search for: unpinning

A kernel test bot reported a problem with the locktorture testcase that was triggered by the GEM VRAM helpers. ... [ 10.004734] RIP: 0010:ttm_bo_validate+0x41/0x141 [ttm] ... [ 10.015669] ? kvm_sched_clock_read+0x5/0xd [ 10.016157] ? get_lock_stats+0x11/0x3f [ 10.016607] drm_gem_vram_pin+0x77/0xa2 [drm_vram_helper] [ 10.017229]

A kernel test bot reported a problem with the locktorture testcase that was triggered by the GEM VRAM helpers. ... [ 10.004734] RIP: 0010:ttm_bo_validate+0x41/0x141 [ttm] ... [ 10.015669] ? kvm_sched_clock_read+0x5/0xd [ 10.016157] ? get_lock_stats+0x11/0x3f [ 10.016607] drm_gem_vram_pin+0x77/0xa2 [drm_vram_helper] [ 10.017229]

Hi, > It turns out that the bochs and vbox drivers automatically reserved and > unreserved the BO from within their pin and unpin functions. The other > drivers; ast, hibmc and mgag200; performed reservation explicitly. With the > GEM VRAM conversion, automatic BO reservation within pin and unpin functions > accidentally got lost. So for bochs and vbox, ttm_bo_validate() worked on

The new interfaces drm_gem_vram_{pin/unpin}_reserved() are variants of the GEM VRAM pin/unpin functions that do not reserve the BO during validation. The mgag200 driver requires this behavior for its cursor handling. The patch also converts the driver to use the new interfaces. Signed-off-by: Thomas Zimmermann <tzimmermann at suse.de> --- drivers/gpu/drm/drm_gem_vram_helper.c | 75

Hi, Patch below is needed to make my system work stable in PAE mode. Havn''t seen problems without PAE, not sure whenever thats just pure luck or whenever there is a bug in my PAE xenlinux kernel. To me it looks like a generic bug though. I''ve actually trapped into problems with unpin only: A process exits, somewhere in exit_mm() the page tables are unpinned, shortly thereafter

On Mon, May 20, 2019 at 06:19:00PM +0200, Daniel Vetter wrote: > On Thu, May 16, 2019 at 06:27:45PM +0200, Thomas Zimmermann wrote: > > The new interfaces drm_gem_vram_{pin/unpin}_reserved() are variants of the > > GEM VRAM pin/unpin functions that do not reserve the BO during validation. > > The mgag200 driver requires this behavior for its cursor handling. The > >

Am 20.05.19 um 18:26 schrieb Daniel Vetter: > [CAUTION: External Email] > > On Mon, May 20, 2019 at 06:19:00PM +0200, Daniel Vetter wrote: >> On Thu, May 16, 2019 at 06:27:45PM +0200, Thomas Zimmermann wrote: >>> The new interfaces drm_gem_vram_{pin/unpin}_reserved() are variants of the >>> GEM VRAM pin/unpin functions that do not reserve the BO during validation.

On Thu, May 16, 2019 at 06:27:45PM +0200, Thomas Zimmermann wrote: > The new interfaces drm_gem_vram_{pin/unpin}_reserved() are variants of the > GEM VRAM pin/unpin functions that do not reserve the BO during validation. > The mgag200 driver requires this behavior for its cursor handling. The > patch also converts the driver to use the new interfaces. > > Signed-off-by: Thomas

On Thu, May 16, 2019 at 06:27:45PM +0200, Thomas Zimmermann wrote: > The new interfaces drm_gem_vram_{pin/unpin}_reserved() are variants of the > GEM VRAM pin/unpin functions that do not reserve the BO during validation. > The mgag200 driver requires this behavior for its cursor handling. The > patch also converts the driver to use the new interfaces. > > Signed-off-by: Thomas

...void the need to implement > an LRU algorithm or another eviction strategy. Userspace with a WS > larger than the absolute VRAM would see degraded performance but > otherwise still work. You still need a list of unpinned bo, and the lru scan algorithm is just a few lines of code more than unpinning everything. Plus it'd be a neat example of the drm_mm scan logic. Given that some folks might think that not having lru evict si a problem and get them to type their own, I'd just add it. But up to you. Plus with ttm you get it no matter what. -Daniel > Best regards > Thomas > &g...

...void the need to implement > an LRU algorithm or another eviction strategy. Userspace with a WS > larger than the absolute VRAM would see degraded performance but > otherwise still work. You still need a list of unpinned bo, and the lru scan algorithm is just a few lines of code more than unpinning everything. Plus it'd be a neat example of the drm_mm scan logic. Given that some folks might think that not having lru evict si a problem and get them to type their own, I'd just add it. But up to you. Plus with ttm you get it no matter what. -Daniel > Best regards > Thomas > &g...

...U algorithm or another eviction strategy. Userspace with a WS > >> larger than the absolute VRAM would see degraded performance but > >> otherwise still work. > > You still need a list of unpinned bo, and the lru scan algorithm is > > just a few lines of code more than unpinning everything. Plus it'd be > > a neat example of the drm_mm scan logic. Given that some folks might > > think that not having lru evict si a problem and get them to type > > their own, I'd just add it. But up to you. Plus with ttm you get it no > > matter what. > &g...

-stable review patch. If anyone has any objections, please let us know. ------------------ From: Jeremy Fitzhardinge <jeremy@goop.org> patch 9f79991d4186089e228274196413572cc000143b in mainline. When a pagetable is no longer in use, it must be unpinned so that its pages can be freed. However, this is only possible if there are no stray uses of the pagetable. The code currently deals

-stable review patch. If anyone has any objections, please let us know. ------------------ From: Jeremy Fitzhardinge <jeremy@goop.org> patch 9f79991d4186089e228274196413572cc000143b in mainline. When a pagetable is no longer in use, it must be unpinned so that its pages can be freed. However, this is only possible if there are no stray uses of the pagetable. The code currently deals

The patched attached enables x86_64 xenlinux with "late pin, early unpin", which is already implemented for x86_32. Since we now only pin the root rather than any of the other levels, the overall performance became better especially with workloads that require heavy memory management operations. On 8-way x86_64 xenlinux (dom0) the kernel build was improved by about 10% (using make

This will otherwise cause a lockdep splat if reservations were a real lock type, so warn when nouveau forgets to unpin a buffer, and fix up the ones I've hit. Signed-off-by: Maarten Lankhorst <maarten.lankhorst at canonical.com> --- diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index cc79c79..acc6b08 100644 ---

This will otherwise cause a lockdep splat, so warn when nouveau forgets to unpin a buffer, and fix up the ones I've hit. Signed-off-by: Maarten Lankhorst <maarten.lankhorst at canonical.com> --- drivers/gpu/drm/nouveau/nouveau_abi16.c | 1 + drivers/gpu/drm/nouveau/nouveau_fbcon.c | 1 + drivers/gpu/drm/nouveau/nouveau_gem.c | 3 ++- drivers/gpu/drm/nouveau/nouveau_prime.c |

When operating on an unpinned pagetable (ie, one under construction or destruction), it isn''t necessary to use a hypercall to update a pud/pmd entry. Jan Beulich observed that a similar optimisation avoided many thousands of hypercalls while doing a kernel build. One tricky part is that early in the kernel boot there''s no page structure, so we can''t check to see if the

virtio-gpu objects never move around, so effectively they are pinned all the time. This makes the the implementation pretty easy ;) Signed-off-by: Gerd Hoffmann <kraxel at redhat.com> --- drivers/gpu/drm/virtio/virtgpu_prime.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_prime.c b/drivers/gpu/drm/virtio/virtgpu_prime.c index

Hi, > I think would be good to have a lockdep_assert_held here for the ww_mutex. > > Also general thing: _reserved is kinda ttm lingo, for dma-buf reservations > we call the structure tracking the fences+lock the "reservation", but the > naming scheme used is _lock/_unlock. > > I think would be good to be consistent with that, and use _locked here. > Especially