机器word操作的原子性

GCC 4.8还是对下面的问题做了修正
材料来源


有些机器（编译器）修改结构成员域是以word为单位的，如果word包括多个成员，又有多个thread对多个成员同时操作，就会发生race condition。

以下面的结构为例，IA-64修改full，是以8字节位单位（即把lock也读入写回）。假设两个线程如下场景：
T1 读入full
T2 修改lock
T1 修改full，写回（实际也把lock的原值写回），导致T2写入lock被破坏

struct btrfs_block_rsv { u64 size; u64 reserved; struct btrfs_space_info *space_info; spinlock_t lock; unsigned int full:1; };

令人恐怖的是
"C does not provide such guarantee, nor can you reliably lock different structure fields with different locks if they share naturally aligned word-size memory regions. The C++11 memory model would guarantee this, but that's not implemented nor do you build the kernel with a C++11 compiler."