drm/i915/bxt: Define bxt DDI PLLs and implement enable/disable sequence
Plug bxt PLL code into existing shared DPLL framework.
v2: (imre)
- squash in Satheeshakrishna's "Define BXT clock registers" and
"Add state variables for bxt clock registers" patches
- squash in Vandanas's "Change grp access to lane access for PLL"
- fix group vs. lane access in bxt_ddi_pll_get_hw_state
- add code comment why we read from lane registers while writing to
group registers
- clean up register macros
- use BXT_PORT_PLL_* macros instead of open-coding the same
- check if BXT_PORT_PCS_DW12_LN01 matches BXT_PORT_PCS_DW12_LN23
during hardware state readout
- add missing LANESTAGGER_STRAP_OVRD masking
- add note about missing step according to the latest BUN for
PORT_PLL_9/lockthresh
Signed-off-by: Satheeshakrishna M <satheeshakrishna.m@intel.com> (v1) Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Wed, 15 Apr 2015 15:39:59 +0000 (16:39 +0100)]
drm/i915: Simplify i915_gem_obj_is_pinned() test for set-tiling
Since the removal of the user pin_ioctl, the only means for pinning an
object is either through binding to the scanout or during execbuf
reservation. As the later prevents a call to set-tiling, we need only
check if the obj is pinned into the display plane to see if we need
reject the set-tiling ioctl.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The HDMI translation table is added back to bspec, so adding it,
and defaulting the 800mV+0dB entry.
The HDMI translation table was removed by following commit as per HW team's
recommendation:
commit 7ff446708bd1 ("drm/i915/skl: Only use the 800mV+2bB HDMI translation entry")
v2: Adding reference to commit which removed this table (Jani)
Daniel Vetter [Fri, 10 Apr 2015 14:22:38 +0000 (16:22 +0200)]
drm/i915: Drop unecessary fb arguments from function signatures
This is a separate patch to simplify conflict handling with other
ongoing atomic work.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Reviewed-by: Ander Conselvan de Oliveira <conselvan2@gmail.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Daniel Vetter [Fri, 10 Apr 2015 14:22:37 +0000 (16:22 +0200)]
drm/i915: Select starting pipe bpp irrespective or the primary plane
Since universal planes the primary plane might not be around, and it's
kinda silly to restrict the pipe bpp to the primary plane if we might
end up displaying a 10bpc video overlay. And with atomic we might very
well enable a pipe without a primary plane. So just use the platform
max as a starting point and then restrict appropriately.
Of course this is all still a bit moot as long as we artificially
compress everything to max 8bpc because we don't use the hi-bpc gamma
tables.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Reviewed-by: Ander Conselvan de Oliveira <conselvan2@gmail.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Tvrtko Ursulin [Tue, 17 Mar 2015 14:45:29 +0000 (14:45 +0000)]
drm/i915: Fix view type in warning message
One month passed between posting a patch and it getting merged, and
unfortunately even though it still applies, it needs fixing to account
for changes in function parameters since:
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
[danvet: Squash in fixup from Tvrtko to fix the rebase conflict.] Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Suketu Shah [Mon, 24 Nov 2014 08:07:45 +0000 (13:37 +0530)]
drm/i915/bxt: Add DC9 Trigger sequence
Add triggers for DC9 as per details provided in bxt_enable_dc9
and bxt_disable_dc9 implementations.
v1:
- Add SKL check in gen9_disable_dc5 as it is possible for DC5
to remain disabled only for SKL.
- Add additional checks for whether DC5 is already disabled during
DC5-disabling only for BXT.
v2:
- rebase to latest.
- Load CSR during DC9 disabling in the beginning before DC9 is
disabled.
- Make gen9_disable_dc5 function non-static as it's being called by
functions in i915_drv.c.
- Enable DC9-related functionality using a macro.
v3: (imre)
- remove BXT_ENABLE_DC9, we want DC9 always, and it's only valid on BXT
- remove DC5 disabling and CSR FW loaded check, these are nop atm
- squash in Vandana's "Do ddi_phy_init always" patch
v4:
- add TODO to re-enable DC5 during resume if CSR FW is available (sagar)
Signed-off-by: Suketu Shah <suketu.j.shah@intel.com> Signed-off-by: A.Sunil Kamath <sunil.kamath@intel.com> (v2) Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Sagar Kamble <sagar.a.kamble@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
A.Sunil Kamath [Mon, 24 Nov 2014 08:07:44 +0000 (13:37 +0530)]
drm/i915/bxt: Implement enable/disable for Display C9 state
v2: Modified as per review comments from Imre
- Mention enabling instead of allowing in the debug trace and
remove unnecessary comments.
v3:
- Rebase to latest.
- Move DC9-related functions from intel_display.c to intel_runtime_pm.c.
v4: (imre)
- remove DC5 disabling, it's a nop at this point
- squashed in Suketu's "Assert the requirements to enter or exit DC9"
patch
- remove check for RUNTIME_PM from assert_can_enable_dc9, it's not a
dependency
Signed-off-by: A.Sunil Kamath <sunil.kamath@intel.com> (v3) Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Sagar Kamble <sagar.a.kamble@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Imre Deak [Tue, 10 Mar 2015 19:18:30 +0000 (21:18 +0200)]
drm/i915/bxt: add description about the BXT PHYs
Extend the VLV/CHV DPIO (PHY) documentation with the BXT specifics.
v2:
- add more detail about the mapping between ports and transcoders (ville)
Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Add PHY specific display initialization sequence as per BSpec.
Note that the PHY initialization/uninitialization are done
at their current place only for simplicity, in a future patch - when more
of the runtime PM features will be enabled - these will be moved to
power well#1 and modeset encoder enabling/disabling hooks respectively.
The call to uninitialize the PHY during system/runtime suspend will be
added later in this patchset.
v1: Added function definitions in header files
v2: Imre's review comments addressed
- Moved CDCLK related definitions to i915_reg.h
- Removed defintions for CDCLK frequency
- Split uninit_cdclk() by adding a phy_uninit function
- Calculate freq and decimal based on input frequency
- Program SSA precharge based on input frequency
- Use wait_for 1ms instead 200us udelay for DE PLL locking
- Removed initial value for divider, freq, decimal, ratio.
- Replaced polling loops with wait_for
- Parameterized latency optim setting
- Fix the parts where DE PLL has to be disabled.
- Call CDCLK selection from mode set
v3: (imre)
- add note about the plan to move the cdclk/phy init to a better place
- take rps.hw_lock around pcode access
- fix DDI PHY timeout value
- squash in Vandana's "PORT_CL2CM_DW6_A BUN fix",
"DDI PHY programming register defn", "Do ddi_phy_init always",
- move PHY register macros next to the corresponding CHV/VLV macros
- move DE PLL register macros here from another patch since they are
used here first
- add BXT_ prefix to CDCLK flags
- s/COMMON_RESET/COMMON_RESET_DIS/ and clarify related code comments
- fix incorrect read value for the RMW of BXT_PHY_CTL_FAMILY_DDI
- fix using GT_DISPLAY_EDP_POWER_ON vs. GT_DISPLAY_DDI_POWER_ON
when powering on DDI ports
- fix incorrect port when setting BXT_PORT_TX_DW14_LN for DDI ports
- add missing masking when programming CDCLK_FREQ_DECIMAL
- add missing powering on for DDI-C port, rename OCL2_LDOFUSE_PWR_EN
to OCL2_LDOFUSE_PWR_DIS to reduce confusion
- add note about mismatch with bspec in the PORT_REF_DW6 fields
- factor out PHY init code to a new function, so we can call it for
PHY1 and PHY0, instead of open-coding the same
v4: (ville)
- split the CDCLK/PHY parts into two patches, update commit message
accordingly
- use the existing dpio_phy enum instead of adding a new one for the
same purpose
- flip the meaning of PHYs so that PHY_A is PHY1 and PHY_BC is PHY0 to
better match CHV
- s/BXT_PHY/_BXT_PHY/
- use _PIPE for _BXT_PHY instead of open-coding it
- drop _0_2_0_GTTMMADR suffix from BXT_P_CR_GT_DISP_PWRON
- define GT_DISPLAY_POWER_ON in a more standard way
- make a note that the CHV ConfigDB also disagrees about GRC_CODE field
definitions
- fix lane optimization refactoring fumble from v3
- add per PHY uninit functions to match the init counterparts
Signed-off-by: Vandana Kannan <vandana.kannan@intel.com> (v2) Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Add CDCLK specific display clock initialization sequence as per BSpec.
Note that the CDCLK initialization/uninitialization are done at their
current place only for simplicity, in a future patch - when more of the
runtime PM features will be enabled - these will be moved to power
well#1 and modeset encoder enabling/disabling hooks respectively. This
also means that atm dynamic power gating power well #1 is effectively
disabled.
The call to uninitialize CDCLK during system/runtime suspend will be
added later in this patchset.
v1: Added function definitions in header files
v2: Imre's review comments addressed
- Moved CDCLK related definitions to i915_reg.h
- Removed defintions for CDCLK frequency
- Split uninit_cdclk() by adding a phy_uninit function
- Calculate freq and decimal based on input frequency
- Program SSA precharge based on input frequency
- Use wait_for 1ms instead 200us udelay for DE PLL locking
- Removed initial value for divider, freq, decimal, ratio.
- Replaced polling loops with wait_for
- Parameterized latency optim setting
- Fix the parts where DE PLL has to be disabled.
- Call CDCLK selection from mode set
v3: (imre)
- add note about the plan to move the cdclk/phy init to a better place
- take rps.hw_lock around pcode access
- move DE PLL register macros here from another patch since they are
used here first
- add BXT_ prefix to CDCLK flags
- add missing masking when programming CDCLK_FREQ_DECIMAL
v4: (ville)
- split the CDCLK/PHY parts into two patches, update commit message
accordingly
- s/DISPLAY_PCU_CONTROL/HSW_PCODE_DE_WRITE_FREQ_REQ/
- simplify BXT_DE_PLL_RATIO macros
- fix BXT_DE_PLL_RATIO_MASK
- s/bxt_select_cdclk_freq/broxton_set_cdclk_freq/
- move cdclk init/uninit/set code from intel_ddi.c to intel_display.c
- remove redundant code comments for broxton_set_cdclk_freq()
- sanitize fixed point<->integer frequency value conversion
- use DRM_ERROR instead of WARN
- do RMW when programming BXT_DE_PLL_CTL for safety
- add note about PLL lock timeout being exactly 200us
- make PCU error messages more descriptive
- instead of using 0 freq to mean PLL off/bypass freq use 19200
for clarity, as the latter one is the actual rate
- simplify pcode programming, removing duplicated
sandybridge_pcode_write() call
- sanitize code flow, remove unnecessary scratch vars in
broxton_set_cdclk() (imre)
- Remove bound check for maxmimum freq to match current code.
This check will be added later at a more proper platform
independent place once atomic support lands.
- add note to remove freq guard band which isn't needed on BXT
- add note to reduce freq to minimum if no pipe is enabled
- combine broxton_modeset_global_pipes() with
valleyview_modeset_global_pipes()
Signed-off-by: Vandana Kannan <vandana.kannan@intel.com> (v2) Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
According to spec: "In PSR HW or SW mode, SW set this bit before writing
registers for a flip. It will be self-clear when it gets to the PSR
active state."
Some versions of spec mention that this is needed when in
"Persistent mode" but define it as same as "SW mode". Since this
fix the page flip case let's assume this is exactly what we need.
drm/i915: PSR: deprecate link_standby support for core platforms.
On Haswell and Broadwell with link in standby when exit event happens
between vblank and VSC packet, PSR exit on panel but DPA transmitter
still sends black pixel. When this condition hits, panel will intermittently
display black frame.
The known W/A for this case involve the of single_frame update
that isn't supported on Haswell and to be supported on Broadwell
3 other workarounds would be required. So it is better and safe to
just deprecate link_standby for now.
Also, link fully off saves more power than link_standby and afwk
no OEM is requesting link standby on VBT. There is no reason for that.
For Skylake let's just consider it behaves like Broadwell until
we prove otherwise.
v2: Fix commit message (Durga).
v3: Fix conflict with PSR2.
Reference: HSD: bdwgfx/1912559 Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Reviewed-by: Durgadoss R <durgadoss.r@intel.com> Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Since the beginning there is a missunderstanding on the meaning of this
dpcd bit.
This bit shouldn't indicate whether to use link standby or not, but just
be used to configure TP1, TP2 and TP3 times and tell hw aux should be skiped
since HW is the responsible one.
Even with help of frontbuffer tracking, HW is still fully responsible for
PSR exit logic with/without DP training.
DP_PSR_NO_TRAIN_ON_EXIT means the source doesn't need to do the training, but
it doesn't tell to avoid TP patterns, so we will send minimal TP1 and avoid
TP2. It also means that sink itself can take up to 5 idle frames for training.
6 in our case since we might be off by 1. So we also increment idle_frames by 4
here.
v2: Fix and improve commit message (Durga).
v3: Use minimal TP1 time avoiding TP2 and increase idle frame.
Cc: Durgadoss R <durgadoss.r@intel.com> Cc: Arthur Runyan <arthur.j.runyan@intel.com> Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Reviewed-by: Durgadoss R <durgadoss.r@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Shashank Sharma [Fri, 22 Aug 2014 12:10:43 +0000 (17:40 +0530)]
drm/i915/bxt: Enable GMBUS IRQ
GMBUS interrupt has been moved to CPU side in BXT.
What this patch does is:
1. Enable GMBUS IRQ in de_post_install function
2. Handle this interrupt as a port interrupt in display irq
handler
v2: Rebase on top of the for_each_pipe() change adding dev_priv as
first argument (Damien).
v3: read BXT_DE_PORT_GMBUS IIR flag only on BXT on other platforms
it's reserved (imre)
v4: (jani)
- remove redundant 'BXT GMBUS' comment
- fix formatting of BXT_DE_PORT_GMBUS definition
Reviewed-by: Satheeshakrishna M <satheeshakrishna.m@intel.com> Signed-off-by: Damien Lespiau <damien.lespiau@intel.com> Signed-off-by: Shashank Sharma <shashank.sharma@intel.com> (v1) Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Jani Nikula <jani.nikula@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Shashank Sharma [Fri, 22 Aug 2014 12:10:42 +0000 (17:40 +0530)]
drm/i915/bxt: Add BXT support in gen8_irq functions
This patch adds conditional checks in gen8_irq functions
to support BXT. Most of the checks just look for PCH split
availability, and block the call to PCH interrupt functions if
not available.
v2: (jani)
- drop redundant TODO comment about PCH IRQ flags on BXT
- check HAS_PCH_SPLIT instead of IS_BROXTON when handling PCH specific
IRQ events in gen8_irq_handler()
- check HAS_PCH_SPLIT before calling the function instead of a
corresponding early return within the called function for
ibx_irq_reset(), ibx_irq_pre_postinstall(), ibx_irq_postinstall()
v3: (jani)
- in ironlake_irq_postinstall() and ironlake_irq_reset() HAS_PCH_SPLIT
is always true, so drop the check for it
Reviewed-by: Satheeshakrishna M <satheeshakrishna.m@intel.com> Signed-off-by: Damien Lespiau <damien.lespiau@intel.com> Signed-off-by: Shashank Sharma <ppashank.sharma@intel.com> (v1) Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Jani Nikula <jani.nikula@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Shashank Sharma [Fri, 22 Aug 2014 12:10:41 +0000 (17:40 +0530)]
drm/i915/bxt: Add DDI hpd handler
This patch adds a hot plug interrupt handler function for BXT.
What this function typically does is:
1. Check if hot plug is enabled from hot plug control register.
2. Call hpd_irq_handler with appropriate trigger to detect a
plug storm and schedule a bottom half.
3. Clear sticky status bits in hot plug control register..
v2: (jani)
- drop redundant unlikely()
- s/Todo/FIXME:/ in code comment
- declare 'found' var in the scope where it's used
- check for IS_BROXTON before handling BXT_DE_PORT_HOTPLUG_MASK
Reviewed-by: Satheeshakrishna M <satheeshakrishna.m@intel.com> Signed-off-by: Damien Lespiau <damien.lespiau@intel.com> Signed-off-by: Shashank Sharma <shashank.sharma@intel.com> (v1) Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Jani Nikula <jani.nikula@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Imre Deak [Fri, 27 Mar 2015 15:22:34 +0000 (17:22 +0200)]
drm/i915/bxt: support for HPD long/short status decoding
All non-GMCH platforms have the same register layout for HPD long/short
status, so let's use this condition instead of HAS_PCH_SPLIT, as the
latter doesn't apply for BXT.
Noticed by Daniel.
Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Jani Nikula <jani.nikula@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Shashank Sharma [Fri, 27 Mar 2015 12:54:14 +0000 (14:54 +0200)]
drm/i915/bxt: DDI Hotplug interrupt setup
In BXT, DDI hotplug control has been moved to CPU from PCH.
This patch adds a new IRQ setup function for BXT which:
1. Checks which HPD ports are requested to be enabled by encoders.
2. Enables those ports in the hot plug control register.
3. Un-masks these port interrupts in the IMR register.
4. Enables these port interrupts in the IER register.
V3: Kept the default HPD filter count to default (500 us) as per
satheesh's comment
v4: Remove unused HPD filter defines (Damien)
v5: warn if trying to setup HPD on port A (imre)
v6: fix order of definitions for register bitfields (Daniel)
v7: (jani)
- define the size of the hpd_bxt array explicitly for bound checking
- use for_each_intel_encoder instead of open coding it
- fix format/order of definitions for BXT_HOTPLUG_CTL reg bitfields
Reviewed-by: Satheeshakrishna M <satheeshakrishna.m@intel.com> Signed-off-by: Damien Lespiau <damien.lespiau@intel.com> Signed-off-by: Shashank Sharma <shashank.sharma@intel.com> (v4) Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Jani Nikula <jani.nikula@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Jani Nikula [Wed, 1 Apr 2015 07:58:05 +0000 (10:58 +0300)]
drm/i915: add bxt gmbus support
For BXT gmbus is pulled from PCH to CPU. From implementation point of
view only pin pair configuration will change. The existing
implementation supports all platforms previous to GEN8 and also SKL. But
for BXT pin pair configuration is completely different than SKL or other
previous GEN's. This patch introduces the new pin pair configuration
structure specific to BXT and also ensures every real gmbus port has a
gpio pin.
v3 by Jani: with the platform independent prep work in place, the bxt
enabling reduces to a fairly trivial patch. Credits are due Sunil for
giving me the ideas (with his patches) what the platform independent
parts should look like.
v4: Fix intel_hdmi_init_connector() for bxt. Abstract gmbus_pin access
more. s/GPU/PCH/ in commit message.
v5: Rebase.
Issue: VIZ-3574 Signed-off-by: A.Sunil Kamath <sunil.kamath@intel.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com> Reviewed-by: Imre Deak <imre.deak@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Vandana Kannan [Tue, 19 Aug 2014 06:35:01 +0000 (12:05 +0530)]
drm/i915/bxt: don't use unsupported port detection
The port detection register flags in SFUSE_STRAP and DDI_BUF_CTL_A are
not defined for BXT, so don't use them.
Suggested by Satheesh.
v2:
- DDI_BUF_CTL_A bit 0 is not useful on BXT. Making changes to use this
bit when simulator or BXT is not applicable. Code re-arranged as per
Damien's suggestion.
Robert Beckett [Wed, 11 Mar 2015 08:28:25 +0000 (10:28 +0200)]
drm/i915/bxt: add workaround to avoid PTE corruption
Set TLBPF in TILECTL. This fixes an issue with BXT HW seeing
corrupted pte entries.
v2:
- move the workaround to bxt_init_clock_gating (imre)
Signed-off-by: Robert Beckett <robert.beckett@intel.com> (v1) Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Nick Hoath <nicholas.hoath@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Nick Hoath <nicholas.hoath@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Nick Hoath <nicholas.hoath@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Nick Hoath <nicholas.hoath@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Nick Hoath <nicholas.hoath@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Imre Deak [Fri, 27 Mar 2015 12:00:04 +0000 (14:00 +0200)]
drm/i915/bxt: add bxt_init_clock_gating
v2:
- Make the condition to select between SKL and BXT consistent with the
corresponding condition in init_workarounds_ring (Nick)
Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Nick Hoath <nicholas.hoath@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Imre Deak [Sun, 25 Jan 2015 21:27:11 +0000 (13:27 -0800)]
drm/i915/gen9: fix PIPE_CONTROL flush for VS_INVALIDATE
On GEN9+ per specification a NULL PIPE_CONTROL needs to be emitted
before any PIPE_CONTROL command with the VS_INVALIDATE flag set.
Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Nick Hoath <nicholas.hoath@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 16:28:24 +0000 (17:28 +0100)]
drm/i915: Remove obj->pin_mappable
The obj->pin_mappable flag only exists for debug purposes and is a
hindrance that is mistreated with rotated GGTT views. For debug
purposes, it suffices to mark objects with pin_display as being of note.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 15:20:41 +0000 (16:20 +0100)]
drm/i915: Optimistically spin for the request completion
This provides a nice boost to mesa in swap bound scenarios (as mesa
throttles itself to the previous frame and given the scenario that will
complete shortly). It will also provide a good boost to systems running
with semaphores disabled and so frequently waiting on the GPU as it
switches rings. In the most favourable of microbenchmarks, this can
increase performance by around 15% - though in practice improvements
will be marginal and rarely noticeable.
v2: Account for user timeouts
v3: Limit the spinning to a single jiffie (~1us) at most. On an
otherwise idle system, there is no scheduler contention and so without a
limit we would spin until the GPU is ready.
v4: Drop forcewake - the lazy coherent access doesn't require it, and we
have no reason to believe that the forcewake itself improves seqno
coherency - it only adds delay.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Cc: Eero Tamminen <eero.t.tamminen@intel.com> Cc: "Rantala, Valtteri" <valtteri.rantala@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
drm/i915: skylake panel fitting using shared scalers
Enabling skylake panel fitting feature using shared scalers
v2:
-added force detach parameter for pfit disable purpose (me)
-read crtc scaler state from hw state (Daniel)
-replaced both skylake_pfit_enable and disable with skylake_pfit_update (me)
-added scaler id check to intel_pipe_config_compare (Daniel)
v3:
-updated function header to kerneldoc format (Matt)
-dropped need_scaling checks (Matt)
v4:
-move clearing of scaler id from commit path to check path (Matt)
-updated colorkey checks based on recent updates (me)
-squashed scaler check while enabling colorkey to here (me)
-use values in plane_state->src as regular integers (me)
-changes made not to modify state in commit path (Matt)
v5:
-squashed helper function to update scaler users to here (Matt)
-squashed helper function to detach scaler to here (Matt, me)
-changes to align with updated scaler structures (Matt, me)
Signed-off-by: Chandra Konduru <chandra.konduru@intel.com> Reviewed-by: Matt Roper <matthew.d.roper@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
drm/i915: Ensure setting up scalers into staged crtc_state
From intel_atomic_check, call intel_atomic_setup_scalers() to
assign scalers based on staged scaling requests. Fail the
transaction if setup returns error.
Setting up of scalers should be moved to atomic crtc check once
atomic crtc is ready.
v2:
-updated parameter passing to setup_scalers (me)
Signed-off-by: Chandra Konduru <chandra.konduru@intel.com> Reviewed-by: Matt Roper <matthew.d.roper@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Added intel_atomic_setup_scalers to setup scalers based on
staged scaling requests from a crtc and its planes. If staged
requests are supportable, this function assigns scalers to
requested planes and crtc. Note that the scaler assignement
itself is staged into crtc_state and respective plane_states
for later commit after all checks have been done.
overall high level flow:
- scaler requests are staged into crtc_state by planes/crtc
- check whether staged scaling requests can be supported
- add planes using scalers that aren't in current transaction
- assign scalers to requested users
- as part of plane commit, scalers will be committed
(i.e., either attached or detached) to respective planes in hw
- as part of crtc_commit, scaler will be either attached or detached
to crtc in hw
crtc_compute_config calls intel_atomic_setup_scalers() to start
scaler assignments as per scaler state in crtc config. This call
should be moved to atomic crtc once it is available.
v2:
-removed a log message (me)
-changed input parameter to crtc_state (me)
v3:
-remove assigning plane_state returned by drm_atomic_get_plane_state (Matt)
-fail if there is an error from drm_atomic_get_plane_state (Matt)
v4:
-changes to align with updated scaler structure (Matt, me)
v5:
-added addtional checks before enabling HQ mode (me)
-added comments to enable HQ mode (Matt)
Signed-off-by: Chandra Konduru <chandra.konduru@intel.com> Reviewed-by: Matt Roper <matthew.d.roper@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
drm/i915: Preserve scaler state when clearing crtc_state
crtc_state is cleared during mode set which wipes out complete
scaler state too. This is causing issues. To fix, ensure scaler
state is preserved because it contains not only crtc
scaler usage, but also planes using scalers on this crtc.
Signed-off-by: Chandra Konduru <chandra.konduru@intel.com> Reviewed-by: Matt Roper <matthew.d.roper@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
drm/i915: Allocate connector state together with the connectors
Connector states were being allocated in intel_setup_outputs() in loop
over all connectors. That meant hot-added connectors would have a NULL
state. Since the change to use a struct drm_atomic_state for the legacy
modeset, connector states are necessary for the i915 driver to function
properly, so that would lead to oopses.
v2: Fix test for intel_connector_init() success in lvds and sdvo (PRTS)
Signed-off-by: Ander Conselvan de Oliveira <ander.conselvan.de.oliveira@intel.com> Reported-and-tested-by: Nicolas Kalkhof <nkalkhof@web.de> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Michel Thierry <michel.thierry@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
drm/i915: add i915 specific connector debugfs file for DPCD
Reported-by: kbuild test robot <fengguang.wu@intel.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Mika Kuoppala [Fri, 10 Apr 2015 12:54:58 +0000 (15:54 +0300)]
drm/i915: Move vm page allocation in proper place
Move to i915_vma_bind as it is part of the binding.
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Michel Thierry <michel.thierry@intel.com> Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
v2: Moving creation of property in a function, checking for 90/270
rotation simultaneously (Chris)
Letting primary plane to be positioned
v3: Adding if/else for 90/270 and rest params programming, adding check for
pixel_format, some cleanup (review comments)
v4: Adding right pixel_formats, using src_* params instead of crtc_* for offset
and size programming (Ville)
v5: Rebased on -nightly and Tvrtko's series for gtt remapping.
v6: Rebased on -nightly (Tvrtko's series merged)
v7: Moving pixel_format check to intel_atomic_plane_check (Matt)
Signed-off-by: Sonika Jindal <sonika.jindal@intel.com> Reviewed-by: Matt Roper <matthew.d.roper@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
drm/i915: Remove stale comment from __intel_set_mode()
Since the following commit, the PLL calculations are done earlier, so
the code following the comment doesn't do anything PLL or encoder
related. It only updates the primary plane now.
commit f3019a4d92f08b2dd92443a4b567a066a51c6ec0
Author: Ander Conselvan de Oliveira <ander.conselvan.de.oliveira@intel.com>
Date: Wed Oct 29 11:32:37 2014 +0200
drm/i915: Remove crtc_mode_set() hook
Signed-off-by: Ander Conselvan de Oliveira <ander.conselvan.de.oliveira@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 16:28:17 +0000 (17:28 +0100)]
drm/i915: Simplify object is-pinned checking for shrinker
When looking for viable candidates to shrink, we only want objects that
are not pinned. However to do so we performed a double iteration over
the vma in the objects, first looking for the pin-count, then looking
for allocations. We can do both at once and be slightly more explicit in
our validity test.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 15:21:11 +0000 (16:21 +0100)]
drm/i915: Allocate context objects from stolen
As we never expose context objects directly to userspace, we can forgo
allocating a first-class GEM object for them and prefer to use the
limited resource of reserved/stolen memory for them. Note this means
that their initial contents are undefined.
However, a downside of using stolen objects for execlists is that we
cannot access the physical address directly (thanks MCH!) which prevents
their use.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 15:21:09 +0000 (16:21 +0100)]
drm/i915: Remove request->uniq
We already assign a unique identifier to every request: seqno. That
someone felt like adding a second one without even mentioning why and
tweaking ABI smells very fishy.
drm/i915: Fix a use after free, and unbalanced refcounting
v2: Rebase
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Nick Hoath <nicholas.hoath@intel.com> Cc: Thomas Daniel <thomas.daniel@intel.com> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Jani Nikula <jani.nikula@intel.com>
[danvet: Fixup because different merge order.] Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 15:21:04 +0000 (16:21 +0100)]
drm/i915: Reduce locking in gen8 IRQ handler
Similar in vain in reducing the number of unrequired spinlocks used for
execlist command submission (where the forcewake is required but
manually controlled), we know that the IRQ registers are outside of the
powerwell and so we can access them directly. Since we now have direct
access exported via I915_READ_FW/I915_WRITE_FW, lets put those to use in
the irq handlers as well.
In the process, reorder the execlist submission to happen as early as
possible.
v2: Restrict the untraced register mmio to just the GT path (i.e. the
hotpath for execlists)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 15:21:02 +0000 (16:21 +0100)]
drm/i915: Reduce locking in execlist command submission
This eliminates six needless spin lock/unlock pairs when writing out
ELSP.
v2: Respin with my preferred colour.
v3: Mostly back to the original colour
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> [v1] Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Matt Roper [Thu, 9 Apr 2015 17:48:38 +0000 (10:48 -0700)]
drm/i915: Clear crtc atomic flags at beginning of transaction
Once we have full atomic modeset, these kind of flags should be in a
real intel_crtc_state that's tracked properly. In the meantime, make
sure we clear out any old flags at the beginning of a transaction so
that we don't wind up seeing leftover flags from old transactions that
were checked, but never went to the commit step. At the moment, a
failed check or prepare could leave stale flags behind that interfere
with the next atomic transaction.
v2: Just do a memset; the series this patch was originally part of
placed additional fields into the structure that shouldn't be
cleared, but that's no longer the case.
Signed-off-by: Matt Roper <matthew.d.roper@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Matt Roper [Thu, 9 Apr 2015 01:56:53 +0000 (18:56 -0700)]
drm/i915: Switch to full atomic helpers for plane updates/disable, take two
Switch from our plane update/disable entrypoints to use the full atomic
helpers (which generate a top-level atomic transaction) rather than the
transitional helpers (which only create/manipulate orphaned plane states
independent of a top-level transaction). Various upcoming work (SKL
scalers, atomic watermarks, etc.) requires a full atomic transaction to
behave properly/cleanly.
Last time we tried this, we had to back out the change because we still
call the drm_plane vfuncs directly from within our legacy modesetting
code. This potentially results in nested atomic transactions, locking
collisions, and other failures. To avoid that problem again, we
sidestep the issue by calling the transitional helpers directly (rather
than through a vfunc) when we're nested inside of other legacy
modesetting code. However this does allow legacy SetPlane() ioctl's to
process an entire drm_atomic_state transaction, which is important for
upcoming patches.
Cc: Chandra Konduru <chandra.konduru@intel.com> Signed-off-by: Matt Roper <matthew.d.roper@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 15:20:51 +0000 (16:20 +0100)]
drm/i915: Remove vestigal DRI1 ring quiescing code
After the removal of DRI1, all access to the rings are through requests
and so we can always be sure that there is a request to wait upon to
free up available space. The fallback code only existed so that we could
quiesce the GPU following unmediated access by DRI1.
v2: Rebase
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 15:20:49 +0000 (16:20 +0100)]
drm/i915: Use the global runtime-pm wakelock for a busy GPU for execlists
When we submit a request to the GPU, we first take the rpm wakelock, and
only release it once the GPU has been idle for a small period of time
after all requests have been complete. This means that we are sure no
new interrupt can arrive whilst we do not hold the rpm wakelock and so
can drop the individual get/put around every single request inside
execlists.
Note: to close one potential issue we should mark the GPU as busy
earlier in __i915_add_request.
To elaborate: The issue is that we emit the irq signalling sequence
before we grab the rpm reference, which means we could miss the
resulting interrupt (since that's not set up when suspended). The only
bad side effect is a missed interrupt, gt mmio writes automatically
wake up the hw itself. But otoh we have an umbrella rpm reference for
the entirety of execbuf, as long as that's there we're covered.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Explain a bit more about the add_request issue, which after
some irc chatting with Chris turns out to not be an issue really.] Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Ville Syrjälä [Wed, 25 Mar 2015 16:45:58 +0000 (18:45 +0200)]
drm/i915: Fix the VBT child device parsing for BSW
Recent BSW VBT has a VBT child device size 37 bytes instead of the 33
bytes our code assumes. This means we fail to parse the VBT and thus
fail to detect eDP ports properly and just register them as DP ports
instead.
Fix it up by using the reported child device size from the VBT instead
of assuming it matches out struct defintions.
The latest spec I have shows that the child device size should be 36
bytes for rev >= 195, however on my BSW the size is actually 37 bytes.
And our current struct definition is 33 bytes.
Feels like the entire VBT parses would need to be rewritten to handle
changes in the layout better, but for now I've decided to do just the
bare minimum to get my eDP port back.
Cc: Vijay Purushothaman <vijay.a.purushothaman@linux.intel.com> Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Reviewed-by: Damien Lespiau <damien.lespiau@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Michel Thierry [Wed, 8 Apr 2015 11:13:35 +0000 (12:13 +0100)]
drm/i915: Use complete address space in true PPGTT
True PPGTT is capable of having a full address space, even if the system
has less allocated memory.
Note that aliasing PPGTT always aliases the GGTT and thus should remain
of the same size.
Signed-off-by: Michel Thierry <michel.thierry@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Michel Thierry [Wed, 8 Apr 2015 11:13:34 +0000 (12:13 +0100)]
drm/i915/gen8: Dynamic page table allocations
This finishes off the dynamic page tables allocations, in the legacy 3
level style that already exists. Most everything has already been setup
to this point, the patch finishes off the enabling by setting the
appropriate function pointers.
In LRC mode, contexts need to know the PDPs when they are populated. With
dynamic page table allocations, these PDPs may not exist yet. Check if
PDPs have been allocated and use the scratch page if they do not exist yet.
Before submission, update the PDPs in the logic ring context as PDPs
have been allocated.
v2: Update aliasing/true ppgtt allocate/teardown/clear functions for
gen 6 & 7.
v3: Rebase.
v4: Remove BUG() from ppgtt_unbind_vma, but keep checking that either
teardown_va_range or clear_range functions exist (Daniel).
v5: Similar to gen6, in init, gen8_ppgtt_clear_range call is only needed
for aliasing ppgtt. Zombie tracking was originally added for teardown
function and is no longer required.
v6: Update err_out case in gen8_alloc_va_range (missed from lastest
rebase).
v7: Rebase after s/page_tables/page_table/.
v8: Updated scratch_pt check after scratch flag was removed in previous
patch.
v9: Note that lrc mode needs to be updated to support init state without
any PDP.
v10: Unmap correct page_table in gen8_alloc_va_range's error case, clean-up
gen8_aliasing_ppgtt_init (remove duplicated map), and initialize PTs
during page table allocation.
v11: Squashed LRC enabling commit, otherwise LRC mode would be left broken
until it was updated to handle the init case without any PDP.
v12: Do not overallocate new_pts bitmap, make alloc_gen8_temp_bitmaps
static and don't abuse of inline functions. (Mika)
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Michel Thierry <michel.thierry@intel.com> (v2+) Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Michel Thierry [Wed, 8 Apr 2015 11:13:33 +0000 (12:13 +0100)]
drm/i915/gen8: begin bitmap tracking
Like with gen6/7, we can enable bitmap tracking with all the
preallocations to make sure things actually don't blow up.
v2: Rebased to match changes from previous patches.
v3: Without teardown logic, rely on used_pdpes and used_pdes when
freeing page tables.
v4: Rebased after s/page_tables/page_table/.
v5: Rebased after page table generalizations.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Michel Thierry <michel.thierry@intel.com> (v2+) Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Michel Thierry [Wed, 8 Apr 2015 11:13:32 +0000 (12:13 +0100)]
drm/i915/gen8: Split out mappings
When we do dynamic page table allocations for gen8, we'll need to have
more control over how and when we map page tables, similar to gen6.
In particular, DMA mappings for page directories/tables occur at allocation
time.
This patch adds the functionality and calls it at init, which should
have no functional change.
The PDPEs are still a special case for now. We'll need a function for
that in the future as well.
v2: Handle renamed unmap_and_free_page functions.
v3: Updated after teardown_va logic was removed.
v4: Rebase after s/page_tables/page_table/.
v5: No longer allocate all PDPs in GEN8+ systems with less than 4GB of
memory, and update populate_lr_context to handle this new case (proper
tracking will be added later in the patch series).
v6: Assign lrc page directory pointer addresses using a macro. (Mika)
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Michel Thierry <michel.thierry@intel.com> (v2+) Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Michel Thierry [Wed, 8 Apr 2015 11:13:31 +0000 (12:13 +0100)]
drm/i915: Extract PPGTT param from page_directory alloc
This will be useful for when we move to 48b addressing, and the PDP isn't
the root of the page table structure.
v2: Rebase after changes for Gen8+ systems with less than 4GB of memory.
v3: Rebase after Mika's code review.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Michel Thierry <michel.thierry@intel.com> (v2) Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
These values are never quite useful for dynamic allocations of the page
tables. Getting rid of them will help prevent later confusion.
v2: Updated to use unmap_and_free_pd functions.
v3: Updated gen8_ppgtt_free after teardown logic was removed.
v4: Rebase after s/page_tables/page_table/.
v5: Keep allocating all page directories in GEN8+ systems with less
than 4GB of memory. Updated gen6_for_all_pdes.
v6: Prevent (harmless) out of range access in gen6_for_all_pdes.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Michel Thierry <michel.thierry@intel.com> (v2+) Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Michel Thierry [Wed, 8 Apr 2015 11:13:29 +0000 (12:13 +0100)]
drm/i915/gen8: Update pdp switch and point unused PDPs to scratch page
One important part of this patch is we now write a scratch page
directory into any unused PDP descriptors. This matters for 2 reasons,
first, we're not allowed to just use 0, or an invalid pointer, and second,
we must wipe out any previous contents from the last context.
The latter point only matters with full PPGTT. The former point only
effect platforms with less than 4GB memory.
v2: Updated commit message to point that we must set unused PDPs to the
scratch page.
v3: Unmap scratch_pd in gen8_ppgtt_free.
v4: Initialize scratch_pd. (Mika)
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Michel Thierry <michel.thierry@intel.com> (v2+) Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Michel Thierry [Wed, 8 Apr 2015 11:13:28 +0000 (12:13 +0100)]
drm/i915/gen8: pagetable allocation rework
Start using gen8_for_each_pde macro to allocate page tables.
v2: teardown_va_range references removed.
v3: Rebase after s/page_tables/page_table/.
v4: Keep setting up page tables for all page directories in systems with
less than 4GB of memory.
v5: Also initialize the page tables. (Mika)
v6: Initialize all page tables, including the extra ones from systems
with less than 4GB of memory. (Mika)
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Michel Thierry <michel.thierry@intel.com> (v2+) Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Michel Thierry [Wed, 8 Apr 2015 11:13:27 +0000 (12:13 +0100)]
drm/i915/gen8: page directories rework allocation
Start using gen8_for_each_pdpe macro to allocate the page directories.
Similar to PTs, while setting up a page directory, make all entries of
the pd point to the scratch pd before mapping (and make all its entries
point to the scratch page); this is to be safe in case of out of bound
access or proactive prefetch. Systems without LLC require an explicit
flush.
v2: Rebased after s/free_pt_*/unmap_and_free_pt/ change.
v3: Rebased after teardown va range logic was removed.
v4: Keep setting up all page directories for systems with less than 4GB
of memory.
v5: Initialize PDs. (Mika)
v6: Initialize also the extra PDs from systems with less than 4GB of
memory. (Mika)
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Michel Thierry <michel.thierry@intel.com> (v2+) Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Michel Thierry [Wed, 8 Apr 2015 11:13:26 +0000 (12:13 +0100)]
drm/i915/gen8: Add dynamic allocation macros and helper functions
Similar to gen6, we will use for_each_pde/for_each_pdpe
and pte/pde/pdpe_index to iterate over these new structures.
v2: Match trace_i915_va_teardown params
v3: Multiple rebases.
v4: Updated to use unmap_and_free_pt.
v5: teardown_va_range logic no longer needed.
v6: Rebase after s/page_tables/page_table/.
v7: Renamed commit to match what it does now (it was "Use dynamic
allocation idioms on free").
v8: Prevent (harmless) out of range access in gen8_for_each_pde and
gen8_for_each_pdpe_e.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Michel Thierry <michel.thierry@intel.com> (v2+) Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
[danvet: s/BUG/WARN/] Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Michel Thierry [Wed, 8 Apr 2015 11:13:25 +0000 (12:13 +0100)]
drm/i915/gen8: Initialize page tables
Similar to gen6, while setting up a page table, make all entries of the
pt point to the scratch page before mapping; this is to be safe in case
of out of bound access or proactive prefetch.
Systems without LLC require an explicit flush.
v2: Expanded commit text and fixed indentation (Mika)
Signed-off-by: Michel Thierry <michel.thierry@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We are already unmapping them in gen8_ppgtt_free. This function became
redundant since commit 06fda602dbca9c59d87db7da71192e4b54c9f5ff
("drm/i915: Create page table allocators").
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Signed-off-by: Michel Thierry <michel.thierry@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Michel Thierry [Wed, 8 Apr 2015 11:13:23 +0000 (12:13 +0100)]
drm/i915: Remove _entry from PPGTT page structures
Lets try to keep this consistent:
Page Directory Pointer (PDP).
Page Directory (PD), also known as page directory pointer entries.
Page Table (PT), also known as page directory entries.
Suggested-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Signed-off-by: Michel Thierry <michel.thierry@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 15:20:47 +0000 (16:20 +0100)]
drm/i915: Record ring->start address in error state
This is mostly useful for execlists where the rings switch between
contexts (and so checking that the ring's start register matches the
context is important).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 15:20:40 +0000 (16:20 +0100)]
drm/i915: Suppress empty lines from debugfs/i915_gem_objects
This is just so that I don't have to read about the batch pool on
systems that are not using it! Rather than using a newline between the
kernel clients and userspace clients, just distinguish the internal
allocations with a '[k]'
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 15:20:39 +0000 (16:20 +0100)]
drm/i915: Include active flag when describing objects in debugfs
Since we use obj->active as a hint in many places throughout the code,
knowing its state in debugfs is extremely useful.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 15:20:38 +0000 (16:20 +0100)]
drm/i915: Split batch pool into size buckets
Now with the trimmed memcpy before the command parser, we try to
allocate many different sizes of batches, predominantly one or two
pages. We can therefore speed up searching for a good sized batch by
keeping the objects of buckets of roughly the same size.
v2: Add a comment about bucket sizes
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 15:20:37 +0000 (16:20 +0100)]
drm/i915: Free batch pool when idle
At runtime, this helps ensure that the batch pools are kept trim and
fast. Then at suspend, this releases memory that we do not need to
restore. It also ties into the oom-notifier to ensure that we recover as
much kernel memory as possible during OOM.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 15:20:36 +0000 (16:20 +0100)]
drm/i915: Split the batch pool by engine
I woke up one morning and found 50k objects sitting in the batch pool
and every search seemed to iterate the entire list... Painting the
screen in oils would provide a more fluid display.
One issue with the current design is that we only check for retirements
on the current ring when preparing to submit a new batch. This means
that we can have thousands of "active" batches on another ring that we
have to walk over. The simplest way to avoid that is to split the pools
per ring and then our LRU execution ordering will also ensure that the
inactive buffers remain at the front.
v2: execlists still requires duplicate code.
v3: execlists requires more duplicate code
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 15:20:35 +0000 (16:20 +0100)]
drm/i915: Tidy batch pool logic
Move the madvise logic out of the execbuffer main path into the
relatively rare allocation path, making the execbuffer manipulation less
fragile.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 15:20:34 +0000 (16:20 +0100)]
drm/i915: Split i915_gem_batch_pool into its own header
In the next patch, I want to use the structure elsewhere and so require
it defined earlier. Rather than move the definition to an earlier location
where it feels very odd, place it in its own header file.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The premise that media/blitter workloads are not affected by boosting is
patently false with a trip through igt. The question that remains is
what exactly is going wrong with the media workload that prompted this?
Hopefully that would be fixed by the missing agressive downclocking, in
addition to the extra restrictions imposed on how frequent a process is
allowed to boost.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Deepak S <deepak.s@linux.intel.com> Cc: Daniel Vetter <daniel.vetter@ffwll> Acked-by: Deepak S <deepak.s@linux.intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 15:20:32 +0000 (16:20 +0100)]
drm/i915: Deminish contribution of wait-boosting from clients
With boosting for missed pageflips, we have a much stronger indication
of when we need to (temporarily) boost GPU frequency to ensure smooth
delivery of frames. So now only allow each client to perform one RPS boost
in each period of GPU activity due to stalling on results.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Deepak S <deepak.s@linux.intel.com> Reviewed-by: Deepak S <deepak.s@linux.intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Chris Wilson [Tue, 7 Apr 2015 15:20:31 +0000 (16:20 +0100)]
drm/i915: Boost GPU frequency if we detect outstanding pageflips
If we hit a vblank and see that have a pageflip queue but not yet
processed, ensure that the GPU is running at maximum in order to clear
the backlog. Pageflips are only queued for the following vblank, if we
miss it, there will be a visible stutter. Boosting the GPU frequency
doesn't prevent us from missing the target vblank, but it should help
the subsequent frames hitting theirs.
v2: Reorder vblank vs flip-complete so that we only check for a missed
flip after processing the completion events, and avoid spurious boosts.
v3: Rename missed_vblank
v4: Rebase
v5: Cancel the outstanding work in runtime suspend
v6: Rebase
v7: Rebase required fixing
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Deepak S<deepak.s@linux.intel.com> Reviewed-by: Deepak S<deepak.s@linux.intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
projects / linux-beck.git / log