Date:	Wed, 10 Sep 2008 16:51:37 +0900
From:	"MinChan Kim" <minchan.kim@...il.com>
To:	"Oren Laadan" <orenl@...columbia.edu>
Cc:	dave@...ux.vnet.ibm.com, arnd@...db.de, jeremy@...p.org,
	linux-kernel@...r.kernel.org, containers@...ts.linux-foundation.org
Subject: Re: [RFC v4][PATCH 4/9] Memory management (dump)

On Tue, Sep 9, 2008 at 4:42 PM, Oren Laadan <orenl@...columbia.edu> wrote:
> For each VMA, there is a 'struct cr_vma'; if the VMA is file-mapped,
> it will be followed by the file name.  The cr_vma->npages will tell
> how many pages were dumped for this VMA.  Then it will be followed
> by the actual data: first a dump of the addresses of all dumped
> pages (npages entries) followed by a dump of the contents of all
> dumped pages (npages pages). Then will come the next VMA and so on.
>
> Signed-off-by: Oren Laadan <orenl@...columbia.edu>
> ---
>  arch/x86/mm/checkpoint.c   |   30 +++
>  arch/x86/mm/restart.c      |    1 +
>  checkpoint/Makefile        |    3 +-
>  checkpoint/checkpoint.c    |   53 ++++++
>  checkpoint/ckpt_arch.h     |    1 +
>  checkpoint/ckpt_mem.c      |  448 ++++++++++++++++++++++++++++++++++++++++++++
>  checkpoint/ckpt_mem.h      |   35 ++++
>  checkpoint/sys.c           |   23 ++-
>  include/asm-x86/ckpt_hdr.h |    5 +
>  include/linux/ckpt.h       |   12 ++
>  include/linux/ckpt_hdr.h   |   30 +++
>  11 files changed, 635 insertions(+), 6 deletions(-)
>  create mode 100644 checkpoint/ckpt_mem.c
>  create mode 100644 checkpoint/ckpt_mem.h
>
> diff --git a/arch/x86/mm/checkpoint.c b/arch/x86/mm/checkpoint.c
> index 71d21e6..50cfd29 100644
> --- a/arch/x86/mm/checkpoint.c
> +++ b/arch/x86/mm/checkpoint.c
> @@ -192,3 +192,33 @@ int cr_write_cpu(struct cr_ctx *ctx, struct task_struct *t)
>        cr_hbuf_put(ctx, sizeof(*hh));
>        return ret;
>  }
> +
> +/* dump the mm->context state */
> +int cr_write_mm_context(struct cr_ctx *ctx, struct mm_struct *mm, int parent)
> +{
> +       struct cr_hdr h;
> +       struct cr_hdr_mm_context *hh = cr_hbuf_get(ctx, sizeof(*hh));
> +       int ret;
> +
> +       h.type = CR_HDR_MM_CONTEXT;
> +       h.len = sizeof(*hh);
> +       h.parent = parent;
> +
> +       mutex_lock(&mm->context.lock);
> +
> +       hh->ldt_entry_size = LDT_ENTRY_SIZE;
> +       hh->nldt = mm->context.size;
> +
> +       cr_debug("nldt %d\n", hh->nldt);
> +
> +       ret = cr_write_obj(ctx, &h, hh);
> +       cr_hbuf_put(ctx, sizeof(*hh));
> +       if (ret < 0)
> +               return ret;
> +
> +       ret = cr_kwrite(ctx, mm->context.ldt, hh->nldt * LDT_ENTRY_SIZE);
> +
> +       mutex_unlock(&mm->context.lock);
> +
> +       return ret;
> +}
> diff --git a/arch/x86/mm/restart.c b/arch/x86/mm/restart.c
> index 883a163..d7fb89a 100644
> --- a/arch/x86/mm/restart.c
> +++ b/arch/x86/mm/restart.c
> @@ -8,6 +8,7 @@
>  *  distribution for more details.
>  */
>
> +#include <linux/unistd.h>
>  #include <asm/desc.h>
>  #include <asm/i387.h>
>
> diff --git a/checkpoint/Makefile b/checkpoint/Makefile
> index d2df68c..3a0df6d 100644
> --- a/checkpoint/Makefile
> +++ b/checkpoint/Makefile
> @@ -2,4 +2,5 @@
>  # Makefile for linux checkpoint/restart.
>  #
>
> -obj-$(CONFIG_CHECKPOINT_RESTART) += sys.o checkpoint.o restart.o
> +obj-$(CONFIG_CHECKPOINT_RESTART) += sys.o checkpoint.o restart.o \
> +               ckpt_mem.o
> diff --git a/checkpoint/checkpoint.c b/checkpoint/checkpoint.c
> index d34a691..4dae775 100644
> --- a/checkpoint/checkpoint.c
> +++ b/checkpoint/checkpoint.c
> @@ -55,6 +55,55 @@ int cr_write_string(struct cr_ctx *ctx, char *str, int len)
>        return cr_write_obj(ctx, &h, str);
>  }
>
> +/**
> + * cr_fill_fname - return pathname of a given file
> + * @path: path name
> + * @root: relative root
> + * @buf: buffer for pathname
> + * @n: buffer length (in) and pathname length (out)
> + */
> +static char *
> +cr_fill_fname(struct path *path, struct path *root, char *buf, int *n)
> +{
> +       char *fname;
> +
> +       BUG_ON(!buf);
> +       fname = __d_path(path, root, buf, *n);
> +       if (!IS_ERR(fname))
> +               *n = (buf + (*n) - fname);
> +       return fname;
> +}
> +
> +/**
> + * cr_write_fname - write a file name
> + * @ctx: checkpoint context
> + * @path: path name
> + * @root: relative root
> + */
> +int cr_write_fname(struct cr_ctx *ctx, struct path *path, struct path *root)
> +{
> +       struct cr_hdr h;
> +       char *buf, *fname;
> +       int ret, flen;
> +
> +       flen = PATH_MAX;
> +       buf = kmalloc(flen, GFP_KERNEL);
> +       if (!buf)
> +               return -ENOMEM;
> +
> +       fname = cr_fill_fname(path, root, buf, &flen);
> +       if (!IS_ERR(fname)) {
> +               h.type = CR_HDR_FNAME;
> +               h.len = flen;
> +               h.parent = 0;
> +               ret = cr_write_obj(ctx, &h, fname);
> +       } else
> +               ret = PTR_ERR(fname);
> +
> +       kfree(buf);
> +       return ret;
> +}
> +
>  /* write the checkpoint header */
>  static int cr_write_head(struct cr_ctx *ctx)
>  {
> @@ -164,6 +213,10 @@ static int cr_write_task(struct cr_ctx *ctx, struct task_struct *t)
>        cr_debug("task_struct: ret %d\n", ret);
>        if (ret < 0)
>                goto out;
> +       ret = cr_write_mm(ctx, t);
> +       cr_debug("memory: ret %d\n", ret);
> +       if (ret < 0)
> +               goto out;
>        ret = cr_write_thread(ctx, t);
>        cr_debug("thread: ret %d\n", ret);
>        if (ret < 0)
> diff --git a/checkpoint/ckpt_arch.h b/checkpoint/ckpt_arch.h
> index 5bd4703..9bd0ba4 100644
> --- a/checkpoint/ckpt_arch.h
> +++ b/checkpoint/ckpt_arch.h
> @@ -2,6 +2,7 @@
>
>  int cr_write_thread(struct cr_ctx *ctx, struct task_struct *t);
>  int cr_write_cpu(struct cr_ctx *ctx, struct task_struct *t);
> +int cr_write_mm_context(struct cr_ctx *ctx, struct mm_struct *mm, int parent);
>
>  int cr_read_thread(struct cr_ctx *ctx);
>  int cr_read_cpu(struct cr_ctx *ctx);
> diff --git a/checkpoint/ckpt_mem.c b/checkpoint/ckpt_mem.c
> new file mode 100644
> index 0000000..2c93447
> --- /dev/null
> +++ b/checkpoint/ckpt_mem.c
> @@ -0,0 +1,448 @@
> +/*
> + *  Checkpoint memory contents
> + *
> + *  Copyright (C) 2008 Oren Laadan
> + *
> + *  This file is subject to the terms and conditions of the GNU General Public
> + *  License.  See the file COPYING in the main directory of the Linux
> + *  distribution for more details.
> + */
> +
> +#include <linux/kernel.h>
> +#include <linux/sched.h>
> +#include <linux/slab.h>
> +#include <linux/file.h>
> +#include <linux/pagemap.h>
> +#include <linux/mm_types.h>
> +#include <linux/ckpt.h>
> +#include <linux/ckpt_hdr.h>
> +
> +#include "ckpt_arch.h"
> +#include "ckpt_mem.h"
> +
> +/*
> + * utilities to alloc, free, and handle 'struct cr_pgarr' (page-arrays)
> + * (common to ckpt_mem.c and rstr_mem.c).
> + *
> + * The checkpoint context structure has two members for page-arrays:
> + *   ctx->pgarr: list head of the page-array chain
> + *   ctx->pgcur: tracks the "current" position in the chain
> + *
> + * During checkpoint (and restart) the chain tracks the dirty pages (page
> + * pointer and virtual address) of each MM. For a particular MM, these are
> + * always added to the "current" page-array (ctx->pgcur). The "current"
> + * page-array advances as necessary, and new page-array descriptors are
> + * allocated on-demand. Before the next MM, the chain is reset but not
> + * freed (that is, dereference page pointers and reset ctx->pgcur).
> + */
> +
> +#define CR_PGARR_ORDER  0
> +#define CR_PGARR_TOTAL  ((PAGE_SIZE << CR_PGARR_ORDER) / sizeof(void *))
> +
> +/* release pages referenced by a page-array */
> +void cr_pgarr_unref_pages(struct cr_pgarr *pgarr)
> +{
> +       int n;
> +
> +       /* only checkpoint keeps references to pages */
> +       if (pgarr->pages) {
> +               cr_debug("nr_used %d\n", pgarr->nr_used);
> +               for (n = pgarr->nr_used; n--; )
> +                       page_cache_release(pgarr->pages[n]);
> +       }
> +}
> +
> +/* free a single page-array object */
> +static void cr_pgarr_free_one(struct cr_pgarr *pgarr)
> +{
> +       cr_pgarr_unref_pages(pgarr);
> +       if (pgarr->pages)
> +               free_pages((unsigned long) pgarr->pages, CR_PGARR_ORDER);
> +       if (pgarr->vaddrs)
> +               free_pages((unsigned long) pgarr->vaddrs, CR_PGARR_ORDER);
> +       kfree(pgarr);
> +}
> +
> +/* free a chain of page-arrays */
> +void cr_pgarr_free(struct cr_ctx *ctx)
> +{
> +       struct cr_pgarr *pgarr, *tmp;
> +
> +       list_for_each_entry_safe(pgarr, tmp, &ctx->pgarr, list) {
> +               list_del(&pgarr->list);
> +               cr_pgarr_free_one(pgarr);
> +       }
> +       ctx->pgcur = NULL;
> +}
> +
> +/* allocate a single page-array object */
> +static struct cr_pgarr *cr_pgarr_alloc_one(void)
> +{
> +       struct cr_pgarr *pgarr;
> +
> +       pgarr = kzalloc(sizeof(*pgarr), GFP_KERNEL);
> +       if (!pgarr)
> +               return NULL;
> +
> +       pgarr->nr_free = CR_PGARR_TOTAL;
> +       pgarr->nr_used = 0;
> +
> +       pgarr->pages = (struct page **)
> +               __get_free_pages(GFP_KERNEL, CR_PGARR_ORDER);
> +       pgarr->vaddrs = (unsigned long *)
> +               __get_free_pages(GFP_KERNEL, CR_PGARR_ORDER);
> +       if (!pgarr->pages || !pgarr->vaddrs) {
> +               cr_pgarr_free_one(pgarr);
> +               return NULL;
> +       }
> +
> +       return pgarr;
> +}
> +
> +/* cr_pgarr_alloc - return the next available pgarr in the page-array chain
> + * @ctx: checkpoint context
> + *
> + * Return the page-array following ctx->pgcur, extending the chain if needed
> + */
> +struct cr_pgarr *cr_pgarr_alloc(struct cr_ctx *ctx)
> +{
> +       struct cr_pgarr *pgarr;
> +
> +       /* can reuse next element after ctx->pgcur ? */
> +       pgarr = ctx->pgcur;
> +       if (pgarr && !list_is_last(&pgarr->list, &ctx->pgarr)) {
> +               pgarr = list_entry(pgarr->list.next, struct cr_pgarr, list);
> +               goto out;
> +       }
> +
> +       /* nope, need to extend the page-array chain */
> +       pgarr = cr_pgarr_alloc_one();
> +       if (!pgarr)
> +               return NULL;
> +
> +       list_add_tail(&pgarr->list, &ctx->pgarr);
> + out:
> +       ctx->pgcur = pgarr;
> +       return pgarr;
> +
> +}
> +
> +/* reset the page-array chain (dropping page references if necessary) */
> +void cr_pgarr_reset(struct cr_ctx *ctx)
> +{
> +       struct cr_pgarr *pgarr;
> +
> +       list_for_each_entry(pgarr, &ctx->pgarr, list) {
> +               cr_pgarr_unref_pages(pgarr);
> +               pgarr->nr_free = CR_PGARR_TOTAL;
> +               pgarr->nr_used = 0;
> +       }
> +       ctx->pgcur = NULL;
> +}
> +
> +
> +/* return current page-array (and allocate if needed) */
> +struct cr_pgarr *cr_pgarr_prep(struct cr_ctx *ctx
> +)

Brace shoudl be located in above line. :)
> +{
> +       struct cr_pgarr *pgarr = ctx->pgcur;
> +
> +       if (!pgarr->nr_free)
> +               pgarr = cr_pgarr_alloc(ctx);
> +       return pgarr;
> +}
> +
> +/*
> + * Checkpoint is outside the context of the checkpointee, so one cannot
> + * simply read pages from user-space. Instead, we scan the address space
> + * of the target to cherry-pick pages of interest. Selected pages are
> + * enlisted in a page-array chain (attached to the checkpoint context).
> + * To save their contents, each page is mapped to kernel memory and then
> + * dumped to the file descriptor.
> + */
> +
> +/**
> + * cr_vma_fill_pgarr - fill a page-array with addr/page tuples for a vma
> + * @ctx - checkpoint context
> + * @pgarr - page-array to fill
> + * @vma - vma to scan
> + * @start - start address (updated)
> + */
> +static int cr_vma_fill_pgarr(struct cr_ctx *ctx, struct cr_pgarr *pgarr,
> +                            struct vm_area_struct *vma, unsigned long *start)
> +{
> +       unsigned long end = vma->vm_end;
> +       unsigned long addr = *start;
> +       struct page **pagep;
> +       unsigned long *addrp;
> +       int cow, nr, ret = 0;
> +
> +       nr = pgarr->nr_free;
> +       pagep = &pgarr->pages[pgarr->nr_used];
> +       addrp = &pgarr->vaddrs[pgarr->nr_used];
> +       cow = !!vma->vm_file;
> +
> +       while (addr < end) {
> +               struct page *page;
> +
> +               /*
> +                * simplified version of get_user_pages(): already have vma,
> +                * only need FOLL_TOUCH, and (for now) ignore fault stats.
> +                *
> +                * FIXME: consolidate with get_user_pages()
> +                */
> +
> +               cond_resched();
> +               while (!(page = follow_page(vma, addr, FOLL_TOUCH))) {
> +                       ret = handle_mm_fault(vma->vm_mm, vma, addr, 0);
> +                       if (ret & VM_FAULT_ERROR) {
> +                               if (ret & VM_FAULT_OOM)
> +                                       ret = -ENOMEM;
> +                               else if (ret & VM_FAULT_SIGBUS)
> +                                       ret = -EFAULT;
> +                               else
> +                                       BUG();
> +                               break;
> +                       }
> +                       cond_resched();
> +                       ret = 0;
> +               }
> +
> +               if (IS_ERR(page))
> +                       ret = PTR_ERR(page);
> +
> +               if (ret < 0)
> +                       break;
> +
> +               if (page == ZERO_PAGE(0)) {
> +                       page = NULL;    /* zero page: ignore */
> +               } else if (cow && page_mapping(page) != NULL) {
> +                       page = NULL;    /* clean cow: ignore */
> +               } else {
> +                       get_page(page);
> +                       *(addrp++) = addr;
> +                       *(pagep++) = page;
> +                       if (--nr == 0) {
> +                               addr += PAGE_SIZE;
> +                               break;
> +                       }
> +               }
> +
> +               addr += PAGE_SIZE;
> +       }
> +
> +       if (unlikely(ret < 0)) {
> +               nr = pgarr->nr_free - nr;
> +               while (nr--)
> +                       page_cache_release(*(--pagep));
> +               return ret;
> +       }
> +
> +       *start = addr;
> +       return pgarr->nr_free - nr;
> +}
> +
> +/**
> + * cr_vma_scan_pages - scan vma for pages that will need to be dumped
> + * @ctx - checkpoint context
> + * @vma - vma to scan
> + *
> + * lists of page pointes and corresponding virtual addresses are tracked
> + * inside ctx->pgarr page-array chain
> + */
> +static int cr_vma_scan_pages(struct cr_ctx *ctx, struct vm_area_struct *vma)
> +{
> +       unsigned long addr = vma->vm_start;
> +       unsigned long end = vma->vm_end;
> +       struct cr_pgarr *pgarr;
> +       int nr, total = 0;
> +
> +       while (addr < end) {
> +               pgarr = cr_pgarr_prep(ctx);
> +               if (!pgarr)
> +                       return -ENOMEM;
> +               nr = cr_vma_fill_pgarr(ctx, pgarr, vma, &addr);
> +               if (nr < 0)
> +                       return nr;
> +               pgarr->nr_free -= nr;
> +               pgarr->nr_used += nr;
> +               total += nr;
> +       }
> +
> +       cr_debug("total %d\n", total);
> +       return total;
> +}
> +
> +static int cr_page_write(struct cr_ctx *ctx, struct page *page, char *buf)
> +{
> +       void *ptr;
> +
> +       ptr = kmap_atomic(page, KM_USER1);
> +       memcpy(buf, ptr, PAGE_SIZE);
> +       kunmap_atomic(page, KM_USER1);
> +
> +       return cr_kwrite(ctx, buf, PAGE_SIZE);
> +}
> +
> +/**
> + * cr_vma_dump_pages - dump pages listed in the ctx page-array chain
> + * @ctx - checkpoint context
> + * @total - total number of pages
> + *
> + * First dump all virtual addresses, followed by the contents of all pages
> + */
> +static int cr_vma_dump_pages(struct cr_ctx *ctx, int total)
> +{
> +       struct cr_pgarr *pgarr;
> +       char *buf;
> +       int i, ret = 0;
> +
> +       if (!total)
> +               return 0;
> +
> +       list_for_each_entry(pgarr, &ctx->pgarr, list) {
> +               ret = cr_kwrite(ctx, pgarr->vaddrs,
> +                               pgarr->nr_used * sizeof(*pgarr->vaddrs));
> +               if (ret < 0)
> +                       return ret;
> +       }
> +
> +       buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
> +       if (!buf)
> +               return -ENOMEM;
> +
> +       list_for_each_entry(pgarr, &ctx->pgarr, list) {
> +               for (i = 0; i < pgarr->nr_used; i++) {
> +                       ret = cr_page_write(ctx, pgarr->pages[i], buf);
> +                       if (ret < 0)
> +                               goto out;
> +               }
> +       }
> +
> + out:
> +       kfree(buf);
> +       return ret;
> +}
> +
> +static int cr_write_vma(struct cr_ctx *ctx, struct vm_area_struct *vma)
> +{
> +       struct cr_hdr h;
> +       struct cr_hdr_vma *hh = cr_hbuf_get(ctx, sizeof(*hh));
> +       int vma_type, nr, ret;
> +
> +       h.type = CR_HDR_VMA;
> +       h.len = sizeof(*hh);
> +       h.parent = 0;
> +
> +       hh->vm_start = vma->vm_start;
> +       hh->vm_end = vma->vm_end;
> +       hh->vm_page_prot = vma->vm_page_prot.pgprot;
> +       hh->vm_flags = vma->vm_flags;
> +       hh->vm_pgoff = vma->vm_pgoff;
> +
> +       if (vma->vm_flags & (VM_SHARED | VM_IO | VM_HUGETLB | VM_NONLINEAR)) {
> +               pr_warning("CR: unsupported VMA %#lx\n", vma->vm_flags);
> +               return -ETXTBSY;
> +       }
> +
> +       /* by default assume anon memory */
> +       vma_type = CR_VMA_ANON;
> +
> +       /* if there is a backing file, assume private-mapped */
> +       /* (FIX: check if the file is unlinked) */
> +       if (vma->vm_file)
> +               vma_type = CR_VMA_FILE;
> +
> +       hh->vma_type = vma_type;
> +
> +       /*
> +        * it seems redundant now, but we do it in 3 steps for because:
> +        * first, the logic is simpler when we how many pages before
> +        * dumping them; second, a future optimization will defer the
> +        * writeout (dump, and free) to a later step; in which case all
> +        * the pages to be dumped will be aggregated on the checkpoint ctx
> +        */
> +
> +       /* (1) scan: scan through the PTEs of the vma to count the pages
> +        * to dump (and later make those pages COW), and keep the list of
> +        * pages (and a reference to each page) on the checkpoint ctx */
> +       nr = cr_vma_scan_pages(ctx, vma);
> +       if (nr < 0)
> +               return nr;
> +
> +       hh->nr_pages = nr;
> +       ret = cr_write_obj(ctx, &h, hh);
> +       cr_hbuf_put(ctx, sizeof(*hh));
> +       if (ret < 0)
> +               return ret;
> +       /* save the file name, if relevant */
> +       if (vma->vm_file)
> +               ret = cr_write_fname(ctx, &vma->vm_file->f_path, ctx->vfsroot);
> +
> +       if (ret < 0)
> +               return ret;
> +
> +       /* (2) dump: write out the addresses of all pages in the list (on
> +        * the checkpoint ctx) followed by the contents of all pages */
> +       ret = cr_vma_dump_pages(ctx, nr);
> +
> +       /* (3) free: release the extra references to the pages in the list */
> +       cr_pgarr_reset(ctx);
> +
> +       return ret;
> +}
> +
> +int cr_write_mm(struct cr_ctx *ctx, struct task_struct *t)
> +{
> +       struct cr_hdr h;
> +       struct cr_hdr_mm *hh = cr_hbuf_get(ctx, sizeof(*hh));
> +       struct mm_struct *mm;
> +       struct vm_area_struct *vma;
> +       int objref, ret;
> +
> +       h.type = CR_HDR_MM;
> +       h.len = sizeof(*hh);
> +       h.parent = task_pid_vnr(t);
> +
> +       mm = get_task_mm(t);
> +
> +       objref = 0;     /* will be meaningful with multiple processes */
> +       hh->objref = objref;
> +
> +       down_read(&mm->mmap_sem);
> +
> +       hh->start_code = mm->start_code;
> +       hh->end_code = mm->end_code;
> +       hh->start_data = mm->start_data;
> +       hh->end_data = mm->end_data;
> +       hh->start_brk = mm->start_brk;
> +       hh->brk = mm->brk;
> +       hh->start_stack = mm->start_stack;
> +       hh->arg_start = mm->arg_start;
> +       hh->arg_end = mm->arg_end;
> +       hh->env_start = mm->env_start;
> +       hh->env_end = mm->env_end;
> +
> +       hh->map_count = mm->map_count;
> +
> +       /* FIX: need also mm->flags */
> +
> +       ret = cr_write_obj(ctx, &h, hh);
> +       cr_hbuf_put(ctx, sizeof(*hh));
> +       if (ret < 0)
> +               goto out;
> +
> +       /* write the vma's */
> +       for (vma = mm->mmap; vma; vma = vma->vm_next) {
> +               ret = cr_write_vma(ctx, vma);
> +               if (ret < 0)
> +                       goto out;
> +       }
> +
> +       ret = cr_write_mm_context(ctx, mm, objref);
> +
> + out:
> +       up_read(&mm->mmap_sem);
> +       mmput(mm);
> +       return ret;
> +}
> diff --git a/checkpoint/ckpt_mem.h b/checkpoint/ckpt_mem.h
> new file mode 100644
> index 0000000..8ee211d
> --- /dev/null
> +++ b/checkpoint/ckpt_mem.h
> @@ -0,0 +1,35 @@
> +#ifndef _CHECKPOINT_CKPT_MEM_H_
> +#define _CHECKPOINT_CKPT_MEM_H_
> +/*
> + *  Generic container checkpoint-restart
> + *
> + *  Copyright (C) 2008 Oren Laadan
> + *
> + *  This file is subject to the terms and conditions of the GNU General Public
> + *  License.  See the file COPYING in the main directory of the Linux
> + *  distribution for more details.
> + */
> +
> +#include <linux/mm_types.h>
> +
> +/*
> + * page-array chains: each cr_pgarr describes a set of <strcut page *,vaddr>
> + * tuples (where vaddr is the virtual address of a page in a particular mm).
> + * Specifically, we use separate arrays so that all vaddrs can be written
> + * and read at once.
> + */
> +
> +struct cr_pgarr {
> +       unsigned long *vaddrs;
> +       struct page **pages;
> +       unsigned int nr_used;   /* how many entries already used */
> +       unsigned int nr_free;   /* how many entries still free */
> +       struct list_head list;
> +};
> +
> +void cr_pgarr_reset(struct cr_ctx *ctx);
> +void cr_pgarr_free(struct cr_ctx *ctx);
> +struct cr_pgarr *cr_pgarr_alloc(struct cr_ctx *ctx);
> +struct cr_pgarr *cr_pgarr_prep(struct cr_ctx *ctx);
> +
> +#endif /* _CHECKPOINT_CKPT_MEM_H_ */
> diff --git a/checkpoint/sys.c b/checkpoint/sys.c
> index 113e0df..8141161 100644
> --- a/checkpoint/sys.c
> +++ b/checkpoint/sys.c
> @@ -16,6 +16,8 @@
>  #include <linux/capability.h>
>  #include <linux/ckpt.h>
>
> +#include "ckpt_mem.h"
> +
>  /*
>  * helpers to write/read to/from the image file descriptor
>  *
> @@ -110,7 +112,6 @@ int cr_kread(struct cr_ctx *ctx, void *buf, int count)
>        return ret;
>  }
>
> -
>  /*
>  * helpers to manage CR contexts: allocated for each checkpoint and/or
>  * restart operation, and persists until the operation is completed.
> @@ -126,6 +127,11 @@ void cr_ctx_free(struct cr_ctx *ctx)
>
>        free_pages((unsigned long) ctx->hbuf, CR_HBUF_ORDER);
>
> +       if (ctx->vfsroot)
> +               path_put(ctx->vfsroot);
> +
> +       cr_pgarr_free(ctx);
> +
>        kfree(ctx);
>  }
>
> @@ -145,10 +151,13 @@ struct cr_ctx *cr_ctx_alloc(pid_t pid, int fd, unsigned long flags)
>        get_file(ctx->file);
>
>        ctx->hbuf = (void *) __get_free_pages(GFP_KERNEL, CR_HBUF_ORDER);
> -       if (!ctx->hbuf) {
> -               cr_ctx_free(ctx);
> -               return ERR_PTR(-ENOMEM);
> -       }
> +       if (!ctx->hbuf)
> +               goto nomem;
> +
> +       /* assume checkpointer is in container's root vfs */
> +       /* FIXME: this works for now, but will change with real containers */
> +       ctx->vfsroot = &current->fs->root;
> +       path_get(ctx->vfsroot);
>
>        ctx->pid = pid;
>        ctx->flags = flags;
> @@ -156,6 +165,10 @@ struct cr_ctx *cr_ctx_alloc(pid_t pid, int fd, unsigned long flags)
>        ctx->crid = atomic_inc_return(&cr_ctx_count);
>
>        return ctx;
> +
> + nomem:
> +       cr_ctx_free(ctx);
> +       return ERR_PTR(-ENOMEM);
>  }
>
>  /*
> diff --git a/include/asm-x86/ckpt_hdr.h b/include/asm-x86/ckpt_hdr.h
> index 44a903c..6bc61ac 100644
> --- a/include/asm-x86/ckpt_hdr.h
> +++ b/include/asm-x86/ckpt_hdr.h
> @@ -69,4 +69,9 @@ struct cr_hdr_cpu {
>
>  } __attribute__((aligned(8)));
>
> +struct cr_hdr_mm_context {
> +       __s16 ldt_entry_size;
> +       __s16 nldt;
> +} __attribute__((aligned(8)));
> +
>  #endif /* __ASM_X86_CKPT_HDR__H */
> diff --git a/include/linux/ckpt.h b/include/linux/ckpt.h
> index 91f4998..5c62a90 100644
> --- a/include/linux/ckpt.h
> +++ b/include/linux/ckpt.h
> @@ -10,6 +10,9 @@
>  *  distribution for more details.
>  */
>
> +#include <linux/path.h>
> +#include <linux/fs.h>
> +
>  #define CR_VERSION  1
>
>  struct cr_ctx {
> @@ -24,6 +27,11 @@ struct cr_ctx {
>
>        void *hbuf;             /* temporary buffer for headers */
>        int hpos;               /* position in headers buffer */
> +
> +       struct list_head pgarr; /* page array for dumping VMA contents */
> +       struct cr_pgarr *pgcur; /* current position in page array */
> +
> +       struct path *vfsroot;   /* container root (FIXME) */
>  };
>
>  /* cr_ctx: flags */
> @@ -46,11 +54,15 @@ struct cr_hdr;
>
>  int cr_write_obj(struct cr_ctx *ctx, struct cr_hdr *h, void *buf);
>  int cr_write_string(struct cr_ctx *ctx, char *str, int len);
> +int cr_write_fname(struct cr_ctx *ctx, struct path *path, struct path *root);
>
>  int cr_read_obj(struct cr_ctx *ctx, struct cr_hdr *h, void *buf, int n);
>  int cr_read_obj_type(struct cr_ctx *ctx, void *buf, int n, int type);
>  int cr_read_string(struct cr_ctx *ctx, void *str, int len);
>
> +int cr_write_mm(struct cr_ctx *ctx, struct task_struct *t);
> +int cr_read_mm(struct cr_ctx *ctx);
> +
>  int do_checkpoint(struct cr_ctx *ctx);
>  int do_restart(struct cr_ctx *ctx);
>
> diff --git a/include/linux/ckpt_hdr.h b/include/linux/ckpt_hdr.h
> index e66f322..ac77d7d 100644
> --- a/include/linux/ckpt_hdr.h
> +++ b/include/linux/ckpt_hdr.h
> @@ -32,6 +32,7 @@ struct cr_hdr {
>  enum {
>        CR_HDR_HEAD = 1,
>        CR_HDR_STRING,
> +       CR_HDR_FNAME,
>
>        CR_HDR_TASK = 101,
>        CR_HDR_THREAD,
> @@ -82,4 +83,33 @@ struct cr_hdr_task {
>        __s32 task_comm_len;
>  } __attribute__((aligned(8)));
>
> +struct cr_hdr_mm {
> +       __u32 objref;           /* identifier for shared objects */
> +       __u32 map_count;
> +
> +       __u64 start_code, end_code, start_data, end_data;
> +       __u64 start_brk, brk, start_stack;
> +       __u64 arg_start, arg_end, env_start, env_end;
> +
> +} __attribute__((aligned(8)));
> +
> +/* vma subtypes */
> +enum vm_type {
> +       CR_VMA_ANON = 1,
> +       CR_VMA_FILE
> +};
> +
> +struct cr_hdr_vma {
> +       __u32 vma_type;
> +       __u32 _padding;
> +       __s64 nr_pages;
> +
> +       __u64 vm_start;
> +       __u64 vm_end;
> +       __u64 vm_page_prot;
> +       __u64 vm_flags;
> +       __u64 vm_pgoff;
> +
> +} __attribute__((aligned(8)));
> +
>  #endif /* _CHECKPOINT_CKPT_HDR_H_ */
> --
> 1.5.4.3
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@...r.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/
>



-- 
Kinds regards,
MinChan Kim
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists