Quoting Joonas Lahtinen (2017-11-27 11:18:55)
> On Sun, 2017-11-26 at 21:48 +, Chris Wilson wrote:
> > Even though all rendering should have been flushed at the end of the
> > previous requests, add an extra flush after switching to the
> > kernel_context. As the switch to the kernel_context
Thanks for the email. It has been refined recently, the code can be found here:
https://cgit.freedesktop.org/drm-intel/tree/drivers/gpu/drm/i915/gvt/cmd_parser.c
Thanks for the notification, again. :)
-Original Message-
From: David Binderman [mailto:dcb...@hotmail.com]
Sent: Monday,
A new context assumes that all of its registers are in the default state
when it is created. What may happen is that a register written by one
context may leak into the second, causing mass confusion.
v2: Extend back to Sandybridge (etc)
v3: Check context preserves registers across
Gabriel Krisman Bertazi writes:
> Hi,
>
> This is a new version of the series with the updates requested by
> reviewers. It fixes the KBL issue pointed out by Arkadiusz, adds a test
> for pitches[1] mentioned by Ville and does some other improvements.
>
> It does not
Building i915 without backlight support results in a harmless warning
for intel_panel_set_backlight:
drivers/gpu/drm/i915/intel_panel.c:653:13: error: 'intel_panel_set_backlight'
defined but not used [-Werror=unused-function]
This moves it into the CONFIG_BACKLIGHT_CLASS_DEVICE section that
its
== Series Details ==
Series: series starting with [v4] drm/i915: Expose the busyspin durations for
i915_wait_request (rev2)
URL : https://patchwork.freedesktop.org/series/34404/
State : failure
== Summary ==
Test kms_frontbuffer_tracking:
Subgroup
On 24.11.2017 17:17, Arkadiusz Hiler wrote:
This patch gets rid of the Android support, deleting all the hacks and
moving code around to the places it belongs.
Android build is not really maintained properly and rots rather fast.
With recent push for Meson here and Android going for Soong it
> -Original Message-
> From: Joonas Lahtinen [mailto:joonas.lahti...@linux.intel.com]
> Sent: Monday, November 27, 2017 11:13 AM
> To: Intel graphics driver community testing & development g...@lists.freedesktop.org>
> Cc: Joonas Lahtinen ; Auld, Matthew
>
Quoting Joonas Lahtinen (2017-11-27 12:02:03)
> On Sun, 2017-11-26 at 22:09 +, Chris Wilson wrote:
> > It may be of interest to both compare the active HW context against the
> > default (or NULL) context, to see what has been changed and if either are
> > corrupt.
> >
> > Signed-off-by:
The kerneldoc markup for i915_gem_timelines_mark_idle() was incorrect,
so take the opportunity to also convert it from the "mark_idle" to "park"
naming scheme.
drivers/gpu/drm/i915/i915_gem_timeline.c:120: warning: No description found for
parameter 'i915'
Signed-off-by: Chris Wilson
On Sun, 2017-11-26 at 22:09 +, Chris Wilson wrote:
> It may be of interest to both compare the active HW context against the
> default (or NULL) context, to see what has been changed and if either are
> corrupt.
>
> Signed-off-by: Chris Wilson
> Cc: Mika Kuoppala
On Mon, 2017-11-27 at 12:30 +, Chris Wilson wrote:
> The kerneldoc markup for i915_gem_timelines_mark_idle() was incorrect,
> so take the opportunity to also convert it from the "mark_idle" to "park"
> naming scheme.
>
> drivers/gpu/drm/i915/i915_gem_timeline.c:120: warning: No description
== Series Details ==
Series: igt/gem_ctx_isolation: Check isolation of registers between contexts
(rev8)
URL : https://patchwork.freedesktop.org/series/32531/
State : success
== Summary ==
Test kms_flip:
Subgroup vblank-vs-dpms-suspend:
notrun -> INCOMPLETE
Hey all,
For some time already CI sends out 1-2 mails per series per (re)run, i.e. BAT
results and "full IGT" results (if BAT has not failed).
Recently we have added 32bit build check, and if that fails it sends out
additional mail In-Reply-To the series.
I am working on adding some static
The alternative intel_backlight_device_register() definition apparently
never got used, but I have now run into a case of i915 being compiled
without CONFIG_BACKLIGHT_CLASS_DEVICE, resulting in a number of
identical warnings:
drivers/gpu/drm/i915/intel_drv.h:1739:12: error:
== Series Details ==
Series: igt/gem_ctx_isolation: Check isolation of registers between contexts
(rev8)
URL : https://patchwork.freedesktop.org/series/32531/
State : success
== Summary ==
IGT patchset tested on top of latest successful build
4c57ff468fa4870184b3da56432602f967af
On Thu, 2017-11-23 at 11:53 +, Chris Wilson wrote:
> Switch over from the non-descript dev_priv locals to i915.
>
> Signed-off-by: Chris Wilson
> Cc: Joonas Lahtinen
It's very much its own island of code anyway.
Reviewed-by:
On 27/11/2017 11:02, Chris Wilson wrote:
We have chosen batch_duration_ns to be the minimum duration we need to
meet our accuracy requirements for legacy ringbuffer PMU sampling. As
such, we need to be careful to use multiples of it during tests, and not
split it into different phases with a
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Add domain parameter
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Hard-code the domain
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Domain number is not
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Replace
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
We don't search for
Deprecate pci_get_bus_and_slot() in favor of pci_get_domain_bus_and_slot()
in order to remove domain 0 assumptions in the kernel.
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Extract the domain
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Use pci_get_domain_bus_and_slot() with a domain number of 0 where we can't
extract the domain number. Other places, use
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Use domain number of 0
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Use
== Series Details ==
Series: drm/i915: Rename i915_gem_timelines_mark_idle
URL : https://patchwork.freedesktop.org/series/34457/
State : failure
== Summary ==
Series 34457 revision 1 was fully merged or fully failed: no git log
___
Intel-gfx
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Introduce
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Use the domain
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Extract the domain
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Hard-coding the domain
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Use pci_get_domain_bus_and_slot() with a domain number of 0 where we can't
extract the domain number. Other places, use
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Hard-coding the domain
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Use
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Hard-coding the domain
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Hard-coding the domain
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Replace
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Hard-code the domain
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Replace
Remove unused rtsx_read_pci_cfg_byte() function.
Signed-off-by: Sinan Kaya
---
drivers/staging/rts5208/rtsx.c | 17 -
drivers/staging/rts5208/rtsx.h | 2 --
2 files changed, 19 deletions(-)
diff --git a/drivers/staging/rts5208/rtsx.c
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function. Since ISP always
uses domain 0, hard-code it in the code when
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Hard-coding the domain
I feel we generally tend to ignore the results mails for series that we are not
actively involved on (although we might be
interested in series itself). Also if number of revisions some series can
undergo is high, this tendency can grow.
How about the option of sending the results mails to
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
struct riva_par has a
i7300_idle.h is not being called by any source file and contains calls to
pci_get_bus_and_slot() that we are trying to deprecate. Remove unused file.
Signed-off-by: Sinan Kaya
---
include/linux/i7300_idle.h | 84 --
1 file
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Now that all users of pci_get_bus_and_slot() switched to
pci_get_domain_bus_and_slot(), it is now safe to remove this
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
struct nvidia_par has
pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
where a PCI device is present. This restricts the device drivers to be
reused for other domain numbers.
Getting ready to remove pci_get_bus_and_slot() function in favor of
pci_get_domain_bus_and_slot().
Find the domain number
== Series Details ==
Series: series starting with [1/2] drm/i915: fix
intel_backlight_device_register declaration
URL : https://patchwork.freedesktop.org/series/34467/
State : failure
== Summary ==
Series 34467 revision 1 was fully merged or fully failed: no git log
We currently have two module parameters that control GuC:
"enable_guc_loading" and "enable_guc_submission". Whenever
we need submission=1, we also need loading=1.We also need
loading=1 when we want to want to verify the HuC, which
is every time we have a HuC (but all platforms with HuC
have a GuC
The aim of this series is to remove the enable_guc_loading and
enable_guc_submission module parameters. They are being replaced
by a common, newly defined enable_guc module parameter.
This series has been split from a bigger series that has previously
been sent to this mailing list.
Cc: Daniele
Updating GuC and HuC firmware select function to support removing
i915_modparams.enable_guc_loading module parameter.
v2: Clarifying the commit message (Anusha)
v3: Unify seq_puts messages, Re-factoring code as per review (Michal)
v4: Rebase
v5: Separating message unification into a separate
On Mon, Nov 27, 2017 at 08:16:15AM +, Valtteri Rantala wrote:
> Testing the texture read performance shows that the same tuning for
> the SQ credits is needed on GLK as on BXT/APL. This has been also
> confirmed by Altug from the HW team.
>
> V3: Rebase + fix
> Signed-off-by: Valtteri Rantala
+dri-de...@lists.freedesktop.org
On 11/27/2017 11:57 AM, Sinan Kaya wrote:
> pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
> where a PCI device is present. This restricts the device drivers to be
> reused for other domain numbers.
>
> Getting ready to remove
+dri-de...@lists.freedesktop.org
On 11/27/2017 11:57 AM, Sinan Kaya wrote:
> pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
> where a PCI device is present. This restricts the device drivers to be
> reused for other domain numbers.
>
> Getting ready to remove
On Mon, Nov 27, 2017 at 11:57:41AM -0500, Sinan Kaya wrote:
> pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
> where a PCI device is present. This restricts the device drivers to be
> reused for other domain numbers.
>
> Getting ready to remove pci_get_bus_and_slot()
On Mon, Nov 27, 2017 at 02:54:02PM +, Arkadiusz Hiler wrote:
> Hey all,
>
> For some time already CI sends out 1-2 mails per series per (re)run, i.e. BAT
> results and "full IGT" results (if BAT has not failed).
>
> Recently we have added 32bit build check, and if that fails it sends out
>
Hi Ben, Kyle,
Please consider pulling i915 updates to linux-firmware.git.
i915-firmware-2017-11-27
The following changes since commit 17e6288135d4500f9fe60224dce2b46d850c346b:
brcm: update firmware for bcm4358 (2017-11-25 10:15:53 -0500)
are available in the git repository at:
On Thu, Nov 23, 2017 at 7:21 AM, Ville Syrjälä
wrote:
> On Wed, Nov 22, 2017 at 10:55:14AM -0800, Lucas De Marchi wrote:
>> WA Display #1178 is meant to fix Aux channel voltage swing too low with
>> some type C dongles. Although it is for type C, HW engineers
This is just a very plain stress test that doesn't do any verification,
and is entirely duplicated by the other context tests. The test
currently leaks objects from every thread on every pass, while fixing it
would be trivial, it also is pointless as the test is of little merit.
Signed-off-by:
We have chosen batch_duration_ns to be the minimum duration we need to
meet our accuracy requirements for legacy ringbuffer PMU sampling. As
such, we need to be careful to use multiples of it during tests, and not
split it into different phases with a test, like multi_client does.
Signed-off-by:
== Series Details ==
Series: drm/i915: Enable hotplug polling after registering the outputs
URL : https://patchwork.freedesktop.org/series/34445/
State : success
== Summary ==
Test kms_flip:
Subgroup flip-vs-expired-vblank-interruptible:
fail -> PASS
On Sun, 2017-11-26 at 21:48 +, Chris Wilson wrote:
> Even though all rendering should have been flushed at the end of the
> previous requests, add an extra flush after switching to the
> kernel_context. As the switch to the kernel_context is used when idling
> the gpu (e.g. suspend), having an
== Series Details ==
Series: igt/perf_pmu: Keep batch_duration_ns as the minimum measurement duration
URL : https://patchwork.freedesktop.org/series/34450/
State : warning
== Summary ==
IGT patchset tested on top of latest successful build
4c57ff468fa4870184b3da56432602f967af intel/pmu:
Bunch of neat improvements:
- xml generates correctly depend upon the test binaries
- no need to re-run autogen.sh when new chapters/functions get added,
all handed by meson
Still one issue:
- the gtkdoc target doesn't depend upon the custom_target yet, hacked
around using build_by_default:
On Sat, 2017-11-25 at 00:48 +0100, Thomas Gleixner wrote:
> On Fri, 24 Nov 2017, Matthew Auld wrote:
>
> > From: Joonas Lahtinen
>
> Please CC the linux kernel mailinglist on patches related to x86. The
> MAINTAINERS file says:
>
> X86 ARCHITECTURE (32-BIT AND
== Series Details ==
Series: series starting with [1/4] lib: avoid < in gtkdoc comments (rev3)
URL : https://patchwork.freedesktop.org/series/34413/
State : success
== Summary ==
IGT patchset tested on top of latest successful build
4c57ff468fa4870184b3da56432602f967af intel/pmu: Catch-up
== Series Details ==
Series: drm/i915/glk: Apply WaProgramL3SqcReg1DefaultForPerf for GLK too (rev3)
URL : https://patchwork.freedesktop.org/series/33772/
State : failure
== Summary ==
CHK include/config/kernel.release
CHK include/generated/uapi/linux/version.h
CHK
On 26/11/2017 19:42, Daniel Vetter wrote:
Helps with making it compile everywhere. This fixes:
commit db31e3c1ca0953b6e6832c25060acd01012a66dd
Author: Tvrtko Ursulin
Date: Wed Nov 8 12:06:52 2017 +
lib/core: Avoid unused result in backtrace printing
On Thu, 2017-11-23 at 11:53 +, Chris Wilson wrote:
> Since the shrinker is registered and unregistered during
> i915_driver_register and i915_driver_unregister, respectively, rename
> the init/cleanup functions to match.
>
> Signed-off-by: Chris Wilson
> Cc: Joonas
Testing the texture read performance shows that the same tuning for
the SQ credits is needed on GLK as on BXT/APL. This has been also
confirmed by Altug from the HW team.
V3: Rebase + fix
Signed-off-by: Valtteri Rantala
---
drivers/gpu/drm/i915/intel_engine_cs.c | 15
== Series Details ==
Series: series starting with [1/4] lib: avoid < in gtkdoc comments (rev3)
URL : https://patchwork.freedesktop.org/series/34413/
State : warning
== Summary ==
Test drv_module_reload:
Subgroup basic-no-display:
dmesg-warn -> PASS (shard-snb)
+nouv...@lists.freedesktop.org
On 11/27/2017 11:57 AM, Sinan Kaya wrote:
> pci_get_bus_and_slot() is restrictive such that it assumes domain=0 as
> where a PCI device is present. This restricts the device drivers to be
> reused for other domain numbers.
>
> Getting ready to remove
== Series Details ==
Series: drm/i915/guc : Removing GuC loading and submission modparams
URL : https://patchwork.freedesktop.org/series/34490/
State : failure
== Summary ==
Applying: drm/i915/guc : Removing enable_guc_loading and enable_guc_submission
module parameters
Patch failed at 0001
On Mon, Nov 27, 2017 at 08:20:26AM +, Patchwork wrote:
> == Series Details ==
>
> Series: drm/i915/glk: Apply WaProgramL3SqcReg1DefaultForPerf for GLK too
> (rev3)
> URL : https://patchwork.freedesktop.org/series/33772/
> State : failure
>
> == Summary ==
>
> CHK
>-Original Message-
>From: Jani Nikula [mailto:jani.nik...@linux.intel.com]
>Sent: Wednesday, November 22, 2017 11:15 PM
>To: Srivatsa, Anusha ; intel-
>g...@lists.freedesktop.org
>Cc: Srivatsa, Anusha ; Ville Syrjala
Forward Error Correction is supported on DP 1.4.
This patch adds corresponding DPCD register definitions.
v2: Add dri-devel to the CC list
Cc: dri-de...@lists.freedesktop.org
Cc: Ville Syrjala
Cc: Jani Nikula
Cc: Manasi Navare
Hello there,
linux-4.15-rc1/drivers/gpu/drm/i915/gvt/cmd_parser.c:1640]: (style) Checking if
unsigned variable 'bb_size' is less than zero.
Source code is
/* get the size of the batch buffer */
bb_size = find_bb_size(s);
if (bb_size < 0)
return -EINVAL;
but
static int
This looks okay to me.
Reviewed-by: Sinclair Yeh
On Thu, Nov 23, 2017 at 09:05:00PM +0200, Ville Syrjala wrote:
> From: Ville Syrjälä
>
> Use drm_mode_get_hv_timing() to fill out the plane clip rectangle.
>
> Note that this replaces
In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.
Addresses-Coverity-ID: 141432
Addresses-Coverity-ID: 141433
Addresses-Coverity-ID: 141434
Addresses-Coverity-ID: 141435
Addresses-Coverity-ID: 141436
Addresses-Coverity-ID: 1357360
== Series Details ==
Series: igt: Remove gem_ctx_basic
URL : https://patchwork.freedesktop.org/series/34500/
State : failure
== Summary ==
Series 34500 revision 1 was fully merged or fully failed: no git log
___
Intel-gfx mailing list
On Sun, 2017-11-26 at 20:40 -0800, Nick Desaulniers wrote:
> Do I need to be basing my patches on a different tree than Linus'? In
> general, how do people find what tree they should be basing their
> patch off of?
"T:" line from the MAINTAINERS entry would tell you that.
Regards, Joonas
--
== Series Details ==
Series: series starting with [v4] drm/i915: Expose the busyspin durations for
i915_wait_request (rev2)
URL : https://patchwork.freedesktop.org/series/34404/
State : success
== Summary ==
Series 34404v2 series starting with [v4] drm/i915: Expose the busyspin
durations
== Series Details ==
Series: drm/i915: Disable THP until we have a GPU read BW W/A
URL : https://patchwork.freedesktop.org/series/34441/
State : warning
== Summary ==
Test kms_flip:
Subgroup flip-vs-expired-vblank-interruptible:
fail -> PASS (shard-hsw)
Quoting Maarten Lankhorst (2017-11-27 10:18:46)
> Op 27-11-17 om 10:45 schreef Chris Wilson:
> > Previously we would enable hotplug polling on the outputs immediately
> > upon construction. This would allow a very early hotplug event to
> > trigger before we had finishing setting up the driver to
> -Original Message-
> From: daniel.vet...@ffwll.ch [mailto:daniel.vet...@ffwll.ch] On Behalf Of
> Daniel Vetter
> Sent: Monday, November 27, 2017 2:47 PM
> To: Srinivas, Vidya
> Cc: intel-gfx
> Subject: Re: [Intel-gfx] [PATCH
We seem to be missing some W/A for 2M pages and are getting
a hit on raw GPU read bandwidths (even 30%) even though the
GPU write bandwidths improve (even 10%).
For now, disable THP, which is our only practical source of
2M pages until we have a W/A for the issue.
v2:
- Be explicit that we talk
Somehow I forgot to send out my irc feedback to the m-l.
On Wed, Nov 22, 2017 at 9:15 AM, Vidya Srinivas
wrote:
> +igt_main
> {
> data_t data = {};
>
> @@ -308,11 +765,26 @@ igt_simple_main
> data.drm_fd = drm_open_driver(DRIVER_INTEL);
>
Quoting Sagar Arun Kamble (2017-11-27 07:20:01)
>
>
> On 11/26/2017 5:50 PM, Chris Wilson wrote:
> > An interesting discussion regarding "hybrid interrupt polling" for NVMe
> > came to the conclusion that the ideal busyspin before sleeping
>
> I think hybrid approach suggests sleep (1/2
On Fri, 2017-11-24 at 22:05 +, Chris Wilson wrote:
> Quoting Matthew Auld (2017-11-24 21:29:22)
> > From: Joonas Lahtinen
> >
> > In preparation for upcoming SKUs, allow more freedom in placement
> > of the Intel graphics stolen memory by BIOS to full 64bit
== Series Details ==
Series: drm/i915: Disable THP until we have a GPU read BW W/A
URL : https://patchwork.freedesktop.org/series/34441/
State : success
== Summary ==
Series 34441v1 drm/i915: Disable THP until we have a GPU read BW W/A
Previously we would enable hotplug polling on the outputs immediately
upon construction. This would allow a very early hotplug event to
trigger before we had finishing setting up the driver to handle it.
Instead, move the output polling to the last step of registration, after
we have set up all
An interesting discussion regarding "hybrid interrupt polling" for NVMe
came to the conclusion that the ideal busyspin before sleeping was half
of the expected request latency (and better if it was already halfway
through that request). This suggested that we too should look again at
our tradeoff
== Series Details ==
Series: drm/i915: Enable hotplug polling after registering the outputs
URL : https://patchwork.freedesktop.org/series/34445/
State : success
== Summary ==
Series 34445v1 drm/i915: Enable hotplug polling after registering the outputs
On Fri, 2017-11-24 at 11:21 +, Tvrtko Ursulin wrote:
> From: Tvrtko Ursulin
>
> Will be adding a new per-engine flags shortly so it makes sense
> to consolidate.
>
> Signed-off-by: Tvrtko Ursulin
> Suggested-by: Chris Wilson
Op 27-11-17 om 10:45 schreef Chris Wilson:
> Previously we would enable hotplug polling on the outputs immediately
> upon construction. This would allow a very early hotplug event to
> trigger before we had finishing setting up the driver to handle it.
> Instead, move the output polling to the
On Sun, Nov 26, 2017 at 07:49:14PM -0800, Nick Desaulniers wrote:
> Fixes the following enum conversion warning:
>
> drivers/gpu/drm/i915/intel_ddi.c:1481:30: error: implicit conversion
> from enumeration type 'enum port' to different enumeration type 'enum
> intel_dpll_id'
On Mon, Nov 27, 2017 at 2:26 AM, Joonas Lahtinen
wrote:
> On Sun, 2017-11-26 at 20:40 -0800, Nick Desaulniers wrote:
>> In
>> general, how do people find what tree they should be basing their
>> patch off of?
>
> "T:" line from the MAINTAINERS entry would tell you
1 - 100 of 102 matches
Mail list logo