aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/nouveau/nouveau_mem.c (follow)
AgeCommit message (Collapse)AuthorFilesLines
2011-09-20drm/nouveau/pm: Document and expose CL and WR for 0x1002CxRoy Spliet1-13/+15
Signed-off-by: Roy Spliet <r.spliet@student.tudelft.nl>
2011-09-20drm/nouveau/pm: add initial NV3x/NVCx memtiming support, improve other cardsRoy Spliet1-130/+148
NV30: Create framework for memtm NV50: Improve reg creation, NV50: Use P.version instead of card codename/stepping, NVC0: Initial memtiming code for Fermi, Renamed regs for consistency, Overall redesign to improve readability, Avoid kfree on null-pointer Signed-off-by: Roy Spliet <r.spliet@student.tudelft.nl>
2011-09-20drm/nouveau: make general drm modesetting init commonBen Skeggs1-2/+0
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-07-13DRM: remove drm_pci_device_is_pcieJon Mason1-1/+1
drm_pci_device_is_pcie duplicates the funcationality of pci_is_pcie. Convert callers of the former to the latter. This has the side benefit of removing an unnecessary search in the PCI configuration space due to using a saved PCIe capability offset. [airlied: update for new callsite] Signed-off-by: Jon Mason <jdmason@kudzu.us> Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-06-27drm/nouveau: Calculate reserved VRAM for PRAMIN value before use.Younes Manton1-28/+0
'drm/nouveau: rework vram init/fini ordering a little' changed the order of instmem.init() and nouveau_mem_vram_init() which resulted in using ramin_rsvd_vram before it was calculated and failing to init any accel on pre-NV50 cards. Since it's only used on <NV50 just calculate it where it's needed and leave it as default 0 for NV50. Signed-off-by: Younes Manton <younes.m@gmail.com> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-06-27drm/nouveau: fix nouveau_mem object leakMarcin Slusarz1-1/+1
It's a regression from "drm/nouveau: create temp vmas for both src and dst of bo moves". Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-06-23drm/nouveau: rework vram init/fini ordering a littleBen Skeggs1-27/+3
Commit "drm/nouveau: add some debug output if nouveau_mm busy at destroy time" revealed an issue where vram mm takedown would actually fail due to there still being nodes present, causing nouveau to leak a small amount of memory on module unload. This splits TTM/nouveau_mm a bit more cleanly and ensures nouveau_mm fini isn't done until all gpuobjs are also destroyed. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-06-23drm/nouveau: remove 'chan' argument from nouveau_bo_newBen Skeggs1-1/+1
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-06-23drm/nouveau: create temp vmas for both src and dst of bo movesBen Skeggs1-35/+18
Greatly simplifies a number of things, particularly once per-client GPU address spaces are involved. May add this back later once I know what things'll look like. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-06-23drm/nouveau: store bo's page size in nouveau_boBen Skeggs1-4/+2
Was previously assuming a page size of 4KiB unless a VMA was present to override it. Eventually, a buffer won't necessarily have a VMA at all at some stages of its life, so we need to store this info elsewhere. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-06-07drm/nv40: fall back to paged dma object for the momentBen Skeggs1-1/+1
PCI(E)GART isn't quite stable it seems, fall back to old method until I get the time to sort it out properly. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-06-07drm/nouveau: fix leak of gart mm nodeBen Skeggs1-0/+2
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-05-16drm/nouveau: Associate memtimings with performance levels on cards <= nv98Martin Peres1-1/+2
v2 (Ben Skeggs): fix ramcfg strap, and remove bogus handling of perf 0x40 Signed-off-by: Martin Peres <martin.peres@ensi-bourges.fr> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-05-16drm/nouveau: Fix a crash at card takedown for NV40 and older cardsJimmy Rentz1-2/+0
NV40 and older cards (pre NV50) reserve a vram bo for the vga memory at card init. This bo is then freed at card shutdown. The problem is that the ttm bo vram manager was already freed. So a crash occurs when the vga bo is freed. The fix is to free the vga bo prior to freeing the ttm bo vram manager. There might be other solutions but this seemed the simplest to me. Signed-off-by: Jimmy Rentz <jb17bsome@gmail.com> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-05-16drm/nouveau: move set_tile_region to nouveau_exec_engineBen Skeggs1-3/+5
In the very least VPE (PMPEG and friends) also has this style of tile region regs, lets make them just work if/when they get added. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-05-16drm/nouveau: improve memtiming table parsingRoy Spliet1-14/+31
Improves the parsing of the memory timing table on NV50-NV98revA1 chipsets. Added stepping to drm_nouveau_private to make sure newer NV98 (105M) is zero rather than incorrect. Signed-off-by: Roy Spliet <r.spliet@student.tudelft.nl> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-05-16drm/nouveau: Fix missing whitespace checkpatch.pl errors.Emil Velikov1-2/+2
This patch fixes messages such as ERROR: space required after that ',' ERROR: spaces required around that '=' Signed-off-by: Emil Velikov <emil.l.velikov@gmail.com> Signed-off-by: Francisco Jerez <currojerez@riseup.net>
2011-05-16drm/nouveau: Fix indentation-related checkpatch.pl error messages.Emil Velikov1-7/+7
Fix 'ERROR: code indent should use tabs where possible' Fix 'ERROR: space required before the open parenthesis (' Signed-off-by: Emil Velikov <emil.l.velikov@gmail.com> Signed-off-by: Francisco Jerez <currojerez@riseup.net>
2011-04-20drm/nouveau: fix nv30 pcie boardsBen Skeggs1-1/+1
Wasn't aware they even existed, apparently they do! They're actually AGP chips with a bridge as far as I can tell, which puts them in the same boat as nv40/nv45. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-04-05drm/nouveau: correct memtiming table parsing for nv4xRoy Spliet1-27/+49
In line with envytools, verified on 4 or 5 BIOS'es. Signed-off-by: Ben Skeggs <bskeggs@redhat.com> Signed-off-by: Roy Spliet <r.spliet@student.tudelft.nl>
2011-03-16Merge commit '5359533801e3dd3abca5b7d3d985b0b33fd9fe8b' into drm-core-nextDave Airlie1-2/+4
This commit changed an internal radeon structure, that meant a new driver in -next had to be fixed up, merge in the commit and fix up the driver. Also fixes a trivial nouveau merge. Conflicts: drivers/gpu/drm/nouveau/nouveau_mem.c
2011-03-14drm/nv40: attempt to reserve just enough vram for all 32 channelsBen Skeggs1-8/+26
This also makes the fact we're giving 512MiB of GART space to all PCIE boards explicit, although the vast majority (if not all) of them will now have a ramin_rsvd_vram larger than 2MiB anyway. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-03-08drm/nouveau: fix regression causing ttm to not be able to evict vramBen Skeggs1-2/+4
TTM assumes an error condition from man->func->get_node() means that something went horribly wrong, and causes it to bail. The driver is supposed to return 0, and leave mm_node == NULL to signal that it couldn't allocate any memory. Signed-off-by: Ben Skeggs <bskeggs@redhat.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-02-25drm/nv50: support for compressionBen Skeggs1-1/+1
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-02-25drm/nv50-nvc0: delay GART binding until move_notify timeBen Skeggs1-0/+81
The immediate benefit of doing this is that on NV50 and up, the GPU virtual address of any buffer is now constant, regardless of what memtype they're placed in. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-02-25drm/nouveau: rename nouveau_vram to nouveau_memBen Skeggs1-3/+3
This structure will also be used for GART in the near future. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-02-25drm/nv50-nvc0: unmap buffers from the vm when they're evictedBen Skeggs1-0/+6
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-02-25drm/nouveau: remove no_vm/mappable flags from nouveau_boBen Skeggs1-12/+16
'mappable' isn't really used at all, nor is it necessary anymore as the bo code is capable of moving buffers to mappable vram as required. 'no_vm' isn't necessary anymore either, any places that don't want to be mapped into a GPU address space should allocate the VRAM directly instead. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-02-25drm/nv40: support for 39-bit dma addresses on native PCIE chipsetsBen Skeggs1-5/+11
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-02-23Revert "ttm: Include the 'struct dev' when using the DMA API."Dave Airlie1-1/+0
This reverts commit 5a893fc28f0393adb7c885a871b8c59e623fd528. This causes a use after free in the ttm free alloc pages path, when it tries to get the be after the be has been destroyed. Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-02-23Merge branch 'stable/ttm.pci-api.v5' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen into drm-nextDave Airlie1-0/+1
* 'stable/ttm.pci-api.v5' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen: ttm: Include the 'struct dev' when using the DMA API. nouveau/ttm/PCIe: Use dma_addr if TTM has set it. radeon/ttm/PCIe: Use dma_addr if TTM has set it. ttm: Expand (*populate) to support an array of DMA addresses. ttm: Utilize the DMA API for pages that have TTM_PAGE_FLAG_DMA32 set. ttm: Introduce a placeholder for DMA (bus) addresses.
2011-02-22ttm: Include the 'struct dev' when using the DMA API.Konrad Rzeszutek Wilk1-0/+1
This makes the accounting when using 'debug_dma_dump_mappings()' and CONFIG_DMA_API_DEBUG=y be assigned to the correct device instead of 'fallback'. No functional change - just cosmetic. Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2011-02-07drm: rework PCI/platform driver interface.Dave Airlie1-1/+1
This abstracts the pci/platform interface out a step further, we can go further but this is far enough for now to allow USB to be plugged in. The drivers now just call the init code directly for their device type. Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-01-17drm/nouveau: greatly simplify mm, killing some bugs in the processBen Skeggs1-16/+10
Reviewed-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-21drm/nvc0: initial vm implementation, use for bar1/bar3 managementBen Skeggs1-3/+0
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-21drm/nvc0: import initial vm backendBen Skeggs1-0/+4
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-08drm/nouveau: kick vram functions out into an "engine"Ben Skeggs1-21/+26
NVC0 will be able to share some of nv50's paths this way. This also makes it the card-specific vram code responsible for deciding if a given set of tile_flags is valid, rather than duplicating the allowed types in nv50_vram.c and nouveau_gem.c Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-08drm/nv50: enable non-contig vram allocations where requestedBen Skeggs1-1/+5
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-08drm/nv50: enable 4KiB pages for small vram allocationsBen Skeggs1-1/+2
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-08drm/nv50: implement global channel address space on new VM codeBen Skeggs1-94/+0
As of this commit, it's guaranteed that if an object is in VRAM that its GPU virtual address will be constant. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-08drm/nv50: import new vm codeBen Skeggs1-2/+3
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-08drm/nv50: implement custom vram mmBen Skeggs1-82/+119
This is required on nv50 as we need to be able to have more precise control over physical VRAM allocations to avoid buffer corruption when using buffers of mixed memory types. This removes some nasty overallocation/alignment that we were previously using to "control" this problem. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03drm/nouveau: Rework tile region handling.Francisco Jerez1-45/+66
The point is to share more code between the PFB/PGRAPH tile region hooks, and give the hardware specific functions a chance to allocate per-region resources. Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03drm/nouveau: fix annoying nouveau_fence type issueMarcin Slusarz1-2/+2
nouveau_fence_* functions are not type safe, which could lead to bugs. Additionally every use of nouveau_fence_unref had to cast struct nouveau_fence to void **. Fix it by renaming old functions and creating static inline functions with new prototypes. We still need old functions, because we pass function pointers to ttm. As we are wrapping functions, drop unused "void *arg" parameter where possible. Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com> Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-11-18drm/nouveau/pm: improve memtiming mappingsRoy Spliet1-12/+19
Improvements: - Fix bug in switch statement - Add parts of 0x10022c, 0x10023c - Clean up 0x100234 - Comment out assumption in 0x100228 until verified Signed-off-by: Roy Spliet <r.spliet@student.tudelft.nl> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-11-18drm/nv50: implement possible workaround for NV86 PGRAPH TLB flush hangBen Skeggs1-8/+6
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-11-18drm/nouveau: Some random cleanups.Francisco Jerez1-3/+3
Remove some unused/duplicated definitions and make sparse happy again. Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-10-05drm/nouveau: fix thinkos in mem timing table recordlen checkRoy Spliet1-5/+7
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-10-05drm/nouveau: Import initial memory timing workRoy Spliet1-0/+144
This isn't correct everywhere yet, but since we don't use the data yet it's perfectly safe to push in, and the information we gain from logs will help to fix the remaining issues. v2 (Ben Skeggs <bskeggs@redhat.com>): - fixed up formatting - free parsed timing info on takedown - switched timing table printout to debug loglevel Signed-off-by: Roy Spliet <r.spliet@student.tudelft.nl> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-09-24drm/nouveau: Simplify tile region handling.Francisco Jerez1-17/+13
Instead of emptying the caches to avoid a race with the PFIFO puller, go straight ahead and try to recover from it when it happens. Also, kill pfifo->cache_flush and tile->lock, we don't need them anymore. Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.