Jammy Zhou [Tue, 10 Nov 2015 23:31:08 +0000 (18:31 -0500)]
drm/amdgpu: support per device powerplay enablement (v2)
The amdgu_powerplay variable is global for multiple GPU instances.
v2: fold in Flora's module option change, protect adev reference in
macros
Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
The hwmgr handles all hardware related calls, including clock/power
gating control, DPM, read and parse PPTable, etc.
v5: squash in fixes
v4: implement acpi's atcs function use cgs interface
v3: fix code style error and add big-endian mode support.
v2: use cgs interface directly in hwmgr sub-module
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
The SMUMGR is one sub-component of powerplay for SMU firmware support.
The SMU handles firmware loading for other IP blocks (GFX, SDMA, etc.)
on VI parts. The adds the core powerplay infrastructure to handle that.
v3: direct use printk in powerplay module.
v2: direct use cgs_read/write_register functions in smu-modules
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Felix Kuehling [Mon, 23 Nov 2015 22:43:48 +0000 (17:43 -0500)]
drm/amdgpu: Fix off-by-one errors in amdgpu_vm_bo_map
eaddr is sometimes treated as the last address inside the address
range, and sometimes as the first address outside the range. This
was resulting in errors when a test filled up the entire address
space. Make it consistent to always be the last address within the
range.
Signed-off-by: Felix.Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Cc: stable@vger.kernel.org
Felix Kuehling [Mon, 23 Nov 2015 22:39:11 +0000 (17:39 -0500)]
drm/radeon: Fix off-by-one errors in radeon_vm_bo_set_addr
eoffset is sometimes treated as the last address inside the address
range, and sometimes as the first address outside the range. This
was resulting in errors when a test filled up the entire address
space. Make it consistent to always be the last address within the
range. Also fixed related errors when checking the VA limit and in
radeon_vm_fence_pts.
Signed-off-by: Felix.Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Cc: stable@vger.kernel.org
Commit 88e72717c2de ("drm/irq: Use unsigned int pipe in public API")
updated the prototype of this function but not the implementation. This
wasn't noticed even through compile tests because the prototype is part
of the source file that uses it and hence the compiler won't know the
prototype when it compiles the implementation.
The right thing would've been to move the prototype to a header that's
included in radeon_kms.c so that the implementation signature could be
checked against it, but the closest thing would've been radeon_drv.h
and including that results in a lot of build errors, so we'll leave it
as is for now.
Cc: Christian König <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Thierry Reding <treding@nvidia.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Mario Kleiner [Wed, 25 Nov 2015 19:14:31 +0000 (20:14 +0100)]
drm/radeon: Fixup hw vblank counter/ts for new drm_update_vblank_count() (v2)
commit 4dfd6486 "drm: Use vblank timestamps to guesstimate how many
vblanks were missed" introduced in Linux 4.4-rc1 makes the drm core
more fragile to drivers which don't update hw vblank counters and
vblank timestamps in sync with firing of the vblank irq and
essentially at leading edge of vblank.
This exposed a problem with radeon-kms/amdgpu-kms which do not
satisfy above requirements:
The vblank irq fires a few scanlines before start of vblank, but
programmed pageflips complete at start of vblank and
vblank timestamps update at start of vblank, whereas the
hw vblank counter increments only later, at start of vsync.
This leads to problems like off by one errors for vblank counter
updates, vblank counters apparently going backwards or vblank
timestamps apparently having time going backwards. The net result
is stuttering of graphics in games, or little hangs, as well as
total failure of timing sensitive applications.
See bug #93147 for an example of the regression on Linux 4.4-rc:
This patch tries to align all above events better from the
viewpoint of the drm core / of external callers to fix the problem:
1. The apparent start of vblank is shifted a few scanlines earlier,
so the vblank irq now always happens after start of this extended
vblank interval and thereby drm_update_vblank_count() always samples
the updated vblank count and timestamp of the new vblank interval.
To achieve this, the reporting of scanout positions by
radeon_get_crtc_scanoutpos() now operates as if the vblank starts
radeon_crtc->lb_vblank_lead_lines before the real start of the hw
vblank interval. This means that the vblank timestamps which are based
on these scanout positions will now update at this earlier start of
vblank.
2. The driver->get_vblank_counter() function will bump the returned
vblank count as read from the hw by +1 if the query happens after
the shifted earlier start of the vblank, but before the real hw increment
at start of vsync, so the counter appears to increment at start of vblank
in sync with the timestamp update.
3. Calls from vblank irq-context and regular non-irq calls are now
treated identical, always simulating the shifted vblank start, to
avoid inconsistent results for queries happening from vblank irq vs.
happening from drm_vblank_enable() or vblank_disable_fn().
4. The radeon_flip_work_func will delay mmio programming a pageflip until
the start of the real vblank iff it happens to execute inside the shifted
earlier start of the vblank, so pageflips now also appear to execute at
start of the shifted vblank, in sync with vblank counter and timestamp
updates. This to avoid some races between updates of vblank count and
timestamps that are used for swap scheduling and pageflip execution which
could cause pageflips to execute before the scheduled target vblank.
The lb_vblank_lead_lines "fudge" value is calculated as the size of
the display controllers line buffer in scanlines for the given video
mode: Vblank irq's are triggered by the line buffer logic when the line
buffer refill for a video frame ends, ie. when the line buffer source read
position enters the hw vblank. This means that a vblank irq could fire at
most as many scanlines before the current reported scanout position of the
crtc timing generator as the number of scanlines the line buffer can
maximally hold for a given video mode.
This patch has been successfully tested on a RV730 card with DCE-3 display
engine and on a evergreen card with DCE-4 display engine, in single-display
and dual-display configuration, with different video modes.
A similar patch is needed for amdgpu-kms to fix the same problem.
Limitations:
- Line buffer sizes in pixels are hard-coded on < DCE-4 to a value
i just guessed to be high enough to work ok, lacking info on the true
sizes atm.
Fixes: fdo#93147 Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Michel Dänzer <michel.daenzer@amd.com> Cc: Harry Wentland <Harry.Wentland@amd.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
(v1) Tested-by: Dave Witbrodt <dawitbro@sbcglobal.net>
(v2) Refine radeon_flip_work_func() for better efficiency:
In radeon_flip_work_func, replace the busy waiting udelay(5)
with event lock held by a more performance and energy efficient
usleep_range() until at least predicted true start of hw vblank,
with some slack for scheduler happiness. Release the event lock
during waits to not delay other outputs in doing their stuff, as
the waiting can last up to 200 usecs in some cases.
Retested on DCE-3 and DCE-4 to verify it still works nicely.
(v2) Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Fri, 11 Dec 2015 20:01:23 +0000 (21:01 +0100)]
drm/amdgpu: keep the PTs validation list in the VM v2
This avoids allocating it on the fly.
v2: fix grammar in comment
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Christian König [Fri, 11 Dec 2015 14:16:32 +0000 (15:16 +0100)]
drm/amdgpu: split VM PD and PT handling during CS
This way we avoid the extra allocation for the page directory entry.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Christian König [Fri, 11 Dec 2015 13:39:05 +0000 (14:39 +0100)]
drm/amdgpu: put VM page tables directly into duplicates list
They share the reservation object with the page directory anyway.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Chunming Zhou [Thu, 10 Dec 2015 07:46:50 +0000 (15:46 +0800)]
drm/amdgpu: change default sched jobs to 32
Change the default scheduler queue size from 16 to 32.
Signed-off-by: Chunming Zhou <David1.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Chunming Zhou [Thu, 10 Dec 2015 07:45:11 +0000 (15:45 +0800)]
drm/amdgpu: unify AMDGPU_CTX_MAX_CS_PENDING and amdgpu_sched_jobs
Signed-off-by: Chunming Zhou <David1.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Chunming Zhou [Thu, 10 Dec 2015 07:50:02 +0000 (15:50 +0800)]
drm/amdgpu: handle error case for ctx
Properly handle ctx init failure.
Signed-off-by: Chunming Zhou <David1.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Chunming Zhou [Fri, 11 Dec 2015 10:22:52 +0000 (18:22 +0800)]
drm/amdgpu: add entity only when first job come
umd somtimes will create a context for every ring,
that means some entities wouldn't be used at all.
Signed-off-by: Chunming Zhou <David1.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Nicolai Hähnle [Wed, 2 Dec 2015 16:35:12 +0000 (17:35 +0100)]
drm/amdgpu: fix race condition in amd_sched_entity_push_job
As soon as we leave the spinlock after the job has been added to the job
queue, we can no longer rely on the job's data to be available.
I have seen a null-pointer dereference due to sched == NULL in
amd_sched_wakeup via amd_sched_entity_push_job and
amd_sched_ib_submit_kernel_helper. Since the latter initializes
sched_job->sched with the address of the ring scheduler, which is
guaranteed to be non-NULL, this race appears to be a likely culprit.
Signed-off-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Bugzilla: https://bugs.freedesktop.org/attachment.cgi?bugid=93079 Reviewed-by: Christian König <christian.koenig@amd.com>
Tom St Denis [Mon, 30 Nov 2015 19:13:11 +0000 (14:13 -0500)]
amdgpu/gfxv8: Add missing break to switch statement from states init code
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
Alex Deucher [Tue, 24 Nov 2015 22:43:42 +0000 (17:43 -0500)]
drm/amdgpu: add EDC support for CZ (v3)
This adds EDC support for CZ.
EDC = Error Correction and Detection
This code properly initializes the EDC hardware and
resets the error counts. This is done in late_init
since it requires the IB pool which is not initialized
during hw_init.
v2: fix the IB size as noted by Felix, fix shader pgm
register programming
v3: use the IB for the shaders as suggested by Christian
Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Daniel Vetter [Mon, 23 Nov 2015 09:32:38 +0000 (10:32 +0100)]
drm/radeon: Use unlocked gem unreferencing
For drm_gem_object_unreference callers are required to hold
dev->struct_mutex, which these paths don't. Enforcing this requirement
has become a bit more strict with
drm/gem: Check locking in drm_gem_object_unreference
Cc: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Daniel Vetter [Mon, 23 Nov 2015 09:32:37 +0000 (10:32 +0100)]
drm/amdgpu: Use unlocked gem unreferencing
For drm_gem_object_unreference callers are required to hold
dev->struct_mutex, which these paths don't. Enforcing this requirement
has become a bit more strict with
drm/gem: Check locking in drm_gem_object_unreference
Cc: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
monk.liu [Thu, 29 Oct 2015 07:33:06 +0000 (15:33 +0800)]
drm/amdgpu: Use new read bios from rom callback
Read the vbios directly from the rom. In some cases,
e.g., virtualization, the rom is not available via
the BAR or other means. Access it directly.
This is an updated version of Monks original patch which
uses family specific callbacks and unifies some of the
validation checking.
Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com> Signed-off-by: Monk Liu <Monk.Liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex Deucher [Tue, 24 Nov 2015 15:37:54 +0000 (10:37 -0500)]
drm/amdgpu: add read_bios_from_rom callback for VI parts
Read the vbios image directly from the rom.
Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Monk Liu <monk.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex Deucher [Tue, 24 Nov 2015 15:34:45 +0000 (10:34 -0500)]
drm/amdgpu: add read_bios_from_rom callback for CI parts
Read the vbios image directly from the rom.
Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Monk Liu <monk.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex Deucher [Tue, 24 Nov 2015 15:14:28 +0000 (10:14 -0500)]
drm/amdgpu: add a callback for reading the bios from the rom directly
This is necessary when the vbios image is not directly accessible via
the rom BAR or legacy vga location.
Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Monk Liu <monk.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Julia Lawall [Sun, 29 Nov 2015 16:12:41 +0000 (17:12 +0100)]
drm/radeon: constify radeon_asic_ring structures
The radeon_asic_ring structures are never modified, so declare them as
const.
Done with the help of Coccinelle.
Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex Deucher [Mon, 23 Nov 2015 18:13:45 +0000 (13:13 -0500)]
drm/radeon: remove UMS support
It's been deprecated behind a kconfig option for almost
two years and hasn't really been supported for years before
that. DDX support was dropped more than three years ago.
Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Dave Airlie [Mon, 30 Nov 2015 22:01:53 +0000 (08:01 +1000)]
Merge tag 'drm-intel-next-2015-11-20-merged' of git://anongit.freedesktop.org/drm-intel into drm-next
drm-intel-next-2015-11-20-rebased:
4 weeks because of my vacation, so a bit more:
- final bits of the typesafe register mmio functions (Ville)
- power domain fix for hdmi detection (Imre)
- tons of fixes and improvements to the psr code (Rodrigo)
- refactoring of the dp detection code (Ander)
- complete rework of the dmc loader and dc5/dc6 handling (Imre, Patrik and
others)
- dp compliance improvements from Shubhangi Shrivastava
- stop_machine hack from Chris to fix corruptions when updating GTT ptes on bsw
- lots of fifo underrun fixes from Ville
- big pile of fbc fixes and improvements from Paulo
- fix fbdev failures paths (Tvrtko and Lukas Wunner)
- dp link training refactoring (Ander)
- interruptible prepare_plane for atomic (Maarten)
- basic kabylake support (Deepak&Rodrigo)
- don't leak ringspace on resets (Chris)
drm-intel-next-2015-10-23:
- 2nd attempt at atomic watermarks from Matt, but just prep for now
- fixes all over
* tag 'drm-intel-next-2015-11-20-merged' of git://anongit.freedesktop.org/drm-intel: (209 commits)
drm/i915: Update DRIVER_DATE to 20151120
drm/i915: take a power domain reference while checking the HDMI live status
drm/i915: take a power domain ref only when needed during HDMI detect
drm/i915: Tear down fbdev if initialization fails
async: export current_is_async()
Revert "drm/i915: Initialize HWS page address after GPU reset"
drm/i915: Fix oops caused by fbdev initialization failure
drm/i915: Fix i915_ggtt_view_equal to handle rotation correctly
drm/i915: Stuff rotation params into view union
drm/i915: Drop return value from intel_fill_fb_ggtt_view
drm/i915 : Fix to remove unnecsessary checks in postclose function.
drm/i915: add MISSING_CASE to a few port/aux power domain helpers
drm/i915/ddi: fix intel_display_port_aux_power_domain() after HDMI detect
drm/i915: Remove platform specific *_dp_detect() functions
drm/i915: Don't do edp panel detection in g4x_dp_detect()
drm/i915: Send TP1 TP2/3 even when panel claims no NO_TRAIN_ON_EXIT.
drm/i915: PSR: Don't Skip aux handshake on DP_PSR_NO_TRAIN_ON_EXIT.
drm/i915: Reduce PSR re-activation time for VLV/CHV.
drm/i915: Delay first PSR activation.
drm/i915: Type safe register read/write
...
Dave Airlie [Mon, 30 Nov 2015 22:01:18 +0000 (08:01 +1000)]
Merge tag 'topic/drm-misc-2015-11-26' of git://anongit.freedesktop.org/drm-intel into drm-next
Here's the first drm-misc pull, with really mostly misc stuff all over.
Somewhat invasive is only Ville's change to mark the arg struct for
fb_create const - that might conflict with a new driver pull. So better to
get in fast.
* tag 'topic/drm-misc-2015-11-26' of git://anongit.freedesktop.org/drm-intel:
drm/mm: use list_next_entry
drm/i915: fix potential dangling else problems in for_each_ macros
drm: fix potential dangling else problems in for_each_ macros
drm/sysfs: Send out uevent when connector->force changes
drm/atomic: Small documentation fix.
drm/mm: rewrite drm_mm_for_each_hole
drm/sysfs: Grab lock for edid/modes_show
drm: Print the src/dst/clip rectangles in error in drm_plane_helper
drm: Add "prefix" parameter to drm_rect_debug_print()
drm: Keep coordinates in the typical x, y, w, h order instead of x, y, h, w
drm: Pass the user drm_mode_fb_cmd2 as const to .fb_create()
drm: modes: replace simple_strtoul by kstrtouint
drm: Describe the Rotation property bits.
drm: Remove unused fbdev_list members
GPU-DRM: Delete unnecessary checks before drm_property_unreference_blob()
drm/dp: add eDP DPCD backlight control bit definitions
drm/tegra: Remove local fbdev emulation Kconfig option
drm/imx: Remove local fbdev emulation Kconfig option
drm/gem: Update/Polish docs
drm: Update GEM refcounting docs
Linus Torvalds [Mon, 30 Nov 2015 01:38:08 +0000 (17:38 -0800)]
Merge branch 'drm-fixes' of git://people.freedesktop.org/~airlied/linux
Pull nouveau and radeon fixes from Dave Airlie:
"Just some nouveau and radeon/amdgpu fixes.
The nouveau fixes look large as the firmware context files are
regenerated, but the actual change is quite small"
* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux:
drm/radeon: make some dpm errors debug only
drm/nouveau/volt/pwm/gk104: fix an off-by-one resulting in the voltage not being set
drm/nouveau/nvif: allow userspace access to its own client object
drm/nouveau/gr/gf100-: fix oops when calling zbc methods
drm/nouveau/gr/gf117-: assume no PPC if NV_PGRAPH_GPC_GPM_PD_PES_TPC_ID_MASK is zero
drm/nouveau/gr/gf117-: read NV_PGRAPH_GPC_GPM_PD_PES_TPC_ID_MASK from correct GPC
drm/nouveau/gr/gf100-: split out per-gpc address calculation macro
drm/nouveau/bios: return actual size of the buffer retrieved via _ROM
drm/nouveau/instmem: protect instobj list with a spinlock
drm/nouveau/pci: enable c800 magic for some unknown Samsung laptop
drm/nouveau/pci: enable c800 magic for Clevo P157SM
drm/radeon: make rv770_set_sw_state failures non-fatal
drm/amdgpu: move dependency handling out of atomic section v2
drm/amdgpu: optimize scheduler fence handling
drm/amdgpu: remove vm->mutex
drm/amdgpu: add mutex for ba_va->valids/invalids
drm/amdgpu: adapt vce session create interface changes
drm/amdgpu: vce use multiple cache surface starting from stoney
drm/amdgpu: reset vce trap interrupt flag
projects / karo-tx-linux.git / log