[PATCH v2] cg: fix masking of lower 32 bits

The "and %r0, 0xffffffff' instruction does not actually mask off the
lower 32 bits as one would expect because 0xffffffff is interpreted as
-1 and then sign-extended to a 64-bit value, i.e. keeping all bits.

The "mov32 %r0, %r0" instruction does correctly mask off the lower 32
bits because it forced the value in %r0 to be a 32-bit value.

Signed-off-by: Kris Van Hees <[email protected]>
---
 include/bpf_asm.h | 11 +++++++++++
 libdtrace/dt_cg.c |  3 ++-
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/include/bpf_asm.h b/include/bpf_asm.h
index 152d2312..63987e01 100644
--- a/include/bpf_asm.h
+++ b/include/bpf_asm.h
@@ -36,6 +36,15 @@
 		.imm = 0						\
 	})
 
+#define BPF_ALU32_REG(op, dst, src)					\
+	((struct bpf_insn) {						\
+		.code = BPF_ALU | (op) | BPF_X,				\
+		.dst_reg = (dst),					\
+		.src_reg = (src),					\
+		.off = 0,						\
+		.imm = 0						\
+	})
+
 #define BPF_END_REG(sz, dst, dir)					\
 	((struct bpf_insn) {						\
 		.code = BPF_ALU | BPF_END | (dir),			\
@@ -68,6 +77,8 @@
 #define BPF_MOV_REG(dst, src)	BPF_ALU64_REG(BPF_MOV, dst, src)
 #define BPF_MOV_IMM(dst, val)	BPF_ALU64_IMM(BPF_MOV, dst, val)
 
+#define BPF_MOV32_REG(dst, src)	BPF_ALU32_REG(BPF_MOV, dst, src)
+
 #define BPF_LOAD(sz, dst, src, ofs)					\
 	((struct bpf_insn) {						\
 		.code = BPF_LDX | BPF_MEM | (sz),			\
diff --git a/libdtrace/dt_cg.c b/libdtrace/dt_cg.c
index a8f2c9d2..28b7e7c4 100644
--- a/libdtrace/dt_cg.c
+++ b/libdtrace/dt_cg.c
@@ -2757,7 +2757,8 @@ dt_cg_act_stack_sub(dt_pcb_t *pcb, dt_node_t *dnp, int reg, int off, dtrace_actk
 		dt_regset_xalloc(drp, BPF_REG_0);
 		emit(dlp,  BPF_CALL_HELPER(BPF_FUNC_get_current_pid_tgid));
 		dt_regset_free_args(drp);
-		emit(dlp,  BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xffffffff));
+		/* mov32 %r0, %r0 effectively masks the lower 32 bits. */
+		emit(dlp,  BPF_MOV32_REG(BPF_REG_0, BPF_REG_0));
 		emit(dlp,  BPF_STORE(BPF_DW, reg, off, BPF_REG_0));
 		dt_regset_free(drp, BPF_REG_0);
 	}
-- 
2.43.5