bpf: Add bitwise atomic instructions

This adds instructions for

atomic[64]_[fetch_]and
atomic[64]_[fetch_]or
atomic[64]_[fetch_]xor

All these operations are isomorphic enough to implement with the same
verifier, interpreter, and x86 JIT code, hence being a single commit.

The main interesting thing here is that x86 doesn't directly support
the fetch_ version these operations, so we need to generate a CMPXCHG
loop in the JIT. This requires the use of two temporary registers,
IIUC it's safe to use BPF_REG_AX and x86's AUX_REG for this purpose.
Signed-off-by: Brendan Jackman <jackmanb@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210114181751.768687-10-jackmanb@google.com

arch/x86/net/bpf_jit_comp.c

@@ -808,6 +808,10 @@ static int emit_atomic(u8 **pprog, u8 atomic_op,
 	/* emit opcode */
 	switch (atomic_op) {
 	case BPF_ADD:
+	case BPF_SUB:
+	case BPF_AND:
+	case BPF_OR:
+	case BPF_XOR:
 		/* lock *(u32/u64*)(dst_reg + off) <op>= src_reg */
 		EMIT1(simple_alu_opcodes[atomic_op]);
 		break;
@@ -1292,8 +1296,52 @@ st:			if (is_imm8(insn->off))
 
 		case BPF_STX | BPF_ATOMIC | BPF_W:
 		case BPF_STX | BPF_ATOMIC | BPF_DW:
+			if (insn->imm == (BPF_AND | BPF_FETCH) ||
+			    insn->imm == (BPF_OR | BPF_FETCH) ||
+			    insn->imm == (BPF_XOR | BPF_FETCH)) {
+				u8 *branch_target;
+				bool is64 = BPF_SIZE(insn->code) == BPF_DW;
+
+				/*
+				 * Can't be implemented with a single x86 insn.
+				 * Need to do a CMPXCHG loop.
+				 */
+
+				/* Will need RAX as a CMPXCHG operand so save R0 */
+				emit_mov_reg(&prog, true, BPF_REG_AX, BPF_REG_0);
+				branch_target = prog;
+				/* Load old value */
+				emit_ldx(&prog, BPF_SIZE(insn->code),
+					 BPF_REG_0, dst_reg, insn->off);
+				/*
+				 * Perform the (commutative) operation locally,
+				 * put the result in the AUX_REG.
+				 */
+				emit_mov_reg(&prog, is64, AUX_REG, BPF_REG_0);
+				maybe_emit_mod(&prog, AUX_REG, src_reg, is64);
+				EMIT2(simple_alu_opcodes[BPF_OP(insn->imm)],
+				      add_2reg(0xC0, AUX_REG, src_reg));
+				/* Attempt to swap in new value */
+				err = emit_atomic(&prog, BPF_CMPXCHG,
+						  dst_reg, AUX_REG, insn->off,
+						  BPF_SIZE(insn->code));
+				if (WARN_ON(err))
+					return err;
+				/*
+				 * ZF tells us whether we won the race. If it's
+				 * cleared we need to try again.
+				 */
+				EMIT2(X86_JNE, -(prog - branch_target) - 2);
+				/* Return the pre-modification value */
+				emit_mov_reg(&prog, is64, src_reg, BPF_REG_0);
+				/* Restore R0 after clobbering RAX */
+				emit_mov_reg(&prog, true, BPF_REG_0, BPF_REG_AX);
+				break;
+
+			}
+
 			err = emit_atomic(&prog, insn->imm, dst_reg, src_reg,
-					  insn->off, BPF_SIZE(insn->code));
+						  insn->off, BPF_SIZE(insn->code));
 			if (err)
 				return err;
 			break;

include/linux/filter.h

@@ -264,7 +264,13 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
  * Atomic operations:
  *
  *   BPF_ADD                  *(uint *) (dst_reg + off16) += src_reg
+ *   BPF_AND                  *(uint *) (dst_reg + off16) &= src_reg
+ *   BPF_OR                   *(uint *) (dst_reg + off16) |= src_reg
+ *   BPF_XOR                  *(uint *) (dst_reg + off16) ^= src_reg
  *   BPF_ADD | BPF_FETCH      src_reg = atomic_fetch_add(dst_reg + off16, src_reg);
+ *   BPF_AND | BPF_FETCH      src_reg = atomic_fetch_and(dst_reg + off16, src_reg);
+ *   BPF_OR | BPF_FETCH       src_reg = atomic_fetch_or(dst_reg + off16, src_reg);
+ *   BPF_XOR | BPF_FETCH      src_reg = atomic_fetch_xor(dst_reg + off16, src_reg);
  *   BPF_XCHG                 src_reg = atomic_xchg(dst_reg + off16, src_reg)
  *   BPF_CMPXCHG              r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg)
  */

kernel/bpf/core.c

@@ -1642,6 +1642,9 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 	STX_ATOMIC_W:
 		switch (IMM) {
 		ATOMIC_ALU_OP(BPF_ADD, add)
+		ATOMIC_ALU_OP(BPF_AND, and)
+		ATOMIC_ALU_OP(BPF_OR, or)
+		ATOMIC_ALU_OP(BPF_XOR, xor)
 #undef ATOMIC_ALU_OP
 
 		case BPF_XCHG:

kernel/bpf/disasm.c

@@ -80,6 +80,13 @@ const char *const bpf_alu_string[16] = {
 	[BPF_END >> 4]  = "endian",
 };
 
+static const char *const bpf_atomic_alu_string[16] = {
+	[BPF_ADD >> 4]  = "add",
+	[BPF_AND >> 4]  = "and",
+	[BPF_OR >> 4]  = "or",
+	[BPF_XOR >> 4]  = "or",
+};
+
 static const char *const bpf_ldst_string[] = {
 	[BPF_W >> 3]  = "u32",
 	[BPF_H >> 3]  = "u16",
@@ -154,17 +161,23 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
 				insn->dst_reg,
 				insn->off, insn->src_reg);
 		else if (BPF_MODE(insn->code) == BPF_ATOMIC &&
-			 insn->imm == BPF_ADD) {
-			verbose(cbs->private_data, "(%02x) lock *(%s *)(r%d %+d) += r%d\n",
+			 (insn->imm == BPF_ADD || insn->imm == BPF_ADD ||
+			  insn->imm == BPF_OR || insn->imm == BPF_XOR)) {
+			verbose(cbs->private_data, "(%02x) lock *(%s *)(r%d %+d) %s r%d\n",
 				insn->code,
 				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
 				insn->dst_reg, insn->off,
+				bpf_alu_string[BPF_OP(insn->imm) >> 4],
 				insn->src_reg);
 		} else if (BPF_MODE(insn->code) == BPF_ATOMIC &&
-			   insn->imm == (BPF_ADD | BPF_FETCH)) {
-			verbose(cbs->private_data, "(%02x) r%d = atomic%s_fetch_add((%s *)(r%d %+d), r%d)\n",
+			   (insn->imm == (BPF_ADD | BPF_FETCH) ||
+			    insn->imm == (BPF_AND | BPF_FETCH) ||
+			    insn->imm == (BPF_OR | BPF_FETCH) ||
+			    insn->imm == (BPF_XOR | BPF_FETCH))) {
+			verbose(cbs->private_data, "(%02x) r%d = atomic%s_fetch_%s((%s *)(r%d %+d), r%d)\n",
 				insn->code, insn->src_reg,
 				BPF_SIZE(insn->code) == BPF_DW ? "64" : "",
+				bpf_atomic_alu_string[BPF_OP(insn->imm) >> 4],
 				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
 				insn->dst_reg, insn->off, insn->src_reg);
 		} else if (BPF_MODE(insn->code) == BPF_ATOMIC &&

kernel/bpf/verifier.c

@@ -3612,6 +3612,12 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 	switch (insn->imm) {
 	case BPF_ADD:
 	case BPF_ADD | BPF_FETCH:
+	case BPF_AND:
+	case BPF_AND | BPF_FETCH:
+	case BPF_OR:
+	case BPF_OR | BPF_FETCH:
+	case BPF_XOR:
+	case BPF_XOR | BPF_FETCH:
 	case BPF_XCHG:
 	case BPF_CMPXCHG:
 		break;

tools/include/linux/filter.h

@@ -173,7 +173,13 @@
  * Atomic operations:
  *
  *   BPF_ADD                  *(uint *) (dst_reg + off16) += src_reg
+ *   BPF_AND                  *(uint *) (dst_reg + off16) &= src_reg
+ *   BPF_OR                   *(uint *) (dst_reg + off16) |= src_reg
+ *   BPF_XOR                  *(uint *) (dst_reg + off16) ^= src_reg
  *   BPF_ADD | BPF_FETCH      src_reg = atomic_fetch_add(dst_reg + off16, src_reg);
+ *   BPF_AND | BPF_FETCH      src_reg = atomic_fetch_and(dst_reg + off16, src_reg);
+ *   BPF_OR | BPF_FETCH       src_reg = atomic_fetch_or(dst_reg + off16, src_reg);
+ *   BPF_XOR | BPF_FETCH      src_reg = atomic_fetch_xor(dst_reg + off16, src_reg);
  *   BPF_XCHG                 src_reg = atomic_xchg(dst_reg + off16, src_reg)
  *   BPF_CMPXCHG              r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg)
  */