Message-ID: <20080904160311.GC19364@us.ibm.com>
Date:	Thu, 4 Sep 2008 11:03:11 -0500
From:	"Serge E. Hallyn" <serue@...ibm.com>
To:	Oren Laadan <orenl@...columbia.edu>
Cc:	dave@...ux.vnet.ibm.com, containers@...ts.linux-foundation.org,
	jeremy@...p.org, linux-kernel@...r.kernel.org, arnd@...db.de
Subject: Re: [RFC v3][PATCH 2/9] General infrastructure for checkpoint
	restart

Quoting Oren Laadan (orenl@...columbia.edu):
> 
> Add those interfaces, as well as helpers needed to easily manage the
> file format. The code is roughly broken out as follows:
> 
> checkpoint/sys.c - user/kernel data transfer, as well as setup of the
> checkpoint/restart context (a per-checkpoint data structure for
> housekeeping)
> 
> checkpoint/checkpoint.c - output wrappers and basic checkpoint handling
> 
> checkpoint/restart.c - input wrappers and basic restart handling
> 
> Patches to add the per-architecture support as well as the actual
> work to do the memory checkpoint follow in subsequent patches.
> 
> Signed-off-by: Oren Laadan <orenl@...columbia.edu>

This really looks good to me - nothing particularly exotic, nice and
simple.

Dave, are you happy with the allocations here, or were you objecting
to cr_hbuf_get() and cr_hbuf_put()?

thanks,
-serge

> ---
>   Makefile                 |    2 +-
>   checkpoint/Makefile      |    2 +-
>   checkpoint/checkpoint.c  |  188 ++++++++++++++++++++++++++++++++++++++
>   checkpoint/restart.c     |  189 ++++++++++++++++++++++++++++++++++++++
>   checkpoint/sys.c         |  226 +++++++++++++++++++++++++++++++++++++++++++++-
>   include/linux/ckpt.h     |   65 +++++++++++++
>   include/linux/ckpt_hdr.h |   82 +++++++++++++++++
>   include/linux/magic.h    |    3 +
>   8 files changed, 751 insertions(+), 6 deletions(-)
>   create mode 100644 checkpoint/checkpoint.c
>   create mode 100644 checkpoint/restart.c
>   create mode 100644 include/linux/ckpt.h
>   create mode 100644 include/linux/ckpt_hdr.h
> 
> diff --git a/Makefile b/Makefile
> index f448e00..a558ad2 100644
> --- a/Makefile
> +++ b/Makefile
> @@ -619,7 +619,7 @@ export mod_strip_cmd
> 
> 
>   ifeq ($(KBUILD_EXTMOD),)
> -core-y		+= kernel/ mm/ fs/ ipc/ security/ crypto/ block/
> +core-y		+= kernel/ mm/ fs/ ipc/ security/ crypto/ block/ checkpoint/
> 
>   vmlinux-dirs	:= $(patsubst %/,%,$(filter %/, $(init-y) $(init-m) \
>   		     $(core-y) $(core-m) $(drivers-y) $(drivers-m) \
> diff --git a/checkpoint/Makefile b/checkpoint/Makefile
> index 07d018b..d2df68c 100644
> --- a/checkpoint/Makefile
> +++ b/checkpoint/Makefile
> @@ -2,4 +2,4 @@
>   # Makefile for linux checkpoint/restart.
>   #
> 
> -obj-$(CONFIG_CHECKPOINT_RESTART) += sys.o
> +obj-$(CONFIG_CHECKPOINT_RESTART) += sys.o checkpoint.o restart.o
> diff --git a/checkpoint/checkpoint.c b/checkpoint/checkpoint.c
> new file mode 100644
> index 0000000..ad1099f
> --- /dev/null
> +++ b/checkpoint/checkpoint.c
> @@ -0,0 +1,188 @@
> +/*
> + *  Checkpoint logic and helpers
> + *
> + *  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/version.h>
> +#include <linux/sched.h>
> +#include <linux/time.h>
> +#include <linux/fs.h>
> +#include <linux/file.h>
> +#include <linux/dcache.h>
> +#include <linux/mount.h>
> +#include <linux/utsname.h>
> +#include <linux/magic.h>
> +#include <linux/ckpt.h>
> +#include <linux/ckpt_hdr.h>
> +
> +/**
> + * cr_write_obj - write a record described by a cr_hdr
> + * @ctx: checkpoint context
> + * @h: record descriptor
> + * @buf: record buffer
> + */
> +int cr_write_obj(struct cr_ctx *ctx, struct cr_hdr *h, void *buf)
> +{
> +	int ret;
> +
> +	ret = cr_kwrite(ctx, h, sizeof(*h));
> +	if (ret < 0)
> +		return ret;
> +	return cr_kwrite(ctx, buf, h->len);
> +}
> +
> +/**
> + * cr_write_string - write a string
> + * @ctx: checkpoint context
> + * @str: string pointer
> + * @len: string length
> + */
> +int cr_write_string(struct cr_ctx *ctx, char *str, int len)
> +{
> +	struct cr_hdr h;
> +
> +	h.type = CR_HDR_STRING;
> +	h.len = len;
> +	h.parent = 0;
> +
> +	return cr_write_obj(ctx, &h, str);
> +}
> +
> +/* write the checkpoint header */
> +static int cr_write_head(struct cr_ctx *ctx)
> +{
> +	struct cr_hdr h;
> +	struct cr_hdr_head *hh = cr_hbuf_get(ctx, sizeof(*hh));
> +	struct new_utsname *uts;
> +	struct timeval ktv;
> +	int ret;
> +
> +	h.type = CR_HDR_HEAD;
> +	h.len = sizeof(*hh);
> +	h.parent = 0;
> +
> +	do_gettimeofday(&ktv);
> +
> +	hh->magic = CHECKPOINT_MAGIC_HEAD;
> +	hh->major = (LINUX_VERSION_CODE >> 16) & 0xff;
> +	hh->minor = (LINUX_VERSION_CODE >> 8) & 0xff;
> +	hh->patch = (LINUX_VERSION_CODE) & 0xff;
> +
> +	hh->rev = CR_VERSION;
> +
> +	hh->flags = ctx->flags;
> +	hh->time = ktv.tv_sec;
> +
> +	uts = utsname();
> +	memcpy(hh->release, uts->release, __NEW_UTS_LEN);
> +	memcpy(hh->version, uts->version, __NEW_UTS_LEN);
> +	memcpy(hh->machine, uts->machine, __NEW_UTS_LEN);
> +
> +	ret = cr_write_obj(ctx, &h, hh);
> +	cr_hbuf_put(ctx, sizeof(*hh));
> +	return ret;
> +}
> +
> +/* write the checkpoint trailer */
> +static int cr_write_tail(struct cr_ctx *ctx)
> +{
> +	struct cr_hdr h;
> +	struct cr_hdr_tail *hh = cr_hbuf_get(ctx, sizeof(*hh));
> +	int ret;
> +
> +	h.type = CR_HDR_TAIL;
> +	h.len = sizeof(*hh);
> +	h.parent = 0;
> +
> +	hh->magic = CHECKPOINT_MAGIC_TAIL;
> +
> +	ret = cr_write_obj(ctx, &h, hh);
> +	cr_hbuf_put(ctx, sizeof(*hh));
> +	return ret;
> +}
> +
> +/* dump the task_struct of a given task */
> +static int cr_write_task_struct(struct cr_ctx *ctx, struct task_struct *t)
> +{
> +	struct cr_hdr h;
> +	struct cr_hdr_task *hh = cr_hbuf_get(ctx, sizeof(*hh));
> +	int ret;
> +
> +	h.type = CR_HDR_TASK;
> +	h.len = sizeof(*hh);
> +	h.parent = 0;
> +
> +	hh->state = t->state;
> +	hh->exit_state = t->exit_state;
> +	hh->exit_code = t->exit_code;
> +	hh->exit_signal = t->exit_signal;
> +
> +	hh->utime = t->utime;
> +	hh->stime = t->stime;
> +	hh->utimescaled = t->utimescaled;
> +	hh->stimescaled = t->stimescaled;
> +	hh->gtime = t->gtime;
> +	hh->prev_utime = t->prev_utime;
> +	hh->prev_stime = t->prev_stime;
> +	hh->nvcsw = t->nvcsw;
> +	hh->nivcsw = t->nivcsw;
> +	hh->start_time_sec = t->start_time.tv_sec;
> +	hh->start_time_nsec = t->start_time.tv_nsec;
> +	hh->real_start_time_sec = t->real_start_time.tv_sec;
> +	hh->real_start_time_nsec = t->real_start_time.tv_nsec;
> +	hh->min_flt = t->min_flt;
> +	hh->maj_flt = t->maj_flt;
> +
> +	hh->task_comm_len = TASK_COMM_LEN;
> +
> +	ret = cr_write_obj(ctx, &h, hh);
> +	cr_hbuf_put(ctx, sizeof(*hh));
> +	if (ret < 0)
> +		return ret;
> +
> +	return cr_write_string(ctx, t->comm, TASK_COMM_LEN);
> +}
> +
> +/* dump the entire state of a given task */
> +static int cr_write_task(struct cr_ctx *ctx, struct task_struct *t)
> +{
> +	int ret ;
> +
> +	if (t->state == TASK_DEAD) {
> +		pr_warning("CR: task may not be in state TASK_DEAD\n");
> +		return -EAGAIN;
> +	}
> +
> +	ret = cr_write_task_struct(ctx, t);
> +	cr_debug("ret %d\n", ret);
> +
> +	return ret;
> +}
> +
> +int do_checkpoint(struct cr_ctx *ctx)
> +{
> +	int ret;
> +
> +	/* FIX: need to test whether container is checkpointable */
> +
> +	ret = cr_write_head(ctx);
> +	if (ret < 0)
> +		goto out;
> +	ret = cr_write_task(ctx, current);
> +	if (ret < 0)
> +		goto out;
> +	ret = cr_write_tail(ctx);
> +	if (ret < 0)
> +		goto out;
> +
> +	/* on success, return (unique) checkpoint identifier */
> +	ret = ctx->crid;
> +
> + out:
> +	return ret;
> +}
> diff --git a/checkpoint/restart.c b/checkpoint/restart.c
> new file mode 100644
> index 0000000..171cd2d
> --- /dev/null
> +++ b/checkpoint/restart.c
> @@ -0,0 +1,189 @@
> +/*
> + *  Restart logic and helpers
> + *
> + *  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/version.h>
> +#include <linux/sched.h>
> +#include <linux/file.h>
> +#include <linux/magic.h>
> +#include <linux/ckpt.h>
> +#include <linux/ckpt_hdr.h>
> +
> +/**
> + * cr_read_obj - read a whole record (cr_hdr followed by payload)
> + * @ctx: checkpoint context
> + * @h: record descriptor
> + * @buf: record buffer
> + * @n: available buffer size
> + *
> + * @return: size of payload
> + */
> +int cr_read_obj(struct cr_ctx *ctx, struct cr_hdr *h, void *buf, int n)
> +{
> +	int ret;
> +
> +	ret = cr_kread(ctx, h, sizeof(*h));
> +	if (ret < 0)
> +		return ret;
> +
> +	cr_debug("type %d len %d parent %d\n", h->type, h->len, h->parent);
> +
> +	if (h->len < 0 || h->len > n)
> +		return -EINVAL;
> +
> +	return cr_kread(ctx, buf, h->len);
> +}
> +
> +/**
> + * cr_read_obj_type - read a whole record of expected type
> + * @ctx: checkpoint context
> + * @buf: record buffer
> + * @n: available buffer size
> + * @type: expected record type
> + *
> + * @return: object reference of the parent object
> + */
> +int cr_read_obj_type(struct cr_ctx *ctx, void *buf, int n, int type)
> +{
> +	struct cr_hdr h;
> +	int ret;
> +
> +	ret = cr_read_obj(ctx, &h, buf, n);
> +	if (!ret) {
> +		if (h.type == type)
> +			ret = h.parent;
> +		else
> +			ret = -EINVAL;
> +	}
> +	return ret;
> +}
> +
> +/**
> + * cr_read_string - read a string
> + * @ctx: checkpoint context
> + * @str: string buffer
> + * @len: buffer buffer length
> + */
> +int cr_read_string(struct cr_ctx *ctx, void *str, int len)
> +{
> +	return cr_read_obj_type(ctx, str, len, CR_HDR_STRING);
> +}
> +
> +/* read the checkpoint header */
> +static int cr_read_head(struct cr_ctx *ctx)
> +{
> +	struct cr_hdr_head *hh = cr_hbuf_get(ctx, sizeof(*hh));
> +	int parent;
> +
> +	parent = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_HEAD);
> +	if (parent < 0)
> +		return parent;
> +	else if (parent != 0)
> +		return -EINVAL;
> +
> +	if (hh->magic != CHECKPOINT_MAGIC_HEAD || hh->rev != CR_VERSION ||
> +	    hh->major != ((LINUX_VERSION_CODE >> 16) & 0xff) ||
> +	    hh->minor != ((LINUX_VERSION_CODE >> 8) & 0xff) ||
> +	    hh->patch != ((LINUX_VERSION_CODE) & 0xff))
> +		return -EINVAL;
> +
> +	if (hh->flags & ~CR_CTX_CKPT)
> +		return -EINVAL;
> +
> +	ctx->oflags = hh->flags;
> +
> +	/* FIX: verify compatibility of release, version and machine */
> +
> +	cr_hbuf_put(ctx, sizeof(*hh));
> +	return 0;
> +}
> +
> +/* read the checkpoint trailer */
> +static int cr_read_tail(struct cr_ctx *ctx)
> +{
> +	struct cr_hdr_tail *hh = cr_hbuf_get(ctx, sizeof(*hh));
> +	int parent;
> +
> +	parent = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_TAIL);
> +	if (parent < 0)
> +		return parent;
> +	else if (parent != 0)
> +		return -EINVAL;
> +
> +	if (hh->magic != CHECKPOINT_MAGIC_TAIL)
> +		return -EINVAL;
> +
> +	cr_hbuf_put(ctx, sizeof(*hh));
> +	return 0;
> +}
> +
> +/* read the task_struct into the current task */
> +static int cr_read_task_struct(struct cr_ctx *ctx)
> +{
> +	struct cr_hdr_task *hh = cr_hbuf_get(ctx, sizeof(*hh));
> +	struct task_struct *t = current;
> +	char *buf;
> +	int parent, ret;
> +
> +	parent = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_TASK);
> +	if (parent < 0)
> +		return parent;
> +	else if (parent != 0)
> +		return -EINVAL;
> +
> +	/* FIXME: for now, only restore t->comm */
> +
> +	/* upper limit for task_comm_len to prevent DoS */
> +	if (hh->task_comm_len < 0 || hh->task_comm_len > PAGE_SIZE)
> +		return -EINVAL;
> +
> +	buf = kmalloc(hh->task_comm_len, GFP_KERNEL);
> +	if (!buf)
> +		return -ENOMEM;
> +	ret = cr_read_string(ctx, buf, hh->task_comm_len);
> +	if (!ret) {
> +		/* if t->comm is too long, silently truncate */
> +		memset(t->comm, 0, TASK_COMM_LEN);
> +		memcpy(t->comm, buf, min(hh->task_comm_len, TASK_COMM_LEN));
> +	}
> +	kfree(buf);
> +
> +	cr_hbuf_put(ctx, sizeof(*hh));
> +	return ret;
> +}
> +
> +/* read the entire state of the current task */
> +static int cr_read_task(struct cr_ctx *ctx)
> +{
> +	int ret;
> +
> +	ret = cr_read_task_struct(ctx);
> +	cr_debug("ret %d\n", ret);
> +
> +	return ret;
> +}
> +
> +int do_restart(struct cr_ctx *ctx)
> +{
> +	int ret;
> +
> +	ret = cr_read_head(ctx);
> +	if (ret < 0)
> +		goto out;
> +	ret = cr_read_task(ctx);
> +	if (ret < 0)
> +		goto out;
> +	ret = cr_read_tail(ctx);
> +	if (ret < 0)
> +		goto out;
> +
> +	/* on success, adjust the return value if needed [TODO] */
> + out:
> +	return ret;
> +}
> diff --git a/checkpoint/sys.c b/checkpoint/sys.c
> index b9018a4..4268bae 100644
> --- a/checkpoint/sys.c
> +++ b/checkpoint/sys.c
> @@ -10,6 +10,197 @@
> 
>   #include <linux/sched.h>
>   #include <linux/kernel.h>
> +#include <linux/fs.h>
> +#include <linux/file.h>
> +#include <linux/uaccess.h>
> +#include <linux/capability.h>
> +#include <linux/ckpt.h>
> +
> +/*
> + * helpers to write/read to/from the image file descriptor
> + *
> + *   cr_uwrite() - write a user-space buffer to the checkpoint image
> + *   cr_kwrite() - write a kernel-space buffer to the checkpoint image
> + *   cr_uread() - read from the checkpoint image to a user-space buffer
> + *   cr_kread() - read from the checkpoint image to a kernel-space buffer
> + *
> + */
> +
> +/* (temporarily added file_pos_read() and file_pos_write() because they
> + * are static in fs/read_write.c... should cleanup and remove later) */
> +static inline loff_t file_pos_read(struct file *file)
> +{
> +	return file->f_pos;
> +}
> +
> +static inline void file_pos_write(struct file *file, loff_t pos)
> +{
> +	file->f_pos = pos;
> +}
> +
> +int cr_uwrite(struct cr_ctx *ctx, void *buf, int count)
> +{
> +	struct file *file = ctx->file;
> +	ssize_t nwrite;
> +	int nleft;
> +
> +	for (nleft = count; nleft; nleft -= nwrite) {
> +		loff_t pos = file_pos_read(file);
> +		nwrite = vfs_write(file, (char __user *) buf, nleft, &pos);
> +		file_pos_write(file, pos);
> +		if (nwrite <= 0) {
> +			if (nwrite == -EAGAIN)
> +				nwrite = 0;
> +			else
> +				return nwrite;
> +		}
> +		buf += nwrite;
> +	}
> +
> +	ctx->total += count;
> +	return 0;
> +}
> +
> +int cr_kwrite(struct cr_ctx *ctx, void *buf, int count)
> +{
> +	mm_segment_t oldfs;
> +	int ret;
> +
> +	oldfs = get_fs();
> +	set_fs(KERNEL_DS);
> +	ret = cr_uwrite(ctx, buf, count);
> +	set_fs(oldfs);
> +
> +	return ret;
> +}
> +
> +int cr_uread(struct cr_ctx *ctx, void *buf, int count)
> +{
> +	struct file *file = ctx->file;
> +	ssize_t nread;
> +	int nleft;
> +
> +	for (nleft = count; nleft; nleft -= nread) {
> +		loff_t pos = file_pos_read(file);
> +		nread = vfs_read(file, (char __user *) buf, nleft, &pos);
> +		file_pos_write(file, pos);
> +		if (nread <= 0) {
> +			if (nread == -EAGAIN)
> +				nread = 0;
> +			else
> +				return nread;
> +		}
> +		buf += nread;
> +	}
> +
> +	ctx->total += count;
> +	return 0;
> +}
> +
> +int cr_kread(struct cr_ctx *ctx, void *buf, int count)
> +{
> +	mm_segment_t oldfs;
> +	int ret;
> +
> +	oldfs = get_fs();
> +	set_fs(KERNEL_DS);
> +	ret = cr_uread(ctx, buf, count);
> +	set_fs(oldfs);
> +
> +	return ret;
> +}
> +
> +
> +/*
> + * helpers to manage CR contexts: allocated for each checkpoint and/or
> + * restart operation, and persists until the operation is completed.
> + */
> +
> +/* unique checkpoint identifier (FIXME: should be per-container) */
> +static atomic_t cr_ctx_count;
> +
> +void cr_ctx_free(struct cr_ctx *ctx)
> +{
> +
> +	if (ctx->file)
> +		fput(ctx->file);
> +	if (ctx->vfsroot)
> +		path_put(ctx->vfsroot);
> +
> +	free_pages((unsigned long) ctx->hbuf, CR_HBUF_ORDER);
> +
> +	kfree(ctx);
> +}
> +
> +struct cr_ctx *cr_ctx_alloc(pid_t pid, int fd, unsigned long flags)
> +{
> +	struct cr_ctx *ctx;
> +
> +	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
> +	if (!ctx)
> +		return ERR_PTR(-ENOMEM);
> +
> +	ctx->file = fget(fd);
> +	if (!ctx->file) {
> +		cr_ctx_free(ctx);
> +		return ERR_PTR(-EBADF);
> +	}
> +	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);
> +	}
> +
> +	ctx->pid = pid;
> +	ctx->flags = flags;
> +
> +	/* 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->crid = atomic_inc_return(&cr_ctx_count);
> +
> +	return ctx;
> +}
> +
> +/*
> + * During checkpoint and restart the code writes outs/reads in data
> + * to/from the chekcpoint image from/to a temporary buffer (ctx->hbuf).
> + * Because operations can be nested, one should call cr_hbuf_get() to
> + * reserve space in the buffer, and then cr_hbuf_put() when no longer
> + * needs that space.
> + */
> +
> +/**
> + * cr_hbuf_get - reserve space on the hbuf
> + * @ctx: checkpoint context
> + * @n: number of bytes to reserve
> + *
> + * @return: pointer to reserved space
> + */
> +void *cr_hbuf_get(struct cr_ctx *ctx, int n)
> +{
> +	void *ptr;
> +
> +	BUG_ON(ctx->hpos + n > CR_HBUF_TOTAL);
> +	ptr = (void *) (((char *) ctx->hbuf) + ctx->hpos);
> +	ctx->hpos += n;
> +	return ptr;
> +}
> +
> +/**
> + * cr_hbuf_put - unreserve space on the hbuf
> + * @ctx: checkpoint context
> + * @n: number of bytes to reserve
> + */
> +void cr_hbuf_put(struct cr_ctx *ctx, int n)
> +{
> +	BUG_ON(ctx->hpos < n);
> +	ctx->hpos -= n;
> +}
> 
>   /**
>    * sys_checkpoint - checkpoint a container
> @@ -19,9 +210,23 @@
>    */
>   asmlinkage long sys_checkpoint(pid_t pid, int fd, unsigned long flags)
>   {
> -	pr_debug("sys_checkpoint not implemented yet\n");
> -	return -ENOSYS;
> +	struct cr_ctx *ctx;
> +	int ret;
> +
> +	/* no flags for now */
> +	if (flags)
> +		return -EINVAL;
> +
> +	ctx = cr_ctx_alloc(pid, fd, flags | CR_CTX_CKPT);
> +	if (IS_ERR(ctx))
> +		return PTR_ERR(ctx);
> +
> +	ret = do_checkpoint(ctx);
> +
> +	cr_ctx_free(ctx);
> +	return ret;
>   }
> +
>   /**
>    * sys_restart - restart a container
>    * @crid: checkpoint image identifier
> @@ -30,6 +235,19 @@ asmlinkage long sys_checkpoint(pid_t pid, int fd, unsigned long flags)
>    */
>   asmlinkage long sys_restart(int crid, int fd, unsigned long flags)
>   {
> -	pr_debug("sys_restart not implemented yet\n");
> -	return -ENOSYS;
> +	struct cr_ctx *ctx;
> +	int ret;
> +
> +	/* no flags for now */
> +	if (flags)
> +		return -EINVAL;
> +
> +	ctx = cr_ctx_alloc(crid, fd, flags | CR_CTX_RSTR);
> +	if (IS_ERR(ctx))
> +		return PTR_ERR(ctx);
> +
> +	ret = do_restart(ctx);
> +
> +	cr_ctx_free(ctx);
> +	return ret;
>   }
> diff --git a/include/linux/ckpt.h b/include/linux/ckpt.h
> new file mode 100644
> index 0000000..1bb2b09
> --- /dev/null
> +++ b/include/linux/ckpt.h
> @@ -0,0 +1,65 @@
> +#ifndef _CHECKPOINT_CKPT_H_
> +#define _CHECKPOINT_CKPT_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/path.h>
> +#include <linux/fs.h>
> +
> +#define CR_VERSION  1
> +
> +struct cr_ctx {
> +	pid_t pid;		/* container identifier */
> +	int crid;		/* unique checkpoint id */
> +
> +	unsigned long flags;
> +	unsigned long oflags;	/* restart: old flags */
> +
> +	struct file *file;
> +	int total;		/* total read/written */
> +
> +	void *hbuf;		/* temporary buffer for headers */
> +	int hpos;		/* position in headers buffer */
> +
> +	struct path *vfsroot;	/* container root */
> +};
> +
> +/* cr_ctx: flags */
> +#define CR_CTX_CKPT	0x1
> +#define CR_CTX_RSTR	0x2
> +
> +/* allocation defaults */
> +#define CR_HBUF_ORDER  1
> +#define CR_HBUF_TOTAL  (PAGE_SIZE << CR_HBUF_ORDER)
> +
> +int cr_uwrite(struct cr_ctx *ctx, void *buf, int count);
> +int cr_kwrite(struct cr_ctx *ctx, void *buf, int count);
> +int cr_uread(struct cr_ctx *ctx, void *buf, int count);
> +int cr_kread(struct cr_ctx *ctx, void *buf, int count);
> +
> +void *cr_hbuf_get(struct cr_ctx *ctx, int n);
> +void cr_hbuf_put(struct cr_ctx *ctx, int n);
> +
> +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_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 do_checkpoint(struct cr_ctx *ctx);
> +int do_restart(struct cr_ctx *ctx);
> +
> +#define cr_debug(fmt, args...)  \
> +	pr_debug("[CR:%s] " fmt, __func__, ## args)
> +
> +#endif /* _CHECKPOINT_CKPT_H_ */
> diff --git a/include/linux/ckpt_hdr.h b/include/linux/ckpt_hdr.h
> new file mode 100644
> index 0000000..629ad5a
> --- /dev/null
> +++ b/include/linux/ckpt_hdr.h
> @@ -0,0 +1,82 @@
> +#ifndef _CHECKPOINT_CKPT_HDR_H_
> +#define _CHECKPOINT_CKPT_HDR_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/types.h>
> +#include <linux/utsname.h>
> +
> +/*
> + * To maintain compatibility between 32-bit and 64-bit architecture flavors,
> + * keep data 64-bit aligned: use padding for structure members, and use
> + * __attribute__ ((aligned (8))) for the entire structure.
> + */
> +
> +/* records: generic header */
> +
> +struct cr_hdr {
> +	__s16 type;
> +	__s16 len;
> +	__u32 parent;
> +};
> +
> +/* header types */
> +enum {
> +	CR_HDR_HEAD = 1,
> +	CR_HDR_STRING,
> +
> +	CR_HDR_TASK = 101,
> +	CR_HDR_THREAD,
> +	CR_HDR_CPU,
> +
> +	CR_HDR_MM = 201,
> +	CR_HDR_VMA,
> +	CR_HDR_MM_CONTEXT,
> +
> +	CR_HDR_TAIL = 5001
> +};
> +
> +struct cr_hdr_head {
> +	__u64 magic;
> +
> +	__u16 major;
> +	__u16 minor;
> +	__u16 patch;
> +	__u16 rev;
> +
> +	__u64 time;	/* when checkpoint taken */
> +	__u64 flags;	/* checkpoint options */
> +
> +	char release[__NEW_UTS_LEN];
> +	char version[__NEW_UTS_LEN];
> +	char machine[__NEW_UTS_LEN];
> +} __attribute__((aligned(8)));
> +
> +struct cr_hdr_tail {
> +	__u64 magic;
> +} __attribute__((aligned(8)));
> +
> +struct cr_hdr_task {
> +	__u64 state;
> +	__u32 exit_state;
> +	__u32 exit_code, exit_signal;
> +
> +	__u64 utime, stime, utimescaled, stimescaled;
> +	__u64 gtime;
> +	__u64 prev_utime, prev_stime;
> +	__u64 nvcsw, nivcsw;
> +	__u64 start_time_sec, start_time_nsec;
> +	__u64 real_start_time_sec, real_start_time_nsec;
> +	__u64 min_flt, maj_flt;
> +
> +	__s32 task_comm_len;
> +} __attribute__((aligned(8)));
> +
> +#endif /* _CHECKPOINT_CKPT_HDR_H_ */
> diff --git a/include/linux/magic.h b/include/linux/magic.h
> index 1fa0c2c..c2b811c 100644
> --- a/include/linux/magic.h
> +++ b/include/linux/magic.h
> @@ -42,4 +42,7 @@
>   #define FUTEXFS_SUPER_MAGIC	0xBAD1DEA
>   #define INOTIFYFS_SUPER_MAGIC	0x2BAD1DEA
> 
> +#define CHECKPOINT_MAGIC_HEAD  0x00feed0cc0a2d200LL
> +#define CHECKPOINT_MAGIC_TAIL  0x002d2a0cc0deef00LL
> +
>   #endif /* __LINUX_MAGIC_H__ */
> -- 
> 1.5.4.3
> 
> _______________________________________________
> Containers mailing list
> Containers@...ts.linux-foundation.org
> https://lists.linux-foundation.org/mailman/listinfo/containers
--
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