Linux内核有什么之内存管理子系统有什么第四回 —— 小内存分配（2）
接前一篇文章：Linux内核有什么之内存管理子系统有什么第三回 —— 小内存分配（1）
本文内容参考：
内存分配不再神秘：深入剖析malloc函数实现原理与机制
系统调用与内存管理（sbrk、brk、mmap、munmap）
Linux系统调用详解（实现机制分析）
特此致谢！
二、小内存分配 —— brk与sbrk
本回开始结合代码，对于brk()和sbrk()进行详解。
1. brk源码解析
brk系统调用实现的入口是sys_brk函数，其代码在内核源码目录下的mm/mmap.c中，代码如下：
SYSCALL_DEFINE1(brk, unsigned long, brk)
{
unsigned long newbrk, oldbrk, origbrk;
struct mm_struct *mm = current->mm;
struct vm_area_struct *brkvma, *next = NULL;
unsigned long min_brk;
bool populate;
bool downgraded = false;
LIST_HEAD(uf);
MA_STATE(mas, &mm->mm_mt, 0, 0);
if (mmap_write_lock_killable(mm))
return -EINTR;
origbrk = mm->brk;
#ifdef CONFIG_COMPAT_BRK
/*
* CONFIG_COMPAT_BRK can still be overridden by setting
* randomize_va_space to 2, which will still cause mm->start_brk
* to be arbitrarily shifted
*/
if (current->brk_randomized)
min_brk = mm->start_brk;
else
min_brk = mm->end_data;
#else
min_brk = mm->start_brk;
#endif
if (brk < min_brk)
goto out;
/*
* Check against rlimit here. If this check is done later after the test
* of oldbrk with newbrk then it can escape the test and let the data
* segment grow beyond its set limit the in case where the limit is
* not page aligned -Ram Gupta
*/
if (check_data_rlimit(rlimit(RLIMIT_DATA), brk, mm->start_brk,
mm->end_data, mm->start_data))
goto out;
newbrk = PAGE_ALIGN(brk);
oldbrk = PAGE_ALIGN(mm->brk);
if (oldbrk == newbrk) {
mm->brk = brk;
goto success;
}
/*
* Always allow shrinking brk.
* do_brk_munmap() may downgrade mmap_lock to read.
*/
if (brk <= mm->brk) {
int ret;
/* Search one past newbrk */
mas_set(&mas, newbrk);
brkvma = mas_find(&mas, oldbrk);
if (!brkvma || brkvma->vm_start >= oldbrk)
goto out; /* mapping intersects with an existing non-brk vma. */
/*
* mm->brk must be protected by write mmap_lock.
* do_brk_munmap() may downgrade the lock, so update it
* before calling do_brk_munmap().
*/
mm->brk = brk;
ret = do_brk_munmap(&mas, brkvma, newbrk, oldbrk, &uf);
if (ret == 1) {
downgraded = true;
goto success;
} else if (!ret)
goto success;
mm->brk = origbrk;
goto out;
}
if (check_brk_limits(oldbrk, newbrk - oldbrk))
goto out;
/*
* Only check if the next VMA is within the stack_guard_gap of the
* expansion area
*/
mas_set(&mas, oldbrk);
next = mas_find(&mas, newbrk - 1 + PAGE_SIZE + stack_guard_gap);
if (next && newbrk + PAGE_SIZE > vm_start_gap(next))
goto out;
brkvma = mas_prev(&mas, mm->start_brk);
/* Ok, looks good - let it rip. */
if (do_brk_flags(&mas, brkvma, oldbrk, newbrk - oldbrk, 0) < 0)
goto out;
mm->brk = brk;
success:
populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0;
if (downgraded)
mmap_read_unlock(mm);
else
mmap_write_unlock(mm);
userfaultfd_unmap_complete(mm, &uf);
if (populate)
mm_populate(oldbrk, newbrk - oldbrk);
return brk;
out:
mmap_write_unlock(mm);
return origbrk;
}先来看SYSCALL_DEFINE1。
SYSCALL_DEFINE1的定义在include/linux/syscalls.h中，如下：
#define SYSCALL_DEFINE1(name, ...) SYSCALL_DEFINEx(1, _##name, __VA_ARGS__)
#define SYSCALL_DEFINE2(name, ...) SYSCALL_DEFINEx(2, _##name, __VA_ARGS__)
#define SYSCALL_DEFINE3(name, ...) SYSCALL_DEFINEx(3, _##name, __VA_ARGS__)
#define SYSCALL_DEFINE4(name, ...) SYSCALL_DEFINEx(4, _##name, __VA_ARGS__)
#define SYSCALL_DEFINE5(name, ...) SYSCALL_DEFINEx(5, _##name, __VA_ARGS__)
#define SYSCALL_DEFINE6(name, ...) SYSCALL_DEFINEx(6, _##name, __VA_ARGS__)SYSCALL_DEFINEx的定义在同文件中，如下：
#define SYSCALL_DEFINEx(x, sname, ...) \
SYSCALL_METADATA(sname, x, __VA_ARGS__) \
__SYSCALL_DEFINEx(x, sname, __VA_ARGS__)SYSCALL_METADATA的定义也在include/linux/syscalls.h中，如下：
#ifdef CONFIG_FTRACE_SYSCALLS
……
#define SYSCALL_METADATA(sname, nb, ...) \
static const char *types_##sname[] = { \
__MAP(nb,__SC_STR_TDECL,__VA_ARGS__) \
}; \
static const char *args_##sname[] = { \
__MAP(nb,__SC_STR_ADECL,__VA_ARGS__) \
}; \
SYSCALL_TRACE_ENTER_EVENT(sname); \
SYSCALL_TRACE_EXIT_EVENT(sname); \
static struct syscall_metadata __used \
__syscall_meta_##sname = { \
.name = "sys"#sname, \
.syscall_nr = -1, /* Filled in at boot */ \
.nb_args = nb, \
.types = nb ? types_##sname : NULL, \
.args = nb ? args_##sname : NULL, \
.enter_event = &event_enter_##sname, \
.exit_event = &event_exit_##sname, \
.enter_fields = LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \
}; \
static struct syscall_metadata __used \
__section("__syscalls_metadata") \
*__p_syscall_meta_##sname = &__syscall_meta_##sname;
static inline int is_syscall_trace_event(struct trace_event_call *tp_event)
{
return tp_event->class == &event_class_syscall_enter ||
tp_event->class == &event_class_syscall_exit;
}
#else
#define SYSCALL_METADATA(sname, nb, ...)这里为了简化问题、便于理解，可以暂时先假设没有配置CONFIG_FTRACE_SYSCALLS，即SYSCALL_METADATA宏无任何值。
__SYSCALL_DEFINEx的定义同样还是在include/linux/syscalls.h中，如下：
/*
* The asmlinkage stub is aliased to a function named __se_sys_*() which
* sign-extends 32-bit ints to longs whenever needed. The actual work is
* done within __do_sys_*().
*/
#ifndef __SYSCALL_DEFINEx
#define __SYSCALL_DEFINEx(x, name, ...) \
__diag_push(); \
__diag_ignore(GCC, 8, "-Wattribute-alias", \
"Type aliasing is used to sanitize syscall arguments");\
asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \
__attribute__((alias(__stringify(__se_sys##name)))); \
ALLOW_ERROR_INJECTION(sys##name, ERRNO); \
static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
asmlinkage long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \
asmlinkage long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \
{ \
long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__));\
__MAP(x,__SC_TEST,__VA_ARGS__); \
__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \
return ret; \
} \
__diag_pop(); \
static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
#endif /* __SYSCALL_DEFINEx */这里就不再向下继续深入展开了。
下一回开始对于sys_brk函数的代码内容进行解析。