This loop in the error handling code should start a "i - 1" and end at
"i == 0". Currently it starts a "i" and ends at "i == 1". The result
is that it removes one attribute that wasn't created yet, and leaks the
zeroeth attribute.
Fixes: 4e01847c38 ("drm/amdgpu: optimize amdgpu device attribute code")
Acked-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Only ras supportted need to set MP1 state to prepare for unload before
reloading SMU FW.
Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Under xgmi setup,some sysfs fail to create for the second time of kmd
driver loading. It's due to sysfs nodes are not removed appropriately
in the last unlod time.
Changes of this patch:
1. remove sysfs for dev_attr_xgmi_error
2. remove sysfs_link adev->dev->kobj with target name.
And it only needs to be removed once for a xgmi setup
3. remove sysfs_link hive->kobj with target name
In amdgpu_xgmi_remove_device:
1. amdgpu_xgmi_sysfs_rem_dev_info needs to be run per device
2. amdgpu_xgmi_sysfs_destroy needs to be run on the last node of
device.
v2: initialize array with memset
Signed-off-by: Jack Zhang <Jack.Zhang1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
SCRATCH2 is used to keep decode wptr as a workaround
which fix a hardware DPG decode wptr update bug for
vcn2.5 beforehand.
Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Remove JPEG_ENC_MASK from clock ungating since MJPEG encoder
hasn't been support yet.
Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
At bringup we want to be able to disable various power features.
[How]
These features are already exposed as dc_debug_options and exercised
on other OSes. Create a new dc_debug_mask module parameter and expose
relevant bits, in particular
* DC_DISABLE_PIPE_SPLIT
* DC_DISABLE_STUTTER
* DC_DISABLE_DSC
* DC_DISABLE_CLOCK_GATING
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
the amdgpu device attribute node will be created accordding to sriov vf
mode at runtime.
cleanup unnecessary sriov check in attribute operation function.
Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Spelling out _unlocked for each and every driver is a annoying.
Especially if we consider how many drivers, do not know (or need to)
about the horror stories involving struct_mutex.
Just drop the suffix. It makes the API cleaner.
Done via the following script:
__from=drm_gem_object_put_unlocked
__to=drm_gem_object_put
for __file in $(git grep --name-only $__from); do
sed -i "s/$__from/$__to/g" $__file;
done
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: "Christian König" <christian.koenig@amd.com>
Cc: "David (ChunMing) Zhou" <David1.Zhou@amd.com>
Signed-off-by: Emil Velikov <emil.velikov@collabora.com>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20200515095118.2743122-15-emil.l.velikov@gmail.com
The driver does not hold struct_mutex, thus using the locked version of
the helper is incorrect.
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: amd-gfx@lists.freedesktop.org
Fixes: a39414716c ("drm/amdgpu: add independent DMA-buf import v9")
Signed-off-by: Emil Velikov <emil.velikov@collabora.com>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Reviewed-by: Christian König <christian.koenig@amd.com>
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20200515095118.2743122-8-emil.l.velikov@gmail.com
When this flag is set in the CS IB flags, it causes
a memory cache flush of the GFX.
v2:
Move new flag to drm_amdgpu_cs_chunk_ib.flags
Bump up UAPI version
Remove condition on job != null to emit mem_sync
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Luben Tuikov <luben.tuikov@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Compute IBs need this too.
v2: split out version bump
v3: squash in emit frame count fixes
Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Used to flush and invalidate various caches.
v2: Rename function hook
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Luben Tuikov <luben.tuikov@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
unified amdgpu device attribute node functions:
1. add some helper functions to create amdgpu device attribute node.
2. create device node according to device attr flags on different VF mode.
3. rename some functions name to adapt a new interface.
v2:
1. remove ATTR_STATE_DEAD, ATTR_STATE_ALIVE enum.
2. rename callback function perform to attr_update.
3. modify some variable names
Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
the swsmu or powerplay(hwmgr) need to handle task according to different VF mode,
this function to help query vf mode.
vf mode:
1. SRIOV_VF_MODE_BARE_METAL: the driver work on host OS (PF)
2. SRIOV_VF_MODE_ONE_VF : the driver work on guest OS with one VF
3. SRIOV_VF_MODE_MULTI_VF : the driver work on guest OS with multi VF
Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When GPU got timeout, it would notify an interested part
of an opportunity to dump info before actual GPU reset.
A usermode app would open 'autodump' node under debugfs system
and poll() for readable/writable. When a GPU reset is due,
amdgpu would notify usermode app through wait_queue_head and give
it 10 minutes to dump info.
After usermode app has done its work, this 'autodump' node is closed.
On node closure, amdgpu gets to know the dump is done through
the completion that is triggered in release().
There is no write or read callback because necessary info can be
obtained through dmesg and umr. Messages back and forth between
usermode app and amdgpu are unnecessary.
v2: (1) changed 'registered' to 'app_listening'
(2) add a mutex in open() to prevent race condition
v3 (chk): grab the reset lock to avoid race in autodump_open,
rename debugfs file to amdgpu_autodump,
provide autodump_read as well,
style and code cleanups
v4: add 'bool app_listening' to differentiate situations, so that
the node can be reopened; also, there is no need to wait for
completion when no app is waiting for a dump.
v5: change 'bool app_listening' to 'enum amdgpu_autodump_state'
add 'app_state_mutex' for race conditions:
(1)Only 1 user can open this file node
(2)wait_dump() can only take effect after poll() executed.
(3)eliminated the race condition between release() and
wait_dump()
v6: removed 'enum amdgpu_autodump_state' and 'app_state_mutex'
removed state checking in amdgpu_debugfs_wait_dump
Improve on top of version 3 so that the node can be reopened.
v7: move reinit_completion into open() so that only one user
can open it.
v8: remove complete_all() from amdgpu_debugfs_wait_dump().
Signed-off-by: Jiange Zhao <Jiange.Zhao@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Disable XGMI link power down prior to issuing a XGMI RAS error
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The variable ret is being initializeed with a value that is never read
and it is being updated later with a new value. The initialization
is redundant and can be removed.
Addresses-Coverity: ("Unused value")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
There is no need to use amdgpu_mm_wreg_mmio_rlc()
during initialization time because this interface
is only designed for debugfs case to access the
registers which are only permitted by RLCG during
run-time. Therefore, turn back rlcg write for gfx_v10.
If we not turn back it, it will raise amdgpu load failure.
[ 54.904333] amdgpu: SMU driver if version not matched
[ 54.904393] amdgpu: SMU is initialized successfully!
[ 54.905971] [drm] kiq ring mec 2 pipe 1 q 0
[ 55.115416] amdgpu 0000:00:06.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring gfx_0.0.0 test failed (-110)
[ 55.118877] [drm:amdgpu_device_init [amdgpu]] *ERROR* hw_init of IP block <gfx_v10_0> failed -110
[ 55.126587] amdgpu 0000:00:06.0: amdgpu_device_ip_init failed
[ 55.133466] amdgpu 0000:00:06.0: Fatal error during GPU init
Signed-off-by: Yintian Tao <yttao@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
On my raven1 system (rev c6) with VBIOS 113-RAVEN-114 GFXOFF is
not stable (resulting in large block tiling noise in some applications).
Disabling GFXOFF via the quirk list fixes the problems for me.
Signed-off-by: Tom St Denis <tom.stdenis@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Fix the following gcc warning:
drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c:65:18: warning: ‘crtc_offsets’
defined but not used [-Wunused-const-variable=]
static const u32 crtc_offsets[6] =
^~~~~~~~~~~~
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Jason Yan <yanaijie@huawei.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
On my raven1 system (rev c6) with VBIOS 113-RAVEN-114 GFXOFF is
not stable (resulting in large block tiling noise in some applications).
Disabling GFXOFF via the quirk list fixes the problems for me.
Signed-off-by: Tom St Denis <tom.stdenis@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Presumably the intent here was that hmm_range_fault() could put the data
into some HW specific format and thus avoid some work. However, nothing
actually does that, and it isn't clear how anything actually could do that
as hmm_range_fault() provides CPU addresses which must be DMA mapped.
Perhaps there is some special HW that does not need DMA mapping, but we
don't have any examples of this, and the theoretical performance win of
avoiding an extra scan over the pfns array doesn't seem worth the
complexity. Plus pfns needs to be scanned anyhow to sort out any
DEVICE_PRIVATE pages.
This version replaces the uint64_t with an usigned long containing a pfn
and fixed flags. On input flags is filled with the HMM_PFN_REQ_* values,
on successful output it is filled with HMM_PFN_* values, describing the
state of the pages.
amdgpu is simple to convert, it doesn't use snapshot and doesn't use
per-page flags.
nouveau uses only 16 hmm_pte entries at most (ie fits in a few cache
lines), and it sweeps over its pfns array a couple of times anyhow. It
also has a nasty call chain before it reaches the dma map and hardware
suggesting performance isn't important:
nouveau_svm_fault():
args.i.m.method = NVIF_VMM_V0_PFNMAP
nouveau_range_fault()
nvif_object_ioctl()
client->driver->ioctl()
struct nvif_driver nvif_driver_nvkm:
.ioctl = nvkm_client_ioctl
nvkm_ioctl()
nvkm_ioctl_path()
nvkm_ioctl_v0[type].func(..)
nvkm_ioctl_mthd()
nvkm_object_mthd()
struct nvkm_object_func nvkm_uvmm:
.mthd = nvkm_uvmm_mthd
nvkm_uvmm_mthd()
nvkm_uvmm_mthd_pfnmap()
nvkm_vmm_pfn_map()
nvkm_vmm_ptes_get_map()
func == gp100_vmm_pgt_pfn
struct nvkm_vmm_desc_func gp100_vmm_desc_spt:
.pfn = gp100_vmm_pgt_pfn
nvkm_vmm_iter()
REF_PTES == func == gp100_vmm_pgt_pfn()
dma_map_page()
Link: https://lore.kernel.org/r/5-v2-b4e84f444c7d+24f57-hmm_no_flags_jgg@mellanox.com
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This is just an alias for HMM_PFN_ERROR, nothing cares that the error was
because of a special page vs any other error case.
Link: https://lore.kernel.org/r/4-v2-b4e84f444c7d+24f57-hmm_no_flags_jgg@mellanox.com
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Since amdgpu does not use the snapshot mode of hmm_range_fault() a
successful return already proves that all entries in the pfns are
HMM_PFN_VALID, there is no need to check the return result of
hmm_device_entry_to_page().
Link: https://lore.kernel.org/r/3-v2-b4e84f444c7d+24f57-hmm_no_flags_jgg@mellanox.com
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
hmm_vma_walk->last is supposed to be updated after every write to the
pfns, so that it can be returned by hmm_range_fault(). However, this is
not done consistently. Fortunately nothing checks the return code of
hmm_range_fault() for anything other than error.
More importantly last must be set before returning -EBUSY as it is used to
prevent reading an output pfn as an input flags when the loop restarts.
For clarity and simplicity make hmm_range_fault() return 0 or -ERRNO. Only
set last when returning -EBUSY.
Link: https://lore.kernel.org/r/2-v2-b4e84f444c7d+24f57-hmm_no_flags_jgg@mellanox.com
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Same as gfx9. This allows us to kill the waves for hung
shaders.
Acked-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
BACO is needed to support hibernate on Navi1X.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Releasing the AMDGPU BO ref directly leads to problems when BOs were
exported as DMA bufs. Releasing the GEM reference makes sure that the
AMDGPU/TTM BO is not freed too early.
Also take a GEM reference when importing BOs from DMABufs to keep
references to imported BOs balances properly.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Alex Sierra <alex.sierra@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Sierra <alex.sierra@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
We set the fb smem pointer to the offset into the BAR, so keep
the fbdev bo in vram.
Bug: https://bugzilla.kernel.org/show_bug.cgi?id=207581
Fixes: 6c8d74caa2 ("drm/amdgpu: Enable scatter gather display support")
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
As this is already properly handled in amdgpu_gfx_off_ctrl(). In fact,
this unnecessary cancel_delayed_work_sync may leave a small time window
for race condition and is dangerous.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Otherwise, MGCG/MGLS will be left enabled.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
We only need to set DPM_FLAG_NEVER_SKIP for the legacy ATPX
BOCO case. D3cold and BACO work as expected.
Acked-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
We should be checking whether the driver enabled runtime pm
rather than whether the asic supports BOCO or BACO. That said
in general they are equivalent unless the user has disabled
runpm or it has been disabled for a specific asic.
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Same as gfx9. This allows us to kill the waves for hung
shaders.
Acked-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Create sysfs file using attributes.
Signed-off-by: Nirmoy Das <nirmoy.das@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
BACO is needed to support hibernate on Navi1X.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
physical_node_id * node_segment_size should be the
dram_base_address for current gpu node in xgmi config
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drop IP specific psp function for rlc autoload since
the autoload_supported was introduced to mark ASICs
that support rlc_autoload
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: John Clements <john.clements@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
cure posion command was replaced by ras recovery
solution and was not a formal command supported
by ras ta anymore
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: John Clements <john.clements@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
TRIGGER_ERROR is common ras ta command for all the
ASICs that support RAS feature. switch to common helper
to avoid duplicate implementation per IP generation
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: John Clements <john.clements@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
get_hive_id/get_node_id/get_topology_info/set_topology_info
are common xgmi command supported by TA for all the ASICs
that support xgmi link. They should be implemented as common
helper functions to avoid duplicated code per IP generation
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: John Clements <john.clements@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
There is DEVICE_ATTR mechanism in separate attribute define.
So this change is to use attr array, also use
sysfs_create_files in init function & sysfs_remove_files in
fini function.
This maybe make the code a bit readable.
Signed-off-by: Bernard Zhao <bernard@vivo.com>
Changes since V1:
*Use DEVICE_ATTR mechanism
Link for V1:
*https://lore.kernel.org/patchwork/patch/1228076/
V2: make array const to fix build errors
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Invoke sequence should abort when ras interrupt is detected before reading TA host shared memory
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
