* Re: [PATCH] drm: Permit video-buffers writecombine mapping for MIPS
2019-04-23 12:31 [PATCH] drm: Permit video-buffers writecombine mapping for MIPS Serge Semin
@ 2019-04-23 12:36 ` Koenig, Christian
2019-04-23 17:52 ` Paul Burton
2019-06-17 13:47 ` Serge Semin
2 siblings, 0 replies; 6+ messages in thread
From: Koenig, Christian @ 2019-04-23 12:36 UTC (permalink / raw)
To: Serge Semin, Maarten Lankhorst, Maxime Ripard, Sean Paul,
David Airlie, Daniel Vetter, Huang, Ray, Zhang, Jerry
Cc: dri-devel@lists.freedesktop.org, linux-mips@vger.kernel.org,
linux-kernel@vger.kernel.org, Ralf Baechle, Paul Burton,
James Hogan, Vadim V . Vlasov
Am 23.04.19 um 14:31 schrieb Serge Semin:
> Since commit 4b050ba7a66c ("MIPS: pgtable.h: Implement the
> pgprot_writecombine function for MIPS") and commit c4687b15a848 ("MIPS: Fix
> definition of pgprot_writecombine()") write-combine vma mapping is
> available to be used by kernel subsystems for MIPS. In particular the
> uncached accelerated attribute is requested to be set by ioremap_wc()
> method and by generic PCI memory pages/ranges mapping methods. The same
> is done by the drm_io_prot()/ttm_io_prot() functions in case if
> write-combine flag is set for vma's passed for mapping. But for some
> reason the pgprot_writecombine() method calling is ifdefed to be a
> platform-specific with MIPS system being marked as lacking of one. At the
> very least it doesn't reflect the current MIPS platform implementation.
> So in order to improve the DRM subsystem performance on MIPS with UCA
> mapping enabled, we need to have pgprot_writecombine() called for buffers,
> which need store operations being combined. In case if particular MIPS
> chip doesn't support the UCA attribute, the mapping will fall back to
> noncached.
>
> Cc: Ralf Baechle <ralf@linux-mips.org>
> Cc: Paul Burton <paul.burton@mips.com>
> Cc: James Hogan <jhogan@kernel.org>
> Signed-off-by: Vadim V. Vlasov <vadim.vlasov@t-platforms.ru>
> Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Not sure about all the details, but at least from the two mile high view
that seems to make sense.
Acked-by: Christian König <christian.koenig@amd.com>
> ---
> drivers/gpu/drm/drm_vm.c | 5 +++--
> drivers/gpu/drm/ttm/ttm_bo_util.c | 4 ++--
> 2 files changed, 5 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
> index c3301046dfaa..50178dc64060 100644
> --- a/drivers/gpu/drm/drm_vm.c
> +++ b/drivers/gpu/drm/drm_vm.c
> @@ -62,7 +62,8 @@ static pgprot_t drm_io_prot(struct drm_local_map *map,
> /* We don't want graphics memory to be mapped encrypted */
> tmp = pgprot_decrypted(tmp);
>
> -#if defined(__i386__) || defined(__x86_64__) || defined(__powerpc__)
> +#if defined(__i386__) || defined(__x86_64__) || defined(__powerpc__) || \
> + defined(__mips__)
> if (map->type == _DRM_REGISTERS && !(map->flags & _DRM_WRITE_COMBINING))
> tmp = pgprot_noncached(tmp);
> else
> @@ -73,7 +74,7 @@ static pgprot_t drm_io_prot(struct drm_local_map *map,
> tmp = pgprot_writecombine(tmp);
> else
> tmp = pgprot_noncached(tmp);
> -#elif defined(__sparc__) || defined(__arm__) || defined(__mips__)
> +#elif defined(__sparc__) || defined(__arm__)
> tmp = pgprot_noncached(tmp);
> #endif
> return tmp;
> diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
> index 895d77d799e4..9f918b992f7e 100644
> --- a/drivers/gpu/drm/ttm/ttm_bo_util.c
> +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
> @@ -539,13 +539,13 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp)
> tmp = pgprot_noncached(tmp);
> #endif
> #if defined(__ia64__) || defined(__arm__) || defined(__aarch64__) || \
> - defined(__powerpc__)
> + defined(__powerpc__) || defined(__mips__)
> if (caching_flags & TTM_PL_FLAG_WC)
> tmp = pgprot_writecombine(tmp);
> else
> tmp = pgprot_noncached(tmp);
> #endif
> -#if defined(__sparc__) || defined(__mips__)
> +#if defined(__sparc__)
> tmp = pgprot_noncached(tmp);
> #endif
> return tmp;
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [PATCH] drm: Permit video-buffers writecombine mapping for MIPS
2019-04-23 12:31 [PATCH] drm: Permit video-buffers writecombine mapping for MIPS Serge Semin
2019-04-23 12:36 ` Koenig, Christian
@ 2019-04-23 17:52 ` Paul Burton
2019-06-17 13:47 ` Serge Semin
2 siblings, 0 replies; 6+ messages in thread
From: Paul Burton @ 2019-04-23 17:52 UTC (permalink / raw)
To: Serge Semin
Cc: Maarten Lankhorst, Maxime Ripard, Sean Paul, David Airlie,
Daniel Vetter, Christian Koenig, Huang Rui, Junwei Zhang,
dri-devel@lists.freedesktop.org, linux-mips@vger.kernel.org,
linux-kernel@vger.kernel.org, Ralf Baechle, James Hogan,
Vadim V . Vlasov
Hi Serge,
On Tue, Apr 23, 2019 at 03:31:22PM +0300, Serge Semin wrote:
> Since commit 4b050ba7a66c ("MIPS: pgtable.h: Implement the
> pgprot_writecombine function for MIPS") and commit c4687b15a848 ("MIPS: Fix
> definition of pgprot_writecombine()") write-combine vma mapping is
> available to be used by kernel subsystems for MIPS. In particular the
> uncached accelerated attribute is requested to be set by ioremap_wc()
> method and by generic PCI memory pages/ranges mapping methods. The same
> is done by the drm_io_prot()/ttm_io_prot() functions in case if
> write-combine flag is set for vma's passed for mapping. But for some
> reason the pgprot_writecombine() method calling is ifdefed to be a
> platform-specific with MIPS system being marked as lacking of one. At the
> very least it doesn't reflect the current MIPS platform implementation.
> So in order to improve the DRM subsystem performance on MIPS with UCA
> mapping enabled, we need to have pgprot_writecombine() called for buffers,
> which need store operations being combined. In case if particular MIPS
> chip doesn't support the UCA attribute, the mapping will fall back to
> noncached.
>
> Cc: Ralf Baechle <ralf@linux-mips.org>
> Cc: Paul Burton <paul.burton@mips.com>
> Cc: James Hogan <jhogan@kernel.org>
> Signed-off-by: Vadim V. Vlasov <vadim.vlasov@t-platforms.ru>
> Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
> ---
> drivers/gpu/drm/drm_vm.c | 5 +++--
> drivers/gpu/drm/ttm/ttm_bo_util.c | 4 ++--
> 2 files changed, 5 insertions(+), 4 deletions(-)
Looks good to me:
Reviewed-by: Paul Burton <paul.burton@mips.com>
Thanks,
Paul
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [PATCH] drm: Permit video-buffers writecombine mapping for MIPS
2019-04-23 12:31 [PATCH] drm: Permit video-buffers writecombine mapping for MIPS Serge Semin
2019-04-23 12:36 ` Koenig, Christian
2019-04-23 17:52 ` Paul Burton
@ 2019-06-17 13:47 ` Serge Semin
2019-06-18 19:52 ` Sean Paul
2 siblings, 1 reply; 6+ messages in thread
From: Serge Semin @ 2019-06-17 13:47 UTC (permalink / raw)
To: Maarten Lankhorst, Maxime Ripard, Sean Paul, David Airlie,
Daniel Vetter, Christian Koenig, Huang Rui, Junwei Zhang,
Greg Kroah-Hartman
Cc: dri-devel, linux-mips, linux-kernel, Ralf Baechle, Paul Burton,
James Hogan, Vadim V . Vlasov
Hello folks,
Any updates of this patch status? It has been here for about two months.
Regards,
-Sergey
On Tue, Apr 23, 2019 at 03:31:22PM +0300, Serge Semin wrote:
> Since commit 4b050ba7a66c ("MIPS: pgtable.h: Implement the
> pgprot_writecombine function for MIPS") and commit c4687b15a848 ("MIPS: Fix
> definition of pgprot_writecombine()") write-combine vma mapping is
> available to be used by kernel subsystems for MIPS. In particular the
> uncached accelerated attribute is requested to be set by ioremap_wc()
> method and by generic PCI memory pages/ranges mapping methods. The same
> is done by the drm_io_prot()/ttm_io_prot() functions in case if
> write-combine flag is set for vma's passed for mapping. But for some
> reason the pgprot_writecombine() method calling is ifdefed to be a
> platform-specific with MIPS system being marked as lacking of one. At the
> very least it doesn't reflect the current MIPS platform implementation.
> So in order to improve the DRM subsystem performance on MIPS with UCA
> mapping enabled, we need to have pgprot_writecombine() called for buffers,
> which need store operations being combined. In case if particular MIPS
> chip doesn't support the UCA attribute, the mapping will fall back to
> noncached.
>
> Cc: Ralf Baechle <ralf@linux-mips.org>
> Cc: Paul Burton <paul.burton@mips.com>
> Cc: James Hogan <jhogan@kernel.org>
> Signed-off-by: Vadim V. Vlasov <vadim.vlasov@t-platforms.ru>
> Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
> ---
> drivers/gpu/drm/drm_vm.c | 5 +++--
> drivers/gpu/drm/ttm/ttm_bo_util.c | 4 ++--
> 2 files changed, 5 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
> index c3301046dfaa..50178dc64060 100644
> --- a/drivers/gpu/drm/drm_vm.c
> +++ b/drivers/gpu/drm/drm_vm.c
> @@ -62,7 +62,8 @@ static pgprot_t drm_io_prot(struct drm_local_map *map,
> /* We don't want graphics memory to be mapped encrypted */
> tmp = pgprot_decrypted(tmp);
>
> -#if defined(__i386__) || defined(__x86_64__) || defined(__powerpc__)
> +#if defined(__i386__) || defined(__x86_64__) || defined(__powerpc__) || \
> + defined(__mips__)
> if (map->type == _DRM_REGISTERS && !(map->flags & _DRM_WRITE_COMBINING))
> tmp = pgprot_noncached(tmp);
> else
> @@ -73,7 +74,7 @@ static pgprot_t drm_io_prot(struct drm_local_map *map,
> tmp = pgprot_writecombine(tmp);
> else
> tmp = pgprot_noncached(tmp);
> -#elif defined(__sparc__) || defined(__arm__) || defined(__mips__)
> +#elif defined(__sparc__) || defined(__arm__)
> tmp = pgprot_noncached(tmp);
> #endif
> return tmp;
> diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
> index 895d77d799e4..9f918b992f7e 100644
> --- a/drivers/gpu/drm/ttm/ttm_bo_util.c
> +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
> @@ -539,13 +539,13 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp)
> tmp = pgprot_noncached(tmp);
> #endif
> #if defined(__ia64__) || defined(__arm__) || defined(__aarch64__) || \
> - defined(__powerpc__)
> + defined(__powerpc__) || defined(__mips__)
> if (caching_flags & TTM_PL_FLAG_WC)
> tmp = pgprot_writecombine(tmp);
> else
> tmp = pgprot_noncached(tmp);
> #endif
> -#if defined(__sparc__) || defined(__mips__)
> +#if defined(__sparc__)
> tmp = pgprot_noncached(tmp);
> #endif
> return tmp;
> --
> 2.21.0
>
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [PATCH] drm: Permit video-buffers writecombine mapping for MIPS
2019-06-17 13:47 ` Serge Semin
@ 2019-06-18 19:52 ` Sean Paul
2019-06-21 6:07 ` Serge Semin
0 siblings, 1 reply; 6+ messages in thread
From: Sean Paul @ 2019-06-18 19:52 UTC (permalink / raw)
To: Serge Semin
Cc: Maarten Lankhorst, Maxime Ripard, Sean Paul, David Airlie,
Daniel Vetter, Christian Koenig, Huang Rui, Junwei Zhang,
Greg Kroah-Hartman, dri-devel, linux-mips, linux-kernel,
Ralf Baechle, Paul Burton, James Hogan, Vadim V . Vlasov
On Mon, Jun 17, 2019 at 04:47:30PM +0300, Serge Semin wrote:
> Hello folks,
>
> Any updates of this patch status? It has been here for about two months.
>
Sorry for the mixup, looks like this one just fell through the cracks. I've
applied it to drm-misc-next with the attached Ack and Review.
Sean
> Regards,
> -Sergey
>
> On Tue, Apr 23, 2019 at 03:31:22PM +0300, Serge Semin wrote:
> > Since commit 4b050ba7a66c ("MIPS: pgtable.h: Implement the
> > pgprot_writecombine function for MIPS") and commit c4687b15a848 ("MIPS: Fix
> > definition of pgprot_writecombine()") write-combine vma mapping is
> > available to be used by kernel subsystems for MIPS. In particular the
> > uncached accelerated attribute is requested to be set by ioremap_wc()
> > method and by generic PCI memory pages/ranges mapping methods. The same
> > is done by the drm_io_prot()/ttm_io_prot() functions in case if
> > write-combine flag is set for vma's passed for mapping. But for some
> > reason the pgprot_writecombine() method calling is ifdefed to be a
> > platform-specific with MIPS system being marked as lacking of one. At the
> > very least it doesn't reflect the current MIPS platform implementation.
> > So in order to improve the DRM subsystem performance on MIPS with UCA
> > mapping enabled, we need to have pgprot_writecombine() called for buffers,
> > which need store operations being combined. In case if particular MIPS
> > chip doesn't support the UCA attribute, the mapping will fall back to
> > noncached.
> >
> > Cc: Ralf Baechle <ralf@linux-mips.org>
> > Cc: Paul Burton <paul.burton@mips.com>
> > Cc: James Hogan <jhogan@kernel.org>
> > Signed-off-by: Vadim V. Vlasov <vadim.vlasov@t-platforms.ru>
> > Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
> > ---
> > drivers/gpu/drm/drm_vm.c | 5 +++--
> > drivers/gpu/drm/ttm/ttm_bo_util.c | 4 ++--
> > 2 files changed, 5 insertions(+), 4 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
> > index c3301046dfaa..50178dc64060 100644
> > --- a/drivers/gpu/drm/drm_vm.c
> > +++ b/drivers/gpu/drm/drm_vm.c
> > @@ -62,7 +62,8 @@ static pgprot_t drm_io_prot(struct drm_local_map *map,
> > /* We don't want graphics memory to be mapped encrypted */
> > tmp = pgprot_decrypted(tmp);
> >
> > -#if defined(__i386__) || defined(__x86_64__) || defined(__powerpc__)
> > +#if defined(__i386__) || defined(__x86_64__) || defined(__powerpc__) || \
> > + defined(__mips__)
> > if (map->type == _DRM_REGISTERS && !(map->flags & _DRM_WRITE_COMBINING))
> > tmp = pgprot_noncached(tmp);
> > else
> > @@ -73,7 +74,7 @@ static pgprot_t drm_io_prot(struct drm_local_map *map,
> > tmp = pgprot_writecombine(tmp);
> > else
> > tmp = pgprot_noncached(tmp);
> > -#elif defined(__sparc__) || defined(__arm__) || defined(__mips__)
> > +#elif defined(__sparc__) || defined(__arm__)
> > tmp = pgprot_noncached(tmp);
> > #endif
> > return tmp;
> > diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
> > index 895d77d799e4..9f918b992f7e 100644
> > --- a/drivers/gpu/drm/ttm/ttm_bo_util.c
> > +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
> > @@ -539,13 +539,13 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp)
> > tmp = pgprot_noncached(tmp);
> > #endif
> > #if defined(__ia64__) || defined(__arm__) || defined(__aarch64__) || \
> > - defined(__powerpc__)
> > + defined(__powerpc__) || defined(__mips__)
> > if (caching_flags & TTM_PL_FLAG_WC)
> > tmp = pgprot_writecombine(tmp);
> > else
> > tmp = pgprot_noncached(tmp);
> > #endif
> > -#if defined(__sparc__) || defined(__mips__)
> > +#if defined(__sparc__)
> > tmp = pgprot_noncached(tmp);
> > #endif
> > return tmp;
> > --
> > 2.21.0
> >
--
Sean Paul, Software Engineer, Google / Chromium OS
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [PATCH] drm: Permit video-buffers writecombine mapping for MIPS
2019-06-18 19:52 ` Sean Paul
@ 2019-06-21 6:07 ` Serge Semin
0 siblings, 0 replies; 6+ messages in thread
From: Serge Semin @ 2019-06-21 6:07 UTC (permalink / raw)
To: Sean Paul
Cc: Maarten Lankhorst, Maxime Ripard, David Airlie, Daniel Vetter,
Christian Koenig, Huang Rui, Junwei Zhang, Greg Kroah-Hartman,
dri-devel, linux-mips, linux-kernel, Ralf Baechle, Paul Burton,
James Hogan, Vadim V . Vlasov
Hello Sean,
On Tue, Jun 18, 2019 at 03:52:04PM -0400, Sean Paul wrote:
> On Mon, Jun 17, 2019 at 04:47:30PM +0300, Serge Semin wrote:
> > Hello folks,
> >
> > Any updates of this patch status? It has been here for about two months.
> >
>
> Sorry for the mixup, looks like this one just fell through the cracks. I've
> applied it to drm-misc-next with the attached Ack and Review.
>
Great! Thank you.
Regards,
-Sergey
> Sean
>
>
> > Regards,
> > -Sergey
> >
> > On Tue, Apr 23, 2019 at 03:31:22PM +0300, Serge Semin wrote:
> > > Since commit 4b050ba7a66c ("MIPS: pgtable.h: Implement the
> > > pgprot_writecombine function for MIPS") and commit c4687b15a848 ("MIPS: Fix
> > > definition of pgprot_writecombine()") write-combine vma mapping is
> > > available to be used by kernel subsystems for MIPS. In particular the
> > > uncached accelerated attribute is requested to be set by ioremap_wc()
> > > method and by generic PCI memory pages/ranges mapping methods. The same
> > > is done by the drm_io_prot()/ttm_io_prot() functions in case if
> > > write-combine flag is set for vma's passed for mapping. But for some
> > > reason the pgprot_writecombine() method calling is ifdefed to be a
> > > platform-specific with MIPS system being marked as lacking of one. At the
> > > very least it doesn't reflect the current MIPS platform implementation.
> > > So in order to improve the DRM subsystem performance on MIPS with UCA
> > > mapping enabled, we need to have pgprot_writecombine() called for buffers,
> > > which need store operations being combined. In case if particular MIPS
> > > chip doesn't support the UCA attribute, the mapping will fall back to
> > > noncached.
> > >
> > > Cc: Ralf Baechle <ralf@linux-mips.org>
> > > Cc: Paul Burton <paul.burton@mips.com>
> > > Cc: James Hogan <jhogan@kernel.org>
> > > Signed-off-by: Vadim V. Vlasov <vadim.vlasov@t-platforms.ru>
> > > Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
> > > ---
> > > drivers/gpu/drm/drm_vm.c | 5 +++--
> > > drivers/gpu/drm/ttm/ttm_bo_util.c | 4 ++--
> > > 2 files changed, 5 insertions(+), 4 deletions(-)
> > >
> > > diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
> > > index c3301046dfaa..50178dc64060 100644
> > > --- a/drivers/gpu/drm/drm_vm.c
> > > +++ b/drivers/gpu/drm/drm_vm.c
> > > @@ -62,7 +62,8 @@ static pgprot_t drm_io_prot(struct drm_local_map *map,
> > > /* We don't want graphics memory to be mapped encrypted */
> > > tmp = pgprot_decrypted(tmp);
> > >
> > > -#if defined(__i386__) || defined(__x86_64__) || defined(__powerpc__)
> > > +#if defined(__i386__) || defined(__x86_64__) || defined(__powerpc__) || \
> > > + defined(__mips__)
> > > if (map->type == _DRM_REGISTERS && !(map->flags & _DRM_WRITE_COMBINING))
> > > tmp = pgprot_noncached(tmp);
> > > else
> > > @@ -73,7 +74,7 @@ static pgprot_t drm_io_prot(struct drm_local_map *map,
> > > tmp = pgprot_writecombine(tmp);
> > > else
> > > tmp = pgprot_noncached(tmp);
> > > -#elif defined(__sparc__) || defined(__arm__) || defined(__mips__)
> > > +#elif defined(__sparc__) || defined(__arm__)
> > > tmp = pgprot_noncached(tmp);
> > > #endif
> > > return tmp;
> > > diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
> > > index 895d77d799e4..9f918b992f7e 100644
> > > --- a/drivers/gpu/drm/ttm/ttm_bo_util.c
> > > +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
> > > @@ -539,13 +539,13 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp)
> > > tmp = pgprot_noncached(tmp);
> > > #endif
> > > #if defined(__ia64__) || defined(__arm__) || defined(__aarch64__) || \
> > > - defined(__powerpc__)
> > > + defined(__powerpc__) || defined(__mips__)
> > > if (caching_flags & TTM_PL_FLAG_WC)
> > > tmp = pgprot_writecombine(tmp);
> > > else
> > > tmp = pgprot_noncached(tmp);
> > > #endif
> > > -#if defined(__sparc__) || defined(__mips__)
> > > +#if defined(__sparc__)
> > > tmp = pgprot_noncached(tmp);
> > > #endif
> > > return tmp;
> > > --
> > > 2.21.0
> > >
>
> --
> Sean Paul, Software Engineer, Google / Chromium OS
^ permalink raw reply [flat|nested] 6+ messages in thread