[CRIU] [PATCH 11/11] mem: Delayed vma/pr restore (v2)

Kirill Tkhai ktkhai at virtuozzo.com
Mon May 15 09:16:57 PDT 2017


After this commit (previous is OK) I got the following:

root at pro:/home/kirill/criu# ./test/zdtm.py run -t zdtm/static/maps06
=== Run 1/1 ================ zdtm/static/maps06

========================= Run zdtm/static/maps06 in h ==========================
Start test
./maps06 --pidfile=maps06.pid --outfile=maps06.out --filename=maps06.test
Run criu dump
Run criu restore
=[log]=> dump/zdtm/static/maps06/27/1/restore.log
------------------------ grep Error ------------------------
(00.006707)     27: Opening 0x007fcd1c7f4000-0x007fcd1c7f5000 0000000000000000 (41) vma
(00.006709)     27: Opening 0x007fcd1c7f6000-0x007fcd1c7f7000 0000000000000000 (41) vma
(00.006711)     27: Opening 0x007fcd1c7f8000-0x007fcd1c7f9000 0000000000000000 (41) vma
(00.006714)     27: Opening 0x007fcd1c7fa000-0x007fcd1c7fb000 0000000000000000 (41) vma
(00.006718)     27: Error (criu/files-reg.c:1567): Can't open file home/kirill/criu/test/zdtm/static/maps06.test on restore: Too many open files
(00.006721)     27: Error (criu/files-reg.c:1506): Can't open file home/kirill/criu/test/zdtm/static/maps06.test: Too many open files
(00.006722)     27: Error (criu/mem.c:1113): `- Can't open vma
(00.006761) Error (criu/cr-restore.c:2366): Restoring FAILED.
------------------------ ERROR OVER ------------------------
################# Test zdtm/static/maps06 FAIL at CRIU restore #################
##################################### FAIL #####################################

Also, the open files list looks like:

root at pro:/home/kirill/github/criu# ls /proc/5637/fd -l
P8QP>P3P> 0
lrwx------ 1 root root 64 P<P0P9 15 18:56 0 -> /dev/null
l-wx------ 1 root root 64 P<P0P9 15 18:56 1 -> /home/kirill/criu/test/zdtm/static/maps06.out.inprogress
lrwx------ 1 root root 64 P<P0P9 15 18:56 10 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 100 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 1000 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 1001 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 1002 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 1003 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 1004 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 1005 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 1006 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 1007 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 1008 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 1009 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 101 -> /home/kirill/criu/test/zdtm/static/maps06.test
...
lrwx------ 1 root root 64 P<P0P9 15 18:56 99 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 990 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 991 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 992 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 993 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 994 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 995 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 996 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 997 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 998 -> /home/kirill/criu/test/zdtm/static/maps06.test
lrwx------ 1 root root 64 P<P0P9 15 18:56 999 -> /home/kirill/criu/test/zdtm/static/maps06.test

On 11.05.2017 12:13, Pavel Emelyanov wrote:
> Performance experiments show, that we spend (relatively) a lot of time
> mremap-ing areas from premap area into their proper places. This time
> depends on the task being restored, but for those with many vmas this
> can be up to 20%.
> 
> The thing is that premapping is only needed to restore cow pages since
> we don't have any API in the kernel to share a page between two or more
> anonymous vmas. For non-cowing areas we map mmap() them directly in
> place. But for such cases we'll also need to restore the page's contents
> also from the pie code.
> 
> Doing the whole page-read code from PIE is way too complex (for now), so
> the proposal is to optimize the case when we have a single local pagemap
> layer. This is what pr.pieok boolean stands for.
> 
> v2:
> * Fixed ARM compiling (vma addresses formatting)
> * Unused tail of premapped area was left in task after restore
> * Preadv-ing pages in restorer context worked on corrupted iovs
>   due to mistakes in pointer arithmetics
> * AIO mapping skipped at premap wasn't mapped in pie
> * Growsdown VMAs should sometimes (when they are "guarded" by
>   previous VMA and guard page's contents cannot be restored in
>   place) be premmaped
> * Always premmap for lazy-pages restore
> 
> Signed-off-by: Pavel Emelyanov <xemul at virtuozzo.com>
> ---
>  criu/cr-restore.c       |  1 +
>  criu/include/pagemap.h  |  6 ++++
>  criu/include/restorer.h | 12 +++++++
>  criu/include/rst_info.h |  2 ++
>  criu/mem.c              | 94 ++++++++++++++++++++++++++++++++++++++++++++++---
>  criu/pagemap.c          | 35 ++++++++++++++++--
>  criu/pie/restorer.c     | 52 +++++++++++++++++++++++++--
>  criu/pstree.c           |  1 +
>  8 files changed, 195 insertions(+), 8 deletions(-)
> 
> diff --git a/criu/cr-restore.c b/criu/cr-restore.c
> index 66a5e91..63c86e8 100644
> --- a/criu/cr-restore.c
> +++ b/criu/cr-restore.c
> @@ -3477,6 +3477,7 @@ static int sigreturn_restore(pid_t pid, struct task_restore_args *task_args, uns
>  	RST_MEM_FIXUP_PPTR(task_args->helpers);
>  	RST_MEM_FIXUP_PPTR(task_args->zombies);
>  	RST_MEM_FIXUP_PPTR(task_args->seccomp_filters);
> +	RST_MEM_FIXUP_PPTR(task_args->vma_ios);
>  
>  	if (core->tc->has_seccomp_mode)
>  		task_args->seccomp_mode = core->tc->seccomp_mode;
> diff --git a/criu/include/pagemap.h b/criu/include/pagemap.h
> index aa3c4aa..08633ef 100644
> --- a/criu/include/pagemap.h
> +++ b/criu/include/pagemap.h
> @@ -58,6 +58,9 @@ struct page_read {
>  	int (*maybe_read_page)(struct page_read *pr, unsigned long vaddr,
>  			       int nr, void *buf, unsigned flags);
>  
> +	/* Whether or not pages can be read in PIE code */
> +	bool pieok;
> +
>  	/* Private data of reader */
>  	struct cr_img *pmi;
>  	struct cr_img *pi;
> @@ -104,8 +107,11 @@ extern int open_page_read(int pid, struct page_read *, int pr_flags);
>  extern int open_page_read_at(int dfd, int pid, struct page_read *pr,
>  		int pr_flags);
>  
> +struct task_restore_args;
> +
>  int pagemap_enqueue_iovec(struct page_read *pr, void *buf,
>  			      unsigned long len, struct list_head *to);
> +int pagemap_render_iovec(struct list_head *from, struct task_restore_args *ta);
>  
>  /*
>   * Create a shallow copy of page_read object.
> diff --git a/criu/include/restorer.h b/criu/include/restorer.h
> index 87de026..1866bbd 100644
> --- a/criu/include/restorer.h
> +++ b/criu/include/restorer.h
> @@ -102,6 +102,14 @@ struct thread_restore_args {
>  
>  typedef long (*thread_restore_fcall_t) (struct thread_restore_args *args);
>  
> +struct restore_vma_io {
> +	int nr_iovs;
> +	loff_t off;
> +	struct iovec iovs[0];
> +};
> +
> +#define RIO_SIZE(niovs)	(sizeof(struct restore_vma_io) + (niovs) * sizeof(struct iovec))
> +
>  struct task_restore_args {
>  	struct thread_restore_args	*t;			/* thread group leader */
>  
> @@ -124,6 +132,10 @@ struct task_restore_args {
>  	VmaEntry			*vmas;
>  	unsigned int			vmas_n;
>  
> +	int				vma_ios_fd;
> +	struct restore_vma_io		*vma_ios;
> +	unsigned int			vma_ios_n;
> +
>  	struct restore_posix_timer	*posix_timers;
>  	unsigned int			posix_timers_n;
>  
> diff --git a/criu/include/rst_info.h b/criu/include/rst_info.h
> index 92dfc9d..c3dbe2d 100644
> --- a/criu/include/rst_info.h
> +++ b/criu/include/rst_info.h
> @@ -39,6 +39,8 @@ struct rst_info {
>  
>  	struct vm_area_list	vmas;
>  	struct _MmEntry		*mm;
> +	struct list_head	vma_io;
> +	unsigned int		pages_img_id;
>  
>  	u32			cg_set;
>  
> diff --git a/criu/mem.c b/criu/mem.c
> index b4f9990..942d5d9 100644
> --- a/criu/mem.c
> +++ b/criu/mem.c
> @@ -741,8 +741,34 @@ static int premap_private_vma(struct pstree_item *t, struct vma_area *vma, void
>  	return 0;
>  }
>  
> +static inline bool vma_force_premap(struct vma_area *vma, struct list_head *head)
> +{
> +	/*
> +	 * Growsdown VMAs always have one guard page at the
> +	 * beginning and sometimes this page contains data.
> +	 * In case the VMA is premmaped, we premmap one page
> +	 * larger VMA. In case of in place restore we can only
> +	 * do this if the VMA in question is not "guarded" by
> +	 * some other VMA.
> +	 */
> +	if (vma->e->flags & MAP_GROWSDOWN) {
> +		if (vma->list.prev != head) {
> +			struct vma_area *prev;
> +
> +			prev = list_entry(vma->list.prev, struct vma_area, list);
> +			if (prev->e->end == vma->e->start) {
> +				pr_debug("Force premmap for 0x%"PRIx64":0x%"PRIx64"\n",
> +						vma->e->start, vma->e->end);
> +				return true;
> +			}
> +		}
> +	}
> +
> +	return false;
> +}
> +
>  static int premap_priv_vmas(struct pstree_item *t, struct vm_area_list *vmas,
> -		void *at, struct page_read *pr)
> +		void **at, struct page_read *pr)
>  {
>  	struct vma_area *vma;
>  	unsigned long pstart = 0;
> @@ -760,7 +786,14 @@ static int premap_priv_vmas(struct pstree_item *t, struct vm_area_list *vmas,
>  		if (!vma_area_is_private(vma, kdat.task_size))
>  			continue;
>  
> -		ret = premap_private_vma(t, vma, &at);
> +		if (vma->pvma == NULL && pr->pieok && !vma_force_premap(vma, &vmas->h))
> +			/*
> +			 * VMA in question is not shared with anyone. We'll
> +			 * restore it with its contents in restorer.
> +			 */
> +			continue;
> +
> +		ret = premap_private_vma(t, vma, at);
>  		if (ret < 0)
>  			break;
>  	}
> @@ -773,6 +806,7 @@ static int restore_priv_vma_content(struct pstree_item *t, struct page_read *pr)
>  	struct vma_area *vma;
>  	int ret = 0;
>  	struct list_head *vmas = &rsti(t)->vmas.h;
> +	struct list_head *vma_io = &rsti(t)->vma_io;
>  
>  	unsigned int nr_restored = 0;
>  	unsigned int nr_shared = 0;
> @@ -787,6 +821,7 @@ static int restore_priv_vma_content(struct pstree_item *t, struct page_read *pr)
>  	}
>  
>  	vma = list_first_entry(vmas, struct vma_area, list);
> +	rsti(t)->pages_img_id = pr->pages_img_id;
>  
>  	/*
>  	 * Read page contents.
> @@ -839,6 +874,28 @@ static int restore_priv_vma_content(struct pstree_item *t, struct page_read *pr)
>  				goto err_addr;
>  			}
>  
> +			if (!vma_area_is(vma, VMA_PREMMAPED)) {
> +				unsigned long len = min_t(unsigned long,
> +						(nr_pages - i) * PAGE_SIZE,
> +						vma->e->end - va);
> +
> +				if (pagemap_enqueue_iovec(pr, (void *)va, len, vma_io))
> +					return -1;
> +
> +				pr->skip_pages(pr, len);
> +
> +				va += len;
> +				len >>= PAGE_SHIFT;
> +				nr_restored += len;
> +				i += len - 1;
> +				pr_debug("Enqueue page-read\n");
> +				continue;
> +			}
> +
> +			/*
> +			 * Otherwise to the COW restore
> +			 */
> +
>  			off = (va - vma->e->start) / PAGE_SIZE;
>  			p = decode_pointer((off) * PAGE_SIZE +
>  					vma->premmaped_addr);
> @@ -974,7 +1031,7 @@ int prepare_mappings(struct pstree_item *t)
>  
>  	pr.advance(&pr); /* shift to the 1st iovec */
>  
> -	ret = premap_priv_vmas(t, vmas, addr, &pr);
> +	ret = premap_priv_vmas(t, vmas, &addr, &pr);
>  	if (ret < 0)
>  		goto out;
>  
> @@ -991,6 +1048,23 @@ int prepare_mappings(struct pstree_item *t)
>  					old_premmapped_addr, old_premmapped_len);
>  	}
>  
> +	/*
> +	 * Not all VMAs were premmaped. Find out the unused tail of the
> +	 * premapped area and unmap it.
> +	 */
> +	old_premmapped_len = addr - rsti(t)->premmapped_addr;
> +	if (old_premmapped_len < rsti(t)->premmapped_len) {
> +		unsigned long tail;
> +
> +		tail = rsti(t)->premmapped_len - old_premmapped_len;
> +		ret = munmap(addr, tail);
> +		if (ret < 0)
> +			pr_perror("Unable to unmap %p(%lx)", addr, tail);
> +		rsti(t)->premmapped_len = old_premmapped_len;
> +		pr_info("Shrunk premap area to %p(%lx)\n",
> +				rsti(t)->premmapped_addr, rsti(t)->premmapped_len);
> +	}
> +
>  out:
>  	return ret;
>  }
> @@ -1044,6 +1118,18 @@ int open_vmas(struct pstree_item *t)
>  	return 0;
>  }
>  
> +static int prepare_vma_ios(struct pstree_item *t, struct task_restore_args *ta)
> +{
> +	struct cr_img *pages;
> +
> +	pages = open_image(CR_FD_PAGES, O_RSTR, rsti(t)->pages_img_id);
> +	if (!pages)
> +		return -1;
> +
> +	ta->vma_ios_fd = img_raw_fd(pages);
> +	return pagemap_render_iovec(&rsti(t)->vma_io, ta);
> +}
> +
>  int prepare_vmas(struct pstree_item *t, struct task_restore_args *ta)
>  {
>  	struct vma_area *vma;
> @@ -1069,6 +1155,6 @@ int prepare_vmas(struct pstree_item *t, struct task_restore_args *ta)
>  			vma_premmaped_start(vme) = vma->premmaped_addr;
>  	}
>  
> -	return 0;
> +	return prepare_vma_ios(t, ta);
>  }
>  
> diff --git a/criu/pagemap.c b/criu/pagemap.c
> index dcc1332..d770e81 100644
> --- a/criu/pagemap.c
> +++ b/criu/pagemap.c
> @@ -11,7 +11,8 @@
>  #include "servicefd.h"
>  #include "pagemap.h"
>  #include "page-xfer.h"
> -
> +#include "restorer.h"
> +#include "rst-malloc.h"
>  #include "fault-injection.h"
>  #include "xmalloc.h"
>  #include "protobuf.h"
> @@ -309,6 +310,32 @@ static int enqueue_async_iov(struct page_read *pr, void *buf,
>  	return 0;
>  }
>  
> +int pagemap_render_iovec(struct list_head *from, struct task_restore_args *ta)
> +{
> +	struct page_read_iov *piov;
> +
> +	ta->vma_ios = (struct restore_vma_io *)rst_mem_align_cpos(RM_PRIVATE);
> +	ta->vma_ios_n = 0;
> +
> +	list_for_each_entry(piov, from, l) {
> +		struct restore_vma_io *rio;
> +
> +		pr_info("`- render %d iovs (%p:%zd...)\n", piov->nr,
> +				piov->to[0].iov_base, piov->to[0].iov_len);
> +		rio = rst_mem_alloc(RIO_SIZE(piov->nr), RM_PRIVATE);
> +		if (!rio)
> +			return -1;
> +
> +		rio->nr_iovs = piov->nr;
> +		rio->off = piov->from;
> +		memcpy(rio->iovs, piov->to, piov->nr * sizeof(struct iovec));
> +
> +		ta->vma_ios_n++;
> +	}
> +
> +	return 0;
> +}
> +
>  int pagemap_enqueue_iovec(struct page_read *pr, void *buf,
>  			      unsigned long len, struct list_head *to)
>  {
> @@ -795,6 +822,7 @@ int open_page_read_at(int dfd, int pid, struct page_read *pr, int pr_flags)
>  	pr->bunch.iov_len = 0;
>  	pr->bunch.iov_base = NULL;
>  	pr->pmes = NULL;
> +	pr->pieok = false;
>  
>  	pr->pmi = open_image_at(dfd, i_typ, O_RSTR, (long)pid);
>  	if (!pr->pmi)
> @@ -836,8 +864,11 @@ int open_page_read_at(int dfd, int pid, struct page_read *pr, int pr_flags)
>  		pr->maybe_read_page = maybe_read_page_img_cache;
>  	else if (remote)
>  		pr->maybe_read_page = maybe_read_page_remote;
> -	else
> +	else {
>  		pr->maybe_read_page = maybe_read_page_local;
> +		if (!pr->parent && !opts.lazy_pages)
> +			pr->pieok = true;
> +	}
>  
>  	pr_debug("Opened %s page read %u (parent %u)\n",
>  		 remote ? "remote" : "local", pr->id,
> diff --git a/criu/pie/restorer.c b/criu/pie/restorer.c
> index 9852d77..98c81f3 100644
> --- a/criu/pie/restorer.c
> +++ b/criu/pie/restorer.c
> @@ -616,6 +616,10 @@ static unsigned long restore_mapping(VmaEntry *vma_entry)
>  	if (vma_entry_is(vma_entry, VMA_ANON_SHARED) && (vma_entry->fd != -1UL))
>  		flags &= ~MAP_ANONYMOUS;
>  
> +	/* See comment in premap_private_vma() for this flag change */
> +	if (vma_entry_is(vma_entry, VMA_AREA_AIORING))
> +		flags |= MAP_ANONYMOUS;
> +
>  	/* A mapping of file with MAP_SHARED is up to date */
>  	if (vma_entry->fd == -1 || !(vma_entry->flags & MAP_SHARED))
>  		prot |= PROT_WRITE;
> @@ -1156,7 +1160,7 @@ long __export_restore_task(struct task_restore_args *args)
>  	int i, k;
>  	VmaEntry *vma_entry;
>  	unsigned long va;
> -
> +	struct restore_vma_io *rio;
>  	struct rt_sigframe *rt_sigframe;
>  	struct prctl_mm_map prctl_map;
>  	unsigned long new_sp;
> @@ -1265,7 +1269,8 @@ long __export_restore_task(struct task_restore_args *args)
>  	for (i = 0; i < args->vmas_n; i++) {
>  		vma_entry = args->vmas + i;
>  
> -		if (!vma_entry_is(vma_entry, VMA_AREA_REGULAR))
> +		if (!vma_entry_is(vma_entry, VMA_AREA_REGULAR) &&
> +				!vma_entry_is(vma_entry, VMA_AREA_AIORING))
>  			continue;
>  
>  		if (vma_entry_is(vma_entry, VMA_PREMMAPED))
> @@ -1279,6 +1284,49 @@ long __export_restore_task(struct task_restore_args *args)
>  		}
>  	}
>  
> +	/*
> +	 * Now read the contents (if any)
> +	 */
> +
> +	rio = args->vma_ios;
> +	for (i = 0; i < args->vma_ios_n; i++) {
> +		struct iovec *iovs = rio->iovs;
> +		int nr = rio->nr_iovs;
> +		ssize_t r;
> +
> +		while (nr) {
> +			pr_debug("Preadv %lx:%d... (%d iovs)\n",
> +					(unsigned long)iovs->iov_base,
> +					(int)iovs->iov_len, nr);
> +			r = sys_preadv(args->vma_ios_fd, iovs, nr, rio->off);
> +			if (r < 0) {
> +				pr_err("Can't read pages data (%d)\n", (int)r);
> +				goto core_restore_end;
> +			}
> +
> +			pr_debug("`- returned %ld\n", (long)r);
> +			rio->off += r;
> +			/* Advance the iovecs */
> +			do {
> +				if (iovs->iov_len <= r) {
> +					pr_debug("   `- skip pagemap\n");
> +					r -= iovs->iov_len;
> +					iovs++;
> +					nr--;
> +					continue;
> +				}
> +
> +				iovs->iov_base += r;
> +				iovs->iov_len -= r;
> +				break;
> +			} while (nr > 0);
> +		}
> +
> +		rio = ((void *)rio) + RIO_SIZE(rio->nr_iovs);
> +	}
> +
> +	sys_close(args->vma_ios_fd);
> +
>  #ifdef CONFIG_VDSO
>  	/*
>  	 * Proxify vDSO.
> diff --git a/criu/pstree.c b/criu/pstree.c
> index 2cc0844..bbad67d 100644
> --- a/criu/pstree.c
> +++ b/criu/pstree.c
> @@ -228,6 +228,7 @@ struct pstree_item *__alloc_pstree_item(bool rst, int level)
>  			return NULL;
>  		memset(item, 0, sz);
>  		vm_area_list_init(&rsti(item)->vmas);
> +		INIT_LIST_HEAD(&rsti(item)->vma_io);
>  		/*
>  		 * On restore we never expand pid level,
>  		 * so allocate them all at once.
> 


More information about the CRIU mailing list