From b2ad54e1533e91449cb2a371e034942bd7882b58 Mon Sep 17 00:00:00 2001 From: Xu Kuohai Date: Mon, 11 Jul 2022 11:08:22 -0400 Subject: bpf, arm64: Implement bpf_arch_text_poke() for arm64 Implement bpf_arch_text_poke() for arm64, so bpf prog or bpf trampoline can be patched with it. When the target address is NULL, the original instruction is patched to a NOP. When the target address and the source address are within the branch range, the original instruction is patched to a bl instruction to the target address directly. To support attaching bpf trampoline to both regular kernel function and bpf prog, we follow the ftrace patchsite way for bpf prog. That is, two instructions are inserted at the beginning of bpf prog, the first one saves the return address to x9, and the second is a nop which will be patched to a bl instruction when a bpf trampoline is attached. However, when a bpf trampoline is attached to bpf prog, the distance between target address and source address may exceed 128MB, the maximum branch range, because bpf trampoline and bpf prog are allocated separately with vmalloc. So long jump should be handled. When a bpf prog is constructed, a plt pointing to empty trampoline dummy_tramp is placed at the end: bpf_prog: mov x9, lr nop // patchsite ... ret plt: ldr x10, target br x10 target: .quad dummy_tramp // plt target This is also the state when no trampoline is attached. When a short-jump bpf trampoline is attached, the patchsite is patched to a bl instruction to the trampoline directly: bpf_prog: mov x9, lr bl // patchsite ... ret plt: ldr x10, target br x10 target: .quad dummy_tramp // plt target When a long-jump bpf trampoline is attached, the plt target is filled with the trampoline address and the patchsite is patched to a bl instruction to the plt: bpf_prog: mov x9, lr bl plt // patchsite ... ret plt: ldr x10, target br x10 target: .quad dummy_tramp is used to prevent another CPU from jumping to an unknown location during the patching process, making the patching process easier. The patching process is as follows: 1. when neither the old address or the new address is a long jump, the patchsite is replaced with a bl to the new address, or nop if the new address is NULL; 2. when the old address is not long jump but the new one is, the branch target address is written to plt first, then the patchsite is replaced with a bl instruction to the plt; 3. when the old address is long jump but the new one is not, the address of dummy_tramp is written to plt first, then the patchsite is replaced with a bl to the new address, or a nop if the new address is NULL; 4. when both the old address and the new address are long jump, the new address is written to plt and the patchsite is not changed. Signed-off-by: Xu Kuohai Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Reviewed-by: KP Singh Reviewed-by: Jean-Philippe Brucker Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20220711150823.2128542-4-xukuohai@huawei.com --- arch/arm64/net/bpf_jit.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'arch/arm64/net/bpf_jit.h') diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index 194c95ccc1cf..a6acb94ea3d6 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -80,6 +80,12 @@ #define A64_STR64I(Xt, Xn, imm) A64_LS_IMM(Xt, Xn, imm, 64, STORE) #define A64_LDR64I(Xt, Xn, imm) A64_LS_IMM(Xt, Xn, imm, 64, LOAD) +/* LDR (literal) */ +#define A64_LDR32LIT(Wt, offset) \ + aarch64_insn_gen_load_literal(0, offset, Wt, false) +#define A64_LDR64LIT(Xt, offset) \ + aarch64_insn_gen_load_literal(0, offset, Xt, true) + /* Load/store register pair */ #define A64_LS_PAIR(Rt, Rt2, Rn, offset, ls, type) \ aarch64_insn_gen_load_store_pair(Rt, Rt2, Rn, offset, \ @@ -270,6 +276,7 @@ #define A64_BTI_C A64_HINT(AARCH64_INSN_HINT_BTIC) #define A64_BTI_J A64_HINT(AARCH64_INSN_HINT_BTIJ) #define A64_BTI_JC A64_HINT(AARCH64_INSN_HINT_BTIJC) +#define A64_NOP A64_HINT(AARCH64_INSN_HINT_NOP) /* DMB */ #define A64_DMB_ISH aarch64_insn_gen_dmb(AARCH64_INSN_MB_ISH) -- cgit v1.2.3