In resource_parse_asic_id, the check for GC_11_0_4 was unbounded, which
caused it to override the detection of DCN42B.
Signed-off-by: Matthew Stewart <Matthew.Stewart2@amd.com>
Reviewed-by: Roman Li <Roman.Li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Replace BUG()/BUG_ON() with error logs and safe returns in several
places where they can be triggered by invalid userspace input,
preventing DoS via kernel panic.
Signed-off-by: Ce Sun <cesun102@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
In smu_v14_0_0_set_soft_freq_limited_range(), the gfxclk floor is
programmed via SetHardMinGfxClk together with SetSoftMaxGfxClk. Under
power_dpm_force_performance_level=high this pins HardMin to peak gfxclk.
In PMFW arbitration HardMin has higher priority than SoftMax, so the
firmware thermal/PPT throttler cannot clamp gfxclk via SoftMax once
HardMin is set to peak. Replace SetHardMinGfxClk with SetSoftMinGfxclk
so the driver still requests peak performance but the firmware
throttler retains the ability to clamp gfxclk under thermal/PPT
pressure. SoftMax handling is unchanged and no other clock domains
are affected.
Signed-off-by: Priya Hosur <Priya.Hosur@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When mapping VRAM pages into the GART page table,
amdgpu_gart_map_vram_range() assumes that the system page size is the
same as the GPU page size.
On systems with non-4K page sizes, multiple GPU pages can exist within
a single CPU page. As a result, the mappings are created incorrectly
because fewer page table entries are programmed than required.
Fix this by programming the mappings correctly for non-4K page size
systems.
Fixes: 237d623ae6 ("drm/amdgpu/gart: Add helper to bind VRAM pages (v2)")
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Donet Tom <donettom@linux.ibm.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
cp_ecc_error_irq is acquired in amdgpu_gfx_ras_late_init() but
released in gfx_v9_0_hw_fini(), so the put site has to query
amdgpu_irq_enabled() because the get is skipped on SR-IOV VF.
ras_late_init / ras_fini have no suspend counterpart, so move the
put to amdgpu_gfx_ras_suspend() / amdgpu_gfx_ras_fini() and add a
matching ras_suspend callback that is invoked from
amdgpu_ras_suspend() before disable_all_features(). The get and
put now sit in the same place and check the same condition (not
VF, funcs registered), no refcount querying needed.
An active flag gates ras_fini so the
suspend-then-unload-without-resume path falls into
amdgpu_ras_block_late_fini_default() instead of double-releasing
what ras_suspend already cleaned up.
Drop the cp_ecc_error_irq put from gfx_v9_0_hw_fini(). gfx_v8_0
manages cp_ecc_error_irq locally and is unaffected; no other GFX
generation has this IRQ.
Signed-off-by: Yunxiang Li <Yunxiang.Li@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The mca ras sub-blocks (mp0, mp1, mpio) all share the
AMDGPU_RAS_BLOCK__MCA block id and are distinguished only by
sub_block_index. The ras manager object for an mca block is selected
with:
con->objs[AMDGPU_RAS_BLOCK__LAST + head->sub_block_index]
Since the rework in commit 7f544c5488 ("drm/amdgpu: Rework mca ras
sw_init") moved the ras_comm setup into amdgpu_mca_mp*_ras_sw_init() but
left sub_block_index unset, mp0/mp1/mpio all default to index 0 and
collide on the same object slot. mp0 grabs the slot and creates its
sysfs node first; mp1 (and mpio) then find the slot already in use, so
amdgpu_ras_block_late_init() -> amdgpu_ras_sysfs_create() returns
-EINVAL:
amdgpu: mca.mp1 failed to execute ras_block_late_init_default! ret:-22
amdgpu: amdgpu_ras_late_init failed -22
amdgpu: amdgpu_device_ip_late_init failed
amdgpu: Fatal error during GPU init
The error is currently masked because amdgpu_ras_late_init() does not
check the return value of amdgpu_ras_block_late_init_default(), but it
already leaves mp1/mpio without their sysfs nodes and becomes a fatal
init failure as soon as that return value is honored.
Restore the per-sub-block sub_block_index assignment so each mca
sub-block maps to its own object slot.
Fixes: 7f544c5488 ("drm/amdgpu: Rework mca ras sw_init")
Signed-off-by: Yunxiang Li <Yunxiang.Li@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
In case when queue_create fails and mqd has already been
allocated and hence wptr_obj is not cleaned up.
So moving that cleanup part to mqd_destroy so it takes
care of all the cases of clean up and during tear down of
the queue.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Legacy CPER ring readers can issue one debugfs read with a buffer larger
than the UNIRAS RAS command payload limit. Passing that full size to
GET_CPER_RECORD makes the command reject the request, so userspace may
only see the ring prefix and treat the CPER stream as empty.
Commit 3c88fb7aa5 ("drm/amd/ras: bound CPER record fetch buffer
size") intentionally bounds CPER record fetch allocation by the command
buffer size. Keep the debugfs ABI as a single contiguous ring read by
splitting the internal GET_CPER_RECORD requests into
RAS_CMD_MAX_CPER_BUF_SZ chunks.
Accumulate the copied payload and update the legacy header write pointers
from the total bytes returned to userspace.
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>
Use find_next_zero_bit() to locate the next free seq slot bit
instead of the current walk, for more efficient bitmap scanning.
Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
_PR3 detection was changed in commit 134b8c5d86 ("drm/amd: Fix
detection of _PR3 on the PCIe root port") to look at the root port
of the topology containing the GPU. This however was too far because
it ignored whether or not all the intermediary bridges could power
off the device. The original design in commit b10c1c5b3a ("drm/amdgpu:
add check for ACPI power resources") was too narrow because it matched
the switches internal to the GPU.
Use the goldilocks approach and look for the first bridge outside of the
GPU and check for _PR3 on that device.
Fixes: 134b8c5d86 ("drm/amd: Fix detection of _PR3 on the PCIe root port")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The VF RAS error handler used fixed-size bps[] / bps_bo[] arrays (512
slots). When the PF2VF bad-page block listed more entries than fit,
amdgpu_virt_ras_add_bps() could memcpy() past the end of those arrays.
Replace the fixed backing store with a dynamically grown table:
- Add capacity to track allocated slots separately from count.
- Start at 512 slots and realloc bps / bps_bo together when full.
- Refuse growth beyond maximum EEPROM record limit (AMDGPU_VIRT_RAS_BAD_PAGE_TABLE_MAX_CAPACITY).
- Return failure from amdgpu_virt_ras_add_bps() and stop processing
the PF2VF block if allocation fails or the cap is reached.
Signed-off-by: Chenglei Xie <Chenglei.Xie@amd.com>
Reviewed-by: YiPeng Chai <YiPeng.Chai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Mesa userqueues free does not wait for the free to complete and go ahead
in unmapping the vital bos while kernel is still in queue free and
corresponding cleanup.
So ideally we don't need the logging for that and hence remove the warn
message as this is expected behaviour and functionally, we are making
sure to wait for the required fences before unmap.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The v11 MQD manager incorrectly assigned the CP-compute variants of
checkpoint_mqd/restore_mqd for KFD_MQD_TYPE_SDMA queues. These functions
use sizeof(struct v11_compute_mqd) (2048 bytes) instead of sizeof(struct
v11_sdma_mqd) (512 bytes), causing a 1536-byte overflow.
During CRIU checkpoint of an SDMA queue on Navi3x:
- checkpoint_mqd() reads 2048 bytes from a 512-byte SDMA MQD buffer,
leaking 1536 bytes of adjacent GTT memory to userspace
During CRIU restore:
- restore_mqd() writes 2048 bytes into a 512-byte SDMA MQD buffer,
corrupting 1536 bytes of adjacent GTT memory (often the ring buffer
or neighboring MQDs)
This is a copy-paste regression unique to v11. All other ASIC backends
(cik, vi, v9, v10, v12) correctly use the SDMA-specific variants.
Add checkpoint_mqd_sdma() and restore_mqd_sdma() functions that properly
handle the smaller v11_sdma_mqd structure, matching the pattern used in
other MQD managers.
Fixes: cc009e613d ("drm/amdkfd: Add KFD support for soc21 v3")
Assisted-by: Claude:Sonnet 4-5
Signed-off-by: Andrew Martin <andrew.martin@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When usr_queue_id_array is NULL and num_queues is non-zero,
get_queue_ids() returns NULL. The callers check only IS_ERR() on the
return value; since IS_ERR(NULL) == false the check passes, and
suspend_queues() calls q_array_invalidate() which immediately
dereferences NULL while iterating num_queues times.
Userspace can trigger this via kfd_ioctl_set_debug_trap() by supplying
num_queues > 0 with a zero queue_array_ptr, causing a kernel panic.
A NULL usr_queue_id_array with num_queues == 0 is a legitimate no-op
(q_array_invalidate never executes, and resume_queues already guards
all queue_ids dereferences behind a NULL check). Return ERR_PTR(-EINVAL)
only when num_queues is non-zero and the pointer is absent; both callers
already propagate IS_ERR() returns correctly to userspace.
Fixes: a70a93fa56 ("drm/amdkfd: add debug suspend and resume process queues operation")
Signed-off-by: Muhammad Bilal <meatuni001@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
force_frl_rate, select_ffe and limit_ffe in dc_debug_options carry
non-negative configuration values: an FRL link-rate enum (0..0xF), an
FFE level selector and an FFE level limit. They are only ever compared
against 0/0xF, assigned, or cast to uint8_t before being written to
hardware. No call site relies on signed semantics.
Make the types unsigned int to match how the values are actually used
and to silence MISRA-style signedness warnings on internal builds.
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Problem:
While developing the amd_close_race IGT test (which intentionally triggers
execute permission faults by removing VM_PAGE_EXECUTABLE from GPU page table
entries), we discovered that on Navi10 (GFX 10.1.x) these faults produce
zero diagnostic output. The GPU simply hangs silently for ~10s until the
scheduler timeout fires. There is no way to distinguish an execute
permission fault from any other type of GPU hang.
Root cause:
GFX 10.1.x defaults to noretry=0, which sets
RETRY_PERMISSION_OR_INVALID_PAGE_FAULT=1 in the GFXHUB UTCL2 registers
(gfxhub_v2_0.c line 313). With this bit set, permission faults (valid PTE,
wrong R/W/X bits) are handled entirely within the UTCL1/UTCL2 hardware
loop: UTCL2 returns an XNACK to UTCL1, and UTCL1 re-requests the
translation indefinitely, expecting software to eventually fix the
permission bits (as happens in SVM/HMM recovery). No interrupt of any kind
reaches the IH ring.
This is different from invalid-page faults (V=0) which DO generate a retry
fault interrupt that the driver can escalate to a no-retry fault. Permission
faults with valid PTEs loop silently forever in hardware.
GFX 10.3+ already defaults to noretry=1, which makes permission faults
generate immediate L2 protection fault interrupts. GFX 10.1.x was
inadvertently left out of this default.
Fix:
Change the noretry=1 threshold from IP_VERSION(10, 3, 0) to
IP_VERSION(10, 1, 0) in amdgpu_gmc_noretry_set(). This is a one-line
change that aligns GFX 10.1.x behavior with GFX 10.3+ and all newer
generations.
With noretry=1, the existing non-retry fault handler
(gmc_v10_0_process_interrupt) already decodes and prints the full
GCVM_L2_PROTECTION_FAULT_STATUS register including PERMISSION_FAULTS,
faulting address, VMID, PASID, and process name. No additional logging
code is needed — the fix is purely routing permission faults to the
existing, fully-capable non-retry interrupt handler.
v2: Dropped GFX10-specific logging from gmc_v10_0.c and
kfd_int_process_v10.c (Felix Kuehling). v1 added logging in the retry
fault handler, but with noretry=1 permission faults take the non-retry
path — the v1 retry handler code was dead and would never execute.
Tested on Navi10 (GFX 10.1.10):
- Execute permission faults now produce immediate, clear output:
[gfxhub] page fault (src_id:0 ring:64 vmid:4 pasid:592)
Process amd_close_race pid 13380 thread amd_close_race pid 13384
in page at address 0x40001000 from client 0x1b (UTCL2)
GCVM_L2_PROTECTION_FAULT_STATUS:0x00700881
PERMISSION_FAULTS: 0x8
- No regressions with properly-mapped GPU workloads
Cc: Christian Koenig <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When the fault stop mode isn't AMDGPU_VM_FAULT_STOP_ALWAYS,
these bits should be programmed to 0.
Program CRASH_ON_NO_RETRY_FAULT and CRASH_ON_RETRY_FAULT
always, to make sure to clear the bits when we don't want
to crash.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
For PTE creation use asic specific physical page base address mask
v2: Change variable name from pa_mask to pte_addr_mask
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
SMU messages may use fewer arguments than the available argument registers,
the previous code only wrote used registers and left the rest unchanged,
so stale values from a prior message could persist.
Write all argument registers for each message and zero the unused tail
to keep command arguments deterministic and avoid unintended carry-over.
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
smu_v13_0_0_get_power_limit() and smu_v13_0_7_get_power_limit() mix
runtime power_limit with PP table limits when reporting default/min/max.
When current power limit query succeeds, default_power_limit was set to the
runtime value instead of the PP table default, and min/max could be derived
from inconsistent bases (MsgLimits/runtime), leading to incorrect cap info.
Use SocketPowerLimitAc/Dc as the PP default base (pp_limit), keep
current_power_limit as runtime value, and derive min/max from pp_limit with
OD percentages.
Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/5227
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
On SMU v13.0.10, sending PrepareMp1ForUnload with the default
parameter may leave the device in an inaccessible state. This can
affect runtime power management and partial PnP flows.
e.g: kexec, driver unload, boco/d3cold.
Pass the required workaround parameter 0x55, when preparing MP1 for
unload on SMU v13.0.10, keep the existing behavior for other SMU
versions.
Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/5133
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Use kcalloc() so multiplication overflow is detected
and allocation fails safely for phm table copy helpers.
Signed-off-by: Candice Li <candice.li@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Use strncpy_from_user() instead of copy_from_user() before sscanf() in
the securedisplay_test debugfs write handler so a full-length write
cannot leave the stack buffer without a terminator.
Signed-off-by: Candice Li <candice.li@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Corrupt EEPROM data can set tbl_size below the table header size.
Guard the RAS_NUM_RECS macros against undersized tbl_size and reset
the table during init when tbl_size is below the minimum for the table
version instead of trusting the header.
Signed-off-by: Candice Li <candice.li@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Corrupt EEPROM data can set tbl_size below the table header size.
Guard the RAS_NUM_RECS macros against undersized tbl_size and reset
the table during init when tbl_size is below the minimum for the table
version instead of trusting the header.
Signed-off-by: Candice Li <candice.li@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The powerplay path allocates hardcode_pp_table once with kmemdup(...,
soft_pp_table_size). memcpy(..., size) used the sysfs store count (up to
PAGE_SIZE) with no upper bound, causing heap overflow. Reject
writes where size exceeds soft_pp_table_size.
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
In case of concurrent calling to the bin file writing, use the mutex
to avoid allocating the temporary buffer more than once.
Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Clamp the buffer postion to write by setting the bin attribute
to the maximum buffer size so that VFS layer will block the
out-of-bounds accessing.
Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Discovery: Fuzzing for secure supply chain requirements
Tool: amd_fuzzing_sysfs (IGT test)
The thermal_throttling_logging sysfs store function accepts negative
values like -1 and -9999999, which are nonsensical for a logging interval.
Current behavior:
- Values <= 0 disable logging (intended for 0 only)
- Values 1-3600 enable logging with interval in seconds
- Negative values are accepted and treated as disable
Issue:
Large negative values like -9999999 make no semantic sense and could
indicate input validation bypass attempts. While they functionally
disable logging (same as 0), accepting arbitrary negative values
suggests inadequate input validation.
Fix:
Add explicit check to reject values < 0 before processing.
Only accept:
- 0: disable thermal throttling logging
- 1-3600: enable with interval in seconds (existing validation)
This improves input validation and makes the interface more robust.
Test Results Before Fix:
thermal_throttling_logging: 6 failures
- Accepted: 0, -1, -9999999, -2147483648, empty string, 0777
Test Results After Fix:
thermal_throttling_logging: 3 failures
- Rejected: -1, -9999999, -2147483648 (now return -EINVAL)
- Remaining: empty string (VFS behavior), 0 (valid), 0777 (octal)
Tested: amd_fuzzing_sysfs IGT test
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Jesse Zhang <jesse.zhang@amd.com>
Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Discovery: Fuzzing for secure supply chain requirements
Tool: amd_fuzzing_sysfs (IGT test)
The AMDGPU power management sysfs store functions accept whitespace-only
strings when they should reject them with -EINVAL. This was discovered via
systematic fuzzing of sysfs interfaces crossing the user/kernel trust
boundary.
Affected functions:
- amdgpu_set_power_dpm_force_performance_level (power_dpm_force_performance_level)
- amdgpu_set_power_dpm_state (power_dpm_state)
- amdgpu_set_pp_power_profile_mode (pp_power_profile_mode)
- amdgpu_read_mask (used by pp_dpm_sclk/mclk/fclk/socclk/pcie)
- amdgpu_set_pp_features (pp_features)
Impact:
- Whitespace-only writes (e.g., "\n", " ") can cause unexpected behavior
- Better input validation at user/kernel trust boundary
- Defense-in-depth improvement
Root Cause:
The sysfs_streq() function matches whitespace-only strings against empty
string, allowing invalid input to be processed.
Fix:
Add explicit validation at the start of each affected store function:
if (count == 0 || sysfs_streq(buf, ""))
return -EINVAL;
This rejects whitespace-only inputs before they are processed. Note that
write() calls with count=0 (truly empty strings) are handled by the VFS
layer before reaching the sysfs .store() callback - the VFS returns 0
(success) without calling the kernel function. This is POSIX-compliant
behavior and cannot be changed at the kernel driver level.
What This Patch Fixes:
- Whitespace-only strings: "\n", " ", " ", etc. are now rejected
- Defense-in-depth: Explicit validation at trust boundary
- Code clarity: Intent to reject invalid input is explicit
What This Patch Cannot Fix:
- write(fd, "", 0) returning success - this is VFS layer behavior
- Fuzzer tests for empty strings (count=0) will still report "accepted"
because the VFS handles this before the kernel callback
Test Results After Fix:
- Whitespace strings ("\n", " ") now properly rejected
- Empty string tests (count=0) still show as "accepted" due to VFS behavior
- Overall improvement in input validation robustness
- No impact on valid inputs
This is a defense-in-depth improvement that hardens input validation
even though VFS layer behavior prevents catching all edge cases.
Tested: amd_fuzzing_sysfs IGT test
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Jesse Zhang <jesse.zhang@amd.com>
Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The ring content dump in amdgpu_coredump() uses two separate loops over
adev->rings[]: the first counts rings with unsignalled fences to size
the allocation, and the second copies ring data into the allocated
buffers.
Both loops use the same condition to skip rings:
atomic_read(&ring->fence_drv.last_seq) == ring->fence_drv.sync_seq
Because last_seq is an atomic that is updated concurrently by the fence
signalling path, additional rings may appear unsignalled in the second
loop that were signalled during the first. When this happens, idx
exceeds the allocated ring_count and the store to coredump->rings[idx]
writes past the end of the kcalloc-ed buffer.
This was found during IGT stressful test amd_queue_reset which
triggers random GPU resets. The OVERSIZE subtest
(CMD_STREAM_EXEC_INVALID_PACKET_LENGTH_OVERSIZE on GFX ring) provokes
a ring timeout and subsequent coredump, which hits the race between
the counting and copying loops. The failure is non-deterministic and
depends on fence signalling timing during the reset.
KASAN log:
BUG: KASAN: slab-out-of-bounds in amdgpu_coredump+0x1274/0x12f0 [amdgpu]
Write of size 4 at addr ffff888106154258 by task kworker/u128:5/23625
CPU: 16 UID: 0 PID: 23625 Comm: kworker/u128:5 Not tainted 6.19.0+ #35
Workqueue: amdgpu-reset-dev drm_sched_job_timedout [gpu_sched]
Call Trace:
<TASK>
dump_stack_lvl+0xa5/0x110
print_report+0xd1/0x660
kasan_report+0xf3/0x130
__asan_report_store4_noabort+0x17/0x30
amdgpu_coredump+0x1274/0x12f0 [amdgpu]
amdgpu_job_timedout+0xef0/0x16c0 [amdgpu]
drm_sched_job_timedout+0x194/0x5c0 [gpu_sched]
process_one_work+0x84b/0x1990
worker_thread+0x6b8/0x11b0
</TASK>
Allocated by task 23625:
kasan_save_stack+0x39/0x70
__kasan_kmalloc+0xc3/0xd0
__kmalloc_noprof+0x2ec/0x910
amdgpu_coredump+0x5c5/0x12f0 [amdgpu]
amdgpu_job_timedout+0xef0/0x16c0 [amdgpu]
The buggy address belongs to the object at ffff888106154200
which belongs to the cache kmalloc-rnd-09-96 of size 96
The buggy address is located 16 bytes to the right of
allocated 72-byte region [ffff888106154200, ffff888106154248)
72 bytes = 3 * sizeof(struct amdgpu_coredump_ring), so ring_count was 3
but idx reached 3+, writing ring_index (at struct offset 16) 16 bytes
past the allocation.
Fix by adding an idx < ring_count guard to the copy loop so it cannot
exceed the allocated count even when the fence state changes between
the two passes.
Fixes: eea85914d1 (drm/amdgpu: save ring content before resetting the device)
Cc: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Replace the open-coded TLV walk with fru_pia_advance()
and fru_pia_copy_field() helpers that bound every read
by the actual EEPROM data length, preventing out-of-bounds
reads on truncated or malformed FRU data.
Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The UNIRAS CPER debugfs path returned a zeroed 12-byte prefix and used
file offset directly as the CPER record index. Legacy CPER ring readers
expect the prefix to contain three 32-bit ring pointers followed
immediately by CPER payload data.
Build the same header shape for UNIRAS reads by reporting a zero read
pointer and matching write pointers for the returned payload size. Keep
an internal record cursor behind the debugfs offset so follow-up reads
continue from the correct CPER record while first reads still expose the
legacy prefix.
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>
amdgpu_ras_inject_error() currently prints an extra "ras inject block %u
failed" message, remove the redundant log.
Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: YiPeng Chai <YiPeng.Chai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The response header lives in PF-controlled shared memory. Copy it
into a local struct once, then read cmd_res and output_size from the
snapshot so the PF cannot flip cmd_res or grow output_size between
checks.
Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
