summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2017-12-20drm/nouveau: fix obvious memory leakBen Skeggs
fdo#104340. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-12-19drm/nouveau: use alternate memory type for system-memory buffers with kind != 0Ben Skeggs
Fixes bug on Tegra where we'd strip kind information from system memory (ie. all) buffers, resulting in misrendering. Behaviour on dGPU should be unchanged. Reported-by: Thierry Reding <treding@nvidia.com> Fixes: d7722134b8 ("drm/nouveau: switch over to new memory and vmm interfaces") Signed-off-by: Ben Skeggs <bskeggs@redhat.com> Tested-by: Thierry Reding <treding@nvidia.com>
2017-12-19drm/nouveau: avoid GPU page sizes > PAGE_SIZE for buffer objects in host memoryBen Skeggs
While the Tegra (GK20A, GM20B, GP10B) MMUs support large pages in host memory, we're currently lacking IOMMU support for merging system pages into large enough chunks to be mapped as such by the GPU. The core VMM code actually supports automatically determining the best page size to map with, which is intended for these situations, but for various complicated reasons the DRM is currently forcing the page size selection on a per-BO basis. This should fix breakage reported on Tegra GPUs in the meantime, until one or both of the above issues are resolved properly. Reported-by: Mikko Perttunen <cyndis@kapsi.fi> Fixes: 7dc6a446da7c ("drm/nouveau: improve selection of GPU page size") Signed-off-by: Ben Skeggs <bskeggs@redhat.com> Tested-by: Thierry Reding <treding@nvidia.com>
2017-12-19drm/nouveau/mmu/gp10b: use correct implementationBen Skeggs
Reported-by: Mikko Perttunen <cyndis@kapsi.fi> Fixes: 6359c98224 ("drm/nouveau/mmu/gp10b: fork from gf100") Signed-off-by: Ben Skeggs <bskeggs@redhat.com> Tested-by: Thierry Reding <treding@nvidia.com>
2017-12-19drm/nouveau/pci: do a msi rearm on initKarol Herbst
On my GP107 when I load nouveau after unloading it, for some reason the GPU stopped sending or the CPU stopped receiving interrupts if MSI was enabled. Doing a rearm once before getting any interrupts fixes this. Signed-off-by: Karol Herbst <kherbst@redhat.com> Reviewed-by: Thierry Reding <treding@nvidia.com> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-12-19drm/nouveau/imem/nv50: fix refcount_t warningBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-12-19drm/nouveau/bios/dp: support DP Info Table 2.0Ben Skeggs
Reported-by: Hans de Goede <hdegoede@redhat.com> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-12-19drm/nouveau/fbcon: fix NULL pointer access in nouveau_fbcon_destroyKarol Herbst
When the fbcon object is initialized, but nouveau_fbcon_create is not called, we run into a NULL pointer access within nouveau_fbcon_create when unloading nouveau. The call to drm_fb_helper_funcs.fb_probe is deferred until there is a display for real since 4.14, that's why fbcon->helper.fb is still not set. Signed-off-by: Karol Herbst <kherbst@redhat.com> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-03drm/nouveau/bios/timing: mark expected switch fall-throughsGustavo A. R. Silva
In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Addresses-Coverity-ID: 1260018 Addresses-Coverity-ID: 1260019 Addresses-Coverity-ID: 1260022 Signed-off-by: Gustavo A. R. Silva <garsilva@embeddedor.com> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-03drm/nouveau/devinit/nv04: mark expected switch fall-throughsGustavo A. R. Silva
In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Addresses-Coverity-ID: 143119 Addresses-Coverity-ID: 143120 Addresses-Coverity-ID: 143121 Addresses-Coverity-ID: 143122 Addresses-Coverity-ID: 143123 Addresses-Coverity-ID: 143124 Signed-off-by: Gustavo A. R. Silva <garsilva@embeddedor.com> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-03drm/nouveau/bios: make const arrays hwsq_signature and edid_sig staticColin Ian King
Don't populate arrays hwsq_signature and edid_sig on the stack but instead make them static. Makes the object code smaller by over 190 bytes: Before: text data bss dec hex filename 35676 3312 64 39052 988c nouveau_bios.o After: text data bss dec hex filename 35319 3472 64 38855 97c7 nouveau_bios.o (gcc version 7.2.0 x86_64) Signed-off-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-03drm/nouveau/core/memory: fix missing mutex unlockBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-03drm/nouveau/mmu: swap out round for ALIGNBen Skeggs
Rounding value is guaranteed to be power-of-two, so this is better anyway. Fixes build on 32-bit. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/gr/gf100-: don't prevent module load if firmware missingBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/mmu: remove old vmm frontendBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau: improve selection of GPU page sizeBen Skeggs
Enables the use of Pascal's 2MiB pages for larger buffers. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau: switch over to new memory and vmm interfacesBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau: remove unused nouveau_fence_work()Ben Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau: queue delayed unmapping of VMAs on client workqueueBen Skeggs
VMAs are about to not take references on the VMM they belong to, which means more care is required when handling delayed unmapping. Queuing it on the client workqueue ensures all pending VMA unmaps will have completed before the VMM is destroyed. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau: implement per-client delayed workqueue with fence supportBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau: determine memory class for each clientBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau: pass handle of vmm object to channel allocation ioctlsBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau: switch to vmm limitBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau: allocate vmm object for every clientBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau: replace use of cpu_coherent with memory typesBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau: use nvif_mmu_type to determine BAR1 cachingBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau: fetch memory type indices that we care about for ttmBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau: consolidate handling of dma maskBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau: check kind validity against mmu objectBen Skeggs
This is already handled in the top-level gem_new() ioctl in another manner, but this will be removed in a future commit. Ideally we'd not need to check up-front at all, and let the VMM code handle error checking, but there are paths in the current BO management code where this isn't possible due to map() not always being called during BO creation, and map() calls not being allowed to fail during buffer migration. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau: allocate mmu object for every clientBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau: remove trivial cases of nvxx_device() usageBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/mmu: define user interfaces to mmu vmm opertaionsBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/mmu: define user interfaces to mmu memory allocationBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/mmu: define user interfaces to mmuBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/mmu/gf100-: type-based vram allocation and bar mappingBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/mmu/nv50,g84: type-based vram allocation and bar mappingBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/mmu/nv04-nv4x: type-based vram allocation and bar mappingBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/mmu: add base for type-based memory allocationBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/mmu: build up information on available memory typesBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau: remove explicit unmapsBen Skeggs
If the VMA is being deleted, we don't need to explicity unmap first anymore. The MMU code will automatically merge the operations into a single page tree walk. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/gr/gf100-: replace hardcoded instance/vmm setup in grctx generationBen Skeggs
Could be useful for if/when a future GPU removes support for the GF100 PT layout. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/gr/gf100-: use new interfaces for vmm operationsBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/fifo/gf100-: use new interfaces for vmm operationsBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/secboot/gm200: use new interfaces for vmm operationsBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/imem/nv50-: use new interfaces for vmm operationsBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/fb/ram: use new interfaces for vmm operationsBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/fifo: initialise vmm with new interfacesBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/secboot/gm200: initialise vmm with new interfacesBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/bar/gf100: initialise vmm with new interfacesBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2017-11-02drm/nouveau/bar/nv50: initialise vmm with new interfacesBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
generated by cgit (git 2.34.1) at 2025-09-11 07:44:54 +0000