Restore open file descriptors: for each FD read 'struct cr_hdr_fd_ent' and lookup objref in the hash table; if not found (first occurence), read in 'struct cr_hdr_fd_data', create a new FD and register in the hash. Otherwise attach the file pointer from the hash as an FD.
This patch only handles basic FDs - regular files, directories and also symbolic links. Changelog[v14]: - Revert change to pr_debug(), back to cr_debug() - Rename: cr_read_files() => cr_read_fd_table() - Rename: cr_read_fd_data() => cr_read_file() - Discard field 'hh->parent' - Check whether calls to cr_hbuf_get() fail Changelog[v12]: - Replace obsolete cr_debug() with pr_debug() Changelog[v6]: - Balance all calls to cr_hbuf_get() with matching cr_hbuf_put() (even though it's not really needed) Signed-off-by: Oren Laadan <or...@cs.columbia.edu> Acked-by: Serge Hallyn <se...@us.ibm.com> Signed-off-by: Dave Hansen <d...@linux.vnet.ibm.com> --- checkpoint/Makefile | 2 +- checkpoint/rstr_file.c | 236 ++++++++++++++++++++++++++++++++++++++++++++ checkpoint/rstr_task.c | 4 + include/linux/checkpoint.h | 1 + 4 files changed, 242 insertions(+), 1 deletions(-) create mode 100644 checkpoint/rstr_file.c diff --git a/checkpoint/Makefile b/checkpoint/Makefile index 306e676..420c2e6 100644 --- a/checkpoint/Makefile +++ b/checkpoint/Makefile @@ -6,4 +6,4 @@ obj-$(CONFIG_CHECKPOINT) += sys.o objhash.o \ checkpoint.o restart.o \ ckpt_task.o rstr_task.o \ ckpt_mem.o rstr_mem.o \ - ckpt_file.o + ckpt_file.o rstr_file.o diff --git a/checkpoint/rstr_file.c b/checkpoint/rstr_file.c new file mode 100644 index 0000000..4a2b47e --- /dev/null +++ b/checkpoint/rstr_file.c @@ -0,0 +1,236 @@ +/* + * Checkpoint file descriptors + * + * Copyright (C) 2008-2009 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/fs.h> +#include <linux/file.h> +#include <linux/fdtable.h> +#include <linux/fsnotify.h> +#include <linux/syscalls.h> +#include <linux/checkpoint.h> +#include <linux/checkpoint_hdr.h> + +#include "checkpoint_file.h" + +static int cr_close_all_fds(struct files_struct *files) +{ + int *fdtable; + int nfds; + + nfds = cr_scan_fds(files, &fdtable); + if (nfds < 0) + return nfds; + while (nfds--) + sys_close(fdtable[nfds]); + kfree(fdtable); + return 0; +} + +/** + * cr_attach_file - attach a lonely file ptr to a file descriptor + * @file: lonely file pointer + */ +static int cr_attach_file(struct file *file) +{ + int fd = get_unused_fd_flags(0); + + if (fd >= 0) { + fsnotify_open(file->f_path.dentry); + fd_install(fd, file); + } + return fd; +} + +/** + * cr_attach_get_file - attach (and get) lonely file ptr to a file descriptor + * @file: lonely file pointer + */ +static int cr_attach_get_file(struct file *file) +{ + int fd = get_unused_fd_flags(0); + + if (fd >= 0) { + fsnotify_open(file->f_path.dentry); + get_file(file); + fd_install(fd, file); + } + return fd; +} + +#define CR_SETFL_MASK (O_APPEND|O_NONBLOCK|O_NDELAY|FASYNC|O_DIRECT|O_NOATIME) + +/* cr_read_file - restore the state of a given file pointer */ +static int cr_read_file(struct cr_ctx *ctx, int objref) +{ + struct cr_hdr_file *hh; + struct file *file; + int fd = 0; /* pacify gcc warning */ + int ret; + + hh = cr_hbuf_get(ctx, sizeof(*hh)); + if (!hh) + return -ENOMEM; + + ret = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_FILE); + cr_debug("flags %#x mode %#x how %d\n", + hh->f_flags, hh->f_mode, hh->fd_type); + if (ret < 0) + goto out; + + ret = -EINVAL; + + /* FIX: more sanity checks on f_flags, f_mode etc */ + + switch (hh->fd_type) { + case CR_FD_GENERIC: + file = cr_read_open_fname(ctx, hh->f_flags, hh->f_mode); + break; + default: + goto out; + } + + if (IS_ERR(file)) { + ret = PTR_ERR(file); + goto out; + } + + /* FIX: need to restore uid, gid, owner etc */ + + /* adding <objref,file> to the hash will keep a reference to it */ + ret = cr_obj_add_ref(ctx, file, objref, CR_OBJ_FILE, 0); + if (ret < 0) { + filp_close(file, NULL); + goto out; + } + + fd = cr_attach_file(file); /* no need to cleanup 'file' below */ + if (fd < 0) { + ret = fd; + filp_close(file, NULL); + goto out; + } + + ret = sys_fcntl(fd, F_SETFL, hh->f_flags & CR_SETFL_MASK); + if (ret < 0) + goto out; + ret = vfs_llseek(file, hh->f_pos, SEEK_SET); + if (ret == -ESPIPE) /* ignore error on non-seekable files */ + ret = 0; + + ret = 0; + out: + cr_hbuf_put(ctx, sizeof(*hh)); + return ret < 0 ? ret : fd; +} + +/** + * cr_read_fd_ent - restore the state of a given file descriptor + * @ctx: checkpoint context + * + * Restores the state of a file descriptor; looks up the objref (in the + * header) in the hash table, and if found picks the matching file and + * use it; otherwise calls cr_read_file to restore the file too. + */ +static int cr_read_fd_ent(struct cr_ctx *ctx) +{ + struct cr_hdr_fd_ent *hh; + struct file *file; + int newfd, ret; + + hh = cr_hbuf_get(ctx, sizeof(*hh)); + if (!hh) + return -ENOMEM; + + ret = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_FD_ENT); + if (ret < 0) + goto out; + + cr_debug("ref %d fd %d c.o.e %d\n", + hh->objref, hh->fd, hh->close_on_exec); + + ret = -EINVAL; + if (hh->objref <= 0 || hh->fd < 0) + goto out; + + file = cr_obj_get_by_ref(ctx, hh->objref, CR_OBJ_FILE); + if (IS_ERR(file)) { + ret = PTR_ERR(file); + goto out; + } + + if (file) { + /* reuse file pointer found in the hash table */ + newfd = cr_attach_get_file(file); + } else { + /* create new file pointer (and register in hash table) */ + newfd = cr_read_file(ctx, hh->objref); + } + + if (newfd < 0) { + ret = newfd; + goto out; + } + + cr_debug("newfd got %d wanted %d\n", newfd, hh->fd); + + /* if newfd isn't desired fd then reposition it */ + if (newfd != hh->fd) { + ret = sys_dup2(newfd, hh->fd); + if (ret < 0) + goto out; + sys_close(newfd); + } + + if (hh->close_on_exec) + set_close_on_exec(hh->fd, 1); + + ret = 0; + out: + cr_hbuf_put(ctx, sizeof(*hh)); + return ret; +} + +int cr_read_fd_table(struct cr_ctx *ctx) +{ + struct cr_hdr_fd_table *hh; + int i, ret; + + hh = cr_hbuf_get(ctx, sizeof(*hh)); + if (!hh) + return -ENOMEM; + + ret = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_FD_TABLE); + if (ret < 0) + goto out; + + cr_debug("objref %d nfds %d\n", hh->objref, hh->nfds); + + if (hh->nfds < 0 || hh->nfds > sysctl_nr_open) { + ret = -EMFILE; + goto out; + } + + /* point of no return -- close all file descriptors */ + ret = cr_close_all_fds(current->files); + if (ret < 0) + goto out; + + for (i = 0; i < hh->nfds; i++) { + ret = cr_read_fd_ent(ctx); + if (ret < 0) + break; + } + + ret = 0; + out: + cr_hbuf_put(ctx, sizeof(*hh)); + return ret; +} diff --git a/checkpoint/rstr_task.c b/checkpoint/rstr_task.c index 6aa9c6b..93c86ab 100644 --- a/checkpoint/rstr_task.c +++ b/checkpoint/rstr_task.c @@ -65,6 +65,10 @@ int cr_read_task(struct cr_ctx *ctx) cr_debug("memory: ret %d\n", ret); if (ret < 0) goto out; + ret = cr_read_fd_table(ctx); + cr_debug("files: ret %d\n", ret); + if (ret < 0) + goto out; ret = cr_read_thread(ctx); cr_debug("thread: ret %d\n", ret); if (ret < 0) diff --git a/include/linux/checkpoint.h b/include/linux/checkpoint.h index 506c719..b7ca0e9 100644 --- a/include/linux/checkpoint.h +++ b/include/linux/checkpoint.h @@ -90,6 +90,7 @@ extern int cr_write_fd_table(struct cr_ctx *ctx, struct task_struct *t); extern int cr_read_task(struct cr_ctx *ctx); extern int cr_read_mm(struct cr_ctx *ctx); +extern int cr_read_fd_table(struct cr_ctx *ctx); extern int do_checkpoint(struct cr_ctx *ctx, pid_t pid); extern int do_restart(struct cr_ctx *ctx, pid_t pid); -- 1.5.4.3 _______________________________________________ Containers mailing list contain...@lists.linux-foundation.org https://lists.linux-foundation.org/mailman/listinfo/containers _______________________________________________ Devel mailing list Devel@openvz.org https://openvz.org/mailman/listinfo/devel