| Age | Commit message (Collapse) | Author |
|---|
|
amdgpu_pci_remove() calls drm_dev_unplug() before invoking the fini
routines. After drm_dev_unplug() the drm_dev_enter() guard in
amdgpu_ttm_fini() always returns false, so iounmap() for
aper_base_kaddr is silently skipped. On connected_to_cpu hardware
ioremap_cache() maps the aperture as WB; when iounmap() is skipped the
stale WB PAT entry persists. On reload IP discovery's
memremap(MEMREMAP_WC) on the same aperture range hits a WB/WC conflict,
producing an ioremap error and failing re-probe.
Remove the drm_dev_enter() guard and call iounmap() unconditionally.
The aperture mapping is plain MMIO and does not require device-presence
protection. Surprise-removal cleanup of aper_base_kaddr is already
handled unconditionally by amdgpu_device_unmap_mmio().
Fixes: 62d5f9f7110a ("drm/amdgpu: Unmap MMIO mappings when device is not unplugged")
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
devres teardown is LIFO. The aperture devres node was registered after
the DRM device node, so devres_release_all() unmaps the aperture before
the DRM device release callback fires amdgpu_device_fini_sw(). IP
sw_fini callbacks (e.g. vcn_v4_0_sw_fini) write to fw_shared through a
pointer derived from aper_base_kaddr, causing a kernel page fault on
probe failure / rollback:
BUG: unable to handle page fault ... PMD 0
RIP: vcn_v4_0_sw_fini+0x7b/0x170 [amdgpu]
Call Trace:
amdgpu_device_fini_sw
amdgpu_driver_release_kms
devm_drm_dev_init_release
devres_release_all
This reverts commit d871e99879cb5fd1fa798b006b4888887e63a17a.
Fixes: d871e99879cb ("drm/amdgpu: fix aperture mapping leak")
Reported-by: Yuansheng Mao <yuansheng.mao@amd.com>
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Enable IP block soft reset as a GPU recovery method for GFX6
graphics and compute rings.
This improves current user experience on all GFX6 chips.
The current GPU recovery method is a legacy ASIC reset which
always clears the contents of VRAM, which means that a buggy
(hanging) app can crash the whole graphical session, which
is less than ideal. Also on some GPUs the ASIC reset causes
the GPU to fall off the PCIe bus so it's not desireable.
Using GFX IP block soft reset means that we can now
move on from GFX hangs on GFX6 dGPUs without crashing the
whole system.
Tested with the "hard_reset_cp_wait" test case from the
Hang Test Suite created by Natalie Vock and Konstantin Seurer.
This Vulkan testcase waits for an event that never occurs,
effectively a WAIT_REG_MEM packet that intentionally hangs.
IP block soft reset can resolve that hang and allow
the rest of the system to move on and keep functioning
without needing a full ASIC reset.
Tested on the following chips:
Tahiti (FirePro W9000, Radeon HD 7870 XT)
Cape Verde (Radeon R7 450)
Pitcairn (Radeon R9 270X)
Oland (Radeon 430)
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Update the register definition for GRBM_SOFT_RESET
to match what was in the old radeon driver and use
these bits in the soft reset implementation.
For the soft reset, use basically the same
implementation as GFX7-8, the main difference being
the GRBM_SOFT_RESET bit fields and the fact that
GFX6 doesn't have MQD/HQD. Reset every block using
the GRBM, then proceed to reset the GRBM and SEM blocks
using the SRBM.
The soft reset also calls the clock and powergating
functions of the IP block. This is necessary for
correct operation, otherwise the GPU might fall
off the PCIe bus.
Add a gfx_v6_0_late_init() function for consistency
with other GPU generations. This function will
later serve the same purpose as it does on GFX7+
when we get around to enable more IRQs on GFX6.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
COND_EXEC tells the CP to discard the dwords following it
when its condition is zero (false).
This is useful for GPU recovery because it can help reduce
collateral damage during GFX IP block soft reset, meaning
that it reduces the likelyhood that we fail some jobs which
are not guilty of the hang as the IP block soft reset
mechanism clears the condition before doing the reset.
Note that this packet is only 4 DW on GFX6 (as opposed
to GFX7 and newer where it's 5 DW).
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Adjust gfx_v6_0_setup_tcc() to keep it working after
a GFX IP block soft reset. On a soft reset, the
TCP_CHAN_STEER_LO/HI registers are not cleared so
the function needs a slight adjustment to how the
number of active TCCs are calculated.
Additionally, let's expose the disabled TCC mask
in the tcc_disabled_mask field, like on other GPUs.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Emit a compute CLEAR_STATE packet on the compute rings after
the GFX ring already finished executing ME_INITIALIZE and
before the ring test, so that gfx_v6_0_cp_gfx_resume() can
wait until the CLEAR_STATE is complete.
For reference, see si_cp_start() in the old radeon driver.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Clear the WPTR and RPTR at ring initialization.
Additionally clear the ring contents too.
This is necessary so that the IP block soft reset can
bring the rings back to a clean state.
After a reset, the ring contents could contain packets
emitted before the reset, and thus need to be cleared
to prevent the command processor from executing packets
left over in the ring from before the reset.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
In GFX6 GPUs, compute takes the same CP path as graphics.
CP ME command parser executes packets for each ring buffer:
RB0 supports graphics, RB1 and RB2 are compute only.
Initialize all three rings before calling gfx_v6_0_cp_gfx_start()
to make sure they are all in a sane state before execution starts.
Previously, the two compute-only rings were initialized after
the ME had been already started, which could cause the ME to
start executing the ring contents before the rings could be
properly initialized. This happens to work when the HW is first
initialized, but not during an IP block reset where we want
to reinitialize the compute rings before starting the ME
to prevent it from executing garbage from these rings.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
On GFX6, the compute rings use the same CP path as
the graphics ring. The only difference is that they
don't support draw commands. (As opposed to GFX7 and
newer which have a separate command parser that is
called MEC for compute queues.)
This means that we have to take into consideration
that the PFP also exists on compute queues on GFX6:
Use PFP for register writes on both graphics and
compute queues.
In the pipeline sync, use the PFP to wait for the
previous fence (and not the ME) to prevent the PFP
from starting to execute the next submission while
the ME is still in the previous submission.
After a VM flush, emit PFP_SYNC_ME on compute
queues as well.
Fixes: 2cd46ad22383 ("drm/amdgpu: add graphic pipeline implementation for si v8")
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Implement the emit_switch_buffer() function instead of emitting
them duing emit_ib, emit_pipeline_sync and emit_vm_flush.
Note that it isn't necessary to emit these in both
emit_pipeline_sync() and emit_vm_flush() because
amdgpu_vm_flush() already calls these when calling
either of those functions.
Fixes: 2cd46ad22383 ("drm/amdgpu: add graphic pipeline implementation for si v8")
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Enable the MES process/gang context load from MES local memory,
this will reduce the MES firmware and driver handshake latency.
Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Michael Chen <michael.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
The RAS manager uses the rascore debug mode setting to control whether
MCA data is read directly or collected through PMFW MCA polling and
ClearMcaOnRead. Track that debug mode state in ras_mgr so
amdgpu_ras_get_error_query_mode() can classify queries as direct or
firmware-backed.
Limit the PMFW polling wait in recovery to firmware-backed MODE1 fatal
recovery so other reset paths, such as MODE2, do not pay the delay
unnecessarily.
Signed-off-by: Xiang Liu <xiang.liu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
It's more reasonable to tear down the rs64mem bitmap software
context at MES sw_fini phase. This also can avoid the following
lock order issue.
[ 2529.150983] kworker/u64:1/3134 is trying to acquire lock:
[ 2529.151206] ffff8aebd9a3fa10 (reservation_ww_class_mutex){+.+.}-{4:4}, at: amdgpu_bo_free_kernel+0x4e/0x130 [amdgpu]
[ 2529.151989]
but task is already holding lock:
[ 2529.152227] ffff8aebd2411648 (&reset_domain->sem){++++}-{4:4}, at: amdgpu_device_lock_reset_domain+0x20/0x30 [amdgpu]
[ 2529.153008]
which lock already depends on the new lock.
[ 2529.153342]
the existing dependency chain (in reverse order) is:
[ 2529.153645]
-> #2 (&reset_domain->sem){++++}-{4:4}:
[ 2529.153913] down_read+0x4a/0x240
[ 2529.154081] amdgpu_userq_destroy+0xd8/0x3a0 [amdgpu]
[ 2529.154635] amdgpu_userq_ioctl+0x3e2/0xe30 [amdgpu]
[ 2529.155157] drm_ioctl_kernel+0xaf/0x110 [drm]
[ 2529.155401] drm_ioctl+0x290/0x510 [drm]
[ 2529.155612] amdgpu_drm_ioctl+0x52/0x90 [amdgpu]
[ 2529.156068] __x64_sys_ioctl+0xa0/0xf0
[ 2529.156249] x64_sys_call+0x1278/0x21c0
[ 2529.156434] do_syscall_64+0xbe/0x5f0
[ 2529.156611] entry_SYSCALL_64_after_hwframe+0x76/0x7e
[ 2529.156842]
-> #1 (&userq_mgr->userq_mutex){+.+.}-{4:4}:
[ 2529.157127] __mutex_lock+0xb2/0x11a0
[ 2529.157304] mutex_lock_nested+0x1f/0x30
[ 2529.157492] amdgpu_userq_vm_validate_and_restore_queue+0x710/0x9b0 [amdgpu]
[ 2529.158098] amdgpu_userq_restore_worker+0x39/0x290 [amdgpu]
[ 2529.158646] process_one_work+0x23e/0x6f
-> #0 (reservation_ww_class_mutex){+.+.}-{4:4}:
[ 2529.159832] __lock_acquire+0x14c4/0x2210
[ 2529.160021] lock_acquire+0xc6/0x310
[ 2529.160193] __ww_mutex_lock.constprop.0+0xd9/0x1a30
[ 2529.160419] ww_mutex_lock+0x40/0xb0
[ 2529.160590] amdgpu_bo_free_kernel+0x4e/0x130 [amdgpu]
[ 2529.161077] amdgpu_mes_rs64mem_fini+0x35/0x60 [amdgpu]
[ 2529.161601] mes_v11_0_suspend+0x2d/0x40 [amdgpu]
[ 2529.162102] amdgpu_ip_block_suspend+0x2b/0x70 [amdgpu]
[ 2529.162609] amdgpu_device_ip_suspend_phase2+0xa4/0x270 [amdgpu]
[ 2529.163116] amdgpu_device_pre_asic_reset+0x130/0x1f0 [amdgpu]
[ 2529.163617] amdgpu_device_asic_reset+0x55/0x530 [amdgpu]
[ 2529.164101] amdgpu_device_gpu_recover+0x1e5/0x410 [amdgpu]
[ 2529.164592] amdgpu_userq_mgr_reset_work+0x80/0xa0 [amdgpu]
[ 2529.165140] amdgpu_userq_hang_detect_work+0xbb/0x1c0 [amdgpu]
[ 2529.165693] process_one_work+0x23e/0x6f0
[ 2529.165884] worker_thread+0x1c4/0x380
[ 2529.166065] kthread+0x10c/0x150
[ 2529.166226] ret_from_fork+0x314/0x390
[ 2529.166408] ret_from_fork_asm+0x1a/0x30
[ 2529.166595]
other info that might help us debug this:
[ 2529.166917] Chain exists of:
reservation_ww_class_mutex --> &userq_mgr->userq_mutex --> &reset_domain->sem
Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Michael Chen <michael.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
- Unify amdgpu_mes_alloc/free_proc|gang_ctx_index to provide
centralized RS64mem bitmap management for both KGD and KFD.
- Retrieve the bitmap bit for userq contex index based on a
per process granularity.
Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Michael Chen <michael.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
On gfx12, when more queues are ready than there are HQD slots
(oversubscription), MES keeps queues unmapped and maps a queue to an HQD
on demand when its doorbell rings; a queue is only refetched once its
per-queue work_done is cleared.
Historically oversubscription was handled via the aggregated doorbell,
but that is a shared level-wide signal: MES cannot tell which queue rang
and never clears a queue's work_done, so it relies on the coarse
oversubscription timer to rescan. gfx12 therefore drives GFX/compute
through the per-queue unmapped-doorbell path instead (the aggregated
doorbell now only serves SDMA), which can pinpoint the ringing queue and
lets MES stay idle otherwise.
But with unmapped-doorbell mode 1 (basic) a ring only sets a coarse
level-wide ready flag and does not read the per-queue bitmap or clear the
ringing queue's work_done. A queue still marked done from a prior dispatch
is skipped and its new work is never fetched: the completion never
signals, while queue creation succeeds and no dmesg error is reported.
Switch to mode 2 (basic+): MES reads the per-queue CP_UNMAPPED_QUEUE
bitmap, identifies which queue rang, and clears its work_done so it is
rescheduled promptly. This affects every queue MES schedules on gfx12
(KFD and DRM user queues), which share the one MES instance and this
global setting.
Tested on gfx1201: concurrent multi-queue dispatch that intermittently
stalled under mode 1 now passes on both the KFD and DRM userq paths.
v2: update commit message: describe the oversubscription case, why the
aggregated doorbell is not used for GFX/compute on gfx12, and why
basic+ (not basic) is required.
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Reviewed-by: Shaoyun Liu <shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Set bits on dword 2 like GFX7-8 except load_global_uconfig
which doesn't exist on GFX6.
Emit VS_PARTIAL_FLUSH before VGT_FLUSH like GFX7-8.
For reference see old PAL which explains the bit fields in
this register and that load_global_uconfig doesn't exist on GFX6
and also see gfx_v7_ring_emit_cntxcntl() for the GFX7 code
which this commit follows.
Fixes: 2cd46ad22383 ("drm/amdgpu: add graphic pipeline implementation for si v8")
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Check for mmhub0 rather than mmhub1. Looks like a copy
paste typo.
Fixes: d0c989a0aad3 ("drm/amd/amdgpu : Use the MES INV_TLBS API for tlb invalidation on gfx12_1")
Cc: Shaoyun Liu <shaoyun.liu@amd.com>
Reviewed-by: Shaoyun Liu <shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
- Add hooks in various entry points to perform hw/sw init for DCN6 asic
- Add dependent changes needed to enable DCN6 asic
- Update the Makefiles so that DCN6 related newly added sources are compiled
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Roman Li <Roman.Li@amd.com>
Reviewed-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Allocate each ring buffer separately. A single allocation summing all
ring sizes can exceed the page allocator's MAX_ORDER limit and fail;
per-ring buffers stay small enough to satisfy. The existing allocation
style doesn't capture any ring data if the huge allocation fails.
Splitting into multiple allocations helps to capture as much data as
possible for the core dump.
A failed ring is left with a NULL buffer and skipped when formatting.
Fixes: eea85914d15b ("drm/amdgpu: save ring content before resetting the device")
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Assisted-by: Claude Code
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
The number of rings with outstanding fences can be large, requiring a
bigger allocation. Such allocations don't need to be physically
contiguous, so use kvzalloc/kvcalloc which fall back to vmalloc when
contiguous memory isn't available. This also matches the existing
kvfree used to free these allocations.
Also guard the allocation with ring_count to avoid passing 0 size to
allocation routines.
Fixes: eea85914d15b ("drm/amdgpu: save ring content before resetting the device")
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
On GFX rings, amdgpu_cs_p2_ib() passed user-supplied ib_bytes through
to ib->length_dw without a limit, while ring_emit_ib() encodes length
into packet fields. Oversized values can corrupt adjacent control bits
and destabilize command submission.
Add a per-ring IB packet size limit helper and reject command
submissions exceeding the corresponding dword limit before IB
allocation. Use the documented 20-bit limit for GFX/compute/SDMA/VPE,
and apply the MM fallback limit for other ring types.
Signed-off-by: Candice Li <candice.li@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Creating a user queue can race with a GPU reset. While recovery holds
reset_domain->sem for write, MES is unresponsive, so the ADD_QUEUE from
amdgpu_userq_map_helper() times out (-110) and an otherwise valid queue
create fails:
amdgpu: MES(0) failed to respond to msg=ADD_QUEUE
[drm:mes_userq_map [amdgpu]] *ERROR* Failed to map queue in HW, err (-110)
amdgpu: [drm] *ERROR* ... Failed to map Queue
amdgpu: [drm] *ERROR* ... Failed to create usermode queue
Take reset_domain->sem for read around the map so it runs only once MES
is back up. This mirrors amdgpu_userq_cleanup() and honors the
userq_mutex -> reset_domain->sem order; the reset path never takes
userq_mutex, so there is no deadlock.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
mes_userq_reset() unmaps the queue via the low-level mes_userq_unmap()
(REMOVE_QUEUE) but does not update queue->state, so the queue still looks
MAPPED. The destroy path then issues a second, redundant REMOVE_QUEUE for
the already-removed queue; for gfx that unmap waits on an EOP that never
arrives, times out (-110) and escalates to a full GPU reset.
Mark the queue UNMAPPED on a successful reset-path unmap so destroy skips
the redundant REMOVE_QUEUE.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
If a priv/bad-op fault does not match a kernel queue slot, it belongs to a
MES-scheduled user queue. Extend the shared amdgpu_gfx_handle_priv_fault()
helper introduced by commit d8ab7636160e ("drm/amd/amdgpu: remove
duplicated code in gfx_v11 and gfx_v12") to recover it: gate on
adev->gfx.disable_uq, reset a compute user queue directly from its
doorbell, and for a gfx user queue (whose IV carries no doorbell) record
the HW slot and schedule the per-IP recovery worker.
v2:
- gate on adev->gfx.disable_uq instead of !adev->enable_mes (Alex)
- document why both the doorbell (compute) and HW-slot (gfx) reset
paths are needed (Alex)
v3:
- rebase amd-staging-drm-next. adapt to the
commit 9243cf4777fc ("drm/amd/amdgpu: remove duplicated code in gfx_v11 and gfx_v12");
no functional change
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Suggested-by: Mario Sopena-Novales <Mario.Novales@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Mirror the gfx11 priv-fault user-queue recovery worker for GFX12, reading
the doorbell back from the HQD via soc24_grbm_select.
The shared amdgpu_gfx_handle_priv_fault() helper schedules this worker for
a gfx user-queue fault; wiring the helper up is done in a later patch.
v2:
- gate on adev->gfx.disable_uq instead of !adev->enable_mes (Alex)
- document why both the doorbell (compute) and HW-slot (gfx) reset
paths are needed (Alex)
v3:
- rebase amd-staging-drm-next. adapt to the commit 9243cf4777fc ("drm/amd/amdgpu: remove duplicated code in gfx_v11 and gfx_v12"); no functional change
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Suggested-by: Mario Sopena-Novales <Mario.Novales@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
A gfx user-queue priv/bad-op fault is raised by the ME and carries only
the HW slot, not the faulting queue's doorbell. Add a per-IP worker that
drains adev->gfx.userq_priv_fault_slots, reads the doorbell back from each
HQD via soc21_grbm_select (regCP_RB_DOORBELL_CONTROL), looks up the user
queue and kicks its per-queue reset.
The shared amdgpu_gfx_handle_priv_fault() helper schedules this worker for
a gfx user-queue fault; wiring the helper up is done in a later patch.
v2:
- gate on adev->gfx.disable_uq instead of !adev->enable_mes (Alex)
- document why both the doorbell (compute) and HW-slot (gfx) reset
paths are needed (Alex)
v3:
- rebase amd-staging-drm-next. adapt to the commit 9243cf4777fc ("drm/amd/amdgpu: remove duplicated code in gfx_v11 and gfx_v12"); no functional change
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Suggested-by: Mario Sopena-Novales <Mario.Novales@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
A gfx priv/bad-op fault IV carries only the HW slot (ring_id), not the
faulting user queue's doorbell. Add userq_priv_fault_slots (an atomic
bitmap of faulted slots, so concurrent faults are not dropped) and
userq_priv_fault_work to struct amdgpu_gfx; a worker drains the bitmap
and reads the doorbell back from each HQD to locate and reset the queue.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Move fs_reclaim_acquire() to before all lock acquisitions to eliminate
false positive circular locking dependency warning.
This is a 7.2-cycle regression fix suitable for stable backport.
v3: Address Mikhail Gavrilov technical review:
- Clarify that fs_reclaim_acquire/release pair only REGISTERS the
fs_reclaim lock class, does NOT create a static edge when called
with no locks held
- Explain that the actual fs_reclaim -> notifier_lock edge is
established at runtime during memory reclaim -> MMU notifier path
- Add Cc: Arunpravin PaneerSelvam
v2: Address Mikhail Gavrilov review feedback:
- Fix author name: Michael -> Mikhail Gavrilov in all trailers
- Add Fixes: tag to link regression to original commit
- Add Tested-by: Mikhail Gavrilov (tested on RX 7900 XTX)
Fixes: 1d0f5838b126 ("drm/amdgpu: Add lockdep annotations for lock ordering validation")
Reported-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Analyzed-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Test-case-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Tested-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Tested-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Arunpravin PaneerSelvam <Arunpravin.PaneerSelvam@amd.com>
Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Acked-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Needed to properly lock the interface before using it.
Cc: Sonny Jiang <sonny.jiang@amd.com>
Reviewed-by: Sonny Jiang <sonny.jiang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
amdgpu_userq_input_va_validate() converts expected_size to page count
with a plain right shift. For expected_size smaller than one GPU page,
the computed size becomes 0 and the range check is effectively bypassed.
This allows sub-page userq buffers (e.g. EOP/CSA) to pass validation
as long as the start VA is mapped, without verifying the full span.
Fix it by rejecting zero expected_size, checking overflow when
computing end address, and deriving page span from [start_addr,
end_addr] inclusive.
Signed-off-by: Candice Li <candice.li@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
If a valid signature is seen at the default offset, use the default
size/offset for discovery.
Fixes: 01bdc7e219c4 ("drm/amdgpu: New interface to get IP discovery binary v3")
Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/5447
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Remove the obsolete gmc ras helpers including
amdgpu_gmc_ras_late_init and amdgpu_gmc_ras_fini
and their declarations, and call sites.
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Ce Sun <cesun102@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
TA_CNTL2.TRUNCATE_COORD_MODE selects whether texture coordinate
truncation is D3D9/GL/Vulkan conformant. gfx11 reads it and reports it to
userspace via AMDGPU_IDS_FLAGS_CONFORMANT_TRUNC_COORD, but gfx12 never
read it, so the flag was always reported as 0 and userspace fell back to
the non-conformant path.
Read it in gfx_v12_0_constants_init() like gfx11 does.
Fixes: 52cb80c12e8a ("drm/amdgpu: Add gfx v12_0 ip block support (v6)")
Signed-off-by: Qiang Yu <Qiang.Yu@amd.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Like jpeg_v5_0_0, in DPG mode the ring reset path only clears the
JPEG_PG_MODE bit and never resets a hung JRBC, so the post-reset ring test
times out and the driver falls back to a full MODE1 reset.
Temporarily force the static power-gating path during the reset so the
stop/start sequence power-cycles the JPEG block (JMI soft reset + power
off/on), matching the jpeg_v4_0 reset.
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Like jpeg_v5_0_0, in DPG mode the ring reset path only clears the
JPEG_PG_MODE bit and never resets a hung JRBC, so the post-reset ring test
times out and the driver falls back to a full MODE1 reset.
Temporarily force the static power-gating path during the reset so the
stop/start sequence power-cycles the JPEG block (JMI soft reset + power
off/on), matching the jpeg_v4_0 reset.
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
In DPG mode jpeg_v5_0_0_ring_reset() takes the DPG stop path, which only
clears the JPEG_PG_MODE bit and never resets the JRBC. A hung ring is not
recovered: the post-reset ring test times out and the driver falls back to
a full MODE1 reset.
Temporarily force the static power-gating path during the reset so the
stop/start sequence power-cycles the JPEG block (JMI soft reset + power
off/on), matching the jpeg_v4_0 reset which has no DPG path.
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
The functions gfx_v11_0_handle_priv_fault and
gfx_v12_0_handle_priv_fault share the same logic for searching and
triggering a scheduler fault on a ring. This patch moves the shared
ring-searching logic to a common function, amdgpu_gfx_handle_priv_fault,
in amdgpu_gfx.c. The hardware-specific decoding of ring IDs remains in
the version-specific files to maintain proper architectural separation.
Signed-off-by: Ulisses Paixao <ulissespaixao@usp.br>
Co-developed-by: Felipe Sousa <felipesousa@usp.br>
Signed-off-by: Felipe Sousa <felipesousa@usp.br>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Enable IP block soft reset as a GPU recovery method for GFX7
graphics and compute rings.
This improves current user experience on all GFX7 chips:
* On Kaveri and Kabini there is currently no working
GPU recovery method so those chips currently require
the user to manually reset the computer when there
was a hang.
* On Hawaii and Bonaire, the current GPU recovery method
always clears the contents of VRAM, which means that
a buggy (hanging) app can crash the whole graphical
session, which is less than ideal.
Using GFX IP block soft reset means that we can now
have a working recovery on GFX7 APUs and we can also
move on from GFX hangs on dGPUs without crashing the
whole system.
Tested with the "hard_reset_cp_wait" test case from the
Hang Test Suite created by Natalie Vock and Konstantin Seurer.
This Vulkan testcase waits for an event that never occurs,
effectively a WAIT_REG_MEM packet that intentionally hangs.
IP block soft reset can resolve that hang and allow
the rest of the system to move on and keep functioning
without needing a full ASIC reset.
Tested on the following chips:
Bonaire (Radeon HD 7790)
Hawaii (Radeon R9 390X)
Kaveri (A10-7850K)
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Use basically the same implementation as GFX8,
except for the GFX7 specific MQD functions.
Reset every block using the GRBM, then proceed
to reset the GRBM and SEM blocks using the SRBM.
Remove the redundant gfx_v7_0_update_cg() function.
The soft reset now calls the clock and powergating
functions of the IP block instead.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
COND_EXEC tells the CP to discard the dwords following it
when its condition is zero (false).
This is useful for GPU recovery because it can help reduce
collateral damage during GFX IP block soft reset, meaning
that it reduces the likelyhood that we fail some jobs which
are not guilty of the hang as the IP block soft reset
mechanism clears the condition before doing the reset.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Clear the WPTR and RPTR at ring initialization.
Additionally clear the ring contents during reset.
After a reset, the ring contents could be "dirty"
and contain packets emitted before the reset.
and thus need to be cleared to prevent the command
processor from executing packets left over in the
ring from before the reset.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
This packet is interpreted by the CE (constant engine).
The reason why this packet is emitted is basically to
make sure the CE can't start executing packets from the
next job submission until the current one is finished.
(Note that CE is not utilized by any maintained userspace
driver and is discontinued in new GPUs. It is now also
deprecated in the kernel.)
Implement the emit_switch_buffer() function instead of emitting
them duing emit_ib, emit_pipeline_sync and emit_vm_flush.
It isn't necessary to emit these in both emit_pipeline_sync()
and emit_vm_flush() because amdgpu_vm_flush() already calls
these when calling either of those functions.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Return an error code instead of silently failing.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
The gfx_v7_0_cp_compute_resume() function should only return
success when all compute rings are actually functional.
This will be especially important for soft reset which needs
this to know whether the reset was successful.
Note that the gfx_v8_0_cp_test_all_rings() function already
does this on GFX8, here we just follow the same idea.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Call amdgpu_gfx_mqd_sw_init()/_fini() on GFX7 to initialize and
finalize MQD BOs, just like GFX8 and newer; instead of doing
an ad-hoc BO allocation. Introduce the possibility of backing
up the MQD instead of trying to reinitialize every time.
This solves an issue with GFX IP block soft reset where
all compute rings would hang after the reset.
Rename gfx_v7_0_mqd_deactivate() to gfx_v7_0_deactivate_hqd()
to more closely reflect what it does and for consistency
with the GFX8 code.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
GFX7 supports KIQ, but amdgpu doesn't use it.
Change amdgpu_gfx_mqd_sw_init() to only allocate the MQD BO
for the KIQ on GFX8 and newer (that is, TOPAZ and newer).
This makes amdgpu_gfx_mqd_sw_init() usable on GFX7 without
any further changes to its functionality.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
SVM BOs are now migrated back to system memory synchronously from the TTM
eviction path (svm_range_evict_svm_bo), so the per-svm_bo eviction fence
is no longer used.
Remove the eviction fence from svm_range_bo, drop the
amdgpu_amdkfd_fence->svm_bo back pointer and the
amdgpu_amdkfd_evict_svm_bo() helper, and stop special-casing svm_bo
fences in the KFD fence enable_signaling and check_mm paths. Embed struct
amdgpu_bo directly in svm_range_bo with a dedicated svm_range_bo_destroy()
callback, and keep the owning mm via mmgrab()/mmdrop() instead of through
the fence.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
On APUs, the GTT pool is backed by system RAM, but its size is not bound
to the non-carveout memory that actually backs it. A user can end up
with GTT + VRAM exceeding total physical memory through the following
sequence:
- Have a large non-carveout memory space (~128GB) and accordingly set a
large GTT (~100GB) via the ttm module parameter.
- Lower the non-carveout memory space in BIOS by increasing the UMA
Frame Buffer Size (VRAM) to 64GB.
- The previously set GTT value (~100GB) persists, even though the new
non-carveout space (64GB) can no longer back it.
This leads to a case where kernel reports GTT (100GB) + VRAM (64GB)
despite the sum being greater than total physical memory (128GB).
Cap the GTT size to totalram_pages() on APUs. totalram_pages() already
excludes the VRAM carveout, so the resulting GTT can never exceed the
system RAM that actually backs it.
Signed-off-by: Harkirat Gill <harkirat.gill@amd.com>
Reviewed-by: David Francis <David.Francis@amd.com>
Assisted-by: Claude:claude-opus-4
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 5dafdd649280c7dc6c22c8f877da3f54fcc441e1)
Cc: stable@vger.kernel.org
|
|
GPU average and input power backends report a mix of whole watts,
milliwatts, Q24.8 watts and decimal-packed fractions. Q24.8 is inherited
from the legacy PowerPlay sensor format. Milliwatts are a more natural unit
for the hwmon and pm_info consumers in amdgpu_pm.c. A common decoder cannot
distinguish these formats, and converting native milliwatts through Q24.8
also loses precision.
Use milliwatts as the internal unit across all PPT and PowerPlay backends.
Decode Q24.8 only at the legacy smu7 input boundary and encode it only for
the raw amdgpu_sensors debugfs interface. This gives hwmon, pm_info and the
sensor ioctl one unambiguous unit while preserving the format used by UMR.
Fixes: 5b79d0482f3c ("drm/amd/pp: Remove struct pp_gpu_power")
Fixes: 01992b121fb6 ("drm/amd/pm: fix amdgpu_pm_info power display units")
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Reported-by: Lars Nieradzik <l.nieradzik@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 757ba0790bafec47a507e9662bf380f2e027d420)
Cc: stable@vger.kernel.org
|
