diff options
Diffstat (limited to 'fs')
134 files changed, 2209 insertions, 1604 deletions
diff --git a/fs/9p/fid.c b/fs/9p/fid.c index b364da70ff2..dfebdbe7440 100644 --- a/fs/9p/fid.c +++ b/fs/9p/fid.c @@ -175,7 +175,7 @@ struct p9_fid *v9fs_fid_lookup(struct dentry *dentry) if (!wnames) return ERR_PTR(-ENOMEM); - for (d = dentry, i = n; i >= 0; i--, d = d->d_parent) + for (d = dentry, i = (n-1); i >= 0; i--, d = d->d_parent) wnames[i] = (char *) d->d_name.name; clone = 1; @@ -183,7 +183,7 @@ struct p9_fid *v9fs_fid_lookup(struct dentry *dentry) while (i < n) { l = min(n - i, P9_MAXWELEM); fid = p9_client_walk(fid, l, &wnames[i], clone); - if (!fid) { + if (IS_ERR(fid)) { kfree(wnames); return fid; } diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index fbb12dadba8..9b0f0222e8b 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -3,7 +3,7 @@ * * This file contains functions assisting in mapping VFS to 9P2000 * - * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com> + * Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov> * * This program is free software; you can redistribute it and/or modify @@ -31,7 +31,6 @@ #include <linux/idr.h> #include <net/9p/9p.h> #include <net/9p/transport.h> -#include <net/9p/conn.h> #include <net/9p/client.h> #include "v9fs.h" #include "v9fs_vfs.h" @@ -43,11 +42,11 @@ enum { /* Options that take integer arguments */ - Opt_debug, Opt_msize, Opt_dfltuid, Opt_dfltgid, Opt_afid, + Opt_debug, Opt_dfltuid, Opt_dfltgid, Opt_afid, /* String options */ Opt_uname, Opt_remotename, Opt_trans, /* Options that take no arguments */ - Opt_legacy, Opt_nodevmap, + Opt_nodevmap, /* Cache options */ Opt_cache_loose, /* Access options */ @@ -58,14 +57,11 @@ enum { static match_table_t tokens = { {Opt_debug, "debug=%x"}, - {Opt_msize, "msize=%u"}, {Opt_dfltuid, "dfltuid=%u"}, {Opt_dfltgid, "dfltgid=%u"}, {Opt_afid, "afid=%u"}, {Opt_uname, "uname=%s"}, {Opt_remotename, "aname=%s"}, - {Opt_trans, "trans=%s"}, - {Opt_legacy, "noextend"}, {Opt_nodevmap, "nodevmap"}, {Opt_cache_loose, "cache=loose"}, {Opt_cache_loose, "loose"}, @@ -85,16 +81,14 @@ static void v9fs_parse_options(struct v9fs_session_info *v9ses) char *options; substring_t args[MAX_OPT_ARGS]; char *p; - int option; - int ret; + int option = 0; char *s, *e; + int ret; /* setup defaults */ - v9ses->maxdata = 8192; v9ses->afid = ~0; v9ses->debug = 0; v9ses->cache = 0; - v9ses->trans = v9fs_default_trans(); if (!v9ses->options) return; @@ -106,7 +100,8 @@ static void v9fs_parse_options(struct v9fs_session_info *v9ses) continue; token = match_token(p, tokens, args); if (token < Opt_uname) { - if ((ret = match_int(&args[0], &option)) < 0) { + ret = match_int(&args[0], &option); + if (ret < 0) { P9_DPRINTK(P9_DEBUG_ERROR, "integer field, but no integer?\n"); continue; @@ -119,9 +114,7 @@ static void v9fs_parse_options(struct v9fs_session_info *v9ses) p9_debug_level = option; #endif break; - case Opt_msize: - v9ses->maxdata = option; - break; + case Opt_dfltuid: v9ses->dfltuid = option; break; @@ -131,18 +124,12 @@ static void v9fs_parse_options(struct v9fs_session_info *v9ses) case Opt_afid: v9ses->afid = option; break; - case Opt_trans: - v9ses->trans = v9fs_match_trans(&args[0]); - break; case Opt_uname: match_strcpy(v9ses->uname, &args[0]); break; case Opt_remotename: match_strcpy(v9ses->aname, &args[0]); break; - case Opt_legacy: - v9ses->flags &= ~V9FS_EXTENDED; - break; case Opt_nodevmap: v9ses->nodev = 1; break; @@ -185,7 +172,6 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, const char *dev_name, char *data) { int retval = -EINVAL; - struct p9_trans *trans = NULL; struct p9_fid *fid; v9ses->uname = __getname(); @@ -207,24 +193,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, v9ses->options = kstrdup(data, GFP_KERNEL); v9fs_parse_options(v9ses); - if (v9ses->trans == NULL) { - retval = -EPROTONOSUPPORT; - P9_DPRINTK(P9_DEBUG_ERROR, - "No transport defined or default transport\n"); - goto error; - } - - trans = v9ses->trans->create(dev_name, v9ses->options); - if (IS_ERR(trans)) { - retval = PTR_ERR(trans); - trans = NULL; - goto error; - } - if ((v9ses->maxdata+P9_IOHDRSZ) > v9ses->trans->maxsize) - v9ses->maxdata = v9ses->trans->maxsize-P9_IOHDRSZ; - - v9ses->clnt = p9_client_create(trans, v9ses->maxdata+P9_IOHDRSZ, - v9fs_extended(v9ses)); + v9ses->clnt = p9_client_create(dev_name, v9ses->options); if (IS_ERR(v9ses->clnt)) { retval = PTR_ERR(v9ses->clnt); @@ -236,6 +205,8 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, if (!v9ses->clnt->dotu) v9ses->flags &= ~V9FS_EXTENDED; + v9ses->maxdata = v9ses->clnt->msize; + /* for legacy mode, fall back to V9FS_ACCESS_ANY */ if (!v9fs_extended(v9ses) && ((v9ses->flags&V9FS_ACCESS_MASK) == V9FS_ACCESS_USER)) { diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index db4b4193f2e..7d3a1018db5 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -1,7 +1,7 @@ /* * V9FS definitions. * - * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com> + * Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov> * * This program is free software; you can redistribute it and/or modify @@ -28,7 +28,6 @@ struct v9fs_session_info { /* options */ - unsigned int maxdata; unsigned char flags; /* session flags */ unsigned char nodev; /* set to 1 if no disable device mapping */ unsigned short debug; /* debug level */ @@ -38,10 +37,10 @@ struct v9fs_session_info { char *options; /* copy of mount options */ char *uname; /* user name to mount as */ char *aname; /* name of remote hierarchy being mounted */ + unsigned int maxdata; /* max data for client interface */ unsigned int dfltuid; /* default uid/muid for legacy support */ unsigned int dfltgid; /* default gid for legacy support */ u32 uid; /* if ACCESS_SINGLE, the uid that has access */ - struct p9_trans_module *trans; /* 9p transport */ struct p9_client *clnt; /* 9p client */ struct dentry *debugfs_dir; }; diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index ba4b1caa9c4..a616fff8906 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -184,7 +184,7 @@ static const struct file_operations v9fs_cached_file_operations = { .open = v9fs_file_open, .release = v9fs_dir_release, .lock = v9fs_file_lock, - .mmap = generic_file_mmap, + .mmap = generic_file_readonly_mmap, }; const struct file_operations v9fs_file_operations = { @@ -194,5 +194,5 @@ const struct file_operations v9fs_file_operations = { .open = v9fs_file_open, .release = v9fs_dir_release, .lock = v9fs_file_lock, - .mmap = generic_file_mmap, + .mmap = generic_file_readonly_mmap, }; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 23581bcb599..5c5137c1148 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -77,6 +77,8 @@ static int unixmode2p9mode(struct v9fs_session_info *v9ses, int mode) res |= P9_DMSETUID; if ((mode & S_ISGID) == S_ISGID) res |= P9_DMSETGID; + if ((mode & S_ISVTX) == S_ISVTX) + res |= P9_DMSETVTX; if ((mode & P9_DMLINK)) res |= P9_DMLINK; } @@ -119,6 +121,9 @@ static int p9mode2unixmode(struct v9fs_session_info *v9ses, int mode) if ((mode & P9_DMSETGID) == P9_DMSETGID) res |= S_ISGID; + + if ((mode & P9_DMSETVTX) == P9_DMSETVTX) + res |= S_ISVTX; } return res; diff --git a/fs/Kconfig b/fs/Kconfig index 219ec06a8c7..ea5b3594762 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -1152,7 +1152,7 @@ config BEFS_DEBUG depends on BEFS_FS help If you say Y here, you can use the 'debug' mount option to enable - debugging output from the driver. + debugging output from the driver. config BFS_FS tristate "BFS file system support (EXPERIMENTAL)" @@ -1263,7 +1263,7 @@ config JFFS2_FS_XATTR Extended attributes are name:value pairs associated with inodes by the kernel or by users (see the attr(5) manual page, or visit <http://acl.bestbits.at/> for details). - + If unsure, say N. config JFFS2_FS_POSIX_ACL @@ -1274,10 +1274,10 @@ config JFFS2_FS_POSIX_ACL help Posix Access Control Lists (ACLs) support permissions for users and groups beyond the owner/group/world scheme. - + To learn more about Access Control Lists, visit the Posix ACLs for Linux website <http://acl.bestbits.at/>. - + If you don't know what Access Control Lists are, say N config JFFS2_FS_SECURITY @@ -1289,7 +1289,7 @@ config JFFS2_FS_SECURITY implemented by security modules like SELinux. This option enables an extended attribute handler for file security labels in the jffs2 filesystem. - + If you are not using a security module that requires using extended attributes for file security labels, say N. @@ -1674,6 +1674,8 @@ config NFSD select CRYPTO_MD5 if NFSD_V4 select CRYPTO if NFSD_V4 select FS_POSIX_ACL if NFSD_V4 + select PROC_FS if NFSD_V4 + select PROC_FS if SUNRPC_GSS help If you want your Linux box to act as an NFS *server*, so that other computers on your local network which support NFS can access certain @@ -1833,7 +1835,7 @@ config RPCSEC_GSS_SPKM3 If unsure, say N. config SMB_FS - tristate "SMB file system support (to mount Windows shares etc.)" + tristate "SMB file system support (OBSOLETE, please use CIFS)" depends on INET select NLS help @@ -1856,8 +1858,8 @@ config SMB_FS General information about how to connect Linux, Windows machines and Macs is on the WWW at <http://www.eats.com/linux_mac_win.html>. - To compile the SMB support as a module, choose M here: the module will - be called smbfs. Most people say N, however. + To compile the SMB support as a module, choose M here: + the module will be called smbfs. Most people say N, however. config SMB_NLS_DEFAULT bool "Use a default NLS" @@ -1889,7 +1891,7 @@ config SMB_NLS_REMOTE smbmount from samba 2.2.0 or later supports this. config CIFS - tristate "CIFS support (advanced network filesystem for Samba, Window and other CIFS compliant servers)" + tristate "CIFS support (advanced network filesystem, SMBFS successor)" depends on INET select NLS help @@ -1947,16 +1949,16 @@ config CIFS_WEAK_PW_HASH LANMAN based servers such as OS/2 and Windows 95, but such mounts may be less secure than mounts using NTLM or more recent security mechanisms if you are on a public network. Unless you - have a need to access old SMB servers (and are on a private + have a need to access old SMB servers (and are on a private network) you probably want to say N. Even if this support is enabled in the kernel build, LANMAN authentication will not be used automatically. At runtime LANMAN mounts are disabled but can be set to required (or optional) either in /proc/fs/cifs (see fs/cifs/README for more detail) or via an - option on the mount command. This support is disabled by + option on the mount command. This support is disabled by default in order to reduce the possibility of a downgrade attack. - + If unsure, say N. config CIFS_XATTR @@ -1997,7 +1999,7 @@ config CIFS_DEBUG2 messages in some error paths, slowing performance. This option can be turned off unless you are debugging cifs problems. If unsure, say N. - + config CIFS_EXPERIMENTAL bool "CIFS Experimental Features (EXPERIMENTAL)" depends on CIFS && EXPERIMENTAL @@ -2088,7 +2090,7 @@ config CODA_FS_OLD_API However this new API is not backward compatible with older clients. If you really need to run the old Coda userspace cache manager then say Y. - + For most cases you probably want to say N. config AFS_FS diff --git a/fs/befs/btree.c b/fs/befs/btree.c index af5bb93276f..4202db7496c 100644 --- a/fs/befs/btree.c +++ b/fs/befs/btree.c @@ -232,7 +232,7 @@ befs_bt_read_node(struct super_block *sb, befs_data_stream * ds, * @key: Key string to lookup in btree * @value: Value stored with @key * - * On sucess, returns BEFS_OK and sets *@value to the value stored + * On success, returns BEFS_OK and sets *@value to the value stored * with @key (usually the disk block number of an inode). * * On failure, returns BEFS_ERR or BEFS_BT_NOT_FOUND. diff --git a/fs/befs/datastream.c b/fs/befs/datastream.c index aacb4da6298..e3287d0d1a5 100644 --- a/fs/befs/datastream.c +++ b/fs/befs/datastream.c @@ -236,7 +236,7 @@ befs_count_blocks(struct super_block * sb, befs_data_stream * ds) as in the indirect region code). When/if blockno is found, if blockno is inside of a block - run as stored on disk, we offset the start and lenght members + run as stored on disk, we offset the start and length members of the block run, so that blockno is the start and len is still valid (the run ends in the same place). diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 18ed6dd906c..111771d38e6 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -117,7 +117,7 @@ static int padzero(unsigned long elf_bss) return 0; } -/* Let's use some macros to make this stack manipulation a litle clearer */ +/* Let's use some macros to make this stack manipulation a little clearer */ #ifdef CONFIG_STACK_GROWSUP #define STACK_ADD(sp, items) ((elf_addr_t __user *)(sp) + (items)) #define STACK_ROUND(sp, items) \ @@ -1077,7 +1077,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) current->mm->start_stack = bprm->p; #ifdef arch_randomize_brk - if (current->flags & PF_RANDOMIZE) + if ((current->flags & PF_RANDOMIZE) && (randomize_va_space > 1)) current->mm->brk = current->mm->start_brk = arch_randomize_brk(current->mm); #endif diff --git a/fs/block_dev.c b/fs/block_dev.c index e48a630ae26..e63067d25cd 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -534,7 +534,6 @@ void __init bdev_cache_init(void) if (err) panic("Cannot register bdev pseudo-fs"); bd_mnt = kern_mount(&bd_type); - err = PTR_ERR(bd_mnt); if (IS_ERR(bd_mnt)) panic("Cannot create bdev pseudo-fs"); blockdev_superblock = bd_mnt->mnt_sb; /* For writeback */ diff --git a/fs/buffer.c b/fs/buffer.c index 456c9ab7705..826baf4f04b 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1798,7 +1798,7 @@ void page_zero_new_buffers(struct page *page, unsigned from, unsigned to) start = max(from, block_start); size = min(to, block_end) - start; - zero_user_page(page, start, size, KM_USER0); + zero_user(page, start, size); set_buffer_uptodate(bh); } @@ -1861,19 +1861,10 @@ static int __block_prepare_write(struct inode *inode, struct page *page, mark_buffer_dirty(bh); continue; } - if (block_end > to || block_start < from) { - void *kaddr; - - kaddr = kmap_atomic(page, KM_USER0); - if (block_end > to) - memset(kaddr+to, 0, - block_end-to); - if (block_start < from) - memset(kaddr+block_start, - 0, from-block_start); - flush_dcache_page(page); - kunmap_atomic(kaddr, KM_USER0); - } + if (block_end > to || block_start < from) + zero_user_segments(page, + to, block_end, + block_start, from); continue; } } @@ -2104,8 +2095,7 @@ int block_read_full_page(struct page *page, get_block_t *get_block) SetPageError(page); } if (!buffer_mapped(bh)) { - zero_user_page(page, i * blocksize, blocksize, - KM_USER0); + zero_user(page, i * blocksize, blocksize); if (!err) set_buffer_uptodate(bh); continue; @@ -2218,7 +2208,7 @@ int cont_expand_zero(struct file *file, struct address_space *mapping, &page, &fsdata); if (err) goto out; - zero_user_page(page, zerofrom, len, KM_USER0); + zero_user(page, zerofrom, len); err = pagecache_write_end(file, mapping, curpos, len, len, page, fsdata); if (err < 0) @@ -2245,7 +2235,7 @@ int cont_expand_zero(struct file *file, struct address_space *mapping, &page, &fsdata); if (err) goto out; - zero_user_page(page, zerofrom, len, KM_USER0); + zero_user(page, zerofrom, len); err = pagecache_write_end(file, mapping, curpos, len, len, page, fsdata); if (err < 0) @@ -2422,7 +2412,6 @@ int nobh_write_begin(struct file *file, struct address_space *mapping, unsigned block_in_page; unsigned block_start, block_end; sector_t block_in_file; - char *kaddr; int nr_reads = 0; int ret = 0; int is_mapped_to_disk = 1; @@ -2493,13 +2482,8 @@ int nobh_write_begin(struct file *file, struct address_space *mapping, continue; } if (buffer_new(bh) || !buffer_mapped(bh)) { - kaddr = kmap_atomic(page, KM_USER0); - if (block_start < from) - memset(kaddr+block_start, 0, from-block_start); - if (block_end > to) - memset(kaddr + to, 0, block_end - to); - flush_dcache_page(page); - kunmap_atomic(kaddr, KM_USER0); + zero_user_segments(page, block_start, from, + to, block_end); continue; } if (buffer_uptodate(bh)) @@ -2636,7 +2620,7 @@ int nobh_writepage(struct page *page, get_block_t *get_block, * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ - zero_user_page(page, offset, PAGE_CACHE_SIZE - offset, KM_USER0); + zero_user_segment(page, offset, PAGE_CACHE_SIZE); out: ret = mpage_writepage(page, get_block, wbc); if (ret == -EAGAIN) @@ -2709,7 +2693,7 @@ has_buffers: if (page_has_buffers(page)) goto has_buffers; } - zero_user_page(page, offset, length, KM_USER0); + zero_user(page, offset, length); set_page_dirty(page); err = 0; @@ -2785,7 +2769,7 @@ int block_truncate_page(struct address_space *mapping, goto unlock; } - zero_user_page(page, offset, length, KM_USER0); + zero_user(page, offset, length); mark_buffer_dirty(bh); err = 0; @@ -2831,7 +2815,7 @@ int block_write_full_page(struct page *page, get_block_t *get_block, * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ - zero_user_page(page, offset, PAGE_CACHE_SIZE - offset, KM_USER0); + zero_user_segment(page, offset, PAGE_CACHE_SIZE); return __block_write_full_page(inode, page, get_block, wbc); } @@ -3169,7 +3153,7 @@ static void recalc_bh_state(void) struct buffer_head *alloc_buffer_head(gfp_t gfp_flags) { - struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, + struct buffer_head *ret = kmem_cache_alloc(bh_cachep, set_migrateflags(gfp_flags, __GFP_RECLAIMABLE)); if (ret) { INIT_LIST_HEAD(&ret->b_assoc_buffers); @@ -3257,12 +3241,24 @@ int bh_submit_read(struct buffer_head *bh) } EXPORT_SYMBOL(bh_submit_read); +static void +init_buffer_head(struct kmem_cache *cachep, void *data) +{ + struct buffer_head *bh = data; + + memset(bh, 0, sizeof(*bh)); + INIT_LIST_HEAD(&bh->b_assoc_buffers); +} + void __init buffer_init(void) { int nrpages; - bh_cachep = KMEM_CACHE(buffer_head, - SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD); + bh_cachep = kmem_cache_create("buffer_head", + sizeof(struct buffer_head), 0, + (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| + SLAB_MEM_SPREAD), + init_buffer_head); /* * Limit the bh occupancy to 10% of ZONE_NORMAL diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index d9567ba2960..47f2621001e 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1386,7 +1386,7 @@ static int cifs_truncate_page(struct address_space *mapping, loff_t from) if (!page) return -ENOMEM; - zero_user_page(page, offset, PAGE_CACHE_SIZE - offset, KM_USER0); + zero_user_segment(page, offset, PAGE_CACHE_SIZE); unlock_page(page); page_cache_release(page); return rc; diff --git a/fs/compat.c b/fs/compat.c index 5216c3fd751..ee80ff341d3 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -2083,51 +2083,6 @@ long asmlinkage compat_sys_nfsservctl(int cmd, void *notused, void *notused2) #ifdef CONFIG_EPOLL -#ifdef CONFIG_HAS_COMPAT_EPOLL_EVENT -asmlinkage long compat_sys_epoll_ctl(int epfd, int op, int fd, - struct compat_epoll_event __user *event) -{ - long err = 0; - struct compat_epoll_event user; - struct epoll_event __user *kernel = NULL; - - if (event) { - if (copy_from_user(&user, event, sizeof(user))) - return -EFAULT; - kernel = compat_alloc_user_space(sizeof(struct epoll_event)); - err |= __put_user(user.events, &kernel->events); - err |= __put_user(user.data, &kernel->data); - } - - return err ? err : sys_epoll_ctl(epfd, op, fd, kernel); -} - - -asmlinkage long compat_sys_epoll_wait(int epfd, - struct compat_epoll_event __user *events, - int maxevents, int timeout) -{ - long i, ret, err = 0; - struct epoll_event __user *kbuf; - struct epoll_event ev; - - if ((maxevents <= 0) || - (maxevents > (INT_MAX / sizeof(struct epoll_event)))) - return -EINVAL; - kbuf = compat_alloc_user_space(sizeof(struct epoll_event) * maxevents); - ret = sys_epoll_wait(epfd, kbuf, maxevents, timeout); - for (i = 0; i < ret; i++) { - err |= __get_user(ev.events, &kbuf[i].events); - err |= __get_user(ev.data, &kbuf[i].data); - err |= __put_user(ev.events, &events->events); - err |= __put_user_unaligned(ev.data, &events->data); - events++; - } - - return err ? -EFAULT: ret; -} -#endif /* CONFIG_HAS_COMPAT_EPOLL_EVENT */ - #ifdef TIF_RESTORE_SIGMASK asmlinkage long compat_sys_epoll_pwait(int epfd, struct compat_epoll_event __user *events, @@ -2153,11 +2108,7 @@ asmlinkage long compat_sys_epoll_pwait(int epfd, sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); } -#ifdef CONFIG_HAS_COMPAT_EPOLL_EVENT - err = compat_sys_epoll_wait(epfd, events, maxevents, timeout); -#else err = sys_epoll_wait(epfd, events, maxevents, timeout); -#endif /* * If we changed the signal mask, we need to restore the original one. @@ -2206,19 +2157,41 @@ asmlinkage long compat_sys_signalfd(int ufd, #ifdef CONFIG_TIMERFD -asmlinkage long compat_sys_timerfd(int ufd, int clockid, int flags, - const struct compat_itimerspec __user *utmr) +asmlinkage long compat_sys_timerfd_settime(int ufd, int flags, + const struct compat_itimerspec __user *utmr, + struct compat_itimerspec __user *otmr) { + int error; struct itimerspec t; struct itimerspec __user *ut; if (get_compat_itimerspec(&t, utmr)) return -EFAULT; - ut = compat_alloc_user_space(sizeof(*ut)); - if (copy_to_user(ut, &t, sizeof(t))) + ut = compat_alloc_user_space(2 * sizeof(struct itimerspec)); + if (copy_to_user(&ut[0], &t, sizeof(t))) return -EFAULT; + error = sys_timerfd_settime(ufd, flags, &ut[0], &ut[1]); + if (!error && otmr) + error = (copy_from_user(&t, &ut[1], sizeof(struct itimerspec)) || + put_compat_itimerspec(otmr, &t)) ? -EFAULT: 0; + + return error; +} + +asmlinkage long compat_sys_timerfd_gettime(int ufd, + struct compat_itimerspec __user *otmr) +{ + int error; + struct itimerspec t; + struct itimerspec __user *ut; - return sys_timerfd(ufd, clockid, flags, ut); + ut = compat_alloc_user_space(sizeof(struct itimerspec)); + error = sys_timerfd_gettime(ufd, ut); + if (!error) + error = (copy_from_user(&t, ut, sizeof(struct itimerspec)) || + put_compat_itimerspec(otmr, &t)) ? -EFAULT: 0; + + return error; } #endif /* CONFIG_TIMERFD */ diff --git a/fs/dcache.c b/fs/dcache.c index d9ca1e5ceb9..44f6cf23b70 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -89,7 +89,7 @@ static void d_free(struct dentry *dentry) if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); /* if dentry was never inserted into hash, immediate free is OK */ - if (dentry->d_hash.pprev == NULL) + if (hlist_unhashed(&dentry->d_hash)) __d_free(dentry); else call_rcu(&dentry->d_u.d_rcu, d_callback); @@ -1408,9 +1408,6 @@ void d_delete(struct dentry * dentry) if (atomic_read(&dentry->d_count) == 1) { dentry_iput(dentry); fsnotify_nameremove(dentry, isdir); - - /* remove this and other inotify debug checks after 2.6.18 */ - dentry->d_flags &= ~DCACHE_INOTIFY_PARENT_WATCHED; return; } diff --git a/fs/direct-io.c b/fs/direct-io.c index acf0da1bd25..9e81addbd6e 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -878,8 +878,8 @@ do_holes: page_cache_release(page); goto out; } - zero_user_page(page, block_in_page << blkbits, - 1 << blkbits, KM_USER0); + zero_user(page, block_in_page << blkbits, + 1 << blkbits); dio->block_in_file++; block_in_page++; goto next_block; diff --git a/fs/dquot.c b/fs/dquot.c index cee7c6f428f..def4e969df7 100644 --- a/fs/dquot.c +++ b/fs/dquot.c @@ -696,9 +696,8 @@ static int dqinit_needed(struct inode *inode, int type) /* This routine is guarded by dqonoff_mutex mutex */ static void add_dquot_ref(struct super_block *sb, int type) { - struct inode *inode; + struct inode *inode, *old_inode = NULL; -restart: spin_lock(&inode_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { if (!atomic_read(&inode->i_writecount)) @@ -711,12 +710,18 @@ restart: __iget(inode); spin_unlock(&inode_lock); + iput(old_inode); sb->dq_op->initialize(inode, type); - iput(inode); - /* As we may have blocked we had better restart... */ - goto restart; + /* We hold a reference to 'inode' so it couldn't have been + * removed from s_inodes list while we dropped the inode_lock. + * We cannot iput the inode now as we can be holding the last + * reference and we cannot iput it under inode_lock. So we + * keep the reference and iput it later. */ + old_inode = inode; + spin_lock(&inode_lock); } spin_unlock(&inode_lock); + iput(old_inode); } /* Return 0 if dqput() won't block (note that 1 doesn't necessarily mean blocking) */ diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index f8ef0af919e..a066e109ad9 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -355,8 +355,11 @@ static int encrypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat, } /* Consider doing this once, when the file is opened */ mutex_lock(&crypt_stat->cs_tfm_mutex); - rc = crypto_blkcipher_setkey(crypt_stat->tfm, crypt_stat->key, - crypt_stat->key_size); + if (!(crypt_stat->flags & ECRYPTFS_KEY_SET)) { + rc = crypto_blkcipher_setkey(crypt_stat->tfm, crypt_stat->key, + crypt_stat->key_size); + crypt_stat->flags |= ECRYPTFS_KEY_SET; + } if (rc) { ecryptfs_printk(KERN_ERR, "Error setting key; rc = [%d]\n", rc); @@ -376,11 +379,10 @@ out: * * Convert an eCryptfs page index into a lower byte offset */ -void ecryptfs_lower_offset_for_extent(loff_t *offset, loff_t extent_num, - struct ecryptfs_crypt_stat *crypt_stat) +static void ecryptfs_lower_offset_for_extent(loff_t *offset, loff_t extent_num, + struct ecryptfs_crypt_stat *crypt_stat) { - (*offset) = ((crypt_stat->extent_size - * crypt_stat->num_header_extents_at_front) + (*offset) = (crypt_stat->num_header_bytes_at_front + (crypt_stat->extent_size * extent_num)); } @@ -842,15 +844,13 @@ void ecryptfs_set_default_sizes(struct ecryptfs_crypt_stat *crypt_stat) set_extent_mask_and_shift(crypt_stat); crypt_stat->iv_bytes = ECRYPTFS_DEFAULT_IV_BYTES; if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) - crypt_stat->num_header_extents_at_front = 0; + crypt_stat->num_header_bytes_at_front = 0; else { if (PAGE_CACHE_SIZE <= ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE) - crypt_stat->num_header_extents_at_front = - (ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE - / crypt_stat->extent_size); + crypt_stat->num_header_bytes_at_front = + ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE; else - crypt_stat->num_header_extents_at_front = - (PAGE_CACHE_SIZE / crypt_stat->extent_size); + crypt_stat->num_header_bytes_at_front = PAGE_CACHE_SIZE; } } @@ -1128,7 +1128,7 @@ write_ecryptfs_flags(char *page_virt, struct ecryptfs_crypt_stat *crypt_stat, struct ecryptfs_cipher_code_str_map_elem { char cipher_str[16]; - u16 cipher_code; + u8 cipher_code; }; /* Add support for additional ciphers by adding elements here. The @@ -1152,10 +1152,10 @@ ecryptfs_cipher_code_str_map[] = { * * Returns zero on no match, or the cipher code on match */ -u16 ecryptfs_code_for_cipher_string(struct ecryptfs_crypt_stat *crypt_stat) +u8 ecryptfs_code_for_cipher_string(struct ecryptfs_crypt_stat *crypt_stat) { int i; - u16 code = 0; + u8 code = 0; struct ecryptfs_cipher_code_str_map_elem *map = ecryptfs_cipher_code_str_map; @@ -1187,7 +1187,7 @@ u16 ecryptfs_code_for_cipher_string(struct ecryptfs_crypt_stat *crypt_stat) * * Returns zero on success */ -int ecryptfs_cipher_code_to_string(char *str, u16 cipher_code) +int ecryptfs_cipher_code_to_string(char *str, u8 cipher_code) { int rc = 0; int i; @@ -1236,7 +1236,8 @@ ecryptfs_write_header_metadata(char *virt, header_extent_size = (u32)crypt_stat->extent_size; num_header_extents_at_front = - (u16)crypt_stat->num_header_extents_at_front; + (u16)(crypt_stat->num_header_bytes_at_front + / crypt_stat->extent_size); header_extent_size = cpu_to_be32(header_extent_size); memcpy(virt, &header_extent_size, 4); virt += 4; @@ -1311,40 +1312,16 @@ static int ecryptfs_write_headers_virt(char *page_virt, size_t *size, static int ecryptfs_write_metadata_to_contents(struct ecryptfs_crypt_stat *crypt_stat, struct dentry *ecryptfs_dentry, - char *page_virt) + char *virt) { - int current_header_page; - int header_pages; int rc; - rc = ecryptfs_write_lower(ecryptfs_dentry->d_inode, page_virt, - 0, PAGE_CACHE_SIZE); - if (rc) { + rc = ecryptfs_write_lower(ecryptfs_dentry->d_inode, virt, + 0, crypt_stat->num_header_bytes_at_front); + if (rc) printk(KERN_ERR "%s: Error attempting to write header " "information to lower file; rc = [%d]\n", __FUNCTION__, rc); - goto out; - } - header_pages = ((crypt_stat->extent_size - * crypt_stat->num_header_extents_at_front) - / PAGE_CACHE_SIZE); - memset(page_virt, 0, PAGE_CACHE_SIZE); - current_header_page = 1; - while (current_header_page < header_pages) { - loff_t offset; - - offset = (((loff_t)current_header_page) << PAGE_CACHE_SHIFT); - if ((rc = ecryptfs_write_lower(ecryptfs_dentry->d_inode, - page_virt, offset, - PAGE_CACHE_SIZE))) { - printk(KERN_ERR "%s: Error attempting to write header " - "information to lower file; rc = [%d]\n", - __FUNCTION__, rc); - goto out; - } - current_header_page++; - } -out: return rc; } @@ -1370,15 +1347,13 @@ ecryptfs_write_metadata_to_xattr(struct dentry *ecryptfs_dentry, * retrieved via a prompt. Exactly what happens at this point should * be policy-dependent. * - * TODO: Support header information spanning multiple pages - * * Returns zero on success; non-zero on error */ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry) { struct ecryptfs_crypt_stat *crypt_stat = &ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->crypt_stat; - char *page_virt; + char *virt; size_t size = 0; int rc = 0; @@ -1389,40 +1364,39 @@ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry) goto out; } } else { + printk(KERN_WARNING "%s: Encrypted flag not set\n", + __FUNCTION__); rc = -EINVAL; - ecryptfs_printk(KERN_WARNING, - "Called with crypt_stat->encrypted == 0\n"); goto out; } /* Released in this function */ - page_virt = kmem_cache_zalloc(ecryptfs_header_cache_0, GFP_USER); - if (!page_virt) { - ecryptfs_printk(KERN_ERR, "Out of memory\n"); + virt = kzalloc(crypt_stat->num_header_bytes_at_front, GFP_KERNEL); + if (!virt) { + printk(KERN_ERR "%s: Out of memory\n", __FUNCTION__); rc = -ENOMEM; goto out; } - rc = ecryptfs_write_headers_virt(page_virt, &size, crypt_stat, - ecryptfs_dentry); + rc = ecryptfs_write_headers_virt(virt, &size, crypt_stat, + ecryptfs_dentry); if (unlikely(rc)) { - ecryptfs_printk(KERN_ERR, "Error whilst writing headers\n"); - memset(page_virt, 0, PAGE_CACHE_SIZE); + printk(KERN_ERR "%s: Error whilst writing headers; rc = [%d]\n", + __FUNCTION__, rc); goto out_free; } if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) rc = ecryptfs_write_metadata_to_xattr(ecryptfs_dentry, - crypt_stat, page_virt, - size); + crypt_stat, virt, size); else rc = ecryptfs_write_metadata_to_contents(crypt_stat, - ecryptfs_dentry, - page_virt); + ecryptfs_dentry, virt); if (rc) { - printk(KERN_ERR "Error writing metadata out to lower file; " - "rc = [%d]\n", rc); + printk(KERN_ERR "%s: Error writing metadata out to lower file; " + "rc = [%d]\n", __FUNCTION__, rc); goto out_free; } out_free: - kmem_cache_free(ecryptfs_header_cache_0, page_virt); + memset(virt, 0, crypt_stat->num_header_bytes_at_front); + kfree(virt); out: return rc; } @@ -1442,16 +1416,16 @@ static int parse_header_metadata(struct ecryptfs_crypt_stat *crypt_stat, virt += sizeof(u32); memcpy(&num_header_extents_at_front, virt, sizeof(u16)); num_header_extents_at_front = be16_to_cpu(num_header_extents_at_front); - crypt_stat->num_header_extents_at_front = - (int)num_header_extents_at_front; + crypt_stat->num_header_bytes_at_front = + (((size_t)num_header_extents_at_front + * (size_t)header_extent_size)); (*bytes_read) = (sizeof(u32) + sizeof(u16)); if ((validate_header_size == ECRYPTFS_VALIDATE_HEADER_SIZE) - && ((crypt_stat->extent_size - * crypt_stat->num_header_extents_at_front) + && (crypt_stat->num_header_bytes_at_front < ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE)) { rc = -EINVAL; - printk(KERN_WARNING "Invalid number of header extents: [%zd]\n", - crypt_stat->num_header_extents_at_front); + printk(KERN_WARNING "Invalid header size: [%zd]\n", + crypt_stat->num_header_bytes_at_front); } return rc; } @@ -1466,7 +1440,8 @@ static int parse_header_metadata(struct ecryptfs_crypt_stat *crypt_stat, */ static void set_default_header_data(struct ecryptfs_crypt_stat *crypt_stat) { - crypt_stat->num_header_extents_at_front = 2; + crypt_stat->num_header_bytes_at_front = + ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE; } /** @@ -1552,9 +1527,10 @@ int ecryptfs_read_xattr_region(char *page_virt, struct inode *ecryptfs_inode) size = ecryptfs_getxattr_lower(lower_dentry, ECRYPTFS_XATTR_NAME, page_virt, ECRYPTFS_DEFAULT_EXTENT_SIZE); if (size < 0) { - printk(KERN_ERR "Error attempting to read the [%s] " - "xattr from the lower file; return value = [%zd]\n", - ECRYPTFS_XATTR_NAME, size); + if (unlikely(ecryptfs_verbosity > 0)) + printk(KERN_INFO "Error attempting to read the [%s] " + "xattr from the lower file; return value = " + "[%zd]\n", ECRYPTFS_XATTR_NAME, size); rc = -EINVAL; goto out; } @@ -1802,7 +1778,7 @@ out: } struct kmem_cache *ecryptfs_key_tfm_cache; -struct list_head key_tfm_list; +static struct list_head key_tfm_list; struct mutex key_tfm_list_mutex; int ecryptfs_init_crypto(void) @@ -1812,6 +1788,11 @@ int ecryptfs_init_crypto(void) return 0; } +/** + * ecryptfs_destroy_crypto - free all cached key_tfms on key_tfm_list + * + * Called only at module unload time + */ int ecryptfs_destroy_crypto(void) { struct ecryptfs_key_tfm *key_tfm, *key_tfm_tmp; @@ -1835,6 +1816,8 @@ ecryptfs_add_new_key_tfm(struct ecryptfs_key_tfm **key_tfm, char *cipher_name, struct ecryptfs_key_tfm *tmp_tfm; int rc = 0; + BUG_ON(!mutex_is_locked(&key_tfm_list_mutex)); + tmp_tfm = kmem_cache_alloc(ecryptfs_key_tfm_cache, GFP_KERNEL); if (key_tfm != NULL) (*key_tfm) = tmp_tfm; @@ -1861,13 +1844,50 @@ ecryptfs_add_new_key_tfm(struct ecryptfs_key_tfm **key_tfm, char *cipher_name, (*key_tfm) = NULL; goto out; } - mutex_lock(&key_tfm_list_mutex); list_add(&tmp_tfm->key_tfm_list, &key_tfm_list); - mutex_unlock(&key_tfm_list_mutex); out: return rc; } +/** + * ecryptfs_tfm_exists - Search for existing tfm for cipher_name. + * @cipher_name: the name of the cipher to search for + * @key_tfm: set to corresponding tfm if found + * + * Searches for cached key_tfm matching @cipher_name + * Must be called with &key_tfm_list_mutex held + * Returns 1 if found, with @key_tfm set + * Returns 0 if not found, with @key_tfm set to NULL + */ +int ecryptfs_tfm_exists(char *cipher_name, struct ecryptfs_key_tfm **key_tfm) +{ + struct ecryptfs_key_tfm *tmp_key_tfm; + + BUG_ON(!mutex_is_locked(&key_tfm_list_mutex)); + + list_for_each_entry(tmp_key_tfm, &key_tfm_list, key_tfm_list) { + if (strcmp(tmp_key_tfm->cipher_name, cipher_name) == 0) { + if (key_tfm) + (*key_tfm) = tmp_key_tfm; + return 1; + } + } + if (key_tfm) + (*key_tfm) = NULL; + return 0; +} + +/** + * ecryptfs_get_tfm_and_mutex_for_cipher_name + * + * @tfm: set to cached tfm found, or new tfm created + * @tfm_mutex: set to mutex for cached tfm found, or new tfm created + * @cipher_name: the name of the cipher to search for and/or add + * + * Sets pointers to @tfm & @tfm_mutex matching @cipher_name. + * Searches for cached item first, and creates new if not found. + * Returns 0 on success, non-zero if adding new cipher failed + */ int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_blkcipher **tfm, struct mutex **tfm_mutex, char *cipher_name) @@ -1877,22 +1897,17 @@ int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_blkcipher **tfm, (*tfm) = NULL; (*tfm_mutex) = NULL; + mutex_lock(&key_tfm_list_mutex); - list_for_each_entry(key_tfm, &key_tfm_list, key_tfm_list) { - if (strcmp(key_tfm->cipher_name, cipher_name) == 0) { - (*tfm) = key_tfm->key_tfm; - (*tfm_mutex) = &key_tfm->key_tfm_mutex; - mutex_unlock(&key_tfm_list_mutex); + if (!ecryptfs_tfm_exists(cipher_name, &key_tfm)) { + rc = ecryptfs_add_new_key_tfm(&key_tfm, cipher_name, 0); + if (rc) { + printk(KERN_ERR "Error adding new key_tfm to list; " + "rc = [%d]\n", rc); goto out; } } mutex_unlock(&key_tfm_list_mutex); - rc = ecryptfs_add_new_key_tfm(&key_tfm, cipher_name, 0); - if (rc) { - printk(KERN_ERR "Error adding new key_tfm to list; rc = [%d]\n", - rc); - goto out; - } (*tfm) = key_tfm->key_tfm; (*tfm_mutex) = &key_tfm->key_tfm_mutex; out: diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index ce7a5d4aec3..5007f788da0 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -234,10 +234,11 @@ struct ecryptfs_crypt_stat { #define ECRYPTFS_KEY_VALID 0x00000080 #define ECRYPTFS_METADATA_IN_XATTR 0x00000100 #define ECRYPTFS_VIEW_AS_ENCRYPTED 0x00000200 +#define ECRYPTFS_KEY_SET 0x00000400 u32 flags; unsigned int file_version; size_t iv_bytes; - size_t num_header_extents_at_front; + size_t num_header_bytes_at_front; size_t extent_size; /* Data extent size; default is 4096 */ size_t key_size; size_t extent_shift; @@ -322,7 +323,6 @@ struct ecryptfs_key_tfm { unsigned char cipher_name[ECRYPTFS_MAX_CIPHER_NAME_SIZE + 1]; }; -extern struct list_head key_tfm_list; extern struct mutex key_tfm_list_mutex; /** @@ -521,11 +521,9 @@ extern struct kmem_cache *ecryptfs_file_info_cache; extern struct kmem_cache *ecryptfs_dentry_info_cache; extern struct kmem_cache *ecryptfs_inode_info_cache; extern struct kmem_cache *ecryptfs_sb_info_cache; -extern struct kmem_cache *ecryptfs_header_cache_0; extern struct kmem_cache *ecryptfs_header_cache_1; extern struct kmem_cache *ecryptfs_header_cache_2; extern struct kmem_cache *ecryptfs_xattr_cache; -extern struct kmem_cache *ecryptfs_lower_page_cache; extern struct kmem_cache *ecryptfs_key_record_cache; extern struct kmem_cache *ecryptfs_key_sig_cache; extern struct kmem_cache *ecryptfs_global_auth_tok_cache; @@ -562,8 +560,8 @@ int ecryptfs_read_and_validate_header_region(char *data, struct inode *ecryptfs_inode); int ecryptfs_read_and_validate_xattr_region(char *page_virt, struct dentry *ecryptfs_dentry); -u16 ecryptfs_code_for_cipher_string(struct ecryptfs_crypt_stat *crypt_stat); -int ecryptfs_cipher_code_to_string(char *str, u16 cipher_code); +u8 ecryptfs_code_for_cipher_string(struct ecryptfs_crypt_stat *crypt_stat); +int ecryptfs_cipher_code_to_string(char *str, u8 cipher_code); void ecryptfs_set_default_sizes(struct ecryptfs_crypt_stat *crypt_stat); int ecryptfs_generate_key_packet_set(char *dest_base, struct ecryptfs_crypt_stat *crypt_stat, @@ -576,8 +574,6 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length); int ecryptfs_inode_test(struct inode *inode, void *candidate_lower_inode); int ecryptfs_inode_set(struct inode *inode, void *lower_inode); void ecryptfs_init_inode(struct inode *inode, struct inode *lower_inode); -ssize_t ecryptfs_getxattr(struct dentry *dentry, const char *name, void *value, - size_t size); ssize_t ecryptfs_getxattr_lower(struct dentry *lower_dentry, const char *name, void *value, size_t size); @@ -623,6 +619,7 @@ ecryptfs_add_new_key_tfm(struct ecryptfs_key_tfm **key_tfm, char *cipher_name, size_t key_size); int ecryptfs_init_crypto(void); int ecryptfs_destroy_crypto(void); +int ecryptfs_tfm_exists(char *cipher_name, struct ecryptfs_key_tfm **key_tfm); int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_blkcipher **tfm, struct mutex **tfm_mutex, char *cipher_name); @@ -631,8 +628,6 @@ int ecryptfs_keyring_auth_tok_for_sig(struct key **auth_tok_key, char *sig); int ecryptfs_write_zeros(struct file *file, pgoff_t index, int start, int num_zeros); -void ecryptfs_lower_offset_for_extent(loff_t *offset, loff_t extent_num, - struct ecryptfs_crypt_stat *crypt_stat); int ecryptfs_write_lower(struct inode *ecryptfs_inode, char *data, loff_t offset, size_t size); int ecryptfs_write_lower_page_segment(struct inode *ecryptfs_inode, @@ -646,8 +641,6 @@ int ecryptfs_read_lower_page_segment(struct page *page_for_ecryptfs, pgoff_t page_index, size_t offset_in_page, size_t size, struct inode *ecryptfs_inode); -int ecryptfs_read(char *data, loff_t offset, size_t size, - struct file *ecryptfs_file); struct page *ecryptfs_get_locked_page(struct file *file, loff_t index); #endif /* #ifndef ECRYPTFS_KERNEL_H */ diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index c98c4690a77..2b8f5ed4ade 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -209,9 +209,10 @@ static int ecryptfs_open(struct inode *inode, struct file *file) if (!(mount_crypt_stat->flags & ECRYPTFS_PLAINTEXT_PASSTHROUGH_ENABLED)) { rc = -EIO; - printk(KERN_WARNING "Attempt to read file that " + printk(KERN_WARNING "Either the lower file " "is not in a valid eCryptfs format, " - "and plaintext passthrough mode is not " + "or the key could not be retrieved. " + "Plaintext passthrough mode is not " "enabled; returning -EIO\n"); mutex_unlock(&crypt_stat->cs_mutex); goto out_free; diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 5a719180983..edd1e44e9d4 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -365,8 +365,7 @@ static struct dentry *ecryptfs_lookup(struct inode *dir, struct dentry *dentry, dentry->d_sb)->mount_crypt_stat; if (mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) { if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) - file_size = ((crypt_stat->extent_size - * crypt_stat->num_header_extents_at_front) + file_size = (crypt_stat->num_header_bytes_at_front + i_size_read(lower_dentry->d_inode)); else file_size = i_size_read(lower_dentry->d_inode); @@ -685,7 +684,7 @@ ecryptfs_put_link(struct dentry *dentry, struct nameidata *nd, void *ptr) * @crypt_stat: Crypt_stat associated with file * @upper_size: Size of the upper file * - * Calculate the requried size of the lower file based on the + * Calculate the required size of the lower file based on the * specified size of the upper file. This calculation is based on the * number of headers in the underlying file and the extent size. * @@ -697,8 +696,7 @@ upper_size_to_lower_size(struct ecryptfs_crypt_stat *crypt_stat, { loff_t lower_size; - lower_size = (crypt_stat->extent_size - * crypt_stat->num_header_extents_at_front); + lower_size = crypt_stat->num_header_bytes_at_front; if (upper_size != 0) { loff_t num_extents; @@ -875,11 +873,11 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia) if (!(mount_crypt_stat->flags & ECRYPTFS_PLAINTEXT_PASSTHROUGH_ENABLED)) { rc = -EIO; - printk(KERN_WARNING "Attempt to read file that " + printk(KERN_WARNING "Either the lower file " "is not in a valid eCryptfs format, " - "and plaintext passthrough mode is not " + "or the key could not be retrieved. " + "Plaintext passthrough mode is not " "enabled; returning -EIO\n"); - mutex_unlock(&crypt_stat->cs_mutex); goto out; } @@ -954,7 +952,7 @@ out: return rc; } -ssize_t +static ssize_t ecryptfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size) { diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index f458c1f3556..682b1b2482c 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -189,7 +189,7 @@ out: } static int -parse_tag_65_packet(struct ecryptfs_session_key *session_key, u16 *cipher_code, +parse_tag_65_packet(struct ecryptfs_session_key *session_key, u8 *cipher_code, struct ecryptfs_message *msg) { size_t i = 0; @@ -275,7 +275,7 @@ out: static int -write_tag_66_packet(char *signature, size_t cipher_code, +write_tag_66_packet(char *signature, u8 cipher_code, struct ecryptfs_crypt_stat *crypt_stat, char **packet, size_t *packet_len) { @@ -428,7 +428,7 @@ static int decrypt_pki_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok, struct ecryptfs_crypt_stat *crypt_stat) { - u16 cipher_code = 0; + u8 cipher_code = 0; struct ecryptfs_msg_ctx *msg_ctx; struct ecryptfs_message *msg = NULL; char *auth_tok_sig; @@ -1537,7 +1537,7 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes, struct scatterlist dst_sg; struct scatterlist src_sg; struct mutex *tfm_mutex = NULL; - size_t cipher_code; + u8 cipher_code; size_t packet_size_length; size_t max_packet_size; struct ecryptfs_mount_crypt_stat *mount_crypt_stat = diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 0249aa4ae18..778c420e4ca 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -117,7 +117,7 @@ void __ecryptfs_printk(const char *fmt, ...) * * Returns zero on success; non-zero otherwise */ -int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry) +static int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry) { struct ecryptfs_inode_info *inode_info = ecryptfs_inode_to_private(ecryptfs_dentry->d_inode); @@ -226,17 +226,15 @@ out: return rc; } -enum { ecryptfs_opt_sig, ecryptfs_opt_ecryptfs_sig, ecryptfs_opt_debug, - ecryptfs_opt_ecryptfs_debug, ecryptfs_opt_cipher, - ecryptfs_opt_ecryptfs_cipher, ecryptfs_opt_ecryptfs_key_bytes, +enum { ecryptfs_opt_sig, ecryptfs_opt_ecryptfs_sig, + ecryptfs_opt_cipher, ecryptfs_opt_ecryptfs_cipher, + ecryptfs_opt_ecryptfs_key_bytes, ecryptfs_opt_passthrough, ecryptfs_opt_xattr_metadata, ecryptfs_opt_encrypted_view, ecryptfs_opt_err }; static match_table_t tokens = { {ecryptfs_opt_sig, "sig=%s"}, {ecryptfs_opt_ecryptfs_sig, "ecryptfs_sig=%s"}, - {ecryptfs_opt_debug, "debug=%u"}, - {ecryptfs_opt_ecryptfs_debug, "ecryptfs_debug=%u"}, {ecryptfs_opt_cipher, "cipher=%s"}, {ecryptfs_opt_ecryptfs_cipher, "ecryptfs_cipher=%s"}, {ecryptfs_opt_ecryptfs_key_bytes, "ecryptfs_key_bytes=%u"}, @@ -313,7 +311,6 @@ static int ecryptfs_parse_options(struct super_block *sb, char *options) substring_t args[MAX_OPT_ARGS]; int token; char *sig_src; - char *debug_src; char *cipher_name_dst; char *cipher_name_src; char *cipher_key_bytes_src; @@ -341,16 +338,6 @@ static int ecryptfs_parse_options(struct super_block *sb, char *options) } sig_set = 1; break; - case ecryptfs_opt_debug: - case ecryptfs_opt_ecryptfs_debug: - debug_src = args[0].from; - ecryptfs_verbosity = - (int)simple_strtol(debug_src, &debug_src, - 0); - ecryptfs_printk(KERN_DEBUG, - "Verbosity set to [%d]" "\n", - ecryptfs_verbosity); - break; case ecryptfs_opt_cipher: case ecryptfs_opt_ecryptfs_cipher: cipher_name_src = args[0].from; @@ -423,9 +410,13 @@ static int ecryptfs_parse_options(struct super_block *sb, char *options) if (!cipher_key_bytes_set) { mount_crypt_stat->global_default_cipher_key_size = 0; } - rc = ecryptfs_add_new_key_tfm( - NULL, mount_crypt_stat->global_default_cipher_name, - mount_crypt_stat->global_default_cipher_key_size); + mutex_lock(&key_tfm_list_mutex); + if (!ecryptfs_tfm_exists(mount_crypt_stat->global_default_cipher_name, + NULL)) + rc = ecryptfs_add_new_key_tfm( + NULL, mount_crypt_stat->global_default_cipher_name, + mount_crypt_stat->global_default_cipher_key_size); + mutex_unlock(&key_tfm_list_mutex); if (rc) { printk(KERN_ERR "Error attempting to initialize cipher with " "name = [%s] and key size = [%td]; rc = [%d]\n", @@ -654,11 +645,6 @@ static struct ecryptfs_cache_info { .size = sizeof(struct ecryptfs_sb_info), }, { - .cache = &ecryptfs_header_cache_0, - .name = "ecryptfs_headers_0", - .size = PAGE_CACHE_SIZE, - }, - { .cache = &ecryptfs_header_cache_1, .name = "ecryptfs_headers_1", .size = PAGE_CACHE_SIZE, @@ -821,6 +807,10 @@ static int __init ecryptfs_init(void) "rc = [%d]\n", rc); goto out_release_messaging; } + if (ecryptfs_verbosity > 0) + printk(KERN_CRIT "eCryptfs verbosity set to %d. Secret values " + "will be written to the syslog!\n", ecryptfs_verbosity); + goto out; out_release_messaging: ecryptfs_release_messaging(ecryptfs_transport); diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index 32c5711d79a..dc74b186145 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -34,8 +34,6 @@ #include <linux/scatterlist.h> #include "ecryptfs_kernel.h" -struct kmem_cache *ecryptfs_lower_page_cache; - /** * ecryptfs_get_locked_page * @@ -102,13 +100,14 @@ static void set_header_info(char *page_virt, struct ecryptfs_crypt_stat *crypt_stat) { size_t written; - int save_num_header_extents_at_front = - crypt_stat->num_header_extents_at_front; + size_t save_num_header_bytes_at_front = + crypt_stat->num_header_bytes_at_front; - crypt_stat->num_header_extents_at_front = 1; + crypt_stat->num_header_bytes_at_front = + ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE; ecryptfs_write_header_metadata(page_virt + 20, crypt_stat, &written); - crypt_stat->num_header_extents_at_front = - save_num_header_extents_at_front; + crypt_stat->num_header_bytes_at_front = + save_num_header_bytes_at_front; } /** @@ -134,8 +133,11 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page, loff_t view_extent_num = ((((loff_t)page->index) * num_extents_per_page) + extent_num_in_page); + size_t num_header_extents_at_front = + (crypt_stat->num_header_bytes_at_front + / crypt_stat->extent_size); - if (view_extent_num < crypt_stat->num_header_extents_at_front) { + if (view_extent_num < num_header_extents_at_front) { /* This is a header extent */ char *page_virt; @@ -157,9 +159,8 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page, } else { /* This is an encrypted data extent */ loff_t lower_offset = - ((view_extent_num - - crypt_stat->num_header_extents_at_front) - * crypt_stat->extent_size); + ((view_extent_num * crypt_stat->extent_size) + - crypt_stat->num_header_bytes_at_front); rc = ecryptfs_read_lower_page_segment( page, (lower_offset >> PAGE_CACHE_SHIFT), @@ -257,8 +258,7 @@ static int fill_zeros_to_end_of_page(struct page *page, unsigned int to) end_byte_in_page = i_size_read(inode) % PAGE_CACHE_SIZE; if (to > end_byte_in_page) end_byte_in_page = to; - zero_user_page(page, end_byte_in_page, - PAGE_CACHE_SIZE - end_byte_in_page, KM_USER0); + zero_user_segment(page, end_byte_in_page, PAGE_CACHE_SIZE); out: return 0; } @@ -307,7 +307,7 @@ static int ecryptfs_prepare_write(struct file *file, struct page *page, */ if ((i_size_read(page->mapping->host) == prev_page_end_size) && (from != 0)) { - zero_user_page(page, 0, PAGE_CACHE_SIZE, KM_USER0); + zero_user(page, 0, PAGE_CACHE_SIZE); } out: return rc; diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c index 948f57624c0..0c4928623bb 100644 --- a/fs/ecryptfs/read_write.c +++ b/fs/ecryptfs/read_write.c @@ -293,6 +293,7 @@ int ecryptfs_read_lower_page_segment(struct page *page_for_ecryptfs, return rc; } +#if 0 /** * ecryptfs_read * @data: The virtual address into which to write the data read (and @@ -371,3 +372,4 @@ int ecryptfs_read(char *data, loff_t offset, size_t size, out: return rc; } +#endif /* 0 */ diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c index 4859c4eecd6..c27ac2b358a 100644 --- a/fs/ecryptfs/super.c +++ b/fs/ecryptfs/super.c @@ -156,32 +156,38 @@ static void ecryptfs_clear_inode(struct inode *inode) /** * ecryptfs_show_options * - * Prints the directory we are currently mounted over. - * Returns zero on success; non-zero otherwise + * Prints the mount options for a given superblock. + * Returns zero; does not fail. */ static int ecryptfs_show_options(struct seq_file *m, struct vfsmount *mnt) { struct super_block *sb = mnt->mnt_sb; - struct dentry *lower_root_dentry = ecryptfs_dentry_to_lower(sb->s_root); - struct vfsmount *lower_mnt = ecryptfs_dentry_to_lower_mnt(sb->s_root); - char *tmp_page; - char *path; - int rc = 0; - - tmp_page = (char *)__get_free_page(GFP_KERNEL); - if (!tmp_page) { - rc = -ENOMEM; - goto out; - } - path = d_path(lower_root_dentry, lower_mnt, tmp_page, PAGE_SIZE); - if (IS_ERR(path)) { - rc = PTR_ERR(path); - goto out; + struct ecryptfs_mount_crypt_stat *mount_crypt_stat = + &ecryptfs_superblock_to_private(sb)->mount_crypt_stat; + struct ecryptfs_global_auth_tok *walker; + + mutex_lock(&mount_crypt_stat->global_auth_tok_list_mutex); + list_for_each_entry(walker, + &mount_crypt_stat->global_auth_tok_list, + mount_crypt_stat_list) { + seq_printf(m, ",ecryptfs_sig=%s", walker->sig); } - seq_printf(m, ",dir=%s", path); - free_page((unsigned long)tmp_page); -out: - return rc; + mutex_unlock(&mount_crypt_stat->global_auth_tok_list_mutex); + + seq_printf(m, ",ecryptfs_cipher=%s", + mount_crypt_stat->global_default_cipher_name); + + if (mount_crypt_stat->global_default_cipher_key_size) + seq_printf(m, ",ecryptfs_key_bytes=%zd", + mount_crypt_stat->global_default_cipher_key_size); + if (mount_crypt_stat->flags & ECRYPTFS_PLAINTEXT_PASSTHROUGH_ENABLED) + seq_printf(m, ",ecryptfs_passthrough"); + if (mount_crypt_stat->flags & ECRYPTFS_XATTR_METADATA_ENABLED) + seq_printf(m, ",ecryptfs_xattr_metadata"); + if (mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) + seq_printf(m, ",ecryptfs_encrypted_view"); + + return 0; } const struct super_operations ecryptfs_sops = { diff --git a/fs/eventfd.c b/fs/eventfd.c index 2ce19c000d2..a9f130cd50a 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -15,6 +15,7 @@ #include <linux/spinlock.h> #include <linux/anon_inodes.h> #include <linux/eventfd.h> +#include <linux/syscalls.h> struct eventfd_ctx { wait_queue_head_t wqh; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 81c04abfb1a..a415f42d32c 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -353,7 +353,7 @@ static void ep_poll_safewake(struct poll_safewake *psw, wait_queue_head_t *wq) spin_unlock_irqrestore(&psw->lock, flags); /* Do really wake up now */ - wake_up(wq); + wake_up_nested(wq, 1 + wake_nests); /* Remove the current task from the list */ spin_lock_irqsave(&psw->lock, flags); diff --git a/fs/exec.c b/fs/exec.c index 282240afe99..be923e4bc38 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -760,7 +760,7 @@ static int de_thread(struct task_struct *tsk) */ read_lock(&tasklist_lock); spin_lock_irq(lock); - if (sig->flags & SIGNAL_GROUP_EXIT) { + if (signal_group_exit(sig)) { /* * Another group action in progress, just * return so that the signal is processed. @@ -778,6 +778,7 @@ static int de_thread(struct task_struct *tsk) if (unlikely(tsk->group_leader == task_child_reaper(tsk))) task_active_pid_ns(tsk)->child_reaper = tsk; + sig->group_exit_task = tsk; zap_other_threads(tsk); read_unlock(&tasklist_lock); @@ -802,7 +803,6 @@ static int de_thread(struct task_struct *tsk) } sig->notify_count = count; - sig->group_exit_task = tsk; while (atomic_read(&sig->count) > count) { __set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock_irq(lock); @@ -871,15 +871,10 @@ static int de_thread(struct task_struct *tsk) leader->exit_state = EXIT_DEAD; write_unlock_irq(&tasklist_lock); - } + } sig->group_exit_task = NULL; sig->notify_count = 0; - /* - * There may be one thread left which is just exiting, - * but it's safe to stop telling the group to kill themselves. - */ - sig->flags = 0; no_thread_group: exit_itimers(sig); @@ -947,12 +942,13 @@ static void flush_old_files(struct files_struct * files) spin_unlock(&files->file_lock); } -void get_task_comm(char *buf, struct task_struct *tsk) +char *get_task_comm(char *buf, struct task_struct *tsk) { /* buf must be at least sizeof(tsk->comm) in size */ task_lock(tsk); strncpy(buf, tsk->comm, sizeof(tsk->comm)); task_unlock(tsk); + return buf; } void set_task_comm(struct task_struct *tsk, char *buf) @@ -1548,7 +1544,7 @@ static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm, int err = -EAGAIN; spin_lock_irq(&tsk->sighand->siglock); - if (!(tsk->signal->flags & SIGNAL_GROUP_EXIT)) { + if (!signal_group_exit(tsk->signal)) { tsk->signal->group_exit_code = exit_code; zap_process(tsk); err = 0; diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c index 377ad172d74..e7b2bafa1dd 100644 --- a/fs/ext2/balloc.c +++ b/fs/ext2/balloc.c @@ -69,9 +69,53 @@ struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb, return desc + offset; } +static int ext2_valid_block_bitmap(struct super_block *sb, + struct ext2_group_desc *desc, + unsigned int block_group, + struct buffer_head *bh) +{ + ext2_grpblk_t offset; + ext2_grpblk_t next_zero_bit; + ext2_fsblk_t bitmap_blk; + ext2_fsblk_t group_first_block; + + group_first_block = ext2_group_first_block_no(sb, block_group); + + /* check whether block bitmap block number is set */ + bitmap_blk = le32_to_cpu(desc->bg_block_bitmap); + offset = bitmap_blk - group_first_block; + if (!ext2_test_bit(offset, bh->b_data)) + /* bad block bitmap */ + goto err_out; + + /* check whether the inode bitmap block number is set */ + bitmap_blk = le32_to_cpu(desc->bg_inode_bitmap); + offset = bitmap_blk - group_first_block; + if (!ext2_test_bit(offset, bh->b_data)) + /* bad block bitmap */ + goto err_out; + + /* check whether the inode table block number is set */ + bitmap_blk = le32_to_cpu(desc->bg_inode_table); + offset = bitmap_blk - group_first_block; + next_zero_bit = ext2_find_next_zero_bit(bh->b_data, + offset + EXT2_SB(sb)->s_itb_per_group, + offset); + if (next_zero_bit >= offset + EXT2_SB(sb)->s_itb_per_group) + /* good bitmap for inode tables */ + return 1; + +err_out: + ext2_error(sb, __FUNCTION__, + "Invalid block bitmap - " + "block_group = %d, block = %lu", + block_group, bitmap_blk); + return 0; +} + /* - * Read the bitmap for a given block_group, reading into the specified - * slot in the superblock's bitmap cache. + * Read the bitmap for a given block_group,and validate the + * bits for block/inode/inode tables are set in the bitmaps * * Return buffer_head on success or NULL in case of failure. */ @@ -80,17 +124,36 @@ read_block_bitmap(struct super_block *sb, unsigned int block_group) { struct ext2_group_desc * desc; struct buffer_head * bh = NULL; - - desc = ext2_get_group_desc (sb, block_group, NULL); + ext2_fsblk_t bitmap_blk; + + desc = ext2_get_group_desc(sb, block_group, NULL); if (!desc) - goto error_out; - bh = sb_bread(sb, le32_to_cpu(desc->bg_block_bitmap)); - if (!bh) - ext2_error (sb, "read_block_bitmap", + return NULL; + bitmap_blk = le32_to_cpu(desc->bg_block_bitmap); + bh = sb_getblk(sb, bitmap_blk); + if (unlikely(!bh)) { + ext2_error(sb, __FUNCTION__, + "Cannot read block bitmap - " + "block_group = %d, block_bitmap = %u", + block_group, le32_to_cpu(desc->bg_block_bitmap)); + return NULL; + } + if (likely(bh_uptodate_or_lock(bh))) + return bh; + + if (bh_submit_read(bh) < 0) { + brelse(bh); + ext2_error(sb, __FUNCTION__, "Cannot read block bitmap - " "block_group = %d, block_bitmap = %u", block_group, le32_to_cpu(desc->bg_block_bitmap)); -error_out: + return NULL; + } + if (!ext2_valid_block_bitmap(sb, desc, block_group, bh)) { + brelse(bh); + return NULL; + } + return bh; } @@ -474,11 +537,13 @@ do_more: in_range (block, le32_to_cpu(desc->bg_inode_table), sbi->s_itb_per_group) || in_range (block + count - 1, le32_to_cpu(desc->bg_inode_table), - sbi->s_itb_per_group)) + sbi->s_itb_per_group)) { ext2_error (sb, "ext2_free_blocks", "Freeing blocks in system zones - " "Block = %lu, count = %lu", block, count); + goto error_return; + } for (i = 0, group_freed = 0; i < count; i++) { if (!ext2_clear_bit_atomic(sb_bgl_lock(sbi, block_group), @@ -1250,8 +1315,8 @@ retry_alloc: smp_rmb(); /* - * Now search the rest of the groups. We assume that - * i and gdp correctly point to the last group visited. + * Now search the rest of the groups. We assume that + * group_no and gdp correctly point to the last group visited. */ for (bgi = 0; bgi < ngroups; bgi++) { group_no++; @@ -1311,11 +1376,13 @@ allocated: in_range(ret_block, le32_to_cpu(gdp->bg_inode_table), EXT2_SB(sb)->s_itb_per_group) || in_range(ret_block + num - 1, le32_to_cpu(gdp->bg_inode_table), - EXT2_SB(sb)->s_itb_per_group)) + EXT2_SB(sb)->s_itb_per_group)) { ext2_error(sb, "ext2_new_blocks", "Allocating block in system zone - " "blocks from "E2FSBLK", length %lu", ret_block, num); + goto out; + } performed_allocation = 1; @@ -1466,9 +1533,6 @@ int ext2_bg_has_super(struct super_block *sb, int group) */ unsigned long ext2_bg_num_gdb(struct super_block *sb, int group) { - if (EXT2_HAS_RO_COMPAT_FEATURE(sb,EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER)&& - !ext2_group_sparse(group)) - return 0; - return EXT2_SB(sb)->s_gdb_count; + return ext2_bg_has_super(sb, group) ? EXT2_SB(sb)->s_gdb_count : 0; } diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index d868e26c15e..8dededd80fe 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -703,7 +703,7 @@ const struct file_operations ext2_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .readdir = ext2_readdir, - .ioctl = ext2_ioctl, + .unlocked_ioctl = ext2_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext2_compat_ioctl, #endif diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index c87ae29c19c..bb9948cdd50 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -139,8 +139,7 @@ int __ext2_write_begin(struct file *file, struct address_space *mapping, struct page **pagep, void **fsdata); /* ioctl.c */ -extern int ext2_ioctl (struct inode *, struct file *, unsigned int, - unsigned long); +extern long ext2_ioctl(struct file *, unsigned int, unsigned long); extern long ext2_compat_ioctl(struct file *, unsigned int, unsigned long); /* namei.c */ diff --git a/fs/ext2/file.c b/fs/ext2/file.c index c051798459a..5f2fa9c3629 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -48,7 +48,7 @@ const struct file_operations ext2_file_operations = { .write = do_sync_write, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, - .ioctl = ext2_ioctl, + .unlocked_ioctl = ext2_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext2_compat_ioctl, #endif @@ -65,7 +65,7 @@ const struct file_operations ext2_xip_file_operations = { .llseek = generic_file_llseek, .read = xip_file_read, .write = xip_file_write, - .ioctl = ext2_ioctl, + .unlocked_ioctl = ext2_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext2_compat_ioctl, #endif diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index b1ab32ab5a7..03978ec2a91 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -286,15 +286,12 @@ static unsigned long ext2_find_near(struct inode *inode, Indirect *ind) * ext2_find_goal - find a prefered place for allocation. * @inode: owner * @block: block we want - * @chain: chain of indirect blocks * @partial: pointer to the last triple within a chain * * Returns preferred place for a block (the goal). */ -static inline int ext2_find_goal(struct inode *inode, - long block, - Indirect chain[4], +static inline int ext2_find_goal(struct inode *inode, long block, Indirect *partial) { struct ext2_block_alloc_info *block_i; @@ -569,7 +566,6 @@ static void ext2_splice_branch(struct inode *inode, * * `handle' can be NULL if create == 0. * - * The BKL may not be held on entry here. Be sure to take it early. * return > 0, # of blocks mapped or allocated. * return = 0, if plain lookup failed. * return < 0, error case. @@ -639,7 +635,7 @@ reread: if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info)) ext2_init_block_alloc_info(inode); - goal = ext2_find_goal(inode, iblock, chain, partial); + goal = ext2_find_goal(inode, iblock, partial); /* the number of blocks need to allocate for [d,t]indirect blocks */ indirect_blks = (chain + depth) - partial - 1; diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c index 320b2cb3d4d..b8ea11fee5c 100644 --- a/fs/ext2/ioctl.c +++ b/fs/ext2/ioctl.c @@ -17,9 +17,9 @@ #include <asm/uaccess.h> -int ext2_ioctl (struct inode * inode, struct file * filp, unsigned int cmd, - unsigned long arg) +long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { + struct inode *inode = filp->f_dentry->d_inode; struct ext2_inode_info *ei = EXT2_I(inode); unsigned int flags; unsigned short rsv_window_size; @@ -141,9 +141,6 @@ int ext2_ioctl (struct inode * inode, struct file * filp, unsigned int cmd, #ifdef CONFIG_COMPAT long ext2_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - struct inode *inode = file->f_path.dentry->d_inode; - int ret; - /* These are just misnamed, they actually get/put from/to user an int */ switch (cmd) { case EXT2_IOC32_GETFLAGS: @@ -161,9 +158,6 @@ long ext2_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) default: return -ENOIOCTLCMD; } - lock_kernel(); - ret = ext2_ioctl(inode, file, cmd, (unsigned long) compat_ptr(arg)); - unlock_kernel(); - return ret; + return ext2_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); } #endif diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 6abaf75163f..1ba18b72d43 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -234,16 +234,16 @@ static int ext2_show_options(struct seq_file *seq, struct vfsmount *vfs) le16_to_cpu(es->s_def_resgid) != EXT2_DEF_RESGID) { seq_printf(seq, ",resgid=%u", sbi->s_resgid); } - if (test_opt(sb, ERRORS_CONT)) { + if (test_opt(sb, ERRORS_RO)) { int def_errors = le16_to_cpu(es->s_errors); if (def_errors == EXT2_ERRORS_PANIC || - def_errors == EXT2_ERRORS_RO) { - seq_puts(seq, ",errors=continue"); + def_errors == EXT2_ERRORS_CONTINUE) { + seq_puts(seq, ",errors=remount-ro"); } } - if (test_opt(sb, ERRORS_RO)) - seq_puts(seq, ",errors=remount-ro"); + if (test_opt(sb, ERRORS_CONT)) + seq_puts(seq, ",errors=continue"); if (test_opt(sb, ERRORS_PANIC)) seq_puts(seq, ",errors=panic"); if (test_opt(sb, NO_UID32)) @@ -617,27 +617,24 @@ static int ext2_setup_super (struct super_block * sb, return res; } -static int ext2_check_descriptors (struct super_block * sb) +static int ext2_check_descriptors(struct super_block *sb) { int i; - int desc_block = 0; struct ext2_sb_info *sbi = EXT2_SB(sb); unsigned long first_block = le32_to_cpu(sbi->s_es->s_first_data_block); unsigned long last_block; - struct ext2_group_desc * gdp = NULL; ext2_debug ("Checking group descriptors"); - for (i = 0; i < sbi->s_groups_count; i++) - { + for (i = 0; i < sbi->s_groups_count; i++) { + struct ext2_group_desc *gdp = ext2_get_group_desc(sb, i, NULL); + if (i == sbi->s_groups_count - 1) last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1; else last_block = first_block + (EXT2_BLOCKS_PER_GROUP(sb) - 1); - if ((i % EXT2_DESC_PER_BLOCK(sb)) == 0) - gdp = (struct ext2_group_desc *) sbi->s_group_desc[desc_block++]->b_data; if (le32_to_cpu(gdp->bg_block_bitmap) < first_block || le32_to_cpu(gdp->bg_block_bitmap) > last_block) { @@ -667,7 +664,6 @@ static int ext2_check_descriptors (struct super_block * sb) return 0; } first_block += EXT2_BLOCKS_PER_GROUP(sb); - gdp++; } return 1; } @@ -820,10 +816,10 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_PANIC) set_opt(sbi->s_mount_opt, ERRORS_PANIC); - else if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_RO) - set_opt(sbi->s_mount_opt, ERRORS_RO); - else + else if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_CONTINUE) set_opt(sbi->s_mount_opt, ERRORS_CONT); + else + set_opt(sbi->s_mount_opt, ERRORS_RO); sbi->s_resuid = le16_to_cpu(es->s_def_resuid); sbi->s_resgid = le16_to_cpu(es->s_def_resgid); @@ -868,8 +864,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); - if ((ext2_use_xip(sb)) && ((blocksize != PAGE_SIZE) || - (sb->s_blocksize != blocksize))) { + if (ext2_use_xip(sb) && blocksize != PAGE_SIZE) { if (!silent) printk("XIP: Unsupported blocksize\n"); goto failed_mount; diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c index a8ba7e83127..a7571303110 100644 --- a/fs/ext3/balloc.c +++ b/fs/ext3/balloc.c @@ -80,13 +80,57 @@ struct ext3_group_desc * ext3_get_group_desc(struct super_block * sb, return desc + offset; } +static int ext3_valid_block_bitmap(struct super_block *sb, + struct ext3_group_desc *desc, + unsigned int block_group, + struct buffer_head *bh) +{ + ext3_grpblk_t offset; + ext3_grpblk_t next_zero_bit; + ext3_fsblk_t bitmap_blk; + ext3_fsblk_t group_first_block; + + group_first_block = ext3_group_first_block_no(sb, block_group); + + /* check whether block bitmap block number is set */ + bitmap_blk = le32_to_cpu(desc->bg_block_bitmap); + offset = bitmap_blk - group_first_block; + if (!ext3_test_bit(offset, bh->b_data)) + /* bad block bitmap */ + goto err_out; + + /* check whether the inode bitmap block number is set */ + bitmap_blk = le32_to_cpu(desc->bg_inode_bitmap); + offset = bitmap_blk - group_first_block; + if (!ext3_test_bit(offset, bh->b_data)) + /* bad block bitmap */ + goto err_out; + + /* check whether the inode table block number is set */ + bitmap_blk = le32_to_cpu(desc->bg_inode_table); + offset = bitmap_blk - group_first_block; + next_zero_bit = ext3_find_next_zero_bit(bh->b_data, + offset + EXT3_SB(sb)->s_itb_per_group, + offset); + if (next_zero_bit >= offset + EXT3_SB(sb)->s_itb_per_group) + /* good bitmap for inode tables */ + return 1; + +err_out: + ext3_error(sb, __FUNCTION__, + "Invalid block bitmap - " + "block_group = %d, block = %lu", + block_group, bitmap_blk); + return 0; +} + /** * read_block_bitmap() * @sb: super block * @block_group: given block group * - * Read the bitmap for a given block_group, reading into the specified - * slot in the superblock's bitmap cache. + * Read the bitmap for a given block_group,and validate the + * bits for block/inode/inode tables are set in the bitmaps * * Return buffer_head on success or NULL in case of failure. */ @@ -95,17 +139,35 @@ read_block_bitmap(struct super_block *sb, unsigned int block_group) { struct ext3_group_desc * desc; struct buffer_head * bh = NULL; + ext3_fsblk_t bitmap_blk; - desc = ext3_get_group_desc (sb, block_group, NULL); + desc = ext3_get_group_desc(sb, block_group, NULL); if (!desc) - goto error_out; - bh = sb_bread(sb, le32_to_cpu(desc->bg_block_bitmap)); - if (!bh) - ext3_error (sb, "read_block_bitmap", + return NULL; + bitmap_blk = le32_to_cpu(desc->bg_block_bitmap); + bh = sb_getblk(sb, bitmap_blk); + if (unlikely(!bh)) { + ext3_error(sb, __FUNCTION__, "Cannot read block bitmap - " "block_group = %d, block_bitmap = %u", block_group, le32_to_cpu(desc->bg_block_bitmap)); -error_out: + return NULL; + } + if (likely(bh_uptodate_or_lock(bh))) + return bh; + + if (bh_submit_read(bh) < 0) { + brelse(bh); + ext3_error(sb, __FUNCTION__, + "Cannot read block bitmap - " + "block_group = %d, block_bitmap = %u", + block_group, le32_to_cpu(desc->bg_block_bitmap)); + return NULL; + } + if (!ext3_valid_block_bitmap(sb, desc, block_group, bh)) { + brelse(bh); + return NULL; + } return bh; } /* @@ -468,11 +530,13 @@ do_more: in_range (block, le32_to_cpu(desc->bg_inode_table), sbi->s_itb_per_group) || in_range (block + count - 1, le32_to_cpu(desc->bg_inode_table), - sbi->s_itb_per_group)) + sbi->s_itb_per_group)) { ext3_error (sb, "ext3_free_blocks", "Freeing blocks in system zones - " "Block = "E3FSBLK", count = %lu", block, count); + goto error_return; + } /* * We are about to start releasing blocks in the bitmap, @@ -1508,7 +1572,7 @@ retry_alloc: /* * Now search the rest of the groups. We assume that - * i and gdp correctly point to the last group visited. + * group_no and gdp correctly point to the last group visited. */ for (bgi = 0; bgi < ngroups; bgi++) { group_no++; @@ -1575,11 +1639,13 @@ allocated: in_range(ret_block, le32_to_cpu(gdp->bg_inode_table), EXT3_SB(sb)->s_itb_per_group) || in_range(ret_block + num - 1, le32_to_cpu(gdp->bg_inode_table), - EXT3_SB(sb)->s_itb_per_group)) + EXT3_SB(sb)->s_itb_per_group)) { ext3_error(sb, "ext3_new_block", "Allocating block in system zone - " "blocks from "E3FSBLK", length %lu", ret_block, num); + goto out; + } performed_allocation = 1; @@ -1782,11 +1848,7 @@ static unsigned long ext3_bg_num_gdb_meta(struct super_block *sb, int group) static unsigned long ext3_bg_num_gdb_nometa(struct super_block *sb, int group) { - if (EXT3_HAS_RO_COMPAT_FEATURE(sb, - EXT3_FEATURE_RO_COMPAT_SPARSE_SUPER) && - !ext3_group_sparse(group)) - return 0; - return EXT3_SB(sb)->s_gdb_count; + return ext3_bg_has_super(sb, group) ? EXT3_SB(sb)->s_gdb_count : 0; } /** diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 9b162cd6c16..8a9ce2d09bd 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -439,16 +439,14 @@ static ext3_fsblk_t ext3_find_near(struct inode *inode, Indirect *ind) * ext3_find_goal - find a prefered place for allocation. * @inode: owner * @block: block we want - * @chain: chain of indirect blocks * @partial: pointer to the last triple within a chain - * @goal: place to store the result. * * Normally this function find the prefered place for block allocation, - * stores it in *@goal and returns zero. + * returns it. */ static ext3_fsblk_t ext3_find_goal(struct inode *inode, long block, - Indirect chain[4], Indirect *partial) + Indirect *partial) { struct ext3_block_alloc_info *block_i; @@ -884,7 +882,7 @@ int ext3_get_blocks_handle(handle_t *handle, struct inode *inode, if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info)) ext3_init_block_alloc_info(inode); - goal = ext3_find_goal(inode, iblock, chain, partial); + goal = ext3_find_goal(inode, iblock, partial); /* the number of blocks need to allocate for [d,t]indirect blocks */ indirect_blks = (chain + depth) - partial - 1; @@ -941,55 +939,45 @@ out: return err; } -#define DIO_CREDITS (EXT3_RESERVE_TRANS_BLOCKS + 32) +/* Maximum number of blocks we map for direct IO at once. */ +#define DIO_MAX_BLOCKS 4096 +/* + * Number of credits we need for writing DIO_MAX_BLOCKS: + * We need sb + group descriptor + bitmap + inode -> 4 + * For B blocks with A block pointers per block we need: + * 1 (triple ind.) + (B/A/A + 2) (doubly ind.) + (B/A + 2) (indirect). + * If we plug in 4096 for B and 256 for A (for 1KB block size), we get 25. + */ +#define DIO_CREDITS 25 static int ext3_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { handle_t *handle = ext3_journal_current_handle(); - int ret = 0; + int ret = 0, started = 0; unsigned max_blocks = bh_result->b_size >> inode->i_blkbits; - if (!create) - goto get_block; /* A read */ - - if (max_blocks == 1) - goto get_block; /* A single block get */ - - if (handle->h_transaction->t_state == T_LOCKED) { - /* - * Huge direct-io writes can hold off commits for long - * periods of time. Let this commit run. - */ - ext3_journal_stop(handle); - handle = ext3_journal_start(inode, DIO_CREDITS); - if (IS_ERR(handle)) + if (create && !handle) { /* Direct IO write... */ + if (max_blocks > DIO_MAX_BLOCKS) + max_blocks = DIO_MAX_BLOCKS; + handle = ext3_journal_start(inode, DIO_CREDITS + + 2 * EXT3_QUOTA_TRANS_BLOCKS(inode->i_sb)); + if (IS_ERR(handle)) { ret = PTR_ERR(handle); - goto get_block; - } - - if (handle->h_buffer_credits <= EXT3_RESERVE_TRANS_BLOCKS) { - /* - * Getting low on buffer credits... - */ - ret = ext3_journal_extend(handle, DIO_CREDITS); - if (ret > 0) { - /* - * Couldn't extend the transaction. Start a new one. - */ - ret = ext3_journal_restart(handle, DIO_CREDITS); + goto out; } + started = 1; } -get_block: - if (ret == 0) { - ret = ext3_get_blocks_handle(handle, inode, iblock, + ret = ext3_get_blocks_handle(handle, inode, iblock, max_blocks, bh_result, create, 0); - if (ret > 0) { - bh_result->b_size = (ret << inode->i_blkbits); - ret = 0; - } + if (ret > 0) { + bh_result->b_size = (ret << inode->i_blkbits); + ret = 0; } + if (started) + ext3_journal_stop(handle); +out: return ret; } @@ -1680,7 +1668,8 @@ static int ext3_releasepage(struct page *page, gfp_t wait) * if the machine crashes during the write. * * If the O_DIRECT write is intantiating holes inside i_size and the machine - * crashes then stale disk data _may_ be exposed inside the file. + * crashes then stale disk data _may_ be exposed inside the file. But current + * VFS code falls back into buffered path in that case so we are safe. */ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t offset, @@ -1689,7 +1678,7 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct ext3_inode_info *ei = EXT3_I(inode); - handle_t *handle = NULL; + handle_t *handle; ssize_t ret; int orphan = 0; size_t count = iov_length(iov, nr_segs); @@ -1697,17 +1686,21 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, if (rw == WRITE) { loff_t final_size = offset + count; - handle = ext3_journal_start(inode, DIO_CREDITS); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - goto out; - } if (final_size > inode->i_size) { + /* Credits for sb + inode write */ + handle = ext3_journal_start(inode, 2); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } ret = ext3_orphan_add(handle, inode); - if (ret) - goto out_stop; + if (ret) { + ext3_journal_stop(handle); + goto out; + } orphan = 1; ei->i_disksize = inode->i_size; + ext3_journal_stop(handle); } } @@ -1715,18 +1708,21 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, offset, nr_segs, ext3_get_block, NULL); - /* - * Reacquire the handle: ext3_get_block() can restart the transaction - */ - handle = ext3_journal_current_handle(); - -out_stop: - if (handle) { + if (orphan) { int err; - if (orphan && inode->i_nlink) + /* Credits for sb + inode write */ + handle = ext3_journal_start(inode, 2); + if (IS_ERR(handle)) { + /* This is really bad luck. We've written the data + * but cannot extend i_size. Bail out and pretend + * the write failed... */ + ret = PTR_ERR(handle); + goto out; + } + if (inode->i_nlink) ext3_orphan_del(handle, inode); - if (orphan && ret > 0) { + if (ret > 0) { loff_t end = offset + ret; if (end > inode->i_size) { ei->i_disksize = end; @@ -1845,7 +1841,7 @@ static int ext3_block_truncate_page(handle_t *handle, struct page *page, */ if (!page_has_buffers(page) && test_opt(inode->i_sb, NOBH) && ext3_should_writeback_data(inode) && PageUptodate(page)) { - zero_user_page(page, offset, length, KM_USER0); + zero_user(page, offset, length); set_page_dirty(page); goto unlock; } @@ -1898,7 +1894,7 @@ static int ext3_block_truncate_page(handle_t *handle, struct page *page, goto unlock; } - zero_user_page(page, offset, length, KM_USER0); + zero_user(page, offset, length); BUFFER_TRACE(bh, "zeroed end of block"); err = 0; diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 4ab6f76e63d..92b83b004dd 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -860,14 +860,10 @@ static struct buffer_head * ext3_find_entry (struct dentry *dentry, int nblocks, i, err; struct inode *dir = dentry->d_parent->d_inode; int namelen; - const u8 *name; - unsigned blocksize; *res_dir = NULL; sb = dir->i_sb; - blocksize = sb->s_blocksize; namelen = dentry->d_name.len; - name = dentry->d_name.name; if (namelen > EXT3_NAME_LEN) return NULL; if (is_dx(dir)) { diff --git a/fs/ext3/super.c b/fs/ext3/super.c index f3675cc630e..343677e8c35 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -575,16 +575,16 @@ static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs) le16_to_cpu(es->s_def_resgid) != EXT3_DEF_RESGID) { seq_printf(seq, ",resgid=%u", sbi->s_resgid); } - if (test_opt(sb, ERRORS_CONT)) { + if (test_opt(sb, ERRORS_RO)) { int def_errors = le16_to_cpu(es->s_errors); if (def_errors == EXT3_ERRORS_PANIC || - def_errors == EXT3_ERRORS_RO) { - seq_puts(seq, ",errors=continue"); + def_errors == EXT3_ERRORS_CONTINUE) { + seq_puts(seq, ",errors=remount-ro"); } } - if (test_opt(sb, ERRORS_RO)) - seq_puts(seq, ",errors=remount-ro"); + if (test_opt(sb, ERRORS_CONT)) + seq_puts(seq, ",errors=continue"); if (test_opt(sb, ERRORS_PANIC)) seq_puts(seq, ",errors=panic"); if (test_opt(sb, NO_UID32)) @@ -1252,28 +1252,24 @@ static int ext3_setup_super(struct super_block *sb, struct ext3_super_block *es, } /* Called at mount-time, super-block is locked */ -static int ext3_check_descriptors (struct super_block * sb) +static int ext3_check_descriptors(struct super_block *sb) { struct ext3_sb_info *sbi = EXT3_SB(sb); ext3_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); ext3_fsblk_t last_block; - struct ext3_group_desc * gdp = NULL; - int desc_block = 0; int i; ext3_debug ("Checking group descriptors"); - for (i = 0; i < sbi->s_groups_count; i++) - { + for (i = 0; i < sbi->s_groups_count; i++) { + struct ext3_group_desc *gdp = ext3_get_group_desc(sb, i, NULL); + if (i == sbi->s_groups_count - 1) last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1; else last_block = first_block + (EXT3_BLOCKS_PER_GROUP(sb) - 1); - if ((i % EXT3_DESC_PER_BLOCK(sb)) == 0) - gdp = (struct ext3_group_desc *) - sbi->s_group_desc[desc_block++]->b_data; if (le32_to_cpu(gdp->bg_block_bitmap) < first_block || le32_to_cpu(gdp->bg_block_bitmap) > last_block) { @@ -1306,7 +1302,6 @@ static int ext3_check_descriptors (struct super_block * sb) return 0; } first_block += EXT3_BLOCKS_PER_GROUP(sb); - gdp++; } sbi->s_es->s_free_blocks_count=cpu_to_le32(ext3_count_free_blocks(sb)); @@ -1583,10 +1578,10 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_PANIC) set_opt(sbi->s_mount_opt, ERRORS_PANIC); - else if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_RO) - set_opt(sbi->s_mount_opt, ERRORS_RO); - else + else if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_CONTINUE) set_opt(sbi->s_mount_opt, ERRORS_CONT); + else + set_opt(sbi->s_mount_opt, ERRORS_RO); sbi->s_resuid = le16_to_cpu(es->s_def_resuid); sbi->s_resgid = le16_to_cpu(es->s_def_resgid); diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index ac75ea953d8..0737e05ba3d 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -1700,7 +1700,7 @@ retry_alloc: /* * Now search the rest of the groups. We assume that - * i and gdp correctly point to the last group visited. + * group_no and gdp correctly point to the last group visited. */ for (bgi = 0; bgi < ngroups; bgi++) { group_no++; @@ -2011,11 +2011,7 @@ static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb, static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb, ext4_group_t group) { - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) && - !ext4_group_sparse(group)) - return 0; - return EXT4_SB(sb)->s_gdb_count; + return ext4_bg_has_super(sb, group) ? EXT4_SB(sb)->s_gdb_count : 0; } /** diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index bb717cbb749..0e9055cf700 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -429,16 +429,13 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind) * ext4_find_goal - find a prefered place for allocation. * @inode: owner * @block: block we want - * @chain: chain of indirect blocks * @partial: pointer to the last triple within a chain - * @goal: place to store the result. * * Normally this function find the prefered place for block allocation, - * stores it in *@goal and returns zero. + * returns it. */ - static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block, - Indirect chain[4], Indirect *partial) + Indirect *partial) { struct ext4_block_alloc_info *block_i; @@ -839,7 +836,7 @@ int ext4_get_blocks_handle(handle_t *handle, struct inode *inode, if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info)) ext4_init_block_alloc_info(inode); - goal = ext4_find_goal(inode, iblock, chain, partial); + goal = ext4_find_goal(inode, iblock, partial); /* the number of blocks need to allocate for [d,t]indirect blocks */ indirect_blks = (chain + depth) - partial - 1; @@ -1840,7 +1837,7 @@ int ext4_block_truncate_page(handle_t *handle, struct page *page, */ if (!page_has_buffers(page) && test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode) && PageUptodate(page)) { - zero_user_page(page, offset, length, KM_USER0); + zero_user(page, offset, length); set_page_dirty(page); goto unlock; } @@ -1893,7 +1890,7 @@ int ext4_block_truncate_page(handle_t *handle, struct page *page, goto unlock; } - zero_user_page(page, offset, length, KM_USER0); + zero_user(page, offset, length); BUFFER_TRACE(bh, "zeroed end of block"); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 055a0cd0168..c89bb879776 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1458,7 +1458,7 @@ int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 block_group, } /* Called at mount-time, super-block is locked */ -static int ext4_check_descriptors (struct super_block * sb) +static int ext4_check_descriptors(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); @@ -1466,8 +1466,6 @@ static int ext4_check_descriptors (struct super_block * sb) ext4_fsblk_t block_bitmap; ext4_fsblk_t inode_bitmap; ext4_fsblk_t inode_table; - struct ext4_group_desc * gdp = NULL; - int desc_block = 0; int flexbg_flag = 0; ext4_group_t i; @@ -1476,17 +1474,15 @@ static int ext4_check_descriptors (struct super_block * sb) ext4_debug ("Checking group descriptors"); - for (i = 0; i < sbi->s_groups_count; i++) - { + for (i = 0; i < sbi->s_groups_count; i++) { + struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL); + if (i == sbi->s_groups_count - 1 || flexbg_flag) last_block = ext4_blocks_count(sbi->s_es) - 1; else last_block = first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1); - if ((i % EXT4_DESC_PER_BLOCK(sb)) == 0) - gdp = (struct ext4_group_desc *) - sbi->s_group_desc[desc_block++]->b_data; block_bitmap = ext4_block_bitmap(sb, gdp); if (block_bitmap < first_block || block_bitmap > last_block) { @@ -1524,8 +1520,6 @@ static int ext4_check_descriptors (struct super_block * sb) } if (!flexbg_flag) first_block += EXT4_BLOCKS_PER_GROUP(sb); - gdp = (struct ext4_group_desc *) - ((__u8 *)gdp + EXT4_DESC_SIZE(sb)); } ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb)); diff --git a/fs/fat/file.c b/fs/fat/file.c index 69a83b59dce..c614175876e 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -155,6 +155,42 @@ out: return err; } +static int check_mode(const struct msdos_sb_info *sbi, mode_t mode) +{ + mode_t req = mode & ~S_IFMT; + + /* + * Of the r and x bits, all (subject to umask) must be present. Of the + * w bits, either all (subject to umask) or none must be present. + */ + + if (S_ISREG(mode)) { + req &= ~sbi->options.fs_fmask; + + if ((req & (S_IRUGO | S_IXUGO)) != + ((S_IRUGO | S_IXUGO) & ~sbi->options.fs_fmask)) + return -EPERM; + + if ((req & S_IWUGO) != 0 && + (req & S_IWUGO) != (S_IWUGO & ~sbi->options.fs_fmask)) + return -EPERM; + } else if (S_ISDIR(mode)) { + req &= ~sbi->options.fs_dmask; + + if ((req & (S_IRUGO | S_IXUGO)) != + ((S_IRUGO | S_IXUGO) & ~sbi->options.fs_dmask)) + return -EPERM; + + if ((req & S_IWUGO) != 0 && + (req & S_IWUGO) != (S_IWUGO & ~sbi->options.fs_dmask)) + return -EPERM; + } else { + return -EPERM; + } + + return 0; +} + int fat_notify_change(struct dentry *dentry, struct iattr *attr) { struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb); @@ -186,9 +222,7 @@ int fat_notify_change(struct dentry *dentry, struct iattr *attr) if (((attr->ia_valid & ATTR_UID) && (attr->ia_uid != sbi->options.fs_uid)) || ((attr->ia_valid & ATTR_GID) && - (attr->ia_gid != sbi->options.fs_gid)) || - ((attr->ia_valid & ATTR_MODE) && - (attr->ia_mode & ~MSDOS_VALID_MODE))) + (attr->ia_gid != sbi->options.fs_gid))) error = -EPERM; if (error) { @@ -196,6 +230,13 @@ int fat_notify_change(struct dentry *dentry, struct iattr *attr) error = 0; goto out; } + + if (attr->ia_valid & ATTR_MODE) { + error = check_mode(sbi, attr->ia_mode); + if (error != 0 && !sbi->options.quiet) + goto out; + } + error = inode_setattr(inode, attr); if (error) goto out; diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 920a576e1c2..24c0aaa5ae8 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -1295,10 +1295,8 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, fsinfo = (struct fat_boot_fsinfo *)fsinfo_bh->b_data; if (!IS_FSINFO(fsinfo)) { - printk(KERN_WARNING - "FAT: Did not find valid FSINFO signature.\n" - " Found signature1 0x%08x signature2 0x%08x" - " (sector = %lu)\n", + printk(KERN_WARNING "FAT: Invalid FSINFO signature: " + "0x%08x, 0x%08x (sector = %lu)\n", le32_to_cpu(fsinfo->signature1), le32_to_cpu(fsinfo->signature2), sbi->fsinfo_sector); diff --git a/fs/fat/misc.c b/fs/fat/misc.c index 308f2b6b502..61f23511eac 100644 --- a/fs/fat/misc.c +++ b/fs/fat/misc.c @@ -55,9 +55,8 @@ void fat_clusters_flush(struct super_block *sb) fsinfo = (struct fat_boot_fsinfo *)bh->b_data; /* Sanity check */ if (!IS_FSINFO(fsinfo)) { - printk(KERN_ERR "FAT: Did not find valid FSINFO signature.\n" - " Found signature1 0x%08x signature2 0x%08x" - " (sector = %lu)\n", + printk(KERN_ERR "FAT: Invalid FSINFO signature: " + "0x%08x, 0x%08x (sector = %lu)\n", le32_to_cpu(fsinfo->signature1), le32_to_cpu(fsinfo->signature2), sbi->fsinfo_sector); diff --git a/fs/file.c b/fs/file.c index c5575de0111..5110acb1c9e 100644 --- a/fs/file.c +++ b/fs/file.c @@ -24,6 +24,8 @@ struct fdtable_defer { struct fdtable *next; }; +int sysctl_nr_open __read_mostly = 1024*1024; + /* * We use this list to defer free fdtables that have vmalloced * sets/arrays. By keeping a per-cpu list, we avoid having to embed @@ -147,8 +149,8 @@ static struct fdtable * alloc_fdtable(unsigned int nr) nr /= (1024 / sizeof(struct file *)); nr = roundup_pow_of_two(nr + 1); nr *= (1024 / sizeof(struct file *)); - if (nr > NR_OPEN) - nr = NR_OPEN; + if (nr > sysctl_nr_open) + nr = sysctl_nr_open; fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL); if (!fdt) @@ -233,7 +235,7 @@ int expand_files(struct files_struct *files, int nr) if (nr < fdt->max_fds) return 0; /* Can we expand? */ - if (nr >= NR_OPEN) + if (nr >= sysctl_nr_open) return -EMFILE; /* All good, so we try */ diff --git a/fs/freevxfs/vxfs_dir.h b/fs/freevxfs/vxfs_dir.h index 3c96d6e6397..aaf1fb09863 100644 --- a/fs/freevxfs/vxfs_dir.h +++ b/fs/freevxfs/vxfs_dir.h @@ -41,7 +41,7 @@ * VxFS directory block header. * * This entry is the head of every filesystem block in a directory. - * It is used for free space managment and additionally includes + * It is used for free space management and additionally includes * a hash for speeding up directory search (lookup). * * The hash may be empty and in fact we do not use it all in the diff --git a/fs/freevxfs/vxfs_immed.c b/fs/freevxfs/vxfs_immed.c index 24b5a775ff9..8a5959a61ba 100644 --- a/fs/freevxfs/vxfs_immed.c +++ b/fs/freevxfs/vxfs_immed.c @@ -54,7 +54,7 @@ const struct inode_operations vxfs_immed_symlink_iops = { }; /* - * Adress space operations for immed files and directories. + * Address space operations for immed files and directories. */ const struct address_space_operations vxfs_immed_aops = { .readpage = vxfs_immed_readpage, diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 300324bd563..db80ce9eb1d 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -284,7 +284,17 @@ __sync_single_inode(struct inode *inode, struct writeback_control *wbc) * soon as the queue becomes uncongested. */ inode->i_state |= I_DIRTY_PAGES; - requeue_io(inode); + if (wbc->nr_to_write <= 0) { + /* + * slice used up: queue for next turn + */ + requeue_io(inode); + } else { + /* + * somehow blocked: retry later + */ + redirty_tail(inode); + } } else { /* * Otherwise fully redirty the inode so that @@ -334,9 +344,6 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) WARN_ON(inode->i_state & I_WILL_FREE); if ((wbc->sync_mode != WB_SYNC_ALL) && (inode->i_state & I_SYNC)) { - struct address_space *mapping = inode->i_mapping; - int ret; - /* * We're skipping this inode because it's locked, and we're not * doing writeback-for-data-integrity. Move it to s_more_io so @@ -345,15 +352,7 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * completed a full scan of s_io. */ requeue_io(inode); - - /* - * Even if we don't actually write the inode itself here, - * we can at least start some of the data writeout.. - */ - spin_unlock(&inode_lock); - ret = do_writepages(mapping, wbc); - spin_lock(&inode_lock); - return ret; + return 0; } /* @@ -479,8 +478,12 @@ sync_sb_inodes(struct super_block *sb, struct writeback_control *wbc) iput(inode); cond_resched(); spin_lock(&inode_lock); - if (wbc->nr_to_write <= 0) + if (wbc->nr_to_write <= 0) { + wbc->more_io = 1; break; + } + if (!list_empty(&sb->s_more_io)) + wbc->more_io = 1; } return; /* Leave any unwritten inodes on s_io */ } @@ -512,8 +515,7 @@ writeback_inodes(struct writeback_control *wbc) might_sleep(); spin_lock(&sb_lock); restart: - sb = sb_entry(super_blocks.prev); - for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.prev)) { + list_for_each_entry_reverse(sb, &super_blocks, s_list) { if (sb_has_dirty_inodes(sb)) { /* we're making our own get_super here */ sb->s_count++; @@ -578,10 +580,8 @@ static void set_sb_syncing(int val) { struct super_block *sb; spin_lock(&sb_lock); - sb = sb_entry(super_blocks.prev); - for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.prev)) { + list_for_each_entry_reverse(sb, &super_blocks, s_list) sb->s_syncing = val; - } spin_unlock(&sb_lock); } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index db534bcde45..af639807524 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -201,6 +201,55 @@ void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req) } } +static unsigned len_args(unsigned numargs, struct fuse_arg *args) +{ + unsigned nbytes = 0; + unsigned i; + + for (i = 0; i < numargs; i++) + nbytes += args[i].size; + + return nbytes; +} + +static u64 fuse_get_unique(struct fuse_conn *fc) +{ + fc->reqctr++; + /* zero is special */ + if (fc->reqctr == 0) + fc->reqctr = 1; + + return fc->reqctr; +} + +static void queue_request(struct fuse_conn *fc, struct fuse_req *req) +{ + req->in.h.unique = fuse_get_unique(fc); + req->in.h.len = sizeof(struct fuse_in_header) + + len_args(req->in.numargs, (struct fuse_arg *) req->in.args); + list_add_tail(&req->list, &fc->pending); + req->state = FUSE_REQ_PENDING; + if (!req->waiting) { + req->waiting = 1; + atomic_inc(&fc->num_waiting); + } + wake_up(&fc->waitq); + kill_fasync(&fc->fasync, SIGIO, POLL_IN); +} + +static void flush_bg_queue(struct fuse_conn *fc) +{ + while (fc->active_background < FUSE_MAX_BACKGROUND && + !list_empty(&fc->bg_queue)) { + struct fuse_req *req; + + req = list_entry(fc->bg_queue.next, struct fuse_req, list); + list_del(&req->list); + fc->active_background++; + queue_request(fc, req); + } +} + /* * This function is called when a request is finished. Either a reply * has arrived or it was aborted (and not yet sent) or some error @@ -229,6 +278,8 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req) clear_bdi_congested(&fc->bdi, WRITE); } fc->num_background--; + fc->active_background--; + flush_bg_queue(fc); } spin_unlock(&fc->lock); wake_up(&req->waitq); @@ -320,42 +371,6 @@ static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req) } } -static unsigned len_args(unsigned numargs, struct fuse_arg *args) -{ - unsigned nbytes = 0; - unsigned i; - - for (i = 0; i < numargs; i++) - nbytes += args[i].size; - - return nbytes; -} - -static u64 fuse_get_unique(struct fuse_conn *fc) - { - fc->reqctr++; - /* zero is special */ - if (fc->reqctr == 0) - fc->reqctr = 1; - - return fc->reqctr; -} - -static void queue_request(struct fuse_conn *fc, struct fuse_req *req) -{ - req->in.h.unique = fuse_get_unique(fc); - req->in.h.len = sizeof(struct fuse_in_header) + - len_args(req->in.numargs, (struct fuse_arg *) req->in.args); - list_add_tail(&req->list, &fc->pending); - req->state = FUSE_REQ_PENDING; - if (!req->waiting) { - req->waiting = 1; - atomic_inc(&fc->num_waiting); - } - wake_up(&fc->waitq); - kill_fasync(&fc->fasync, SIGIO, POLL_IN); -} - void request_send(struct fuse_conn *fc, struct fuse_req *req) { req->isreply = 1; @@ -375,20 +390,26 @@ void request_send(struct fuse_conn *fc, struct fuse_req *req) spin_unlock(&fc->lock); } +static void request_send_nowait_locked(struct fuse_conn *fc, + struct fuse_req *req) +{ + req->background = 1; + fc->num_background++; + if (fc->num_background == FUSE_MAX_BACKGROUND) + fc->blocked = 1; + if (fc->num_background == FUSE_CONGESTION_THRESHOLD) { + set_bdi_congested(&fc->bdi, READ); + set_bdi_congested(&fc->bdi, WRITE); + } + list_add_tail(&req->list, &fc->bg_queue); + flush_bg_queue(fc); +} + static void request_send_nowait(struct fuse_conn *fc, struct fuse_req *req) { spin_lock(&fc->lock); if (fc->connected) { - req->background = 1; - fc->num_background++; - if (fc->num_background == FUSE_MAX_BACKGROUND) - fc->blocked = 1; - if (fc->num_background == FUSE_CONGESTION_THRESHOLD) { - set_bdi_congested(&fc->bdi, READ); - set_bdi_congested(&fc->bdi, WRITE); - } - - queue_request(fc, req); + request_send_nowait_locked(fc, req); spin_unlock(&fc->lock); } else { req->out.h.error = -ENOTCONN; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 80d2f5292cf..f56f91bd38b 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -416,6 +416,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, fuse_put_request(fc, forget_req); d_instantiate(entry, inode); fuse_change_entry_timeout(entry, &outentry); + fuse_invalidate_attr(dir); file = lookup_instantiate_filp(nd, entry, generic_file_open); if (IS_ERR(file)) { ff->fh = outopen.fh; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index bb05d227cf3..676b0bc8a86 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -77,8 +77,8 @@ static struct fuse_file *fuse_file_get(struct fuse_file *ff) static void fuse_release_end(struct fuse_conn *fc, struct fuse_req *req) { - dput(req->dentry); - mntput(req->vfsmount); + dput(req->misc.release.dentry); + mntput(req->misc.release.vfsmount); fuse_put_request(fc, req); } @@ -86,7 +86,8 @@ static void fuse_file_put(struct fuse_file *ff) { if (atomic_dec_and_test(&ff->count)) { struct fuse_req *req = ff->reserved_req; - struct fuse_conn *fc = get_fuse_conn(req->dentry->d_inode); + struct inode *inode = req->misc.release.dentry->d_inode; + struct fuse_conn *fc = get_fuse_conn(inode); req->end = fuse_release_end; request_send_background(fc, req); kfree(ff); @@ -137,7 +138,7 @@ int fuse_open_common(struct inode *inode, struct file *file, int isdir) void fuse_release_fill(struct fuse_file *ff, u64 nodeid, int flags, int opcode) { struct fuse_req *req = ff->reserved_req; - struct fuse_release_in *inarg = &req->misc.release_in; + struct fuse_release_in *inarg = &req->misc.release.in; inarg->fh = ff->fh; inarg->flags = flags; @@ -153,13 +154,14 @@ int fuse_release_common(struct inode *inode, struct file *file, int isdir) struct fuse_file *ff = file->private_data; if (ff) { struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_req *req = ff->reserved_req; fuse_release_fill(ff, get_node_id(inode), file->f_flags, isdir ? FUSE_RELEASEDIR : FUSE_RELEASE); /* Hold vfsmount and dentry until release is finished */ - ff->reserved_req->vfsmount = mntget(file->f_path.mnt); - ff->reserved_req->dentry = dget(file->f_path.dentry); + req->misc.release.vfsmount = mntget(file->f_path.mnt); + req->misc.release.dentry = dget(file->f_path.dentry); spin_lock(&fc->lock); list_del(&ff->write_entry); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 3ab8a3048e8..67aaf6ee38e 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -215,7 +215,11 @@ struct fuse_req { /** Data for asynchronous requests */ union { struct fuse_forget_in forget_in; - struct fuse_release_in release_in; + struct { + struct fuse_release_in in; + struct vfsmount *vfsmount; + struct dentry *dentry; + } release; struct fuse_init_in init_in; struct fuse_init_out init_out; struct fuse_read_in read_in; @@ -238,12 +242,6 @@ struct fuse_req { /** File used in the request (or NULL) */ struct fuse_file *ff; - /** vfsmount used in release */ - struct vfsmount *vfsmount; - - /** dentry used in release */ - struct dentry *dentry; - /** Request completion callback */ void (*end)(struct fuse_conn *, struct fuse_req *); @@ -298,6 +296,12 @@ struct fuse_conn { /** Number of requests currently in the background */ unsigned num_background; + /** Number of background requests currently queued for userspace */ + unsigned active_background; + + /** The list of background requests set aside for later queuing */ + struct list_head bg_queue; + /** Pending interrupts */ struct list_head interrupts; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index e5e80d1a468..c90f633d0b5 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -465,6 +465,7 @@ static struct fuse_conn *new_conn(void) INIT_LIST_HEAD(&fc->processing); INIT_LIST_HEAD(&fc->io); INIT_LIST_HEAD(&fc->interrupts); + INIT_LIST_HEAD(&fc->bg_queue); atomic_set(&fc->num_waiting, 0); fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE; fc->bdi.unplug_io_fn = default_unplug_io_fn; diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index e4effc47abf..e9456ebd3bb 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -932,7 +932,7 @@ static int gfs2_block_truncate_page(struct address_space *mapping) if (!gfs2_is_writeback(ip)) gfs2_trans_add_bh(ip->i_gl, bh, 0); - zero_user_page(page, offset, length, KM_USER0); + zero_user(page, offset, length); unlock: unlock_page(page); diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c index 38dbe99a30e..ac772b6d9db 100644 --- a/fs/gfs2/ops_address.c +++ b/fs/gfs2/ops_address.c @@ -446,7 +446,7 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page) * so we need to supply one here. It doesn't happen often. */ if (unlikely(page->index)) { - zero_user_page(page, 0, PAGE_CACHE_SIZE, KM_USER0); + zero_user(page, 0, PAGE_CACHE_SIZE); return 0; } diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index b249e294a95..6fb07d67ca8 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -450,7 +450,7 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd) fs_info(sdp, "jid=%u: Trying to acquire journal lock...\n", jd->jd_jid); - /* Aquire the journal lock so we can do recovery */ + /* Acquire the journal lock so we can do recovery */ error = gfs2_glock_nq_num(sdp, jd->jd_jid, &gfs2_journal_glops, LM_ST_EXCLUSIVE, diff --git a/fs/hfs/bfind.c b/fs/hfs/bfind.c index f8452a0eab5..4129cdb3f0d 100644 --- a/fs/hfs/bfind.c +++ b/fs/hfs/bfind.c @@ -52,9 +52,9 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd) rec = (e + b) / 2; len = hfs_brec_lenoff(bnode, rec, &off); keylen = hfs_brec_keylen(bnode, rec); - if (keylen == HFS_BAD_KEYLEN) { + if (keylen == 0) { res = -EINVAL; - goto done; + goto fail; } hfs_bnode_read(bnode, fd->key, off, keylen); cmpval = bnode->tree->keycmp(fd->key, fd->search_key); @@ -71,9 +71,9 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd) if (rec != e && e >= 0) { len = hfs_brec_lenoff(bnode, e, &off); keylen = hfs_brec_keylen(bnode, e); - if (keylen == HFS_BAD_KEYLEN) { + if (keylen == 0) { res = -EINVAL; - goto done; + goto fail; } hfs_bnode_read(bnode, fd->key, off, keylen); } @@ -83,6 +83,7 @@ done: fd->keylength = keylen; fd->entryoffset = off + keylen; fd->entrylength = len - keylen; +fail: return res; } @@ -206,7 +207,7 @@ int hfs_brec_goto(struct hfs_find_data *fd, int cnt) len = hfs_brec_lenoff(bnode, fd->record, &off); keylen = hfs_brec_keylen(bnode, fd->record); - if (keylen == HFS_BAD_KEYLEN) { + if (keylen == 0) { res = -EINVAL; goto out; } diff --git a/fs/hfs/brec.c b/fs/hfs/brec.c index 8626ee375ea..878bf25dbc6 100644 --- a/fs/hfs/brec.c +++ b/fs/hfs/brec.c @@ -49,14 +49,14 @@ u16 hfs_brec_keylen(struct hfs_bnode *node, u16 rec) if (retval > node->tree->max_key_len + 2) { printk(KERN_ERR "hfs: keylen %d too large\n", retval); - retval = HFS_BAD_KEYLEN; + retval = 0; } } else { retval = (hfs_bnode_read_u8(node, recoff) | 1) + 1; if (retval > node->tree->max_key_len + 1) { printk(KERN_ERR "hfs: keylen %d too large\n", retval); - retval = HFS_BAD_KEYLEN; + retval = 0; } } } diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c index 110dd3515dc..24cf6fc4302 100644 --- a/fs/hfs/btree.c +++ b/fs/hfs/btree.c @@ -81,15 +81,23 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke goto fail_page; if (!tree->node_count) goto fail_page; - if ((id == HFS_EXT_CNID) && (tree->max_key_len != HFS_MAX_EXT_KEYLEN)) { - printk(KERN_ERR "hfs: invalid extent max_key_len %d\n", - tree->max_key_len); - goto fail_page; - } - if ((id == HFS_CAT_CNID) && (tree->max_key_len != HFS_MAX_CAT_KEYLEN)) { - printk(KERN_ERR "hfs: invalid catalog max_key_len %d\n", - tree->max_key_len); - goto fail_page; + switch (id) { + case HFS_EXT_CNID: + if (tree->max_key_len != HFS_MAX_EXT_KEYLEN) { + printk(KERN_ERR "hfs: invalid extent max_key_len %d\n", + tree->max_key_len); + goto fail_page; + } + break; + case HFS_CAT_CNID: + if (tree->max_key_len != HFS_MAX_CAT_KEYLEN) { + printk(KERN_ERR "hfs: invalid catalog max_key_len %d\n", + tree->max_key_len); + goto fail_page; + } + break; + default: + BUG(); } tree->node_size_shift = ffs(size) - 1; diff --git a/fs/hfs/hfs.h b/fs/hfs/hfs.h index c6aae61adfe..6f194d0768b 100644 --- a/fs/hfs/hfs.h +++ b/fs/hfs/hfs.h @@ -28,8 +28,6 @@ #define HFS_MAX_NAMELEN 128 #define HFS_MAX_VALENCE 32767U -#define HFS_BAD_KEYLEN 0xFF - /* Meanings of the drAtrb field of the MDB, * Reference: _Inside Macintosh: Files_ p. 2-61 */ diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 16cbd902f8b..32de44ed002 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -6,7 +6,7 @@ * This file may be distributed under the terms of the GNU General Public License. * * This file contains hfs_read_super(), some of the super_ops and - * init_module() and cleanup_module(). The remaining super_ops are in + * init_hfs_fs() and exit_hfs_fs(). The remaining super_ops are in * inode.c since they deal with inodes. * * Based on the minix file system code, (C) 1991, 1992 by Linus Torvalds diff --git a/fs/hostfs/hostfs_user.c b/fs/hostfs/hostfs_user.c index 35c1a9f33f4..53fd0a67c11 100644 --- a/fs/hostfs/hostfs_user.c +++ b/fs/hostfs/hostfs_user.c @@ -285,17 +285,17 @@ int set_attr(const char *file, struct hostfs_iattr *attrs, int fd) return err; times[0].tv_sec = atime_ts.tv_sec; - times[0].tv_usec = atime_ts.tv_nsec * 1000; + times[0].tv_usec = atime_ts.tv_nsec / 1000; times[1].tv_sec = mtime_ts.tv_sec; - times[1].tv_usec = mtime_ts.tv_nsec * 1000; + times[1].tv_usec = mtime_ts.tv_nsec / 1000; if (attrs->ia_valid & HOSTFS_ATTR_ATIME_SET) { times[0].tv_sec = attrs->ia_atime.tv_sec; - times[0].tv_usec = attrs->ia_atime.tv_nsec * 1000; + times[0].tv_usec = attrs->ia_atime.tv_nsec / 1000; } if (attrs->ia_valid & HOSTFS_ATTR_MTIME_SET) { times[1].tv_sec = attrs->ia_mtime.tv_sec; - times[1].tv_usec = attrs->ia_mtime.tv_nsec * 1000; + times[1].tv_usec = attrs->ia_mtime.tv_nsec / 1000; } if (fd >= 0) { diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 09ee07f0266..3b3cc28cdef 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -768,7 +768,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig) case Opt_mode: if (match_octal(&args[0], &option)) goto bad_val; - pconfig->mode = option & 0777U; + pconfig->mode = option & 01777U; break; case Opt_size: { diff --git a/fs/inotify.c b/fs/inotify.c index 2c5b9215287..690e72595e6 100644 --- a/fs/inotify.c +++ b/fs/inotify.c @@ -168,20 +168,14 @@ static void set_dentry_child_flags(struct inode *inode, int watched) struct dentry *child; list_for_each_entry(child, &alias->d_subdirs, d_u.d_child) { - if (!child->d_inode) { - WARN_ON(child->d_flags & DCACHE_INOTIFY_PARENT_WATCHED); + if (!child->d_inode) continue; - } + spin_lock(&child->d_lock); - if (watched) { - WARN_ON(child->d_flags & - DCACHE_INOTIFY_PARENT_WATCHED); + if (watched) child->d_flags |= DCACHE_INOTIFY_PARENT_WATCHED; - } else { - WARN_ON(!(child->d_flags & - DCACHE_INOTIFY_PARENT_WATCHED)); - child->d_flags&=~DCACHE_INOTIFY_PARENT_WATCHED; - } + else + child->d_flags &=~DCACHE_INOTIFY_PARENT_WATCHED; spin_unlock(&child->d_lock); } } @@ -253,7 +247,6 @@ void inotify_d_instantiate(struct dentry *entry, struct inode *inode) if (!inode) return; - WARN_ON(entry->d_flags & DCACHE_INOTIFY_PARENT_WATCHED); spin_lock(&entry->d_lock); parent = entry->d_parent; if (parent->d_inode && inotify_inode_watched(parent->d_inode)) @@ -627,6 +620,7 @@ s32 inotify_add_watch(struct inotify_handle *ih, struct inotify_watch *watch, struct inode *inode, u32 mask) { int ret = 0; + int newly_watched; /* don't allow invalid bits: we don't want flags set */ mask &= IN_ALL_EVENTS | IN_ONESHOT; @@ -653,12 +647,18 @@ s32 inotify_add_watch(struct inotify_handle *ih, struct inotify_watch *watch, */ watch->inode = igrab(inode); - if (!inotify_inode_watched(inode)) - set_dentry_child_flags(inode, 1); - /* Add the watch to the handle's and the inode's list */ + newly_watched = !inotify_inode_watched(inode); list_add(&watch->h_list, &ih->watches); list_add(&watch->i_list, &inode->inotify_watches); + /* + * Set child flags _after_ adding the watch, so there is no race + * windows where newly instantiated children could miss their parent's + * watched flag. + */ + if (newly_watched) + set_dentry_child_flags(inode, 1); + out: mutex_unlock(&ih->mutex); mutex_unlock(&inode->inotify_mutex); diff --git a/fs/inotify_user.c b/fs/inotify_user.c index 5e009331c01..a336c9709f3 100644 --- a/fs/inotify_user.c +++ b/fs/inotify_user.c @@ -79,6 +79,7 @@ struct inotify_device { atomic_t count; /* reference count */ struct user_struct *user; /* user who opened this dev */ struct inotify_handle *ih; /* inotify handle */ + struct fasync_struct *fa; /* async notification */ unsigned int queue_size; /* size of the queue (bytes) */ unsigned int event_count; /* number of pending events */ unsigned int max_events; /* maximum number of events */ @@ -248,6 +249,19 @@ inotify_dev_get_event(struct inotify_device *dev) } /* + * inotify_dev_get_last_event - return the last event in the given dev's queue + * + * Caller must hold dev->ev_mutex. + */ +static inline struct inotify_kernel_event * +inotify_dev_get_last_event(struct inotify_device *dev) +{ + if (list_empty(&dev->events)) + return NULL; + return list_entry(dev->events.prev, struct inotify_kernel_event, list); +} + +/* * inotify_dev_queue_event - event handler registered with core inotify, adds * a new event to the given device * @@ -273,7 +287,7 @@ static void inotify_dev_queue_event(struct inotify_watch *w, u32 wd, u32 mask, put_inotify_watch(w); /* final put */ /* coalescing: drop this event if it is a dupe of the previous */ - last = inotify_dev_get_event(dev); + last = inotify_dev_get_last_event(dev); if (last && last->event.mask == mask && last->event.wd == wd && last->event.cookie == cookie) { const char *lastname = last->name; @@ -302,6 +316,7 @@ static void inotify_dev_queue_event(struct inotify_watch *w, u32 wd, u32 mask, dev->queue_size += sizeof(struct inotify_event) + kevent->event.len; list_add_tail(&kevent->list, &dev->events); wake_up_interruptible(&dev->wq); + kill_fasync(&dev->fa, SIGIO, POLL_IN); out: mutex_unlock(&dev->ev_mutex); @@ -490,6 +505,13 @@ static ssize_t inotify_read(struct file *file, char __user *buf, return ret; } +static int inotify_fasync(int fd, struct file *file, int on) +{ + struct inotify_device *dev = file->private_data; + + return fasync_helper(fd, file, on, &dev->fa) >= 0 ? 0 : -EIO; +} + static int inotify_release(struct inode *ignored, struct file *file) { struct inotify_device *dev = file->private_data; @@ -502,6 +524,9 @@ static int inotify_release(struct inode *ignored, struct file *file) inotify_dev_event_dequeue(dev); mutex_unlock(&dev->ev_mutex); + if (file->f_flags & FASYNC) + inotify_fasync(-1, file, 0); + /* free this device: the put matching the get in inotify_init() */ put_inotify_dev(dev); @@ -530,6 +555,7 @@ static long inotify_ioctl(struct file *file, unsigned int cmd, static const struct file_operations inotify_fops = { .poll = inotify_poll, .read = inotify_read, + .fasync = inotify_fasync, .release = inotify_release, .unlocked_ioctl = inotify_ioctl, .compat_ioctl = inotify_ioctl, @@ -577,6 +603,7 @@ asmlinkage long sys_inotify_init(void) goto out_free_dev; } dev->ih = ih; + dev->fa = NULL; filp->f_op = &inotify_fops; filp->f_path.mnt = mntget(inotify_mnt); diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 5d14243499d..3943a8905eb 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -1457,7 +1457,7 @@ static const char *journal_dev_name(journal_t *journal, char *buffer) * Aborts hard --- we mark the abort as occurred, but do _nothing_ else, * and don't attempt to make any other journal updates. */ -void __journal_abort_hard(journal_t *journal) +static void __journal_abort_hard(journal_t *journal) { transaction_t *transaction; char b[BDEVNAME_SIZE]; diff --git a/fs/jbd/recovery.c b/fs/jbd/recovery.c index c5d9694b6a2..2b8edf4d6ea 100644 --- a/fs/jbd/recovery.c +++ b/fs/jbd/recovery.c @@ -354,7 +354,7 @@ static int do_one_pass(journal_t *journal, struct buffer_head * obh; struct buffer_head * nbh; - cond_resched(); /* We're under lock_kernel() */ + cond_resched(); /* If we already know where to stop the log traversal, * check right now that we haven't gone past the end of diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 921680663fa..d36356f7d22 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -397,7 +397,7 @@ static int do_one_pass(journal_t *journal, struct buffer_head * obh; struct buffer_head * nbh; - cond_resched(); /* We're under lock_kernel() */ + cond_resched(); /* If we already know where to stop the log traversal, * check right now that we haven't gone past the end of diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c index 2eae5d2dbeb..6c1ba3566f5 100644 --- a/fs/jffs2/readinode.c +++ b/fs/jffs2/readinode.c @@ -741,7 +741,7 @@ static inline int read_dnode(struct jffs2_sb_info *c, struct jffs2_raw_node_ref * are not obsolete. * * Of course, this optimization only makes sense in case - * of NAND flashes (or other flashes whith + * of NAND flashes (or other flashes with * !jffs2_can_mark_obsolete()), since on NOR flashes * nodes are marked obsolete physically. * diff --git a/fs/jfs/jfs_xtree.c b/fs/jfs/jfs_xtree.c index 1543906a2e0..a000aaa7513 100644 --- a/fs/jfs/jfs_xtree.c +++ b/fs/jfs/jfs_xtree.c @@ -3965,7 +3965,7 @@ s64 xtTruncate(tid_t tid, struct inode *ip, s64 newsize, int flag) * xtTruncate_pmap() * * function: - * Perform truncate to zero lenghth for deleted file, leaving the + * Perform truncate to zero length for deleted file, leaving the * the xtree and working map untouched. This allows the file to * be accessed via open file handles, while the delete of the file * is committed to disk. diff --git a/fs/libfs.c b/fs/libfs.c index 6e68b700958..5523bde9638 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -341,13 +341,10 @@ int simple_prepare_write(struct file *file, struct page *page, unsigned from, unsigned to) { if (!PageUptodate(page)) { - if (to - from != PAGE_CACHE_SIZE) { - void *kaddr = kmap_atomic(page, KM_USER0); - memset(kaddr, 0, from); - memset(kaddr + to, 0, PAGE_CACHE_SIZE - to); - flush_dcache_page(page); - kunmap_atomic(kaddr, KM_USER0); - } + if (to - from != PAGE_CACHE_SIZE) + zero_user_segments(page, + 0, from, + to, PAGE_CACHE_SIZE); } return 0; } diff --git a/fs/lockd/host.c b/fs/lockd/host.c index 572601e98dc..ca6b16fc310 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -34,10 +34,10 @@ static DEFINE_MUTEX(nlm_host_mutex); static void nlm_gc_hosts(void); static struct nsm_handle * __nsm_find(const struct sockaddr_in *, - const char *, int, int); + const char *, unsigned int, int); static struct nsm_handle * nsm_find(const struct sockaddr_in *sin, const char *hostname, - int hostname_len); + unsigned int hostname_len); /* * Common host lookup routine for server & client @@ -45,7 +45,8 @@ static struct nsm_handle * nsm_find(const struct sockaddr_in *sin, static struct nlm_host * nlm_lookup_host(int server, const struct sockaddr_in *sin, int proto, int version, const char *hostname, - int hostname_len, const struct sockaddr_in *ssin) + unsigned int hostname_len, + const struct sockaddr_in *ssin) { struct hlist_head *chain; struct hlist_node *pos; @@ -176,7 +177,7 @@ nlm_destroy_host(struct nlm_host *host) */ struct nlm_host * nlmclnt_lookup_host(const struct sockaddr_in *sin, int proto, int version, - const char *hostname, int hostname_len) + const char *hostname, unsigned int hostname_len) { struct sockaddr_in ssin = {0}; @@ -189,7 +190,7 @@ nlmclnt_lookup_host(const struct sockaddr_in *sin, int proto, int version, */ struct nlm_host * nlmsvc_lookup_host(struct svc_rqst *rqstp, - const char *hostname, int hostname_len) + const char *hostname, unsigned int hostname_len) { struct sockaddr_in ssin = {0}; @@ -307,7 +308,8 @@ void nlm_release_host(struct nlm_host *host) * Release all resources held by that peer. */ void nlm_host_rebooted(const struct sockaddr_in *sin, - const char *hostname, int hostname_len, + const char *hostname, + unsigned int hostname_len, u32 new_state) { struct hlist_head *chain; @@ -377,8 +379,13 @@ nlm_shutdown_hosts(void) /* First, make all hosts eligible for gc */ dprintk("lockd: nuking all hosts...\n"); for (chain = nlm_hosts; chain < nlm_hosts + NLM_HOST_NRHASH; ++chain) { - hlist_for_each_entry(host, pos, chain, h_hash) + hlist_for_each_entry(host, pos, chain, h_hash) { host->h_expires = jiffies - 1; + if (host->h_rpcclnt) { + rpc_shutdown_client(host->h_rpcclnt); + host->h_rpcclnt = NULL; + } + } } /* Then, perform a garbage collection pass */ @@ -449,7 +456,7 @@ static DEFINE_MUTEX(nsm_mutex); static struct nsm_handle * __nsm_find(const struct sockaddr_in *sin, - const char *hostname, int hostname_len, + const char *hostname, unsigned int hostname_len, int create) { struct nsm_handle *nsm = NULL; @@ -503,7 +510,8 @@ out: } static struct nsm_handle * -nsm_find(const struct sockaddr_in *sin, const char *hostname, int hostname_len) +nsm_find(const struct sockaddr_in *sin, const char *hostname, + unsigned int hostname_len) { return __nsm_find(sin, hostname, hostname_len, 1); } diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 82e2192a0d5..08226464e56 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -219,19 +219,6 @@ lockd(struct svc_rqst *rqstp) module_put_and_exit(0); } - -static int find_socket(struct svc_serv *serv, int proto) -{ - struct svc_sock *svsk; - int found = 0; - list_for_each_entry(svsk, &serv->sv_permsocks, sk_list) - if (svsk->sk_sk->sk_protocol == proto) { - found = 1; - break; - } - return found; -} - /* * Make any sockets that are needed but not present. * If nlm_udpport or nlm_tcpport were set as module @@ -240,17 +227,25 @@ static int find_socket(struct svc_serv *serv, int proto) static int make_socks(struct svc_serv *serv, int proto) { static int warned; + struct svc_xprt *xprt; int err = 0; - if (proto == IPPROTO_UDP || nlm_udpport) - if (!find_socket(serv, IPPROTO_UDP)) - err = svc_makesock(serv, IPPROTO_UDP, nlm_udpport, - SVC_SOCK_DEFAULTS); - if (err >= 0 && (proto == IPPROTO_TCP || nlm_tcpport)) - if (!find_socket(serv, IPPROTO_TCP)) - err = svc_makesock(serv, IPPROTO_TCP, nlm_tcpport, - SVC_SOCK_DEFAULTS); - + if (proto == IPPROTO_UDP || nlm_udpport) { + xprt = svc_find_xprt(serv, "udp", 0, 0); + if (!xprt) + err = svc_create_xprt(serv, "udp", nlm_udpport, + SVC_SOCK_DEFAULTS); + else + svc_xprt_put(xprt); + } + if (err >= 0 && (proto == IPPROTO_TCP || nlm_tcpport)) { + xprt = svc_find_xprt(serv, "tcp", 0, 0); + if (!xprt) + err = svc_create_xprt(serv, "tcp", nlm_tcpport, + SVC_SOCK_DEFAULTS); + else + svc_xprt_put(xprt); + } if (err >= 0) { warned = 0; err = 0; diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index bf27b6c6cb6..385437e3387 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -84,6 +84,7 @@ nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, { struct nlm_host *host; struct nlm_file *file; + int rc = rpc_success; dprintk("lockd: TEST4 called\n"); resp->cookie = argp->cookie; @@ -91,7 +92,7 @@ nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, /* Don't accept test requests during grace period */ if (nlmsvc_grace_period) { resp->status = nlm_lck_denied_grace_period; - return rpc_success; + return rc; } /* Obtain client and file */ @@ -101,12 +102,13 @@ nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, /* Now check for conflicting locks */ resp->status = nlmsvc_testlock(rqstp, file, &argp->lock, &resp->lock, &resp->cookie); if (resp->status == nlm_drop_reply) - return rpc_drop_reply; + rc = rpc_drop_reply; + else + dprintk("lockd: TEST4 status %d\n", ntohl(resp->status)); - dprintk("lockd: TEST4 status %d\n", ntohl(resp->status)); nlm_release_host(host); nlm_release_file(file); - return rpc_success; + return rc; } static __be32 @@ -115,6 +117,7 @@ nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, { struct nlm_host *host; struct nlm_file *file; + int rc = rpc_success; dprintk("lockd: LOCK called\n"); @@ -123,7 +126,7 @@ nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, /* Don't accept new lock requests during grace period */ if (nlmsvc_grace_period && !argp->reclaim) { resp->status = nlm_lck_denied_grace_period; - return rpc_success; + return rc; } /* Obtain client and file */ @@ -146,12 +149,13 @@ nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, resp->status = nlmsvc_lock(rqstp, file, &argp->lock, argp->block, &argp->cookie); if (resp->status == nlm_drop_reply) - return rpc_drop_reply; + rc = rpc_drop_reply; + else + dprintk("lockd: LOCK status %d\n", ntohl(resp->status)); - dprintk("lockd: LOCK status %d\n", ntohl(resp->status)); nlm_release_host(host); nlm_release_file(file); - return rpc_success; + return rc; } static __be32 diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index d120ec39bcb..2f4d8fa6668 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -501,25 +501,29 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, block, block->b_flags, block->b_fl); if (block->b_flags & B_TIMED_OUT) { nlmsvc_unlink_block(block); - return nlm_lck_denied; + ret = nlm_lck_denied; + goto out; } if (block->b_flags & B_GOT_CALLBACK) { + nlmsvc_unlink_block(block); if (block->b_fl != NULL && block->b_fl->fl_type != F_UNLCK) { lock->fl = *block->b_fl; goto conf_lock; - } - else { - nlmsvc_unlink_block(block); - return nlm_granted; + } else { + ret = nlm_granted; + goto out; } } - return nlm_drop_reply; + ret = nlm_drop_reply; + goto out; } error = vfs_test_lock(file->f_file, &lock->fl); - if (error == -EINPROGRESS) - return nlmsvc_defer_lock_rqst(rqstp, block); + if (error == -EINPROGRESS) { + ret = nlmsvc_defer_lock_rqst(rqstp, block); + goto out; + } if (error) { ret = nlm_lck_denied_nolocks; goto out; diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 9cd5c8b3759..88379cc6e0b 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -113,6 +113,7 @@ nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, { struct nlm_host *host; struct nlm_file *file; + int rc = rpc_success; dprintk("lockd: TEST called\n"); resp->cookie = argp->cookie; @@ -120,7 +121,7 @@ nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, /* Don't accept test requests during grace period */ if (nlmsvc_grace_period) { resp->status = nlm_lck_denied_grace_period; - return rpc_success; + return rc; } /* Obtain client and file */ @@ -130,13 +131,14 @@ nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, /* Now check for conflicting locks */ resp->status = cast_status(nlmsvc_testlock(rqstp, file, &argp->lock, &resp->lock, &resp->cookie)); if (resp->status == nlm_drop_reply) - return rpc_drop_reply; + rc = rpc_drop_reply; + else + dprintk("lockd: TEST status %d vers %d\n", + ntohl(resp->status), rqstp->rq_vers); - dprintk("lockd: TEST status %d vers %d\n", - ntohl(resp->status), rqstp->rq_vers); nlm_release_host(host); nlm_release_file(file); - return rpc_success; + return rc; } static __be32 @@ -145,6 +147,7 @@ nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, { struct nlm_host *host; struct nlm_file *file; + int rc = rpc_success; dprintk("lockd: LOCK called\n"); @@ -153,7 +156,7 @@ nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, /* Don't accept new lock requests during grace period */ if (nlmsvc_grace_period && !argp->reclaim) { resp->status = nlm_lck_denied_grace_period; - return rpc_success; + return rc; } /* Obtain client and file */ @@ -176,12 +179,13 @@ nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, resp->status = cast_status(nlmsvc_lock(rqstp, file, &argp->lock, argp->block, &argp->cookie)); if (resp->status == nlm_drop_reply) - return rpc_drop_reply; + rc = rpc_drop_reply; + else + dprintk("lockd: LOCK status %d\n", ntohl(resp->status)); - dprintk("lockd: LOCK status %d\n", ntohl(resp->status)); nlm_release_host(host); nlm_release_file(file); - return rpc_success; + return rc; } static __be32 diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index 84ebba33b98..dbbefbcd671 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -87,7 +87,7 @@ nlm_lookup_file(struct svc_rqst *rqstp, struct nlm_file **result, unsigned int hash; __be32 nfserr; - nlm_debug_print_fh("nlm_file_lookup", f); + nlm_debug_print_fh("nlm_lookup_file", f); hash = file_hash(f); diff --git a/fs/locks.c b/fs/locks.c index 8b8388eca05..49354b9c7dc 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -125,6 +125,7 @@ #include <linux/syscalls.h> #include <linux/time.h> #include <linux/rcupdate.h> +#include <linux/pid_namespace.h> #include <asm/semaphore.h> #include <asm/uaccess.h> @@ -185,6 +186,7 @@ void locks_init_lock(struct file_lock *fl) fl->fl_fasync = NULL; fl->fl_owner = NULL; fl->fl_pid = 0; + fl->fl_nspid = NULL; fl->fl_file = NULL; fl->fl_flags = 0; fl->fl_type = 0; @@ -553,6 +555,8 @@ static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl) { list_add(&fl->fl_link, &file_lock_list); + fl->fl_nspid = get_pid(task_tgid(current)); + /* insert into file's list */ fl->fl_next = *pos; *pos = fl; @@ -584,6 +588,11 @@ static void locks_delete_lock(struct file_lock **thisfl_p) if (fl->fl_ops && fl->fl_ops->fl_remove) fl->fl_ops->fl_remove(fl); + if (fl->fl_nspid) { + put_pid(fl->fl_nspid); + fl->fl_nspid = NULL; + } + locks_wake_up_blocks(fl); locks_free_lock(fl); } @@ -634,33 +643,6 @@ static int flock_locks_conflict(struct file_lock *caller_fl, struct file_lock *s return (locks_conflict(caller_fl, sys_fl)); } -static int interruptible_sleep_on_locked(wait_queue_head_t *fl_wait, int timeout) -{ - int result = 0; - DECLARE_WAITQUEUE(wait, current); - - __set_current_state(TASK_INTERRUPTIBLE); - add_wait_queue(fl_wait, &wait); - if (timeout == 0) - schedule(); - else - result = schedule_timeout(timeout); - if (signal_pending(current)) - result = -ERESTARTSYS; - remove_wait_queue(fl_wait, &wait); - __set_current_state(TASK_RUNNING); - return result; -} - -static int locks_block_on_timeout(struct file_lock *blocker, struct file_lock *waiter, int time) -{ - int result; - locks_insert_block(blocker, waiter); - result = interruptible_sleep_on_locked(&waiter->fl_wait, time); - __locks_delete_block(waiter); - return result; -} - void posix_test_lock(struct file *filp, struct file_lock *fl) { @@ -673,55 +655,67 @@ posix_test_lock(struct file *filp, struct file_lock *fl) if (posix_locks_conflict(fl, cfl)) break; } - if (cfl) + if (cfl) { __locks_copy_lock(fl, cfl); - else + if (cfl->fl_nspid) + fl->fl_pid = pid_nr_ns(cfl->fl_nspid, + task_active_pid_ns(current)); + } else fl->fl_type = F_UNLCK; unlock_kernel(); return; } - EXPORT_SYMBOL(posix_test_lock); -/* This function tests for deadlock condition before putting a process to - * sleep. The detection scheme is no longer recursive. Recursive was neat, - * but dangerous - we risked stack corruption if the lock data was bad, or - * if the recursion was too deep for any other reason. +/* + * Deadlock detection: + * + * We attempt to detect deadlocks that are due purely to posix file + * locks. * - * We rely on the fact that a task can only be on one lock's wait queue - * at a time. When we find blocked_task on a wait queue we can re-search - * with blocked_task equal to that queue's owner, until either blocked_task - * isn't found, or blocked_task is found on a queue owned by my_task. + * We assume that a task can be waiting for at most one lock at a time. + * So for any acquired lock, the process holding that lock may be + * waiting on at most one other lock. That lock in turns may be held by + * someone waiting for at most one other lock. Given a requested lock + * caller_fl which is about to wait for a conflicting lock block_fl, we + * follow this chain of waiters to ensure we are not about to create a + * cycle. * - * Note: the above assumption may not be true when handling lock requests - * from a broken NFS client. But broken NFS clients have a lot more to - * worry about than proper deadlock detection anyway... --okir + * Since we do this before we ever put a process to sleep on a lock, we + * are ensured that there is never a cycle; that is what guarantees that + * the while() loop in posix_locks_deadlock() eventually completes. * - * However, the failure of this assumption (also possible in the case of - * multiple tasks sharing the same open file table) also means there's no - * guarantee that the loop below will terminate. As a hack, we give up - * after a few iterations. + * Note: the above assumption may not be true when handling lock + * requests from a broken NFS client. It may also fail in the presence + * of tasks (such as posix threads) sharing the same open file table. + * + * To handle those cases, we just bail out after a few iterations. */ #define MAX_DEADLK_ITERATIONS 10 +/* Find a lock that the owner of the given block_fl is blocking on. */ +static struct file_lock *what_owner_is_waiting_for(struct file_lock *block_fl) +{ + struct file_lock *fl; + + list_for_each_entry(fl, &blocked_list, fl_link) { + if (posix_same_owner(fl, block_fl)) + return fl->fl_next; + } + return NULL; +} + static int posix_locks_deadlock(struct file_lock *caller_fl, struct file_lock *block_fl) { - struct file_lock *fl; int i = 0; -next_task: - if (posix_same_owner(caller_fl, block_fl)) - return 1; - list_for_each_entry(fl, &blocked_list, fl_link) { - if (posix_same_owner(fl, block_fl)) { - if (i++ > MAX_DEADLK_ITERATIONS) - return 0; - fl = fl->fl_next; - block_fl = fl; - goto next_task; - } + while ((block_fl = what_owner_is_waiting_for(block_fl))) { + if (i++ > MAX_DEADLK_ITERATIONS) + return 0; + if (posix_same_owner(caller_fl, block_fl)) + return 1; } return 0; } @@ -1256,7 +1250,10 @@ restart: if (break_time == 0) break_time++; } - error = locks_block_on_timeout(flock, new_fl, break_time); + locks_insert_block(flock, new_fl); + error = wait_event_interruptible_timeout(new_fl->fl_wait, + !new_fl->fl_next, break_time); + __locks_delete_block(new_fl); if (error >= 0) { if (error == 0) time_out_leases(inode); @@ -2084,6 +2081,12 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, int id, char *pfx) { struct inode *inode = NULL; + unsigned int fl_pid; + + if (fl->fl_nspid) + fl_pid = pid_nr_ns(fl->fl_nspid, task_active_pid_ns(current)); + else + fl_pid = fl->fl_pid; if (fl->fl_file != NULL) inode = fl->fl_file->f_path.dentry->d_inode; @@ -2124,16 +2127,16 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, } if (inode) { #ifdef WE_CAN_BREAK_LSLK_NOW - seq_printf(f, "%d %s:%ld ", fl->fl_pid, + seq_printf(f, "%d %s:%ld ", fl_pid, inode->i_sb->s_id, inode->i_ino); #else /* userspace relies on this representation of dev_t ;-( */ - seq_printf(f, "%d %02x:%02x:%ld ", fl->fl_pid, + seq_printf(f, "%d %02x:%02x:%ld ", fl_pid, MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); #endif } else { - seq_printf(f, "%d <none>:0 ", fl->fl_pid); + seq_printf(f, "%d <none>:0 ", fl_pid); } if (IS_POSIX(fl)) { if (fl->fl_end == OFFSET_MAX) diff --git a/fs/mpage.c b/fs/mpage.c index d54f8f89722..5df564366f3 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -276,9 +276,7 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages, } if (first_hole != blocks_per_page) { - zero_user_page(page, first_hole << blkbits, - PAGE_CACHE_SIZE - (first_hole << blkbits), - KM_USER0); + zero_user_segment(page, first_hole << blkbits, PAGE_CACHE_SIZE); if (first_hole == 0) { SetPageUptodate(page); unlock_page(page); @@ -571,8 +569,7 @@ page_is_mapped: if (page->index > end_index || !offset) goto confused; - zero_user_page(page, offset, PAGE_CACHE_SIZE - offset, - KM_USER0); + zero_user_segment(page, offset, PAGE_CACHE_SIZE); } /* diff --git a/fs/namei.c b/fs/namei.c index 73e2e665817..241cff42365 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2188,6 +2188,7 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry) /* We don't d_delete() NFS sillyrenamed files--they still exist. */ if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) { + fsnotify_link_count(dentry->d_inode); d_delete(dentry); } @@ -2360,7 +2361,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de error = dir->i_op->link(old_dentry, dir, new_dentry); mutex_unlock(&old_dentry->d_inode->i_mutex); if (!error) - fsnotify_create(dir, new_dentry); + fsnotify_link(dir, old_dentry->d_inode, new_dentry); return error; } diff --git a/fs/namespace.c b/fs/namespace.c index 61bf376e29e..e9c10cd01e1 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -25,18 +25,21 @@ #include <linux/security.h> #include <linux/mount.h> #include <linux/ramfs.h> +#include <linux/log2.h> #include <asm/uaccess.h> #include <asm/unistd.h> #include "pnode.h" #include "internal.h" +#define HASH_SHIFT ilog2(PAGE_SIZE / sizeof(struct list_head)) +#define HASH_SIZE (1UL << HASH_SHIFT) + /* spinlock for vfsmount related operations, inplace of dcache_lock */ __cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock); static int event; static struct list_head *mount_hashtable __read_mostly; -static int hash_mask __read_mostly, hash_bits __read_mostly; static struct kmem_cache *mnt_cache __read_mostly; static struct rw_semaphore namespace_sem; @@ -48,8 +51,8 @@ static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry) { unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); tmp += ((unsigned long)dentry / L1_CACHE_BYTES); - tmp = tmp + (tmp >> hash_bits); - return tmp & hash_mask; + tmp = tmp + (tmp >> HASH_SHIFT); + return tmp & (HASH_SIZE - 1); } struct vfsmount *alloc_vfsmnt(const char *name) @@ -1813,9 +1816,7 @@ static void __init init_mount_tree(void) void __init mnt_init(void) { - struct list_head *d; - unsigned int nr_hash; - int i; + unsigned u; int err; init_rwsem(&namespace_sem); @@ -1828,35 +1829,11 @@ void __init mnt_init(void) if (!mount_hashtable) panic("Failed to allocate mount hash table\n"); - /* - * Find the power-of-two list-heads that can fit into the allocation.. - * We don't guarantee that "sizeof(struct list_head)" is necessarily - * a power-of-two. - */ - nr_hash = PAGE_SIZE / sizeof(struct list_head); - hash_bits = 0; - do { - hash_bits++; - } while ((nr_hash >> hash_bits) != 0); - hash_bits--; + printk("Mount-cache hash table entries: %lu\n", HASH_SIZE); + + for (u = 0; u < HASH_SIZE; u++) + INIT_LIST_HEAD(&mount_hashtable[u]); - /* - * Re-calculate the actual number of entries and the mask - * from the number of bits we can fit. - */ - nr_hash = 1UL << hash_bits; - hash_mask = nr_hash - 1; - - printk("Mount-cache hash table entries: %d\n", nr_hash); - - /* And initialize the newly allocated array */ - d = mount_hashtable; - i = nr_hash; - do { - INIT_LIST_HEAD(d); - d++; - i--; - } while (i); err = sysfs_init(); if (err) printk(KERN_WARNING "%s: sysfs_init error: %d\n", diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index e1cb70c643f..eff1f18d034 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -987,7 +987,7 @@ static struct file_system_type ncp_fs_type = { static int __init init_ncp_fs(void) { int err; - DPRINTK("ncpfs: init_module called\n"); + DPRINTK("ncpfs: init_ncp_fs called\n"); err = init_inodecache(); if (err) @@ -1004,7 +1004,7 @@ out1: static void __exit exit_ncp_fs(void) { - DPRINTK("ncpfs: cleanup_module called\n"); + DPRINTK("ncpfs: exit_ncp_fs called\n"); unregister_filesystem(&ncp_fs_type); destroy_inodecache(); } diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c index a94473d3072..5d8dcb9ee32 100644 --- a/fs/ncpfs/mmap.c +++ b/fs/ncpfs/mmap.c @@ -50,10 +50,6 @@ static int ncp_file_mmap_fault(struct vm_area_struct *area, pos = vmf->pgoff << PAGE_SHIFT; count = PAGE_SIZE; - if ((unsigned long)vmf->virtual_address + PAGE_SIZE > area->vm_end) { - WARN_ON(1); /* shouldn't happen? */ - count = area->vm_end - (unsigned long)vmf->virtual_address; - } /* what we can read in one go */ bufsize = NCP_SERVER(inode)->buffer_size; diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 9b6bbf1b978..bd185a572a2 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -119,8 +119,8 @@ int nfs_callback_up(void) if (!serv) goto out_err; - ret = svc_makesock(serv, IPPROTO_TCP, nfs_callback_set_tcpport, - SVC_SOCK_ANONYMOUS); + ret = svc_create_xprt(serv, "tcp", nfs_callback_set_tcpport, + SVC_SOCK_ANONYMOUS); if (ret <= 0) goto out_destroy; nfs_callback_tcpport = ret; diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 8fd6dfbe1bc..3d7d9631e12 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -79,7 +79,7 @@ void nfs_readdata_release(void *data) static int nfs_return_empty_page(struct page *page) { - zero_user_page(page, 0, PAGE_CACHE_SIZE, KM_USER0); + zero_user(page, 0, PAGE_CACHE_SIZE); SetPageUptodate(page); unlock_page(page); return 0; @@ -103,10 +103,10 @@ static void nfs_readpage_truncate_uninitialised_page(struct nfs_read_data *data) pglen = PAGE_CACHE_SIZE - base; for (;;) { if (remainder <= pglen) { - zero_user_page(*pages, base, remainder, KM_USER0); + zero_user(*pages, base, remainder); break; } - zero_user_page(*pages, base, pglen, KM_USER0); + zero_user(*pages, base, pglen); pages++; remainder -= pglen; pglen = PAGE_CACHE_SIZE; @@ -130,7 +130,7 @@ static int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, return PTR_ERR(new); } if (len < PAGE_CACHE_SIZE) - zero_user_page(page, len, PAGE_CACHE_SIZE - len, KM_USER0); + zero_user_segment(page, len, PAGE_CACHE_SIZE); nfs_list_add_request(new, &one_request); if (NFS_SERVER(inode)->rsize < PAGE_CACHE_SIZE) @@ -532,7 +532,7 @@ readpage_async_filler(void *data, struct page *page) goto out_error; if (len < PAGE_CACHE_SIZE) - zero_user_page(page, len, PAGE_CACHE_SIZE - len, KM_USER0); + zero_user_segment(page, len, PAGE_CACHE_SIZE); nfs_pageio_add_request(desc->pgio, new); return 0; out_error: diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 522efff3e2c..b144b1957dd 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -665,9 +665,7 @@ zero_page: * then we need to zero any uninitalised data. */ if (req->wb_pgbase == 0 && req->wb_bytes != PAGE_CACHE_SIZE && !PageUptodate(req->wb_page)) - zero_user_page(req->wb_page, req->wb_bytes, - PAGE_CACHE_SIZE - req->wb_bytes, - KM_USER0); + zero_user_segment(req->wb_page, req->wb_bytes, PAGE_CACHE_SIZE); return req; } diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index 21928056e35..d13403e3362 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -11,8 +11,6 @@ #include <linux/nfsd/nfsd.h> #include <linux/nfsd/export.h> -#define CAP_NFSD_MASK (CAP_FS_MASK|CAP_TO_MASK(CAP_SYS_RESOURCE)) - int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp) { struct exp_flavor_info *f; @@ -69,10 +67,12 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) ret = set_current_groups(cred.cr_group_info); put_group_info(cred.cr_group_info); if ((cred.cr_uid)) { - cap_t(current->cap_effective) &= ~CAP_NFSD_MASK; + current->cap_effective = + cap_drop_nfsd_set(current->cap_effective); } else { - cap_t(current->cap_effective) |= (CAP_NFSD_MASK & - current->cap_permitted); + current->cap_effective = + cap_raise_nfsd_set(current->cap_effective, + current->cap_permitted); } return ret; } diff --git a/fs/nfsd/auth.h b/fs/nfsd/auth.h new file mode 100644 index 00000000000..78b3c0e9382 --- /dev/null +++ b/fs/nfsd/auth.h @@ -0,0 +1,22 @@ +/* + * nfsd-specific authentication stuff. + * uid/gid mapping not yet implemented. + * + * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> + */ + +#ifndef LINUX_NFSD_AUTH_H +#define LINUX_NFSD_AUTH_H + +#define nfsd_luid(rq, uid) ((u32)(uid)) +#define nfsd_lgid(rq, gid) ((u32)(gid)) +#define nfsd_ruid(rq, uid) ((u32)(uid)) +#define nfsd_rgid(rq, gid) ((u32)(gid)) + +/* + * Set the current process's fsuid/fsgid etc to those of the NFS + * client user + */ +int nfsd_setuser(struct svc_rqst *, struct svc_export *); + +#endif /* LINUX_NFSD_AUTH_H */ diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 66d0aeb32a4..79b4bf81296 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -1357,8 +1357,6 @@ exp_pseudoroot(struct svc_rqst *rqstp, struct svc_fh *fhp) mk_fsid(FSID_NUM, fsidv, 0, 0, 0, NULL); exp = rqst_exp_find(rqstp, FSID_NUM, fsidv); - if (PTR_ERR(exp) == -ENOENT) - return nfserr_perm; if (IS_ERR(exp)) return nfserrno(PTR_ERR(exp)); rv = fh_compose(fhp, exp, exp->ex_dentry, NULL); @@ -1637,13 +1635,19 @@ exp_verify_string(char *cp, int max) /* * Initialize the exports module. */ -void +int nfsd_export_init(void) { + int rv; dprintk("nfsd: initializing export module.\n"); - cache_register(&svc_export_cache); - cache_register(&svc_expkey_cache); + rv = cache_register(&svc_export_cache); + if (rv) + return rv; + rv = cache_register(&svc_expkey_cache); + if (rv) + cache_unregister(&svc_export_cache); + return rv; } @@ -1670,10 +1674,8 @@ nfsd_export_shutdown(void) exp_writelock(); - if (cache_unregister(&svc_expkey_cache)) - printk(KERN_ERR "nfsd: failed to unregister expkey cache\n"); - if (cache_unregister(&svc_export_cache)) - printk(KERN_ERR "nfsd: failed to unregister export cache\n"); + cache_unregister(&svc_expkey_cache); + cache_unregister(&svc_export_cache); svcauth_unix_purge(); exp_writeunlock(); diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 0e5fa11e6b4..1c3b7654e96 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -221,12 +221,17 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_getaclres *resp) { struct dentry *dentry = resp->fh.fh_dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode; struct kvec *head = rqstp->rq_res.head; unsigned int base; int n; int w; + /* + * Since this is version 2, the check for nfserr in + * nfsd_dispatch actually ensures the following cannot happen. + * However, it seems fragile to depend on that. + */ if (dentry == NULL || dentry->d_inode == NULL) return 0; inode = dentry->d_inode; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index f917fd25858..d7647f70e02 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -21,6 +21,7 @@ #include <linux/sunrpc/svc.h> #include <linux/nfsd/nfsd.h> #include <linux/nfsd/xdr3.h> +#include "auth.h" #define NFSDDBG_FACILITY NFSDDBG_XDR @@ -88,10 +89,10 @@ encode_fh(__be32 *p, struct svc_fh *fhp) * no slashes or null bytes. */ static __be32 * -decode_filename(__be32 *p, char **namp, int *lenp) +decode_filename(__be32 *p, char **namp, unsigned int *lenp) { char *name; - int i; + unsigned int i; if ((p = xdr_decode_string_inplace(p, namp, lenp, NFS3_MAXNAMLEN)) != NULL) { for (i = 0, name = *namp; i < *lenp; i++, name++) { @@ -452,8 +453,7 @@ int nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_symlinkargs *args) { - unsigned int len; - int avail; + unsigned int len, avail; char *old, *new; struct kvec *vec; @@ -486,7 +486,8 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, /* now copy next page if there is one */ if (len && !avail && rqstp->rq_arg.page_len) { avail = rqstp->rq_arg.page_len; - if (avail > PAGE_SIZE) avail = PAGE_SIZE; + if (avail > PAGE_SIZE) + avail = PAGE_SIZE; old = page_address(rqstp->rq_arg.pages[0]); } while (len && avail && *old) { @@ -816,11 +817,11 @@ static __be32 * encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p, struct svc_fh *fhp) { - p = encode_post_op_attr(cd->rqstp, p, fhp); - *p++ = xdr_one; /* yes, a file handle follows */ - p = encode_fh(p, fhp); - fh_put(fhp); - return p; + p = encode_post_op_attr(cd->rqstp, p, fhp); + *p++ = xdr_one; /* yes, a file handle follows */ + p = encode_fh(p, fhp); + fh_put(fhp); + return p; } static int diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 9d536a8cb37..aae2b29ae2c 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -350,30 +350,6 @@ static struct rpc_version * nfs_cb_version[] = { static int do_probe_callback(void *data) { struct nfs4_client *clp = data; - struct nfs4_callback *cb = &clp->cl_callback; - struct rpc_message msg = { - .rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL], - .rpc_argp = clp, - }; - int status; - - status = rpc_call_sync(cb->cb_client, &msg, RPC_TASK_SOFT); - - if (status) { - rpc_shutdown_client(cb->cb_client); - cb->cb_client = NULL; - } else - atomic_set(&cb->cb_set, 1); - put_nfs4_client(clp); - return 0; -} - -/* - * Set up the callback client and put a NFSPROC4_CB_NULL on the wire... - */ -void -nfsd4_probe_callback(struct nfs4_client *clp) -{ struct sockaddr_in addr; struct nfs4_callback *cb = &clp->cl_callback; struct rpc_timeout timeparms = { @@ -390,13 +366,15 @@ nfsd4_probe_callback(struct nfs4_client *clp) .timeout = &timeparms, .program = program, .version = nfs_cb_version[1]->number, - .authflavor = RPC_AUTH_UNIX, /* XXX: need AUTH_GSS... */ + .authflavor = RPC_AUTH_UNIX, /* XXX: need AUTH_GSS... */ .flags = (RPC_CLNT_CREATE_NOPING), }; - struct task_struct *t; - - if (atomic_read(&cb->cb_set)) - return; + struct rpc_message msg = { + .rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL], + .rpc_argp = clp, + }; + struct rpc_clnt *client; + int status; /* Initialize address */ memset(&addr, 0, sizeof(addr)); @@ -416,29 +394,50 @@ nfsd4_probe_callback(struct nfs4_client *clp) program->stats->program = program; /* Create RPC client */ - cb->cb_client = rpc_create(&args); - if (IS_ERR(cb->cb_client)) { + client = rpc_create(&args); + if (IS_ERR(client)) { dprintk("NFSD: couldn't create callback client\n"); + status = PTR_ERR(client); goto out_err; } + status = rpc_call_sync(client, &msg, RPC_TASK_SOFT); + + if (status) + goto out_release_client; + + cb->cb_client = client; + atomic_set(&cb->cb_set, 1); + put_nfs4_client(clp); + return 0; +out_release_client: + rpc_shutdown_client(client); +out_err: + put_nfs4_client(clp); + dprintk("NFSD: warning: no callback path to client %.*s\n", + (int)clp->cl_name.len, clp->cl_name.data); + return status; +} + +/* + * Set up the callback client and put a NFSPROC4_CB_NULL on the wire... + */ +void +nfsd4_probe_callback(struct nfs4_client *clp) +{ + struct task_struct *t; + + BUG_ON(atomic_read(&clp->cl_callback.cb_set)); + /* the task holds a reference to the nfs4_client struct */ atomic_inc(&clp->cl_count); t = kthread_run(do_probe_callback, clp, "nfs4_cb_probe"); if (IS_ERR(t)) - goto out_release_clp; + atomic_dec(&clp->cl_count); return; - -out_release_clp: - atomic_dec(&clp->cl_count); - rpc_shutdown_client(cb->cb_client); -out_err: - cb->cb_client = NULL; - dprintk("NFSD: warning: no callback path to client %.*s\n", - (int)clp->cl_name.len, clp->cl_name.data); } /* @@ -458,9 +457,6 @@ nfsd4_cb_recall(struct nfs4_delegation *dp) int retries = 1; int status = 0; - if ((!atomic_read(&clp->cl_callback.cb_set)) || !clnt) - return; - cbr->cbr_trunc = 0; /* XXX need to implement truncate optimization */ cbr->cbr_dp = dp; @@ -469,6 +465,7 @@ nfsd4_cb_recall(struct nfs4_delegation *dp) switch (status) { case -EIO: /* Network partition? */ + atomic_set(&clp->cl_callback.cb_set, 0); case -EBADHANDLE: case -NFS4ERR_BAD_STATEID: /* Race: client probably got cb_recall @@ -481,11 +478,10 @@ nfsd4_cb_recall(struct nfs4_delegation *dp) status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFT); } out_put_cred: - if (status == -EIO) - atomic_set(&clp->cl_callback.cb_set, 0); - /* Success or failure, now we're either waiting for lease expiration - * or deleg_return. */ - dprintk("NFSD: nfs4_cb_recall: dp %p dl_flock %p dl_count %d\n",dp, dp->dl_flock, atomic_read(&dp->dl_count)); + /* + * Success or failure, now we're either waiting for lease expiration + * or deleg_return. + */ put_nfs4_client(clp); nfs4_put_delegation(dp); return; diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index 4c0c683ce07..996bd88b75b 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -255,13 +255,10 @@ idtoname_parse(struct cache_detail *cd, char *buf, int buflen) goto out; if (len == 0) set_bit(CACHE_NEGATIVE, &ent.h.flags); - else { - if (error >= IDMAP_NAMESZ) { - error = -EINVAL; - goto out; - } + else if (len >= IDMAP_NAMESZ) + goto out; + else memcpy(ent.name, buf1, sizeof(ent.name)); - } error = -ENOMEM; res = idtoname_update(&ent, res); if (res == NULL) @@ -467,20 +464,25 @@ nametoid_update(struct ent *new, struct ent *old) * Exported API */ -void +int nfsd_idmap_init(void) { - cache_register(&idtoname_cache); - cache_register(&nametoid_cache); + int rv; + + rv = cache_register(&idtoname_cache); + if (rv) + return rv; + rv = cache_register(&nametoid_cache); + if (rv) + cache_unregister(&idtoname_cache); + return rv; } void nfsd_idmap_shutdown(void) { - if (cache_unregister(&idtoname_cache)) - printk(KERN_ERR "nfsd: failed to unregister idtoname cache\n"); - if (cache_unregister(&nametoid_cache)) - printk(KERN_ERR "nfsd: failed to unregister nametoid cache\n"); + cache_unregister(&idtoname_cache); + cache_unregister(&nametoid_cache); } /* diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 18ead1790bb..c593db047d8 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -750,7 +750,7 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, cstate->current_fh.fh_export, cstate->current_fh.fh_dentry, buf, &count, verify->ve_bmval, - rqstp); + rqstp, 0); /* this means that nfsd4_encode_fattr() ran out of space */ if (status == nfserr_resource && count == 0) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 31673cd251c..f6744bc03da 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -61,7 +61,6 @@ static time_t lease_time = 90; /* default lease time */ static time_t user_lease_time = 90; static time_t boot_time; static int in_grace = 1; -static u32 current_clientid = 1; static u32 current_ownerid = 1; static u32 current_fileid = 1; static u32 current_delegid = 1; @@ -340,21 +339,20 @@ STALE_CLIENTID(clientid_t *clid) * This type of memory management is somewhat inefficient, but we use it * anyway since SETCLIENTID is not a common operation. */ -static inline struct nfs4_client * -alloc_client(struct xdr_netobj name) +static struct nfs4_client *alloc_client(struct xdr_netobj name) { struct nfs4_client *clp; - if ((clp = kzalloc(sizeof(struct nfs4_client), GFP_KERNEL))!= NULL) { - if ((clp->cl_name.data = kmalloc(name.len, GFP_KERNEL)) != NULL) { - memcpy(clp->cl_name.data, name.data, name.len); - clp->cl_name.len = name.len; - } - else { - kfree(clp); - clp = NULL; - } + clp = kzalloc(sizeof(struct nfs4_client), GFP_KERNEL); + if (clp == NULL) + return NULL; + clp->cl_name.data = kmalloc(name.len, GFP_KERNEL); + if (clp->cl_name.data == NULL) { + kfree(clp); + return NULL; } + memcpy(clp->cl_name.data, name.data, name.len); + clp->cl_name.len = name.len; return clp; } @@ -363,8 +361,11 @@ shutdown_callback_client(struct nfs4_client *clp) { struct rpc_clnt *clnt = clp->cl_callback.cb_client; - /* shutdown rpc client, ending any outstanding recall rpcs */ if (clnt) { + /* + * Callback threads take a reference on the client, so there + * should be no outstanding callbacks at this point. + */ clp->cl_callback.cb_client = NULL; rpc_shutdown_client(clnt); } @@ -422,12 +423,13 @@ expire_client(struct nfs4_client *clp) put_nfs4_client(clp); } -static struct nfs4_client * -create_client(struct xdr_netobj name, char *recdir) { +static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir) +{ struct nfs4_client *clp; - if (!(clp = alloc_client(name))) - goto out; + clp = alloc_client(name); + if (clp == NULL) + return NULL; memcpy(clp->cl_recdir, recdir, HEXDIR_LEN); atomic_set(&clp->cl_count, 1); atomic_set(&clp->cl_callback.cb_set, 0); @@ -436,32 +438,30 @@ create_client(struct xdr_netobj name, char *recdir) { INIT_LIST_HEAD(&clp->cl_openowners); INIT_LIST_HEAD(&clp->cl_delegations); INIT_LIST_HEAD(&clp->cl_lru); -out: return clp; } -static void -copy_verf(struct nfs4_client *target, nfs4_verifier *source) { - memcpy(target->cl_verifier.data, source->data, sizeof(target->cl_verifier.data)); +static void copy_verf(struct nfs4_client *target, nfs4_verifier *source) +{ + memcpy(target->cl_verifier.data, source->data, + sizeof(target->cl_verifier.data)); } -static void -copy_clid(struct nfs4_client *target, struct nfs4_client *source) { +static void copy_clid(struct nfs4_client *target, struct nfs4_client *source) +{ target->cl_clientid.cl_boot = source->cl_clientid.cl_boot; target->cl_clientid.cl_id = source->cl_clientid.cl_id; } -static void -copy_cred(struct svc_cred *target, struct svc_cred *source) { - +static void copy_cred(struct svc_cred *target, struct svc_cred *source) +{ target->cr_uid = source->cr_uid; target->cr_gid = source->cr_gid; target->cr_group_info = source->cr_group_info; get_group_info(target->cr_group_info); } -static inline int -same_name(const char *n1, const char *n2) +static int same_name(const char *n1, const char *n2) { return 0 == memcmp(n1, n2, HEXDIR_LEN); } @@ -485,26 +485,26 @@ same_creds(struct svc_cred *cr1, struct svc_cred *cr2) return cr1->cr_uid == cr2->cr_uid; } -static void -gen_clid(struct nfs4_client *clp) { +static void gen_clid(struct nfs4_client *clp) +{ + static u32 current_clientid = 1; + clp->cl_clientid.cl_boot = boot_time; clp->cl_clientid.cl_id = current_clientid++; } -static void -gen_confirm(struct nfs4_client *clp) { - struct timespec tv; - u32 * p; +static void gen_confirm(struct nfs4_client *clp) +{ + static u32 i; + u32 *p; - tv = CURRENT_TIME; p = (u32 *)clp->cl_confirm.data; - *p++ = tv.tv_sec; - *p++ = tv.tv_nsec; + *p++ = get_seconds(); + *p++ = i++; } -static int -check_name(struct xdr_netobj name) { - +static int check_name(struct xdr_netobj name) +{ if (name.len == 0) return 0; if (name.len > NFS4_OPAQUE_LIMIT) { @@ -683,39 +683,6 @@ out_err: return; } -/* - * RFC 3010 has a complex implmentation description of processing a - * SETCLIENTID request consisting of 5 bullets, labeled as - * CASE0 - CASE4 below. - * - * NOTES: - * callback information will be processed in a future patch - * - * an unconfirmed record is added when: - * NORMAL (part of CASE 4): there is no confirmed nor unconfirmed record. - * CASE 1: confirmed record found with matching name, principal, - * verifier, and clientid. - * CASE 2: confirmed record found with matching name, principal, - * and there is no unconfirmed record with matching - * name and principal - * - * an unconfirmed record is replaced when: - * CASE 3: confirmed record found with matching name, principal, - * and an unconfirmed record is found with matching - * name, principal, and with clientid and - * confirm that does not match the confirmed record. - * CASE 4: there is no confirmed record with matching name and - * principal. there is an unconfirmed record with - * matching name, principal. - * - * an unconfirmed record is deleted when: - * CASE 1: an unconfirmed record that matches input name, verifier, - * and confirmed clientid. - * CASE 4: any unconfirmed records with matching name and principal - * that exist after an unconfirmed record has been replaced - * as described above. - * - */ __be32 nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_setclientid *setclid) @@ -748,11 +715,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfs4_lock_state(); conf = find_confirmed_client_by_str(dname, strhashval); if (conf) { - /* - * CASE 0: - * clname match, confirmed, different principal - * or different ip_address - */ + /* RFC 3530 14.2.33 CASE 0: */ status = nfserr_clid_inuse; if (!same_creds(&conf->cl_cred, &rqstp->rq_cred) || conf->cl_addr != sin->sin_addr.s_addr) { @@ -761,12 +724,17 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } } + /* + * section 14.2.33 of RFC 3530 (under the heading "IMPLEMENTATION") + * has a description of SETCLIENTID request processing consisting + * of 5 bullet points, labeled as CASE0 - CASE4 below. + */ unconf = find_unconfirmed_client_by_str(dname, strhashval); status = nfserr_resource; if (!conf) { - /* - * CASE 4: - * placed first, because it is the normal case. + /* + * RFC 3530 14.2.33 CASE 4: + * placed first, because it is the normal case */ if (unconf) expire_client(unconf); @@ -776,17 +744,8 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, gen_clid(new); } else if (same_verf(&conf->cl_verifier, &clverifier)) { /* - * CASE 1: - * cl_name match, confirmed, principal match - * verifier match: probable callback update - * - * remove any unconfirmed nfs4_client with - * matching cl_name, cl_verifier, and cl_clientid - * - * create and insert an unconfirmed nfs4_client with same - * cl_name, cl_verifier, and cl_clientid as existing - * nfs4_client, but with the new callback info and a - * new cl_confirm + * RFC 3530 14.2.33 CASE 1: + * probable callback update */ if (unconf) { /* Note this is removing unconfirmed {*x***}, @@ -802,43 +761,25 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, copy_clid(new, conf); } else if (!unconf) { /* - * CASE 2: - * clname match, confirmed, principal match - * verfier does not match - * no unconfirmed. create a new unconfirmed nfs4_client - * using input clverifier, clname, and callback info - * and generate a new cl_clientid and cl_confirm. + * RFC 3530 14.2.33 CASE 2: + * probable client reboot; state will be removed if + * confirmed. */ new = create_client(clname, dname); if (new == NULL) goto out; gen_clid(new); - } else if (!same_verf(&conf->cl_confirm, &unconf->cl_confirm)) { - /* - * CASE3: - * confirmed found (name, principal match) - * confirmed verifier does not match input clverifier - * - * unconfirmed found (name match) - * confirmed->cl_confirm != unconfirmed->cl_confirm - * - * remove unconfirmed. - * - * create an unconfirmed nfs4_client - * with same cl_name as existing confirmed nfs4_client, - * but with new callback info, new cl_clientid, - * new cl_verifier and a new cl_confirm + } else { + /* + * RFC 3530 14.2.33 CASE 3: + * probable client reboot; state will be removed if + * confirmed. */ expire_client(unconf); new = create_client(clname, dname); if (new == NULL) goto out; gen_clid(new); - } else { - /* No cases hit !!! */ - status = nfserr_inval; - goto out; - } copy_verf(new, &clverifier); new->cl_addr = sin->sin_addr.s_addr; @@ -857,11 +798,9 @@ out: /* - * RFC 3010 has a complex implmentation description of processing a - * SETCLIENTID_CONFIRM request consisting of 4 bullets describing - * processing on a DRC miss, labeled as CASE1 - CASE4 below. - * - * NOTE: callback information will be processed here in a future patch + * Section 14.2.34 of RFC 3530 (under the heading "IMPLEMENTATION") has + * a description of SETCLIENTID_CONFIRM request processing consisting of 4 + * bullets, labeled as CASE1 - CASE4 below. */ __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, @@ -892,16 +831,16 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, if (unconf && unconf->cl_addr != sin->sin_addr.s_addr) goto out; - if ((conf && unconf) && - (same_verf(&unconf->cl_confirm, &confirm)) && - (same_verf(&conf->cl_verifier, &unconf->cl_verifier)) && - (same_name(conf->cl_recdir,unconf->cl_recdir)) && - (!same_verf(&conf->cl_confirm, &unconf->cl_confirm))) { - /* CASE 1: - * unconf record that matches input clientid and input confirm. - * conf record that matches input clientid. - * conf and unconf records match names, verifiers - */ + /* + * section 14.2.34 of RFC 3530 has a description of + * SETCLIENTID_CONFIRM request processing consisting + * of 4 bullet points, labeled as CASE1 - CASE4 below. + */ + if (conf && unconf && same_verf(&confirm, &unconf->cl_confirm)) { + /* + * RFC 3530 14.2.34 CASE 1: + * callback update + */ if (!same_creds(&conf->cl_cred, &unconf->cl_cred)) status = nfserr_clid_inuse; else { @@ -914,15 +853,11 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, status = nfs_ok; } - } else if ((conf && !unconf) || - ((conf && unconf) && - (!same_verf(&conf->cl_verifier, &unconf->cl_verifier) || - !same_name(conf->cl_recdir, unconf->cl_recdir)))) { - /* CASE 2: - * conf record that matches input clientid. - * if unconf record matches input clientid, then - * unconf->cl_name or unconf->cl_verifier don't match the - * conf record. + } else if (conf && !unconf) { + /* + * RFC 3530 14.2.34 CASE 2: + * probable retransmitted request; play it safe and + * do nothing. */ if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) status = nfserr_clid_inuse; @@ -930,10 +865,9 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, status = nfs_ok; } else if (!conf && unconf && same_verf(&unconf->cl_confirm, &confirm)) { - /* CASE 3: - * conf record not found. - * unconf record found. - * unconf->cl_confirm matches input confirm + /* + * RFC 3530 14.2.34 CASE 3: + * Normal case; new or rebooted client: */ if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred)) { status = nfserr_clid_inuse; @@ -948,16 +882,15 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, } move_to_confirmed(unconf); conf = unconf; + nfsd4_probe_callback(conf); status = nfs_ok; } } else if ((!conf || (conf && !same_verf(&conf->cl_confirm, &confirm))) && (!unconf || (unconf && !same_verf(&unconf->cl_confirm, &confirm)))) { - /* CASE 4: - * conf record not found, or if conf, conf->cl_confirm does not - * match input confirm. - * unconf record not found, or if unconf, unconf->cl_confirm - * does not match input confirm. + /* + * RFC 3530 14.2.34 CASE 4: + * Client probably hasn't noticed that we rebooted yet. */ status = nfserr_stale_clientid; } else { @@ -965,8 +898,6 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, status = nfserr_clid_inuse; } out: - if (!status) - nfsd4_probe_callback(conf); nfs4_unlock_state(); return status; } @@ -1226,14 +1157,19 @@ find_file(struct inode *ino) return NULL; } -static int access_valid(u32 x) +static inline int access_valid(u32 x) { - return (x > 0 && x < 4); + if (x < NFS4_SHARE_ACCESS_READ) + return 0; + if (x > NFS4_SHARE_ACCESS_BOTH) + return 0; + return 1; } -static int deny_valid(u32 x) +static inline int deny_valid(u32 x) { - return (x >= 0 && x < 5); + /* Note: unlike access bits, deny bits may be zero. */ + return x <= NFS4_SHARE_DENY_BOTH; } static void @@ -2162,8 +2098,10 @@ nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *statei goto check_replay; } + *stpp = stp; + *sopp = sop = stp->st_stateowner; + if (lock) { - struct nfs4_stateowner *sop = stp->st_stateowner; clientid_t *lockclid = &lock->v.new.clientid; struct nfs4_client *clp = sop->so_client; int lkflg = 0; @@ -2193,9 +2131,6 @@ nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *statei return nfserr_bad_stateid; } - *stpp = stp; - *sopp = sop = stp->st_stateowner; - /* * We now validate the seqid and stateid generation numbers. * For the moment, we ignore the possibility of diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 57333944af7..b0592e7c378 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -148,12 +148,12 @@ xdr_error: \ } \ } while (0) -static __be32 *read_buf(struct nfsd4_compoundargs *argp, int nbytes) +static __be32 *read_buf(struct nfsd4_compoundargs *argp, u32 nbytes) { /* We want more bytes than seem to be available. * Maybe we need a new page, maybe we have just run out */ - int avail = (char*)argp->end - (char*)argp->p; + unsigned int avail = (char *)argp->end - (char *)argp->p; __be32 *p; if (avail + argp->pagelen < nbytes) return NULL; @@ -169,6 +169,11 @@ static __be32 *read_buf(struct nfsd4_compoundargs *argp, int nbytes) return NULL; } + /* + * The following memcpy is safe because read_buf is always + * called with nbytes > avail, and the two cases above both + * guarantee p points to at least nbytes bytes. + */ memcpy(p, argp->p, avail); /* step to next page */ argp->p = page_address(argp->pagelist[0]); @@ -1448,7 +1453,7 @@ static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err) __be32 nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, __be32 *buffer, int *countp, u32 *bmval, - struct svc_rqst *rqstp) + struct svc_rqst *rqstp, int ignore_crossmnt) { u32 bmval0 = bmval[0]; u32 bmval1 = bmval[1]; @@ -1828,7 +1833,12 @@ out_acl: if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) { if ((buflen -= 8) < 0) goto out_resource; - if (exp->ex_mnt->mnt_root->d_inode == dentry->d_inode) { + /* + * Get parent's attributes if not ignoring crossmount + * and this is the root of a cross-mounted filesystem. + */ + if (ignore_crossmnt == 0 && + exp->ex_mnt->mnt_root->d_inode == dentry->d_inode) { err = vfs_getattr(exp->ex_mnt->mnt_parent, exp->ex_mnt->mnt_mountpoint, &stat); if (err) @@ -1864,13 +1874,25 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd, struct svc_export *exp = cd->rd_fhp->fh_export; struct dentry *dentry; __be32 nfserr; + int ignore_crossmnt = 0; dentry = lookup_one_len(name, cd->rd_fhp->fh_dentry, namlen); if (IS_ERR(dentry)) return nfserrno(PTR_ERR(dentry)); exp_get(exp); - if (d_mountpoint(dentry)) { + /* + * In the case of a mountpoint, the client may be asking for + * attributes that are only properties of the underlying filesystem + * as opposed to the cross-mounted file system. In such a case, + * we will not follow the cross mount and will fill the attribtutes + * directly from the mountpoint dentry. + */ + if (d_mountpoint(dentry) && + (cd->rd_bmval[0] & ~FATTR4_WORD0_RDATTR_ERROR) == 0 && + (cd->rd_bmval[1] & ~FATTR4_WORD1_MOUNTED_ON_FILEID) == 0) + ignore_crossmnt = 1; + else if (d_mountpoint(dentry)) { int err; /* @@ -1889,7 +1911,7 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd, } nfserr = nfsd4_encode_fattr(NULL, exp, dentry, p, buflen, cd->rd_bmval, - cd->rd_rqstp); + cd->rd_rqstp, ignore_crossmnt); out_put: dput(dentry); exp_put(exp); @@ -2043,7 +2065,7 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 buflen = resp->end - resp->p - (COMPOUND_ERR_SLACK_SPACE >> 2); nfserr = nfsd4_encode_fattr(fhp, fhp->fh_export, fhp->fh_dentry, resp->p, &buflen, getattr->ga_bmval, - resp->rqstp); + resp->rqstp, 0); if (!nfserr) resp->p += buflen; return nfserr; diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 578f2c9d56b..5bfc2ac60d5 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -44,17 +44,17 @@ static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec); */ static DEFINE_SPINLOCK(cache_lock); -void -nfsd_cache_init(void) +int nfsd_reply_cache_init(void) { struct svc_cacherep *rp; int i; INIT_LIST_HEAD(&lru_head); i = CACHESIZE; - while(i) { + while (i) { rp = kmalloc(sizeof(*rp), GFP_KERNEL); - if (!rp) break; + if (!rp) + goto out_nomem; list_add(&rp->c_lru, &lru_head); rp->c_state = RC_UNUSED; rp->c_type = RC_NOCACHE; @@ -62,23 +62,19 @@ nfsd_cache_init(void) i--; } - if (i) - printk (KERN_ERR "nfsd: cannot allocate all %d cache entries, only got %d\n", - CACHESIZE, CACHESIZE-i); - hash_list = kcalloc (HASHSIZE, sizeof(struct hlist_head), GFP_KERNEL); - if (!hash_list) { - nfsd_cache_shutdown(); - printk (KERN_ERR "nfsd: cannot allocate %Zd bytes for hash list\n", - HASHSIZE * sizeof(struct hlist_head)); - return; - } + if (!hash_list) + goto out_nomem; cache_disabled = 0; + return 0; +out_nomem: + printk(KERN_ERR "nfsd: failed to allocate reply cache\n"); + nfsd_reply_cache_shutdown(); + return -ENOMEM; } -void -nfsd_cache_shutdown(void) +void nfsd_reply_cache_shutdown(void) { struct svc_cacherep *rp; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 77dc9893b7b..8516137cdbb 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -304,6 +304,9 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size) struct auth_domain *dom; struct knfsd_fh fh; + if (size == 0) + return -EINVAL; + if (buf[size-1] != '\n') return -EINVAL; buf[size-1] = 0; @@ -503,7 +506,7 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size) int len = 0; lock_kernel(); if (nfsd_serv) - len = svc_sock_names(buf, nfsd_serv, NULL); + len = svc_xprt_names(nfsd_serv, buf, 0); unlock_kernel(); return len; } @@ -540,7 +543,7 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size) } return err < 0 ? err : 0; } - if (buf[0] == '-') { + if (buf[0] == '-' && isdigit(buf[1])) { char *toclose = kstrdup(buf+1, GFP_KERNEL); int len = 0; if (!toclose) @@ -554,6 +557,53 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size) kfree(toclose); return len; } + /* + * Add a transport listener by writing it's transport name + */ + if (isalpha(buf[0])) { + int err; + char transport[16]; + int port; + if (sscanf(buf, "%15s %4d", transport, &port) == 2) { + err = nfsd_create_serv(); + if (!err) { + err = svc_create_xprt(nfsd_serv, + transport, port, + SVC_SOCK_ANONYMOUS); + if (err == -ENOENT) + /* Give a reasonable perror msg for + * bad transport string */ + err = -EPROTONOSUPPORT; + } + return err < 0 ? err : 0; + } + } + /* + * Remove a transport by writing it's transport name and port number + */ + if (buf[0] == '-' && isalpha(buf[1])) { + struct svc_xprt *xprt; + int err = -EINVAL; + char transport[16]; + int port; + if (sscanf(&buf[1], "%15s %4d", transport, &port) == 2) { + if (port == 0) + return -EINVAL; + lock_kernel(); + if (nfsd_serv) { + xprt = svc_find_xprt(nfsd_serv, transport, + AF_UNSPEC, port); + if (xprt) { + svc_close_xprt(xprt); + svc_xprt_put(xprt); + err = 0; + } else + err = -ENOTCONN; + } + unlock_kernel(); + return err < 0 ? err : 0; + } + } return -EINVAL; } @@ -616,7 +666,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size) char *recdir; int len, status; - if (size > PATH_MAX || buf[size-1] != '\n') + if (size == 0 || size > PATH_MAX || buf[size-1] != '\n') return -EINVAL; buf[size-1] = 0; @@ -674,6 +724,27 @@ static struct file_system_type nfsd_fs_type = { .kill_sb = kill_litter_super, }; +#ifdef CONFIG_PROC_FS +static int create_proc_exports_entry(void) +{ + struct proc_dir_entry *entry; + + entry = proc_mkdir("fs/nfs", NULL); + if (!entry) + return -ENOMEM; + entry = create_proc_entry("fs/nfs/exports", 0, NULL); + if (!entry) + return -ENOMEM; + entry->proc_fops = &exports_operations; + return 0; +} +#else /* CONFIG_PROC_FS */ +static int create_proc_exports_entry(void) +{ + return 0; +} +#endif + static int __init init_nfsd(void) { int retval; @@ -683,32 +754,43 @@ static int __init init_nfsd(void) if (retval) return retval; nfsd_stat_init(); /* Statistics */ - nfsd_cache_init(); /* RPC reply cache */ - nfsd_export_init(); /* Exports table */ + retval = nfsd_reply_cache_init(); + if (retval) + goto out_free_stat; + retval = nfsd_export_init(); + if (retval) + goto out_free_cache; nfsd_lockd_init(); /* lockd->nfsd callbacks */ - nfsd_idmap_init(); /* Name to ID mapping */ - if (proc_mkdir("fs/nfs", NULL)) { - struct proc_dir_entry *entry; - entry = create_proc_entry("fs/nfs/exports", 0, NULL); - if (entry) - entry->proc_fops = &exports_operations; - } + retval = nfsd_idmap_init(); + if (retval) + goto out_free_lockd; + retval = create_proc_exports_entry(); + if (retval) + goto out_free_idmap; retval = register_filesystem(&nfsd_fs_type); - if (retval) { - nfsd_export_shutdown(); - nfsd_cache_shutdown(); - remove_proc_entry("fs/nfs/exports", NULL); - remove_proc_entry("fs/nfs", NULL); - nfsd_stat_shutdown(); - nfsd_lockd_shutdown(); - } + if (retval) + goto out_free_all; + return 0; +out_free_all: + remove_proc_entry("fs/nfs/exports", NULL); + remove_proc_entry("fs/nfs", NULL); +out_free_idmap: + nfsd_idmap_shutdown(); +out_free_lockd: + nfsd_lockd_shutdown(); + nfsd_export_shutdown(); +out_free_cache: + nfsd_reply_cache_shutdown(); +out_free_stat: + nfsd_stat_shutdown(); + nfsd4_free_slabs(); return retval; } static void __exit exit_nfsd(void) { nfsd_export_shutdown(); - nfsd_cache_shutdown(); + nfsd_reply_cache_shutdown(); remove_proc_entry("fs/nfs/exports", NULL); remove_proc_entry("fs/nfs", NULL); nfsd_stat_shutdown(); diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 468f17a7844..8fbd2dc08a9 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -22,6 +22,7 @@ #include <linux/sunrpc/svc.h> #include <linux/sunrpc/svcauth_gss.h> #include <linux/nfsd/nfsd.h> +#include "auth.h" #define NFSDDBG_FACILITY NFSDDBG_FH diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 1190aeaa92b..9647b0f7bc0 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -155,8 +155,8 @@ static int killsig; /* signal that was used to kill last nfsd */ static void nfsd_last_thread(struct svc_serv *serv) { /* When last nfsd thread exits we need to do some clean-up */ - struct svc_sock *svsk; - list_for_each_entry(svsk, &serv->sv_permsocks, sk_list) + struct svc_xprt *xprt; + list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list) lockd_down(); nfsd_serv = NULL; nfsd_racache_shutdown(); @@ -236,7 +236,7 @@ static int nfsd_init_socks(int port) error = lockd_up(IPPROTO_UDP); if (error >= 0) { - error = svc_makesock(nfsd_serv, IPPROTO_UDP, port, + error = svc_create_xprt(nfsd_serv, "udp", port, SVC_SOCK_DEFAULTS); if (error < 0) lockd_down(); @@ -247,7 +247,7 @@ static int nfsd_init_socks(int port) #ifdef CONFIG_NFSD_TCP error = lockd_up(IPPROTO_TCP); if (error >= 0) { - error = svc_makesock(nfsd_serv, IPPROTO_TCP, port, + error = svc_create_xprt(nfsd_serv, "tcp", port, SVC_SOCK_DEFAULTS); if (error < 0) lockd_down(); diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index b86e3658a0a..61ad61743d9 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -15,6 +15,7 @@ #include <linux/nfsd/nfsd.h> #include <linux/nfsd/xdr.h> #include <linux/mm.h> +#include "auth.h" #define NFSDDBG_FACILITY NFSDDBG_XDR @@ -62,10 +63,10 @@ encode_fh(__be32 *p, struct svc_fh *fhp) * no slashes or null bytes. */ static __be32 * -decode_filename(__be32 *p, char **namp, int *lenp) +decode_filename(__be32 *p, char **namp, unsigned int *lenp) { char *name; - int i; + unsigned int i; if ((p = xdr_decode_string_inplace(p, namp, lenp, NFS_MAXNAMLEN)) != NULL) { for (i = 0, name = *namp; i < *lenp; i++, name++) { @@ -78,10 +79,10 @@ decode_filename(__be32 *p, char **namp, int *lenp) } static __be32 * -decode_pathname(__be32 *p, char **namp, int *lenp) +decode_pathname(__be32 *p, char **namp, unsigned int *lenp) { char *name; - int i; + unsigned int i; if ((p = xdr_decode_string_inplace(p, namp, lenp, NFS_MAXPATHLEN)) != NULL) { for (i = 0, name = *namp; i < *lenp; i++, name++) { diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index d0199189924..cc75e4fcd02 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -132,7 +132,7 @@ out: __be32 nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, - const char *name, int len, + const char *name, unsigned int len, struct svc_export **exp_ret, struct dentry **dentry_ret) { struct svc_export *exp; @@ -226,7 +226,7 @@ out_nfserr: */ __be32 nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name, - int len, struct svc_fh *resfh) + unsigned int len, struct svc_fh *resfh) { struct svc_export *exp; struct dentry *dentry; @@ -1151,6 +1151,26 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, } #endif /* CONFIG_NFSD_V3 */ +__be32 +nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp, + struct iattr *iap) +{ + /* + * Mode has already been set earlier in create: + */ + iap->ia_valid &= ~ATTR_MODE; + /* + * Setting uid/gid works only for root. Irix appears to + * send along the gid on create when it tries to implement + * setgid directories via NFS: + */ + if (current->fsuid != 0) + iap->ia_valid &= ~(ATTR_UID|ATTR_GID); + if (iap->ia_valid) + return nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0); + return 0; +} + /* * Create a file (regular, directory, device, fifo); UNIX sockets * not yet implemented. @@ -1167,6 +1187,7 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, struct dentry *dentry, *dchild = NULL; struct inode *dirp; __be32 err; + __be32 err2; int host_err; err = nfserr_perm; @@ -1257,16 +1278,9 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, } - /* Set file attributes. Mode has already been set and - * setting uid/gid works only for root. Irix appears to - * send along the gid when it tries to implement setgid - * directories via NFS. - */ - if ((iap->ia_valid &= ~(ATTR_UID|ATTR_GID|ATTR_MODE)) != 0) { - __be32 err2 = nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0); - if (err2) - err = err2; - } + err2 = nfsd_create_setattr(rqstp, resfhp, iap); + if (err2) + err = err2; /* * Update the file handle to get the new inode info. */ @@ -1295,6 +1309,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, struct dentry *dentry, *dchild = NULL; struct inode *dirp; __be32 err; + __be32 err2; int host_err; __u32 v_mtime=0, v_atime=0; @@ -1399,16 +1414,10 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, iap->ia_atime.tv_nsec = 0; } - /* Set file attributes. - * Irix appears to send along the gid when it tries to - * implement setgid directories via NFS. Clear out all that cruft. - */ set_attr: - if ((iap->ia_valid &= ~(ATTR_UID|ATTR_GID|ATTR_MODE)) != 0) { - __be32 err2 = nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0); - if (err2) - err = err2; - } + err2 = nfsd_create_setattr(rqstp, resfhp, iap); + if (err2) + err = err2; /* * Update the filehandle to get the new inode info. diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c index ad87cb01299..00e9ccde8e4 100644 --- a/fs/ntfs/aops.c +++ b/fs/ntfs/aops.c @@ -87,13 +87,17 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate) /* Check for the current buffer head overflowing. */ if (unlikely(file_ofs + bh->b_size > init_size)) { int ofs; + void *kaddr; ofs = 0; if (file_ofs < init_size) ofs = init_size - file_ofs; local_irq_save(flags); - zero_user_page(page, bh_offset(bh) + ofs, - bh->b_size - ofs, KM_BIO_SRC_IRQ); + kaddr = kmap_atomic(page, KM_BIO_SRC_IRQ); + memset(kaddr + bh_offset(bh) + ofs, 0, + bh->b_size - ofs); + flush_dcache_page(page); + kunmap_atomic(kaddr, KM_BIO_SRC_IRQ); local_irq_restore(flags); } } else { @@ -334,7 +338,7 @@ handle_hole: bh->b_blocknr = -1UL; clear_buffer_mapped(bh); handle_zblock: - zero_user_page(page, i * blocksize, blocksize, KM_USER0); + zero_user(page, i * blocksize, blocksize); if (likely(!err)) set_buffer_uptodate(bh); } while (i++, iblock++, (bh = bh->b_this_page) != head); @@ -410,7 +414,7 @@ retry_readpage: /* Is the page fully outside i_size? (truncate in progress) */ if (unlikely(page->index >= (i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT)) { - zero_user_page(page, 0, PAGE_CACHE_SIZE, KM_USER0); + zero_user(page, 0, PAGE_CACHE_SIZE); ntfs_debug("Read outside i_size - truncated?"); goto done; } @@ -459,7 +463,7 @@ retry_readpage: * ok to ignore the compressed flag here. */ if (unlikely(page->index > 0)) { - zero_user_page(page, 0, PAGE_CACHE_SIZE, KM_USER0); + zero_user(page, 0, PAGE_CACHE_SIZE); goto done; } if (!NInoAttr(ni)) @@ -788,8 +792,7 @@ lock_retry_remap: if (err == -ENOENT || lcn == LCN_ENOENT) { bh->b_blocknr = -1; clear_buffer_dirty(bh); - zero_user_page(page, bh_offset(bh), blocksize, - KM_USER0); + zero_user(page, bh_offset(bh), blocksize); set_buffer_uptodate(bh); err = 0; continue; @@ -1414,8 +1417,7 @@ retry_writepage: if (page->index >= (i_size >> PAGE_CACHE_SHIFT)) { /* The page straddles i_size. */ unsigned int ofs = i_size & ~PAGE_CACHE_MASK; - zero_user_page(page, ofs, PAGE_CACHE_SIZE - ofs, - KM_USER0); + zero_user_segment(page, ofs, PAGE_CACHE_SIZE); } /* Handle mst protected attributes. */ if (NInoMstProtected(ni)) diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c index d1619d05eb2..33ff314cc50 100644 --- a/fs/ntfs/compress.c +++ b/fs/ntfs/compress.c @@ -565,7 +565,7 @@ int ntfs_read_compressed_block(struct page *page) if (xpage >= max_page) { kfree(bhs); kfree(pages); - zero_user_page(page, 0, PAGE_CACHE_SIZE, KM_USER0); + zero_user(page, 0, PAGE_CACHE_SIZE); ntfs_debug("Compressed read outside i_size - truncated?"); SetPageUptodate(page); unlock_page(page); diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 6cd08dfdc2e..3c5550cd11d 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -607,8 +607,8 @@ do_next_page: ntfs_submit_bh_for_read(bh); *wait_bh++ = bh; } else { - zero_user_page(page, bh_offset(bh), - blocksize, KM_USER0); + zero_user(page, bh_offset(bh), + blocksize); set_buffer_uptodate(bh); } } @@ -683,9 +683,8 @@ map_buffer_cached: ntfs_submit_bh_for_read(bh); *wait_bh++ = bh; } else { - zero_user_page(page, - bh_offset(bh), - blocksize, KM_USER0); + zero_user(page, bh_offset(bh), + blocksize); set_buffer_uptodate(bh); } } @@ -703,8 +702,8 @@ map_buffer_cached: */ if (bh_end <= pos || bh_pos >= end) { if (!buffer_uptodate(bh)) { - zero_user_page(page, bh_offset(bh), - blocksize, KM_USER0); + zero_user(page, bh_offset(bh), + blocksize); set_buffer_uptodate(bh); } mark_buffer_dirty(bh); @@ -743,8 +742,7 @@ map_buffer_cached: if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); } else if (!buffer_uptodate(bh)) { - zero_user_page(page, bh_offset(bh), blocksize, - KM_USER0); + zero_user(page, bh_offset(bh), blocksize); set_buffer_uptodate(bh); } continue; @@ -868,8 +866,8 @@ rl_not_mapped_enoent: if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); } else if (!buffer_uptodate(bh)) { - zero_user_page(page, bh_offset(bh), - blocksize, KM_USER0); + zero_user(page, bh_offset(bh), + blocksize); set_buffer_uptodate(bh); } continue; @@ -1128,8 +1126,8 @@ rl_not_mapped_enoent: if (likely(bh_pos < initialized_size)) ofs = initialized_size - bh_pos; - zero_user_page(page, bh_offset(bh) + ofs, - blocksize - ofs, KM_USER0); + zero_user_segment(page, bh_offset(bh) + ofs, + blocksize); } } else /* if (unlikely(!buffer_uptodate(bh))) */ err = -EIO; @@ -1269,8 +1267,8 @@ rl_not_mapped_enoent: if (PageUptodate(page)) set_buffer_uptodate(bh); else { - zero_user_page(page, bh_offset(bh), - blocksize, KM_USER0); + zero_user(page, bh_offset(bh), + blocksize); set_buffer_uptodate(bh); } } @@ -1330,7 +1328,7 @@ err_out: len = PAGE_CACHE_SIZE; if (len > bytes) len = bytes; - zero_user_page(*pages, 0, len, KM_USER0); + zero_user(*pages, 0, len); } goto out; } @@ -1451,7 +1449,7 @@ err_out: len = PAGE_CACHE_SIZE; if (len > bytes) len = bytes; - zero_user_page(*pages, 0, len, KM_USER0); + zero_user(*pages, 0, len); } goto out; } diff --git a/fs/ntfs/malloc.h b/fs/ntfs/malloc.h index e38e402e410..cd0be3f5c3c 100644 --- a/fs/ntfs/malloc.h +++ b/fs/ntfs/malloc.h @@ -85,8 +85,7 @@ static inline void *ntfs_malloc_nofs_nofail(unsigned long size) static inline void ntfs_free(void *addr) { - if (likely(((unsigned long)addr < VMALLOC_START) || - ((unsigned long)addr >= VMALLOC_END ))) { + if (!is_vmalloc_addr(addr)) { kfree(addr); /* free_page((unsigned long)addr); */ return; diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index e6df06ac640..447206eb5c2 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -3338,7 +3338,7 @@ static int ocfs2_insert_path(struct inode *inode, if (insert->ins_split != SPLIT_NONE) { /* * We could call ocfs2_insert_at_leaf() for some types - * of splits, but it's easier to just let one seperate + * of splits, but it's easier to just let one separate * function sort it all out. */ ocfs2_split_record(inode, left_path, right_path, @@ -5670,7 +5670,7 @@ static void ocfs2_map_and_dirty_page(struct inode *inode, handle_t *handle, mlog_errno(ret); if (zero) - zero_user_page(page, from, to - from, KM_USER0); + zero_user_segment(page, from, to); /* * Need to set the buffers we zero'd into uptodate diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index bc7b4cbbe8e..82243127eeb 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -307,7 +307,7 @@ static int ocfs2_readpage(struct file *file, struct page *page) * XXX sys_readahead() seems to get that wrong? */ if (start >= i_size_read(inode)) { - zero_user_page(page, 0, PAGE_SIZE, KM_USER0); + zero_user(page, 0, PAGE_SIZE); SetPageUptodate(page); ret = 0; goto out_alloc; @@ -869,7 +869,7 @@ int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno, if (block_start >= to) break; - zero_user_page(page, block_start, bh->b_size, KM_USER0); + zero_user(page, block_start, bh->b_size); set_buffer_uptodate(bh); mark_buffer_dirty(bh); @@ -1034,7 +1034,7 @@ static void ocfs2_zero_new_buffers(struct page *page, unsigned from, unsigned to start = max(from, block_start); end = min(to, block_end); - zero_user_page(page, start, end - start, KM_USER0); + zero_user_segment(page, start, end); set_buffer_uptodate(bh); } diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 6b0107f2134..e280833ceb9 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -1215,7 +1215,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, down_write(&oi->ip_alloc_sem); /* - * Prepare for worst case allocation scenario of two seperate + * Prepare for worst case allocation scenario of two separate * extents. */ if (alloc == 2) diff --git a/fs/ocfs2/ocfs1_fs_compat.h b/fs/ocfs2/ocfs1_fs_compat.h index 0b499bccec5..dfb313bda5d 100644 --- a/fs/ocfs2/ocfs1_fs_compat.h +++ b/fs/ocfs2/ocfs1_fs_compat.h @@ -77,7 +77,7 @@ struct ocfs1_disk_lock { /*00*/ __u32 curr_master; __u8 file_lock; - __u8 compat_pad[3]; /* Not in orignal definition. Used to + __u8 compat_pad[3]; /* Not in original definition. Used to make the already existing alignment explicit */ __u64 last_write_time; diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 7e397e2c25d..72c198a004d 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -646,7 +646,7 @@ bail: * sync-data inodes." * * Note: OCFS2 already does this differently for metadata vs data - * allocations, as those bitmaps are seperate and undo access is never + * allocations, as those bitmaps are separate and undo access is never * called on a metadata group descriptor. */ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh, diff --git a/fs/partitions/Kconfig b/fs/partitions/Kconfig index a99acd8de35..cb5f0a3f1b0 100644 --- a/fs/partitions/Kconfig +++ b/fs/partitions/Kconfig @@ -198,7 +198,7 @@ config LDM_DEBUG config SGI_PARTITION bool "SGI partition support" if PARTITION_ADVANCED - default y if (SGI_IP22 || SGI_IP27 || ((MACH_JAZZ || SNI_RM) && !CPU_LITTLE_ENDIAN)) + default y if DEFAULT_SGI_PARTITION help Say Y here if you would like to be able to read the hard disk partition table format used by SGI machines. diff --git a/fs/pnode.c b/fs/pnode.c index 89940f243fc..05ba692bc54 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -83,6 +83,8 @@ void change_mnt_propagation(struct vfsmount *mnt, int type) mnt->mnt_master = NULL; if (type == MS_UNBINDABLE) mnt->mnt_flags |= MNT_UNBINDABLE; + else + mnt->mnt_flags &= ~MNT_UNBINDABLE; } } diff --git a/fs/proc/array.c b/fs/proc/array.c index b380313092b..6ba2746e451 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -281,14 +281,23 @@ static inline char *task_sig(struct task_struct *p, char *buffer) return buffer; } +static char *render_cap_t(const char *header, kernel_cap_t *a, char *buffer) +{ + unsigned __capi; + + buffer += sprintf(buffer, "%s", header); + CAP_FOR_EACH_U32(__capi) { + buffer += sprintf(buffer, "%08x", + a->cap[(_LINUX_CAPABILITY_U32S-1) - __capi]); + } + return buffer + sprintf(buffer, "\n"); +} + static inline char *task_cap(struct task_struct *p, char *buffer) { - return buffer + sprintf(buffer, "CapInh:\t%016x\n" - "CapPrm:\t%016x\n" - "CapEff:\t%016x\n", - cap_t(p->cap_inheritable), - cap_t(p->cap_permitted), - cap_t(p->cap_effective)); + buffer = render_cap_t("CapInh:\t", &p->cap_inheritable, buffer); + buffer = render_cap_t("CapPrm:\t", &p->cap_permitted, buffer); + return render_cap_t("CapEff:\t", &p->cap_effective, buffer); } static inline char *task_context_switch_counts(struct task_struct *p, diff --git a/fs/proc/base.c b/fs/proc/base.c index 33537487f5a..c59852b3878 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -88,10 +88,6 @@ * in /proc for a task before it execs a suid executable. */ - -/* Worst case buffer size needed for holding an integer. */ -#define PROC_NUMBUF 13 - struct pid_entry { char *name; int len; @@ -787,7 +783,7 @@ out_no_task: } #endif -static loff_t mem_lseek(struct file * file, loff_t offset, int orig) +loff_t mem_lseek(struct file *file, loff_t offset, int orig) { switch (orig) { case 0: @@ -935,42 +931,6 @@ static const struct file_operations proc_oom_adjust_operations = { .write = oom_adjust_write, }; -#ifdef CONFIG_MMU -static ssize_t clear_refs_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct task_struct *task; - char buffer[PROC_NUMBUF], *end; - struct mm_struct *mm; - - memset(buffer, 0, sizeof(buffer)); - if (count > sizeof(buffer) - 1) - count = sizeof(buffer) - 1; - if (copy_from_user(buffer, buf, count)) - return -EFAULT; - if (!simple_strtol(buffer, &end, 0)) - return -EINVAL; - if (*end == '\n') - end++; - task = get_proc_task(file->f_path.dentry->d_inode); - if (!task) - return -ESRCH; - mm = get_task_mm(task); - if (mm) { - clear_refs_smap(mm); - mmput(mm); - } - put_task_struct(task); - if (end - buffer == 0) - return -EIO; - return end - buffer; -} - -static struct file_operations proc_clear_refs_operations = { - .write = clear_refs_write, -}; -#endif - #ifdef CONFIG_AUDITSYSCALL #define TMPBUFLEN 21 static ssize_t proc_loginuid_read(struct file * file, char __user * buf, @@ -2289,9 +2249,10 @@ static const struct pid_entry tgid_base_stuff[] = { LNK("exe", exe), REG("mounts", S_IRUGO, mounts), REG("mountstats", S_IRUSR, mountstats), -#ifdef CONFIG_MMU +#ifdef CONFIG_PROC_PAGE_MONITOR REG("clear_refs", S_IWUSR, clear_refs), REG("smaps", S_IRUGO, smaps), + REG("pagemap", S_IRUSR, pagemap), #endif #ifdef CONFIG_SECURITY DIR("attr", S_IRUGO|S_IXUGO, attr_dir), @@ -2360,7 +2321,8 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid) name.len = snprintf(buf, sizeof(buf), "%d", pid); dentry = d_hash_and_lookup(mnt->mnt_root, &name); if (dentry) { - shrink_dcache_parent(dentry); + if (!(current->flags & PF_EXITING)) + shrink_dcache_parent(dentry); d_drop(dentry); dput(dentry); } @@ -2617,9 +2579,10 @@ static const struct pid_entry tid_base_stuff[] = { LNK("root", root), LNK("exe", exe), REG("mounts", S_IRUGO, mounts), -#ifdef CONFIG_MMU +#ifdef CONFIG_PROC_PAGE_MONITOR REG("clear_refs", S_IWUSR, clear_refs), REG("smaps", S_IRUGO, smaps), + REG("pagemap", S_IRUSR, pagemap), #endif #ifdef CONFIG_SECURITY DIR("attr", S_IRUGO|S_IXUGO, attr_dir), diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 05b3e900626..7d57e806992 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -52,15 +52,13 @@ extern int proc_tid_stat(struct task_struct *, char *); extern int proc_tgid_stat(struct task_struct *, char *); extern int proc_pid_status(struct task_struct *, char *); extern int proc_pid_statm(struct task_struct *, char *); +extern loff_t mem_lseek(struct file *file, loff_t offset, int orig); extern const struct file_operations proc_maps_operations; extern const struct file_operations proc_numa_maps_operations; extern const struct file_operations proc_smaps_operations; - -extern const struct file_operations proc_maps_operations; -extern const struct file_operations proc_numa_maps_operations; -extern const struct file_operations proc_smaps_operations; - +extern const struct file_operations proc_clear_refs_operations; +extern const struct file_operations proc_pagemap_operations; void free_proc_entry(struct proc_dir_entry *de); diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 1be73082edd..7dd26e18cbf 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -325,7 +325,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) if (m == NULL) { if (clear_user(buffer, tsz)) return -EFAULT; - } else if ((start >= VMALLOC_START) && (start < VMALLOC_END)) { + } else if (is_vmalloc_addr((void *)start)) { char * elf_buf; struct vm_struct *m; unsigned long curstart = start; diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index 3462bfde89f..2686592dbcb 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -29,6 +29,7 @@ #include <linux/mm.h> #include <linux/mmzone.h> #include <linux/pagemap.h> +#include <linux/interrupt.h> #include <linux/swap.h> #include <linux/slab.h> #include <linux/smp.h> @@ -46,6 +47,7 @@ #include <linux/vmalloc.h> #include <linux/crash_dump.h> #include <linux/pid_namespace.h> +#include <linux/bootmem.h> #include <asm/uaccess.h> #include <asm/pgtable.h> #include <asm/io.h> @@ -63,7 +65,6 @@ */ extern int get_hardware_list(char *); extern int get_stram_list(char *); -extern int get_filesystem_list(char *); extern int get_exec_domain_list(char *); extern int get_dma_list(char *); @@ -83,10 +84,15 @@ static int loadavg_read_proc(char *page, char **start, off_t off, { int a, b, c; int len; + unsigned long seq; + + do { + seq = read_seqbegin(&xtime_lock); + a = avenrun[0] + (FIXED_1/200); + b = avenrun[1] + (FIXED_1/200); + c = avenrun[2] + (FIXED_1/200); + } while (read_seqretry(&xtime_lock, seq)); - a = avenrun[0] + (FIXED_1/200); - b = avenrun[1] + (FIXED_1/200); - c = avenrun[2] + (FIXED_1/200); len = sprintf(page,"%d.%02d %d.%02d %d.%02d %ld/%d %d\n", LOAD_INT(a), LOAD_FRAC(a), LOAD_INT(b), LOAD_FRAC(b), @@ -598,7 +604,6 @@ static void int_seq_stop(struct seq_file *f, void *v) } -extern int show_interrupts(struct seq_file *f, void *v); /* In arch code */ static struct seq_operations int_seq_ops = { .start = int_seq_start, .next = int_seq_next, @@ -675,6 +680,137 @@ static const struct file_operations proc_sysrq_trigger_operations = { }; #endif +#ifdef CONFIG_PROC_PAGE_MONITOR +#define KPMSIZE sizeof(u64) +#define KPMMASK (KPMSIZE - 1) +/* /proc/kpagecount - an array exposing page counts + * + * Each entry is a u64 representing the corresponding + * physical page count. + */ +static ssize_t kpagecount_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + u64 __user *out = (u64 __user *)buf; + struct page *ppage; + unsigned long src = *ppos; + unsigned long pfn; + ssize_t ret = 0; + u64 pcount; + + pfn = src / KPMSIZE; + count = min_t(size_t, count, (max_pfn * KPMSIZE) - src); + if (src & KPMMASK || count & KPMMASK) + return -EIO; + + while (count > 0) { + ppage = NULL; + if (pfn_valid(pfn)) + ppage = pfn_to_page(pfn); + pfn++; + if (!ppage) + pcount = 0; + else + pcount = atomic_read(&ppage->_count); + + if (put_user(pcount, out++)) { + ret = -EFAULT; + break; + } + + count -= KPMSIZE; + } + + *ppos += (char __user *)out - buf; + if (!ret) + ret = (char __user *)out - buf; + return ret; +} + +static struct file_operations proc_kpagecount_operations = { + .llseek = mem_lseek, + .read = kpagecount_read, +}; + +/* /proc/kpageflags - an array exposing page flags + * + * Each entry is a u64 representing the corresponding + * physical page flags. + */ + +/* These macros are used to decouple internal flags from exported ones */ + +#define KPF_LOCKED 0 +#define KPF_ERROR 1 +#define KPF_REFERENCED 2 +#define KPF_UPTODATE 3 +#define KPF_DIRTY 4 +#define KPF_LRU 5 +#define KPF_ACTIVE 6 +#define KPF_SLAB 7 +#define KPF_WRITEBACK 8 +#define KPF_RECLAIM 9 +#define KPF_BUDDY 10 + +#define kpf_copy_bit(flags, srcpos, dstpos) (((flags >> srcpos) & 1) << dstpos) + +static ssize_t kpageflags_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + u64 __user *out = (u64 __user *)buf; + struct page *ppage; + unsigned long src = *ppos; + unsigned long pfn; + ssize_t ret = 0; + u64 kflags, uflags; + + pfn = src / KPMSIZE; + count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src); + if (src & KPMMASK || count & KPMMASK) + return -EIO; + + while (count > 0) { + ppage = NULL; + if (pfn_valid(pfn)) + ppage = pfn_to_page(pfn); + pfn++; + if (!ppage) + kflags = 0; + else + kflags = ppage->flags; + + uflags = kpf_copy_bit(KPF_LOCKED, PG_locked, kflags) | + kpf_copy_bit(kflags, KPF_ERROR, PG_error) | + kpf_copy_bit(kflags, KPF_REFERENCED, PG_referenced) | + kpf_copy_bit(kflags, KPF_UPTODATE, PG_uptodate) | + kpf_copy_bit(kflags, KPF_DIRTY, PG_dirty) | + kpf_copy_bit(kflags, KPF_LRU, PG_lru) | + kpf_copy_bit(kflags, KPF_ACTIVE, PG_active) | + kpf_copy_bit(kflags, KPF_SLAB, PG_slab) | + kpf_copy_bit(kflags, KPF_WRITEBACK, PG_writeback) | + kpf_copy_bit(kflags, KPF_RECLAIM, PG_reclaim) | + kpf_copy_bit(kflags, KPF_BUDDY, PG_buddy); + + if (put_user(uflags, out++)) { + ret = -EFAULT; + break; + } + + count -= KPMSIZE; + } + + *ppos += (char __user *)out - buf; + if (!ret) + ret = (char __user *)out - buf; + return ret; +} + +static struct file_operations proc_kpageflags_operations = { + .llseek = mem_lseek, + .read = kpageflags_read, +}; +#endif /* CONFIG_PROC_PAGE_MONITOR */ + struct proc_dir_entry *proc_root_kcore; void create_seq_entry(char *name, mode_t mode, const struct file_operations *f) @@ -755,6 +891,10 @@ void __init proc_misc_init(void) (size_t)high_memory - PAGE_OFFSET + PAGE_SIZE; } #endif +#ifdef CONFIG_PROC_PAGE_MONITOR + create_seq_entry("kpagecount", S_IRUSR, &proc_kpagecount_operations); + create_seq_entry("kpageflags", S_IRUSR, &proc_kpageflags_operations); +#endif #ifdef CONFIG_PROC_VMCORE proc_vmcore = create_proc_entry("vmcore", S_IRUSR, NULL); if (proc_vmcore) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 8043a3eab52..38338ed98cc 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -5,7 +5,10 @@ #include <linux/highmem.h> #include <linux/ptrace.h> #include <linux/pagemap.h> +#include <linux/ptrace.h> #include <linux/mempolicy.h> +#include <linux/swap.h> +#include <linux/swapops.h> #include <asm/elf.h> #include <asm/uaccess.h> @@ -114,24 +117,124 @@ static void pad_len_spaces(struct seq_file *m, int len) seq_printf(m, "%*c", len, ' '); } -struct mem_size_stats +static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma) { - unsigned long resident; - unsigned long shared_clean; - unsigned long shared_dirty; - unsigned long private_clean; - unsigned long private_dirty; - unsigned long referenced; -}; + if (vma && vma != priv->tail_vma) { + struct mm_struct *mm = vma->vm_mm; + up_read(&mm->mmap_sem); + mmput(mm); + } +} -struct pmd_walker { - struct vm_area_struct *vma; - void *private; - void (*action)(struct vm_area_struct *, pmd_t *, unsigned long, - unsigned long, void *); -}; +static void *m_start(struct seq_file *m, loff_t *pos) +{ + struct proc_maps_private *priv = m->private; + unsigned long last_addr = m->version; + struct mm_struct *mm; + struct vm_area_struct *vma, *tail_vma = NULL; + loff_t l = *pos; + + /* Clear the per syscall fields in priv */ + priv->task = NULL; + priv->tail_vma = NULL; + + /* + * We remember last_addr rather than next_addr to hit with + * mmap_cache most of the time. We have zero last_addr at + * the beginning and also after lseek. We will have -1 last_addr + * after the end of the vmas. + */ + + if (last_addr == -1UL) + return NULL; + + priv->task = get_pid_task(priv->pid, PIDTYPE_PID); + if (!priv->task) + return NULL; + + mm = mm_for_maps(priv->task); + if (!mm) + return NULL; + + tail_vma = get_gate_vma(priv->task); + priv->tail_vma = tail_vma; + + /* Start with last addr hint */ + vma = find_vma(mm, last_addr); + if (last_addr && vma) { + vma = vma->vm_next; + goto out; + } + + /* + * Check the vma index is within the range and do + * sequential scan until m_index. + */ + vma = NULL; + if ((unsigned long)l < mm->map_count) { + vma = mm->mmap; + while (l-- && vma) + vma = vma->vm_next; + goto out; + } + + if (l != mm->map_count) + tail_vma = NULL; /* After gate vma */ + +out: + if (vma) + return vma; + + /* End of vmas has been reached */ + m->version = (tail_vma != NULL)? 0: -1UL; + up_read(&mm->mmap_sem); + mmput(mm); + return tail_vma; +} -static int show_map_internal(struct seq_file *m, void *v, struct mem_size_stats *mss) +static void *m_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct proc_maps_private *priv = m->private; + struct vm_area_struct *vma = v; + struct vm_area_struct *tail_vma = priv->tail_vma; + + (*pos)++; + if (vma && (vma != tail_vma) && vma->vm_next) + return vma->vm_next; + vma_stop(priv, vma); + return (vma != tail_vma)? tail_vma: NULL; +} + +static void m_stop(struct seq_file *m, void *v) +{ + struct proc_maps_private *priv = m->private; + struct vm_area_struct *vma = v; + + vma_stop(priv, vma); + if (priv->task) + put_task_struct(priv->task); +} + +static int do_maps_open(struct inode *inode, struct file *file, + struct seq_operations *ops) +{ + struct proc_maps_private *priv; + int ret = -ENOMEM; + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (priv) { + priv->pid = proc_pid(inode); + ret = seq_open(file, ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = priv; + } else { + kfree(priv); + } + } + return ret; +} + +static int show_map(struct seq_file *m, void *v) { struct proc_maps_private *priv = m->private; struct task_struct *task = priv->task; @@ -191,41 +294,71 @@ static int show_map_internal(struct seq_file *m, void *v, struct mem_size_stats } seq_putc(m, '\n'); - if (mss) - seq_printf(m, - "Size: %8lu kB\n" - "Rss: %8lu kB\n" - "Shared_Clean: %8lu kB\n" - "Shared_Dirty: %8lu kB\n" - "Private_Clean: %8lu kB\n" - "Private_Dirty: %8lu kB\n" - "Referenced: %8lu kB\n", - (vma->vm_end - vma->vm_start) >> 10, - mss->resident >> 10, - mss->shared_clean >> 10, - mss->shared_dirty >> 10, - mss->private_clean >> 10, - mss->private_dirty >> 10, - mss->referenced >> 10); - if (m->count < m->size) /* vma is copied successfully */ m->version = (vma != get_gate_vma(task))? vma->vm_start: 0; return 0; } -static int show_map(struct seq_file *m, void *v) +static struct seq_operations proc_pid_maps_op = { + .start = m_start, + .next = m_next, + .stop = m_stop, + .show = show_map +}; + +static int maps_open(struct inode *inode, struct file *file) { - return show_map_internal(m, v, NULL); + return do_maps_open(inode, file, &proc_pid_maps_op); } -static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, unsigned long end, - void *private) +const struct file_operations proc_maps_operations = { + .open = maps_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; + +/* + * Proportional Set Size(PSS): my share of RSS. + * + * PSS of a process is the count of pages it has in memory, where each + * page is divided by the number of processes sharing it. So if a + * process has 1000 pages all to itself, and 1000 shared with one other + * process, its PSS will be 1500. + * + * To keep (accumulated) division errors low, we adopt a 64bit + * fixed-point pss counter to minimize division errors. So (pss >> + * PSS_SHIFT) would be the real byte count. + * + * A shift of 12 before division means (assuming 4K page size): + * - 1M 3-user-pages add up to 8KB errors; + * - supports mapcount up to 2^24, or 16M; + * - supports PSS up to 2^52 bytes, or 4PB. + */ +#define PSS_SHIFT 12 + +#ifdef CONFIG_PROC_PAGE_MONITOR +struct mem_size_stats +{ + struct vm_area_struct *vma; + unsigned long resident; + unsigned long shared_clean; + unsigned long shared_dirty; + unsigned long private_clean; + unsigned long private_dirty; + unsigned long referenced; + u64 pss; +}; + +static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, + void *private) { struct mem_size_stats *mss = private; + struct vm_area_struct *vma = mss->vma; pte_t *pte, ptent; spinlock_t *ptl; struct page *page; + int mapcount; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) { @@ -242,26 +375,88 @@ static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd, /* Accumulate the size in pages that have been accessed. */ if (pte_young(ptent) || PageReferenced(page)) mss->referenced += PAGE_SIZE; - if (page_mapcount(page) >= 2) { + mapcount = page_mapcount(page); + if (mapcount >= 2) { if (pte_dirty(ptent)) mss->shared_dirty += PAGE_SIZE; else mss->shared_clean += PAGE_SIZE; + mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount; } else { if (pte_dirty(ptent)) mss->private_dirty += PAGE_SIZE; else mss->private_clean += PAGE_SIZE; + mss->pss += (PAGE_SIZE << PSS_SHIFT); } } pte_unmap_unlock(pte - 1, ptl); cond_resched(); + return 0; } -static void clear_refs_pte_range(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, unsigned long end, - void *private) +static struct mm_walk smaps_walk = { .pmd_entry = smaps_pte_range }; + +static int show_smap(struct seq_file *m, void *v) { + struct vm_area_struct *vma = v; + struct mem_size_stats mss; + int ret; + + memset(&mss, 0, sizeof mss); + mss.vma = vma; + if (vma->vm_mm && !is_vm_hugetlb_page(vma)) + walk_page_range(vma->vm_mm, vma->vm_start, vma->vm_end, + &smaps_walk, &mss); + + ret = show_map(m, v); + if (ret) + return ret; + + seq_printf(m, + "Size: %8lu kB\n" + "Rss: %8lu kB\n" + "Pss: %8lu kB\n" + "Shared_Clean: %8lu kB\n" + "Shared_Dirty: %8lu kB\n" + "Private_Clean: %8lu kB\n" + "Private_Dirty: %8lu kB\n" + "Referenced: %8lu kB\n", + (vma->vm_end - vma->vm_start) >> 10, + mss.resident >> 10, + (unsigned long)(mss.pss >> (10 + PSS_SHIFT)), + mss.shared_clean >> 10, + mss.shared_dirty >> 10, + mss.private_clean >> 10, + mss.private_dirty >> 10, + mss.referenced >> 10); + + return ret; +} + +static struct seq_operations proc_pid_smaps_op = { + .start = m_start, + .next = m_next, + .stop = m_stop, + .show = show_smap +}; + +static int smaps_open(struct inode *inode, struct file *file) +{ + return do_maps_open(inode, file, &proc_pid_smaps_op); +} + +const struct file_operations proc_smaps_operations = { + .open = smaps_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; + +static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, + unsigned long end, void *private) +{ + struct vm_area_struct *vma = private; pte_t *pte, ptent; spinlock_t *ptl; struct page *page; @@ -282,235 +477,248 @@ static void clear_refs_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } pte_unmap_unlock(pte - 1, ptl); cond_resched(); + return 0; } -static inline void walk_pmd_range(struct pmd_walker *walker, pud_t *pud, - unsigned long addr, unsigned long end) +static struct mm_walk clear_refs_walk = { .pmd_entry = clear_refs_pte_range }; + +static ssize_t clear_refs_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) { - pmd_t *pmd; - unsigned long next; + struct task_struct *task; + char buffer[PROC_NUMBUF], *end; + struct mm_struct *mm; + struct vm_area_struct *vma; - for (pmd = pmd_offset(pud, addr); addr != end; - pmd++, addr = next) { - next = pmd_addr_end(addr, end); - if (pmd_none_or_clear_bad(pmd)) - continue; - walker->action(walker->vma, pmd, addr, next, walker->private); + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) + return -EFAULT; + if (!simple_strtol(buffer, &end, 0)) + return -EINVAL; + if (*end == '\n') + end++; + task = get_proc_task(file->f_path.dentry->d_inode); + if (!task) + return -ESRCH; + mm = get_task_mm(task); + if (mm) { + down_read(&mm->mmap_sem); + for (vma = mm->mmap; vma; vma = vma->vm_next) + if (!is_vm_hugetlb_page(vma)) + walk_page_range(mm, vma->vm_start, vma->vm_end, + &clear_refs_walk, vma); + flush_tlb_mm(mm); + up_read(&mm->mmap_sem); + mmput(mm); } + put_task_struct(task); + if (end - buffer == 0) + return -EIO; + return end - buffer; } -static inline void walk_pud_range(struct pmd_walker *walker, pgd_t *pgd, - unsigned long addr, unsigned long end) -{ - pud_t *pud; - unsigned long next; +const struct file_operations proc_clear_refs_operations = { + .write = clear_refs_write, +}; - for (pud = pud_offset(pgd, addr); addr != end; - pud++, addr = next) { - next = pud_addr_end(addr, end); - if (pud_none_or_clear_bad(pud)) - continue; - walk_pmd_range(walker, pud, addr, next); +struct pagemapread { + char __user *out, *end; +}; + +#define PM_ENTRY_BYTES sizeof(u64) +#define PM_RESERVED_BITS 3 +#define PM_RESERVED_OFFSET (64 - PM_RESERVED_BITS) +#define PM_RESERVED_MASK (((1LL<<PM_RESERVED_BITS)-1) << PM_RESERVED_OFFSET) +#define PM_SPECIAL(nr) (((nr) << PM_RESERVED_OFFSET) | PM_RESERVED_MASK) +#define PM_NOT_PRESENT PM_SPECIAL(1LL) +#define PM_SWAP PM_SPECIAL(2LL) +#define PM_END_OF_BUFFER 1 + +static int add_to_pagemap(unsigned long addr, u64 pfn, + struct pagemapread *pm) +{ + /* + * Make sure there's room in the buffer for an + * entire entry. Otherwise, only copy part of + * the pfn. + */ + if (pm->out + PM_ENTRY_BYTES >= pm->end) { + if (copy_to_user(pm->out, &pfn, pm->end - pm->out)) + return -EFAULT; + pm->out = pm->end; + return PM_END_OF_BUFFER; } + + if (put_user(pfn, pm->out)) + return -EFAULT; + pm->out += PM_ENTRY_BYTES; + return 0; } -/* - * walk_page_range - walk the page tables of a VMA with a callback - * @vma - VMA to walk - * @action - callback invoked for every bottom-level (PTE) page table - * @private - private data passed to the callback function - * - * Recursively walk the page table for the memory area in a VMA, calling - * a callback for every bottom-level (PTE) page table. - */ -static inline void walk_page_range(struct vm_area_struct *vma, - void (*action)(struct vm_area_struct *, - pmd_t *, unsigned long, - unsigned long, void *), - void *private) +static int pagemap_pte_hole(unsigned long start, unsigned long end, + void *private) { - unsigned long addr = vma->vm_start; - unsigned long end = vma->vm_end; - struct pmd_walker walker = { - .vma = vma, - .private = private, - .action = action, - }; - pgd_t *pgd; - unsigned long next; - - for (pgd = pgd_offset(vma->vm_mm, addr); addr != end; - pgd++, addr = next) { - next = pgd_addr_end(addr, end); - if (pgd_none_or_clear_bad(pgd)) - continue; - walk_pud_range(&walker, pgd, addr, next); + struct pagemapread *pm = private; + unsigned long addr; + int err = 0; + for (addr = start; addr < end; addr += PAGE_SIZE) { + err = add_to_pagemap(addr, PM_NOT_PRESENT, pm); + if (err) + break; } + return err; } -static int show_smap(struct seq_file *m, void *v) +u64 swap_pte_to_pagemap_entry(pte_t pte) { - struct vm_area_struct *vma = v; - struct mem_size_stats mss; - - memset(&mss, 0, sizeof mss); - if (vma->vm_mm && !is_vm_hugetlb_page(vma)) - walk_page_range(vma, smaps_pte_range, &mss); - return show_map_internal(m, v, &mss); + swp_entry_t e = pte_to_swp_entry(pte); + return PM_SWAP | swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT); } -void clear_refs_smap(struct mm_struct *mm) +static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, + void *private) { - struct vm_area_struct *vma; + struct pagemapread *pm = private; + pte_t *pte; + int err = 0; + + for (; addr != end; addr += PAGE_SIZE) { + u64 pfn = PM_NOT_PRESENT; + pte = pte_offset_map(pmd, addr); + if (is_swap_pte(*pte)) + pfn = swap_pte_to_pagemap_entry(*pte); + else if (pte_present(*pte)) + pfn = pte_pfn(*pte); + /* unmap so we're not in atomic when we copy to userspace */ + pte_unmap(pte); + err = add_to_pagemap(addr, pfn, pm); + if (err) + return err; + } - down_read(&mm->mmap_sem); - for (vma = mm->mmap; vma; vma = vma->vm_next) - if (vma->vm_mm && !is_vm_hugetlb_page(vma)) - walk_page_range(vma, clear_refs_pte_range, NULL); - flush_tlb_mm(mm); - up_read(&mm->mmap_sem); + cond_resched(); + + return err; } -static void *m_start(struct seq_file *m, loff_t *pos) +static struct mm_walk pagemap_walk = { + .pmd_entry = pagemap_pte_range, + .pte_hole = pagemap_pte_hole +}; + +/* + * /proc/pid/pagemap - an array mapping virtual pages to pfns + * + * For each page in the address space, this file contains one 64-bit + * entry representing the corresponding physical page frame number + * (PFN) if the page is present. If there is a swap entry for the + * physical page, then an encoding of the swap file number and the + * page's offset into the swap file are returned. If no page is + * present at all, PM_NOT_PRESENT is returned. This allows determining + * precisely which pages are mapped (or in swap) and comparing mapped + * pages between processes. + * + * Efficient users of this interface will use /proc/pid/maps to + * determine which areas of memory are actually mapped and llseek to + * skip over unmapped regions. + */ +static ssize_t pagemap_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) { - struct proc_maps_private *priv = m->private; - unsigned long last_addr = m->version; + struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode); + struct page **pages, *page; + unsigned long uaddr, uend; struct mm_struct *mm; - struct vm_area_struct *vma, *tail_vma = NULL; - loff_t l = *pos; - - /* Clear the per syscall fields in priv */ - priv->task = NULL; - priv->tail_vma = NULL; + struct pagemapread pm; + int pagecount; + int ret = -ESRCH; - /* - * We remember last_addr rather than next_addr to hit with - * mmap_cache most of the time. We have zero last_addr at - * the beginning and also after lseek. We will have -1 last_addr - * after the end of the vmas. - */ + if (!task) + goto out; - if (last_addr == -1UL) - return NULL; + ret = -EACCES; + if (!ptrace_may_attach(task)) + goto out; - priv->task = get_pid_task(priv->pid, PIDTYPE_PID); - if (!priv->task) - return NULL; + ret = -EINVAL; + /* file position must be aligned */ + if (*ppos % PM_ENTRY_BYTES) + goto out; - mm = mm_for_maps(priv->task); + ret = 0; + mm = get_task_mm(task); if (!mm) - return NULL; - - priv->tail_vma = tail_vma = get_gate_vma(priv->task); - - /* Start with last addr hint */ - if (last_addr && (vma = find_vma(mm, last_addr))) { - vma = vma->vm_next; goto out; - } - /* - * Check the vma index is within the range and do - * sequential scan until m_index. - */ - vma = NULL; - if ((unsigned long)l < mm->map_count) { - vma = mm->mmap; - while (l-- && vma) - vma = vma->vm_next; - goto out; - } + ret = -ENOMEM; + uaddr = (unsigned long)buf & PAGE_MASK; + uend = (unsigned long)(buf + count); + pagecount = (PAGE_ALIGN(uend) - uaddr) / PAGE_SIZE; + pages = kmalloc(pagecount * sizeof(struct page *), GFP_KERNEL); + if (!pages) + goto out_task; - if (l != mm->map_count) - tail_vma = NULL; /* After gate vma */ + down_read(¤t->mm->mmap_sem); + ret = get_user_pages(current, current->mm, uaddr, pagecount, + 1, 0, pages, NULL); + up_read(¤t->mm->mmap_sem); -out: - if (vma) - return vma; + if (ret < 0) + goto out_free; - /* End of vmas has been reached */ - m->version = (tail_vma != NULL)? 0: -1UL; - up_read(&mm->mmap_sem); - mmput(mm); - return tail_vma; -} + pm.out = buf; + pm.end = buf + count; -static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma) -{ - if (vma && vma != priv->tail_vma) { - struct mm_struct *mm = vma->vm_mm; - up_read(&mm->mmap_sem); - mmput(mm); + if (!ptrace_may_attach(task)) { + ret = -EIO; + } else { + unsigned long src = *ppos; + unsigned long svpfn = src / PM_ENTRY_BYTES; + unsigned long start_vaddr = svpfn << PAGE_SHIFT; + unsigned long end_vaddr = TASK_SIZE_OF(task); + + /* watch out for wraparound */ + if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT) + start_vaddr = end_vaddr; + + /* + * The odds are that this will stop walking way + * before end_vaddr, because the length of the + * user buffer is tracked in "pm", and the walk + * will stop when we hit the end of the buffer. + */ + ret = walk_page_range(mm, start_vaddr, end_vaddr, + &pagemap_walk, &pm); + if (ret == PM_END_OF_BUFFER) + ret = 0; + /* don't need mmap_sem for these, but this looks cleaner */ + *ppos += pm.out - buf; + if (!ret) + ret = pm.out - buf; } -} - -static void *m_next(struct seq_file *m, void *v, loff_t *pos) -{ - struct proc_maps_private *priv = m->private; - struct vm_area_struct *vma = v; - struct vm_area_struct *tail_vma = priv->tail_vma; - - (*pos)++; - if (vma && (vma != tail_vma) && vma->vm_next) - return vma->vm_next; - vma_stop(priv, vma); - return (vma != tail_vma)? tail_vma: NULL; -} - -static void m_stop(struct seq_file *m, void *v) -{ - struct proc_maps_private *priv = m->private; - struct vm_area_struct *vma = v; - vma_stop(priv, vma); - if (priv->task) - put_task_struct(priv->task); -} - -static struct seq_operations proc_pid_maps_op = { - .start = m_start, - .next = m_next, - .stop = m_stop, - .show = show_map -}; - -static struct seq_operations proc_pid_smaps_op = { - .start = m_start, - .next = m_next, - .stop = m_stop, - .show = show_smap -}; - -static int do_maps_open(struct inode *inode, struct file *file, - struct seq_operations *ops) -{ - struct proc_maps_private *priv; - int ret = -ENOMEM; - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (priv) { - priv->pid = proc_pid(inode); - ret = seq_open(file, ops); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = priv; - } else { - kfree(priv); - } + for (; pagecount; pagecount--) { + page = pages[pagecount-1]; + if (!PageReserved(page)) + SetPageDirty(page); + page_cache_release(page); } + mmput(mm); +out_free: + kfree(pages); +out_task: + put_task_struct(task); +out: return ret; } -static int maps_open(struct inode *inode, struct file *file) -{ - return do_maps_open(inode, file, &proc_pid_maps_op); -} - -const struct file_operations proc_maps_operations = { - .open = maps_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_private, +const struct file_operations proc_pagemap_operations = { + .llseek = mem_lseek, /* borrow this */ + .read = pagemap_read, }; +#endif /* CONFIG_PROC_PAGE_MONITOR */ #ifdef CONFIG_NUMA extern int show_numa_map(struct seq_file *m, void *v); @@ -545,15 +753,3 @@ const struct file_operations proc_numa_maps_operations = { .release = seq_release_private, }; #endif - -static int smaps_open(struct inode *inode, struct file *file) -{ - return do_maps_open(inode, file, &proc_pid_smaps_op); -} - -const struct file_operations proc_smaps_operations = { - .open = smaps_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_private, -}; diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c index 16b331dd991..f491ceb5af0 100644 --- a/fs/reiserfs/bitmap.c +++ b/fs/reiserfs/bitmap.c @@ -272,7 +272,7 @@ static inline int block_group_used(struct super_block *s, u32 id) /* If we don't have cached information on this bitmap block, we're * going to have to load it later anyway. Loading it here allows us - * to make a better decision. This favors long-term performace gain + * to make a better decision. This favors long-term performance gain * with a better on-disk layout vs. a short term gain of skipping the * read and potentially having a bad placement. */ if (info->free_count == UINT_MAX) { @@ -663,7 +663,7 @@ static inline void new_hashed_relocation(reiserfs_blocknr_hint_t * hint) /* * Relocation based on dirid, hashing them into a given bitmap block - * files. Formatted nodes are unaffected, a seperate policy covers them + * files. Formatted nodes are unaffected, a separate policy covers them */ static void dirid_groups(reiserfs_blocknr_hint_t * hint) { @@ -688,7 +688,7 @@ static void dirid_groups(reiserfs_blocknr_hint_t * hint) /* * Relocation based on oid, hashing them into a given bitmap block - * files. Formatted nodes are unaffected, a seperate policy covers them + * files. Formatted nodes are unaffected, a separate policy covers them */ static void oid_groups(reiserfs_blocknr_hint_t * hint) { diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 231fd5ccadc..195309857e6 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -2143,7 +2143,7 @@ int reiserfs_truncate_file(struct inode *p_s_inode, int update_timestamps) /* if we are not on a block boundary */ if (length) { length = blocksize - length; - zero_user_page(page, offset, length, KM_USER0); + zero_user(page, offset, length); if (buffer_mapped(bh) && bh->b_blocknr != 0) { mark_buffer_dirty(bh); } @@ -2367,7 +2367,7 @@ static int reiserfs_write_full_page(struct page *page, unlock_page(page); return 0; } - zero_user_page(page, last_offset, PAGE_CACHE_SIZE - last_offset, KM_USER0); + zero_user_segment(page, last_offset, PAGE_CACHE_SIZE); } bh = head; block = page->index << (PAGE_CACHE_SHIFT - s->s_blocksize_bits); diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c index 5e7388b32d0..740bb8c0c1a 100644 --- a/fs/reiserfs/prints.c +++ b/fs/reiserfs/prints.c @@ -575,6 +575,8 @@ void print_block(struct buffer_head *bh, ...) //int print_mode, int first, int l printk ("Block %llu contains unformatted data\n", (unsigned long long)bh->b_blocknr); + + va_end(args); } static char print_tb_buf[2048]; diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 1597f6b649e..a5bd23ce0e4 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -1084,7 +1084,7 @@ ssize_t reiserfs_listxattr(struct dentry * dentry, char *buffer, size_t size) } /* This is the implementation for the xattr plugin infrastructure */ -static struct list_head xattr_handlers = LIST_HEAD_INIT(xattr_handlers); +static LIST_HEAD(xattr_handlers); static DEFINE_RWLOCK(handler_lock); static struct reiserfs_xattr_handler *find_xattr_handler_prefix(const char diff --git a/fs/select.c b/fs/select.c index 47f47925aea..5633fe98078 100644 --- a/fs/select.c +++ b/fs/select.c @@ -739,7 +739,7 @@ asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, timeout_jiffies = -1; else #endif - timeout_jiffies = msecs_to_jiffies(timeout_msecs); + timeout_jiffies = msecs_to_jiffies(timeout_msecs) + 1; } else { /* Infinite (< 0) or no (0) timeout */ timeout_jiffies = timeout_msecs; diff --git a/fs/signalfd.c b/fs/signalfd.c index fb7f7e8034d..cb2b63ae0bf 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -27,6 +27,7 @@ #include <linux/list.h> #include <linux/anon_inodes.h> #include <linux/signalfd.h> +#include <linux/syscalls.h> struct signalfd_ctx { sigset_t sigmask; @@ -66,7 +67,7 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, BUILD_BUG_ON(sizeof(struct signalfd_siginfo) != 128); /* - * Unused memebers should be zero ... + * Unused members should be zero ... */ err = __clear_user(uinfo, sizeof(*uinfo)); diff --git a/fs/smbfs/inode.c b/fs/smbfs/inode.c index 9416ead0c7a..4e5c22ca802 100644 --- a/fs/smbfs/inode.c +++ b/fs/smbfs/inode.c @@ -500,6 +500,13 @@ static int smb_fill_super(struct super_block *sb, void *raw_data, int silent) struct smb_fattr root; int ver; void *mem; + static int warn_count; + + if (warn_count < 5) { + warn_count++; + printk(KERN_EMERG "smbfs is deprecated and will be removed" + "from the 2.6.27 kernel. Please migrate to cifs\n"); + } if (!raw_data) goto out_no_data; diff --git a/fs/smbfs/sock.c b/fs/smbfs/sock.c index e48bd8235a8..e37fe4deebd 100644 --- a/fs/smbfs/sock.c +++ b/fs/smbfs/sock.c @@ -329,9 +329,8 @@ smb_receive(struct smb_sb_info *server, struct smb_request *req) msg.msg_control = NULL; /* Dont repeat bytes and count available bufferspace */ - rlen = smb_move_iov(&p, &num, iov, req->rq_bytes_recvd); - if (req->rq_rlen < rlen) - rlen = req->rq_rlen; + rlen = min_t(int, smb_move_iov(&p, &num, iov, req->rq_bytes_recvd), + (req->rq_rlen - req->rq_bytes_recvd)); result = kernel_recvmsg(sock, &msg, p, num, rlen, flags); diff --git a/fs/timerfd.c b/fs/timerfd.c index 61983f3b107..10c80b59ec4 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -25,13 +25,15 @@ struct timerfd_ctx { struct hrtimer tmr; ktime_t tintv; wait_queue_head_t wqh; + u64 ticks; int expired; + int clockid; }; /* * This gets called when the timer event triggers. We set the "expired" * flag, but we do not re-arm the timer (in case it's necessary, - * tintv.tv64 != 0) until the timer is read. + * tintv.tv64 != 0) until the timer is accessed. */ static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr) { @@ -40,13 +42,24 @@ static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr) spin_lock_irqsave(&ctx->wqh.lock, flags); ctx->expired = 1; + ctx->ticks++; wake_up_locked(&ctx->wqh); spin_unlock_irqrestore(&ctx->wqh.lock, flags); return HRTIMER_NORESTART; } -static void timerfd_setup(struct timerfd_ctx *ctx, int clockid, int flags, +static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx) +{ + ktime_t now, remaining; + + now = ctx->tmr.base->get_time(); + remaining = ktime_sub(ctx->tmr.expires, now); + + return remaining.tv64 < 0 ? ktime_set(0, 0): remaining; +} + +static void timerfd_setup(struct timerfd_ctx *ctx, int flags, const struct itimerspec *ktmr) { enum hrtimer_mode htmode; @@ -57,8 +70,9 @@ static void timerfd_setup(struct timerfd_ctx *ctx, int clockid, int flags, texp = timespec_to_ktime(ktmr->it_value); ctx->expired = 0; + ctx->ticks = 0; ctx->tintv = timespec_to_ktime(ktmr->it_interval); - hrtimer_init(&ctx->tmr, clockid, htmode); + hrtimer_init(&ctx->tmr, ctx->clockid, htmode); ctx->tmr.expires = texp; ctx->tmr.function = timerfd_tmrproc; if (texp.tv64 != 0) @@ -83,7 +97,7 @@ static unsigned int timerfd_poll(struct file *file, poll_table *wait) poll_wait(file, &ctx->wqh, wait); spin_lock_irqsave(&ctx->wqh.lock, flags); - if (ctx->expired) + if (ctx->ticks) events |= POLLIN; spin_unlock_irqrestore(&ctx->wqh.lock, flags); @@ -102,11 +116,11 @@ static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count, return -EINVAL; spin_lock_irq(&ctx->wqh.lock); res = -EAGAIN; - if (!ctx->expired && !(file->f_flags & O_NONBLOCK)) { + if (!ctx->ticks && !(file->f_flags & O_NONBLOCK)) { __add_wait_queue(&ctx->wqh, &wait); for (res = 0;;) { set_current_state(TASK_INTERRUPTIBLE); - if (ctx->expired) { + if (ctx->ticks) { res = 0; break; } @@ -121,22 +135,21 @@ static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count, __remove_wait_queue(&ctx->wqh, &wait); __set_current_state(TASK_RUNNING); } - if (ctx->expired) { - ctx->expired = 0; - if (ctx->tintv.tv64 != 0) { + if (ctx->ticks) { + ticks = ctx->ticks; + if (ctx->expired && ctx->tintv.tv64) { /* * If tintv.tv64 != 0, this is a periodic timer that * needs to be re-armed. We avoid doing it in the timer * callback to avoid DoS attacks specifying a very * short timer period. */ - ticks = (u64) - hrtimer_forward(&ctx->tmr, - hrtimer_cb_get_time(&ctx->tmr), - ctx->tintv); + ticks += hrtimer_forward_now(&ctx->tmr, + ctx->tintv) - 1; hrtimer_restart(&ctx->tmr); - } else - ticks = 1; + } + ctx->expired = 0; + ctx->ticks = 0; } spin_unlock_irq(&ctx->wqh.lock); if (ticks) @@ -150,76 +163,132 @@ static const struct file_operations timerfd_fops = { .read = timerfd_read, }; -asmlinkage long sys_timerfd(int ufd, int clockid, int flags, - const struct itimerspec __user *utmr) +static struct file *timerfd_fget(int fd) +{ + struct file *file; + + file = fget(fd); + if (!file) + return ERR_PTR(-EBADF); + if (file->f_op != &timerfd_fops) { + fput(file); + return ERR_PTR(-EINVAL); + } + + return file; +} + +asmlinkage long sys_timerfd_create(int clockid, int flags) { - int error; + int error, ufd; struct timerfd_ctx *ctx; struct file *file; struct inode *inode; - struct itimerspec ktmr; - - if (copy_from_user(&ktmr, utmr, sizeof(ktmr))) - return -EFAULT; + if (flags) + return -EINVAL; if (clockid != CLOCK_MONOTONIC && clockid != CLOCK_REALTIME) return -EINVAL; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + init_waitqueue_head(&ctx->wqh); + ctx->clockid = clockid; + hrtimer_init(&ctx->tmr, clockid, HRTIMER_MODE_ABS); + + error = anon_inode_getfd(&ufd, &inode, &file, "[timerfd]", + &timerfd_fops, ctx); + if (error) { + kfree(ctx); + return error; + } + + return ufd; +} + +asmlinkage long sys_timerfd_settime(int ufd, int flags, + const struct itimerspec __user *utmr, + struct itimerspec __user *otmr) +{ + struct file *file; + struct timerfd_ctx *ctx; + struct itimerspec ktmr, kotmr; + + if (copy_from_user(&ktmr, utmr, sizeof(ktmr))) + return -EFAULT; + if (!timespec_valid(&ktmr.it_value) || !timespec_valid(&ktmr.it_interval)) return -EINVAL; - if (ufd == -1) { - ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); - if (!ctx) - return -ENOMEM; - - init_waitqueue_head(&ctx->wqh); - - timerfd_setup(ctx, clockid, flags, &ktmr); - - /* - * When we call this, the initialization must be complete, since - * anon_inode_getfd() will install the fd. - */ - error = anon_inode_getfd(&ufd, &inode, &file, "[timerfd]", - &timerfd_fops, ctx); - if (error) - goto err_tmrcancel; - } else { - file = fget(ufd); - if (!file) - return -EBADF; - ctx = file->private_data; - if (file->f_op != &timerfd_fops) { - fput(file); - return -EINVAL; - } - /* - * We need to stop the existing timer before reprogramming - * it to the new values. - */ - for (;;) { - spin_lock_irq(&ctx->wqh.lock); - if (hrtimer_try_to_cancel(&ctx->tmr) >= 0) - break; - spin_unlock_irq(&ctx->wqh.lock); - cpu_relax(); - } - /* - * Re-program the timer to the new value ... - */ - timerfd_setup(ctx, clockid, flags, &ktmr); + file = timerfd_fget(ufd); + if (IS_ERR(file)) + return PTR_ERR(file); + ctx = file->private_data; + /* + * We need to stop the existing timer before reprogramming + * it to the new values. + */ + for (;;) { + spin_lock_irq(&ctx->wqh.lock); + if (hrtimer_try_to_cancel(&ctx->tmr) >= 0) + break; spin_unlock_irq(&ctx->wqh.lock); - fput(file); + cpu_relax(); } - return ufd; + /* + * If the timer is expired and it's periodic, we need to advance it + * because the caller may want to know the previous expiration time. + * We do not update "ticks" and "expired" since the timer will be + * re-programmed again in the following timerfd_setup() call. + */ + if (ctx->expired && ctx->tintv.tv64) + hrtimer_forward_now(&ctx->tmr, ctx->tintv); -err_tmrcancel: - hrtimer_cancel(&ctx->tmr); - kfree(ctx); - return error; + kotmr.it_value = ktime_to_timespec(timerfd_get_remaining(ctx)); + kotmr.it_interval = ktime_to_timespec(ctx->tintv); + + /* + * Re-program the timer to the new value ... + */ + timerfd_setup(ctx, flags, &ktmr); + + spin_unlock_irq(&ctx->wqh.lock); + fput(file); + if (otmr && copy_to_user(otmr, &kotmr, sizeof(kotmr))) + return -EFAULT; + + return 0; +} + +asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr) +{ + struct file *file; + struct timerfd_ctx *ctx; + struct itimerspec kotmr; + + file = timerfd_fget(ufd); + if (IS_ERR(file)) + return PTR_ERR(file); + ctx = file->private_data; + + spin_lock_irq(&ctx->wqh.lock); + if (ctx->expired && ctx->tintv.tv64) { + ctx->expired = 0; + ctx->ticks += + hrtimer_forward_now(&ctx->tmr, ctx->tintv) - 1; + hrtimer_restart(&ctx->tmr); + } + kotmr.it_value = ktime_to_timespec(timerfd_get_remaining(ctx)); + kotmr.it_interval = ktime_to_timespec(ctx->tintv); + spin_unlock_irq(&ctx->wqh.lock); + fput(file); + + return copy_to_user(otmr, &kotmr, sizeof(kotmr)) ? -EFAULT: 0; } diff --git a/fs/utimes.c b/fs/utimes.c index b9912ecbee2..e5588cd8530 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -6,6 +6,7 @@ #include <linux/sched.h> #include <linux/stat.h> #include <linux/utime.h> +#include <linux/syscalls.h> #include <asm/uaccess.h> #include <asm/unistd.h> diff --git a/fs/xattr.c b/fs/xattr.c index 6645b7313b3..f7c8f87bb39 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -105,6 +105,33 @@ out: EXPORT_SYMBOL_GPL(vfs_setxattr); ssize_t +xattr_getsecurity(struct inode *inode, const char *name, void *value, + size_t size) +{ + void *buffer = NULL; + ssize_t len; + + if (!value || !size) { + len = security_inode_getsecurity(inode, name, &buffer, false); + goto out_noalloc; + } + + len = security_inode_getsecurity(inode, name, &buffer, true); + if (len < 0) + return len; + if (size < len) { + len = -ERANGE; + goto out; + } + memcpy(value, buffer, len); +out: + security_release_secctx(buffer, len); +out_noalloc: + return len; +} +EXPORT_SYMBOL_GPL(xattr_getsecurity); + +ssize_t vfs_getxattr(struct dentry *dentry, char *name, void *value, size_t size) { struct inode *inode = dentry->d_inode; @@ -118,23 +145,23 @@ vfs_getxattr(struct dentry *dentry, char *name, void *value, size_t size) if (error) return error; - if (inode->i_op->getxattr) - error = inode->i_op->getxattr(dentry, name, value, size); - else - error = -EOPNOTSUPP; - if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) { const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; - int ret = security_inode_getsecurity(inode, suffix, value, - size, error); + int ret = xattr_getsecurity(inode, suffix, value, size); /* * Only overwrite the return value if a security module * is actually active. */ - if (ret != -EOPNOTSUPP) - error = ret; + if (ret == -EOPNOTSUPP) + goto nolsm; + return ret; } +nolsm: + if (inode->i_op->getxattr) + error = inode->i_op->getxattr(dentry, name, value, size); + else + error = -EOPNOTSUPP; return error; } diff --git a/fs/xfs/linux-2.6/kmem.c b/fs/xfs/linux-2.6/kmem.c index ed2b16dff91..e040f1ce1b6 100644 --- a/fs/xfs/linux-2.6/kmem.c +++ b/fs/xfs/linux-2.6/kmem.c @@ -92,8 +92,7 @@ kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize, void kmem_free(void *ptr, size_t size) { - if (((unsigned long)ptr < VMALLOC_START) || - ((unsigned long)ptr >= VMALLOC_END)) { + if (!is_vmalloc_addr(ptr)) { kfree(ptr); } else { vfree(ptr); diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index a49dd8d4b06..0382c19d652 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -709,8 +709,7 @@ static inline struct page * mem_to_page( void *addr) { - if (((unsigned long)addr < VMALLOC_START) || - ((unsigned long)addr >= VMALLOC_END)) { + if ((!is_vmalloc_addr(addr))) { return virt_to_page(addr); } else { return vmalloc_to_page(addr); diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c index d6a8dddb226..6f614f35f65 100644 --- a/fs/xfs/linux-2.6/xfs_lrw.c +++ b/fs/xfs/linux-2.6/xfs_lrw.c @@ -155,7 +155,7 @@ xfs_iozero( if (status) break; - zero_user_page(page, offset, bytes, KM_USER0); + zero_user(page, offset, bytes); status = pagecache_write_end(NULL, mapping, pos, bytes, bytes, page, fsdata); |