LoongArch: BPF: Fix jump offset calculation in tailcall
Linux
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
|
Linux
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
|
≥ 5dc615520c4dfb358245680f1904bad61116648e · < cd39d9e6b7e4c58fa77783e7aedf7ada51d02ea3| No fix yet |
| Linux Linux |
|
|
In the Linux kernel, the following vulnerability has been resolved:
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
From the CVE record · Linux
The Linux kernel’s LoongArch BPF JIT can calculate an incorrect tail-call jump offset, generating code that causes a CPU soft lockup. The issue was reproduced with a BPF self-test; the input does not establish how an attacker could trigger it or whether authentication or user interaction is required.
Engineers running Linux kernels on LoongArch should check whether their kernel includes the fix; affected versions were not specified.