bpf: Introduce load-acquire and store-release instructions

Introduce BPF instructions with load-acquire and store-release
semantics, as discussed in [1].  Define 2 new flags:

  #define BPF_LOAD_ACQ    0x100
  #define BPF_STORE_REL   0x110

A "load-acquire" is a BPF_STX | BPF_ATOMIC instruction with the 'imm'
field set to BPF_LOAD_ACQ (0x100).

Similarly, a "store-release" is a BPF_STX | BPF_ATOMIC instruction with
the 'imm' field set to BPF_STORE_REL (0x110).

Unlike existing atomic read-modify-write operations that only support
BPF_W (32-bit) and BPF_DW (64-bit) size modifiers, load-acquires and
store-releases also support BPF_B (8-bit) and BPF_H (16-bit).  As an
exception, however, 64-bit load-acquires/store-releases are not
supported on 32-bit architectures (to fix a build error reported by the
kernel test robot).

An 8- or 16-bit load-acquire zero-extends the value before writing it to
a 32-bit register, just like ARM64 instruction LDARH and friends.

Similar to existing atomic read-modify-write operations, misaligned
load-acquires/store-releases are not allowed (even if
BPF_F_ANY_ALIGNMENT is set).

As an example, consider the following 64-bit load-acquire BPF
instruction (assuming little-endian):

  db 10 00 00 00 01 00 00  r0 = load_acquire((u64 *)(r1 + 0x0))

  opcode (0xdb): BPF_ATOMIC | BPF_DW | BPF_STX
  imm (0x00000100): BPF_LOAD_ACQ

Similarly, a 16-bit BPF store-release:

  cb 21 00 00 10 01 00 00  store_release((u16 *)(r1 + 0x0), w2)

  opcode (0xcb): BPF_ATOMIC | BPF_H | BPF_STX
  imm (0x00000110): BPF_STORE_REL

In arch/{arm64,s390,x86}/net/bpf_jit_comp.c, have
bpf_jit_supports_insn(..., /*in_arena=*/true) return false for the new
instructions, until the corresponding JIT compiler supports them in
arena.

[1] https://lore.kernel.org/all/20240729183246.4110549-1-yepeilin@google.com/

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
Cc: kernel test robot <lkp@intel.com>
Signed-off-by: Peilin Ye <yepeilin@google.com>
Link: https://lore.kernel.org/r/a217f46f0e445fbd573a1a024be5c6bf1d5fe716.1741049567.git.yepeilin@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 61 insertions, 6 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index e583c19a0291..62cb9557ad3b 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1663,14 +1663,17 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
 	INSN_3(JMP, JSET, K),			\
 	INSN_2(JMP, JA),			\
 	INSN_2(JMP32, JA),			\
+	/* Atomic operations. */		\
+	INSN_3(STX, ATOMIC, B),			\
+	INSN_3(STX, ATOMIC, H),			\
+	INSN_3(STX, ATOMIC, W),			\
+	INSN_3(STX, ATOMIC, DW),		\
 	/* Store instructions. */		\
 	/*   Register based. */			\
 	INSN_3(STX, MEM,  B),			\
 	INSN_3(STX, MEM,  H),			\
 	INSN_3(STX, MEM,  W),			\
 	INSN_3(STX, MEM,  DW),			\
-	INSN_3(STX, ATOMIC, W),			\
-	INSN_3(STX, ATOMIC, DW),		\
 	/*   Immediate based. */		\
 	INSN_3(ST, MEM, B),			\
 	INSN_3(ST, MEM, H),			\
@@ -2152,24 +2155,33 @@ out:
 			if (BPF_SIZE(insn->code) == BPF_W)		\
 				atomic_##KOP((u32) SRC, (atomic_t *)(unsigned long) \
 					     (DST + insn->off));	\
-			else						\
+			else if (BPF_SIZE(insn->code) == BPF_DW)	\
 				atomic64_##KOP((u64) SRC, (atomic64_t *)(unsigned long) \
 					       (DST + insn->off));	\
+			else						\
+				goto default_label;			\
 			break;						\
 		case BOP | BPF_FETCH:					\
 			if (BPF_SIZE(insn->code) == BPF_W)		\
 				SRC = (u32) atomic_fetch_##KOP(		\
 					(u32) SRC,			\
 					(atomic_t *)(unsigned long) (DST + insn->off)); \
-			else						\
+			else if (BPF_SIZE(insn->code) == BPF_DW)	\
 				SRC = (u64) atomic64_fetch_##KOP(	\
 					(u64) SRC,			\
 					(atomic64_t *)(unsigned long) (DST + insn->off)); \
+			else						\
+				goto default_label;			\
 			break;
 
 	STX_ATOMIC_DW:
 	STX_ATOMIC_W:
+	STX_ATOMIC_H:
+	STX_ATOMIC_B:
 		switch (IMM) {
+		/* Atomic read-modify-write instructions support only W and DW
+		 * size modifiers.
+		 */
 		ATOMIC_ALU_OP(BPF_ADD, add)
 		ATOMIC_ALU_OP(BPF_AND, and)
 		ATOMIC_ALU_OP(BPF_OR, or)
@@ -2181,20 +2193,63 @@ out:
 				SRC = (u32) atomic_xchg(
 					(atomic_t *)(unsigned long) (DST + insn->off),
 					(u32) SRC);
-			else
+			else if (BPF_SIZE(insn->code) == BPF_DW)
 				SRC = (u64) atomic64_xchg(
 					(atomic64_t *)(unsigned long) (DST + insn->off),
 					(u64) SRC);
+			else
+				goto default_label;
 			break;
 		case BPF_CMPXCHG:
 			if (BPF_SIZE(insn->code) == BPF_W)
 				BPF_R0 = (u32) atomic_cmpxchg(
 					(atomic_t *)(unsigned long) (DST + insn->off),
 					(u32) BPF_R0, (u32) SRC);
-			else
+			else if (BPF_SIZE(insn->code) == BPF_DW)
 				BPF_R0 = (u64) atomic64_cmpxchg(
 					(atomic64_t *)(unsigned long) (DST + insn->off),
 					(u64) BPF_R0, (u64) SRC);
+			else
+				goto default_label;
+			break;
+		/* Atomic load and store instructions support all size
+		 * modifiers.
+		 */
+		case BPF_LOAD_ACQ:
+			switch (BPF_SIZE(insn->code)) {
+#define LOAD_ACQUIRE(SIZEOP, SIZE)				\
+			case BPF_##SIZEOP:			\
+				DST = (SIZE)smp_load_acquire(	\
+					(SIZE *)(unsigned long)(SRC + insn->off));	\
+				break;
+			LOAD_ACQUIRE(B,   u8)
+			LOAD_ACQUIRE(H,  u16)
+			LOAD_ACQUIRE(W,  u32)
+#ifdef CONFIG_64BIT
+			LOAD_ACQUIRE(DW, u64)
+#endif
+#undef LOAD_ACQUIRE
+			default:
+				goto default_label;
+			}
+			break;
+		case BPF_STORE_REL:
+			switch (BPF_SIZE(insn->code)) {
+#define STORE_RELEASE(SIZEOP, SIZE)			\
+			case BPF_##SIZEOP:		\
+				smp_store_release(	\
+					(SIZE *)(unsigned long)(DST + insn->off), (SIZE)SRC);	\
+				break;
+			STORE_RELEASE(B,   u8)
+			STORE_RELEASE(H,  u16)
+			STORE_RELEASE(W,  u32)
+#ifdef CONFIG_64BIT
+			STORE_RELEASE(DW, u64)
+#endif
+#undef STORE_RELEASE
+			default:
+				goto default_label;
+			}
 			break;
 
 		default: