== Series Details ==
Series: series starting with [01/19] drm/i915/overlay: Replace
i915_gem_obj_ggtt_offset() with the known flip_addr
URL : https://patchwork.freedesktop.org/series/6017/
State : warning
== Summary ==
Series 6017v1 Series without cover letter
http://patchwork.freedesktop.org
This function is useful for gen2 intel devices which have no frame
counter, but need a way to determine the current vblank count without
racing with the vblank interrupt handler.
intel_pipe_update_start checks if no vblank interrupt will occur
during vblank evasion, but cannot check whether the vb
> -Original Message-
> From: Ville Syrjälä [mailto:ville.syrj...@linux.intel.com]
> Sent: Friday, March 18, 2016 10:42 PM
> To: Kannan, Vandana
> Cc: intel-gfx@lists.freedesktop.org
> Subject: Re: [Intel-gfx] [PATCH 2/2] drm/i915: Render decompression
> support for Gen9 and above
[...]
Sorry for the late review, but see below...
On 04/19/2016 09:52 AM, Maarten Lankhorst wrote:
This function is useful for gen2 intel devices which have no frame
counter, but need a way to determine the current vblank count without
racing with the vblank interrupt handler.
intel_pipe_update_start
Since we do the l3-remap on context switch, we can remove the redundant
early call to set the mapping prior to performing the first context
switch.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_drv.h | 1 -
drivers/gpu/drm/i91
The ioremap() hidden behind the io_mapping_map_wc() convenience helper
can be used for remapping multiple pages. Extend the helper so that
future callers can use it for larger ranges.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Cc: Daniel Vetter
Cc: Jani Nikula
Cc: David Airlie
Cc: Yishai
Instead of allocating a new request when allocating a context, use the
request that initiated the allocation to emit the context
initialisation. This serves two purposes, it makes the initialisation
atomic with first use (simplifying scheduling and our own error
handling). Secondly, it enables us t
The code to switch_mm() is already handled by i915_switch_context(), the
only difference required to setup the aliasing ppgtt is that we need to
emit te switch_mm() on the first context, i.e. when transitioning from
engine->last_context == NULL. This allows us to defer the
initialisation of the GPU
As the contexts are accessed by the hardware until the switch is completed
to a new context, the hardware may still be writing to the context object
after the breadcrumb is visible. We must not unpin/unbind/prune that
object whilst still active and so we keep the previous context pinned until
the f
Both execlists and legacy need to reset the context (and mode) of the
GPU before we lose control of the system. By resetting the GPU, we
revert back to default settings. This simplifies the life of any
subsequent driver (in particular for virtualized setups) as it does not
then have to try and reco
We can hide more details of execlists from higher level code by removing
the explicit call to create an execlist context from execbuffer and
into its first use by execlists.
Signed-off-by: Chris Wilson
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 8
dri
In order to force a reload of the context image upon resume, we first
need to mark its absence on suspend. Currently we are failing to restore
the golden context state and any context w/a to the default context
after resume.
One oversight corrected, is that we had forgotten to reapply the L3
remap
If we move the release of the GEM request (i.e. decoupling it from the
various lists used for client and context tracking) after it is complete
(either by the GPU retiring the request, or by the caller cancelling the
request), we can remove the requirement that the final unreference of
the GEM requ
The hardware tracks contexts and expects all live contexts (those active
on the hardware) to have a unique identifier. This is used by the
hardware to assign pagefaults and the like to a particular context.
Signed-off-by: Chris Wilson
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_de
We can use a single MI_LOAD_REGISTER_IMM command packet to write all the
L3 remapping registers, shrinking the number of bytes required to emit
the context switch.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_gem_context.c | 16 ++
Move the i915_gem_l3_remap function such that it next to the context
switching, which is where we perform the L3 remap.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_gem.c | 31 ---
drivers/gpu/drm/i
From: Tvrtko Ursulin
This way in the following patch we can disconnect requests
from contexts.
Signed-off-by: Tvrtko Ursulin
Reviewed-by: Chris Wilson
Signed-off-by: Chris Wilson
---
drivers/gpu/drm/i915/i915_drv.h | 2 ++
drivers/gpu/drm/i915/intel_lrc.c | 3 ++-
2 files changed, 4 inserti
From: Tvrtko Ursulin
With the previous patch having extended the pinned lifetime of
contexts by referencing the previous context from the current
request until the latter is retired (completed by the GPU),
we can now remove usage of execlist retired queue entirely.
This is because the above now
Rather than reuse the current location of the context in the global GTT
for its hardware identifier, use the context's unique ID assigned to it
for its whole lifetime.
Signed-off-by: Chris Wilson
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_debugfs.c | 12 +---
drivers/gpu/
When setting up the overlay page, we pin it into the GGTT (when using
virtual addresses) and store the offset as overlay->flip_addr. Rather
than doing a lookup of the GGTT address everytime, we can use the known
address instead.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Reviewed-by: Tvrtko
In a couple of places, we have an i915_address_space that we know is
really an i915_ggtt that we want to use. Create an inline helper to
convert from the i915_address_space subclass into its container.
Signed-off-by: Chris Wilson
Cc: Joonas Lahtinen
Cc: Tvrtko Ursulin
Reviewed-by: Joonas Lahtin
Refactor pinning and unpinning of contexts, such that the default
context for an engine is pinned during initialisation and unpinned
during teardown (pinning of the context handles the reference counting).
Thus we can eliminate the special case handling of the default context
that was required to m
Similarly to i915_gem_object_pin_map on LLC platforms, we can
use the new VMA based io mapping on !LLC to amoritize the cost
of ringbuffer pinning and unpinning.
Signed-off-by: Tvrtko Ursulin
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Reviewed-by: Joonas Lahtinen
---
drivers/gpu/drm/i915/
When releasing the intel_fbdev, we should unpin the framebuffer that we
pinned during construction.
Signed-off-by: Chris Wilson
---
drivers/gpu/drm/i915/intel_display.c | 2 +-
drivers/gpu/drm/i915/intel_drv.h | 1 +
drivers/gpu/drm/i915/intel_fbdev.c | 7 ++-
3 files changed, 8 insert
By tracking the iomapping on the VMA itself, we can share that area
between multiple users. Also by only revoking the iomapping upon
unbinding from the mappable portion of the GGTT, we can keep that iomap
across multiple invocations (e.g. execlists context pinning).
Note that by moving the iounnma
== Series Details ==
Series: Enable Gen 7 Observation Architecture (rev3)
URL : https://patchwork.freedesktop.org/series/3024/
State : success
== Summary ==
Series 3024v3 Enable Gen 7 Observation Architecture
http://patchwork.freedesktop.org/api/1.0/series/3024/revisions/3/mbox/
byt-nuc
== Series Details ==
Series: Support for creating/using Stolen memory backed objects (rev13)
URL : https://patchwork.freedesktop.org/series/659/
State : success
== Summary ==
Series 659v13 Support for creating/using Stolen memory backed objects
http://patchwork.freedesktop.org/api/1.0/series/6
== Series Details ==
Series: drm/i915: Cache DisplayPort link signal levels
URL : https://patchwork.freedesktop.org/series/5973/
State : success
== Summary ==
Series 5973v1 drm/i915: Cache DisplayPort link signal levels
http://patchwork.freedesktop.org/api/1.0/series/5973/revisions/1/mbox/
b
== Series Details ==
Series: lib: Always NUL terminate ucs2_as_utf8
URL : https://patchwork.freedesktop.org/series/5969/
State : success
== Summary ==
Series 5969v1 lib: Always NUL terminate ucs2_as_utf8
http://patchwork.freedesktop.org/api/1.0/series/5969/revisions/1/mbox/
byt-nuc
On Sun, Apr 24, 2016 at 11:51:25AM -, Patchwork wrote:
> == Series Details ==
>
> Series: series starting with [v2,01/21] drm/i915/fbdev: Call
> intel_unpin_fb_obj() on release
> URL : https://patchwork.freedesktop.org/series/6215/
> State : failure
>
> == Summary ==
>
> Series 6215v1 Ser
== Series Details ==
Series: series starting with [v2,01/21] drm/i915/fbdev: Call
intel_unpin_fb_obj() on release
URL : https://patchwork.freedesktop.org/series/6215/
State : failure
== Summary ==
Series 6215v1 Series without cover letter
http://patchwork.freedesktop.org/api/1.0/series/6215/r
== Series Details ==
Series: mfd: intel_soc_pmic_core: Terminate panel control GPIO lookup table
correctly
URL : https://patchwork.freedesktop.org/series/6186/
State : failure
== Summary ==
Series 6186v1 mfd: intel_soc_pmic_core: Terminate panel control GPIO lookup
table correctly
http://pat
On Sun, Apr 24, 2016 at 09:53:27AM -, Patchwork wrote:
> == Series Details ==
>
> Series: series starting with [1/3] drm/i915: Macros to convert PM time
> interval values to microseconds
> URL : https://patchwork.freedesktop.org/series/6184/
> State : warning
>
> == Summary ==
>
> Series
== Series Details ==
Series: series starting with [1/2] drm/i915/guc: add enable_guc_loading
parameter
URL : https://patchwork.freedesktop.org/series/6185/
State : warning
== Summary ==
Series 6185v1 Series without cover letter
http://patchwork.freedesktop.org/api/1.0/series/6185/revisions/1/
Op 22-04-16 om 01:20 schreef Matt Roper:
> On Thu, Apr 21, 2016 at 02:19:33PM +0200, Maarten Lankhorst wrote:
>> Op 20-04-16 om 04:26 schreef Matt Roper:
>>> Once we move watermark calculation to the atomic check phase, we'll want
>>> to start rejecting display configurations that exceed out waterm
== Series Details ==
Series: series starting with [1/3] drm/i915: Macros to convert PM time interval
values to microseconds
URL : https://patchwork.freedesktop.org/series/6184/
State : warning
== Summary ==
Series 6184v1 Series without cover letter
http://patchwork.freedesktop.org/api/1.0/ser
== Series Details ==
Series: drm/i915: rename i915_gem_alloc_object() to i915_gem_object_create()
URL : https://patchwork.freedesktop.org/series/6183/
State : warning
== Summary ==
Series 6183v1 drm/i915: rename i915_gem_alloc_object() to
i915_gem_object_create()
http://patchwork.freedesktop.
== Series Details ==
Series: drm/i915: Warn there are any unfreed contexts when we shutdown
URL : https://patchwork.freedesktop.org/series/6157/
State : success
== Summary ==
Series 6157v1 drm/i915: Warn there are any unfreed contexts when we shutdown
http://patchwork.freedesktop.org/api/1.0/s
== Series Details ==
Series: series starting with [1/2] drm/i915: Canonicalize stolen memory
calculations (rev2)
URL : https://patchwork.freedesktop.org/series/6153/
State : warning
== Summary ==
Series 6153v2 Series without cover letter
http://patchwork.freedesktop.org/api/1.0/series/6153/re
send-email died on the last patch, grrr.
-Chris
--
Chris Wilson, Intel Open Source Technology Centre
___
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
From: Tvrtko Ursulin
This way in the following patch we can disconnect requests
from contexts.
Signed-off-by: Tvrtko Ursulin
Reviewed-by: Chris Wilson
Signed-off-by: Chris Wilson
---
drivers/gpu/drm/i915/i915_drv.h | 2 ++
drivers/gpu/drm/i915/intel_lrc.c | 3 ++-
2 files changed, 4 inserti
Similarly to i915_gem_object_pin_map on LLC platforms, we can
use the new VMA based io mapping on !LLC to amoritize the cost
of ringbuffer pinning and unpinning.
Signed-off-by: Tvrtko Ursulin
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Reviewed-by: Joonas Lahtinen
---
drivers/gpu/drm/i915/
When releasing the intel_fbdev, we should unpin the framebuffer that we
pinned during construction.
Signed-off-by: Chris Wilson
---
drivers/gpu/drm/i915/intel_display.c | 2 +-
drivers/gpu/drm/i915/intel_drv.h | 1 +
drivers/gpu/drm/i915/intel_fbdev.c | 7 ++-
3 files changed, 8 insert
Instead of allocating a new request when allocating a context, use the
request that initiated the allocation to emit the context
initialisation. This serves two purposes, it makes the initialisation
atomic with first use (simplifying scheduling and our own error
handling). Secondly, it enables us t
By tracking the iomapping on the VMA itself, we can share that area
between multiple users. Also by only revoking the iomapping upon
unbinding from the mappable portion of the GGTT, we can keep that iomap
across multiple invocations (e.g. execlists context pinning).
Note that by moving the iounnma
As we initialise engines, then contexts, ideally we want to unwind in
the opposite order: contexts then engines. Until now, the engines and
contexts were tightly coupled (the engine owned the default context)
preventing the "natural ordering" during shutdown. Now that execlists
merely holds a refer
In order to force a reload of the context image upon resume, we first
need to mark its absence on suspend. Currently we are failing to restore
the golden context state and any context w/a to the default context
after resume.
One oversight corrected, is that we had forgotten to reapply the L3
remap
As the contexts are accessed by the hardware until the switch is completed
to a new context, the hardware may still be writing to the context object
after the breadcrumb is visible. We must not unpin/unbind/prune that
object whilst still active and so we keep the previous context pinned until
the f
The ioremap() hidden behind the io_mapping_map_wc() convenience helper
can be used for remapping multiple pages. Extend the helper so that
future callers can use it for larger ranges.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Cc: Daniel Vetter
Cc: Jani Nikula
Cc: David Airlie
Cc: Yishai
The hardware tracks contexts and expects all live contexts (those active
on the hardware) to have a unique identifier. This is used by the
hardware to assign pagefaults and the like to a particular context.
Signed-off-by: Chris Wilson
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_de
We can use a single MI_LOAD_REGISTER_IMM command packet to write all the
L3 remapping registers, shrinking the number of bytes required to emit
the context switch.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_gem_context.c | 16 ++
Rather than reuse the current location of the context in the global GTT
for its hardware identifier, use the context's unique ID assigned to it
for its whole lifetime.
Signed-off-by: Chris Wilson
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_debugfs.c | 12 +---
drivers/gpu/
The code to switch_mm() is already handled by i915_switch_context(), the
only difference required to setup the aliasing ppgtt is that we need to
emit te switch_mm() on the first context, i.e. when transitioning from
engine->last_context == NULL. This allows us to defer the
initialisation of the GPU
Move the i915_gem_l3_remap function such that it next to the context
switching, which is where we perform the L3 remap.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_gem.c | 31 ---
drivers/gpu/drm/i
When setting up the overlay page, we pin it into the GGTT (when using
virtual addresses) and store the offset as overlay->flip_addr. Rather
than doing a lookup of the GGTT address everytime, we can use the known
address instead.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Reviewed-by: Tvrtko
Refactor pinning and unpinning of contexts, such that the default
context for an engine is pinned during initialisation and unpinned
during teardown (pinning of the context handles the reference counting).
Thus we can eliminate the special case handling of the default context
that was required to m
If we move the release of the GEM request (i.e. decoupling it from the
various lists used for client and context tracking) after it is complete
(either by the GPU retiring the request, or by the caller cancelling the
request), we can remove the requirement that the final unreference of
the GEM requ
From: Tvrtko Ursulin
With the previous patch having extended the pinned lifetime of
contexts by referencing the previous context from the current
request until the latter is retired (completed by the GPU),
we can now remove usage of execlist retired queue entirely.
This is because the above now
In a couple of places, we have an i915_address_space that we know is
really an i915_ggtt that we want to use. Create an inline helper to
convert from the i915_address_space subclass into its container.
Signed-off-by: Chris Wilson
Cc: Joonas Lahtinen
Cc: Tvrtko Ursulin
Reviewed-by: Joonas Lahtin
We can hide more details of execlists from higher level code by removing
the explicit call to create an execlist context from execbuffer and
into its first use by execlists.
Signed-off-by: Chris Wilson
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 8
dri
Since we do the l3-remap on context switch, we can remove the redundant
early call to set the mapping prior to performing the first context
switch.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_drv.h | 1 -
drivers/gpu/drm/i91
If we move the release of the GEM request (i.e. decoupling it from the
various lists used for client and context tracking) after it is complete
(either by the GPU retiring the request, or by the caller cancelling the
request), we can remove the requirement that the final unreference of
the GEM requ
We can hide more details of execlists from higher level code by removing
the explicit call to create an execlist context from execbuffer and
into its first use by execlists.
Signed-off-by: Chris Wilson
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 8
dri
Instead of allocating a new request when allocating a context, use the
request that initiated the allocation to emit the context
initialisation. This serves two purposes, it makes the initialisation
atomic with first use (simplifying scheduling and our own error
handling). Secondly, it enables us t
As the contexts are accessed by the hardware until the switch is completed
to a new context, the hardware may still be writing to the context object
after the breadcrumb is visible. We must not unpin/unbind/prune that
object whilst still active and so we keep the previous context pinned until
the f
From: Tvrtko Ursulin
With the previous patch having extended the pinned lifetime of
contexts by referencing the previous context from the current
request until the latter is retired (completed by the GPU),
we can now remove usage of execlist retired queue entirely.
This is because the above now
Refactor pinning and unpinning of contexts, such that the default
context for an engine is pinned during initialisation and unpinned
during teardown (pinning of the context handles the reference counting).
Thus we can eliminate the special case handling of the default context
that was required to m
From: Tvrtko Ursulin
This way in the following patch we can disconnect requests
from contexts.
Signed-off-by: Tvrtko Ursulin
Reviewed-by: Chris Wilson
Signed-off-by: Chris Wilson
---
drivers/gpu/drm/i915/i915_drv.h | 2 ++
drivers/gpu/drm/i915/intel_lrc.c | 3 ++-
2 files changed, 4 inserti
The ioremap() hidden behind the io_mapping_map_wc() convenience helper
can be used for remapping multiple pages. Extend the helper so that
future callers can use it for larger ranges.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Cc: Daniel Vetter
Cc: Jani Nikula
Cc: David Airlie
Cc: Yishai
Since we do the l3-remap on context switch, we can remove the redundant
early call to set the mapping prior to performing the first context
switch.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_drv.h | 1 -
drivers/gpu/drm/i91
By tracking the iomapping on the VMA itself, we can share that area
between multiple users. Also by only revoking the iomapping upon
unbinding from the mappable portion of the GGTT, we can keep that iomap
across multiple invocations (e.g. execlists context pinning).
Note that by moving the iounnma
In order to force a reload of the context image upon resume, we first
need to mark its absence on suspend. Currently we are failing to restore
the golden context state and any context w/a to the default context
after resume.
One oversight corrected, is that we had forgotten to reapply the L3
remap
Similarly to i915_gem_object_pin_map on LLC platforms, we can
use the new VMA based io mapping on !LLC to amoritize the cost
of ringbuffer pinning and unpinning.
Signed-off-by: Tvrtko Ursulin
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Reviewed-by: Joonas Lahtinen
---
drivers/gpu/drm/i915/
When releasing the intel_fbdev, we should unpin the framebuffer that we
pinned during construction.
Signed-off-by: Chris Wilson
---
drivers/gpu/drm/i915/intel_display.c | 2 +-
drivers/gpu/drm/i915/intel_drv.h | 1 +
drivers/gpu/drm/i915/intel_fbdev.c | 7 ++-
3 files changed, 8 insert
The code to switch_mm() is already handled by i915_switch_context(), the
only difference required to setup the aliasing ppgtt is that we need to
emit te switch_mm() on the first context, i.e. when transitioning from
engine->last_context == NULL. This allows us to defer the
initialisation of the GPU
The hardware tracks contexts and expects all live contexts (those active
on the hardware) to have a unique identifier. This is used by the
hardware to assign pagefaults and the like to a particular context.
Signed-off-by: Chris Wilson
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_de
Rather than reuse the current location of the context in the global GTT
for its hardware identifier, use the context's unique ID assigned to it
for its whole lifetime.
Signed-off-by: Chris Wilson
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_debugfs.c | 12 +---
drivers/gpu/
When setting up the overlay page, we pin it into the GGTT (when using
virtual addresses) and store the offset as overlay->flip_addr. Rather
than doing a lookup of the GGTT address everytime, we can use the known
address instead.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Reviewed-by: Tvrtko
We can use a single MI_LOAD_REGISTER_IMM command packet to write all the
L3 remapping registers, shrinking the number of bytes required to emit
the context switch.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_gem_context.c | 16 ++
Move the i915_gem_l3_remap function such that it next to the context
switching, which is where we perform the L3 remap.
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/i915_gem.c | 31 ---
drivers/gpu/drm/i
In a couple of places, we have an i915_address_space that we know is
really an i915_ggtt that we want to use. Create an inline helper to
convert from the i915_address_space subclass into its container.
Signed-off-by: Chris Wilson
Cc: Joonas Lahtinen
Cc: Tvrtko Ursulin
Reviewed-by: Joonas Lahtin
81 matches
Mail list logo
