This WA is required when decopled frequencies for slice
and unslice are enabled. This disables DOP clock gating
for SKL GT4.
Cc: David Weinehall
Signed-off-by: Praveen Paneri
---
drivers/gpu/drm/i915/intel_pm.c | 6 ++
1 file
Up until recently sync_file were create to export a single dma-fence to
userspace, and so we could canabalise a bit insie dma-fence to mark
whether or not we had enable polling for the sync_file itself. However,
with the advent of syncobj, we do allow userspace to create multiple
sync_files for a
On Mon, 24 Jul 2017 09:57:46 +0530
Vidya Srinivas wrote:
> From: Chandra Konduru
>
> This patch updates scaler max limit support for NV12
>
> v2: Rebased (me)
>
> v3: Rebased (me)
>
> v4: Missed the Tested-by/Reviewed-by in the previous
Some fixed resolution panels actually support more than one mode,
with the only thing different being the refresh rate. Having this
alternate mode available to us is desirable, because it allows us to
test PSR on panels whose setup time at the preferred mode is too long.
With this patch we allow
v2: Add tests regarding removing configs (Matthew)
Add tests regarding adding/removing configs without permissions
(Matthew)
v3: Add some flex registers (Matthew)
v4: memset oa_config to 0 (Lionel)
Change error code for removing unexisting config EINVAL->ENOENT (Lionel)
v5: Update
The motivation behind this new interface is expose at runtime the
creation of new OA configs which can be used as part of the i915 perf
open interface. This will enable the kernel to learn new configs which
may be experimental, or otherwise not part of the core set currently
available through the
It makes things easier to read to implement whitelisting in the
following patches.
Signed-off-by: Lionel Landwerlin
---
drivers/gpu/drm/i915/i915_reg.h | 212
1 file changed, 106 insertions(+), 106 deletions(-)
diff --git
We already do it on Haswell and the documentation says it saves power.
Signed-off-by: Lionel Landwerlin
---
drivers/gpu/drm/i915/i915_perf.c | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
There will be a need for userspaces configurations to set this
register. We can apply the same model inside the kernel for test
configs.
Signed-off-by: Lionel Landwerlin
---
drivers/gpu/drm/i915/i915_oa_bdw.c| 2 ++
drivers/gpu/drm/i915/i915_oa_bxt.c| 1 +
Hi,
Here is a v8 with some more changes following Andrzej's comment on
whitelisted registers. I've also added some documentation.
Cheers,
Lionel Landwerlin (6):
drm/i915/perf: fix flex eu registers programming
drm/i915/perf: prune OA configs
drm/i915/perf: leave GDT_CHICKEN_BITS
We were reserving fewer dwords in the ring than necessary. Indeed
we're always writing all registers once, so discard the actual number
of registers given by the user and just program the whitelisted ones
once.
Fixes: 19f81df2859e ("drm/i915/perf: Add OA unit support for Gen 8+")
Reported-by:
On Tue, Jul 25, 2017 at 10:01:19AM +0200, Daniel Vetter wrote:
> It's dead code, the core handles all this directly now. This also
> allows us to unexport drm_atomic_helper_plane_set_property.
>
> Signed-off-by: Daniel Vetter
> Cc: Liviu Dudau
> Cc:
On Fri, Jul 28, 2017 at 02:50:30PM +0100, Chris Wilson wrote:
> Quoting Michał Winiarski (2017-07-28 14:36:46)
> > On Fri, Jul 28, 2017 at 01:08:08PM +0100, Chris Wilson wrote:
> > > Signed-off-by: Chris Wilson
> > > ---
> > > tests/gem_eio.c | 2 +-
> > > 1 file
Quoting Michał Winiarski (2017-07-28 14:53:40)
> On Fri, Jul 28, 2017 at 01:08:03PM +0100, Chris Wilson wrote:
> > If we tell the machine to reset but they are disallowed, we will leave
> > the system in a wedged state, preventing the majority of subsequent
> > tests.
> > ---
> >
Quoting Michał Winiarski (2017-07-28 14:53:40)
> On Fri, Jul 28, 2017 at 01:08:03PM +0100, Chris Wilson wrote:
> > If we tell the machine to reset but they are disallowed, we will leave
> > the system in a wedged state, preventing the majority of subsequent
> > tests.
> > ---
> >
On Fri, Jul 28, 2017 at 01:08:03PM +0100, Chris Wilson wrote:
> If we tell the machine to reset but they are disallowed, we will leave
> the system in a wedged state, preventing the majority of subsequent
> tests.
> ---
> tests/drv_hangman.c | 3 +++
> 1 file changed, 3 insertions(+)
Missed
Quoting Michał Winiarski (2017-07-28 14:36:46)
> On Fri, Jul 28, 2017 at 01:08:08PM +0100, Chris Wilson wrote:
> > Signed-off-by: Chris Wilson
> > ---
> > tests/gem_eio.c | 2 +-
> > 1 file changed, 1 insertion(+), 1 deletion(-)
> >
> > diff --git a/tests/gem_eio.c
Quoting Matthew Auld (2017-07-25 20:21:23)
> Support inserting 1G gtt pages into the 48b PPGTT.
>
> v2: sanity check sg->length against page_size
>
> Signed-off-by: Matthew Auld
> Cc: Joonas Lahtinen
> Cc: Chris Wilson
On Fri, Jul 28, 2017 at 01:08:08PM +0100, Chris Wilson wrote:
> Signed-off-by: Chris Wilson
> ---
> tests/gem_eio.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/tests/gem_eio.c b/tests/gem_eio.c
> index 3c826626..15120842 100644
> ---
On Tue, Jul 25, 2017 at 08:21:13PM +0100, Matthew Auld wrote:
> We are planning to use our own tmpfs mnt in i915 in place of the
> shm_mnt, such that we can control the mount options, in particular
> huge=, which we require to support huge-gtt-pages. So rather than roll
> our own version of
mtime is when the file contents last changed, ctime when attributes in
the inode last changed. We want the former. For some reason ctime in
my rr-cache is always very recent.
Signed-off-by: Daniel Vetter
---
dim | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
When grabbing reference CRC with igt_pipe_crc_get_crcs() the number of
words in igt_crc_t structure was incorrectly collected. The fix here is
to switch to igt_pipe_crc_collect_crc() function when collecting CRC for
reference frame.
The problem was caught by CI system and at least affects on HSW
On Fri, Jul 28, 2017 at 01:08:07PM +0100, Chris Wilson wrote:
> After triggering an error (such as trying to use userptr on a GTT
> mmaping), we store the EFAULT on the object permanently. So to test the
> error, we must sacrifice the object and recreate the userptr handle.
> We restrict the error
Just a small variant to apply a continuous context-switch load to all
engines.
---
tests/gem_ctx_switch.c | 80 ++
1 file changed, 80 insertions(+)
diff --git a/tests/gem_ctx_switch.c b/tests/gem_ctx_switch.c
index b6ea71cf..df22efec 100644
---
After triggering an error (such as trying to use userptr on a GTT
mmaping), we store the EFAULT on the object permanently. So to test the
error, we must sacrifice the object and recreate the userptr handle.
We restrict the error to just one of the overlapping userptr handles to
check the object
gdb uses ptrace() to peek and poke bytes of the target's address space.
The kernel must implement an vm_ops->access() handler or else gdb will
be unable to inspect the pointer and report it as out-of-bounds. Worse
than useless as it causes immediate suspicion of the valid GTT pointer.
Ensure that we can suspend the GPU even if it is currently busy in an
indefinite loop, requiring us to declare the task hung.
---
tests/gem_exec_suspend.c | 19 +++
1 file changed, 19 insertions(+)
diff --git a/tests/gem_exec_suspend.c b/tests/gem_exec_suspend.c
index
If we tell the machine to reset but they are disallowed, we will leave
the system in a wedged state, preventing the majority of subsequent
tests.
---
tests/drv_hangman.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/tests/drv_hangman.c b/tests/drv_hangman.c
index 0551ec16..de57e128
Execute the same batch on each engine and check that the composite fence
across all engines completes only after the batch is completed on every
engine.
Signed-off-by: Chris Wilson
---
tests/gem_exec_fence.c | 120 +
1
Signed-off-by: Chris Wilson
---
tests/gem_eio.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tests/gem_eio.c b/tests/gem_eio.c
index 3c826626..15120842 100644
--- a/tests/gem_eio.c
+++ b/tests/gem_eio.c
@@ -53,7 +53,7 @@ static bool
Apply a little more stress to the scheduler.
---
lib/igt_rand.h| 6 +++
tests/gem_exec_schedule.c | 108 +-
2 files changed, 113 insertions(+), 1 deletion(-)
diff --git a/lib/igt_rand.h b/lib/igt_rand.h
index f664af41..c9cb3243 100644
---
The idea is to implement read(dmabuf) and write(dambuf) so provide some
tests.
Signed-off-by: Chris Wilson
---
tests/Makefile.sources | 1 +
tests/prime_rw.c | 179 +
2 files changed, 180 insertions(+)
create
Make sure that our buffers are ready and loaded to reduce the initial
stall.
---
tests/gem_ringfill.c | 10 --
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/tests/gem_ringfill.c b/tests/gem_ringfill.c
index b52996a4..01cbd0a9 100644
--- a/tests/gem_ringfill.c
+++
Ping on the core MM folks.
We'd need either an ack or nack on this one to proceed with the huge
page work for i915.
Regards, Joonas
On ti, 2017-07-25 at 20:21 +0100, Matthew Auld wrote:
> We are planning to use our own tmpfs mnt in i915 in place of the
> shm_mnt, such that we can control the
The purpose of the test was to check per-engine resets would fallback to
the global reset when required, but first we actually need a test for a
basic i915_handle_error()!
Cc: Mika Kuoppala
Cc: Michel Thierry
Signed-off-by: Chris Wilson
Quoting Tvrtko Ursulin (2017-07-27 10:05:03)
> From: Tvrtko Ursulin
>
> Drivers like i915 benefit from being able to control the maxium
> size of the sg coallesced segment while building the scatter-
> gather list.
>
> Introduce and export the
Quoting Tvrtko Ursulin (2017-07-27 10:05:04)
> From: Tvrtko Ursulin
>
> With the addition of __sg_alloc_table_from_pages we can control
> the maximum coallescing size and eliminate a separate path for
> allocating backing store here.
>
> Similar to 871dfbd67d4e
Quoting Tvrtko Ursulin (2017-07-27 10:05:02)
> From: Tvrtko Ursulin
>
> Since the scatterlist length field is an unsigned int, make
> sure that sg_alloc_table_from_pages does not overflow it while
> coallescing pages to a single entry.
>
> v2: Drop reference to future
Quoting Daniel Vetter (2017-07-28 10:28:05)
> On Fri, Jul 28, 2017 at 09:50:22AM +0100, Chris Wilson wrote:
> > If we fail at punit communication, include both the mbox address and the
> > value we tried to write so that we can identify the invalid sequence.
> >
> > Signed-off-by: Chris Wilson
Quoting Chris Wilson (2017-07-27 17:24:20)
> Quoting Daniel Vetter (2017-07-27 15:36:49)
> > On Mon, Jul 24, 2017 at 11:14:13AM +0100, Chris Wilson wrote:
> > > The CI farm reports that trying to write to the PCI config (GDRST: 0xc0)
> > > results in an immediate and silent reboot on Grantsdale
On Thu, Jul 06, 2017 at 09:24:50PM +0200, Hans de Goede wrote:
> intel_uncore_forcewake_reset() does forcewake puts and gets as such
> we need to make sure that no-one tries to access the PUNIT->PMIC bus
> (on systems where this bus is shared) while it runs, otherwise bad
> things happen.
>
>
On Fri, Jul 28, 2017 at 09:50:22AM +0100, Chris Wilson wrote:
> If we fail at punit communication, include both the mbox address and the
> value we tried to write so that we can identify the invalid sequence.
>
> Signed-off-by: Chris Wilson
> Cc: Daniel Vetter
== Series Details ==
Series: drm/i915: Include mbox details for pcode read/write failures
URL : https://patchwork.freedesktop.org/series/28030/
State : success
== Summary ==
Series 28030v1 drm/i915: Include mbox details for pcode read/write failures
If we fail at punit communication, include both the mbox address and the
value we tried to write so that we can identify the invalid sequence.
Signed-off-by: Chris Wilson
Cc: Daniel Vetter
---
drivers/gpu/drm/i915/intel_pm.c | 21
Hi,
> +/**
> + * VFIO_DEVICE_QUERY_GFX_PLANE - _IOW(VFIO_TYPE, VFIO_BASE + 14,
> struct vfio_device_query_gfx_plane)
> + *
> + * Set the drm_plane_type and retrieve information about the gfx
> plane.
+ *
> + * Return: 0 on success, -errno on failure.
I think this should be more verbose,
Op 27-07-17 om 17:30 schreef Daniel Vetter:
> On Thu, Jul 27, 2017 at 03:45:11PM +0100, Emil Velikov wrote:
>> Hi Maarten
>>
>> On 27 July 2017 at 13:58, Maarten Lankhorst
>> wrote:
>>> drm_atomic_commit could previous have always failed when waits failed,
>>>
46 matches
Mail list logo