Hi Tvrtko,
[...]
> > @@ -768,6 +768,9 @@ i915_vma_insert(struct i915_vma *vma, struct
> > i915_gem_ww_ctx *ww,
> > GEM_BUG_ON(!IS_ALIGNED(alignment, I915_GTT_MIN_ALIGNMENT));
> > GEM_BUG_ON(!is_power_of_2(alignment));
> > + guard = vma->guard; /* retain guard across rebinds */
> > +
we avoid adding scratch pages to the entire GGTT we
don't need this hack anymore.
Signed-off-by: Andi Shyti
Cc: Thomas Hellström
Cc: Chris Wilson
Cc: Tvrtko Ursulin
---
drivers/gpu/drm/i915/gt/intel_ggtt.c | 69 ++--
drivers/gpu/drm/i915/gt/intel_gtt.h | 24
-off-by: Tejas Upadhyay
Signed-off-by: Tvrtko Ursulin
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/gem/i915_gem_domain.c | 13 +++
drivers/gpu/drm/i915/gt/intel_ggtt.c | 25 +-
drivers/gpu/drm/i915/i915_vma.c| 9
3 files changed, 23
Signed-off-by: Tejas Upadhyay
Signed-off-by: Tvrtko Ursulin
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/gt/intel_ggtt.c | 14
drivers/gpu/drm/i915/i915_gem_gtt.h | 3 ++-
drivers/gpu/drm/i915/i915_vma.c | 27 ++--
drivers/gpu/drm/i915
rapper.
The notable exceptions are the selftests that are testing exact
behaviour of i915_vma_pin/i915_vma_insert.
Signed-off-by: Chris Wilson
Signed-off-by: Tejas Upadhyay
Co-developed-by: Thomas Hellström
Signed-off-by: Thomas Hellström
Signed-off-by: Tvrtko Ursulin
Signed-off-by: Andi
n suspend / resume
time with VT-d enabled")
Andi
Andi Shyti (1):
Revert "drm/i915: Improve on suspend / resume time with VT-d enabled"
Chris Wilson (3):
drm/i915: Wrap all access to i915_vma.node.start|size
drm/i915: Introduce guard pages to i915_vma
drm/i915: Refine
)
> spin_unlock_irq(>closed_lock);
> }
>
> -static void force_unbind(struct i915_vma *vma)
> +static void force_unbind(struct i915_vma *vma, bool async)
I still like the defines on this, they look cleaner, but it's a
matter of taste.
Reviewed-by: Andi Shyti
Andi
> Just a short heads up on the history.
>
> /Thomas
>
>
> On Wed, 2022-11-09 at 18:40 +0100, Andi Shyti wrote:
> > Hi,
> >
> > This series adds guards around vma's but setting a pages at the
> > beginning and at the end that work as padding.
> &g
Hi Niranjana,
...
> -static void force_unbind(struct i915_vma *vma)
> +static void force_unbind(struct i915_vma *vma, bool async)
> {
> if (!drm_mm_node_allocated(>node))
> return;
> @@ -1725,7 +1727,21 @@ static void force_unbind(struct i915_vma *vma)
>
Hi Thomas,
On Wed, Nov 09, 2022 at 07:03:03PM +0100, Thomas Hellström wrote:
> Hi, Andi,
>
> This has been on the list before (three times I think) and at that
> point it (the guard pages) was NAK'd by Daniel as yet another
> complication, and a VT-d
> scanout workaround was implemented and
Hi,
This series adds guards around vma's but setting a pages at the
beginning and at the end that work as padding.
The first user of the vma guard are scanout objects which don't
need anymore to add scratch to all the unused ggtt's and speeding
up up considerably the boot and resume by several
rapper.
The notable exceptions are the selftests that are testing exact
behaviour of i915_vma_pin/i915_vma_insert.
Signed-off-by: Chris Wilson
Signed-off-by: Tejas Upadhyay
Co-developed-by: Thomas Hellström
Signed-off-by: Thomas Hellström
Signed-off-by: Tvrtko Ursulin
Signed-off-by: Andi
Signed-off-by: Tejas Upadhyay
Signed-off-by: Tvrtko Ursulin
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/gt/intel_ggtt.c | 14
drivers/gpu/drm/i915/i915_gem_gtt.h | 3 ++-
drivers/gpu/drm/i915/i915_vma.c | 27 ++--
drivers/gpu/drm/i915
-off-by: Tejas Upadhyay
Signed-off-by: Tvrtko Ursulin
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/gem/i915_gem_domain.c | 13 +++
drivers/gpu/drm/i915/gt/intel_ggtt.c | 25 +-
drivers/gpu/drm/i915/i915_vma.c| 9
3 files changed, 23
Please ignore, this series is rebased on the wrong branch.
Andi
On Wed, Nov 09, 2022 at 05:49:10PM +0100, Andi Shyti wrote:
> Hi,
>
> This patch series adds a padding around i915_vma's reducing
> consequently the need to add scratch to the unused GGTT.
>
> This speeds up con
-off-by: Tejas Upadhyay
Signed-off-by: Tvrtko Ursulin
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/gem/i915_gem_domain.c | 13 +++
drivers/gpu/drm/i915/gt/intel_ggtt.c | 25 +-
drivers/gpu/drm/i915/i915_vma.c| 9
3 files changed, 23
Cc: Matthew Auld
Reviewed-by: Matthew Auld
Signed-off-by: Tvrtko Ursulin
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/gt/intel_ggtt.c | 12 ++--
drivers/gpu/drm/i915/i915_gem_gtt.h | 1 +
drivers/gpu/drm/i915/i915_vma.c | 28 ++-
drivers/gpu/drm
rapper.
The notable exceptions are the selftests that are testing exact
behaviour of i915_vma_pin/i915_vma_insert.
Signed-off-by: Chris Wilson
Reviewed-by: Matthew Auld
Signed-off-by: Tvrtko Ursulin
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/display/intel_dpt.c | 4 +-
drivers/g
Hi,
This patch series adds a padding around i915_vma's reducing
consequently the need to add scratch to the unused GGTT.
This speeds up considerably the boot and resume by several
hundreds of milliseconds up to over a full second in slower
machines.
Andi
Chris Wilson (3):
drm/i915: Wrap all
Hi Niranjana,
[...]
> +/*
> + * VM_BIND feature version supported.
> + *
> + * The following versions of VM_BIND have been defined:
> + *
> + * 0: No VM_BIND support.
> + *
> + * 1: In VM_UNBIND calls, the UMD must specify the exact mappings created
> + *previously with VM_BIND, the ioctl
adjust certain functions to match the
> type of the ->show() and ->store() members in 'struct kobj_attribute'.
> Add a macro to generate functions for that can be called via both
> dev_attr_{show,store}() or kobj_attr_{show,store}() so that they can be
> called through both kobje
tr_{show,store}() so that they can be
called through both kobject locations without violating kCFI and adjust
the attribute groups to account for this.
Link: https://github.com/ClangBuiltLinux/linux/issues/1716
Reviewed-by: Andi Shyti
Reviewed-by: Andrzej Hajda
Reviewed-by: Kees Cook
Signed-off-b
Hi Niranjana,
[...]
> @@ -307,6 +307,8 @@ struct i915_vma {
> struct list_head non_priv_vm_bind_link;
> /* @vm_rebind_link: link to vm_rebind_list and protected by
> vm_rebind_lock */
> struct list_head vm_rebind_link; /* Link in vm_rebind_list */
> +
Commit 3e7abf814193 ("drm/i915: Extract GT render power state management")
removes the "trace_intel_gpu_freq_change()" trace points but
their definition was left without users. Remove it.
Suggested-by: Tvrtko Ursulin
Signed-off-by: Andi Shyti
Cc: Chris Wilson
---
m_atomic.o \
> + drm_atomic_uapi.o \
> + drm_auth.o drm_cache.o \
You forgot to split here and drm_cache.o goes after drm_bridge.o
Other than this there are no errors, I checked them all.
Reviewed-by: Andi Shyti
Andi
> + drm_blend.o \
> + drm_bridge.o \
> + drm_client.o \
> + drm_client_modeset.o \
> + drm_color_mgmt.o \
> + drm_connector.o \
> + drm_crtc.o \
[...]
Hi Niranjana,
On Mon, Oct 03, 2022 at 02:06:18PM -0700, Niranjana Vishwanathapura wrote:
> On Mon, Oct 03, 2022 at 05:53:37PM +0200, Andi Shyti wrote:
> > Hi Niranjana,
> >
> > [...]
> >
> > > + for_each_child(ce, child) {
> > > +
> Reviewed-by: Anshuman Gupta
This last patch is making me thing that the hwmon should have
been under gt rather than under i915. We leave it to a later
refactoring.
Reviewed-by: Andi Shyti
Thanks,
Andi
Hi Badal,
> diff --git a/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
> b/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
> index f9d6d3b08bba..19b9fe3ef237 100644
> --- a/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
> +++
Hi Badal,
[...]
> diff --git a/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
> b/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
> index 7525db243d74..f9d6d3b08bba 100644
> --- a/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
> +++
Hi Badal,
[...]
> > diff --git a/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
> > b/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
> > index 16e697b1db3d..7525db243d74 100644
> > --- a/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
> > +++
> + } else {
> + val_sku_unit = 0;
> + }
please remove the brackets here and, just a small nitpick:
move val_sky_unit inside the "with_intel_runtime_pm()" and
initialize it to '0', you will save the else statement.
Other than that:
Reviewed-by: Andi Shyti
Thanks,
Andi
Hi Badal,
[...]
> static void
> hwm_get_preregistration_info(struct drm_i915_private *i915)
> {
> + struct i915_hwmon *hwmon = i915->hwmon;
> +
> + if (IS_DG1(i915) || IS_DG2(i915))
why not GRAPHICS_VER(i915) >= 12 here?
Andi
> + hwmon->rg.gt_perf_status =
k
> Signed-off-by: Dale B Stimson
> Signed-off-by: Ashutosh Dixit
> Signed-off-by: Riana Tauro
> Signed-off-by: Badal Nilawar
> Acked-by: Guenter Roeck
> Reviewed-by: Ashutosh Dixit
> Reviewed-by: Anshuman Gupta
Reviewed-by: Andi Shyti
Andi
perhaps also in a comment... (continue)
>
> Thanks.
> --
> Ashutosh
>
> > v2:
> > - Fixed review comments(Ashutosh)
> > - Added function intel_rps_read_rpstat_fw to read RPSTAT without
> > forcewake, required especially for GEN6_RPSTAT1 (Ashutosh, Tv
Hi Niranjana,
On Sun, Oct 02, 2022 at 11:12:42PM -0700, Niranjana Vishwanathapura wrote:
> Rename __i915_request_await_bind() as i915_request_await_bind()
> and make it non-static as it will be used in execbuf3 ioctl path.
>
> Signed-off-by: Niranjana Vishwanathapura
Reviewed-by
Hi Niranjana,
[...]
> + for_each_child(ce, child) {
> + err = intel_context_pin_ww(child, ww);
> + GEM_BUG_ON(err);/* perma-pinned should incr a counter */
> + }
> +
> + for_each_child(ce, child) {
> + err = eb_pin_timeline(child, throttle,
SAGE_BOOKKEEP
> usage. dma-resv fence list will be updated with this usage
> during each submission with this VM in the new execbuf3
> ioctl path.
>
> Update i915_vma_is_active(), i915_vma_sync() and the
> __i915_vma_unbind_async() functions to properly handle
> persistent vmas.
&g
it as it's very easy to get tangled-up in
between all those defines:
Reviewed-by: Andi Shyti
For now I'm quite surprised to see how easily our CI gives green
lights :-P
On Sat, Sep 24, 2022 at 09:39:30PM -0700, Nathan Chancellor wrote:
> On Fri, Sep 23, 2022 at 09:57:47PM -0700, Kees Cook wr
tion
> of VA space. Hence, it do not support aliasing. ie., multiple
> mappings (at different VA) point to the same gtt_view of object.
> Skip vma_lookup for persistent vmas to support aliasing.
>
> Signed-off-by: Niranjana Vishwanathapura
> Signed-off-by: Andi Shyti
> ---
&
Hi Badal,
> > > +struct hwm_reg {
> > > +};
> > > +
> > > +struct hwm_drvdata {
> > > + struct i915_hwmon *hwmon;
> > > + struct intel_uncore *uncore;
> > > + struct device *hwmon_dev;
> > > + char name[12];
> > > +};
> > > +
> > > +struct i915_hwmon {
> > > + struct hwm_drvdata ddat;
> > > +
Hi Badal,
> +struct hwm_reg {
> +};
> +
> +struct hwm_drvdata {
> + struct i915_hwmon *hwmon;
> + struct intel_uncore *uncore;
> + struct device *hwmon_dev;
> + char name[12];
> +};
> +
> +struct i915_hwmon {
> + struct hwm_drvdata ddat;
> + struct mutex hwmon_lock;
Hi Matt, Lucas,
thanks for your feedback,
> > > + switch (gms) {
> > > + case 0x0 ... 0x10:
> > > + return gms * 32;
> > > + case 0x20:
> > > + return 1024;
> > > + case 0x30:
> > > + return 1536;
> > > + case 0x40:
> > > + return 2048;
> > > + case 0xf0 ... 0xfe:
Hi Aravind,
> +static int get_mtl_gms_size(struct intel_uncore *uncore)
> +{
> + u16 ggc, gms;
> +
> + ggc = intel_uncore_read16(uncore, _MMIO(0x108040));
> +
> + /* check GGMS, should be fixed 0x3 (8MB) */
> + if ((ggc & 0xc0) != 0xc0)
> + return -EIO;
> +
> + /*
Hi Badal,
On Mon, Sep 19, 2022 at 05:29:05PM +0530, Badal Nilawar wrote:
> Updated the CAGF functions to get actual resolved frequency of
> 3D and SAMedia
can you please use the imperative form? "Update" and not
"Updated".
Besides I don't really understand what you did from the
commit, can you
Pushed, Thanks!
Andi
On Fri, Sep 16, 2022 at 11:24:01AM +0200, Janusz Krzysztofik wrote:
> i915_perf assumes that it can use the i915_gem_context reference to
> protect its i915->gem.contexts.list iteration. However, this requires
> that we do not remove the context from the list until after we
ually known to the driver.
>
> To accomplish this we need to sprinkle a lot of for_each_gt calls around
> but is otherwise pretty un-eventuful.
>
> v2:
> - Consolidate adjacent GT loops in a couple places. (Daniele)
>
> Cc: Daniele Ceraolo Spurio
> Signed-off-by: Tvrtko Ursu
Hi Jani,
On Thu, Sep 15, 2022 at 03:25:15PM +0300, Jani Nikula wrote:
> On Wed, 14 Sep 2022, Matt Roper wrote:
> > Now that MTL is going to start providing two GTs, there are a few more
> > places in the driver that need to iterate over each GT instead of
> > operating directly on gt0. Also
Hi Matt,
On Wed, Sep 14, 2022 at 03:04:26PM -0700, Matt Roper wrote:
> From: Tvrtko Ursulin
>
> Walk all GTs when suspending.
>
> Signed-off-by: Tvrtko Ursulin
> Signed-off-by: Matt Roper
I had this as well... thanks again!
Reviewed-by: Andi Shyti
Andi
Hi Matt,
On Wed, Sep 14, 2022 at 03:04:25PM -0700, Matt Roper wrote:
> From: Tvrtko Ursulin
>
> Walk all GTs from i915_gem_resume when resuming engines.
>
> Cc: Andi Shyti
> Signed-off-by: Tvrtko Ursulin
> Signed-off-by: Matt Roper
I had this (and others) in my multi-
Hi Lucas,
On Mon, Sep 12, 2022 at 11:12:47AM -0700, Lucas De Marchi wrote:
> On Mon, Sep 12, 2022 at 06:59:53PM +0200, Andi Shyti wrote:
> > Hi Lucas,
> >
> > On Mon, Sep 12, 2022 at 09:19:38AM -0700, Lucas De Marchi wrote:
> > > Support for reading the fuses t
LL(i915) >= IP_VER(12, 60) &&
> + GRAPHICS_VER_FULL(i915) < IP_VER(12, 70)))
> + return;
> +
Isn't it easier if you wrote
if (GRAPHICS_VER_FULL(i915) < IP_VER(12, 60) ||
GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70))
Hi Rasmus,
Thanks for dropping in,
[...]
> >> + * @t1: data type or variable
> >> + * @t2: data type or variable
> >> + *
> >> + * The first and second arguments can be data types or variables or mixed
> >> (the
> >> + * first argument is the data type and the second argument is variable or
>
Hi Mauro,
[...]
> +/**
> + * intel_gt_pm_is_awake: Query whether the runtime PM is awake held
> + *
> + * @gt: pointer to the graphics engine
...
> +/**
> + * intel_gt_pm_get: grab a runtime PM reference ensuring that GT is powered
> up
> + * @gt: pointer to the graphics engine
...
> +/**
>
Hi Mauro,
On Fri, Sep 09, 2022 at 09:34:40AM +0200, Mauro Carvalho Chehab wrote:
> commit d1b48c1e7184 ("drm/i915: Replace execbuf vma ht with an idr")
> added a rbtree list to allow searching for obj/ctx.
>
> Document it.
>
> Reviewed-by: Rodrigo Vivi
> Signed-off-by: Mauro Carvalho Chehab
>
el-doc markups.
>
> Reviewed-by: Rodrigo Vivi
> Signed-off-by: Mauro Carvalho Chehab
nice cleanup!
Reviewed-by: Andi Shyti
Thanks,
Andi
> ---
>
> To avoid mailbombing on a large number of people, only mailing lists were C/C
> on the cover.
> See [PATCH v3 00/37] at:
&g
by: Mauro Carvalho Chehab
Reviewed-by: Andi Shyti
Andi
> ---
>
> To avoid mailbombing on a large number of people, only mailing lists were C/C
> on the cover.
> See [PATCH v3 00/37] at:
> https://lore.kernel.org/all/cover.1662708705.git.mche...@kernel.org/
>
> dri
s the second argument.
>
> Suggested-by: Kees Cook
> Signed-off-by: Gwan-gyeong Mun
> Cc: Thomas Hellström
> Cc: Matthew Auld
> Cc: Nirmoy Das
> Cc: Jani Nikula
> Cc: Andi Shyti
> Cc: Mauro Carvalho Chehab
> Cc: Andrzej Hajda
> Cc: K
Hi Kees,
On Fri, Sep 09, 2022 at 07:59:05PM +0900, Gwan-gyeong Mun wrote:
> From: Kees Cook
>
> When the check_[op]_overflow() helpers were introduced, all arguments were
> required to be the same type to make the fallback macros simpler. However,
> now that the fallback macros have been
From: Niranjana Vishwanathapura
Add i915_vma_is_bind_complete() to check if the binding of a
of the VM of a specific VMA is complete.
Signed-off-by: Niranjana Vishwanathapura
Signed-off-by: Ramalingam C
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/i915_vma.c | 28
From: Niranjana Vishwanathapura
Add getparam support for VM_BIND capability version support.
Signed-off-by: Niranjana Vishwanathapura
Signed-off-by: Ramalingam C
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/i915_getparam.c | 3 +++
include/uapi/drm/i915_drm.h | 21
Vishwanathapura
Signed-off-by: Ramalingam C
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/display/intel_fb_pin.c | 2 +-
.../drm/i915/display/intel_plane_initial.c| 2 +-
.../gpu/drm/i915/gem/i915_gem_execbuffer.c| 4 +-
.../drm/i915/gem/i915_gem_vm_bind_object.c| 2 +-
.../gpu
C
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/i915_driver.c | 1 +
include/uapi/drm/i915_drm.h| 2 ++
2 files changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/i915/i915_driver.c
b/drivers/gpu/drm/i915/i915_driver.c
index 841b5d62c2c01..f3b0bbfbe9746 100644
--- a/drivers/gpu
From: Niranjana Vishwanathapura
Add ioctls to enable the vm_bind and vm_unbind feature
Signed-off-by: Niranjana Vishwanathapura
Signed-off-by: Ramalingam C
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/i915_driver.c | 2 ++
include/uapi/drm/i915_drm.h| 4
2 files changed
From: Niranjana Vishwanathapura
For persistent (vm_bind) vmas of userptr BOs, handle the user
page pinning by using the i915_gem_object_userptr_submit_init()
/done() functions
Signed-off-by: Niranjana Vishwanathapura
Signed-off-by: Ramalingam C
Signed-off-by: Andi Shyti
---
.../gpu/drm/i915
From: Niranjana Vishwanathapura
Handle persistent (VM_BIND) mappings during the request submission
in the execbuf3 path.
Signed-off-by: Niranjana Vishwanathapura
Signed-off-by: Ramalingam C
Signed-off-by: Andi Shyti
---
.../gpu/drm/i915/gem/i915_gem_execbuffer3.c | 200
From: Niranjana Vishwanathapura
Add support for handling out fence of vm_bind call.
Signed-off-by: Niranjana Vishwanathapura
Signed-off-by: Ramalingam C
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/gem/i915_gem_vm_bind.h | 3 +
.../drm/i915/gem/i915_gem_vm_bind_object.c| 82
been requested by the
userspace before submitting the execbuf3.
And the legacy support like relocations etc are removed.
Signed-off-by: Niranjana Vishwanathapura
Signed-off-by: Ramalingam C
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/Makefile |1 +
.../gpu/drm/i915/gem
From: Niranjana Vishwanathapura
To reuse i915_gem_vm_lookup in upcoming implementation, expose it in
i915_gem_context.h
Signed-off-by: Niranjana Vishwanathapura
Signed-off-by: Ramalingam C
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/gem/i915_gem_context.c | 11 ++-
drivers
Vishwanathapura
Signed-off-by: Ramalingam C
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/gem/i915_gem_object.c| 1 +
.../drm/i915/gem/i915_gem_vm_bind_object.c| 8 +++
drivers/gpu/drm/i915/gt/intel_gtt.c | 2 +
drivers/gpu/drm/i915/gt/intel_gtt.h | 4 ++
drivers
From: Niranjana Vishwanathapura
Do not support the vm in vm_bind_mode in execbuf2 ioctl.
Signed-off-by: Niranjana Vishwanathapura
Signed-off-by: Ramalingam C
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 5 +
1 file changed, 5 insertions(+)
diff --git
From: Niranjana Vishwanathapura
VM private BOs can be only mapped on specified VM and cannot be dmabuf
exported.
Signed-off-by: Niranjana Vishwanathapura
Signed-off-by: Ramalingam C
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c | 6 ++
1 file changed, 6
, in the execbuf path.
Signed-off-by: Niranjana Vishwanathapura
Signed-off-by: Ramalingam C
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/gem/i915_gem_object_types.h | 3 +++
drivers/gpu/drm/i915/gem/i915_gem_vm_bind_object.c | 9 +
drivers/gpu/drm/i915/gt/intel_gtt.c| 4
From: Niranjana Vishwanathapura
Implement the bind and unbind of an object at the specified GPU virtual
addresses.
Signed-off-by: Niranjana Vishwanathapura
Signed-off-by: Prathap Kumar Valsan
Signed-off-by: Ramalingam C
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/Makefile
From: Niranjana Vishwanathapura
To reuse i915_gem_object_max_page_size() in upcoming
implementation, expose it in i915_gem_object.h
Signed-off-by: Niranjana Vishwanathapura
Signed-off-by: Ramalingam C
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/gem/i915_gem_create.c | 16
From: Niranjana Vishwanathapura
At vm creation time, add a flag to indicate that the new vm will use
vm_bind only for object binding.
Signed-off-by: Niranjana Vishwanathapura
Signed-off-by: Ramalingam C
Signed-off-by: Andi Shyti
---
drivers/gpu/drm/i915/gem/i915_gem_context.c | 5
Hi,
just sending the original Niranjana's patch as an RFC. It's v3 as
the v2 has been reviewed offline with Ramalingam.
I'm still keeping most of the structure even though some further
discussion can be done starting from here.
Copy pasting Niranjana's original cover letter message:
> Cc: Thomas Hellström
> Cc: Matthew Auld
> Cc: Nirmoy Das
> Cc: Jani Nikula
> Cc: Andi Shyti
> Reviewed-by: Mauro Carvalho Chehab (v5)
> ---
> drivers/gpu/drm/i915/i915_utils.h | 5 +--
> include/linux/overflow.h | 54 +++
> 2
Hi Rodrigo,
On Mon, Aug 08, 2022 at 03:04:13PM -0400, Rodrigo Vivi wrote:
> On Mon, Aug 08, 2022 at 06:37:58PM +0200, Andi Shyti wrote:
> > Hi Mauro,
> >
> > On Thu, Aug 04, 2022 at 09:37:22AM +0200, Mauro Carvalho Chehab wrote:
> > > WRITE_ONCE() sho
Hi Mauro,
On Thu, Aug 04, 2022 at 09:37:24AM +0200, Mauro Carvalho Chehab wrote:
> Add a description for the TLB cache invalidation algorithm and for
> the related kAPI functions.
>
> Signed-off-by: Mauro Carvalho Chehab
Reviewed-by: Andi Shyti
Andi
Hi Mauro,
On Thu, Aug 04, 2022 at 09:37:22AM +0200, Mauro Carvalho Chehab wrote:
> WRITE_ONCE() should happen at the original var, not on a local
> copy of it.
>
> Fixes: 5d36acb7198b ("drm/i915/gt: Batch TLB invalidations")
> Signed-off-by: Mauro Carvalho Chehab
Hi Randy,
> > +/**
> > + * intel_gt_invalidate_tlb_full - do full TLB cache invalidation
> > + * @gt: GT structure
>
> In multiple places (here and below) it would be nice to know what a
> GT structure is. I looked thru multiple C and header files yesterday
> and didn't find any comments about
Hi Jani,
> >> It moves overflows_type utility macro into drm util header from i915_utils
> >> header. The overflows_type can be used to catch the truncation between data
> >> types. And it adds safe_conversion() macro which performs a type conversion
> >> (cast) of an source value into a new
gt; Signed-off-by: Mauro Carvalho Chehab
I already reviewed this patch... anyway I checked it again and
it's all correct.
Reviewed-by: Andi Shyti
Thanks,
Andi
Hi Mauro,
Pushed in drm-intel-gt-next.
Thanks,
Andi
On Wed, Jul 27, 2022 at 02:29:50PM +0200, Mauro Carvalho Chehab wrote:
> Doing TLB invalidation cause performance regressions, like:
> [424.370996] i915 :00:02.0: [drm] *ERROR* rcs0 TLB invalidation did
> not complete in 4ms!
>
>
Hi Mauro,
I think there are still some unanswered questions from Tvrtko on
this patch, am I right?
Andi
On Wed, Jul 27, 2022 at 02:29:55PM +0200, Mauro Carvalho Chehab wrote:
> From: Chris Wilson
>
> Invalidate TLB in batches, in order to reduce performance regressions.
>
> Currently, every
d - Unbind a vma resource
> * @vma_res: The vma resource to unbind.
> + * @tlb: pointer to vma->obj->mm.tlb associated with the resource
> + *to be stored at vma_res->tlb. When not-NULL, it will be used
> + * to do TLB cache invalidation before freeing a VMA resource.
> + *used only for async unbind.
/used/Used/
With that:
Reviewed-by: Andi Shyti
Thanks,
Andi
Hi Mauro,
> Add a kernel-doc markup to document this new macro.
>
> Reviewed-by: Tvrtko Ursulin
> Signed-off-by: Mauro Carvalho Chehab
Reviewed-by: Andi Shyti
Andi
Hi,
On Mon, Jul 25, 2022 at 12:25:22PM +0300, Gwan-gyeong Mun wrote:
> It moves overflows_type utility macro into drm util header from i915_utils
> header. The overflows_type can be used to catch the truncation between data
> types. And it adds safe_conversion() macro which performs a type
gt; Signed-off-by: Mauro Carvalho Chehab
Just a copy paste, I checked line by line and it looked all
correct:
Reviewed-by: Andi Shyti
Thanks,
Andi
nger has access to the TLB's in each engine.
>
> That helps to reduce the performance regression introduced by TLB
> invalidate logic.
>
> Cc: sta...@vger.kernel.org
> Fixes: 7938d61591d3 ("drm/i915: Flush TLBs before releasing backing store")
> Signed-off-by: Chris Wil
> Signed-off-by: Chris Wilson
> Cc: Fei Yang
> Cc: Andi Shyti
> Acked-by: Thomas Hellström
> Signed-off-by: Mauro Carvalho Chehab
Please, once you have sorted out Tvrtko's question you can add:
Reviewed-by: Andi Shyti
Thanks,
Andi
er.kernel.org
> Fixes: 7938d61591d3 ("drm/i915: Flush TLBs before releasing backing store")
> Signed-off-by: Chris Wilson
> Cc: Fei Yang
> Cc: Andi Shyti
> Acked-by: Thomas Hellström
> Signed-off-by: Mauro Carvalho Chehab
Reviewed-by: Andi Shyti
Thanks,
Andi
ing store")
> Signed-off-by: Chris Wilson
> Cc: Fei Yang
> Cc: Andi Shyti
> Cc: Thomas Hellström
> Signed-off-by: Mauro Carvalho Chehab
For me it's good, but please, sort out with Tvrtko about his
doubts:
Reviewed-by: Andi Shyti
Andi
> ---
>
> To avoi
would be [PATCH v2]
> 3. please add a changelog, as this is a single patch, do it
> after the '---'
>
> No need to resend, just keep the three notes in mind for your
> next patches. Anyway, thanks for the fix and as I am at it:
>
> Reviewed-by: Andi Shyti
Pushed in drm-intel-next.
Thanks,
Andi
lease add a changelog, as this is a single patch, do it
after the '---'
No need to resend, just keep the three notes in mind for your
next patches. Anyway, thanks for the fix and as I am at it:
Reviewed-by: Andi Shyti
Thanks,
Andi
> ---
> drivers/gpu/drm/i915/selftests/i915_request.c | 2 +-
&g
Just a trivial review of an the vm bind document that is still
an rfc document.
Signed-off-by: Andi Shyti
---
Hi,
I'm not a big fan of this kind of patches, but while reading and
reviewing this document I spotted few potential grammatical fixes.
Andi
Documentation/gpu/rfc/i915_vm_bind.rst
Hi,
> It seems we are duplicating a lot of code from i915_execbuffer.c. Did
> you consider
yeah... while reading the code I was thinking the same then I see
that you made the same comment. Perhaps we need to group
commonalities and make common library for execbuf 2 and 3.
Andi
Hi,
[...]
> > @@ -28,7 +28,6 @@ static u32 object_max_page_size(struct
> > intel_memory_region **placements,
> > max_page_size = max_t(u32, max_page_size, mr-
> > >min_page_size);
> > }
> >
> > - GEM_BUG_ON(!max_page_size);
> > return max_page_size;
> > }
Hi,
[...]
> > +/*
> > + * VM_BIND feature version supported.
> > + *
> > + * The following versions of VM_BIND have been defined:
> > + *
> > + * 0: No VM_BIND support.
> > + *
> > + * 1: In VM_UNBIND calls, the UMD must specify the exact mappings
> > created
> > + * previously with VM_BIND,
Hi,
[...]
> @@ -1265,10 +1264,15 @@ static void i915_gem_context_release_work(struct
> work_struct *work)
> struct i915_gem_context *ctx = container_of(work, typeof(*ctx),
> release_work);
> struct i915_address_space *vm;
> +
701 - 800 of 1067 matches
Mail list logo
