- Tweak initia DPCD backlight.enabled value (Sean)
- Initialize reserved MOCS indices (Ayaz)
- Mark initial fb obj as WT on eLLC machines to avoid rcu lockup (Ville)
- Support parsing of oversize batches (Chris)
- Delay execlists processing for TGL (Chris)
- Use the active reference on the vma during error capture (Chris)
- Widen CSB pointer (Chris)
- Wait for CSB entries on TGL (Chris)
- Fix unwind for scratch page allocation (Chris)
- Exclude low patches of stolen memory (Chris)
- Force VT'd workarounds when running as a guest OS (Chris)
- Drop runtime-pm assert from vpgu io accessors (Chris)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201022205613.GA3469192@intel.com
0 causes instruction fetch stall at cache line boundary under some
conditions on Navi10. A non-zero prefetch is the preferred default
in any case.
Fixes soft hang in Luxmark.
Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
1. when smc feature bit isn't mapped,
the feature state isn't showed on sysfs node of pp_features.
2. add pp_features table title
Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
On Tigerlake, we are seeing a repeat of commit d8f5053117 ("drm/i915/icl:
Forcibly evict stale csb entries") where, presumably, due to a missing
Global Observation Point synchronisation, the write pointer of the CSB
ringbuffer is updated _prior_ to the contents of the ringbuffer. That is
we see the GPU report more context-switch entries for us to parse, but
those entries have not been written, leading us to process stale events,
and eventually report a hung GPU.
However, this effect appears to be much more severe than we previously
saw on Icelake (though it might be best if we try the same approach
there as well and measure), and Bruce suggested the good idea of resetting
the CSB entry after use so that we can detect when it has been updated by
the GPU. By instrumenting how long that may be, we can set a reliable
upper bound for how long we should wait for:
513 late, avg of 61 retries (590 ns), max of 1061 retries (10099 ns)
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2045
References: d8f5053117 ("drm/i915/icl: Forcibly evict stale csb entries")
References: HSDES#22011327657, HSDES#1508287568
Suggested-by: Bruce Chang <yu.bruce.chang@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Bruce Chang <yu.bruce.chang@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: stable@vger.kernel.org # v5.4
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200915134923.30088-2-chris@chris-wilson.co.uk
(cherry picked from commit 233c1ae3c8)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
We may try to preempt the currently executing request, only to find that
after unravelling all the dependencies that the original executing
context is still the earliest in the topological sort and re-submitted
back to HW (if we do detect some change in the ELSP that requires
re-submission). However, due to the way we check for wrap-around during
the unravelling, we mark any context that has been submitted just once
(i.e. with the rq->wa_tail set, but the ring->tail earlier) as
potentially wrapping and requiring a forced restore on resubmission.
This was expected to be not a problem, as it was anticipated that most
unwinding for preemption would result in a context switch and the few
that did not would be lost in the noise. It did not take long for
someone to find one particular workload where the cost of those extra
context restores was measurable.
However, since we know the wa_tail is of fixed size, and we know that a
request must be larger than the wa_tail itself, we can safely maintain
the check for request wrapping and check against a slightly future point
in the ring that includes an expected wa_tail. (That is if the
ring->tail is already set to rq->wa_tail, including another 8 bytes in
the check does not invalidate the incremental wrap detection.)
Fixes: 8ab3a3812a ("drm/i915/gt: Incrementally check for rewinding")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Bruce Chang <yu.bruce.chang@intel.com>
Cc: Ramalingam C <ramalingam.c@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: <stable@vger.kernel.org> # v5.4+
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201002083425.4605-1-chris@chris-wilson.co.uk
(cherry picked from commit bb65548e3c)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
When running gem_exec_nop, it floods the system with many requests (with
the goal of userspace submitting faster than the HW can process a single
empty batch). This causes the driver to continually resubmit new
requests onto the end of an active context, a flood of lite-restore
preemptions. If we time this just right, Tigerlake hangs.
Inserting a small delay between the processing of CS events and
submitting the next context, prevents the hang. Naturally it does not
occur with debugging enabled. The suspicion then is that this is related
to the issues with the CS event buffer, and inserting an mmio read of
the CS pointer status appears to be very successful in preventing the
hang. Other registers, or uncached reads, or plain mb, do not prevent
the hang, suggesting that register is key -- but that the hang can be
prevented by a simple udelay, suggests it is just a timing issue like
that encountered by commit 233c1ae3c8 ("drm/i915/gt: Wait for CSB
entries on Tigerlake"). Also note that the hang is not prevented by
applying CTX_DESC_FORCE_RESTORE, or by inserting a delay on the GPU
between requests.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Bruce Chang <yu.bruce.chang@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: stable@vger.kernel.org
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201015195023.32346-1-chris@chris-wilson.co.uk
(cherry picked from commit 6ca7217dff)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
In commit 7994672309 ("drm/i915: Assume 100% brightness when not in
DPCD control mode"), we fixed the brightness level when DPCD control was
not active to max brightness. This is as good as we can guess since most
backlights go on full when uncontrolled.
However in doing so we changed the semantics of the initial
'backlight.enabled' value. At least on Pixelbooks, they were relying
on the brightness level in DP_EDP_BACKLIGHT_BRIGHTNESS_MSB to be 0 on
boot such that enabled would be false. This causes the device to be
enabled when the brightness is set. Without this, brightness control
doesn't work. So by changing brightness to max, we also flipped enabled
to be true on boot.
To fix this, make enabled a function of brightness and backlight control
mechanism.
Fixes: 7994672309 ("drm/i915: Assume 100% brightness when not in DPCD control mode")
Cc: Lyude Paul <lyude@redhat.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Juha-Pekka Heikkila <juhapekka.heikkila@gmail.com>
Cc: "Ville Syrjälä" <ville.syrjala@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Kevin Chowski <chowski@chromium.org>>
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Reviewed-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Lyude Paul <lyude@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200918002845.32766-1-sean@poorly.run
(cherry picked from commit 4ade8f31c2)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Recently, in commit 6735b4632d ("Fonts: Support FONT_EXTRA_WORDS macros
for built-in fonts"), we wrapped each of our built-in data buffers in a
`font_data` structure, in order to use the following macros on them, see
include/linux/font.h:
#define REFCOUNT(fd) (((int *)(fd))[-1])
#define FNTSIZE(fd) (((int *)(fd))[-2])
#define FNTCHARCNT(fd) (((int *)(fd))[-3])
#define FNTSUM(fd) (((int *)(fd))[-4])
#define FONT_EXTRA_WORDS 4
Do the same thing to our new 6x8 font. For built-in fonts, currently we
only use FNTSIZE(). Since this is only a temporary solution for an
out-of-bounds issue in the framebuffer layer (see commit 5af0864079
("fbcon: Fix global-out-of-bounds read in fbcon_get_font()")), all the
three other fields are intentionally set to zero in order to discourage
using these negative-indexing macros.
Signed-off-by: Peilin Ye <yepeilin.cs@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/926453876c92caac34cba8545716a491754d04d5.1603037079.git.yepeilin.cs@gmail.com
As reported by Sphinx:
Documentation/gpu/amdgpu.rst:200: WARNING: Inline emphasis start-string without end-string.
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
As warned when running "make htmldocs":
./drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:345: warning: Function parameter or member 'force_timing_sync' not described in 'amdgpu_display_manager'
This new struct member was not documented at kernel-doc markup.
Fixes: 3d4e52d0cf ("drm/amd/display: Add debugfs for forcing stream timing sync")
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
GPU reset might get called during init time, before
sw_init has been called.
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
It was recently introduced a change that enables driver to disable
streams if pixel clock changes. Consequently, the code path executed in
the disable vbios function expanded to an encoder verification part.
The encoder loop is nested inside the pipe count loop, and both loops
share the 'i' variable in control of their flow. This situation may lead
to an infinite loop because the encoder loop constantly updates the `i`
variable, making the first loop always positive. As a result, we can see
a soft hang during the module load (modprobe amdgpu) and a series of
dmesg log that looks like this:
kernel:[ 124.538727] watchdog: BUG: soft lockup - CPU#2 stuck for 22s!
[modprobe:1000]
RSP: 0018:ffffabbf419bf0e8 EFLAGS: 00000282
RAX: ffffffffc0809de0 RBX: ffff93b35ccc0000 RCX: ffff93b366c21800
RDX: 0000000000000000 RSI: 0000000000000141 RDI: ffff93b35ccc0000
RBP: ffffabbf419bf108 R08: ffffabbf419bf164 R09: 0000000000000001
R10: 0000000000000003 R11: 0000000000000003 R12: 0000000008677d40
R13: 0000000000000141 R14: ffff93b35cfc0000 R15: ffff93b35abc0000
FS: 00007f1400717540(0000) GS:ffff93b37f680000(0000)
knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00005649b66b0968 CR3: 00000003e0fec000 CR4: 0000000000350ee0
Call Trace:
amdgpu_device_rreg+0x17/0x20 [amdgpu]
amdgpu_cgs_read_register+0x14/0x20 [amdgpu]
dm_read_reg_func+0x3a/0xb0 [amdgpu]
get_pixel_clk_frequency_100hz+0x30/0x50 [amdgpu]
dc_commit_state+0x8f1/0xae0 [amdgpu]
? drm_calc_timestamping_constants+0x101/0x160 [drm]
amdgpu_dm_atomic_commit_tail+0x39d/0x21a0 [amdgpu]
? dcn21_validate_bandwidth+0xe5/0x290 [amdgpu]
? kfree+0xc3/0x390
? dcn21_validate_bandwidth+0xe5/0x290 [amdgpu]
...
RSP: 002b:00007fff26009bd8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
RAX: ffffffffffffffda RBX: 000055a8025bea50 RCX: 00007f140085c89d
RDX: 0000000000000000 RSI: 000055a8025b8290 RDI: 000000000000000c
RBP: 0000000000040000 R08: 0000000000000000 R09: 0000000000000000
R10: 000000000000000c R11: 0000000000000246 R12: 000055a8025b8290
R13: 0000000000000000 R14: 000055a8025bead0 R15: 000055a8025bea50
This issue was fixed by introducing a second variable for the internal
loop.
Fixes: 8353d30e74 ("drm/amd/display: disable stream if pixel clock changed with link active")
Reviewed-by: Roman Li <Roman.Li@amd.com>
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When the number of potential color planes grew to 4 we stopped
setting all unused color plane offsets to ~0xfff. The code
still tries to do this, but actually does nothing since the
loop limits are bogus.
skl_check_main_surface() actually depends on this ~0xfff
behaviour as it will make sure to move the main surface
offset below the aux surface offset because the hardware
AUX_DIST must be a non-negative value [1], and for simplicity
it doesn't bother checking if the AUX plane is actually
needed or not. So currently it may end up shuffling the
main surface around based on some stale leftover AUX offset.
The skl+ plane code also just blindly calculates the AUX_DIST
whether or not the AUX plane is actually needed by the hw or
not, and that too will now potentially use some stale AUX
surface offset in the calculation. Would seem nicer to
guarantee a consistent non-negative AUX_DIST always.
So bring back the original ~0xfff offset behaviour for
unused color planes. Though it doesn't seem super likely
that this inconsistency would cause any real issues.
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Fixes: 2dfbf9d287 ("drm/i915/tgl: Gen-12 display can decompress surfaces compressed by the media engine")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201008101608.8652-1-ville.syrjala@linux.intel.com
Reviewed-by: Imre Deak <imre.deak@intel.com>
(cherry picked from commit 79148ce4b2)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Propagated from drm-intel-next-queued:
- Fix CRTC state checker (Ville)
Propated from drm-intel-gt-next:
- Avoid implicit vmpa for highmem on 32b (Chris)
- Prevent PAT attriutes for writecombine if CPU doesn't support PAT (Chris)
- Clear the buffer pool age before use. (Chris)
- Fix error code (Dan)
- Break up error capture compression loops (Chris)
- Fix uninitialized variable in context_create_request (Maarten)
- Check for errors on i915_vm_alloc_pt_stash to avoid NULL dereference (Matt)
- Serialize debugfs i915_gem_objects with ctx->mutex (Chris)
- Fix a rebase mistake caused during drm-intel-gt-next creation (Chris)
- Hold request reference for canceling an active context (Chris)
- Heartbeats fixes (Chris)
- Use usigned during batch copies (Chris)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201002182610.GA2204465@intel.com
