mem: Delayed vma/pr restore (v2)

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@virtuozzo.com>
Signed-off-by: Andrei Vagin <avagin@virtuozzo.com>

criu/cr-restore.c

@@ -3136,6 +3136,7 @@ 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;

criu/include/pagemap.h

@@ -52,6 +52,9 @@ struct page_read {
 	int (*sync)(struct page_read *pr);
 	int (*seek_pagemap)(struct page_read *pr, unsigned long vaddr);
 
+	/* Whether or not pages can be read in PIE code */
+	bool pieok;
+
 	/* Private data of reader */
 	struct cr_img *pmi;
 	struct cr_img *pi;
@@ -95,8 +98,11 @@ 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);
 
 extern int dedup_one_iovec(struct page_read *pr, unsigned long base,
 			   unsigned long len);

criu/include/restorer.h

@@ -101,6 +101,14 @@ 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 */
 
@@ -121,6 +129,10 @@ 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;
 

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;
 

criu/mem.c

@@ -710,8 +710,34 @@ 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;
@@ -729,7 +755,14 @@ 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;
 	}
@@ -742,6 +775,7 @@ 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;
@@ -750,6 +784,7 @@ static int restore_priv_vma_content(struct pstree_item *t, struct page_read *pr)
 	unsigned long va;
 
 	vma = list_first_entry(vmas, struct vma_area, list);
+	rsti(t)->pages_img_id = pr->pages_img_id;
 
 	/*
 	 * Read page contents.
@@ -791,6 +826,28 @@ 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);
@@ -925,7 +982,7 @@ 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;
 
@@ -942,6 +999,23 @@ 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;
 }
@@ -995,6 +1069,18 @@ 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;
@@ -1020,6 +1106,6 @@ 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);
 }
 

criu/pagemap.c

@@ -10,7 +10,8 @@
 #include "cr_options.h"
 #include "servicefd.h"
 #include "pagemap.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)
 {
@@ -641,6 +668,7 @@ 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)
@@ -673,6 +701,8 @@ int open_page_read_at(int dfd, int pid, struct page_read *pr, int pr_flags)
 	pr->sync = process_async_reads;
 	pr->seek_pagemap = seek_pagemap;
 	pr->id = ids++;
+	if (!pr->parent)
+		pr->pieok = true;
 
 	pr_debug("Opened page read %u (parent %u)\n",
 			pr->id, pr->parent ? pr->parent->id : 0);

criu/pie/restorer.c

@@ -595,6 +595,10 @@ 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;
@@ -1082,7 +1086,7 @@ long __export_restore_task(struct task_restore_args *args)
 	int i;
 	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;
@@ -1179,7 +1183,8 @@ 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))
@@ -1193,6 +1198,49 @@ 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.

criu/pstree.c

@@ -209,6 +209,7 @@ struct pstree_item *__alloc_pstree_item(bool rst)
 
 		memset(item, 0, sz);
 		vm_area_list_init(&rsti(item)->vmas);
+		INIT_LIST_HEAD(&rsti(item)->vma_io);
 		item->pid = (void *)item + sizeof(*item) + sizeof(struct rst_info);
 	}