== Series Details ==
Series: Fix PSR-vblank-DMC interaction
URL : https://patchwork.freedesktop.org/series/35553/
State : success
== Summary ==
Test kms_frontbuffer_tracking:
Subgroup fbc-1p-offscren-pri-shrfb-draw-render:
fail -> PASS (shard-snb)
== Series Details ==
Series: Fix PSR-vblank-DMC interaction
URL : https://patchwork.freedesktop.org/series/35553/
State : success
== Summary ==
Series 35553v1 Fix PSR-vblank-DMC interaction
https://patchwork.freedesktop.org/api/1.0/series/35553/revisions/1/mbox/
Test kms_pipe_crc_basic:
Updating the vblank counts requires register reads and these reads may not
return meaningful values after the vblank interrupts are disabled as the
device may go to low power state. An additional change would be to allow
the driver to save the vblank counts before entering a low power state, but
The global variable dev_priv->psr.sink_support is set if an eDP sink
supports PSR. Use this instead of redoing the check with is_edp_psr().
Combine source and sink support checks into a macro that can be used to
return early from psr_{invalidate, single_frame_update, flush}.
Cc: Rodrigo Vivi
This flag has become redundant since
commit 4d90f2d507ab ("drm/i915: Start tracking PSR state in crtc state")
It is set at the same place as psr.enabled, which is also exposed via
debugfs.
Cc: Rodrigo Vivi
Cc: Ville Syrjälä
Signed-off-by:
When DC states are enabled and PSR is active, the hardware enters DC5/DC6
states resulting in frame counter resets. The frame counter resets mess
up the vblank counting logic. In order to disable DC states when
vblank interrupts are required and to disallow DC states when vblanks
interrupts are
The HW frame counter can get reset when devices enters low power
states and this messes up any following vblank count updates. So, compute
the missed vblank interrupts for that low power state duration using time
stamps. This is similar to _crtc_vblank_on() except that it doesn't enable
vblank
Convert the power_domains->domain_use_count array that tracks per-domain
use count to atomic_t type. This is needed to be able to read/write the use
counts outside of the power domain mutex.
Cc: Daniel Vetter
Cc: Ville Syrjälä
Cc: Rodrigo
Disable DC states before enabling vblank interrupts and conversely
enable DC states after disabling. Since the frame counter may have got
reset between disabling and enabling, use drm_crtc_vblank_restore() to
compute the missed vblanks.
Cc: Daniel Vetter
Cc: Ville Syrjälä
The first 3 patches are minor PSR improvements. The last 5 introduce a new
power domain to disable DC states when vblanks are required. The tricky
part is to enable and disable the DC_OFF power well in atomic context. I
have addressed the locking issues that CI caught in the last revision.
DPCD read for the eDP is complete by the time intel_psr_init() is
called, which means we can avoid initializing PSR structures and state
if there is no sink support.
Cc: Rodrigo Vivi
Cc: Ville Syrjälä
Signed-off-by: Dhinakaran Pandiyan
== Series Details ==
Series: series starting with [1/2] drm/i915: Implement WaDisableVFclkgate.
URL : https://patchwork.freedesktop.org/series/35456/
State : success
== Summary ==
Test kms_frontbuffer_tracking:
Subgroup fbc-1p-offscren-pri-shrfb-draw-render:
fail
On 12/18/2017 01:47 PM, Chris Wilson wrote:
Quoting Jackie Li (2017-12-18 21:22:08)
From: Zhipeng Gong
SKL platforms requires a higher ring multiplier when there's massive
GPU load. Current driver doesn't provide a way to override the ring
multiplier.
This patch adds
== Series Details ==
Series: overlay: parse tracepoints from sysfs to figure out fields' location
(rev2)
URL : https://patchwork.freedesktop.org/series/35545/
State : failure
== Summary ==
IGT patchset build failed on latest successful build
cfb711c046c22c3881d2334f0b43ec4eb0b9a5fc
With changes going to drm-tip, the tracepoints field locations are
going to change. This change introduces a tracepoint parser (using a
peg parser) which lets us figure out field positions on the fly.
v2: Fix automake build (Lionel)
Signed-off-by: Lionel Landwerlin
== Series Details ==
Series: overlay: parse tracepoints from sysfs to figure out fields' location
URL : https://patchwork.freedesktop.org/series/35545/
State : failure
== Summary ==
IGT patchset build failed on latest successful build
cfb711c046c22c3881d2334f0b43ec4eb0b9a5fc scripts/trace.pl:
With changes going to drm-tip, the tracepoints field locations are
going to change. This change introduces a tracepoint parser (using a
peg parser) which lets us figure out field positions on the fly.
Signed-off-by: Lionel Landwerlin
---
configure.ac
>-Original Message-
>From: daniel.vet...@ffwll.ch [mailto:daniel.vet...@ffwll.ch] On Behalf Of
>Daniel
>Vetter
>Sent: Thursday, December 14, 2017 2:14 AM
>To: Srivatsa, Anusha ; Strano, Luis
>; Latvala, Petri ;
== Series Details ==
Series: series starting with [1/2] drm/i915: Implement WaDisableVFclkgate.
URL : https://patchwork.freedesktop.org/series/35456/
State : success
== Summary ==
Series 35456v1 series starting with [1/2] drm/i915: Implement
WaDisableVFclkgate.
On Wed, Dec 13, 2017 at 09:25:16AM +, Mika Kahola wrote:
> crtc_mask is defined explicitly defined for a certain number of pipes per
> platform. Let's generalize this in a way that crtc_mask dependens only on
> the number of pipes defined in device info.
>
> v2: Use BIT() macro wherever
On Thu, Dec 14, 2017 at 10:14:19AM +, Daniel Vetter wrote:
> On Thu, Nov 23, 2017 at 12:05 AM, Anusha Srivatsa
> wrote:
> > From: Joseph Garvey
> >
> > Test that horizontal flip works with supported rotations. Includes
> > a fix for the
Hi there,
Please report a bug on bugzilla.freedesktop.org as instructed on
https://01.org/linuxgraphics/documentation/how-report-bugs
We will need more info about your platform and more logs to
determine what is happening on your case.
Thanks,
Rodrigo.
On Mon, Dec 18, 2017 at 10:45:53AM +,
On 12/18/2017 4:02 AM, Tvrtko Ursulin wrote:
From: Tvrtko Ursulin
Instead of hard-coding the order of key-value pairs into regular
expressions, auto-detect them as we go.
At the same time re-factor the code so it is smaller and even
slightly faster (10-15% by a quick
Hello, I need you help.
I have a display problem about Intel Graphics driver.
I use CentOS7.4(Kernel 3.10.0-693), and enter to OS without VGA cable. After
entering OS, I plug in VGA cable but without display on my monitor.
I also try to test Win10. If I install the Graphics driver, this problem
On Sat, Dec 16, 2017 at 03:25:01PM +, Ville Syrjälä wrote:
> On Fri, Dec 15, 2017 at 10:22:25PM +, Chris Wilson wrote:
> > Quoting Rodrigo Vivi (2017-12-15 21:38:00)
> > > From: Joonas Lahtinen
> > >
> > > CNL supports horizontal plane flipping on
== Series Details ==
Series: drm/i915: Add a new modparam for customized ring multiplier
URL : https://patchwork.freedesktop.org/series/35535/
State : failure
== Summary ==
Test kms_fbcon_fbt:
Subgroup fbc-suspend:
pass -> SKIP (shard-hsw)
Test
On Mon, Dec 18, 2017 at 10:40:02AM +, Maarten Lankhorst wrote:
> Op 15-12-17 om 23:43 schreef Rodrigo Vivi:
> > In case we have multiple modesets for different connectors
> > happening in parallel we could have a race on the RMW on these
> > shared registers.
> >
> > This possibility was
Quoting Michel Thierry (2017-12-18 21:50:17)
> On 17/12/17 05:28, Chris Wilson wrote:
> > Now that we skip a per-engine reset on an idle engine, we need to update
> > the selftest to take that into account. In the process, we find that we
> > were not stressing the per-engine reset very hard, so
On 17/12/17 05:28, Chris Wilson wrote:
Now that we skip a per-engine reset on an idle engine, we need to update
the selftest to take that into account. In the process, we find that we
were not stressing the per-engine reset very hard, so add those missing
active resets.
v2: Actually test
Quoting Jackie Li (2017-12-18 21:22:08)
> From: Zhipeng Gong
>
> SKL platforms requires a higher ring multiplier when there's massive
> GPU load. Current driver doesn't provide a way to override the ring
> multiplier.
>
> This patch adds a new module parameter to allow
== Series Details ==
Series: drm/i915: Add a new modparam for customized ring multiplier
URL : https://patchwork.freedesktop.org/series/35535/
State : success
== Summary ==
Series 35535v1 drm/i915: Add a new modparam for customized ring multiplier
From: Zhipeng Gong
SKL platforms requires a higher ring multiplier when there's massive
GPU load. Current driver doesn't provide a way to override the ring
multiplier.
This patch adds a new module parameter to allow the overriding of
ring multiplier for Gen9 platforms.
Quoting Jani Nikula (2017-12-18 17:37:13)
> On Mon, 18 Dec 2017, Chris Wilson wrote:
> > Looks good, I'm thinking we might push the drm_printer to the caller of
> > intel_device_info_dump(), but this is already a substantial improvement
>
> Param ordering seems a bit
On Mon, 18 Dec 2017 20:25:17 +0100, Srivatsa, Anusha
wrote:
-Original Message-
From: Vivi, Rodrigo
Sent: Friday, December 15, 2017 3:03 PM
To: Wajdeczko, Michal
Cc: intel-gfx@lists.freedesktop.org; Srivatsa, Anusha
Quoting Antonio Argenziano (2017-12-18 18:15:35)
>
>
> On 15/12/17 16:14, Chris Wilson wrote:
> > Quoting Antonio Argenziano (2017-12-15 19:01:11)
> >> + arg.param = I915_CONTEXT_PARAM_PRIORITY;
> >> +
> >> + igt_subtest("root-set-priority") {
> >> + arg.ctx_id = ctx;
>
== Series Details ==
Series: drm/i915/guc : Decoupling ADS and logs from submission
URL : https://patchwork.freedesktop.org/series/35530/
State : success
== Summary ==
Test drv_suspend:
Subgroup debugfs-reader:
skip -> PASS (shard-hsw)
Test
Hi Dave,
I expect to have one more pile next week for rc6. But for now consider
already applying this one.
On this one here we had one backmerge for a reconciliation drm_print.h
between us and drm-misc-next. But that should be transparent to you.
On the GVT side it is worth to highlight that
On Thu, Dec 7, 2017 at 5:38 AM, Jose Abreu wrote:
> Hi Sean,
>
> On 07-12-2017 00:00, Sean Paul wrote:
>> Welcome to version 4 of the patchset. I think we're nearing the finish line
>> (hopefully) now. This set addresses the review feedback from v3. I applied
>> some
>>
== Series Details ==
Series: drm/i915/guc : Decoupling ADS and logs from submission
URL : https://patchwork.freedesktop.org/series/35530/
State : success
== Summary ==
Series 35530v1 drm/i915/guc : Decoupling ADS and logs from submission
== Series Details ==
Series: scripts/trace.pl: Remove some old code
URL : https://patchwork.freedesktop.org/series/35526/
State : warning
== Summary ==
Test kms_frontbuffer_tracking:
Subgroup fbc-1p-offscren-pri-shrfb-draw-render:
fail -> PASS (shard-snb)
>-Original Message-
>From: Vivi, Rodrigo
>Sent: Friday, December 15, 2017 3:03 PM
>To: Wajdeczko, Michal
>Cc: intel-gfx@lists.freedesktop.org; Srivatsa, Anusha
>
>Subject: Re: [Intel-gfx] [PATCH] drm/i915/glk: Disable Guc and HuC on
Op 14-11-17 om 16:17 schreef Shashank Sharma:
> LSPCON chips are capable of generating YCBCR 4:2:0 outputs, if asked
> nicely :). In order to generate YCBCR 4:2:0 outputs, a source must:
> - send YCBCR 4:4:4 signals to LSPCON
> - program color space as 4:2:0 in AVI infoframes
>
> This will
Op 14-11-17 om 16:17 schreef Shashank Sharma:
> Different LSPCON vendors specify their custom methods to pass
> AVI infoframes to the LSPCON chip, so does Parade tech.
>
> This patch adds functions to arrange and write AVI infoframes
> into Parade LSPCON chips.
>
> Signed-off-by: Shashank Sharma
The Additional Data Struct (ADS) contains objects that are required by
GuC post FW load and are not necessarily submission-only. Even with
submission disabled we may require something inside the ADS, so it
makes more sense for them to be always created.
Similarly, we still want to access GuC logs
On 15/12/17 16:14, Chris Wilson wrote:
Quoting Antonio Argenziano (2017-12-15 19:01:11)
Since commit: drm/i915/scheduler: Support user-defined priorities, the
driver support an extra context param to set context's priority. Add
tests for that interface and update invalid tests.
== Series Details ==
Series: scripts/trace.pl: Remove some old code
URL : https://patchwork.freedesktop.org/series/35526/
State : success
== Summary ==
IGT patchset tested on top of latest successful build
cfb711c046c22c3881d2334f0b43ec4eb0b9a5fc scripts/trace.pl: Auto-detect
tracepoint
On Sun, Dec 17, 2017 at 11:11 PM, Daniel Vetter wrote:
>
> This didn't seem to have made it into -rc4. Anything needed to get it
> going?
Do you actually see the problem in -rc4?
Because we ended up removing the cross-release checking due to other
developers complaining. It
On Mon, 18 Dec 2017, Chris Wilson wrote:
> Quoting Michal Wajdeczko (2017-12-18 15:51:31)
>> We dump device flags in few places (init_early, debugfs, gpu_error)
>> using different functions. Lets add reusable function to avoid
>> code duplication.
>>
>> add/remove: 1/0
== Series Details ==
Series: series starting with [1/2] drm/i915: Add pretty printer for device info
flags
URL : https://patchwork.freedesktop.org/series/35521/
State : success
== Summary ==
Test drv_selftest:
Subgroup live_hangcheck:
incomplete -> PASS
Op 18-12-17 om 08:08 schreef Daniel Vetter:
> Hm, the bisect looks funny. Only way I can explain that is that my
> patch fixed a pre-existing lockdep splat, and uncovered the issue in
> the ww-mutex self tests. That one is uncovered by the new
> cross-release lockdep checks in 4.15.
>
> Anyway I
From: Tvrtko Ursulin
Remove some inactive code which was only uised to support the old execlists
implementation. It is hidden behind a toggle which is not user accesible
anyway.
Signed-off-by: Tvrtko Ursulin
Cc: John Harrison
== Series Details ==
Series: drm/i915: improve tracepoints for process/hw_id tracking (rev2)
URL : https://patchwork.freedesktop.org/series/35506/
State : failure
== Summary ==
Test kms_pipe_crc_basic:
Subgroup suspend-read-crc-pipe-a:
pass -> SKIP
Oops, forgot to send the patch dumping the i915 headers :(
On 18/12/17 16:49, Patchwork wrote:
== Series Details ==
Series: tests: add i915 query tests
URL : https://patchwork.freedesktop.org/series/35520/
State : failure
== Summary ==
IGT patchset build failed on latest successful build
== Series Details ==
Series: tests: add i915 query tests
URL : https://patchwork.freedesktop.org/series/35520/
State : failure
== Summary ==
IGT patchset build failed on latest successful build
c0be3310715e2f744b892c51f09e62273bcc8e57 tests/kms_frontbuffer_tracking:
Correctly handle debugfs
== Series Details ==
Series: series starting with [1/2] drm/i915: Add pretty printer for device info
flags
URL : https://patchwork.freedesktop.org/series/35521/
State : success
== Summary ==
Series 35521v1 series starting with [1/2] drm/i915: Add pretty printer for
device info flags
On 18/12/17 15:22, Chris Wilson wrote:
Quoting Lionel Landwerlin (2017-12-18 15:19:59)
When monitoring the GPU with i915 perf, reports are tagged with a hw
id. Gem context creation tracepoints already have a hw_id field,
unfortunately you only get this correlation between a process id and a
hw
Hi Daniel,
Thank you for the patch.
On Thursday, 14 December 2017 22:30:53 EET Daniel Vetter wrote:
> DK put some nice docs into the commit introducing driver private
> state, but in the git history alone it'll be lost.
You might want to spell DK's name fully.
> Also, since Ville remove the
Quoting Michal Wajdeczko (2017-12-18 15:51:32)
> We dump modparams in few places (debugfs, gpu_error) using different
> functions. Lets add reusable function to avoid code duplication.
>
> add/remove: 1/0 grow/shrink: 0/2 up/down: 1096/-2339 (-1243)
> Function
Hi Alex,
On Friday, 15 December 2017 03:57:48 EET Alex Deucher wrote:
> On Thu, Dec 14, 2017 at 3:30 PM, Daniel Vetter wrote:
> > DK put some nice docs into the commit introducing driver private
> > state, but in the git history alone it'll be lost.
> >
> > Also, since Ville remove the void*
Quoting Michal Wajdeczko (2017-12-18 15:51:31)
> We dump device flags in few places (init_early, debugfs, gpu_error)
> using different functions. Lets add reusable function to avoid
> code duplication.
>
> add/remove: 1/0 grow/shrink: 0/3 up/down: 1296/-3572 (-2276)
> Function
== Series Details ==
Series: drm/i915: expose RCS topology to userspace
URL : https://patchwork.freedesktop.org/series/35519/
State : warning
== Summary ==
Series 35519v1 drm/i915: expose RCS topology to userspace
https://patchwork.freedesktop.org/api/1.0/series/35519/revisions/1/mbox/
Test
On 18/12/17 12:02, Tvrtko Ursulin wrote:
From: Tvrtko Ursulin
Instead of hard-coding the order of key-value pairs into regular
expressions, auto-detect them as we go.
At the same time re-factor the code so it is smaller and even
slightly faster (10-15% by a quick
We dump device flags in few places (init_early, debugfs, gpu_error)
using different functions. Lets add reusable function to avoid
code duplication.
add/remove: 1/0 grow/shrink: 0/3 up/down: 1296/-3572 (-2276)
Function old new delta
We dump modparams in few places (debugfs, gpu_error) using different
functions. Lets add reusable function to avoid code duplication.
add/remove: 1/0 grow/shrink: 0/2 up/down: 1096/-2339 (-1243)
Function old new delta
i915_params_dump
== Series Details ==
Series: drm/i915: improve tracepoints for process/hw_id tracking (rev2)
URL : https://patchwork.freedesktop.org/series/35506/
State : success
== Summary ==
Series 35506v2 drm/i915: improve tracepoints for process/hw_id tracking
Quoting Lionel Landwerlin (2017-12-18 15:35:18)
> This might be useful information for developers looking at an error
> state.
>
> Signed-off-by: Lionel Landwerlin
> ---
> drivers/gpu/drm/i915/i915_gpu_error.c | 35
> +++
> 1 file
Signed-off-by: Lionel Landwerlin
---
tests/Makefile.sources | 1 +
tests/meson.build | 1 +
tests/query.c | 262 +
3 files changed, 264 insertions(+)
create mode 100644 tests/query.c
diff --git
There are a number of information that are readable from hardware
registers and that we would like to make accessible to userspace. One
particular example is the topology of the execution units (how are
execution units grouped in subslices and slices and also which ones
have been fused off for die
This might be useful information for developers looking at an error
state.
Signed-off-by: Lionel Landwerlin
---
drivers/gpu/drm/i915/i915_gpu_error.c | 35 +++
1 file changed, 35 insertions(+)
diff --git
With the introduction of asymetric slices in CNL, we cannot rely on
the previous SUBSLICE_MASK getparam to tell userspace what subslices
are available. Here we introduce a more detailed way of querying the
Gen's GPU topology that doesn't aggregate numbers.
This is essential for monitoring parts
While the end goal is to make this information available to userspace
through a new ioctl, there is no reason we can't display it in a human
readable fashion through debugfs.
slice0 (subslice_mask=0x7):
subslice0:
eu_mask: 0xff (8)
subslice1:
Now that we have that information in topology fields, let's just reused it.
Signed-off-by: Lionel Landwerlin
---
drivers/gpu/drm/i915/i915_debugfs.c | 26 ++
1 file changed, 10 insertions(+), 16 deletions(-)
diff --git
Hi all,
This series a respin of a few attempts ([1], [2], [3]) to expose RCS
topology to userspace.
The motivation for this is to be able to monitor part of the GPU using
i915 perf and have detailled knowledge about what execution units are
fused off. Let's say you monitor slice 1, knowing how
Up to now, subslice mask was assumed to be uniform across slices. But
starting with Cannonlake, slices can be asymetric (for example slice0
has different number of subslices as slice1+). This change stores all
subslices masks for all slices rather than having a single mask that
applies to all
Quoting Lionel Landwerlin (2017-12-18 15:19:59)
> When monitoring the GPU with i915 perf, reports are tagged with a hw
> id. Gem context creation tracepoints already have a hw_id field,
> unfortunately you only get this correlation between a process id and a
> hw context id once when the context
Hey,
I did miss a tracepoint in patch 2. Fixed!
Cheers,
Lionel Landwerlin (2):
drm/i915: reorder field in gem_request tracepoints
drm/i915/trace: add hw_id to gem requests trace points
drivers/gpu/drm/i915/i915_trace.h | 40 +++
1 file changed, 24
When monitoring the GPU with i915 perf, reports are tagged with a hw
id. Gem context creation tracepoints already have a hw_id field,
unfortunately you only get this correlation between a process id and a
hw context id once when the context is created. It doesn't help if you
started monitoring
Let's make the order of the fields of the tracepoints involving gem
request match across i915. This makes userspace processing of
tracepoint a bit easier.
Suggested-by: Chris Wilson
Signed-off-by: Lionel Landwerlin
Reviewed-by: Chris
== Series Details ==
Series: intel_vbt_decode: Typo fixes
URL : https://patchwork.freedesktop.org/series/35441/
State : failure
== Summary ==
IGT patchset tested on top of latest successful build
c0be3310715e2f744b892c51f09e62273bcc8e57 tests/kms_frontbuffer_tracking:
Correctly handle
On 18/12/17 13:35, Chris Wilson wrote:
Quoting Lionel Landwerlin (2017-12-18 12:12:48)
When monitoring the GPU with i915 perf, reports are tagged with a hw
id. Gem context creation tracepoints already have a hw_id field,
unfortunately you only get this correlation between a process id and a
hw
== Series Details ==
Series: scripts/trace.pl: Auto-detect tracepoint field order
URL : https://patchwork.freedesktop.org/series/35504/
State : success
== Summary ==
IGT patchset tested on top of latest successful build
c0be3310715e2f744b892c51f09e62273bcc8e57 tests/kms_frontbuffer_tracking:
Quoting Lionel Landwerlin (2017-12-18 12:12:48)
> When monitoring the GPU with i915 perf, reports are tagged with a hw
> id. Gem context creation tracepoints already have a hw_id field,
> unfortunately you only get this correlation between a process id and a
> hw context id once when the context
Quoting Lionel Landwerlin (2017-12-18 12:12:47)
> Let's make the order of the fields of the tracepoints involving gem
> request match across i915. This makes userspace processing of
> tracepoint a bit easier.
>
> Suggested-by: Chris Wilson
> Signed-off-by: Lionel
== Series Details ==
Series: intel_vbt_decode: Typo fixes
URL : https://patchwork.freedesktop.org/series/35441/
State : warning
== Summary ==
IGT patchset tested on top of latest successful build
c0be3310715e2f744b892c51f09e62273bcc8e57 tests/kms_frontbuffer_tracking:
Correctly handle
Quoting Tvrtko Ursulin (2017-12-18 12:58:51)
>
> On 18/12/2017 12:39, Chris Wilson wrote:
> > A useful bit of information for inspecting GPU stalls from
> > intel_engine_dump() are the error registers, IPEIR and IPEHR.
> >
> > v2: Fixup gen changes in register offsets (Tvrtko)
> > v3: Old FADDR
On 15/12/2017 14:48, Chris Wilson wrote:
We want to exclude any GGTT objects from being present on our internal
lists to avoid the deadlock we may run into with our requirement for
struct_mutex during invalidate. However, if the gup_fast fails, we put
the userptr onto the workqueue and mark it
== Series Details ==
Series: series starting with [1/3] drm/i915: Re-enable GGTT earlier after GPU
reset (rev4)
URL : https://patchwork.freedesktop.org/series/35471/
State : failure
== Summary ==
Series 35471v4 series starting with [1/3] drm/i915: Re-enable GGTT earlier
after GPU reset
> -Original Message-
> From: Nikula, Jani
> Sent: Monday, December 18, 2017 6:21 PM
> To: Chauhan, Madhav ; intel-
> g...@lists.freedesktop.org
> Cc: Daniel Vetter
> Subject: RE: [Intel-gfx] [PATCH 4/4] drm/i915: push shared dpll enable to
On 18/12/2017 12:39, Chris Wilson wrote:
A useful bit of information for inspecting GPU stalls from
intel_engine_dump() are the error registers, IPEIR and IPEHR.
v2: Fixup gen changes in register offsets (Tvrtko)
v3: Old FADDR location as well
v4: Use I915_READ64_2x32
Signed-off-by: Chris
== Series Details ==
Series: drm/i915: improve tracepoints for process/hw_id tracking
URL : https://patchwork.freedesktop.org/series/35506/
State : success
== Summary ==
Series 35506v1 drm/i915: improve tracepoints for process/hw_id tracking
On Mon, 18 Dec 2017, "Chauhan, Madhav" wrote:
>> -Original Message-
>> From: Intel-gfx [mailto:intel-gfx-boun...@lists.freedesktop.org] On Behalf Of
>> Jani Nikula
>> Sent: Thursday, October 12, 2017 9:36 PM
>> To: intel-gfx@lists.freedesktop.org
>> Cc: Nikula,
A useful bit of information for inspecting GPU stalls from
intel_engine_dump() are the error registers, IPEIR and IPEHR.
v2: Fixup gen changes in register offsets (Tvrtko)
v3: Old FADDR location as well
v4: Use I915_READ64_2x32
Signed-off-by: Chris Wilson
Cc: Mika
Quoting Tvrtko Ursulin (2017-12-18 12:32:37)
>
> On 18/12/2017 12:17, Chris Wilson wrote:
> > A useful bit of information for inspecting GPU stalls from
> > intel_engine_dump() are the error registers, IPEIR and IPEHR.
> >
> > v2: Fixup gen changes in register offsets (Tvrtko)
> > v3: Old FADDR
On 18/12/2017 12:17, Chris Wilson wrote:
A useful bit of information for inspecting GPU stalls from
intel_engine_dump() are the error registers, IPEIR and IPEHR.
v2: Fixup gen changes in register offsets (Tvrtko)
v3: Old FADDR location as well
Signed-off-by: Chris Wilson
> -Original Message-
> From: Intel-gfx [mailto:intel-gfx-boun...@lists.freedesktop.org] On Behalf Of
> Jani Nikula
> Sent: Thursday, October 12, 2017 9:36 PM
> To: intel-gfx@lists.freedesktop.org
> Cc: Nikula, Jani ; Daniel Vetter
>
>
A useful bit of information for inspecting GPU stalls from
intel_engine_dump() are the error registers, IPEIR and IPEHR.
v2: Fixup gen changes in register offsets (Tvrtko)
v3: Old FADDR location as well
Signed-off-by: Chris Wilson
Cc: Mika Kuoppala
Hi,
These are just a couple of changes to allow process/hw_id correlation
when using i915 perf to monitor the workloads on the GPU.
Cheers,
Lionel Landwerlin (2):
drm/i915: reorder field in gem_request tracepoints
drm/i915/trace: add hw_id to gem requests trace points
When monitoring the GPU with i915 perf, reports are tagged with a hw
id. Gem context creation tracepoints already have a hw_id field,
unfortunately you only get this correlation between a process id and a
hw context id once when the context is created. It doesn't help if you
started monitoring
Let's make the order of the fields of the tracepoints involving gem
request match across i915. This makes userspace processing of
tracepoint a bit easier.
Suggested-by: Chris Wilson
Signed-off-by: Lionel Landwerlin
---
On 18/12/2017 11:26, Chris Wilson wrote:
A useful bit of information for inspecting GPU stalls from
intel_engine_dump() are the error registers, IPEIR and IPEHR.
v2: Fixup gen changes in register offsets (Tvrtko)
Signed-off-by: Chris Wilson
Cc: Mika Kuoppala
1 - 100 of 131 matches
Mail list logo