smc fw is not needed in SRIOV, thus driver should not try to get smc
fw data.
Signed-off-by: Jingwen Chen
---
.../gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c| 61 ++-
1 file changed, 32 insertions(+), 29 deletions(-)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
b/
smc, sdma, sos and asd fw is not used in SRIOV. Skip them to
accelerate sw_init.
Signed-off-by: Jingwen Chen
---
drivers/gpu/drm/amd/amdgpu/psp_v11_0.c | 16 +---
drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 3 +++
drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c | 3 +++
[AMD Official Use Only - Internal Distribution Only]
Those three patches are
Reviewed-by: Monk Liu
_
Monk Liu|GPU Virtualization Team |AMD
-Original Message-
From: amd-gfx On Behalf Of Bokun Zhang
Sent: Wednesday, September 16, 2020 10:57 PM
To: amd
Always start vblank timer, but only calls vblank function
when vblank is enabled.
This is used to fix the dead lock issue.
When drm_crtc_vblank_off want to disable vblank,
it first get event_lock, and then call hrtimer_cancel,
but hrtimer_cancel want to wait timer handler function finished.
Timer
For debug convenient, add sriov_mcbp parameter.
Signed-off-by: Emily.Deng
Change-Id: I84019eb4344e00d85b2ecc853145aabb312412fe
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 9 +
drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 3 ++-
drivers/gpu/dr
On Thu, Sep 17, 2020 at 6:13 PM Luben Tuikov wrote:
>
> Convert to using devm_drm_dev_alloc(),
> as drm_dev_init() is going away.
>
> v2: Remove drm_dev_put() since
> a) devres doesn't do refcounting, see
> Documentation/driver-api/driver-model/devres.rst,
> Section 4, paragraph 1; and
[AMD Official Use Only - Internal Distribution Only]
Acked-by: Alex Deucher
From: Quan, Evan
Sent: Thursday, September 17, 2020 10:36 PM
To: amd-gfx@lists.freedesktop.org
Cc: Deucher, Alexander ; Quan, Evan
Subject: [PATCH] drm/amd/pm: apply dummy reads workar
[AMD Official Use Only - Internal Distribution Only]
Reviewed-by: Emily.Deng
>-Original Message-
>From: amd-gfx On Behalf Of
>Jingwen Chen
>Sent: Thursday, September 17, 2020 5:43 PM
>To: amd-gfx@lists.freedesktop.org
>Cc: Chen, JingWen
>Subject: [PATCH] drm/amd/pm: Skip smu_post_init
For CDR disabled case, the dummy reads workaround is not needed.
Change-Id: I474619b3d82792151870811c289ab311028de211
Signed-off-by: Evan Quan
---
drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c | 8 +---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/pm/sw
gfxhub functions are now called from function pointers,
instead of from asic-specific functions.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h| 4 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c | 3 +-
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c
This is based on top of Daniel's documentation
patch and it applies cleanly onto amd-staging-drm-next.
I'm also running this live.
This version removes explicit drm_dev_put(), as it seems
that devres acts as a garbage collector.
Luben Tuikov (1):
drm/amdgpu: Convert to using devm_drm_dev_alloc(
Convert to using devm_drm_dev_alloc(),
as drm_dev_init() is going away.
v2: Remove drm_dev_put() since
a) devres doesn't do refcounting, see
Documentation/driver-api/driver-model/devres.rst,
Section 4, paragraph 1; and since
b) devres acts as garbage collector when
the DRM devi
Non-outbound data metrics are non useful so mark them as legacy.
Bucket new perf counters into device and not device ip.
Bind events to chip instead of IP.
Report available event counters and not number of hw counter banks.
Move DF public macros to private since not needed outside of IP version.
v
Add xgmi perfmons for Arcturus.
Signed-off-by: Jonathan Kim
v2: Resend for re-review with alignment for v3 in patch 2.
---
drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c | 41 -
drivers/gpu/drm/amd/amdgpu/df_v3_6.c| 3 ++
2 files changed, 43 insertions(+), 1 deletion(-)
d
Mapping hw counters per event config will cause ABA problems so map per
event instead.
v2: Discontinue starting perf counters if add fails. Make it clear what's
happening with pmc_start.
Signed-off-by: Jonathan Kim
---
drivers/gpu/drm/amd/amdgpu/amdgpu_df.h | 6 +-
drivers/gpu/drm/amd/amdgp
Hi Harish. Thanks for the review. As discussed offline, patch 2 has a problem
where attr groups array is global but allocation is done per-device causing
problems with mem free and pmu unregister. I'm sending out a second series
that should fix this and simplify the solution as well as hopefu
On Wed, Sep 16, 2020 at 06:16:25PM -0400, Alex Deucher wrote:
> On Wed, Sep 16, 2020 at 3:04 AM Christoph Hellwig wrote:
> >
> > On Tue, Sep 15, 2020 at 02:46:07PM -0400, Alex Deucher wrote:
> > > This change breaks tons of systems.
> >
> > Did you do at least some basic root causing on why? Do G
[Why]
Allow user to know how many compute units (CU) are in use at any given
moment.
[How]
Surface files in Sysfs that allow user to determine the number of compute
units that are in use for a given process. One Sysfs file is used per
device.
Signed-off-by: Ramesh Errabolu
---
drivers/gpu/drm/a
[Why]
Allow user to know number of compute units (CU) that are in use at any
given moment.
[How]
Read registers of SQ that give number of waves that are in flight
of various queues. Use this information to determine number of CU's
in use.
Signed-off-by: Ramesh Errabolu
---
drivers/gpu/drm/amd/a
[Why]
Allow user to know how many compute units (CU) are in use at any given
moment.
[How]
Read registers of SQ that give number of waves that are in flight
of various queues. Use this information to determine number of CU's
in use.
Signed-off-by: Ramesh Errabolu
---
.../gpu/drm/amd/amdgpu/amdg
On Thu, Sep 17, 2020 at 4:28 AM Christian König
wrote:
>
> Am 17.09.20 um 05:46 schrieb Xiaoliang Pang:
> > modify the return value is -EINVAL
>
> Maybe better write something like "The correct return value should be
> -EINVAL." With that done feel free to add my acked-by.
Applied with updated co
On Thu, Sep 17, 2020 at 11:09 AM Ye Bin wrote:
>
> Fixes coccicheck warnig:
> drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c:282:12-42:
> duplicated argument to && or ||
> drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c:3240:12-42:
> duplicated argument to && or |
Applied with a slight cleanup to the commit message.
Thanks!
Alex
On Thu, Sep 17, 2020 at 3:33 AM Mauro Rossi wrote:
>
> (v1) Changelog
>
> [Why]
> After commit c69dd2d "drm/amd/display: Refactor clk_mgr functions"
> dc/clk_mgr requires these changes to add SI parts support
> Necessary to avoid
Fixes coccicheck warnig:
drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c:282:12-42:
duplicated argument to && or ||
drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c:3240:12-42:
duplicated argument to && or ||
drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_
[AMD Official Use Only - Internal Distribution Only]
Hi Jinlong,
This is a public thread for upstream review purpose mainly. Let's sync
internally for your issue.
Thanks,
Lillian
-Original Message-
From: Koenig, Christian
Sent: Thursday, September 17, 2020 10:46 AM
To: Zhang, Jinlong
On Thu, Sep 17, 2020 at 10:39 AM Zhang, Jinlong wrote:
>
> HI Christian
> While #include , it prompt
> ..\..\..\..\..\dc\dce\dce_aux.c(31): fatal error C1083: Cannot open include
> file: 'linux/delay.h': No such file or directory
> Could you help to check how to include the header of void
> usl
No idea what that is. I can include delay.h just fine in the rest of the
driver.
Must be something DC specific.
Regards,
Christian.
Am 17.09.20 um 16:39 schrieb Zhang, Jinlong:
HI Christian
While #include , it prompt ..\..\..\..\..\dc\dce\dce_aux.c(31):
fatal error C1083: Cannot open include
HI Christian
While #include , it prompt ..\..\..\..\..\dc\dce\dce_aux.c(31):
fatal error C1083: Cannot open include file: 'linux/delay.h': No such file or
directory
Could you help to check how to include the header of void usleep_range(unsigned
long min, unsigned long max);
-Original Messag
Am 2020-09-17 um 9:11 a.m. schrieb Cox, Philip:
> [AMD Official Use Only - Internal Distribution Only]
>
>>> +static struct attribute *procfs_stats_attrs[] = {
>>> + NULL
>>> +};
>> We could probably use this to populate the attributes in stats automatically
>> instead of calling sysfs_create_fi
[Why]
Update clock only when non-seamless boot stream exists
creates regression on multiple scenerios.
[How]
Update clock in two conditions
1. Non-seamless boot stream exist.
2. Stream_count = 0
Fixes:06f9b1475d98("drm/amd/display: update clock
when non-seamless boot stream exist")
Signed-off-by
Hi Thomas,
On 09/15, Thomas Zimmermann wrote:
> GEM object functions deprecate several similar callback interfaces in
> struct drm_driver. This patch replaces the per-driver callbacks with
> per-instance callbacks in vgem. The only exception is gem_prime_mmap,
> which is non-trivial to convert.
>
[AMD Official Use Only - Internal Distribution Only]
> > +static struct attribute *procfs_stats_attrs[] = {
> > + NULL
> > +};
>
> We could probably use this to populate the attributes in stats automatically
> instead of calling sysfs_create_file and sysfs_remove_file manually. Then we
> may
[AMD Official Use Only - Internal Distribution Only]
Am 17.09.20 um 00:18 schrieb Alex Deucher:
>> On Wed, Sep 16, 2020 at 6:16 PM Zhuo, Qingqing wrote:
>>> [AMD Official Use Only - Internal Distribution Only]
>>>
>>>On Wed, Sep 16, 2020 at 3:42 PM Qingqing Zhuo wrote:
From: jinlong zhang
On Thu, Sep 17, 2020 at 4:26 AM Christian König
wrote:
>
> Am 17.09.20 um 00:18 schrieb Alex Deucher:
> > On Wed, Sep 16, 2020 at 6:16 PM Zhuo, Qingqing
> > wrote:
> >> [AMD Official Use Only - Internal Distribution Only]
> >>
> >> On Wed, Sep 16, 2020 at 3:42 PM Qingqing Zhuo
> >> wrote:
> >>
On Wed, Sep 16, 2020 at 11:27:27AM -0400, Kazlauskas, Nicholas wrote:
> On 2020-09-16 5:12 a.m., Daniel Vetter wrote:
> > On Fri, Sep 11, 2020 at 10:59:23AM -0400, Rodrigo Siqueira wrote:
> > > Debug issues related to display can be a challenge due to the complexity
> > > around this topic and diff
Hi Thomas,
On 09/15, Thomas Zimmermann wrote:
> GEM object functions deprecate several similar callback interfaces in
> struct drm_driver. This patch replaces the per-driver callbacks with
> per-instance callbacks in vkms.
>
> Signed-off-by: Thomas Zimmermann
Thanks! Looks fine.
Reviewed-by: M
On Tue, Sep 15, 2020 at 04:59:51PM +0200, Thomas Zimmermann wrote:
> GEM object functions deprecate several similar callback interfaces in
> struct drm_driver. This patch replaces the per-driver callbacks with
> per-instance callbacks in tegra.
>
> Signed-off-by: Thomas Zimmermann
> ---
> driver
[AMD Public Use]
Typo fixed in v3
Best Regards,
JingWen Chen
> -Original Message-
> From: Chen, Guchun
> Sent: Thursday, September 17, 2020 5:40 PM
> To: Chen, JingWen ; amd-
> g...@lists.freedesktop.org
> Cc: Chen, JingWen
> Subject: RE: [PATCH] drm/amd/pm: Skip smu_post_init in SRIOV
smu_post_init needs to enable SMU feature, while this require
virtualization off. Skip it since this feature is not used in SRIOV.
v2: move the check to the early stage of smu_post_init.
v3: fix typo
Signed-off-by: Jingwen Chen
---
drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c | 3 +++
1 fil
[AMD Public Use]
You want to call it in SRIOV case or in bare-metal case?
Regards,
Guchun
-Original Message-
From: amd-gfx On Behalf Of Jingwen Chen
Sent: Thursday, September 17, 2020 5:17 PM
To: amd-gfx@lists.freedesktop.org
Cc: Chen, JingWen
Subject: [PATCH] drm/amd/pm: Skip smu_post
[AMD Public Use]
Done in v2
Best Regards,
JingWen Chen
> -Original Message-
> From: Chen, Guchun
> Sent: Thursday, September 17, 2020 4:21 PM
> To: Chen, JingWen ; amd-
> g...@lists.freedesktop.org
> Cc: Chen, JingWen
> Subject: RE: [PATCH] drm/amd/pm: Skip smu_post_init in SRIOV
>
>
smu_post_init needs to enable SMU feature, while this require
virtualization off. Skip it since this feature is not used in SRIOV.
v2: move the check to the early stage of smu_post_init.
Signed-off-by: Jingwen Chen
---
drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c | 3 +++
1 file changed, 3 i
read/writes to aux_dpcd_* sysfs entries leads to system
reboot or hang.
Hence fix the handling of input data and reporting of errors
appropriately to the user space.
Signed-off-by: Shirish S
---
.../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c | 10 +-
1 file changed, 5 insertions(
Am 17.09.20 um 05:46 schrieb Xiaoliang Pang:
modify the return value is -EINVAL
Maybe better write something like "The correct return value should be
-EINVAL." With that done feel free to add my acked-by.
Christian.
Fixes: f83a9991648bb("drm/amd/powerplay: add Vega10 powerplay support (v5
Am 17.09.20 um 00:18 schrieb Alex Deucher:
On Wed, Sep 16, 2020 at 6:16 PM Zhuo, Qingqing wrote:
[AMD Official Use Only - Internal Distribution Only]
On Wed, Sep 16, 2020 at 3:42 PM Qingqing Zhuo wrote:
From: jinlong zhang
[why]
while read edid return defer, then it enter to msleep, but it
[AMD Public Use]
Why not moving the check in smu_post_init, and return 0 at the first early
stage if it's SRIOV case?
Regards,
Guchun
-Original Message-
From: amd-gfx On Behalf Of Jingwen Chen
Sent: Thursday, September 17, 2020 4:11 PM
To: amd-gfx@lists.freedesktop.org
Cc: Chen, JingWe
smu_post_init needs to enable SMU feature, while this require
virtualization off. Skip it since this feature is not used in SRIOV.
Signed-off-by: Jingwen Chen
---
drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c | 10 ++
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/
Hi
Am 15.09.20 um 17:05 schrieb Christian König:
> Am 15.09.20 um 16:59 schrieb Thomas Zimmermann:
>> GEM object functions deprecate several similar callback interfaces in
>> struct drm_driver. This patch replaces the per-driver callbacks with
>> per-instance callbacks in amdgpu. The only exceptio
(v1) Changelog
[Why]
After commit c69dd2d "drm/amd/display: Refactor clk_mgr functions"
dc/clk_mgr requires these changes to add SI parts support
Necessary to avoid hitting default: ASSERT(0); /* Unknown Asic */
that would cause kernel freeze
[How]
Add case statement for FAMILY_SI chipsets
(v2)
Hi
Am 15.09.20 um 17:25 schrieb Christian König:
> Added my rb to the amdgpu and radeon patches.
>
> Should we pick those up through the amd branches or do you want to push
> everything to drm-misc-next?
>
> I think the later since this should result in much merge clash.
Yes, preferable, I'd me
50 matches
Mail list logo
