Incomplete read marks debug

Documentation/bpf/bpf_iterators.rst

@@ -86,7 +86,7 @@ following steps:
 The following are a few examples of selftest BPF iterator programs:
 
 * `bpf_iter_tcp4.c <https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/tree/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c>`_
-* `bpf_iter_task_vma.c <https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/tree/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c>`_
+* `bpf_iter_task_vmas.c <https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/tree/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c>`_
 * `bpf_iter_task_file.c <https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/tree/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c>`_
 
 Let us look at ``bpf_iter_task_file.c``, which runs in kernel space:

arch/arm64/include/asm/insn.h

@@ -188,8 +188,10 @@ enum aarch64_insn_ldst_type {
 	AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX,
 	AARCH64_INSN_LDST_LOAD_PAIR_POST_INDEX,
 	AARCH64_INSN_LDST_STORE_PAIR_POST_INDEX,
+	AARCH64_INSN_LDST_LOAD_ACQ,
 	AARCH64_INSN_LDST_LOAD_EX,
 	AARCH64_INSN_LDST_LOAD_ACQ_EX,
+	AARCH64_INSN_LDST_STORE_REL,
 	AARCH64_INSN_LDST_STORE_EX,
 	AARCH64_INSN_LDST_STORE_REL_EX,
 	AARCH64_INSN_LDST_SIGNED_LOAD_IMM_OFFSET,
@@ -351,8 +353,10 @@ __AARCH64_INSN_FUNCS(ldr_imm,	0x3FC00000, 0x39400000)
 __AARCH64_INSN_FUNCS(ldr_lit,	0xBF000000, 0x18000000)
 __AARCH64_INSN_FUNCS(ldrsw_lit,	0xFF000000, 0x98000000)
 __AARCH64_INSN_FUNCS(exclusive,	0x3F800000, 0x08000000)
-__AARCH64_INSN_FUNCS(load_ex,	0x3F400000, 0x08400000)
-__AARCH64_INSN_FUNCS(store_ex,	0x3F400000, 0x08000000)
+__AARCH64_INSN_FUNCS(load_acq,  0x3FDFFC00, 0x08DFFC00)
+__AARCH64_INSN_FUNCS(store_rel, 0x3FDFFC00, 0x089FFC00)
+__AARCH64_INSN_FUNCS(load_ex,	0x3FC00000, 0x08400000)
+__AARCH64_INSN_FUNCS(store_ex,	0x3FC00000, 0x08000000)
 __AARCH64_INSN_FUNCS(mops,	0x3B200C00, 0x19000400)
 __AARCH64_INSN_FUNCS(stp,	0x7FC00000, 0x29000000)
 __AARCH64_INSN_FUNCS(ldp,	0x7FC00000, 0x29400000)
@@ -602,6 +606,10 @@ u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1,
 				     int offset,
 				     enum aarch64_insn_variant variant,
 				     enum aarch64_insn_ldst_type type);
+u32 aarch64_insn_gen_load_acq_store_rel(enum aarch64_insn_register reg,
+					enum aarch64_insn_register base,
+					enum aarch64_insn_size_type size,
+					enum aarch64_insn_ldst_type type);
 u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg,
 				   enum aarch64_insn_register base,
 				   enum aarch64_insn_register state,

arch/arm64/lib/insn.c

@@ -540,6 +540,35 @@ u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1,
 					     offset >> shift);
 }
 
+u32 aarch64_insn_gen_load_acq_store_rel(enum aarch64_insn_register reg,
+					enum aarch64_insn_register base,
+					enum aarch64_insn_size_type size,
+					enum aarch64_insn_ldst_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_LDST_LOAD_ACQ:
+		insn = aarch64_insn_get_load_acq_value();
+		break;
+	case AARCH64_INSN_LDST_STORE_REL:
+		insn = aarch64_insn_get_store_rel_value();
+		break;
+	default:
+		pr_err("%s: unknown load-acquire/store-release encoding %d\n",
+		       __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_ldst_size(size, insn);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn,
+					    reg);
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+					    base);
+}
+
 u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg,
 				   enum aarch64_insn_register base,
 				   enum aarch64_insn_register state,

arch/arm64/net/bpf_jit.h

@@ -119,6 +119,26 @@
 	aarch64_insn_gen_load_store_ex(Rt, Rn, Rs, A64_SIZE(sf), \
 				       AARCH64_INSN_LDST_STORE_REL_EX)
 
+/* Load-acquire & store-release */
+#define A64_LDAR(Rt, Rn, size)  \
+	aarch64_insn_gen_load_acq_store_rel(Rt, Rn, AARCH64_INSN_SIZE_##size, \
+					    AARCH64_INSN_LDST_LOAD_ACQ)
+#define A64_STLR(Rt, Rn, size)  \
+	aarch64_insn_gen_load_acq_store_rel(Rt, Rn, AARCH64_INSN_SIZE_##size, \
+					    AARCH64_INSN_LDST_STORE_REL)
+
+/* Rt = [Rn] (load acquire) */
+#define A64_LDARB(Wt, Xn)	A64_LDAR(Wt, Xn, 8)
+#define A64_LDARH(Wt, Xn)	A64_LDAR(Wt, Xn, 16)
+#define A64_LDAR32(Wt, Xn)	A64_LDAR(Wt, Xn, 32)
+#define A64_LDAR64(Xt, Xn)	A64_LDAR(Xt, Xn, 64)
+
+/* [Rn] = Rt (store release) */
+#define A64_STLRB(Wt, Xn)	A64_STLR(Wt, Xn, 8)
+#define A64_STLRH(Wt, Xn)	A64_STLR(Wt, Xn, 16)
+#define A64_STLR32(Wt, Xn)	A64_STLR(Wt, Xn, 32)
+#define A64_STLR64(Xt, Xn)	A64_STLR(Xt, Xn, 64)
+
 /*
  * LSE atomics
  *

arch/arm64/net/bpf_jit_comp.c

@@ -647,6 +647,81 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	return 0;
 }
 
+static int emit_atomic_ld_st(const struct bpf_insn *insn, struct jit_ctx *ctx)
+{
+	const s32 imm = insn->imm;
+	const s16 off = insn->off;
+	const u8 code = insn->code;
+	const bool arena = BPF_MODE(code) == BPF_PROBE_ATOMIC;
+	const u8 arena_vm_base = bpf2a64[ARENA_VM_START];
+	const u8 dst = bpf2a64[insn->dst_reg];
+	const u8 src = bpf2a64[insn->src_reg];
+	const u8 tmp = bpf2a64[TMP_REG_1];
+	u8 reg;
+
+	switch (imm) {
+	case BPF_LOAD_ACQ:
+		reg = src;
+		break;
+	case BPF_STORE_REL:
+		reg = dst;
+		break;
+	default:
+		pr_err_once("unknown atomic load/store op code %02x\n", imm);
+		return -EINVAL;
+	}
+
+	if (off) {
+		emit_a64_add_i(1, tmp, reg, tmp, off, ctx);
+		reg = tmp;
+	}
+	if (arena) {
+		emit(A64_ADD(1, tmp, reg, arena_vm_base), ctx);
+		reg = tmp;
+	}
+
+	switch (imm) {
+	case BPF_LOAD_ACQ:
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			emit(A64_LDARB(dst, reg), ctx);
+			break;
+		case BPF_H:
+			emit(A64_LDARH(dst, reg), ctx);
+			break;
+		case BPF_W:
+			emit(A64_LDAR32(dst, reg), ctx);
+			break;
+		case BPF_DW:
+			emit(A64_LDAR64(dst, reg), ctx);
+			break;
+		}
+		break;
+	case BPF_STORE_REL:
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			emit(A64_STLRB(src, reg), ctx);
+			break;
+		case BPF_H:
+			emit(A64_STLRH(src, reg), ctx);
+			break;
+		case BPF_W:
+			emit(A64_STLR32(src, reg), ctx);
+			break;
+		case BPF_DW:
+			emit(A64_STLR64(src, reg), ctx);
+			break;
+		}
+		break;
+	default:
+		pr_err_once("unexpected atomic load/store op code %02x\n",
+			    imm);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 #ifdef CONFIG_ARM64_LSE_ATOMICS
 static int emit_lse_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
 {
@@ -1641,11 +1716,17 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 			return ret;
 		break;
 
+	case BPF_STX | BPF_ATOMIC | BPF_B:
+	case BPF_STX | BPF_ATOMIC | BPF_H:
 	case BPF_STX | BPF_ATOMIC | BPF_W:
 	case BPF_STX | BPF_ATOMIC | BPF_DW:
+	case BPF_STX | BPF_PROBE_ATOMIC | BPF_B:
+	case BPF_STX | BPF_PROBE_ATOMIC | BPF_H:
 	case BPF_STX | BPF_PROBE_ATOMIC | BPF_W:
 	case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW:
-		if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
+		if (bpf_atomic_is_load_store(insn))
+			ret = emit_atomic_ld_st(insn, ctx);
+		else if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
 			ret = emit_lse_atomic(insn, ctx);
 		else
 			ret = emit_ll_sc_atomic(insn, ctx);
@@ -2669,7 +2750,8 @@ bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena)
 	switch (insn->code) {
 	case BPF_STX | BPF_ATOMIC | BPF_W:
 	case BPF_STX | BPF_ATOMIC | BPF_DW:
-		if (!cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
+		if (!bpf_atomic_is_load_store(insn) &&
+		    !cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
 			return false;
 	}
 	return true;

arch/s390/net/bpf_jit_comp.c

@@ -2919,10 +2919,16 @@ bool bpf_jit_supports_arena(void)
 
 bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena)
 {
-	/*
-	 * Currently the verifier uses this function only to check which
-	 * atomic stores to arena are supported, and they all are.
-	 */
+	if (!in_arena)
+		return true;
+	switch (insn->code) {
+	case BPF_STX | BPF_ATOMIC | BPF_B:
+	case BPF_STX | BPF_ATOMIC | BPF_H:
+	case BPF_STX | BPF_ATOMIC | BPF_W:
+	case BPF_STX | BPF_ATOMIC | BPF_DW:
+		if (bpf_atomic_is_load_store(insn))
+			return false;
+	}
 	return true;
 }
 

arch/x86/net/Makefile

@@ -6,5 +6,5 @@
 ifeq ($(CONFIG_X86_32),y)
         obj-$(CONFIG_BPF_JIT) += bpf_jit_comp32.o
 else
-        obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o
+        obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o bpf_timed_may_goto.o
 endif