that are not terminated correctly.
>
> Signed-off-by: Ashley Smith
Reviewed-by: Boris Brezillon
> ---
> drivers/gpu/drm/panthor/panthor_sched.c | 11 ++-
> 1 file changed, 10 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/panthor/panthor_sch
On Wed, 7 May 2025 14:01:04 +0100
Adrián Larumbe wrote:
> On 06.05.2025 08:54, Boris Brezillon wrote:
> > On Thu, 24 Apr 2025 03:21:30 +0100
> > Adrián Larumbe wrote:
> >
> > > Unlike in Panthor, from where this change is based on, there is no need
> > >
On Thu, 24 Apr 2025 03:21:30 +0100
Adrián Larumbe wrote:
> Unlike in Panthor, from where this change is based on, there is no need
> to support tagging of BO's other than UM-exposed ones, so all strings
> can be freed with kfree().
>
> This commit is done in preparation of a following one that w
On Thu, 24 Apr 2025 03:21:32 +0100
Adrián Larumbe wrote:
> This change is essentially a Panfrost port of commit a3707f53eb3f
> ("drm/panthor: show device-wide list of DRM GEM objects over DebugFS").
>
> The DebugFS file is almost the same as in Panthor, minus the GEM object
> usage flags, since
On Thu, 24 Apr 2025 03:21:31 +0100
Adrián Larumbe wrote:
> Allow UM to label a BO for which it possesses a DRM handle.
>
> Signed-off-by: Adrián Larumbe
Reviewed-by: Boris Brezillon
> ---
> drivers/gpu/drm/panfrost/panfrost_drv.c | 44 -
> driver
On Wed, 30 Apr 2025 11:07:17 +0200
Simona Vetter wrote:
> On Wed, Apr 16, 2025 at 11:38:03AM +0200, Simona Vetter wrote:
> > On Wed, Apr 16, 2025 at 08:57:45AM +0200, Thomas Zimmermann wrote:
> > > Test struct drm_gem_object.import_attach to detect imported objects.
> > >
> > > During object c
On Thu, 24 Apr 2025 19:40:34 +0100
Adrián Larumbe wrote:
> Commit a3707f53eb3f ("drm/panthor: show device-wide list of DRM GEM
> objects over DebugFS") causes a build warning and linking error when
> built without support for DebugFS, because of a non-inline non-static
> function declaration in a
Hi Iago,
On Mon, 28 Apr 2025 08:55:07 +0200
Iago Toral wrote:
> Hi,
>
> Pitching in to describe the situation for v3d:
Thanks for chiming in.
>
> El vie, 18-04-2025 a las 14:25 +0200, Boris Brezillon escribió:
>
> (...)
> > +For all these reasons, the til
Hi Steve,
On Wed, 23 Apr 2025 10:41:53 +0100
Steven Price wrote:
> On 18/04/2025 13:25, Boris Brezillon wrote:
> > Tile-based GPUs come with a set of constraints that are not present
> > when immediate rendering is used. This new document tries to explain
> > the dif
Hi Alyssa,
On Wed, 23 Apr 2025 10:47:21 -0400
Alyssa Rosenzweig wrote:
> Steven wanted non-Mali eyes, so with my Imaginapple hat on...
>
> > +All lot of embedded GPUs are using tile-based rendering instead of
> > immediate
>
> s/All lot of/Many/
Will change that.
>
> > +- Complex geometr
h is just an artifact of the import. Prepares
> > to make import_attach optional.
> >
> > Signed-off-by: Thomas Zimmermann
> > Cc: Boris Brezillon
> > Cc: Steven Price
> > Cc: Liviu Dudau
> > ---
> > drivers/gpu/drm/panthor/panthor_gem.c | 2 +-
&g
On Thu, 24 Apr 2025 14:10:16 +0200
"Arnd Bergmann" wrote:
> On Thu, Apr 24, 2025, at 13:41, Boris Brezillon wrote:
> > On Thu, 24 Apr 2025 13:25:47 +0200
> >> +#ifdef CONFIG_DEBUG_FS
> >>bo->debugfs.flags = usage_flags |
> &g
On Thu, 24 Apr 2025 13:25:47 +0200
Arnd Bergmann wrote:
> From: Arnd Bergmann
>
> When debugfs is disabled, including panthor_gem.h causes warnings
> about a non-static global function defined in a header:
>
> In file included from drivers/gpu/drm/panthor/panthor_drv.c:30:
> drivers/gpu/drm/pa
On Wed, 23 Apr 2025 03:12:30 +0100
Adrián Larumbe wrote:
> This patch series is aimed at providing UM with detailed memory profiling
> information in debug builds. It is achieved through a device-wide list of
> DRM GEM objects, and also implementing the ability to label BO's from UM
> through a n
On Wed, 23 Apr 2025 09:01:49 +0200
Boris Brezillon wrote:
> > +
> > +enum panthor_debugfs_gem_usage_flags {
> > + PANTHOR_DEBUGFS_GEM_USAGE_KERNEL_BIT = 0,
> > + PANTHOR_DEBUGFS_GEM_USAGE_FW_MAPPED_BIT = 1,
>
> Now that you print the flags as raw hex value
l BO and/or mapped onto the FW's address space.
>
> GEM state and usage flag meanings are printed in the file prelude, so
> that UM parsing tools can interpret the numerical values in the table.
>
> Signed-off-by: Adrián Larumbe
> Reviewed-by: Liviu Dudau
>
On Thu, 17 Apr 2025 14:19:42 +0200
Boris Brezillon wrote:
> Right now the DRM_PANTHOR_BO_NO_MMAP flag is ignored by
> panthor_ioctl_bo_mmap_offset(), meaning BOs with this flag set can
> have a file offset but can't be mapped anyway, because
> panthor_gem_mmap() will filter the
On Fri, 18 Apr 2025 21:15:32 +0100
Adrián Larumbe wrote:
> Hi Boris,
>
> On 18.04.2025 10:04, Boris Brezillon wrote:
> > On Fri, 18 Apr 2025 03:27:07 +0100
> > Adrián Larumbe wrote:
> >
> > > +#ifdef CONFIG_DEBUG_FS
> > > +static void
> >
On Fri, 18 Apr 2025 03:27:07 +0100
Adrián Larumbe wrote:
> + static const char * const gem_state_flags_names[] = {
> + [PANTHOR_DEBUGFS_GEM_STATE_FLAG_IMPORTED] = "imported",
> + [PANTHOR_DEBUGFS_GEM_STATE_FLAG_EXPORTED] = "exported",
Okay, I think I know where the fl
document will be updated with new
materials as we refine the libraries we add to help deal with
tilers, and have more drivers converted to follow the rules listed
here.
Signed-off-by: Boris Brezillon
---
Documentation/gpu/drm-tile-based-renderer.rst | 201 ++
Documentation/gpu/index.rst
On Fri, 18 Apr 2025 10:11:56 +0200
Boris Brezillon wrote:
> On Fri, 18 Apr 2025 03:27:07 +0100
> Adrián Larumbe wrote:
>
> > + static const char * const gem_state_flags_names[] = {
> > + [PANTHOR_DEBUGFS_GEM_STATE_FLAG_IMPORTED] = "imported",
FYI,
On Fri, 18 Apr 2025 03:27:07 +0100
Adrián Larumbe wrote:
> +#ifdef CONFIG_DEBUG_FS
> +static void
> +panthor_gem_debugfs_format_flags(char flags_str[], int flags_len,
> + const char * const names[], u32 name_count,
> + u32 flags)
> +{
> +
On Thu, 17 Apr 2025 16:13:49 +0100
Steven Price wrote:
> On 17/04/2025 15:49, Boris Brezillon wrote:
> > Currently, we pick the MMIO offset based on the size of the pgoff_t
> > type seen by the process that manipulates the FD, such that a 32-bit
> > process can always map
at we need
[1]https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34573
Boris Brezillon (2):
drm/panthor: Add missing explicit padding in drm_panthor_gpu_info
drm/panthor: Fix the user MMIO offset logic for emulators
drivers/gpu/drm/panthor/panthor_device.h | 18
drivers/gpu/drm/p
hor
which are either arm32 or arm64 where the 64-bit alignment of
u64 fields is already enforced a the compiler level.
Changes in v2:
- Rename the garbage field into pad0 and adjust the comment accordingly
- Add Liviu's R-b
Fixes: 0f25e493a246 ("drm/panthor: Add uAPI")
Signed-off-b
IO_OFFSET
requests to race with mmap() requests
- Don't do the is_user_mmio_offset test twice in panthor_mmap()
- Improve the uAPI docs
Signed-off-by: Boris Brezillon
---
drivers/gpu/drm/panthor/panthor_device.h | 18
drivers/gpu/drm/panthor/panthor_drv.c| 56 +
On Thu, 17 Apr 2025 14:10:31 +0200
Boris Brezillon wrote:
> > I can't help feeling we can just simplify this to:
> >
> > u64 mmio_offset = pfile->user_mmio.offset;
> >
> > if (offset >= mmio_offset) {
> >
On Thu, 17 Apr 2025 12:33:01 +0100
Liviu Dudau wrote:
> On Thu, Apr 17, 2025 at 11:41:18AM +0100, Steven Price wrote:
> > On 17/04/2025 11:05, Boris Brezillon wrote:
> > > Currently, we pick the MMIO offset based on the size of the pgoff_t
> > > type seen by the proc
On Tue, 15 Apr 2025 20:15:31 +0100
Adrián Larumbe wrote:
> +/**
> + * struct drm_panthor_bo_set_label - Arguments passed to
> DRM_IOCTL_PANTHOR_BO_SET_LABEL
> + */
> +struct drm_panthor_bo_set_label {
> + /** @handle: Handle of the buffer object to label. */
> + __u32 handle;
> +
Funny
INVAL
Changes in v3:
- Don't leak the BO ref
- Add R-bs
Signed-off-by: Boris Brezillon
Reviewed-by: Steven Price
Reviewed-by: Liviu Dudau
---
drivers/gpu/drm/panthor/panthor_drv.c | 7 +++
drivers/gpu/drm/panthor/panthor_gem.c | 13 +
2 files changed, 8 insertions(+), 12
On Thu, 17 Apr 2025 11:41:18 +0100
Steven Price wrote:
> On 17/04/2025 11:05, Boris Brezillon wrote:
> > Currently, we pick the MMIO offset based on the size of the pgoff_t
> > type seen by the process that manipulates the FD, such that a 32-bit
> > process can always map
On Thu, 17 Apr 2025 11:24:32 +0100
Steven Price wrote:
> On 17/04/2025 11:05, Boris Brezillon wrote:
> > drm_panthor_gpu_info::shader_present is currently automatically offset
> > by 4 byte to meet Arm's 32-bit/64-bit field alignment rules, but those
> > constraints don
On Thu, 17 Apr 2025 10:53:23 +0100
Matthew Auld wrote:
> On 17/04/2025 10:32, Boris Brezillon wrote:
> > Right now the DRM_PANTHOR_BO_NO_MMAP flag is ignored by
> > panthor_ioctl_bo_mmap_offset(), meaning BOs with this flag set can
> > have a file offset but can't
hrough FEX without using the host mesa (if we were to use
the thunked mesa lib, both the kernel and mesa would use
MMIO_OFFSET_64BIT, and the problem doesn't exist anymore).
Regards,
Boris
[1]https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34573
Boris Brezillon (2):
drm/panthor: Fix m
e need a way to explicitly set the user MMIO
offset from the UMD, such that the kernel doesn't have to guess it
from the TIF_32BIT flag set on user thread. We keep the old behavior
if DRM_PANTHOR_SET_USER_MMIO_OFFSET is never called.
Signed-off-by: Boris Brezillon
---
drivers/gpu/drm/panthor/p
hor
which are either arm32 or arm64 where the 64-bit alignment of
u64 fields is already enforced a the compiler level.
Fixes: 0f25e493a246 ("drm/panthor: Add uAPI")
Signed-off-by: Boris Brezillon
---
include/uapi/drm/panthor_drm.h | 12
1 file changed, 12 insertions(+)
On Thu, 17 Apr 2025 11:32:47 +0200
Boris Brezillon wrote:
> Right now the DRM_PANTHOR_BO_NO_MMAP flag is ignored by
> panthor_ioctl_bo_mmap_offset(), meaning BOs with this flag set can
> have a file offset but can't be mapped anyway, because
> panthor_gem_mmap() will filter the
INVAL
Signed-off-by: Boris Brezillon
---
drivers/gpu/drm/panthor/panthor_drv.c | 5 +
drivers/gpu/drm/panthor/panthor_gem.c | 13 +
2 files changed, 6 insertions(+), 12 deletions(-)
diff --git a/drivers/gpu/drm/panthor/panthor_drv.c
b/drivers/gpu/drm/panthor/panthor_drv.c
On Mon, 14 Apr 2025 15:01:20 +0200
Boris Brezillon wrote:
> The panthor_gpu_coherency_init() call has been moved around, but the
> error path hasn't been adjusted accordingly. Make sure we undo what
> has been done before this call in case of failure.
>
> Fixes: 7d5a3b22f5b5
On Wed, 16 Apr 2025 16:16:05 +0100
Steven Price wrote:
> On 15/04/2025 10:47, Boris Brezillon wrote:
> > On Mon, 14 Apr 2025 16:34:35 +0100
> > Steven Price wrote:
> >
> >> On 14/04/2025 13:47, Boris Brezillon wrote:
> >>> On Fri, 11 Apr 2025 1
On Wed, 16 Apr 2025 15:26:42 +0100
Steven Price wrote:
> On 15/04/2025 11:57, Boris Brezillon wrote:
> > Right now the DRM_PANTHOR_BO_NO_MMAP flag is ignored by
> > panthor_ioctl_bo_mmap_offset(), meaning BOs with this flag set can
> > still be mmap-ed.
> >
>
Happens for calls to drm_mode_destroy_dumb_ioctl() that
> clears the dma_buf field in drm_gem_object_exported_dma_buf_free().
Also happens when the GEM handle is released, which is the case we were
hitting in Panthor.
>
> v3:
> - only test for import_attach (Boris)
Reviewed-by: Boris Brezillon
> v2:
>
On Mon, 14 Apr 2025 09:03:55 -0400
Alyssa Rosenzweig wrote:
> > Actually, CSF stands in the way of re-allocating memory to other
> > contexts, because once we've allocated memory to a tiler heap, the FW
> > manages this pool of chunks, and recycles them. Mesa can intercept
> > the "returned chunk
On Tue, 15 Apr 2025 12:57:10 +0200
Boris Brezillon wrote:
> Right now the DRM_PANTHOR_BO_NO_MMAP flag is ignored by
> panthor_ioctl_bo_mmap_offset(), meaning BOs with this flag set can
> still be mmap-ed.
>
> Fortunately, this bug only impacts user BOs, because kernel BOs are n
On Tue, 15 Apr 2025 16:02:20 +0200
Thomas Zimmermann wrote:
> Test struct drm_gem_object.import_attach.dmabuf to detect imported
> objects. Warn if the stored state is inconsistent.
>
> During object clenaup, the dma_buf field might be NULL. Testing it in
> an object's free callback then incorre
On Tue, 15 Apr 2025 14:19:20 +0200
Christian König wrote:
> Am 15.04.25 um 12:45 schrieb Thomas Zimmermann:
> > Hi
> >
> > Am 15.04.25 um 11:39 schrieb Christian König:
> >> Am 15.04.25 um 11:20 schrieb Thomas Zimmermann:
> >>> Test struct drm_gem_object.import_attach to detect imported
> >>>
-ed anyway. Given all user BOs setting this flag are private
anyway (not shareable), there's no potential data leak.
Fixes: 4bdca1150792 ("drm/panthor: Add the driver frontend block")
Signed-off-by: Boris Brezillon
---
drivers/gpu/drm/panthor/panthor_drv.c | 5 +
1 file chang
On Mon, 14 Apr 2025 16:34:35 +0100
Steven Price wrote:
> On 14/04/2025 13:47, Boris Brezillon wrote:
> > On Fri, 11 Apr 2025 16:39:02 +0200
> > Boris Brezillon wrote:
> >
> >> On Fri, 11 Apr 2025 15:13:26 +0200
> >> Christian König wrote:
> >&g
s not scheduled, we suspend the
> > > timeout again which undoes what drm_sched_job_begin() did when calling
> > > drm_sched_start_timeout(). So the timeout does not reset when a job
> > > is finished.
> > >
> > > Co-developed-by: Boris Brezil
On Mon, 14 Apr 2025 16:34:47 +0200
Simona Vetter wrote:
> On Mon, Apr 14, 2025 at 02:08:25PM +0100, Liviu Dudau wrote:
> > On Mon, Apr 14, 2025 at 01:22:06PM +0200, Boris Brezillon wrote:
> > > Hi Sima,
> > >
> > > On Fri, 11 Apr 2025 14:01
eported-by: Dan Carpenter
Closes:
https://lore.kernel.org/dri-devel/4da470aa-4f84-460e-aff8-dabc8cc4da15@stanley.mountain/T/#t
Signed-off-by: Boris Brezillon
---
drivers/gpu/drm/panthor/panthor_device.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/panthor/pant
On Fri, 11 Apr 2025 16:39:02 +0200
Boris Brezillon wrote:
> On Fri, 11 Apr 2025 15:13:26 +0200
> Christian König wrote:
>
> > >
> > >> Background is that you don't get a crash, nor error message, nor
> > >> anything indicating what is happe
Hi Sima,
On Fri, 11 Apr 2025 14:01:16 +0200
Simona Vetter wrote:
> On Thu, Apr 10, 2025 at 08:41:55PM +0200, Boris Brezillon wrote:
> > On Thu, 10 Apr 2025 14:01:03 -0400
> > Alyssa Rosenzweig wrote:
> >
> > > > > > In Panfrost and Lima, we
lable until the vunmap happens. And as the pages
> in DMA or SHMEM areas cannot be moved, there is no reason to call
> pin. Hence remove the pin call.
>
> Update drm_client_buffer_vunmap() accordingly.
>
> Signed-off-by: Thomas Zimmermann
Reviewed-by: Boris Brezillon
> ---
On Sat, 12 Apr 2025 17:39:58 +0300
Dan Carpenter wrote:
> Hello Boris Brezillon,
>
> Commit 7d5a3b22f5b5 ("drm/panthor: Call panthor_gpu_coherency_init()
> after PM resume()") from Apr 4, 2025 (linux-next), leads to the
> following Smatch static checker warning:
&
definitions.
>
> Suggested-by: Boris Brezillon
> Signed-off-by: Karunika Choo
Reviewed-by: Boris Brezillon
> ---
> drivers/gpu/drm/panthor/panthor_gpu.c | 12 ++--
> drivers/gpu/drm/panthor/panthor_gpu.h | 10 +--
> drivers/gpu/drm/panthor/panthor_mmu.c | 16 ++---
> dr
On Fri, 11 Apr 2025 16:17:56 +0100
Karunika Choo wrote:
> On 10/04/2025 17:46, Boris Brezillon wrote:
> > On Thu, 10 Apr 2025 17:35:46 +0100
> > Karunika Choo wrote:
> >
> >> This patch adds 64-bit register accessors to simplify register access in
> >>
> functions.
>
> Signed-off-by: Karunika Choo
Reviewed-by: Boris Brezillon
> ---
> drivers/gpu/drm/panthor/panthor_device.h | 71
> drivers/gpu/drm/panthor/panthor_fw.c | 9 +-
> drivers/gpu/drm/panthor/panthor_gpu.c| 142 ++---
On Fri, 11 Apr 2025 15:13:26 +0200
Christian König wrote:
> >
> >> Background is that you don't get a crash, nor error message, nor
> >> anything indicating what is happening.
> > The job times out at some point, but we might get stuck in the fault
> > handler waiting for memory, which is pre
On Fri, 11 Apr 2025 14:45:49 +0200
Christian König wrote:
> Am 11.04.25 um 14:02 schrieb Boris Brezillon:
> >>> I guess this leaves older GPUs that don't support incremental
> >>> rendering in a bad place though.
> >> Well what's the handling th
On Fri, 11 Apr 2025 12:55:57 +0200
Christian König wrote:
> Am 11.04.25 um 10:38 schrieb Boris Brezillon:
> > On Fri, 11 Apr 2025 10:04:07 +0200
> > Christian König wrote:
> >
> >> Am 10.04.25 um 20:41 schrieb Boris Brezillon:
> >>> On Thu, 10 Apr 2
On Fri, 11 Apr 2025 10:04:07 +0200
Christian König wrote:
> Am 10.04.25 um 20:41 schrieb Boris Brezillon:
> > On Thu, 10 Apr 2025 14:01:03 -0400
> > Alyssa Rosenzweig wrote:
> >
> >>>>> In Panfrost and Lima, we don't have this concept of "in
Hi Christian,
On Thu, 10 Apr 2025 20:52:27 +0200
Christian König wrote:
> Am 10.04.25 um 19:20 schrieb Boris Brezillon:
> > [SNIP]
> >>>> Faulting is only legal when you have something like HMM, SVM or
> >>>> whatever you call it. And then you can
On Thu, 10 Apr 2025 14:01:03 -0400
Alyssa Rosenzweig wrote:
> > > > In Panfrost and Lima, we don't have this concept of "incremental
> > > > rendering", so when we fail the allocation, we just fail the GPU job
> > > > with an unhandled GPU fault.
> > >
> > > To be honest I think that this is
Hi Christian,
On Thu, 10 Apr 2025 18:43:29 +0200
Christian König wrote:
> Hi Boris,
>
> Am 10.04.25 um 17:53 schrieb Boris Brezillon:
> > Hi Christian,
> >
> > On Thu, 10 Apr 2025 17:05:07 +0200
> > Christian König wrote:
> >
> >> Hi Boris,
On Thu, 10 Apr 2025 17:35:46 +0100
Karunika Choo wrote:
> This patch adds 64-bit register accessors to simplify register access in
> Panthor. It also adds 32-bit and 64-bit variants for read_poll_timeout.
>
> This patch also updates Panthor to use the new 64-bit accessors and poll
> functions.
>
On Wed, 9 Apr 2025 14:00:54 +0100
Karunika Choo wrote:
> On 21/03/2025 07:48, Boris Brezillon wrote:
> > On Thu, 20 Mar 2025 11:17:33 +
> > Karunika Choo wrote:
> >
> >> This patch adds 64-bit register accessors to simplify register access in
> >>
Hi Christian,
On Thu, 10 Apr 2025 17:05:07 +0200
Christian König wrote:
> Hi Boris,
>
> thanks for looping me in. Can you also send the full patch set to me since I
> don't see that on the mailing list (yet maybe).
>
> Am 10.04.25 um 16:48 schrieb Boris Brezillon:
>
ab MRs, here's a link [1] to a Draft
> MR grouping those changes, but I'm in no way asking that the review
> happens on gitlab.
>
> Regards,
>
> Boris
>
> [1]https://gitlab.freedesktop.org/panfrost/linux/-/merge_requests/16
> [2]https://lore.kernel.org/lkml/202503
On Thu, 10 Apr 2025 14:20:59 +0100
Karunika Choo wrote:
> On 21/03/2025 08:02, Boris Brezillon wrote:
> > On Thu, 20 Mar 2025 11:17:37 +
> > Karunika Choo wrote:
> >
> >> This patch replaces the previous panthor_model structure with a simple
> >&
On Wed, 9 Apr 2025 14:07:20 +0100
Karunika Choo wrote:
> On 21/03/2025 07:53, Boris Brezillon wrote:
> > On Thu, 20 Mar 2025 11:17:34 +
> > Karunika Choo wrote:
> >
> >> This patch updates Panthor to use the new 64-bit accessors and poll
> >> func
On Fri, 4 Apr 2025 10:09:28 +0200
Boris Brezillon wrote:
> Hello,
>
> This is a collection of fixes for bugs found while working on adding
> JM support to panthor. Those are not particularly tied to JM support
> and are worth having regardless.
>
> Note that the last two
l BO and/or mapped onto the FW's address space.
>
> Signed-off-by: Adrián Larumbe
A couple minor things below, once addressed, this is
`Reviewed-by: Boris Brezillon `
> ---
> drivers/gpu/drm/panthor/panthor_device.c | 5 +
> drivers/gpu/drm/panthor/panthor_device.h | 1
On Tue, 8 Apr 2025 23:24:22 +0100
Adrián Larumbe wrote:
> Allow UM to label a BO for which it possesses a DRM handle.
>
> Signed-off-by: Adrián Larumbe
> Reviewed-by: Liviu Dudau
Just one minor doc issue below, but with this fixed, it's
Reviewed-by: Boris Brezillon
>
n the
> future, this would have to change.
>
> Signed-off-by: Adrián Larumbe
Just one modification suggested on a label, but this looks good
otherwise
Reviewed-by: Boris Brezillon
> ---
> drivers/gpu/drm/panthor/panthor_fw.c| 8 +---
> drivers/gpu/drm/panthor
Hi Philipp,
On Wed, 9 Apr 2025 14:06:37 +0200
Philipp Stanner wrote:
> dma_fence_is_signaled()'s name strongly reads as if this function were
> intended for checking whether a fence is already signaled. Also the
> boolean it returns hints at that.
>
> The function's behavior, however, is more
time, but allocating it is the responsibility
> of callers.
>
> Signed-off-by: Adrián Larumbe
One minor thing below, but this looks good otherwise
Reviewed-by: Boris Brezillon
> ---
> drivers/gpu/drm/panthor/panthor_gem.c | 38 +++
> driv
On Tue, 8 Apr 2025 23:24:24 +0100
Adrián Larumbe wrote:
> Add a device DebugFS file that displays a complete list of all the DRM
> GEM objects that are exposed to UM through a DRM handle.
>
> Since leaking object identifiers that might belong to a different NS is
> inadmissible, this functional
On Tue, 8 Apr 2025 14:38:44 +0100
Adrián Larumbe wrote:
> > > diff --git a/drivers/gpu/drm/panthor/panthor_gem.c
> > > b/drivers/gpu/drm/panthor/panthor_gem.c
> > > index 44d027e6d664..2fc87be9b700 100644
> > > --- a/drivers/gpu/drm/panthor/panthor_gem.c
> > > +++ b/drivers/gpu/drm/panthor/panth
On Wed, 2 Apr 2025 12:54:29 +0100
Adrián Larumbe wrote:
> +static void panthor_gem_debugfs_bo_print(struct panthor_gem_object *bo,
> + struct seq_file *m,
> + struct gem_size_totals *totals)
> +{
> + unsigned int refco
On Tue, 8 Apr 2025 15:38:18 +0100
Adrián Larumbe wrote:
> On 08.04.2025 15:47, Boris Brezillon wrote:
> On Tue, 8 Apr 2025 14:38:44 +0100
> Adrián Larumbe wrote:
>
> > > > > diff --git a/drivers/gpu/drm/panthor/panthor_gem.c
> > > > > b/drivers/gpu
te (Danilo)
> - Add doc (Danilo)
>
> Cc: Danilo Krummrich
> Cc: Matthew Brost
> Cc: Boris Brezillon
> Cc:
> Signed-off-by: Himal Prasad Ghimiray
>
> ---
> RFC Link:
> https://lore.kernel.org/intel-xe/20250314080226.2059819-1-himal.prasad.ghimi...@
On Fri, 4 Apr 2025 16:58:20 +0200
Thomas Zimmermann wrote:
> Hi
>
> Am 04.04.25 um 16:52 schrieb Boris Brezillon:
> > On Fri, 4 Apr 2025 10:01:50 +0200
> > Thomas Zimmermann wrote:
> >
> >>>> In your case, vmap an pin both intent to hold the shmem p
On Tue, 1 Apr 2025 17:17:40 +0100
Liviu Dudau wrote:
> On Tue, Apr 01, 2025 at 09:57:08AM +0200, Boris Brezillon wrote:
> > When the device is coherent, panthor_gpu_coherency_init() will read
> > GPU_COHERENCY_FEATURES to make sure the GPU supports the ACE-Lite
> > coherency
On Thu, 20 Mar 2025 11:17:34 +
Karunika Choo wrote:
> This patch updates Panthor to use the new 64-bit accessors and poll
> functions.
nit: I don't think it makes sense to dissociate the introduction of the
new helpers and their use. Could we squash this patch into the previous
one?
>
> Si
This lets the UMD flag buffers are alloc-on-fault (AKA lazy allocation,
AKA alloc-on-demand). The ultimate goal is to use this infrastructure
for heap objects, but commit only deals with GEM/VM bits.
Signed-off-by: Boris Brezillon
---
drivers/gpu/drm/panthor/panthor_drv.c | 20 +-
drivers/gpu
On Thu, 20 Mar 2025 11:17:39 +
Karunika Choo wrote:
> As the FLUSH_MEM and FLUSH_PT commands are deprecated in GPUs from
> Mali-G720 onwards, this patch adds support for performing cache
> maintenance via the FLUSH_CACHES command in GPU_CONTROL, in place of
> FLUSH_MEM and FLUSH_PT based on P
has been resumed
to prevent that.
Changes in v2:
- Add Liviu's R-b
Changes in v3:
- Add Steve's R-b
Fixes: dd7db8d911a1 ("drm/panthor: Explicitly set the coherency mode")
Signed-off-by: Boris Brezillon
Reviewed-by: Liviu Dudau
Reviewed-by: Steven Price
---
dri
Hi Thomas,
On Mon, 31 Mar 2025 09:13:59 +0200
Thomas Zimmermann wrote:
> Hi
>
> Am 26.03.25 um 03:14 schrieb Adrián Larumbe:
> > This patch series is a proposal for implementing sparse page allocations
> > for shmem objects. It was initially motivated by a kind of BO managed by
> > the Panfrost
Use the new gem_shmem helpers providing sparse GEM backing so we can
simplify the code, and finally have a non-blocking allocation scheme
in the fault handler path.
Signed-off-by: Boris Brezillon
---
drivers/gpu/drm/panfrost/panfrost_drv.c | 2 +-
drivers/gpu/drm/panfrost/panfrost_gem.c | 37
Make heap chunk allocation non-blocking when we are in the growing
path. This way, we can fail the job and signal its fence instead of
blocking on memory reclaim, which will become problematic once we throw
a memory shrinker into the mix.
Signed-off-by: Boris Brezillon
---
drivers/gpu/drm
cking the writer/reader early
on a fault will just make it crash, which is eventually want would
happen anyway.
Regards,
Boris
Boris Brezillon (3):
drm/panthor: Call panthor_gpu_coherency_init() after PM resume()
drm/panthor: Update panthor_mmu::irq::mask when needed
drm/panthor: Let IRQ han
has been resumed
to prevent that.
Fixes: dd7db8d911a1 ("drm/panthor: Explicitly set the coherency mode")
Signed-off-by: Boris Brezillon
---
drivers/gpu/drm/panthor/panthor_device.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/panthor/pantho
GPU_COHERENCY_ACE and GPU_COHERENCY_ACE_LITE definitions have been
swapped.
Changes in v2:
- New patch
Changes in v3:
- Add Steve's R-b
Reported-by: Liviu Dudau
Fixes: 546b366600ef ("drm/panthor: Add GPU register definitions")
Signed-off-by: Boris Brezillon
Reviewed-b
On Fri, 4 Apr 2025 10:01:50 +0200
Thomas Zimmermann wrote:
> >> In your case, vmap an pin both intent to hold the shmem pages in memory.
> >> They might be build on top of the same implementation, but one should
> >> not be implemented with the other because of their different meanings.
> > But
On Fri, 4 Apr 2025 11:26:30 +0200
Boris Brezillon wrote:
> diff --git a/include/uapi/drm/panthor_drm.h b/include/uapi/drm/panthor_drm.h
> index 97e2c4510e69..8071f1c438e2 100644
> --- a/include/uapi/drm/panthor_drm.h
> +++ b/include/uapi/drm/panthor_drm.h
> @@ -615,6 +6
g/dri-devel/20250218232552.3450939-1-adrian.laru...@collabora.com/
Adrián Larumbe (1):
drm/gem: Add helpers to request a range of pages on a GEM
Boris Brezillon (7):
drm/gem-shmem: Support sparse backing
drm/panfrost: Switch to sparse gem shmem to implement our
alloc-on-fault
drm/panth
This will be used by the heap logic to allow for real non-blocking
allocations when growing the heap.
Signed-off-by: Boris Brezillon
---
drivers/gpu/drm/panthor/panthor_fw.c| 6 +++---
drivers/gpu/drm/panthor/panthor_gem.c | 7 ++-
drivers/gpu/drm/panthor/panthor_gem.h | 4
This allows one to pre-allocate resources on a sparse BO to avoid
faulting when the GPU accesses the memory region. Will be used by
the heap logic to pre-populate a heap object with a predefined number
of chunks.
Signed-off-by: Boris Brezillon
---
drivers/gpu/drm/panthor/panthor_mmu.c | 25
From: Adrián Larumbe
This new API provides a way to partially populate/unpopulate a GEM
object, and also lets the caller specify the GFP flags to use for
the allocation.
This will help drivers that need to support sparse/alloc-on-demand
GEM objects.
Signed-off-by: Adrián Larumbe
---
drivers/g
1 - 100 of 1674 matches
Mail list logo
