Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752575AbYKXBTw (ORCPT ); Sun, 23 Nov 2008 20:19:52 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751668AbYKXBTn (ORCPT ); Sun, 23 Nov 2008 20:19:43 -0500 Received: from mail-in-14.arcor-online.net ([151.189.21.54]:55126 "EHLO mail-in-14.arcor-online.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751624AbYKXBTl (ORCPT ); Sun, 23 Nov 2008 20:19:41 -0500 From: Bodo Eggert <7eggert@gmx.de> Subject: Re: Robust shared memory for unrelated processes To: Chris Smowton , linux-kernel@vger.kernel.org Reply-To: 7eggert@gmx.de Date: Mon, 24 Nov 2008 02:19:33 +0100 References: User-Agent: KNode/0.10.4 MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7Bit Message-Id: X-be10.7eggert.dyndns.org-MailScanner-Information: See www.mailscanner.info for information X-be10.7eggert.dyndns.org-MailScanner: Found to be clean X-be10.7eggert.dyndns.org-MailScanner-From: 7eggert@gmx.de Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 8156 Lines: 192 Chris Smowton wrote: > Suppose for simplicity's sake that one wishes to share a sizable piece > of memory with a single other process with which one is already in > contact (say, by a Unix domain socket). > > It seems to me that one cannot do this without introducing the risk of > the shared section not being deallocated until the system next boots, [...] > 3. It needs to be possible for a general file to atomically created and > registered for deletion on closure of its last handle. This gives you an autounlink flag for tmpfs, which will get rid of your shared file as soon as the last process closes it. Unfortunately I don't remember if link()ing it will make it stay. diff -X dontdiff -dpruN linux-2.6.24.pure/include/linux/shmem_fs.h linux-2.6.24.autounlink/include/linux/shmem_fs.h --- linux-2.6.24.pure/include/linux/shmem_fs.h 2006-11-29 22:57:37.000000000 +0100 +++ linux-2.6.24.autounlink/include/linux/shmem_fs.h 2008-02-14 15:35:01.000000000 +0100 @@ -30,11 +30,14 @@ struct shmem_sb_info { unsigned long free_blocks; /* How many are left for allocation */ unsigned long max_inodes; /* How many inodes are allowed */ unsigned long free_inodes; /* How many are left for allocation */ - int policy; /* Default NUMA memory alloc policy */ - nodemask_t policy_nodes; /* nodemask for preferred and bind */ + unsigned int flags; + int policy; /* Default NUMA memory alloc policy */ + nodemask_t policy_nodes; /* nodemask for preferred and bind */ spinlock_t stat_lock; }; +#define TMPFS_FL_AUTOREMOVE 1 + static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) { return container_of(inode, struct shmem_inode_info, vfs_inode); diff -X dontdiff -dpruN linux-2.6.24.pure/mm/shmem.c linux-2.6.24.autounlink/mm/shmem.c --- linux-2.6.24.pure/mm/shmem.c 2008-01-25 15:09:39.000000000 +0100 +++ linux-2.6.24.autounlink/mm/shmem.c 2008-02-14 18:00:54.000000000 +0100 @@ -1747,31 +1747,41 @@ static int shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) { struct inode *inode = shmem_get_inode(dir->i_sb, mode, dev); + struct shmem_sb_info *sbinfo = SHMEM_SB(dir->i_sb); int error = -ENOSPC; - if (inode) { - error = security_inode_init_security(inode, dir, NULL, NULL, - NULL); - if (error) { - if (error != -EOPNOTSUPP) { - iput(inode); - return error; - } - } - error = shmem_acl_init(inode, dir); - if (error) { + if (!inode) + return error; + + error = security_inode_init_security(inode, dir, NULL, NULL, + NULL); + if (error) { + if (error != -EOPNOTSUPP) { iput(inode); return error; } - if (dir->i_mode & S_ISGID) { - inode->i_gid = dir->i_gid; - if (S_ISDIR(mode)) - inode->i_mode |= S_ISGID; - } - dir->i_size += BOGO_DIRENT_SIZE; - dir->i_ctime = dir->i_mtime = CURRENT_TIME; - d_instantiate(dentry, inode); + } + error = shmem_acl_init(inode, dir); + if (error) { + iput(inode); + return error; + } + if (dir->i_mode & S_ISGID) { + inode->i_gid = dir->i_gid; + if (S_ISDIR(mode)) + inode->i_mode |= S_ISGID; + } + + dir->i_size += BOGO_DIRENT_SIZE; + dir->i_ctime = dir->i_mtime = CURRENT_TIME; + d_instantiate(dentry, inode); + if ( S_ISDIR(mode) + || !(sbinfo->flags & TMPFS_FL_AUTOREMOVE)) + { dget(dentry); /* Extra count - pin the dentry in core */ + } else { + dir->i_size -= BOGO_DIRENT_SIZE; + drop_nlink(inode); } return error; } @@ -1800,6 +1810,11 @@ static int shmem_link(struct dentry *old struct inode *inode = old_dentry->d_inode; struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + /* In auto-unlink mode, the newly created link would be unlinked + immediately. We don't need to do anything here. */ + if (sbinfo->flags & TMPFS_FL_AUTOREMOVE) + return 0; + /* * No ordinary (disk based) filesystem counts links as inodes; * but each new link needs a new dentry, pinning lowmem, and @@ -2095,6 +2110,7 @@ static const struct export_operations sh static int shmem_parse_options(char *options, int *mode, uid_t *uid, gid_t *gid, unsigned long *blocks, unsigned long *inodes, + unsigned int * flags, int *policy, nodemask_t *policy_nodes) { char *this_char, *value, *rest; @@ -2120,8 +2136,18 @@ static int shmem_parse_options(char *opt continue; if ((value = strchr(this_char,'=')) != NULL) { *value++ = 0; + + /* These options don't take arguments: */ + } else if (!strcmp(this_char,"autounlink")) { + *flags |= TMPFS_FL_AUTOREMOVE; + continue; + } else if (!strcmp(this_char,"noautounlink")) { + *flags &= ~TMPFS_FL_AUTOREMOVE; + continue; + + /* All other options need an argument */ } else { - printk(KERN_ERR + printk(KERN_ERR "tmpfs: No value for mount option '%s'\n", this_char); return 1; @@ -2192,10 +2218,12 @@ static int shmem_remount_fs(struct super nodemask_t policy_nodes = sbinfo->policy_nodes; unsigned long blocks; unsigned long inodes; + unsigned int sbflags; int error = -EINVAL; + sbflags = sbinfo->flags; if (shmem_parse_options(data, NULL, NULL, NULL, &max_blocks, - &max_inodes, &policy, &policy_nodes)) + &max_inodes, &sbflags, &policy, &policy_nodes)) return error; spin_lock(&sbinfo->stat_lock); @@ -2221,6 +2249,7 @@ static int shmem_remount_fs(struct super sbinfo->free_blocks = max_blocks - blocks; sbinfo->max_inodes = max_inodes; sbinfo->free_inodes = max_inodes - inodes; + sbinfo->flags = sbflags; sbinfo->policy = policy; sbinfo->policy_nodes = policy_nodes; out: @@ -2247,6 +2276,7 @@ static int shmem_fill_super(struct super struct shmem_sb_info *sbinfo; unsigned long blocks = 0; unsigned long inodes = 0; + unsigned int flags = 0; int policy = MPOL_DEFAULT; nodemask_t policy_nodes = node_states[N_HIGH_MEMORY]; @@ -2262,7 +2292,7 @@ static int shmem_fill_super(struct super if (inodes > blocks) inodes = blocks; if (shmem_parse_options(data, &mode, &uid, &gid, &blocks, - &inodes, &policy, &policy_nodes)) + &inodes, &flags, &policy, &policy_nodes)) return -EINVAL; } sb->s_export_op = &shmem_export_ops; @@ -2281,6 +2311,7 @@ static int shmem_fill_super(struct super sbinfo->free_blocks = blocks; sbinfo->max_inodes = inodes; sbinfo->free_inodes = inodes; + sbinfo->flags = flags; sbinfo->policy = policy; sbinfo->policy_nodes = policy_nodes; -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/