summaryrefslogtreecommitdiff
path: root/arch/arm64/net
diff options
context:
space:
mode:
authorHou Tao <houtao1@huawei.com>2022-02-17 10:22:31 +0300
committerDaniel Borkmann <daniel@iogearbox.net>2022-02-28 18:27:22 +0300
commit1902472b4fa97dba1fd10a204c6b231d6a560081 (patch)
tree7ba4d807807c26dd6876d65b83fedafc377d45b6 /arch/arm64/net
parent79e7ce2e519ef5b3a5cacfd0e1d8ed456b89ff9f (diff)
downloadlinux-1902472b4fa97dba1fd10a204c6b231d6a560081.tar.xz
bpf, arm64: Support more atomic operations
Atomics for eBPF patch series adds support for atomic[64]_fetch_add, atomic[64]_[fetch_]{and,or,xor} and atomic[64]_{xchg|cmpxchg}, but it only adds support for x86-64, so support these atomic operations for arm64 as well. Basically the implementation procedure is almost mechanical translation of code snippets in atomic_ll_sc.h & atomic_lse.h & cmpxchg.h located under arch/arm64/include/asm. When LSE atomic is unavailable, an extra temporary register is needed for (BPF_ADD | BPF_FETCH) to save the value of src register, instead of adding TMP_REG_4 just use BPF_REG_AX instead. Also make emit_lse_atomic() as an empty inline function when CONFIG_ARM64_LSE_ATOMICS is disabled. For cpus_have_cap(ARM64_HAS_LSE_ATOMICS) case and no-LSE-ATOMICS case, the following three tests: "./test_verifier", "./test_progs -t atomic" and "insmod ./test_bpf.ko" are exercised and passed. Signed-off-by: Hou Tao <houtao1@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20220217072232.1186625-4-houtao1@huawei.com
Diffstat (limited to 'arch/arm64/net')
-rw-r--r--arch/arm64/net/bpf_jit.h39
-rw-r--r--arch/arm64/net/bpf_jit_comp.c223
2 files changed, 217 insertions, 45 deletions
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index 9d9250c7cc72..dd59b5ad8fe4 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -88,17 +88,42 @@
/* [Rn] = Rt; (atomic) Rs = [state] */
#define A64_STXR(sf, Rt, Rn, Rs) \
A64_LSX(sf, Rt, Rn, Rs, STORE_EX)
+/* [Rn] = Rt (store release); (atomic) Rs = [state] */
+#define A64_STLXR(sf, Rt, Rn, Rs) \
+ aarch64_insn_gen_load_store_ex(Rt, Rn, Rs, A64_SIZE(sf), \
+ AARCH64_INSN_LDST_STORE_REL_EX)
/*
* LSE atomics
*
- * STADD is simply encoded as an alias for LDADD with XZR as
- * the destination register.
+ * ST{ADD,CLR,SET,EOR} is simply encoded as an alias for
+ * LDD{ADD,CLR,SET,EOR} with XZR as the destination register.
*/
-#define A64_STADD(sf, Rn, Rs) \
+#define A64_ST_OP(sf, Rn, Rs, op) \
aarch64_insn_gen_atomic_ld_op(A64_ZR, Rn, Rs, \
- A64_SIZE(sf), AARCH64_INSN_MEM_ATOMIC_ADD, \
+ A64_SIZE(sf), AARCH64_INSN_MEM_ATOMIC_##op, \
AARCH64_INSN_MEM_ORDER_NONE)
+/* [Rn] <op>= Rs */
+#define A64_STADD(sf, Rn, Rs) A64_ST_OP(sf, Rn, Rs, ADD)
+#define A64_STCLR(sf, Rn, Rs) A64_ST_OP(sf, Rn, Rs, CLR)
+#define A64_STEOR(sf, Rn, Rs) A64_ST_OP(sf, Rn, Rs, EOR)
+#define A64_STSET(sf, Rn, Rs) A64_ST_OP(sf, Rn, Rs, SET)
+
+#define A64_LD_OP_AL(sf, Rt, Rn, Rs, op) \
+ aarch64_insn_gen_atomic_ld_op(Rt, Rn, Rs, \
+ A64_SIZE(sf), AARCH64_INSN_MEM_ATOMIC_##op, \
+ AARCH64_INSN_MEM_ORDER_ACQREL)
+/* Rt = [Rn] (load acquire); [Rn] <op>= Rs (store release) */
+#define A64_LDADDAL(sf, Rt, Rn, Rs) A64_LD_OP_AL(sf, Rt, Rn, Rs, ADD)
+#define A64_LDCLRAL(sf, Rt, Rn, Rs) A64_LD_OP_AL(sf, Rt, Rn, Rs, CLR)
+#define A64_LDEORAL(sf, Rt, Rn, Rs) A64_LD_OP_AL(sf, Rt, Rn, Rs, EOR)
+#define A64_LDSETAL(sf, Rt, Rn, Rs) A64_LD_OP_AL(sf, Rt, Rn, Rs, SET)
+/* Rt = [Rn] (load acquire); [Rn] = Rs (store release) */
+#define A64_SWPAL(sf, Rt, Rn, Rs) A64_LD_OP_AL(sf, Rt, Rn, Rs, SWP)
+/* Rs = CAS(Rn, Rs, Rt) (load acquire & store release) */
+#define A64_CASAL(sf, Rt, Rn, Rs) \
+ aarch64_insn_gen_cas(Rt, Rn, Rs, A64_SIZE(sf), \
+ AARCH64_INSN_MEM_ORDER_ACQREL)
/* Add/subtract (immediate) */
#define A64_ADDSUB_IMM(sf, Rd, Rn, imm12, type) \
@@ -203,6 +228,9 @@
#define A64_ANDS(sf, Rd, Rn, Rm) A64_LOGIC_SREG(sf, Rd, Rn, Rm, AND_SETFLAGS)
/* Rn & Rm; set condition flags */
#define A64_TST(sf, Rn, Rm) A64_ANDS(sf, A64_ZR, Rn, Rm)
+/* Rd = ~Rm (alias of ORN with A64_ZR as Rn) */
+#define A64_MVN(sf, Rd, Rm) \
+ A64_LOGIC_SREG(sf, Rd, A64_ZR, Rm, ORN)
/* Logical (immediate) */
#define A64_LOGIC_IMM(sf, Rd, Rn, imm, type) ({ \
@@ -226,4 +254,7 @@
#define A64_BTI_J A64_HINT(AARCH64_INSN_HINT_BTIJ)
#define A64_BTI_JC A64_HINT(AARCH64_INSN_HINT_BTIJC)
+/* DMB */
+#define A64_DMB_ISH aarch64_insn_gen_dmb(AARCH64_INSN_MB_ISH)
+
#endif /* _BPF_JIT_H */
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 4f137424935f..e850c69e128c 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -27,6 +27,17 @@
#define TCALL_CNT (MAX_BPF_JIT_REG + 2)
#define TMP_REG_3 (MAX_BPF_JIT_REG + 3)
+#define check_imm(bits, imm) do { \
+ if ((((imm) > 0) && ((imm) >> (bits))) || \
+ (((imm) < 0) && (~(imm) >> (bits)))) { \
+ pr_info("[%2d] imm=%d(0x%x) out of range\n", \
+ i, imm, imm); \
+ return -EINVAL; \
+ } \
+} while (0)
+#define check_imm19(imm) check_imm(19, imm)
+#define check_imm26(imm) check_imm(26, imm)
+
/* Map BPF registers to A64 registers */
static const int bpf2a64[] = {
/* return value from in-kernel function, and exit value from eBPF */
@@ -329,6 +340,170 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
#undef jmp_offset
}
+#ifdef CONFIG_ARM64_LSE_ATOMICS
+static int emit_lse_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
+{
+ const u8 code = insn->code;
+ const u8 dst = bpf2a64[insn->dst_reg];
+ const u8 src = bpf2a64[insn->src_reg];
+ const u8 tmp = bpf2a64[TMP_REG_1];
+ const u8 tmp2 = bpf2a64[TMP_REG_2];
+ const bool isdw = BPF_SIZE(code) == BPF_DW;
+ const s16 off = insn->off;
+ u8 reg;
+
+ if (!off) {
+ reg = dst;
+ } else {
+ emit_a64_mov_i(1, tmp, off, ctx);
+ emit(A64_ADD(1, tmp, tmp, dst), ctx);
+ reg = tmp;
+ }
+
+ switch (insn->imm) {
+ /* lock *(u32/u64 *)(dst_reg + off) <op>= src_reg */
+ case BPF_ADD:
+ emit(A64_STADD(isdw, reg, src), ctx);
+ break;
+ case BPF_AND:
+ emit(A64_MVN(isdw, tmp2, src), ctx);
+ emit(A64_STCLR(isdw, reg, tmp2), ctx);
+ break;
+ case BPF_OR:
+ emit(A64_STSET(isdw, reg, src), ctx);
+ break;
+ case BPF_XOR:
+ emit(A64_STEOR(isdw, reg, src), ctx);
+ break;
+ /* src_reg = atomic_fetch_<op>(dst_reg + off, src_reg) */
+ case BPF_ADD | BPF_FETCH:
+ emit(A64_LDADDAL(isdw, src, reg, src), ctx);
+ break;
+ case BPF_AND | BPF_FETCH:
+ emit(A64_MVN(isdw, tmp2, src), ctx);
+ emit(A64_LDCLRAL(isdw, src, reg, tmp2), ctx);
+ break;
+ case BPF_OR | BPF_FETCH:
+ emit(A64_LDSETAL(isdw, src, reg, src), ctx);
+ break;
+ case BPF_XOR | BPF_FETCH:
+ emit(A64_LDEORAL(isdw, src, reg, src), ctx);
+ break;
+ /* src_reg = atomic_xchg(dst_reg + off, src_reg); */
+ case BPF_XCHG:
+ emit(A64_SWPAL(isdw, src, reg, src), ctx);
+ break;
+ /* r0 = atomic_cmpxchg(dst_reg + off, r0, src_reg); */
+ case BPF_CMPXCHG:
+ emit(A64_CASAL(isdw, src, reg, bpf2a64[BPF_REG_0]), ctx);
+ break;
+ default:
+ pr_err_once("unknown atomic op code %02x\n", insn->imm);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+#else
+static inline int emit_lse_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
+{
+ return -EINVAL;
+}
+#endif
+
+static int emit_ll_sc_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
+{
+ const u8 code = insn->code;
+ const u8 dst = bpf2a64[insn->dst_reg];
+ const u8 src = bpf2a64[insn->src_reg];
+ const u8 tmp = bpf2a64[TMP_REG_1];
+ const u8 tmp2 = bpf2a64[TMP_REG_2];
+ const u8 tmp3 = bpf2a64[TMP_REG_3];
+ const int i = insn - ctx->prog->insnsi;
+ const s32 imm = insn->imm;
+ const s16 off = insn->off;
+ const bool isdw = BPF_SIZE(code) == BPF_DW;
+ u8 reg;
+ s32 jmp_offset;
+
+ if (!off) {
+ reg = dst;
+ } else {
+ emit_a64_mov_i(1, tmp, off, ctx);
+ emit(A64_ADD(1, tmp, tmp, dst), ctx);
+ reg = tmp;
+ }
+
+ if (imm == BPF_ADD || imm == BPF_AND ||
+ imm == BPF_OR || imm == BPF_XOR) {
+ /* lock *(u32/u64 *)(dst_reg + off) <op>= src_reg */
+ emit(A64_LDXR(isdw, tmp2, reg), ctx);
+ if (imm == BPF_ADD)
+ emit(A64_ADD(isdw, tmp2, tmp2, src), ctx);
+ else if (imm == BPF_AND)
+ emit(A64_AND(isdw, tmp2, tmp2, src), ctx);
+ else if (imm == BPF_OR)
+ emit(A64_ORR(isdw, tmp2, tmp2, src), ctx);
+ else
+ emit(A64_EOR(isdw, tmp2, tmp2, src), ctx);
+ emit(A64_STXR(isdw, tmp2, reg, tmp3), ctx);
+ jmp_offset = -3;
+ check_imm19(jmp_offset);
+ emit(A64_CBNZ(0, tmp3, jmp_offset), ctx);
+ } else if (imm == (BPF_ADD | BPF_FETCH) ||
+ imm == (BPF_AND | BPF_FETCH) ||
+ imm == (BPF_OR | BPF_FETCH) ||
+ imm == (BPF_XOR | BPF_FETCH)) {
+ /* src_reg = atomic_fetch_<op>(dst_reg + off, src_reg) */
+ const u8 ax = bpf2a64[BPF_REG_AX];
+
+ emit(A64_MOV(isdw, ax, src), ctx);
+ emit(A64_LDXR(isdw, src, reg), ctx);
+ if (imm == (BPF_ADD | BPF_FETCH))
+ emit(A64_ADD(isdw, tmp2, src, ax), ctx);
+ else if (imm == (BPF_AND | BPF_FETCH))
+ emit(A64_AND(isdw, tmp2, src, ax), ctx);
+ else if (imm == (BPF_OR | BPF_FETCH))
+ emit(A64_ORR(isdw, tmp2, src, ax), ctx);
+ else
+ emit(A64_EOR(isdw, tmp2, src, ax), ctx);
+ emit(A64_STLXR(isdw, tmp2, reg, tmp3), ctx);
+ jmp_offset = -3;
+ check_imm19(jmp_offset);
+ emit(A64_CBNZ(0, tmp3, jmp_offset), ctx);
+ emit(A64_DMB_ISH, ctx);
+ } else if (imm == BPF_XCHG) {
+ /* src_reg = atomic_xchg(dst_reg + off, src_reg); */
+ emit(A64_MOV(isdw, tmp2, src), ctx);
+ emit(A64_LDXR(isdw, src, reg), ctx);
+ emit(A64_STLXR(isdw, tmp2, reg, tmp3), ctx);
+ jmp_offset = -2;
+ check_imm19(jmp_offset);
+ emit(A64_CBNZ(0, tmp3, jmp_offset), ctx);
+ emit(A64_DMB_ISH, ctx);
+ } else if (imm == BPF_CMPXCHG) {
+ /* r0 = atomic_cmpxchg(dst_reg + off, r0, src_reg); */
+ const u8 r0 = bpf2a64[BPF_REG_0];
+
+ emit(A64_MOV(isdw, tmp2, r0), ctx);
+ emit(A64_LDXR(isdw, r0, reg), ctx);
+ emit(A64_EOR(isdw, tmp3, r0, tmp2), ctx);
+ jmp_offset = 4;
+ check_imm19(jmp_offset);
+ emit(A64_CBNZ(isdw, tmp3, jmp_offset), ctx);
+ emit(A64_STLXR(isdw, src, reg, tmp3), ctx);
+ jmp_offset = -4;
+ check_imm19(jmp_offset);
+ emit(A64_CBNZ(0, tmp3, jmp_offset), ctx);
+ emit(A64_DMB_ISH, ctx);
+ } else {
+ pr_err_once("unknown atomic op code %02x\n", imm);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static void build_epilogue(struct jit_ctx *ctx)
{
const u8 r0 = bpf2a64[BPF_REG_0];
@@ -434,29 +609,16 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
const u8 src = bpf2a64[insn->src_reg];
const u8 tmp = bpf2a64[TMP_REG_1];
const u8 tmp2 = bpf2a64[TMP_REG_2];
- const u8 tmp3 = bpf2a64[TMP_REG_3];
const s16 off = insn->off;
const s32 imm = insn->imm;
const int i = insn - ctx->prog->insnsi;
const bool is64 = BPF_CLASS(code) == BPF_ALU64 ||
BPF_CLASS(code) == BPF_JMP;
- const bool isdw = BPF_SIZE(code) == BPF_DW;
- u8 jmp_cond, reg;
+ u8 jmp_cond;
s32 jmp_offset;
u32 a64_insn;
int ret;
-#define check_imm(bits, imm) do { \
- if ((((imm) > 0) && ((imm) >> (bits))) || \
- (((imm) < 0) && (~(imm) >> (bits)))) { \
- pr_info("[%2d] imm=%d(0x%x) out of range\n", \
- i, imm, imm); \
- return -EINVAL; \
- } \
-} while (0)
-#define check_imm19(imm) check_imm(19, imm)
-#define check_imm26(imm) check_imm(26, imm)
-
switch (code) {
/* dst = src */
case BPF_ALU | BPF_MOV | BPF_X:
@@ -891,33 +1053,12 @@ emit_cond_jmp:
case BPF_STX | BPF_ATOMIC | BPF_W:
case BPF_STX | BPF_ATOMIC | BPF_DW:
- if (insn->imm != BPF_ADD) {
- pr_err_once("unknown atomic op code %02x\n", insn->imm);
- return -EINVAL;
- }
-
- /* STX XADD: lock *(u32 *)(dst + off) += src
- * and
- * STX XADD: lock *(u64 *)(dst + off) += src
- */
-
- if (!off) {
- reg = dst;
- } else {
- emit_a64_mov_i(1, tmp, off, ctx);
- emit(A64_ADD(1, tmp, tmp, dst), ctx);
- reg = tmp;
- }
- if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS)) {
- emit(A64_STADD(isdw, reg, src), ctx);
- } else {
- emit(A64_LDXR(isdw, tmp2, reg), ctx);
- emit(A64_ADD(isdw, tmp2, tmp2, src), ctx);
- emit(A64_STXR(isdw, tmp2, reg, tmp3), ctx);
- jmp_offset = -3;
- check_imm19(jmp_offset);
- emit(A64_CBNZ(0, tmp3, jmp_offset), ctx);
- }
+ if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
+ ret = emit_lse_atomic(insn, ctx);
+ else
+ ret = emit_ll_sc_atomic(insn, ctx);
+ if (ret)
+ return ret;
break;
default: