0
点赞
收藏
分享

微信扫一扫

【原创】【kvm学习笔记】kvm内核代码——内存虚拟化

花海书香 2022-04-29 阅读 78
学习系统架构

  本文为我在学习kvm源码过程中的总结笔记，因个人能力有限，文中可能出现相关错误，请各位批评指正。
  本文发出时最新Linux内核版本为v5.18-rc3。

我的邮箱：szhou12@stu.pku.edu.cn

参考资料：
  [1]Linux：v5.16.20、v5.17.3
  [2]https://www.cnblogs.com/LoyenWang/p/13943005.html

0 前言

   linux5.17版本内核中引入了红黑树对memory slot进行组织管理，而在5.0~5.16版本及使用数组组织memmory slot进行组织。除了结构体以外，相关的内存分配函数也针对新的slot组织方式做出了调整。本文着重于分析5.16中kvm内核代码，最后再讨论5.17版本做出的改动。若无特殊说明，本文中的代码均来自Linux v5.16.20版本，所有涉及到具体架构的代码均来自 /arch/x86/。
  此外，本文仅涉及Linux内核中的kvm代码，不涉及qemu源码。

1 宏定义与结构体

  kvm内核中涉及到多种结构体定义以及一些宏定义，理顺其中的关系对于理解代码有着很重要的意义

1.1 kvm地址类型定义

  我们知道，Guest OS和Host OS都有自己的虚拟地址和物理地址，虚拟机会通过MMU找到它所认为的物理地址，而这个物理地址与宿主的虚拟地址又有一定的对应关系，宿主机的虚拟地址可以通过MMU访问物理内存。当然，也可以使用影子页表直接使用虚拟机的虚拟内存访问物理内存。
影子页表
  本文章主要讲述kvm_memory_slot及相关函数的代码，不涉及影子页表及其实现。
  在头文件vkm_types.h中，定义了以下六种地址类型：

// include/linux/kvm_types.h
/*
 * Address types:
 *
 *  gva - guest virtual address
 *  gpa - guest physical address
 *  gfn - guest frame number
 *  hva - host virtual address
 *  hpa - host physical address
 *  hfn - host frame number
 */

typedef unsigned long  gva_t;
typedef u64            gpa_t;
typedef u64            gfn_t;

#define GPA_INVALID	(~(gpa_t)0)

typedef unsigned long  hva_t;
typedef u64            hpa_t;
typedef u64            hfn_t;

gva_t： GVA，客户机虚拟地址
gpa_t： GPA，客户机物理地址
gfn_t： GFN，客户机页帧编号
hva_t： HVA，宿主机虚拟地址
hpa_t： HPA，宿主机物理地址
hfn_t： HFN， 宿主机页帧编号

1.2 struct kvm 结构体

  kvm结构体定义了一个kvm虚拟机的实体，包含虚拟机内相应的数据以及控制字段

// include/linux/kvm_host.h

struct kvm {
	...
	
	struct mm_struct *mm; /* userspace tied to this vm */
	struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM];
	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];

	...
};

  因为这个结构体包含众多变量，因此只摘出与内存管理相关的部分，此外，还有一些内存操作时所使用的的锁也没有记录进来。
struct mm_struct： 其中包含了struct vm_area_struct，指向一个进程的虚拟空间中的不同区域。
struct kvm_memslots： 该结构体可以理解为虚拟机上的内存插槽，其中的KVM_ADDRESS_SPACE_NUM默认定义为1。

// include/linux/kvm_host.h

#ifndef KVM_ADDRESS_SPACE_NUM
#define KVM_ADDRESS_SPACE_NUM	1
#endif

1.3 struct kvm_memslots结构体

// include/linux/kvm_host.h

/*
 * Note:
 * memslots are not sorted by id anymore, please use id_to_memslot()
 * to get the memslot by its id.
 */
struct kvm_memslots {
	u64 generation;
	/* The mapping table from slot id to the index in memslots[]. */
	short id_to_index[KVM_MEM_SLOTS_NUM];
	atomic_t last_used_slot;
	int used_slots;
	struct kvm_memory_slot memslots[];
};

  正如代码注释中所说，memslot是没有经过排序的，需要使用id_to_memslot()函数获得slot id和数组下标的对应关系。结构体中还有变量记录最后使用的slot和已使用的slot的数量。

atomic_t声明了一个具有原子操作特性的整数，详细信息可以查阅相关资料

1.4 struct kvm_memory_slot结构体

// include/linux/kvm_host.h

struct kvm_memory_slot {
	gfn_t base_gfn;
	unsigned long npages;
	unsigned long *dirty_bitmap;
	struct kvm_arch_memory_slot arch;
	unsigned long userspace_addr;
	u32 flags;
	short id;
	u16 as_id;
};

gfn_t base_gfn： 起始页帧
unsigned long npages： 这个slot的包含的页数（slot的大小）
dirty_bitmap： 脏页的位示图
arch： 与硬件架构相关的memory_slot结构体
unsigned long userspace_addr： 用户空间地址
u32 flags： 标志位
id： memslot的id值，呼应1.3中的id_to_index和id_to_memslot()
as_id： 地址空间（address space）的id值，可以理解为正在使用主板上的第几根插槽上插的内存（当然虚拟机没有主板）

1.5 struct kvm_userspace_memory_region结构体

// include/uapi/linux/kvm.h

/* for KVM_SET_USER_MEMORY_REGION */
struct kvm_userspace_memory_region {
	__u32 slot;
	__u32 flags;
	__u64 guest_phys_addr;
	__u64 memory_size; /* bytes */
	__u64 userspace_addr; /* start of the userspace allocated memory */
};

  该结构体存储在用户空间，供qemu使用，用于映射虚拟机物理地址与宿主机的虚拟地址。

1.6 各结构体之间的关系

1.7 kvm中flag标志的宏定义

// include/uapi/linux/kvm.h

/*
 * The bit 0 ~ bit 15 of kvm_memory_region::flags are visible for userspace,
 * other bits are reserved for kvm internal use which are defined in
 * include/linux/kvm_host.h.
 */
#define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
#define KVM_MEM_READONLY	(1UL << 1)

// include/linux/kvm.host.h

/*
 * The bit 16 ~ bit 31 of kvm_memory_region::flags are internally used
 * in kvm, other bits are visible for userspace which are defined in
 * include/linux/kvm_h.
 */
#define KVM_MEMSLOT_INVALID	(1UL << 16)

  目前一共定义了三个标志，分别为脏页、只读和非法。其中前两个标志放在uapi的文件夹下，是可以被用户空间获取到的。

1UL << 1 ：
U代表无符号数，L代表long类型，左移1位后，该数值为 0b000...0010

1.8 enum kvm_mr_change内存操作

// include/linux/kvm_host.h
/*
 * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations:
 * - create a new memory slot
 * - delete an existing memory slot
 * - modify an existing memory slot
 *   -- move it in the guest physical memory space
 *   -- just change its flags
 *
 * Since flags can be changed by some of these operations, the following
 * differentiation is the best we can do for __kvm_set_memory_region():
 */
enum kvm_mr_change {
	KVM_MR_CREATE,
	KVM_MR_DELETE,
	KVM_MR_MOVE,
	KVM_MR_FLAGS_ONLY,
};

  这个枚举类型声明了在ioctl中KVM_SET_USER_MEMORY_REGION分支下可以对内存进行的四种操作，分别是：
  1、创建一个新的slot
  2、删除一个已有的slot
  3、在客户机物理内存中移动一个slot
  4、修改客户机物理内存中slot的标志

1.9 linux定义的错误类型

// include/uapi/asm-generic/error-base.h

#define	EPERM		 1	/* Operation not permitted */
#define	ENOENT		 2	/* No such file or directory */
#define	ESRCH		 3	/* No such process */
#define	EINTR		 4	/* Interrupted system call */
#define	EIO		     5	/* I/O error */
#define	ENXIO		 6	/* No such device or address */
#define	E2BIG		 7	/* Argument list too long */
#define	ENOEXEC		 8	/* Exec format error */
#define	EBADF		 9	/* Bad file number */
#define	ECHILD		10	/* No child processes */
#define	EAGAIN		11	/* Try again */
#define	ENOMEM		12	/* Out of memory */
#define	EACCES		13	/* Permission denied */
#define	EFAULT		14	/* Bad address */
#define	ENOTBLK		15	/* Block device required */
#define	EBUSY		16	/* Device or resource busy */
#define	EEXIST		17	/* File exists */
#define	EXDEV		18	/* Cross-device link */
#define	ENODEV		19	/* No such device */
#define	ENOTDIR		20	/* Not a directory */
#define	EISDIR		21	/* Is a directory */
#define	EINVAL		22	/* Invalid argument */
#define	ENFILE		23	/* File table overflow */
#define	EMFILE		24	/* Too many open files */
#define	ENOTTY		25	/* Not a typewriter */
#define	ETXTBSY		26	/* Text file busy */
#define	EFBIG		27	/* File too large */
#define	ENOSPC		28	/* No space left on device */
#define	ESPIPE		29	/* Illegal seek */
#define	EROFS		30	/* Read-only file system */
#define	EMLINK		31	/* Too many links */
#define	EPIPE		32	/* Broken pipe */
#define	EDOM		33	/* Math argument out of domain of func */
#define	ERANGE		34	/* Math result not representable */

  函数在进行检查的时候会用到这些错误定义。

2 内存操作函数

2.1 kvm_vm_ioctl()

// virt/kvm/kvm_main.c

static long kvm_vm_ioctl(struct file *filp,
			   unsigned int ioctl, unsigned long arg)
{
	struct kvm *kvm = filp->private_data;
	void __user *argp = (void __user *)arg;
	int r;

	if (kvm->mm != current->mm || kvm->vm_dead)
		return -EIO;
	switch (ioctl) {
	
	...
	
	case KVM_SET_USER_MEMORY_REGION: {
		struct kvm_userspace_memory_region kvm_userspace_mem;

		r = -EFAULT;
		if (copy_from_user(&kvm_userspace_mem, argp,
						sizeof(kvm_userspace_mem)))
			goto out;

		r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem);
		break;
	}
	
	...
	
out:
	return r;
}

  kvm_vm_ioctl()函数是调用kvm的接口，一共有三个输入：
  struct file *filep： 传入kvm的文件指针，其file结构体中private指针指向代表该客户机的struct kvm结构体
  unsigned int ioctl： 传入io操作编号
  unsigned long arg： 传入用户参数的指针

  函数的运行流程如下图所示：
kvm_vm_ioctl
  函数在接收到传入参数后，跳转到KVM_SET_MEMORY_REGION分支，从用户空间读取参数填充kvm_userspace_memory_region结构体，之后调用kvm_vm_ioctl_set_memory_region()函数。

2.2 kvm_vm_ioctl_set_memory_region()

// virt/kvm/kvm_main.c

static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
					  struct kvm_userspace_memory_region *mem)
{
	if ((u16)mem->slot >= KVM_USER_MEM_SLOTS)
		return -EINVAL;

	return kvm_set_memory_region(kvm, mem);
}

  该函数传入kvm结构体和kvm_userspace_memory_region结构体，在验证传入slot值的有效性后调用kvm_set_memory_region()函数。
  其中KVM_USER_MEM_SLOTS的定义如下

// include/linux/kvm_host.h

#ifndef KVM_PRIVATE_MEM_SLOTS
#define KVM_PRIVATE_MEM_SLOTS 0
#endif

#define KVM_MEM_SLOTS_NUM SHRT_MAX
#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_PRIVATE_MEM_SLOTS)

// include/vdso/limits.h

#define USHRT_MAX	((unsigned short)~0U)
#define SHRT_MAX	((short)(USHRT_MAX >> 1))

  默认情况下，隐私页数量定义为0，KVM_USER_MEM_SLOTS即为short类型所表示的最大值。

2.3 kvm_set_memory_region()

// virt/kvm/kvm_main.c

int kvm_set_memory_region(struct kvm *kvm,
			  const struct kvm_userspace_memory_region *mem)
{
	int r;

	mutex_lock(&kvm->slots_lock);
	r = __kvm_set_memory_region(kvm, mem);
	mutex_unlock(&kvm->slots_lock);
	return r;
}

  这个函数在获取到kvm结构体中的slots_lock锁之后，调用__kvm_set_memory_region()函数。

2.4 __kvm_set_memory_region()

// virt/kvm/kvm_main.c

/*
 * Allocate some memory and give it an address in the guest physical address
 * space.
 *
 * Discontiguous memory is allowed, mostly for framebuffers.
 *
 * Must be called holding kvm->slots_lock for write.
 */
int __kvm_set_memory_region(struct kvm *kvm,
			    const struct kvm_userspace_memory_region *mem)
{
	struct kvm_memory_slot old, new;
	struct kvm_memory_slot *tmp;
	enum kvm_mr_change change;
	int as_id, id;
	int r;

	r = check_memory_region_flags(mem);
	if (r)
		return r;

	as_id = mem->slot >> 16;
	id = (u16)mem->slot;

	/* General sanity checks */
	if ((mem->memory_size & (PAGE_SIZE - 1)) ||
	    (mem->memory_size != (unsigned long)mem->memory_size))
		return -EINVAL;
	if (mem->guest_phys_addr & (PAGE_SIZE - 1))
		return -EINVAL;
	/* We can read the guest memory with __xxx_user() later on. */
	if ((mem->userspace_addr & (PAGE_SIZE - 1)) ||
	    (mem->userspace_addr != untagged_addr(mem->userspace_addr)) ||
	     !access_ok((void __user *)(unsigned long)mem->userspace_addr,
			mem->memory_size))
		return -EINVAL;
	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM)
		return -EINVAL;
	if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
		return -EINVAL;

	/*
	 * Make a full copy of the old memslot, the pointer will become stale
	 * when the memslots are re-sorted by update_memslots(), and the old
	 * memslot needs to be referenced after calling update_memslots(), e.g.
	 * to free its resources and for arch specific behavior.
	 */
	tmp = id_to_memslot(__kvm_memslots(kvm, as_id), id);
	if (tmp) {
		old = *tmp;
		tmp = NULL;
	} else {
		memset(&old, 0, sizeof(old));
		old.id = id;
	}

	if (!mem->memory_size)
		return kvm_delete_memslot(kvm, mem, &old, as_id);

	new.as_id = as_id;
	new.id = id;
	new.base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
	new.npages = mem->memory_size >> PAGE_SHIFT;
	new.flags = mem->flags;
	new.userspace_addr = mem->userspace_addr;

	if (new.npages > KVM_MEM_MAX_NR_PAGES)
		return -EINVAL;

	if (!old.npages) {
		change = KVM_MR_CREATE;
		new.dirty_bitmap = NULL;
	} else { /* Modify an existing slot. */
		if ((new.userspace_addr != old.userspace_addr) ||
		    (new.npages != old.npages) ||
		    ((new.flags ^ old.flags) & KVM_MEM_READONLY))
			return -EINVAL;

		if (new.base_gfn != old.base_gfn)
			change = KVM_MR_MOVE;
		else if (new.flags != old.flags)
			change = KVM_MR_FLAGS_ONLY;
		else /* Nothing to change. */
			return 0;

		/* Copy dirty_bitmap from the current memslot. */
		new.dirty_bitmap = old.dirty_bitmap;
	}

	if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
		/* Check for overlaps */
		kvm_for_each_memslot(tmp, __kvm_memslots(kvm, as_id)) {
			if (tmp->id == id)
				continue;
			if (!((new.base_gfn + new.npages <= tmp->base_gfn) ||
			      (new.base_gfn >= tmp->base_gfn + tmp->npages)))
				return -EEXIST;
		}
	}

	/* Allocate/free page dirty bitmap as needed */
	if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES))
		new.dirty_bitmap = NULL;
	else if (!new.dirty_bitmap && !kvm->dirty_ring_size) {
		r = kvm_alloc_dirty_bitmap(&new);
		if (r)
			return r;

		if (kvm_dirty_log_manual_protect_and_init_set(kvm))
			bitmap_set(new.dirty_bitmap, 0, new.npages);
	}

	r = kvm_set_memslot(kvm, mem, &new, as_id, change);
	if (r)
		goto out_bitmap;

	if (old.dirty_bitmap && !new.dirty_bitmap)
		kvm_destroy_dirty_bitmap(&old);
	return 0;

out_bitmap:
	if (new.dirty_bitmap && !old.dirty_bitmap)
		kvm_destroy_dirty_bitmap(&new);
	return r;
}
EXPORT_SYMBOL_GPL(__kvm_set_memory_region);

  这是kvm进行GPA到HVA映射的主要函数，其主要流程如下图所示：
__kvm_set_memory_region

  __kvm_set_memory_region()函数主要进行一些页对齐、内存溢出的检查，并根据内存使用情况设置本次操作的操作数，最终调用kvm_set_memslot()函数。

2.5 kvm_set_memslot()

static int kvm_set_memslot(struct kvm *kvm,
			   const struct kvm_userspace_memory_region *mem,
			   struct kvm_memory_slot *new, int as_id,
			   enum kvm_mr_change change)
{
	struct kvm_memory_slot *slot, old;
	struct kvm_memslots *slots;
	int r;

	/*
	 * Released in install_new_memslots.
	 *
	 * Must be held from before the current memslots are copied until
	 * after the new memslots are installed with rcu_assign_pointer,
	 * then released before the synchronize srcu in install_new_memslots.
	 *
	 * When modifying memslots outside of the slots_lock, must be held
	 * before reading the pointer to the current memslots until after all
	 * changes to those memslots are complete.
	 *
	 * These rules ensure that installing new memslots does not lose
	 * changes made to the previous memslots.
	 */
	mutex_lock(&kvm->slots_arch_lock);

	slots = kvm_dup_memslots(__kvm_memslots(kvm, as_id), change);
	if (!slots) {
		mutex_unlock(&kvm->slots_arch_lock);
		return -ENOMEM;
	}

	if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
		/*
		 * Note, the INVALID flag needs to be in the appropriate entry
		 * in the freshly allocated memslots, not in @old or @new.
		 */
		slot = id_to_memslot(slots, new->id);
		slot->flags |= KVM_MEMSLOT_INVALID;

		/*
		 * We can re-use the memory from the old memslots.
		 * It will be overwritten with a copy of the new memslots
		 * after reacquiring the slots_arch_lock below.
		 */
		slots = install_new_memslots(kvm, as_id, slots);

		/* From this point no new shadow pages pointing to a deleted,
		 * or moved, memslot will be created.
		 *
		 * validation of sp->gfn happens in:
		 *	- gfn_to_hva (kvm_read_guest, gfn_to_pfn)
		 *	- kvm_is_visible_gfn (mmu_check_root)
		 */
		kvm_arch_flush_shadow_memslot(kvm, slot);

		/* Released in install_new_memslots. */
		mutex_lock(&kvm->slots_arch_lock);

		/*
		 * The arch-specific fields of the memslots could have changed
		 * between releasing the slots_arch_lock in
		 * install_new_memslots and here, so get a fresh copy of the
		 * slots.
		 */
		kvm_copy_memslots(slots, __kvm_memslots(kvm, as_id));
	}

	/*
	 * Make a full copy of the old memslot, the pointer will become stale
	 * when the memslots are re-sorted by update_memslots(), and the old
	 * memslot needs to be referenced after calling update_memslots(), e.g.
	 * to free its resources and for arch specific behavior.  This needs to
	 * happen *after* (re)acquiring slots_arch_lock.
	 */
	slot = id_to_memslot(slots, new->id);
	if (slot) {
		old = *slot;
	} else {
		WARN_ON_ONCE(change != KVM_MR_CREATE);
		memset(&old, 0, sizeof(old));
		old.id = new->id;
		old.as_id = as_id;
	}

	/* Copy the arch-specific data, again after (re)acquiring slots_arch_lock. */
	memcpy(&new->arch, &old.arch, sizeof(old.arch));

	r = kvm_arch_prepare_memory_region(kvm, new, mem, change);
	if (r)
		goto out_slots;

	update_memslots(slots, new, change);
	slots = install_new_memslots(kvm, as_id, slots);

	kvm_arch_commit_memory_region(kvm, mem, &old, new, change);

	/* Free the old memslot's metadata.  Note, this is the full copy!!! */
	if (change == KVM_MR_DELETE)
		kvm_free_memslot(kvm, &old);

	kvfree(slots);
	return 0;

out_slots:
	if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
		slot = id_to_memslot(slots, new->id);
		slot->flags &= ~KVM_MEMSLOT_INVALID;
		slots = install_new_memslots(kvm, as_id, slots);
	} else {
		mutex_unlock(&kvm->slots_arch_lock);
	}
	kvfree(slots);
	return r;
}

  写不动了，勉强拿手画的表看看吧。
kvm_set_memslot

后记

  kvm的体系太庞大了，涉及到架构的部分还得对着硬件手册来学，实在写得累了，后面有机会再补充更详细的内容。5.17的对比也后面再说吧。

举报

相关推荐

kvm虚拟化

运维服务器linuxkvm虚拟化

KVM虚拟化

OpenStackkvmjavascriptlinux命令行系统/运维

[虚拟化] KVM QEMU KVM-QEM

虚拟化htmlJavaScript前端开发

【KVM虚拟化】· KVM中的网络

springjava后端原力计划

配置KVM虚拟化​

服务器虚拟化KVM运维

配置kvm虚拟化

centosyum源运维yyds干货盘点

配置KVM虚拟化

centos虚拟化Linux系统/运维

KVM虚拟化技术

虚拟化配置文件xmlLinux系统/运维

部署KVM虚拟化平台笔记

kotlinjava开发语言

虚拟化技术KVM（2）KVM虚机创建

kvm虚拟化云计算
0 条评论