From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756875AbZA0RK4 (ORCPT ); Tue, 27 Jan 2009 12:10:56 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1756241AbZA0RJ0 (ORCPT ); Tue, 27 Jan 2009 12:09:26 -0500 Received: from serrano.cc.columbia.edu ([128.59.29.6]:57667 "EHLO serrano.cc.columbia.edu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755898AbZA0RJV (ORCPT ); Tue, 27 Jan 2009 12:09:21 -0500 From: Oren Laadan To: Andrew Morton Cc: Linus Torvalds , containers@lists.linux-foundation.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, linux-api@vger.kernel.org, Thomas Gleixner , Serge Hallyn , Dave Hansen , Ingo Molnar , "H. Peter Anvin" , Alexander Viro , Oren Laadan Subject: [RFC v13][PATCH 10/14] Restore open file descriprtors Date: Tue, 27 Jan 2009 12:08:08 -0500 Message-Id: <1233076092-8660-11-git-send-email-orenl@cs.columbia.edu> X-Mailer: git-send-email 1.6.0.1 In-Reply-To: <1233076092-8660-1-git-send-email-orenl@cs.columbia.edu> References: <1233076092-8660-1-git-send-email-orenl@cs.columbia.edu> X-No-Spam-Score: Local Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 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[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 Acked-by: Serge Hallyn Signed-off-by: Dave Hansen --- checkpoint/Makefile | 2 +- checkpoint/restart.c | 4 + checkpoint/rstr_file.c | 248 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/checkpoint.h | 1 + 4 files changed, 254 insertions(+), 1 deletions(-) create mode 100644 checkpoint/rstr_file.c diff --git a/checkpoint/Makefile b/checkpoint/Makefile index 7496695..88bbc10 100644 --- a/checkpoint/Makefile +++ b/checkpoint/Makefile @@ -3,4 +3,4 @@ # obj-$(CONFIG_CHECKPOINT_RESTART) += sys.o checkpoint.o restart.o objhash.o \ - ckpt_mem.o rstr_mem.o ckpt_file.o + ckpt_mem.o rstr_mem.o ckpt_file.o rstr_file.o diff --git a/checkpoint/restart.c b/checkpoint/restart.c index 536d017..ece05b7 100644 --- a/checkpoint/restart.c +++ b/checkpoint/restart.c @@ -261,6 +261,10 @@ static int cr_read_task(struct cr_ctx *ctx) pr_debug("memory: ret %d\n", ret); if (ret < 0) goto out; + ret = cr_read_files(ctx); + pr_debug("files: ret %d\n", ret); + if (ret < 0) + goto out; ret = cr_read_thread(ctx); pr_debug("thread: ret %d\n", ret); if (ret < 0) diff --git a/checkpoint/rstr_file.c b/checkpoint/rstr_file.c new file mode 100644 index 0000000..f44b081 --- /dev/null +++ b/checkpoint/rstr_file.c @@ -0,0 +1,248 @@ +/* + * Checkpoint file descriptors + * + * 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 +#include +#include +#include +#include +#include +#include +#include +#include + +#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_fd_data - restore the state of a given file pointer */ +static int +cr_read_fd_data(struct cr_ctx *ctx, struct files_struct *files, int rparent) +{ + struct cr_hdr_fd_data *hh = cr_hbuf_get(ctx, sizeof(*hh)); + struct file *file; + int parent, ret; + int fd = 0; /* pacify gcc warning */ + + parent = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_FD_DATA); + pr_debug("rparent %d parent %d flags %#x mode %#x how %d\n", + rparent, parent, hh->f_flags, hh->f_mode, hh->fd_type); + if (parent < 0) { + ret = parent; + goto out; + } + + ret = -EINVAL; + + if (parent != rparent) + goto out; + + /* FIX: more sanity checks on f_flags, f_mode etc */ + + switch (hh->fd_type) { + case CR_FD_FILE: + case CR_FD_DIR: + 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 to the hash will keep a reference to it */ + ret = cr_obj_add_ref(ctx, file, parent, 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 + * @files: files_struct pointer + * @parent: parent objref + * + * 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_fd_data to restore the file too. + */ +static int +cr_read_fd_ent(struct cr_ctx *ctx, struct files_struct *files, int rparent) +{ + struct cr_hdr_fd_ent *hh = cr_hbuf_get(ctx, sizeof(*hh)); + struct file *file; + int newfd, parent, ret; + + parent = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_FD_ENT); + pr_debug("rparent %d parent %d ref %d fd %d c.o.e %d\n", + rparent, parent, hh->objref, hh->fd, hh->close_on_exec); + if (parent < 0) { + ret = parent; + goto out; + } + + ret = -EINVAL; + + if (parent != rparent) + goto out; + if (hh->objref <= 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 descriptor found in the hash table */ + newfd = cr_attach_get_file(file); + } else { + /* create new file pointer (and register in hash table) */ + newfd = cr_read_fd_data(ctx, files, hh->objref); + } + + if (newfd < 0) { + ret = newfd; + goto out; + } + + pr_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_files(struct cr_ctx *ctx) +{ + struct cr_hdr_files *hh = cr_hbuf_get(ctx, sizeof(*hh)); + struct files_struct *files = current->files; + int i, parent, ret; + + parent = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_FILES); + if (parent < 0) { + ret = parent; + goto out; + } + + ret = -EINVAL; +#if 0 /* activate when containers are used */ + if (parent != task_pid_vnr(current)) + goto out; +#endif + pr_debug("objref %d nfds %d\n", hh->objref, hh->nfds); + if (hh->objref < 0 || hh->nfds < 0) + goto out; + + if (hh->nfds > sysctl_nr_open) { + ret = -EMFILE; + goto out; + } + + /* point of no return -- close all file descriptors */ + ret = cr_close_all_fds(files); + if (ret < 0) + goto out; + + for (i = 0; i < hh->nfds; i++) { + ret = cr_read_fd_ent(ctx, files, hh->objref); + if (ret < 0) + break; + } + + ret = 0; + out: + cr_hbuf_put(ctx, sizeof(*hh)); + return ret; +} diff --git a/include/linux/checkpoint.h b/include/linux/checkpoint.h index 59cc515..ea9ab4c 100644 --- a/include/linux/checkpoint.h +++ b/include/linux/checkpoint.h @@ -89,6 +89,7 @@ extern int cr_write_files(struct cr_ctx *ctx, struct task_struct *t); extern int do_restart(struct cr_ctx *ctx, pid_t pid); extern int cr_read_mm(struct cr_ctx *ctx); +extern int cr_read_files(struct cr_ctx *ctx); #ifdef pr_fmt #undef pr_fmt -- 1.5.4.3 From mboxrd@z Thu Jan 1 00:00:00 1970 From: Oren Laadan Subject: [RFC v13][PATCH 10/14] Restore open file descriprtors Date: Tue, 27 Jan 2009 12:08:08 -0500 Message-ID: <1233076092-8660-11-git-send-email-orenl@cs.columbia.edu> References: <1233076092-8660-1-git-send-email-orenl@cs.columbia.edu> Return-path: In-Reply-To: <1233076092-8660-1-git-send-email-orenl-eQaUEPhvms7ENvBUuze7eA@public.gmane.org> Sender: linux-api-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Andrew Morton Cc: Linus Torvalds , containers-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org, linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Thomas Gleixner , Serge Hallyn , Dave Hansen , Ingo Molnar , "H. Peter Anvin" , Alexander Viro , Oren Laadan List-Id: linux-api@vger.kernel.org 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[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 Acked-by: Serge Hallyn Signed-off-by: Dave Hansen --- checkpoint/Makefile | 2 +- checkpoint/restart.c | 4 + checkpoint/rstr_file.c | 248 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/checkpoint.h | 1 + 4 files changed, 254 insertions(+), 1 deletions(-) create mode 100644 checkpoint/rstr_file.c diff --git a/checkpoint/Makefile b/checkpoint/Makefile index 7496695..88bbc10 100644 --- a/checkpoint/Makefile +++ b/checkpoint/Makefile @@ -3,4 +3,4 @@ # obj-$(CONFIG_CHECKPOINT_RESTART) += sys.o checkpoint.o restart.o objhash.o \ - ckpt_mem.o rstr_mem.o ckpt_file.o + ckpt_mem.o rstr_mem.o ckpt_file.o rstr_file.o diff --git a/checkpoint/restart.c b/checkpoint/restart.c index 536d017..ece05b7 100644 --- a/checkpoint/restart.c +++ b/checkpoint/restart.c @@ -261,6 +261,10 @@ static int cr_read_task(struct cr_ctx *ctx) pr_debug("memory: ret %d\n", ret); if (ret < 0) goto out; + ret = cr_read_files(ctx); + pr_debug("files: ret %d\n", ret); + if (ret < 0) + goto out; ret = cr_read_thread(ctx); pr_debug("thread: ret %d\n", ret); if (ret < 0) diff --git a/checkpoint/rstr_file.c b/checkpoint/rstr_file.c new file mode 100644 index 0000000..f44b081 --- /dev/null +++ b/checkpoint/rstr_file.c @@ -0,0 +1,248 @@ +/* + * Checkpoint file descriptors + * + * 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 +#include +#include +#include +#include +#include +#include +#include +#include + +#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_fd_data - restore the state of a given file pointer */ +static int +cr_read_fd_data(struct cr_ctx *ctx, struct files_struct *files, int rparent) +{ + struct cr_hdr_fd_data *hh = cr_hbuf_get(ctx, sizeof(*hh)); + struct file *file; + int parent, ret; + int fd = 0; /* pacify gcc warning */ + + parent = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_FD_DATA); + pr_debug("rparent %d parent %d flags %#x mode %#x how %d\n", + rparent, parent, hh->f_flags, hh->f_mode, hh->fd_type); + if (parent < 0) { + ret = parent; + goto out; + } + + ret = -EINVAL; + + if (parent != rparent) + goto out; + + /* FIX: more sanity checks on f_flags, f_mode etc */ + + switch (hh->fd_type) { + case CR_FD_FILE: + case CR_FD_DIR: + 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 to the hash will keep a reference to it */ + ret = cr_obj_add_ref(ctx, file, parent, 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 + * @files: files_struct pointer + * @parent: parent objref + * + * 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_fd_data to restore the file too. + */ +static int +cr_read_fd_ent(struct cr_ctx *ctx, struct files_struct *files, int rparent) +{ + struct cr_hdr_fd_ent *hh = cr_hbuf_get(ctx, sizeof(*hh)); + struct file *file; + int newfd, parent, ret; + + parent = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_FD_ENT); + pr_debug("rparent %d parent %d ref %d fd %d c.o.e %d\n", + rparent, parent, hh->objref, hh->fd, hh->close_on_exec); + if (parent < 0) { + ret = parent; + goto out; + } + + ret = -EINVAL; + + if (parent != rparent) + goto out; + if (hh->objref <= 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 descriptor found in the hash table */ + newfd = cr_attach_get_file(file); + } else { + /* create new file pointer (and register in hash table) */ + newfd = cr_read_fd_data(ctx, files, hh->objref); + } + + if (newfd < 0) { + ret = newfd; + goto out; + } + + pr_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_files(struct cr_ctx *ctx) +{ + struct cr_hdr_files *hh = cr_hbuf_get(ctx, sizeof(*hh)); + struct files_struct *files = current->files; + int i, parent, ret; + + parent = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_FILES); + if (parent < 0) { + ret = parent; + goto out; + } + + ret = -EINVAL; +#if 0 /* activate when containers are used */ + if (parent != task_pid_vnr(current)) + goto out; +#endif + pr_debug("objref %d nfds %d\n", hh->objref, hh->nfds); + if (hh->objref < 0 || hh->nfds < 0) + goto out; + + if (hh->nfds > sysctl_nr_open) { + ret = -EMFILE; + goto out; + } + + /* point of no return -- close all file descriptors */ + ret = cr_close_all_fds(files); + if (ret < 0) + goto out; + + for (i = 0; i < hh->nfds; i++) { + ret = cr_read_fd_ent(ctx, files, hh->objref); + if (ret < 0) + break; + } + + ret = 0; + out: + cr_hbuf_put(ctx, sizeof(*hh)); + return ret; +} diff --git a/include/linux/checkpoint.h b/include/linux/checkpoint.h index 59cc515..ea9ab4c 100644 --- a/include/linux/checkpoint.h +++ b/include/linux/checkpoint.h @@ -89,6 +89,7 @@ extern int cr_write_files(struct cr_ctx *ctx, struct task_struct *t); extern int do_restart(struct cr_ctx *ctx, pid_t pid); extern int cr_read_mm(struct cr_ctx *ctx); +extern int cr_read_files(struct cr_ctx *ctx); #ifdef pr_fmt #undef pr_fmt -- 1.5.4.3 -- To unsubscribe from this list: send the line "unsubscribe linux-api" in the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail202.messagelabs.com (mail202.messagelabs.com [216.82.254.227]) by kanga.kvack.org (Postfix) with ESMTP id 1351B6B0088 for ; Tue, 27 Jan 2009 12:08:49 -0500 (EST) From: Oren Laadan Subject: [RFC v13][PATCH 10/14] Restore open file descriprtors Date: Tue, 27 Jan 2009 12:08:08 -0500 Message-Id: <1233076092-8660-11-git-send-email-orenl@cs.columbia.edu> In-Reply-To: <1233076092-8660-1-git-send-email-orenl@cs.columbia.edu> References: <1233076092-8660-1-git-send-email-orenl@cs.columbia.edu> Sender: owner-linux-mm@kvack.org To: Andrew Morton Cc: Linus Torvalds , containers@lists.linux-foundation.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, linux-api@vger.kernel.org, Thomas Gleixner , Serge Hallyn , Dave Hansen , Ingo Molnar , "H. Peter Anvin" , Alexander Viro , Oren Laadan List-ID: 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[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 Acked-by: Serge Hallyn Signed-off-by: Dave Hansen --- checkpoint/Makefile | 2 +- checkpoint/restart.c | 4 + checkpoint/rstr_file.c | 248 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/checkpoint.h | 1 + 4 files changed, 254 insertions(+), 1 deletions(-) create mode 100644 checkpoint/rstr_file.c diff --git a/checkpoint/Makefile b/checkpoint/Makefile index 7496695..88bbc10 100644 --- a/checkpoint/Makefile +++ b/checkpoint/Makefile @@ -3,4 +3,4 @@ # obj-$(CONFIG_CHECKPOINT_RESTART) += sys.o checkpoint.o restart.o objhash.o \ - ckpt_mem.o rstr_mem.o ckpt_file.o + ckpt_mem.o rstr_mem.o ckpt_file.o rstr_file.o diff --git a/checkpoint/restart.c b/checkpoint/restart.c index 536d017..ece05b7 100644 --- a/checkpoint/restart.c +++ b/checkpoint/restart.c @@ -261,6 +261,10 @@ static int cr_read_task(struct cr_ctx *ctx) pr_debug("memory: ret %d\n", ret); if (ret < 0) goto out; + ret = cr_read_files(ctx); + pr_debug("files: ret %d\n", ret); + if (ret < 0) + goto out; ret = cr_read_thread(ctx); pr_debug("thread: ret %d\n", ret); if (ret < 0) diff --git a/checkpoint/rstr_file.c b/checkpoint/rstr_file.c new file mode 100644 index 0000000..f44b081 --- /dev/null +++ b/checkpoint/rstr_file.c @@ -0,0 +1,248 @@ +/* + * Checkpoint file descriptors + * + * 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 +#include +#include +#include +#include +#include +#include +#include +#include + +#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_fd_data - restore the state of a given file pointer */ +static int +cr_read_fd_data(struct cr_ctx *ctx, struct files_struct *files, int rparent) +{ + struct cr_hdr_fd_data *hh = cr_hbuf_get(ctx, sizeof(*hh)); + struct file *file; + int parent, ret; + int fd = 0; /* pacify gcc warning */ + + parent = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_FD_DATA); + pr_debug("rparent %d parent %d flags %#x mode %#x how %d\n", + rparent, parent, hh->f_flags, hh->f_mode, hh->fd_type); + if (parent < 0) { + ret = parent; + goto out; + } + + ret = -EINVAL; + + if (parent != rparent) + goto out; + + /* FIX: more sanity checks on f_flags, f_mode etc */ + + switch (hh->fd_type) { + case CR_FD_FILE: + case CR_FD_DIR: + 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 to the hash will keep a reference to it */ + ret = cr_obj_add_ref(ctx, file, parent, 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 + * @files: files_struct pointer + * @parent: parent objref + * + * 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_fd_data to restore the file too. + */ +static int +cr_read_fd_ent(struct cr_ctx *ctx, struct files_struct *files, int rparent) +{ + struct cr_hdr_fd_ent *hh = cr_hbuf_get(ctx, sizeof(*hh)); + struct file *file; + int newfd, parent, ret; + + parent = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_FD_ENT); + pr_debug("rparent %d parent %d ref %d fd %d c.o.e %d\n", + rparent, parent, hh->objref, hh->fd, hh->close_on_exec); + if (parent < 0) { + ret = parent; + goto out; + } + + ret = -EINVAL; + + if (parent != rparent) + goto out; + if (hh->objref <= 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 descriptor found in the hash table */ + newfd = cr_attach_get_file(file); + } else { + /* create new file pointer (and register in hash table) */ + newfd = cr_read_fd_data(ctx, files, hh->objref); + } + + if (newfd < 0) { + ret = newfd; + goto out; + } + + pr_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_files(struct cr_ctx *ctx) +{ + struct cr_hdr_files *hh = cr_hbuf_get(ctx, sizeof(*hh)); + struct files_struct *files = current->files; + int i, parent, ret; + + parent = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_FILES); + if (parent < 0) { + ret = parent; + goto out; + } + + ret = -EINVAL; +#if 0 /* activate when containers are used */ + if (parent != task_pid_vnr(current)) + goto out; +#endif + pr_debug("objref %d nfds %d\n", hh->objref, hh->nfds); + if (hh->objref < 0 || hh->nfds < 0) + goto out; + + if (hh->nfds > sysctl_nr_open) { + ret = -EMFILE; + goto out; + } + + /* point of no return -- close all file descriptors */ + ret = cr_close_all_fds(files); + if (ret < 0) + goto out; + + for (i = 0; i < hh->nfds; i++) { + ret = cr_read_fd_ent(ctx, files, hh->objref); + if (ret < 0) + break; + } + + ret = 0; + out: + cr_hbuf_put(ctx, sizeof(*hh)); + return ret; +} diff --git a/include/linux/checkpoint.h b/include/linux/checkpoint.h index 59cc515..ea9ab4c 100644 --- a/include/linux/checkpoint.h +++ b/include/linux/checkpoint.h @@ -89,6 +89,7 @@ extern int cr_write_files(struct cr_ctx *ctx, struct task_struct *t); extern int do_restart(struct cr_ctx *ctx, pid_t pid); extern int cr_read_mm(struct cr_ctx *ctx); +extern int cr_read_files(struct cr_ctx *ctx); #ifdef pr_fmt #undef pr_fmt -- 1.5.4.3 -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org