionAlex Deucher2010-02-201-3/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Just compare the i2c id since the i2c structs may be slighly different. Fixes fdo bug 26616. Signed-off-by: Alex Deucher <alexdeucher@gmail.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
| * | drm/radeon/kms/rs600: add connector quirkAlex Deucher2010-02-201-0/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | rs600 board lists DVI port as HDMI. Fixes fdo bug 26605 Signed-off-by: Alex Deucher <alexdeucher@gmail.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
| * | vgaarb: fix "target=default" passingKyle McMartin2010-02-201-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Commit 77c1ff3982c6b36961725dd19e872a1c07df7f3b fixed the userspace pointer dereference, but introduced another bug pointed out by Eugene Teo in RH bug #564264. Instead of comparing the point we were at in the string, we instead compared the beginning of the string to "default". Signed-off-by: Kyle McMartin <kyle@redhat.com> Reported-by: Eugene Teo <eteo@redhat.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
* | | Merge branch 'release' of ↵Linus Torvalds2010-02-181-0/+7
|\ \ \ | |/ / |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6 * 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6: ACPI: fix "acpi=ht" boot option ACPI, i915: blacklist Clevo M5x0N bad_lid state ACPI: fix High cpu temperature with 2.6.32 ACPI: dock: properly initialize local struct dock_station in dock_add() ACPI: remove Asus P2B-DS from acpi=ht blacklist thinkpad-acpi: wrong thermal attribute_group removed in thermal_exit() ACPI: acpi_bus_{scan,bus,add}: return -ENODEV if no device was found ACPI: Add NULL pointer check in acpi_bus_start ACPI: processor: only evaluate _PDC once per processor ACPI: processor: add kernel command line support for early _PDC eval
| | |
| | \
| | \
| | \
| | \
| | \
| *-----. \ Merge branches 'bugzilla-14886', 'bugzilla-15000', 'bugzilla-15040', ↵Len Brown2010-02-181-0/+7
| |\ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | 'bugzilla-15108', 'pdc', 'hotplug-null-ref' and 'thinkpad' into release
| | | * | | | ACPI, i915: blacklist Clevo M5x0N bad_lid stateZhang Rui2010-02-161-0/+7
| | |/ / / / | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Wrong Lid state reported. Need to blacklist this machine for LVDS detection. Signed-off-by: Zhang Rui <rui.zhang@intel.com> Signed-off-by: Len Brown <len.brown@intel.com>
* | | | | | Merge branch 'for-airlied' of ↵Dave Airlie2010-02-183-5/+6
|\ \ \ \ \ \ | | |_|_|_|/ | |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.freedesktop.org/git/nouveau/linux-2.6 into drm-linus * 'for-airlied' of git://git.freedesktop.org/git/nouveau/linux-2.6: drm/nouveau: Force TV encoder DPMS reinit after resume. drm/nouveau: use mutex for vbios lock
| * | | | | drm/nouveau: Force TV encoder DPMS reinit after resume.Francisco Jerez2010-02-161-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
| * | | | | drm/nouveau: use mutex for vbios lockBen Skeggs2010-02-162-5/+4
| | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
* | | | | | drm/radeon/kms: fix bo's fence associationJerome Glisse2010-02-183-29/+21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Previous code did associate fence to bo before the fence was emited and it also didn't lock protected access to ttm sync_obj member. Both of this flaw leads to possible race between different code path. This patch fix this by associating fence only once the fence is emitted and properly lock protect access to sync_obj member of ttm. Fix: https://bugs.freedesktop.org/show_bug.cgi?id=26438 and likely similar others bugs Signed-off-by: Jerome Glisse <jglisse@redhat.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
* | | | | | drm/radeon/kms: fix indirect buffer management V2Jerome Glisse2010-02-183-72/+45
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There is 3 different distinct states for an indirect buffer (IB) : 1- free with no fence 2- free with a fence 3- non free (fence doesn't matter) Previous code mixed case 2 & 3 in a single one leading to possible catastrophique failure. This patch rework the handling and properly separate each case. So when you get ib we set the ib as non free and fence status doesn't matter. Fence become active (ie has a meaning for the ib code) once the ib is scheduled or free. This patch also get rid of the alloc bitmap as it was overkill, we know go through IB pool list like in a ring buffer as the oldest IB is the first one the will be free. Fix : https://bugs.freedesktop.org/show_bug.cgi?id=26438 and likely other bugs. V2 remove the scheduled list, it's useless now, fix free ib scanning Signed-off-by: Jerome Glisse <jglisse@redhat.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
* | | | | | drm/edid: Fix interlaced detailed timings to be frame size, not field.Adam Jackson2010-02-181-2/+45
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | cf. https://bugzilla.redhat.com/show_bug.cgi?id=533561 Signed-off-by: Adam Jackson <ajax@redhat.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
* | | | | | drm/vmwgfx: Use fb handover mechanism instead of stealth mode.Thomas Hellstrom2010-02-182-33/+19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When the vmwgfx module is loaded on top of vesafb, it would operate in stealth mode in parallel with vesafb, evicting VRAM on dropmaster. Change that to use the vesafb handover mechanism, like other drmfb drivers. Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
* | | | | | drm/radeon/kms: use udelay for short delaysDave Airlie2010-02-181-1/+1
| |/ / / / |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | For usec delays use udelay instead of scheduling, this should allow reclocking to happen faster. This also was the cause of reported 33s delays at bootup on certain systems. fixes: freedesktop.org bug 25506 Cc: stable@kernel.org Signed-off-by: Dave Airlie <airlied@redhat.com>
* | | | | drm/radeon/kms: make sure retry count increases.Dave Airlie2010-02-151-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In testing I've never seen it go past 1 retry anyways but better safe than sorry. Reported by Droste on irc. Signed-off-by: Dave Airlie <airlied@redhat.com>
* | | | | drm/radeon/kms/atom: use get_unaligned_le32() for ctx->psMatt Turner2010-02-151-1/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Noticed on a DEC Alpha. Start up into console mode caused 15 unaligned accesses, and starting X caused another 48. Signed-off-by: Matt Turner <mattst88@gmail.com> CC: Jerome Glisse <jglisse@redhat.com> CC: Alex Deucher <alexdeucher@gmail.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
* | | | | drm/ttm: Fix a bug occuring when validating a buffer object in a range.Thomas Hellstrom2010-02-151-0/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If the buffer object was already in the requested memory type, but outside of the requested range it was never moved into the requested range. Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
* | | | | drm: Fix a bug in the range manager.Thomas Hellstrom2010-02-151-1/+2
| |/ / / |/| | | | | | | | | | | | | | | | | | | | | | | When searching for free space in a range, the function could return a node extending outside of the given range. Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
* | | | Merge branch 'for-linus' of ↵Linus Torvalds2010-02-128-142/+332
|\ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/anholt/drm-intel * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/anholt/drm-intel: drm/i915: hold ref on flip object until it completes drm/i915: Fix crash while aborting hibernation drm/i915: Correctly return -ENOMEM on allocation failure in cmdbuf ioctls. drm/i915: fix pipe source image setting in flip command drm/i915: fix flip done interrupt on Ironlake drm/i915: untangle page flip completion drm/i915: handle FBC and self-refresh better drm/i915: Increase fb alignment to 64k drm/i915: Update write_domains on active list after flush. drm/i915: Rework DPLL calculation parameters for Ironlake
| * | | | drm/i915: hold ref on flip object until it completesJesse Barnes2010-02-101-1/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This will prevent things from falling over if the user frees the flip buffer before we complete the flip, since we'll hold an internal reference. Reported-by: Kristian Høgsberg <krh@bitplanet.net> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org> Signed-off-by: Eric Anholt <eric@anholt.net>
| * | | | drm/i915: Fix crash while aborting hibernationRafael J. Wysocki2010-02-101-67/+101
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Commit cbda12d77ea590082edb6d30bd342a67ebc459e0 (drm/i915: implement new pm ops for i915) introduced the problem that if s2disk hibernation is aborted, the system will crash, because i915_pm_freeze() does nothing, while it should at least reverse some operations carried out by i915_suspend(). Fix this issue by splitting the i915 suspend into a freeze part a suspend part, where the latter is not executed before creating a hibernation image, and the i915 resume into a "low-level" resume part and a thaw part, where the former is not executed after the image has been created. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Tested-by: Alan Jenkins <alan-jenkins@tuffmail.co.uk> Signed-off-by: Eric Anholt <eric@anholt.net>
| * | | | drm/i915: Correctly return -ENOMEM on allocation failure in cmdbuf ioctls.Owain Ainsworth2010-02-102-2/+6
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Owain G. Ainsworth <oga@openbsd.org> Signed-off-by: Eric Anholt <eric@anholt.net>
| * | | | drm/i915: fix pipe source image setting in flip commandZhenyu Wang2010-02-101-2/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The MI_DISPLAY_FLIP command needs to be set the same pipe source image like in pipe source register, e.g source image size minus one. This fixes screen corrupt issue on Ironlake. Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com> Signed-off-by: Eric Anholt <eric@anholt.net>
| * | | | drm/i915: fix flip done interrupt on IronlakeZhenyu Wang2010-02-101-8/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | On Ironlake plane flip interrupt means flip done event already, the behavior is not like old chips, and perform like other usual interrupt. So only need to handle flip done event when receiving that interrupt. Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com> Signed-off-by: Eric Anholt <eric@anholt.net>
| * | | | drm/i915: untangle page flip completionJesse Barnes2010-02-101-7/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When a new page flip is requested, we need to both queue an unpin for the current framebuffer, and also increment the flip pending count on the newly submitted buffer. At flip finish time, we need to unpin the old fb and decrement the flip pending count on the new buffer. The old code was conflating the two, and led to hangs when new direct rendered apps were started, replacing the existing frame buffer. This patch splits out the buffers and prevents the hangs. Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Kristian Høgsberg <krh@bitplanet.net> Signed-off-by: Eric Anholt <eric@anholt.net>
| * | | | drm/i915: handle FBC and self-refresh betterJesse Barnes2010-02-102-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | On 945, we need to avoid entering self-refresh if the compressor is busy, or we may cause display FIFO underruns leading to ugly flicker. Fixes fdo bug #24314, kernel bug #15043. Tested-by: Alexander Lam <lambchop468@gmail.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org> Tested-by: Julien Cristau <jcristau@debian.org> (fd.o #25371) Cc: stable@kernel.org Signed-off-by: Eric Anholt <eric@anholt.net>
| * | | | drm/i915: Increase fb alignment to 64kChris Wilson2010-02-101-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | An untiled framebuffer must be aligned to 64k. This is normally handled by intel_pin_and_fence_fb_obj(), but the intelfb_create() likes to be different and do the pinning itself. However, it aligns the buffer object incorrectly for pre-i965 chipsets causing a PGTBL_ERR when it is installed onto the output. Fixes: KMS error message while initializing modesetting - render error detected: EIR: 0x10 [i915] http://bugs.freedesktop.org/show_bug.cgi?id=22936 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: stable@kernel.org Signed-off-by: Eric Anholt <eric@anholt.net>
| * | | | drm/i915: Update write_domains on active list after flush.Daniel Vetter2010-02-102-4/+30
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Before changing the status of a buffer with a pending write we will await upon a new flush for that buffer. So we can take advantage of any flushes posted whilst the buffer is active and pending processing by the GPU, by clearing its write_domain and updating its last_rendering_seqno -- thus saving a potential flush in deep queues and improves flushing behaviour upon eviction for both GTT space and fences. In order to reduce the time spent searching the active list for matching write_domains, we move those to a separate list whose elements are the buffers belong to the active/flushing list with pending writes. Orignal patch by Chris Wilson <chris@chris-wilson.co.uk>, forward-ported by me. In addition to better performance, this also fixes a real bug. Before this changes, i915_gem_evict_everything didn't work as advertised. When the gpu was actually busy and processing request, the flush and subsequent wait would not move active and dirty buffers to the inactive list, but just to the flushing list. Which triggered the BUG_ON at the end of this function. With the more tight dirty buffer tracking, all currently busy and dirty buffers get moved to the inactive list by one i915_gem_flush operation. I've left the BUG_ON I've used to prove this in there. References: Bug 25911 - 2.10.0 causes kernel oops and system hangs http://bugs.freedesktop.org/show_bug.cgi?id=25911 Bug 26101 - [i915] xf86-video-intel 2.10.0 (and git) triggers kernel oops within seconds after login http://bugs.freedesktop.org/show_bug.cgi?id=26101 Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Tested-by: Adam Lantos <hege@playma.org> Cc: stable@kernel.org Signed-off-by: Eric Anholt <eric@anholt.net>
| * | | | drm/i915: Rework DPLL calculation parameters for IronlakeZhenyu Wang2010-02-101-50/+167
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Got Ironlake DPLL parameter table, which reflects the hardware optimized values. So this one trys to list DPLL parameters for different output types, should potential fix clock issue seen on new Arrandale CPUs. This fixes DPLL setting failure on one 1920x1080 dual channel LVDS for Ironlake. Test has also been made on LVDS panels with smaller size and CRT/HDMI/DP ports for different monitors on their all supported modes. Update: - Change name of double LVDS to dual LVDS. - Fix SSC 120M reference clock to use the right range. Cc: CSJ <changsijay@gmail.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com> Signed-off-by: Eric Anholt <eric@anholt.net>
* | | | | vgaarb: fix incorrect dereference of userspace pointer.Andy Getzendanner2010-02-111-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch corrects a userspace pointer dereference in the VGA arbiter in 2.6.32.1. copy_from_user() is used at line 822 to copy the contents of buf into kbuf, but a call to strncmp() on line 964 uses buf rather than kbuf. This problem led to a GPF in strncmp() when X was started on my x86_32 systems. X triggered the behavior with a write of "target PCI:0000:01:00.0" to /dev/vga_arbiter. The patch has been tested against 2.6.32.1 and observed to correct the GPF observed when starting X or manually writing the string "target PCI:0000:01:00.0" to /dev/vga_arbiter. Signed-off-by: Andy Getzendanner <james.getzendanner@students.olin.edu> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Dave Airlie <airlied@redhat.com>
* | | | | Merge branch 'drm-radeon-linus' of ../drm-nextDave Airlie2010-02-119-41/+89
|\ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * 'drm-radeon-linus' of ../drm-next: drm/radeon/kms: retry auxch on 0x20 timeout value. drm/radeon: Skip dma copy test in benchmark if card doesn't have dma engine. drm/radeon/kms: fix screen clearing before fbcon. drm/radeon/kms: add quirk for VGA without DDC on rv730 XFX card. drm/radeon/kms: don't crash if no DDC bus on VGA/DVI connector. drm/radeon/kms: change Kconfig text to reflect the new option. drm/radeon/kms: suspend and resume audio stuff
| * | | | | drm/radeon/kms: retry auxch on 0x20 timeout value.Dave Airlie2010-02-111-3/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ATOM appears to return 0x20 which seems to mean some sort of timeout. retry the transaction up to 10 times before failing, this makes DP->VGA convertor we bought work at least a bit more predictably. Signed-off-by: Dave Airlie <airlied@redhat.com>
| * | | | | drm/radeon: Skip dma copy test in benchmark if card doesn't have dma engine.Pauli Nieminen2010-02-111-22/+33
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | radeon_copy_dma is only available for r200 or newer cards. Call to radeon_copy_dma would result to NULL pointer dereference if benchmarking asic without dma engine. Signed-off-by: Pauli Nieminen <suokkos@gmail.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
| * | | | | drm/radeon/kms: fix screen clearing before fbcon.Dave Airlie2010-02-111-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This memset_io was added to debug something way back and got left behind, memset the fb to black so the borders don't be all white. Signed-off-by: Dave Airlie <airlied@redhat.com>
| * | | | | drm/radeon/kms: add quirk for VGA without DDC on rv730 XFX card.Dave Airlie2010-02-091-0/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Reported on irc by nirbheek. Signed-off-by: Dave Airlie <airlied@redhat.com>
generated by cgit v1.1 at 2024-12-26 23:12:38 +0000