diff options
| author | Haoran Jiang <[email protected]> | 2025-08-05 11:00:22 +0000 |
|---|---|---|
| committer | Huacai Chen <[email protected]> | 2025-08-05 11:00:22 +0000 |
| commit | cd39d9e6b7e4c58fa77783e7aedf7ada51d02ea3 (patch) | |
| tree | 2071534f4bc1a5fb63b985632586508b7b4eb56c /drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c | |
| parent | LoongArch: BPF: Add struct ops support for trampoline (diff) | |
| download | kernel-cd39d9e6b7e4c58fa77783e7aedf7ada51d02ea3.tar.gz kernel-cd39d9e6b7e4c58fa77783e7aedf7ada51d02ea3.zip | |
LoongArch: BPF: Fix jump offset calculation in tailcall
The extra pass of bpf_int_jit_compile() skips JIT context initialization
which essentially skips offset calculation leaving out_offset = -1, so
the jmp_offset in emit_bpf_tail_call is calculated by
"#define jmp_offset (out_offset - (cur_offset))"
is a negative number, which is wrong. The final generated assembly are
as follow.
54: bgeu $a2, $t1, -8 # 0x0000004c
58: addi.d $a6, $s5, -1
5c: bltz $a6, -16 # 0x0000004c
60: alsl.d $t2, $a2, $a1, 0x3
64: ld.d $t2, $t2, 264
68: beq $t2, $zero, -28 # 0x0000004c
Before apply this patch, the follow test case will reveal soft lock issues.
cd tools/testing/selftests/bpf/
./test_progs --allow=tailcalls/tailcall_bpf2bpf_1
dmesg:
watchdog: BUG: soft lockup - CPU#2 stuck for 26s! [test_progs:25056]
Cc: [email protected]
Fixes: 5dc615520c4d ("LoongArch: Add BPF JIT support")
Reviewed-by: Hengqi Chen <[email protected]>
Signed-off-by: Haoran Jiang <[email protected]>
Signed-off-by: Huacai Chen <[email protected]>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c')
0 files changed, 0 insertions, 0 deletions