bpf, arm64: fix bug in BPF_LDX_MEMSX
Subsystems (3)
PATCH 1/1 bpf, arm64: fix bug in BPF_LDX_MEMSX
A64_LDRSW() takes three registers: Xt, Xn, Xm as arguments and it loads and sign extends the value at address Xn + Xm into register Xt.
Currently, the offset is being directly used in place of the tmp register which has the offset already loaded by the last emitted instruction.
This will cause JIT failures. The easiest way to reproduce this is to test the following code through test_bpf module:
{
"BPF_LDX_MEMSX | BPF_W",
.u.insns_int = {
BPF_LD_IMM64(R1, 0x00000000deadbeefULL),
BPF_LD_IMM64(R2, 0xffffffffdeadbeefULL),
BPF_STX_MEM(BPF_DW, R10, R1, -7),
BPF_LDX_MEMSX(BPF_W, R0, R10, -7),
BPF_JMP_REG(BPF_JNE, R0, R2, 1),
BPF_ALU64_IMM(BPF_MOV, R0, 0),
BPF_EXIT_INSN(),
},
INTERNAL,
{ },
{ { 0, 0 } },
.stack_depth = 7,
},We need to use the offset as -7 to trigger this code path, there could be other valid ways to trigger this from proper BPF programs as well.
This code is rejected by the JIT because -7 is passed to A64_LDRSW() but it expects a valid register (0 - 31).
roott@pjy:~# modprobe test_bpf test_name="BPF_LDX_MEMSX | BPF_W" [11300.490371] test_bpf: test_bpf: set 'test_bpf' as the default test_suite. [11300.491750] test_bpf: #345 BPF_LDX_MEMSX | BPF_W [11300.493179] aarch64_insn_encode_register: unknown register encoding -7 [11300.494133] aarch64_insn_encode_register: unknown register encoding -7 [11300.495292] FAIL to select_runtime err=-524 [11300.496804] test_bpf: Summary: 0 PASSED, 1 FAILED, [0/0 JIT'ed] modprobe: ERROR: could not insert 'test_bpf': Invalid argument
Applying this patch fixes the issue.
root@pjy:~# modprobe test_bpf test_name="BPF_LDX_MEMSX | BPF_W" [ 292.837436] test_bpf: test_bpf: set 'test_bpf' as the default test_suite. [ 292.839416] test_bpf: #345 BPF_LDX_MEMSX | BPF_W jited:1 156 PASS [ 292.844794] test_bpf: Summary: 1 PASSED, 0 FAILED, [1/1 JIT'ed]
--- arch/arm64/net/bpf_jit_comp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/arm64/net/bpf_jit_comp.c +1 -1
@@ -1256,7 +1256,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, }else {emit_a64_mov_i (1 , tmp, off, ctx);if (sign_extend) -emit (A64_LDRSW (dst, src_adj, off_adj), ctx); +emit (A64_LDRSW (dst, src, tmp), ctx);else emit (A64_LDR32 (dst, src, tmp), ctx); }
Signature · 1 line
2.40.1
This patch was applied to bpf/bpf.git (master) by Alexei Starovoitov <[email protected]>:
Hello:
This patch was applied to bpf/bpf.git (master)
by Alexei Starovoitov <[email protected]>:
Quoted 8 lines · On Tue, 12 Mar 2024 23:59:17 +0000 you wrote:
A64_LDRSW()takes three registers: Xt, Xn, Xm as arguments and it loads and sign extends the value at address Xn + Xm into register Xt.Currently, the offset is being directly used in place of the tmp register which has the offset already loaded by the last emitted instruction.
[...]
Here is the summary with links:
- [bpf] bpf, arm64: fix bug in BPF_LDX_MEMSX
https://git.kernel.org/bpf/bpf/c/114b5b3b4bde
You are awesome, thank you!
Signature · 2 lines
Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/patchwork/pwbot.html