From: Rob Clark
Combines duplicate vma lookup in the get_and_pin path.
Signed-off-by: Rob Clark
Reviewed-by: Dmitry Osipenko
---
drivers/gpu/drm/msm/msm_gem.c | 50 ++-
1 file changed, 26 insertions(+), 24 deletions(-)
diff --git a/drivers/gpu/drm/msm
From: Rob Clark
There was only a single user, which could just as easily stash the iova
when pinning.
v2: fix prepare->prepare->cleanup->cleanup sequences
Signed-off-by: Rob Clark
Reviewed-by: Dmitry Baryshkov
---
drivers/gpu/drm/msm/msm_fb.c | 20 ++--
drivers/gp
From: Rob Clark
Get rid of all the unnecessary conversion between address/size and page
offsets. It just confuses things.
Signed-off-by: Rob Clark
Reviewed-by: Dmitry Baryshkov
---
drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 2 +-
drivers/gpu/drm/msm/msm_gem.c | 5 ++---
drivers/gpu
From: Rob Clark
Prep for a following patch, where it gets a bit more complicated.
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/msm_gem.c | 2 +-
drivers/gpu/drm/msm/msm_gem.h | 1 +
drivers/gpu/drm/msm/msm_gem_vma.c | 9 +++--
3 files changed, 9 insertions(+), 3 deletions
From: Rob Clark
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/msm_gem_vma.c | 10 +-
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c
b/drivers/gpu/drm/msm/msm_gem_vma.c
index f914ddbaea89..64906594fc65 100644
--- a/drivers/gpu/drm/msm
From: Rob Clark
The ring seqno counter duplicates the fence-context last_fence counter.
They end up getting incremented in lock-step, on the same scheduler
thread, but the split just makes things less obvious.
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 2
From: Rob Clark
These belong more cleanly in the gem header.
Signed-off-by: Rob Clark
Reviewed-by: Dmitry Baryshkov
---
drivers/gpu/drm/msm/msm_drv.h | 23 ---
drivers/gpu/drm/msm/msm_gem.h | 22 ++
2 files changed, 22 insertions(+), 23 deletions
From: Rob Clark
The first six paches are various cleanups and simplifications. The
next two get rid of redundant vma lookups in the submit and retire
paths. Following that, fenced vma lets us indicate a fence value
following which the vma is no longer used, which is needed because
otherwise
t;>> drm-engine-video-enhance: 0 ns
> >>>>
> >>>> v2:
> >>>>* Update for removal of name and pid.
> >>>>
> >>>> v3:
> >>>>* Use drm_driver.name.
> >>>>
> >>>>
On Thu, Mar 24, 2022 at 1:37 AM wrote:
>
> From: Xiaoke Wang
>
> kzalloc() is a memory allocation function which can return NULL when
> some internal memory errors happen. So it is better to check it to
> prevent potential wrong memory access.
>
> Signed-off-by: Xiaoke Wang
> ---
>
Signed-off-by: Robin Murphy
Reviewed-by: Rob Clark
> ---
> drivers/gpu/drm/msm/msm_drv.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
> index affa95eb05fc..9c36b505daab 100644
> --- a/
From: Rob Clark
It would have been cleaner to have a flag to *request* the fence event.
But that ship has sailed. So add a flag so that userspace which doesn't
care about the events can opt-out.
Signed-off-by: Rob Clark
---
drivers/gpu/drm/virtio/virtgpu_ioctl.c | 8 +---
include/uapi
On Fri, Apr 1, 2022 at 8:38 AM Laurent Pinchart
wrote:
>
> Hi Abhinav,
>
> Thank you for the patch.
>
> On Thu, Mar 31, 2022 at 05:12:13PM -0700, Abhinav Kumar wrote:
> > For some vendor driver implementations, display hardware can
> > be shared between the encoder used for writeback and the
so I think I'll cherry-pick
this ahead of the rest of the series
Reviewed-by: Rob Clark
> ---
> drivers/gpu/drm/msm/adreno/a4xx_gpu.c | 3 +--
> drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 27 -
> drivers/gpu/drm/msm/adreno/a5xx_preempt.c | 4 +--
&g
On Thu, Mar 31, 2022 at 12:41 PM Dmitry Osipenko
wrote:
>
> On 3/31/22 22:02, Rob Clark wrote:
> > On Thu, Mar 31, 2022 at 11:52 AM Dmitry Osipenko
> > wrote:
> >>
> >> ...
> >>> +/*
> >>> + * Get the requested iova but don't pin it. F
On Thu, Mar 31, 2022 at 11:52 AM Dmitry Osipenko
wrote:
>
> ...
> > +/*
> > + * Get the requested iova but don't pin it. Fails if the requested iova is
> > + * not available. Doesn't need a put because iovas are currently valid for
> > + * the life of the object.
> > + *
> > + * Setting an iova
On Thu, Mar 31, 2022 at 11:27 AM Dmitry Osipenko
wrote:
>
> On 3/30/22 23:47, Rob Clark wrote:
> > From: Rob Clark
> >
> > Combines duplicate vma lookup in the get_and_pin path.
> >
> > Signed-off-by: Rob Clark
> > -
From: Rob Clark
With userspace allocated iova (next patch), we can have a race condition
where userspace observes the fence completion and deletes the vma before
retire_submit() gets around to unpinning the vma. To handle this, add a
fenced unpin which drops the refcount but tracks the fence
From: Rob Clark
The motivation at this point is mainly native userspace mesa driver in a
VM guest. The one remaining synchronous "hotpath" is buffer allocation,
because guest needs to wait to know the bo's iova before it can start
emitting cmdstream/state that references
From: Rob Clark
Combines duplicate vma lookup in the get_and_pin path.
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/msm_gem.c | 50 ++-
1 file changed, 26 insertions(+), 24 deletions(-)
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm
From: Rob Clark
This way we only lookup vma once per object per submit, for both the
submit and retire path.
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/msm_gem.c| 60 +---
drivers/gpu/drm/msm/msm_gem.h| 9 +++--
drivers/gpu/drm/msm
From: Rob Clark
Get rid of all the unnecessary conversion between address/size and page
offsets. It just confuses things.
Signed-off-by: Rob Clark
Reviewed-by: Dmitry Baryshkov
---
drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 2 +-
drivers/gpu/drm/msm/msm_gem.c | 5 ++---
drivers/gpu
From: Rob Clark
There was only a single user, which could just as easily stash the iova
when pinning.
Signed-off-by: Rob Clark
Reviewed-by: Dmitry Baryshkov
---
drivers/gpu/drm/msm/msm_fb.c | 16 ++--
drivers/gpu/drm/msm/msm_gem.c | 16
drivers/gpu/drm/msm
From: Rob Clark
Prep for a following patch, where it gets a bit more complicated.
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/msm_gem.c | 2 +-
drivers/gpu/drm/msm/msm_gem.h | 1 +
drivers/gpu/drm/msm/msm_gem_vma.c | 9 +++--
3 files changed, 9 insertions(+), 3 deletions
From: Rob Clark
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/msm_gem_vma.c | 10 +-
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c
b/drivers/gpu/drm/msm/msm_gem_vma.c
index f914ddbaea89..64906594fc65 100644
--- a/drivers/gpu/drm/msm
From: Rob Clark
The ring seqno counter duplicates the fence-context last_fence counter.
They end up getting incremented in lock-step, on the same scheduler
thread, but the split just makes things less obvious.
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 2
From: Rob Clark
These belong more cleanly in the gem header.
Signed-off-by: Rob Clark
Reviewed-by: Dmitry Baryshkov
---
drivers/gpu/drm/msm/msm_drv.h | 23 ---
drivers/gpu/drm/msm/msm_gem.h | 22 ++
2 files changed, 22 insertions(+), 23 deletions
From: Rob Clark
The first six paches are various cleanups and simplifications. The
next two get rid of redundant vma lookups in the submit and retire
paths. Following that, fenced vma lets us indicate a fence value
following which the vma is no longer used, which is needed because
otherwise
On Wed, Mar 30, 2022 at 4:32 AM Dmitry Baryshkov
wrote:
>
> On Wed, 30 Mar 2022 at 02:00, Rob Clark wrote:
> >
> > From: Rob Clark
> >
> > Prep for a following patch. While we are at it, convert a few remaining
> > WARN_ON()s to GEM_WARN_ON().
>
> We
On Tue, Mar 29, 2022 at 4:42 PM Dmitry Baryshkov
wrote:
>
> On Wed, 30 Mar 2022 at 02:00, Rob Clark wrote:
> >
> > From: Rob Clark
> >
> > The motivation at this point is mainly native userspace mesa driver in a
> > VM guest. The one remaining synchr
From: Rob Clark
The motivation at this point is mainly native userspace mesa driver in a
VM guest. The one remaining synchronous "hotpath" is buffer allocation,
because guest needs to wait to know the bo's iova before it can start
emitting cmdstream/state that references
From: Rob Clark
This way we only lookup vma once per object per submit, for both the
submit and retire path.
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/msm_gem.c| 60 +---
drivers/gpu/drm/msm/msm_gem.h| 9 +++--
drivers/gpu/drm/msm
From: Rob Clark
With userspace allocated iova (next patch), we can have a race condition
where userspace observes the fence completion and deletes the vma before
retire_submit() gets around to unpinning the vma. To handle this, add a
fenced unpin which drops the refcount but tracks the fence
From: Rob Clark
Combines duplicate vma lookup in the get_and_pin path.
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/msm_gem.c | 50 ++-
1 file changed, 26 insertions(+), 24 deletions(-)
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm
From: Rob Clark
There was only a single user, which could just as easily stash the iova
when pinning.
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/msm_fb.c | 16 ++--
drivers/gpu/drm/msm/msm_gem.c | 16
drivers/gpu/drm/msm/msm_gem.h | 2 --
3 files changed
From: Rob Clark
The first five paches are various cleanups and simplifications. The
next two get rid of redundant vma lookups in the submit and retire
paths. Following that, fenced vma lets us indicate a fence value
following which the vma is no longer used, which is needed because
otherwise
From: Rob Clark
Get rid of all the unnecessary conversion between address/size and page
offsets. It just confuses things.
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 2 +-
drivers/gpu/drm/msm/msm_gem.c | 5 ++---
drivers/gpu/drm/msm/msm_gem.h | 4
From: Rob Clark
Prep for a following patch. While we are at it, convert a few remaining
WARN_ON()s to GEM_WARN_ON().
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/msm_gem.c | 2 +-
drivers/gpu/drm/msm/msm_gem.h | 1 +
drivers/gpu/drm/msm/msm_gem_vma.c | 15 ++-
3
From: Rob Clark
The ring seqno counter duplicates the fence-context last_fence counter.
They end up getting incremented in lock-step, on the same scheduler
thread, but the split just makes things less obvious.
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 2
From: Rob Clark
These belong more cleanly in the gem header.
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/msm_drv.h | 23 ---
drivers/gpu/drm/msm/msm_gem.h | 22 ++
2 files changed, 22 insertions(+), 23 deletions(-)
diff --git a/drivers/gpu/drm/msm
On Wed, Mar 23, 2022 at 8:14 AM Daniel Vetter wrote:
>
> On Wed, 23 Mar 2022 at 15:07, Daniel Stone wrote:
> >
> > Hi,
> >
> > On Mon, 21 Mar 2022 at 16:02, Rob Clark wrote:
> > > On Mon, Mar 21, 2022 at 2:30 AM Christian König
> >
On Mon, Mar 21, 2022 at 2:30 AM Christian König
wrote:
>
> Am 18.03.22 um 16:12 schrieb Rob Clark:
> > On Fri, Mar 18, 2022 at 12:42 AM Christian König
> > wrote:
> >> Am 17.03.22 um 18:31 schrieb Rob Clark:
> >>> On Thu, Mar 17, 2022 at 10:2
On Fri, Mar 18, 2022 at 9:27 AM Andrey Grodzovsky
wrote:
>
>
> On 2022-03-18 12:20, Rob Clark wrote:
> > On Fri, Mar 18, 2022 at 9:04 AM Andrey Grodzovsky
> > wrote:
> >>
> >> On 2022-03-17 16:35, Rob Clark wrote:
> >>> On Thu, Mar
On Fri, Mar 18, 2022 at 9:04 AM Andrey Grodzovsky
wrote:
>
>
> On 2022-03-17 16:35, Rob Clark wrote:
> > On Thu, Mar 17, 2022 at 12:50 PM Andrey Grodzovsky
> > wrote:
> >>
> >> On 2022-03-17 14:25, Rob Clark wrote:
> >>> On Thu, Mar
On Fri, Mar 18, 2022 at 12:42 AM Christian König
wrote:
>
> Am 17.03.22 um 18:31 schrieb Rob Clark:
> > On Thu, Mar 17, 2022 at 10:27 AM Daniel Vetter wrote:
> >> [SNIP]
> >>> (At some point, I'd like to use scheduler for the replay, and actually
> >>&g
On Fri, Mar 18, 2022 at 12:19 AM Dan Carpenter wrote:
>
> On Thu, Mar 17, 2022 at 08:03:59AM -0700, Rob Clark wrote:
> > > > diff --git a/drivers/gpu/drm/msm/msm_gpu.c
> > > > b/drivers/gpu/drm/msm/msm_gpu.c
> > > > index 4ec62b601adc..68f3f8ade76
From: Rob Clark
The motivation at this point is mainly native userspace mesa driver in a
VM guest. The one remaining synchronous "hotpath" is buffer allocation,
because guest needs to wait to know the bo's iova before it can start
emitting cmdstream/state that references
On Thu, Mar 17, 2022 at 1:45 PM Akhil P Oommen wrote:
>
> On 3/11/2022 5:16 AM, Rob Clark wrote:
> > From: Rob Clark
> >
> > The mutex wasn't really protecting anything before. Before the previous
> > patch we could still be racing with the scheduler's kthread,
On Thu, Mar 17, 2022 at 12:50 PM Andrey Grodzovsky
wrote:
>
>
> On 2022-03-17 14:25, Rob Clark wrote:
> > On Thu, Mar 17, 2022 at 11:10 AM Andrey Grodzovsky
> > wrote:
> >>
> >> On 2022-03-17 13:35, Rob Clark wrote:
> >>> On Thu, Mar 17, 2022
From: Rob Clark
Fixes: 25faf2f2e065 ("drm/msm: Show process names in gem_describe")
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/msm_gem.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 02b9ae65a96a..a4
On Thu, Mar 17, 2022 at 11:10 AM Andrey Grodzovsky
wrote:
>
>
> On 2022-03-17 13:35, Rob Clark wrote:
> > On Thu, Mar 17, 2022 at 9:45 AM Christian König
> > wrote:
> >> Am 17.03.22 um 17:18 schrieb Rob Clark:
> >>> On Thu, Mar 17, 2022 at 9:04 AM Christ
On Thu, Mar 17, 2022 at 9:45 AM Christian König
wrote:
>
> Am 17.03.22 um 17:18 schrieb Rob Clark:
> > On Thu, Mar 17, 2022 at 9:04 AM Christian König
> > wrote:
> >> Am 17.03.22 um 16:10 schrieb Rob Clark:
> >>> [SNIP]
> >>> userspace
On Thu, Mar 17, 2022 at 10:27 AM Daniel Vetter wrote:
>
> On Thu, Mar 17, 2022 at 08:40:51AM -0700, Rob Clark wrote:
> > On Thu, Mar 17, 2022 at 2:29 AM Daniel Vetter wrote:
> > >
> > > On Thu, Mar 17, 2022 at 08:03:27AM +0100, Christian König wrote:
> >
From: Rob Clark
In the cause of using the GPU via virtgpu, the host side process is
really a sort of proxy, and not terribly interesting from the PoV of
crash/fault logging. Add a way to override these per process so that
we can see the guest process's name.
v2: Handle kmalloc failure, add
From: Rob Clark
Deduplicate this from fault_worker and recover_worker.
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/msm_gpu.c | 32
1 file changed, 16 insertions(+), 16 deletions(-)
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm
From: Rob Clark
The 64b value field is already suffient to hold a pointer instead of
immediate, but we also need a length field.
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/adreno/adreno_gpu.c | 12 ++--
drivers/gpu/drm/msm/adreno/adreno_gpu.h | 4 ++--
drivers/gpu/drm/msm
From: Rob Clark
Add a way to override comm/cmdline per-drm_file. This is useful for
VM scenarios where the host process is just a proxy for the actual
guest process.
Rob Clark (3):
drm/msm: Add support for pointer params
drm/msm: Split out helper to get comm/cmdline
drm/msm: Add a way
On Thu, Mar 17, 2022 at 9:04 AM Christian König
wrote:
>
> Am 17.03.22 um 16:10 schrieb Rob Clark:
> > [SNIP]
> > userspace frozen != kthread frozen .. that is what this patch is
> > trying to address, so we aren't racing between shutting down the hw
> > and the
On Wed, Mar 16, 2022 at 5:13 PM Dmitry Osipenko
wrote:
>
> On 3/16/22 23:00, Rob Clark wrote:
> > On Mon, Mar 14, 2022 at 3:44 PM Dmitry Osipenko
> > wrote:
> >>
> >> Introduce a common DRM SHMEM shrinker. It allows to reduce code
> >> duplication a
On Thu, Mar 17, 2022 at 2:29 AM Daniel Vetter wrote:
>
> On Thu, Mar 17, 2022 at 08:03:27AM +0100, Christian König wrote:
> > Am 16.03.22 um 16:36 schrieb Rob Clark:
> > > [SNIP]
> > > just one point of clarification.. in the msm and i915 case it is
> > >
On Thu, Mar 17, 2022 at 2:29 AM Daniel Vetter wrote:
>
> On Thu, Mar 17, 2022 at 08:03:27AM +0100, Christian König wrote:
> > Am 16.03.22 um 16:36 schrieb Rob Clark:
> > > [SNIP]
> > > just one point of clarification.. in the msm and i915 case it is
> > >
On Thu, Mar 17, 2022 at 3:06 AM Christian König
wrote:
>
> Am 17.03.22 um 10:59 schrieb Daniel Vetter:
> > On Thu, Mar 10, 2022 at 03:46:05PM -0800, Rob Clark wrote:
> >> From: Rob Clark
> >>
> >> In the system suspend path, we don't want to be racing w
On Thu, Mar 17, 2022 at 1:21 AM Dan Carpenter wrote:
>
> On Wed, Mar 16, 2022 at 05:29:45PM -0700, Rob Clark wrote:
> > switch (param) {
> > + case MSM_PARAM_COMM:
> > + case MSM_PARAM_CMDLINE: {
> > + char *str, **paramp;
> > +
>
From: Rob Clark
In the cause of using the GPU via virtgpu, the host side process is
really a sort of proxy, and not terribly interesting from the PoV of
crash/fault logging. Add a way to override these per process so that
we can see the guest process's name.
Signed-off-by: Rob Clark
From: Rob Clark
Deduplicate this from fault_worker and recover_worker.
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/msm_gpu.c | 32
1 file changed, 16 insertions(+), 16 deletions(-)
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm
From: Rob Clark
The 64b value field is already suffient to hold a pointer instead of
immediate, but we also need a length field.
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/adreno/adreno_gpu.c | 12 ++--
drivers/gpu/drm/msm/adreno/adreno_gpu.h | 4 ++--
drivers/gpu/drm/msm
From: Rob Clark
Add a way to override comm/cmdline per-drm_file. This is useful for
VM scenarios where the host process is just a proxy for the actual
guest process.
Rob Clark (3):
drm/msm: Add support for pointer params
drm/msm: Split out helper to get comm/cmdline
drm/msm: Add a way
On Tue, Mar 8, 2022 at 11:40 PM Shashank Sharma
wrote:
>
> From: Shashank Sharma
>
> This patch adds a new sysfs event, which will indicate
> the userland about a GPU reset, and can also provide
> some information like:
> - process ID of the process involved with the GPU reset
> - process name
On Mon, Mar 14, 2022 at 3:44 PM Dmitry Osipenko
wrote:
>
> Introduce a common DRM SHMEM shrinker. It allows to reduce code
> duplication among DRM drivers, it also handles complicated lockings
> for the drivers. This is initial version of the shrinker that covers
> basic needs of GPU drivers.
>
>
On Wed, Mar 16, 2022 at 8:48 AM Alex Deucher wrote:
>
> On Wed, Mar 16, 2022 at 11:35 AM Rob Clark wrote:
> >
> > On Wed, Mar 16, 2022 at 7:12 AM Alex Deucher wrote:
> > >
> > > On Wed, Mar 16, 2022 at 4:48 AM Pekka Paalanen
> > > wrote:
&
On Wed, Mar 16, 2022 at 7:12 AM Alex Deucher wrote:
>
> On Wed, Mar 16, 2022 at 4:48 AM Pekka Paalanen wrote:
> >
[snip]
> > With new UAPI comes the demand of userspace proof, not hand-waving. You
> > would not be proposing this new interface if you didn't have use cases
> > in mind, even just
From: Rob Clark
The mutex wasn't really protecting anything before. Before the previous
patch we could still be racing with the scheduler's kthread, as that is
not necessarily frozen yet. Now that we've parked the sched threads,
the only race is with jobs retiring, and that is harmless, ie
From: Rob Clark
In the system suspend path, we don't want to be racing with the
scheduler kthreads pushing additional queued up jobs to the hw
queue (ringbuffer). So park them first. While we are at it,
move the wait for active jobs to complete into the new system-
suspend path.
Signed-off
From: Rob Clark
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/adreno/adreno_device.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c
b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 89cfd84760d7..8859834b51b8 100644
From: Rob Clark
In particular, we want to park the scheduler threads so that suspend
is not racing with the kthread pushing more jobs to the driver.
Rob Clark (3):
drm/msm/gpu: Rename runtime suspend/resume functions
drm/msm/gpu: Park scheduler threads for system suspend
drm/msm/gpu
On Thu, Mar 10, 2022 at 11:44 AM Sharma, Shashank
wrote:
>
>
>
> On 3/10/2022 8:35 PM, Rob Clark wrote:
> > On Thu, Mar 10, 2022 at 11:14 AM Sharma, Shashank
> > wrote:
> >>
> >>
> >>
> >> On 3/10/2022 7:33 PM, Abhinav Kumar wr
On Thu, Mar 10, 2022 at 11:14 AM Sharma, Shashank
wrote:
>
>
>
> On 3/10/2022 7:33 PM, Abhinav Kumar wrote:
> >
> >
> > On 3/10/2022 9:40 AM, Rob Clark wrote:
> >> On Thu, Mar 10, 2022 at 9:19 AM Sharma, Shashank
> >> wrote:
> >>
On Thu, Mar 10, 2022 at 9:19 AM Sharma, Shashank
wrote:
>
>
>
> On 3/10/2022 6:10 PM, Rob Clark wrote:
> > On Thu, Mar 10, 2022 at 8:21 AM Sharma, Shashank
> > wrote:
> >>
> >>
> >>
> >> On 3/10/2022 4:24 PM, Rob Clark wrote:
> &
On Thu, Mar 10, 2022 at 8:27 AM Andrey Grodzovsky
wrote:
>
>
> On 2022-03-10 11:21, Sharma, Shashank wrote:
> >
> >
> > On 3/10/2022 4:24 PM, Rob Clark wrote:
> >> On Thu, Mar 10, 2022 at 1:55 AM Christian König
> >> wrote:
> >>>
On Thu, Mar 10, 2022 at 8:21 AM Sharma, Shashank
wrote:
>
>
>
> On 3/10/2022 4:24 PM, Rob Clark wrote:
> > On Thu, Mar 10, 2022 at 1:55 AM Christian König
> > wrote:
> >>
> >>
> >>
> >> Am 09.03.22 um 19:12 schrieb Rob Clark:
> &
On Thu, Mar 10, 2022 at 1:55 AM Christian König
wrote:
>
>
>
> Am 09.03.22 um 19:12 schrieb Rob Clark:
> > On Tue, Mar 8, 2022 at 11:40 PM Shashank Sharma
> > wrote:
> >> From: Shashank Sharma
> >>
> >> This patch adds a new sysfs event, whic
On Wed, Mar 9, 2022 at 12:06 PM Dmitry Osipenko
wrote:
>
> On 3/9/22 03:56, Rob Clark wrote:
> >> If we really can't track madvise state in the guest for dealing with
> >> host memory pressure, I think the better option is to introduce
> >> MADV:WILLNEED_REPLAC
On Tue, Mar 8, 2022 at 11:40 PM Shashank Sharma
wrote:
>
> From: Shashank Sharma
>
> This patch adds a new sysfs event, which will indicate
> the userland about a GPU reset, and can also provide
> some information like:
> - process ID of the process involved with the GPU reset
> - process name
r (1):
drm/msm/adreno: fix cast in adreno_get_param()
Dmitry Baryshkov (1):
dt-bindings: display/msm: add missing brace in dpu-qcm2290.yaml
Rob Clark (8):
drm/msm: Update generated headers
drm/msm: Add SET_PARAM ioctl
drm/msm: Add SYSPROF param (v2)
drm/msm/a6xx:
On Tue, Mar 8, 2022 at 5:17 AM Dmitry Osipenko
wrote:
>
> Add memory shrinker and new madvise IOCTL to the VirtIO-GPU driver.
> Userspace (BO cache manager of Mesa driver) will mark BOs as "don't need"
> using the new IOCTL to let shrinker purge the marked BOs on OOM, thus
> shrinker will lower
On Tue, Mar 8, 2022 at 3:36 PM Dmitry Osipenko
wrote:
>
> On 3/9/22 01:24, Rob Clark wrote:
> > On Tue, Mar 8, 2022 at 11:28 AM Dmitry Osipenko
> > wrote:
> >>
> >> On 3/8/22 19:29, Rob Clark wrote:
> >>> On Tue, Mar 8, 2022 at 5:17 AM D
On Tue, Mar 8, 2022 at 11:28 AM Dmitry Osipenko
wrote:
>
> On 3/8/22 19:29, Rob Clark wrote:
> > On Tue, Mar 8, 2022 at 5:17 AM Dmitry Osipenko
> > wrote:
> >>
> >> Hello,
> >>
> >> This patchset introduces memory shrinker for the VirtIO-GPU
On Tue, Mar 8, 2022 at 10:53 AM Fabio Estevam wrote:
>
> On Tue, Mar 8, 2022 at 3:48 PM Rob Clark wrote:
> >
> > From: Rob Clark
> >
> > Avoid going down devfreq paths on devices where devfreq is not
> > initialized.
> >
> > v2: Change has_dev
From: Rob Clark
Avoid going down devfreq paths on devices where devfreq is not
initialized.
v2: Change has_devfreq() logic [Dmitry]
Reported-by: Linux Kernel Functional Testing
Reported-by: Anders Roxell
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/msm_gpu_devfreq.c | 30
On Tue, Mar 8, 2022 at 5:17 AM Dmitry Osipenko
wrote:
>
> Hello,
>
> This patchset introduces memory shrinker for the VirtIO-GPU DRM driver.
> During OOM, the shrinker will release BOs that are marked as "not needed"
> by userspace using the new madvise IOCTL. The userspace in this case is
> the
From: Rob Clark
Fixes: f6d62d091cfd ("drm/msm/a6xx: add support for Adreno 660 GPU")
Signed-off-by: Rob Clark
Reviewed-by: Dmitry Baryshkov
---
drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 12
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/
On Thu, Mar 3, 2022 at 7:21 PM Dmitry Baryshkov
wrote:
>
> MSM DRM driver already allows one to compile out the DP or DSI support.
> Add support for disabling other features like MDP4/MDP5/DPU drivers or
> direct HDMI output support.
>
> Suggested-by: Stephen Boyd
> Signed-off-by: Dmitry
On Fri, Mar 4, 2022 at 1:47 PM Dmitry Baryshkov
wrote:
>
> On Fri, 4 Mar 2022 at 23:23, Rob Clark wrote:
> >
> > From: Rob Clark
> >
> > Fixes: f6d62d091cfd ("drm/msm/a6xx: add support for Adreno 660 GPU")
> > Signed-off-by: Rob Clark
&g
From: Rob Clark
Fixes: f6d62d091cfd ("drm/msm/a6xx: add support for Adreno 660 GPU")
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
b/drivers/gpu/drm/msm/adreno/a6xx_g
From: Rob Clark
refcount_t complains about 0->1 transitions, which isn't *quite* what we
wanted. So use dirtyfb==1 to mean that the fb is not connected to any
output that requires dirtyfb flushing, so that we can keep the underflow
and overflow checking.
Fixes: 9e4dde28e9cd ("drm/ms
From: Rob Clark
Any app controlled perfcntr collection (GL_AMD_performance_monitor, etc)
does not require counters to maintain state across context switches. So
clear them if systemwide profiling is not active.
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 29
From: Rob Clark
Add a SYSPROF param for system profiling tools like Mesa's pps-producer
(perfetto) to control behavior related to system-wide performance
counter collection. In particular, for profiling, one wants to ensure
that GPU context switches do not effect perfcounter state, and might
From: Rob Clark
It was always expected to have a use for this some day, so we left a
placeholder. Now we do. (And I expect another use in the not too
distant future when we start allowing userspace to allocate GPU iova.)
Signed-off-by: Rob Clark
---
drivers/gpu/drm/msm/adreno/a2xx_gpu.c
From: Rob Clark
Some clever folks figured out a way to use performance counters as a
side-channel[1]. But, other than the special case of using the perf
counters for system profiling, we can reset the counters across context
switches to protect against this.
This series introduces a SYSPROF
On Thu, Mar 3, 2022 at 1:17 PM Rob Clark wrote:
>
> On Thu, Mar 3, 2022 at 12:47 PM Stephen Boyd wrote:
> >
> > Quoting Rob Clark (2022-03-03 11:46:47)
> > > diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
> > > ind
1101 - 1200 of 5720 matches
Mail list logo