This requires a bit of background. Properly done a modeset driver's
unload/remove sequence should be
drm_dev_unplug();
drm_atomic_helper_shutdown();
drm_dev_put();
The trouble is that the drm_dev_unplugged() checks are by design racy,
they do not synchronize against all outstanding ioctl. This is because
those ioctl could block forever (both for modeset and for driver
specific ioctls), leading to deadlocks in hotunplug. Instead the code
sections that touch the hardware need to be annotated with
drm_dev_enter/exit, to avoid accessing hardware resources after the
unload/remove has finished.
To avoid use-after-free issues all the involved userspace visible
objects are supposed to hold a reference on the underlying drm_device,
like drm_file does.
The issue now is that we missed one, the atomic modeset ioctl can be run
in a nonblocking fashion, and in that case it cannot rely on the implied
drm_device reference provided by the ioctl calling context. This can
result in a use-after-free if an nonblocking atomic commit is carefully
raced against a driver unload.
Fix this by unconditionally grabbing a drm_device reference for any
drm_atomic_state structures. Strictly speaking this isn't required for
blocking commits and TEST_ONLY calls, but it's the simpler approach.
Thanks to shanzhulig for the initial idea of grabbing an unconditional
reference, I just added comments, a condensed commit message and fixed a
minor potential issue in where exactly we drop the final reference.
Reported-by: shanzhulig <shanzhulig@gmail.com>
Suggested-by: shanzhulig <shanzhulig@gmail.com>
Reviewed-by: Maxime Ripard <mripard@kernel.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: David Airlie <airlied@gmail.com>
Cc: stable@kernel.org
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Recent code set xcp_id stored from file private data when opening
device to amdgpu bo for accounting memory usage etc, but not all
VMs are attached to this fpriv structure like the vm cases in
amdgpu_mes_self_test, otherwise, KASAN will complain below out
of bound access. And more importantly, VM code should not touch
fpriv structure, so drop fpriv code handling from amdgpu_vm_pt.
[ 77.292314] BUG: KASAN: slab-out-of-bounds in amdgpu_vm_pt_create+0x17e/0x4b0 [amdgpu]
[ 77.293845] Read of size 4 at addr ffff888102c48a48 by task modprobe/1069
[ 77.294146] Call Trace:
[ 77.294178] <TASK>
[ 77.294208] dump_stack_lvl+0x49/0x63
[ 77.294260] print_report+0x16f/0x4a6
[ 77.294307] ? amdgpu_vm_pt_create+0x17e/0x4b0 [amdgpu]
[ 77.295979] ? kasan_complete_mode_report_info+0x3c/0x200
[ 77.296057] ? amdgpu_vm_pt_create+0x17e/0x4b0 [amdgpu]
[ 77.297556] kasan_report+0xb4/0x130
[ 77.297609] ? amdgpu_vm_pt_create+0x17e/0x4b0 [amdgpu]
[ 77.299202] __asan_load4+0x6f/0x90
[ 77.299272] amdgpu_vm_pt_create+0x17e/0x4b0 [amdgpu]
[ 77.300796] ? amdgpu_init+0x6e/0x1000 [amdgpu]
[ 77.302222] ? amdgpu_vm_pt_clear+0x750/0x750 [amdgpu]
[ 77.303721] ? preempt_count_sub+0x18/0xc0
[ 77.303786] amdgpu_vm_init+0x39e/0x870 [amdgpu]
[ 77.305186] ? amdgpu_vm_wait_idle+0x90/0x90 [amdgpu]
[ 77.306683] ? kasan_set_track+0x25/0x30
[ 77.306737] ? kasan_save_alloc_info+0x1b/0x30
[ 77.306795] ? __kasan_kmalloc+0x87/0xa0
[ 77.306852] amdgpu_mes_self_test+0x169/0x620 [amdgpu]
v2: without specifying xcp partition for PD/PT bo, the xcp id is -1.
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2686
Fixes: 3ebfd221c1 ("drm/amdkfd: Store xcp partition id to amdgpu bo")
Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Tested-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
file_priv needs to be setup firstly, otherwise, root PD
will always be allocated on partition 0, even if opening
the device from other partitions.
Fixes: 3ebfd221c1 ("drm/amdkfd: Store xcp partition id to amdgpu bo")
Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
Specific TBT4 dock doesn't send out short HPD to notify source
that IRQ event DOWN_REP_MSG_RDY is set. Which violates the spec
and cause source can't send out streams to mst sinks.
[How]
To cover this misbehavior, add an additional polling method to detect
DOWN_REP_MSG_RDY is set. HPD driven handling method is still kept.
Just hook up our handler to drm mgr->cbs->poll_hpd_irq().
Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Reviewed-by: Jerry Zuo <jerry.zuo@amd.com>
Acked-by: Alan Liu <haoping.liu@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Fix the following errors & warnings reported by checkpatch:
ERROR: space required before the open brace '{'
ERROR: space required before the open parenthesis '('
ERROR: that open brace { should be on the previous line
ERROR: space prohibited before that ',' (ctx:WxW)
ERROR: else should follow close brace '}'
ERROR: open brace '{' following function definitions go on the next line
ERROR: code indent should use tabs where possible
WARNING: braces {} are not necessary for single statement blocks
WARNING: void function return statements are not generally useful
WARNING: Block comments use * on subsequent lines
WARNING: Block comments use a trailing */ on a separate line
Cc: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Up until now, amdgpu was silently degrading to vsync when
user-space requested an async flip but the hardware didn't support
it.
The hardware doesn't support immediate flips when the update changes
the FB pitch, the DCC state, the rotation, enables or disables CRTCs
or planes, etc. This is reflected in the dm_crtc_state.update_type
field: UPDATE_TYPE_FAST means that immediate flip is supported.
Silently degrading async flips to vsync is not the expected behavior
from a uAPI point-of-view. Xorg expects async flips to fail if
unsupported, to be able to fall back to a blit. i915 already behaves
this way.
This patch aligns amdgpu with uAPI expectations and returns a failure
when an async flip is not possible.
Signed-off-by: Simon Ser <contact@emersion.fr>
Reviewed-by: André Almeida <andrealmeid@igalia.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: André Almeida <andrealmeid@igalia.com>
Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
In below thousands of screen rotation loop tests with virtual display
enabled, a CPU hard lockup issue may happen, leading system to unresponsive
and crash.
do {
xrandr --output Virtual --rotate inverted
xrandr --output Virtual --rotate right
xrandr --output Virtual --rotate left
xrandr --output Virtual --rotate normal
} while (1);
NMI watchdog: Watchdog detected hard LOCKUP on cpu 1
? hrtimer_run_softirq+0x140/0x140
? store_vblank+0xe0/0xe0 [drm]
hrtimer_cancel+0x15/0x30
amdgpu_vkms_disable_vblank+0x15/0x30 [amdgpu]
drm_vblank_disable_and_save+0x185/0x1f0 [drm]
drm_crtc_vblank_off+0x159/0x4c0 [drm]
? record_print_text.cold+0x11/0x11
? wait_for_completion_timeout+0x232/0x280
? drm_crtc_wait_one_vblank+0x40/0x40 [drm]
? bit_wait_io_timeout+0xe0/0xe0
? wait_for_completion_interruptible+0x1d7/0x320
? mutex_unlock+0x81/0xd0
amdgpu_vkms_crtc_atomic_disable
It's caused by a stuck in lock dependency in such scenario on different
CPUs.
CPU1 CPU2
drm_crtc_vblank_off hrtimer_interrupt
grab event_lock (irq disabled) __hrtimer_run_queues
grab vbl_lock/vblank_time_block amdgpu_vkms_vblank_simulate
amdgpu_vkms_disable_vblank drm_handle_vblank
hrtimer_cancel grab dev->event_lock
So CPU1 stucks in hrtimer_cancel as timer callback is running endless on
current clock base, as that timer queue on CPU2 has no chance to finish it
because of failing to hold the lock. So NMI watchdog will throw the errors
after its threshold, and all later CPUs are impacted/blocked.
So use hrtimer_try_to_cancel to fix this, as disable_vblank callback
does not need to wait the handler to finish. And also it's not necessary
to check the return value of hrtimer_try_to_cancel, because even if it's
-1 which means current timer callback is running, it will be reprogrammed
in hrtimer_start with calling enable_vblank to make it works.
v2: only re-arm timer when vblank is enabled (Christian) and add a Fixes
tag as well
v3: drop warn printing (Christian)
v4: drop superfluous check of blank->enabled in timer function, as it's
guaranteed in drm_handle_vblank (Christian)
Fixes: 84ec374bd5 ("drm/amdgpu: create amdgpu_vkms (v4)")
Cc: stable@vger.kernel.org
Suggested-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why&How]
DCN301 does not have FAMS hence the workaround needed on other DCN3x
variants related to OTG min/max selector programming is not applicable for it.
Hence isolate it and have it use the old sequence without workaround.
Fixes: 1598fc5764 ("drm/amd/display: Program OTG vtotal min/max selectors unconditionally for DCN1+")
Reviewed-by: Swapnil Patel <swapnil.patel@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Tested-by: Guilherme G. Piccoli <gpiccoli@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why&How]
Make a few functions non static so that they can be reused for other
asic. This is in preparation for separating out OTG programming sequence
for DCN301
Fixes: 1598fc5764 ("drm/amd/display: Program OTG vtotal min/max selectors unconditionally for DCN1+")
Reviewed-by: Swapnil Patel <swapnil.patel@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Tested-by: Guilherme G. Piccoli <gpiccoli@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
SMU7 does a check if the dGPU is inserted into a Rocket Lake system,
to turn off DPM. Extend this check to all systems that have problems
with dynamic switching by using the
amdgpu_device_pcie_dynamic_switching_supported() helper.
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When a new mode is set to modeset->mode, the previous mode should be freed.
This fixes the following kmemleak report:
drm_mode_duplicate+0x45/0x220 [drm]
drm_client_modeset_probe+0x944/0xf50 [drm]
__drm_fb_helper_initial_config_and_unlock+0xb4/0x2c0 [drm_kms_helper]
drm_fbdev_client_hotplug+0x2bc/0x4d0 [drm_kms_helper]
drm_client_register+0x169/0x240 [drm]
ast_pci_probe+0x142/0x190 [ast]
local_pci_probe+0xdc/0x180
work_for_cpu_fn+0x4e/0xa0
process_one_work+0x8b7/0x1540
worker_thread+0x70a/0xed0
kthread+0x29f/0x340
ret_from_fork+0x1f/0x30
cc: <stable@vger.kernel.org>
Reported-by: Zhang Yi <yizhan@redhat.com>
Signed-off-by: Jocelyn Falempe <jfalempe@redhat.com>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20230711092203.68157-3-jfalempe@redhat.com
dmt_mode is allocated and never freed in this function.
It was found with the ast driver, but most drivers using generic fbdev
setup are probably affected.
This fixes the following kmemleak report:
backtrace:
[<00000000b391296d>] drm_mode_duplicate+0x45/0x220 [drm]
[<00000000e45bb5b3>] drm_client_target_cloned.constprop.0+0x27b/0x480 [drm]
[<00000000ed2d3a37>] drm_client_modeset_probe+0x6bd/0xf50 [drm]
[<0000000010e5cc9d>] __drm_fb_helper_initial_config_and_unlock+0xb4/0x2c0 [drm_kms_helper]
[<00000000909f82ca>] drm_fbdev_client_hotplug+0x2bc/0x4d0 [drm_kms_helper]
[<00000000063a69aa>] drm_client_register+0x169/0x240 [drm]
[<00000000a8c61525>] ast_pci_probe+0x142/0x190 [ast]
[<00000000987f19bb>] local_pci_probe+0xdc/0x180
[<000000004fca231b>] work_for_cpu_fn+0x4e/0xa0
[<0000000000b85301>] process_one_work+0x8b7/0x1540
[<000000003375b17c>] worker_thread+0x70a/0xed0
[<00000000b0d43cd9>] kthread+0x29f/0x340
[<000000008d770833>] ret_from_fork+0x1f/0x30
unreferenced object 0xff11000333089a00 (size 128):
cc: <stable@vger.kernel.org>
Fixes: 1d42bbc8f7 ("drm/fbdev: fix cloning on fbcon")
Reported-by: Zhang Yi <yizhan@redhat.com>
Signed-off-by: Jocelyn Falempe <jfalempe@redhat.com>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20230711092203.68157-2-jfalempe@redhat.com
SMU13 overrides dynamic PCIe lane width and dynamic speed by when on
certain hosts. commit 38e4ced804 ("drm/amd/pm: conditionally disable
pcie lane switching for some sienna_cichlid SKUs") worked around this
issue by setting up certain SKUs to set up certain limits, but the same
fundamental problem with those hosts affects all SMU11 implmentations
as well, so align the SMU11 and SMU13 driver handling.
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.1.x
the smu driver_table is used for all types of smu
tables data transcation (e.g: PPtable, Metrics, i2c, Ecc..).
it is necessary to hold this lock to avoiding data tampering
during the i2c read operation.
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Pull drm fixes from Dave Airlie:
"Lots of fixes, mostly i915 and amdgpu. It's two weeks of i915, and I
think three weeks of amdgpu.
fbdev:
- Fix module infos on sparc
panel:
- Fix mode on Starry-ili9882t
i915:
- Allow DC states along with PW2 only for PWB functionality [adlp+]
- Fix SSC selection for MPLLA [mtl]
- Use hw.adjusted mode when calculating io/fast wake times [psr]
- Apply min softlimit correctly [guc/slpc]
- Assign correct hdcp content type [hdcp]
- Add missing forward declarations/includes to display power headers
- Fix BDW PSR AUX CH data register offsets [psr]
- Use mock device info for creating mock device
amdgpu:
- Misc cleanups
- GFX 9.4.3 fixes
- DEBUGFS build fix
- Fix LPDDR5 reporting
- ASPM fixes
- DCN 3.1.4 fixes
- DP MST fixes
- DCN 3.2.x fixes
- Display PSR TCON fixes
- SMU 13.x fixes
- RAS fixes
- Vega12/20 SMU fixes
- PSP flashing cleanup
- GFX9 MCBP fixes
- SR-IOV fixes
- GPUVM clear mappings fix for always valid BOs
- Add FAMS quirk for problematic monitor
- Fix possible UAF
- Better handle monentary temperature fluctuations
- SDMA 4.4.2 fixes
- Fencing fix"
* tag 'drm-next-2023-07-07' of git://anongit.freedesktop.org/drm/drm: (83 commits)
drm/i915: use mock device info for creating mock device
drm/i915/psr: Fix BDW PSR AUX CH data register offsets
drm/amdgpu: Fix potential fence use-after-free v2
drm/amd/pm: avoid unintentional shutdown due to temperature momentary fluctuation
drm/amd/pm: expose swctf threshold setting for legacy powerplay
drm/amd/display: 3.2.241
drm/amd/display: Take full update path if number of planes changed
drm/amd/display: Create debugging mechanism for Gaming FAMS
drm/amd/display: Add monitor specific edid quirk
drm/amd/display: For new fast update path, loop through each surface
drm/amd/display: Remove Phantom Pipe Check When Calculating K1 and K2
drm/amd/display: Limit new fast update path to addr and gamma / color
drm/amd/display: Fix the delta clamping for shaper LUT
drm/amdgpu: Keep non-psp path for partition switch
drm/amd/display: program DPP shaper and 3D LUT if updated
Revert "drm/amd/display: edp do not add non-edid timings"
drm/amdgpu: share drm device for pci amdgpu device with 1st partition device
drm/amd/pm: Add GFX v9.4.3 unique id to sysfs
drm/amd/pm: Enable pp_feature attribute
drm/amdgpu/vcn: Need to unpause dpg before stop dpg
...
