mirrors/linux
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-05-05 01:32:47 -04:00
Code Issues Packages Projects Releases Wiki Activity
591,018 Commits 1 Branch 929 Tags
ca79e49d6add77b69be3362ddfe5b068f62bf1de
Commit Graph

591018 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ben Skeggs
ca79e49d6a drm/nouveau/gr/gf100-: fix race condition in fecs/gpccs ucode 
This is a simplied version of the fix by Roy in fdo#93629.  While this
doesn't appear to fix the issues for the users in that report, it's a
real issue that deserves to be resolved.

Reported-by: Roy Spliet <rspliet@eclipso.eu>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
f9e2029443 drm/nouveau/core: recognise GM108 chipsets 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
00f50c662c drm/nouveau/gr/gm107-: fix touching non-existent ppcs in attrib cb setup 
Also removes an XXX; according to nvgpu headers the field is called
NV_PGRAPH_GPCS_SWDX_TC_BETA_CB_SIZE_DIV3, so, apparently not some
magic we need to figure out :)

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
a00ecf2212 drm/nouveau/gr/gk104-: share implementation of ppc exception init 
This was really inconsistent, some implementations could touch PPCs
that didn't exist, others neglected to touch ones that did.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
87ac331e3f drm/nouveau/gr/gk104-: move rop_active_fbps init to nonctx 
Matches newer RM.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
4d3df19a8e drm/nouveau/bios/pll: check BIT table version before trying to parse it 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
2781c928b1 drm/nouveau/bios/pll: prevent oops when limits table can't be parsed 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Karol Herbst
d07a97e939 drm/nouveau/volt/gk104: round up in gk104_volt_set 
We always want a equal or higher voltage than the requested ones, otherwise
nouveau undervolts.

Signed-off-by: Karol Herbst <nouveau@karolherbst.de>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
e976278ad2 drm/nouveau/fb/gm200: setup mmu debug buffer registers at init() 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
834b21f5e9 drm/nouveau/fb/gk20a,gm20b: setup mmu debug buffer registers at init() 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
99c5917253 drm/nouveau/fb/gf100-: allocate mmu debug buffers 
Later chipsets require setting this up both in FB and GR, so let's just
move the allocation to FB.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
917d95a86e drm/nouveau/fb: allow chipset-specific actions for oneinit() 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
06d4f26cc3 drm/nouveau/gr/gm200-: fix bad hardcoding of a max-tpcs-per-gpc value 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
734a0aa669 drm/nouveau/gr/gm200-: rop count == ltc count 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
c83e7d6836 drm/nouveau/gr/gm200: modify the mask when copying mmu settings from fb 
Appears to more closely match what RM does.

For GM20B, now also copying bit 12 from NV_PFB_MMU_CTRL as upcoming
changes will require it.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
54aa38a8ad drm/nouveau/gr/gm200: move some code into init_gpc_mmu() hook 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
560e6da267 drm/nouveau/gr/gm200: make generate_main() static 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
64cb5a31f4 drm/nouveau/gr/gf100-: abstract fetching rop count 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
5ec3def735 drm/nouveau/gr/gf100-: rename magic_not_rop_nr to screen_tile_row_offset 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
933ad44594 drm/nouveau/gr/gf100-: remove hardcoded idle_timeout values 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
0cdc3fdfb7 drm/nouveau/fifo/gm107-: remove engines from mmu engine mapping array 
These are specified by PTOP on Maxwell GPUs.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
289e082706 drm/nouveau/fifo/gk104-: identify mmu engine ids for host faults 
It appears these don't map to PBDMAs (at least on Kepler, it may or may
be valid for Fermi - this hasn't been checked), but to runlists.

This drops the NVKM_ENGINE_FIFO data from the entries too, as resetting
all of PFIFO is *not* the way to handle such faults.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
e50d0237fc drm/nouveau/fifo/gk104-: implement support for PTOP fault info 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
91419acf78 drm/nouveau/fifo/gk104-: abstract mmu fault data structures 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
98ac3f061a drm/nouveau/fifo/gk104-: subclass func 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
e93e198d46 drm/nouveau/fifo/gk104-: use device info from top subdev 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
56d06fa29e drm/nouveau/core: remove pmc_enable argument from subdev ctor 
These are now specified directly in the MC subdev.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
d85e2a8dd8 drm/nouveau/mc/nv04: define reset masks + intr cleanup 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
667e99ab23 drm/nouveau/mc/nv11: define reset masks + intr cleanup 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
79360b7d5f drm/nouveau/mc/nv17: define reset masks + intr cleanup 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
9199fbdbf8 drm/nouveau/mc/nv50: define reset masks + intr cleanup 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
7354902001 drm/nouveau/mc/g84: define reset masks + intr cleanup 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
e56f90fe17 drm/nouveau/mc/g98: define reset masks + intr cleanup 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
88c0de2cdb drm/nouveau/mc/gt215: define reset masks + intr cleanup 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
a6bb38e902 drm/nouveau/mc/gf100: define reset masks + intr cleanup 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
33537d6fdc drm/nouveau/mc/gk104: define reset masks + intr cleanup 
Engine fields have been removed, as they're specified by PTOP.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
921be10d85 drm/nouveau/mc: implement support for PTOP interrupt routing 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
583f8e4ea2 drm/nouveau/mc: implement support for PTOP reset info 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
70b01f07db drm/nouveau/mc: allow for local definition of reset bits 
With the addition of PTOP-specified reset bits, it makes more sense to
move the definitions here rather than in individual subdev
implementations.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
6defde5ab3 drm/nouveau/mc: add helper function to handle device reset 
This will be later extended to handle PTOP-specified reset masks as well
as the hardcoded ones.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
87f313e6e6 drm/nouveau/mc: rename struct nvkm_mc_intr to nvkm_mc_map 
This will also be used to define NV_PMC_ENABLE <-> subdev mappings in an
upcoming commit.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
fb3e9c61ca drm/nouveau/top/gk104: initial implementation 
Ported from the code currently in engine/fifo/gk104.c.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
5f76f294d1 drm/nouveau/top: initial implementation 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Ben Skeggs
eaebfcc34e drm/nouveau/core: add top plumbing 
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Karol Herbst
2e9a43f901 drm/nouveau/iccsense: configure sensors like nvidia does 
v2: rename ina209/ina219 read function

Signed-off-by: Karol Herbst <nouveau@karolherbst.de>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Karol Herbst
5f1f07de41 drm/nouveau/iccsense: split sensor into own struct 
v2: add list_del call, reword error message

Signed-off-by: Karol Herbst <nouveau@karolherbst.de>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Karol Herbst
92224e751f drm/nouveau/iccsense: convert to linked list 
v2: add list_del calls

Signed-off-by: Karol Herbst <nouveau@karolherbst.de>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Karol Herbst
d03e0f2748 drm/nouveau/iccsense: remove read function 
Signed-off-by: Karol Herbst <nouveau@karolherbst.de>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Karol Herbst
7d28dbae22 drm/nouveau/pmu: be more strict about locking 
When we start communicating with the pmu a bit more, the current code is
a real issue. I encountered a dead lock here, while testing my dynamic
reclocking code

Signed-off-by: Karol Herbst <nouveau@karolherbst.de>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00
Alexandre Courbot
c6007dc4e5 drm/nouveau/devinit/gf100: make devinit on resume safer 
In case of successful suspend, devinit will have to be run and this is
the behavior currently hardcoded. However, as FD bug 94725 suggests,
there might be cases where runtime suspend leaves the GPU powered, and
in such cases devinit should not be run on resume.

On GF100+ we have a reliable way to know whether we need to run devinit.
Use it instead of blindly trusting the flag set by nvkm_devinit_fini().

The code around the NvForcePost also needs to be slightly reworked in
order to keep working.

Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Suggested-by: Dave Airlie <airlied@redhat.com>
Suggested-by: Karol Herbst <nouveau@karolherbst.de>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
 2016-05-20 14:43:04 +10:00