接前一篇文章： QEMU源码全解析 —— 内存虚拟化（14）
本文内容参考：
《 QEMU /KVM源码解析与应用》 —— 李强，机械工业出版社
浅谈QEMU Memory Region 与 Address Space
QEMU内存分析（一）：内存虚拟化关键结构体 - Edver - 博客园
特此致谢！
2. QEMU虚拟机内存初始化
上一回开始对于QEMU内存平坦化的核心函数 —— render_memory_region()进行深入解析，本回继续。为了便于理解和回顾，再次贴出render_memory_region函数代码，在softmmu/memory.c中，如下：
/* Render a memory region into the global view. Ranges in @view obscure
* ranges in @mr.
*/
static void render_memory_region(FlatView *view,
MemoryRegion *mr,
Int128 base,
AddrRange clip,
bool readonly,
bool nonvolatile)
{
MemoryRegion *subregion;
unsigned i;
hwaddr offset_in_region;
Int128 remain;
Int128 now;
FlatRange fr;
AddrRange tmp;
if (!mr->enabled) {
return;
}
int128_addto(&base, int128_make64(mr->addr));
readonly |= mr->readonly;
nonvolatile |= mr->nonvolatile;
tmp = addrrange_make(base, mr->size);
if (!addrrange_intersects(tmp, clip)) {
return;
}
clip = addrrange_intersection(tmp, clip);
if (mr->alias) {
int128_subfrom(&base, int128_make64(mr->alias->addr));
int128_subfrom(&base, int128_make64(mr->alias_offset));
render_memory_region(view, mr->alias, base, clip,
readonly, nonvolatile);
return;
}
/* Render subregions in priority order. */
QTAILQ_FOREACH(subregion, &mr->subregions, subregions_link) {
render_memory_region(view, subregion, base, clip,
readonly, nonvolatile);
}
if (!mr->terminates) {
return;
}
offset_in_region = int128_get64(int128_sub(clip.start, base));
base = clip.start;
remain = clip.size;
fr.mr = mr;
fr.dirty_log_mask = memory_region_get_dirty_log_mask(mr);
fr.romd_mode = mr->romd_mode;
fr.readonly = readonly;
fr.nonvolatile = nonvolatile;
/* Render the region itself into any gaps left by the current view. */
for (i = 0; i < view->nr && int128_nz(remain); ++i) {
if (int128_ge(base, addrrange_end(view->ranges[i].addr))) {
continue;
}
if (int128_lt(base, view->ranges[i].addr.start)) {
now = int128_min(remain,
int128_sub(view->ranges[i].addr.start, base));
fr.offset_in_region = offset_in_region;
fr.addr = addrrange_make(base, now);
flatview_insert(view, i, &fr);
++i;
int128_addto(&base, now);
offset_in_region += int128_get64(now);
int128_subfrom(&remain, now);
}
now = int128_sub(int128_min(int128_add(base, remain),
addrrange_end(view->ranges[i].addr)),
base);
int128_addto(&base, now);
offset_in_region += int128_get64(now);
int128_subfrom(&remain, now);
}
if (int128_nz(remain)) {
fr.offset_in_region = offset_in_region;
fr.addr = addrrange_make(base, remain);
flatview_insert(view, i, &fr);
}
}上一回讲到：
这样比较抽象、不易理解。这里举一实际，结合实例就容易理解代码了。
假设待展开的根MemoryRegion为下图中的MemoryRegion 1，2~5为其对应的子MemoryRegion（4、5为MemoryRegion 1的孙Region）。
首先将MemoryRegion 1作为render_memory_region函数的第2个参数，然后递归调用自己，展开子Region 2~5。
/* Render subregions in priority order. */
QTAILQ_FOREACH(subregion, &mr->subregions, subregions_link) {
render_memory_region(view, subregion, base, clip,
readonly, nonvolatile);
}调用关系如下图所示：
只有当最底层的4、5展开之后，第3个render_memory_region函数才能返回。同样，只有当2、3展开之后，第1个render_memory_region函数才能返回。
由于需要考虑到各种情况，render_memory_region函数很复杂。为了更好地理解该函数，在此通过举例来对于其进行解析。假设有一个MemoryRegion mr1以及虚拟机地址空间。mr1有一个子MemoryRegion mr2，虚拟机物理地址空间已经展开了两个FlatRange，分别是fr1和fr2。如下图所示：
假设需要将mr1平坦化，首先要计算出mr1所表示的地址和clip的交界。这里假设clip的值最开始是(0, UINT64_MAX)，则新计算出来一个clip，这个clip实际上就是mr1所代表的范围。对应代码片段如下：
int128_addto(&base, int128_make64(mr->addr));
readonly |= mr->readonly;
nonvolatile |= mr->nonvolatile;
tmp = addrrange_make(base, mr->size);
if (!addrrange_intersects(tmp, clip)) {
return;
}
clip = addrrange_intersection(tmp, clip);对照着MemoryRegion的定义以及render_memory_region函数的参数clip的说明来看。
/** MemoryRegion:
*
* A struct representing a memory region.
*/
struct MemoryRegion {
Object parent_obj;
/* private: */
/* The following fields should fit in a cache line */
bool romd_mode;
bool ram;
bool subpage;
bool readonly; /* For RAM regions */
bool nonvolatile;
bool rom_device;
bool flush_coalesced_mmio;
uint8_t dirty_log_mask;
bool is_iommu;
RAMBlock *ram_block;
Object *owner;
/* owner as TYPE_DEVICE. Used for re-entrancy checks in MR access hotpath */
DeviceState *dev;
const MemoryRegionOps *ops;
void *opaque;
MemoryRegion *container;
int mapped_via_alias; /* Mapped via an alias, container might be NULL */
Int128 size;
hwaddr addr;
void (*destructor)(MemoryRegion *mr);
uint64_t align;
bool terminates;
bool ram_device;
bool enabled;
bool warning_printed; /* For reservations */
uint8_t vga_logging_count;
MemoryRegion *alias;
hwaddr alias_offset;
int32_t priority;
QTAILQ_HEAD(, MemoryRegion) subregions;
QTAILQ_ENTRY(MemoryRegion) subregions_link;
QTAILQ_HEAD(, CoalescedMemoryRange) coalesced;
const char *name;
unsigned ioeventfd_nb;
MemoryRegionIoeventfd *ioeventfds;
RamDiscardManager *rdm; /* Only for RAM */
/* For devices designed to perform re-entrant IO into their own IO MRs */
bool disable_reentrancy_guard;
};平坦化过程针对的是叶子节点，因此如果是alias，则需要找到实际的mr。对应代码片段如下：
if (mr->alias) {
int128_subfrom(&base, int128_make64(mr->alias->addr));
int128_subfrom(&base, int128_make64(mr->alias_offset));
render_memory_region(view, mr->alias, base, clip,
readonly, nonvolatile);
return;
}
render_memory_region函数更多内容的解析，请看下回。
