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

1 files changed, 35 insertions, 4 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 */