diff options
Diffstat (limited to 'fs')
67 files changed, 702 insertions, 338 deletions
diff --git a/fs/Makefile b/fs/Makefile index 6e82a307bcd4..b5cd8e18dd9f 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -11,7 +11,7 @@ obj-y := open.o read_write.o file_table.o super.o \ attr.o bad_inode.o file.o filesystems.o namespace.o \ seq_file.o xattr.o libfs.o fs-writeback.o \ pnode.o drop_caches.o splice.o sync.o utimes.o \ - stack.o + stack.o fs_struct.o ifeq ($(CONFIG_BLOCK),y) obj-y += buffer.o bio.o block_dev.o direct-io.o mpage.o ioprio.o diff --git a/fs/adfs/super.c b/fs/adfs/super.c index 7f83a46f2b7e..dd9becca4241 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -219,16 +219,20 @@ static int adfs_remount(struct super_block *sb, int *flags, char *data) static int adfs_statfs(struct dentry *dentry, struct kstatfs *buf) { - struct adfs_sb_info *asb = ADFS_SB(dentry->d_sb); + struct super_block *sb = dentry->d_sb; + struct adfs_sb_info *sbi = ADFS_SB(sb); + u64 id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = ADFS_SUPER_MAGIC; - buf->f_namelen = asb->s_namelen; - buf->f_bsize = dentry->d_sb->s_blocksize; - buf->f_blocks = asb->s_size; - buf->f_files = asb->s_ids_per_zone * asb->s_map_size; + buf->f_namelen = sbi->s_namelen; + buf->f_bsize = sb->s_blocksize; + buf->f_blocks = sbi->s_size; + buf->f_files = sbi->s_ids_per_zone * sbi->s_map_size; buf->f_bavail = - buf->f_bfree = adfs_map_free(dentry->d_sb); + buf->f_bfree = adfs_map_free(sb); buf->f_ffree = (long)(buf->f_bfree * buf->f_files) / (long)buf->f_blocks; + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); return 0; } diff --git a/fs/affs/super.c b/fs/affs/super.c index a19d64b582aa..5ce695e707fe 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -533,6 +533,7 @@ affs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; int free; + u64 id = huge_encode_dev(sb->s_bdev->bd_dev); pr_debug("AFFS: statfs() partsize=%d, reserved=%d\n",AFFS_SB(sb)->s_partition_size, AFFS_SB(sb)->s_reserved); @@ -543,6 +544,9 @@ affs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_blocks = AFFS_SB(sb)->s_partition_size - AFFS_SB(sb)->s_reserved; buf->f_bfree = free; buf->f_bavail = free; + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); + buf->f_namelen = 30; return 0; } diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index d06cb023ad02..76afd0d6b86c 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -900,6 +900,7 @@ static int befs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; + u64 id = huge_encode_dev(sb->s_bdev->bd_dev); befs_debug(sb, "---> befs_statfs()"); @@ -910,6 +911,8 @@ befs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bavail = buf->f_bfree; buf->f_files = 0; /* UNKNOWN */ buf->f_ffree = 0; /* UNKNOWN */ + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); buf->f_namelen = BEFS_NAME_LEN; befs_debug(sb, "<--- befs_statfs()"); diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 33b7235f853b..40381df34869 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -12,8 +12,6 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/fs.h> -#include <linux/stat.h> -#include <linux/time.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/errno.h> @@ -21,20 +19,15 @@ #include <linux/binfmts.h> #include <linux/string.h> #include <linux/file.h> -#include <linux/fcntl.h> -#include <linux/ptrace.h> #include <linux/slab.h> -#include <linux/shm.h> #include <linux/personality.h> #include <linux/elfcore.h> #include <linux/init.h> #include <linux/highuid.h> -#include <linux/smp.h> #include <linux/compiler.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/security.h> -#include <linux/syscalls.h> #include <linux/random.h> #include <linux/elf.h> #include <linux/utsname.h> @@ -576,7 +569,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) unsigned long error; struct elf_phdr *elf_ppnt, *elf_phdata; unsigned long elf_bss, elf_brk; - int elf_exec_fileno; int retval, i; unsigned int size; unsigned long elf_entry; @@ -631,12 +623,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) goto out_free_ph; } - retval = get_unused_fd(); - if (retval < 0) - goto out_free_ph; - get_file(bprm->file); - fd_install(elf_exec_fileno = retval, bprm->file); - elf_ppnt = elf_phdata; elf_bss = 0; elf_brk = 0; @@ -655,13 +641,13 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) retval = -ENOEXEC; if (elf_ppnt->p_filesz > PATH_MAX || elf_ppnt->p_filesz < 2) - goto out_free_file; + goto out_free_ph; retval = -ENOMEM; elf_interpreter = kmalloc(elf_ppnt->p_filesz, GFP_KERNEL); if (!elf_interpreter) - goto out_free_file; + goto out_free_ph; retval = kernel_read(bprm->file, elf_ppnt->p_offset, elf_interpreter, @@ -956,8 +942,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) kfree(elf_phdata); - sys_close(elf_exec_fileno); - set_binfmt(&elf_format); #ifdef ARCH_HAS_SETUP_ADDITIONAL_PAGES @@ -1028,8 +1012,6 @@ out_free_dentry: fput(interpreter); out_free_interp: kfree(elf_interpreter); -out_free_file: - sys_close(elf_exec_fileno); out_free_ph: kfree(elf_phdata); goto out; diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index f3e72c5c19f5..70cfc4b84ae0 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -972,9 +972,12 @@ static int elf_fdpic_map_file_constdisp_on_uclinux( params->elfhdr_addr = seg->addr; /* clear any space allocated but not loaded */ - if (phdr->p_filesz < phdr->p_memsz) - clear_user((void *) (seg->addr + phdr->p_filesz), - phdr->p_memsz - phdr->p_filesz); + if (phdr->p_filesz < phdr->p_memsz) { + ret = clear_user((void *) (seg->addr + phdr->p_filesz), + phdr->p_memsz - phdr->p_filesz); + if (ret) + return ret; + } if (mm) { if (phdr->p_flags & PF_X) { @@ -1014,7 +1017,7 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params, struct elf32_fdpic_loadseg *seg; struct elf32_phdr *phdr; unsigned long load_addr, delta_vaddr; - int loop, dvset; + int loop, dvset, ret; load_addr = params->load_addr; delta_vaddr = 0; @@ -1114,7 +1117,9 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params, * PT_LOAD */ if (prot & PROT_WRITE && disp > 0) { kdebug("clear[%d] ad=%lx sz=%lx", loop, maddr, disp); - clear_user((void __user *) maddr, disp); + ret = clear_user((void __user *) maddr, disp); + if (ret) + return ret; maddr += disp; } @@ -1149,15 +1154,19 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params, if (prot & PROT_WRITE && excess1 > 0) { kdebug("clear[%d] ad=%lx sz=%lx", loop, maddr + phdr->p_filesz, excess1); - clear_user((void __user *) maddr + phdr->p_filesz, - excess1); + ret = clear_user((void __user *) maddr + phdr->p_filesz, + excess1); + if (ret) + return ret; } #else if (excess > 0) { kdebug("clear[%d] ad=%lx sz=%lx", loop, maddr + phdr->p_filesz, excess); - clear_user((void *) maddr + phdr->p_filesz, excess); + ret = clear_user((void *) maddr + phdr->p_filesz, excess); + if (ret) + return ret; } #endif diff --git a/fs/binfmt_som.c b/fs/binfmt_som.c index 08644a61616e..eff74b9c9e77 100644 --- a/fs/binfmt_som.c +++ b/fs/binfmt_som.c @@ -188,7 +188,6 @@ out: static int load_som_binary(struct linux_binprm * bprm, struct pt_regs * regs) { - int som_exec_fileno; int retval; unsigned int size; unsigned long som_entry; @@ -220,12 +219,6 @@ load_som_binary(struct linux_binprm * bprm, struct pt_regs * regs) goto out_free; } - retval = get_unused_fd(); - if (retval < 0) - goto out_free; - get_file(bprm->file); - fd_install(som_exec_fileno = retval, bprm->file); - /* Flush all traces of the currently running executable */ retval = flush_old_exec(bprm); if (retval) diff --git a/fs/block_dev.c b/fs/block_dev.c index 8c3c6899ccf3..f45dbc18dd17 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -204,6 +204,7 @@ int fsync_bdev(struct block_device *bdev) } return sync_blockdev(bdev); } +EXPORT_SYMBOL(fsync_bdev); /** * freeze_bdev -- lock a filesystem and force it into a consistent state diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 1d53b62dbba5..7fdd184a528d 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -256,7 +256,7 @@ int btrfs_init_acl(struct inode *inode, struct inode *dir) } if (!acl) - inode->i_mode &= ~current->fs->umask; + inode->i_mode &= ~current_umask(); } if (IS_POSIXACL(dir) && acl) { diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index bca729fc80c8..7594bec1be10 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -267,7 +267,7 @@ static noinline int btrfs_mksubvol(struct path *parent, char *name, goto out_dput; if (!IS_POSIXACL(parent->dentry->d_inode)) - mode &= ~current->fs->umask; + mode &= ~current_umask(); error = mnt_want_write(parent->mnt); if (error) diff --git a/fs/buffer.c b/fs/buffer.c index f5f8b15a6e40..c2fa1be4923d 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -199,13 +199,13 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) head = page_buffers(page); bh = head; do { - if (bh->b_blocknr == block) { + if (!buffer_mapped(bh)) + all_mapped = 0; + else if (bh->b_blocknr == block) { ret = bh; get_bh(bh); goto out_unlock; } - if (!buffer_mapped(bh)) - all_mapped = 0; bh = bh->b_this_page; } while (bh != head); @@ -3315,7 +3315,6 @@ EXPORT_SYMBOL(cont_write_begin); EXPORT_SYMBOL(end_buffer_read_sync); EXPORT_SYMBOL(end_buffer_write_sync); EXPORT_SYMBOL(file_fsync); -EXPORT_SYMBOL(fsync_bdev); EXPORT_SYMBOL(generic_block_bmap); EXPORT_SYMBOL(generic_cont_expand_simple); EXPORT_SYMBOL(init_buffer); diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 2f35cccfcd8d..54dce78fbb73 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -254,7 +254,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, return -ENOMEM; } - mode &= ~current->fs->umask; + mode &= ~current_umask(); if (oplockEnabled) oplock = REQ_OPLOCK; @@ -479,7 +479,7 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode, rc = -ENOMEM; else if (pTcon->unix_ext) { struct cifs_unix_set_info_args args = { - .mode = mode & ~current->fs->umask, + .mode = mode & ~current_umask(), .ctime = NO_CHANGE_64, .atime = NO_CHANGE_64, .mtime = NO_CHANGE_64, diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index a8797cc60805..f121a80fdd6f 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1125,7 +1125,7 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode) goto mkdir_out; } - mode &= ~current->fs->umask; + mode &= ~current_umask(); rc = CIFSPOSIXCreate(xid, pTcon, SMB_O_DIRECTORY | SMB_O_CREAT, mode, NULL /* netfid */, pInfo, &oplock, full_path, cifs_sb->local_nls, @@ -1204,7 +1204,7 @@ mkdir_get_info: if ((direntry->d_inode) && (direntry->d_inode->i_nlink < 2)) direntry->d_inode->i_nlink = 2; - mode &= ~current->fs->umask; + mode &= ~current_umask(); /* must turn on setgid bit if parent dir has it */ if (inode->i_mode & S_ISGID) mode |= S_ISGID; diff --git a/fs/compat.c b/fs/compat.c index 55efdfebdf5a..1c859dae758f 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -51,6 +51,7 @@ #include <linux/poll.h> #include <linux/mm.h> #include <linux/eventpoll.h> +#include <linux/fs_struct.h> #include <asm/uaccess.h> #include <asm/mmu_context.h> @@ -1195,16 +1196,12 @@ out: return ret; } -asmlinkage ssize_t -compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen) +static size_t compat_readv(struct file *file, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t *pos) { - struct file *file; ssize_t ret = -EBADF; - file = fget(fd); - if (!file) - return -EBADF; - if (!(file->f_mode & FMODE_READ)) goto out; @@ -1212,25 +1209,56 @@ compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsign if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read)) goto out; - ret = compat_do_readv_writev(READ, file, vec, vlen, &file->f_pos); + ret = compat_do_readv_writev(READ, file, vec, vlen, pos); out: if (ret > 0) add_rchar(current, ret); inc_syscr(current); - fput(file); return ret; } asmlinkage ssize_t -compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen) +compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, + unsigned long vlen) { struct file *file; - ssize_t ret = -EBADF; + int fput_needed; + ssize_t ret; - file = fget(fd); + file = fget_light(fd, &fput_needed); if (!file) return -EBADF; + ret = compat_readv(file, vec, vlen, &file->f_pos); + fput_light(file, fput_needed); + return ret; +} + +asmlinkage ssize_t +compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low) +{ + loff_t pos = ((loff_t)pos_high << 32) | pos_low; + struct file *file; + int fput_needed; + ssize_t ret; + + if (pos < 0) + return -EINVAL; + file = fget_light(fd, &fput_needed); + if (!file) + return -EBADF; + ret = compat_readv(file, vec, vlen, &pos); + fput_light(file, fput_needed); + return ret; +} + +static size_t compat_writev(struct file *file, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t *pos) +{ + ssize_t ret = -EBADF; + if (!(file->f_mode & FMODE_WRITE)) goto out; @@ -1238,13 +1266,47 @@ compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsig if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write)) goto out; - ret = compat_do_readv_writev(WRITE, file, vec, vlen, &file->f_pos); + ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos); out: if (ret > 0) add_wchar(current, ret); inc_syscw(current); - fput(file); + return ret; +} + +asmlinkage ssize_t +compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, + unsigned long vlen) +{ + struct file *file; + int fput_needed; + ssize_t ret; + + file = fget_light(fd, &fput_needed); + if (!file) + return -EBADF; + ret = compat_writev(file, vec, vlen, &file->f_pos); + fput_light(file, fput_needed); + return ret; +} + +asmlinkage ssize_t +compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low) +{ + loff_t pos = ((loff_t)pos_high << 32) | pos_low; + struct file *file; + int fput_needed; + ssize_t ret; + + if (pos < 0) + return -EINVAL; + file = fget_light(fd, &fput_needed); + if (!file) + return -EBADF; + ret = compat_writev(file, vec, vlen, &pos); + fput_light(file, fput_needed); return ret; } @@ -1441,12 +1503,15 @@ int compat_do_execve(char * filename, bprm->cred = prepare_exec_creds(); if (!bprm->cred) goto out_unlock; - check_unsafe_exec(bprm); + + retval = check_unsafe_exec(bprm); + if (retval) + goto out_unlock; file = open_exec(filename); retval = PTR_ERR(file); if (IS_ERR(file)) - goto out_unlock; + goto out_unmark; sched_exec(); @@ -1488,6 +1553,9 @@ int compat_do_execve(char * filename, goto out; /* execve succeeded */ + write_lock(¤t->fs->lock); + current->fs->in_exec = 0; + write_unlock(¤t->fs->lock); current->in_execve = 0; mutex_unlock(¤t->cred_exec_mutex); acct_update_integrals(current); @@ -1506,6 +1574,11 @@ out_file: fput(bprm->file); } +out_unmark: + write_lock(¤t->fs->lock); + current->fs->in_exec = 0; + write_unlock(¤t->fs->lock); + out_unlock: current->in_execve = 0; mutex_unlock(¤t->cred_exec_mutex); diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index ff786687e93b..3e87ce443ea2 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -23,7 +23,7 @@ #include <linux/if.h> #include <linux/if_bridge.h> #include <linux/slab.h> -#include <linux/raid/md.h> +#include <linux/raid/md_u.h> #include <linux/kd.h> #include <linux/route.h> #include <linux/in6.h> diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index a07338d2d140..dd3634e4c967 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -318,6 +318,7 @@ out: static int cramfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; + u64 id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = CRAMFS_MAGIC; buf->f_bsize = PAGE_CACHE_SIZE; @@ -326,6 +327,8 @@ static int cramfs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bavail = 0; buf->f_files = CRAMFS_SB(sb)->files; buf->f_ffree = 0; + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); buf->f_namelen = CRAMFS_MAXPATHLEN; return 0; } @@ -459,11 +462,14 @@ static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, s static int cramfs_readpage(struct file *file, struct page * page) { struct inode *inode = page->mapping->host; - u32 maxblock, bytes_filled; + u32 maxblock; + int bytes_filled; void *pgdata; maxblock = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; bytes_filled = 0; + pgdata = kmap(page); + if (page->index < maxblock) { struct super_block *sb = inode->i_sb; u32 blkptr_offset = OFFSET(inode) + page->index*4; @@ -472,30 +478,43 @@ static int cramfs_readpage(struct file *file, struct page * page) start_offset = OFFSET(inode) + maxblock*4; mutex_lock(&read_mutex); if (page->index) - start_offset = *(u32 *) cramfs_read(sb, blkptr_offset-4, 4); - compr_len = (*(u32 *) cramfs_read(sb, blkptr_offset, 4) - start_offset); + start_offset = *(u32 *) cramfs_read(sb, blkptr_offset-4, + 4); + compr_len = (*(u32 *) cramfs_read(sb, blkptr_offset, 4) - + start_offset); mutex_unlock(&read_mutex); - pgdata = kmap(page); + if (compr_len == 0) ; /* hole */ - else if (compr_len > (PAGE_CACHE_SIZE << 1)) - printk(KERN_ERR "cramfs: bad compressed blocksize %u\n", compr_len); - else { + else if (unlikely(compr_len > (PAGE_CACHE_SIZE << 1))) { + pr_err("cramfs: bad compressed blocksize %u\n", + compr_len); + goto err; + } else { mutex_lock(&read_mutex); bytes_filled = cramfs_uncompress_block(pgdata, PAGE_CACHE_SIZE, cramfs_read(sb, start_offset, compr_len), compr_len); mutex_unlock(&read_mutex); + if (unlikely(bytes_filled < 0)) + goto err; } - } else - pgdata = kmap(page); + } + memset(pgdata + bytes_filled, 0, PAGE_CACHE_SIZE - bytes_filled); - kunmap(page); flush_dcache_page(page); + kunmap(page); SetPageUptodate(page); unlock_page(page); return 0; + +err: + kunmap(page); + ClearPageUptodate(page); + SetPageError(page); + unlock_page(page); + return 0; } static const struct address_space_operations cramfs_aops = { diff --git a/fs/cramfs/uncompress.c b/fs/cramfs/uncompress.c index fc3ccb74626f..023329800d2e 100644 --- a/fs/cramfs/uncompress.c +++ b/fs/cramfs/uncompress.c @@ -50,7 +50,7 @@ int cramfs_uncompress_block(void *dst, int dstlen, void *src, int srclen) err: printk("Error %d while decompressing!\n", err); printk("%p(%d)->%p(%d)\n", src, srclen, dst, dstlen); - return 0; + return -EIO; } int cramfs_uncompress_init(void) diff --git a/fs/dcache.c b/fs/dcache.c index 90bbd7e1b116..761d30be2683 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -17,7 +17,6 @@ #include <linux/syscalls.h> #include <linux/string.h> #include <linux/mm.h> -#include <linux/fdtable.h> #include <linux/fs.h> #include <linux/fsnotify.h> #include <linux/slab.h> @@ -32,6 +31,7 @@ #include <linux/seqlock.h> #include <linux/swap.h> #include <linux/bootmem.h> +#include <linux/fs_struct.h> #include "internal.h" int sysctl_vfs_cache_pressure __read_mostly = 100; diff --git a/fs/drop_caches.c b/fs/drop_caches.c index 44d725f612cf..b6a719a909f8 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -18,7 +18,7 @@ static void drop_pagecache_sb(struct super_block *sb) spin_lock(&inode_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { - if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) + if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW)) continue; if (inode->i_mapping->nrpages == 0) continue; diff --git a/fs/efs/super.c b/fs/efs/super.c index 73b19cfc91fc..f04942810818 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -329,18 +329,22 @@ out_no_fs: } static int efs_statfs(struct dentry *dentry, struct kstatfs *buf) { - struct efs_sb_info *sb = SUPER_INFO(dentry->d_sb); + struct super_block *sb = dentry->d_sb; + struct efs_sb_info *sbi = SUPER_INFO(sb); + u64 id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = EFS_SUPER_MAGIC; /* efs magic number */ buf->f_bsize = EFS_BLOCKSIZE; /* blocksize */ - buf->f_blocks = sb->total_groups * /* total data blocks */ - (sb->group_size - sb->inode_blocks); - buf->f_bfree = sb->data_free; /* free data blocks */ - buf->f_bavail = sb->data_free; /* free blocks for non-root */ - buf->f_files = sb->total_groups * /* total inodes */ - sb->inode_blocks * + buf->f_blocks = sbi->total_groups * /* total data blocks */ + (sbi->group_size - sbi->inode_blocks); + buf->f_bfree = sbi->data_free; /* free data blocks */ + buf->f_bavail = sbi->data_free; /* free blocks for non-root */ + buf->f_files = sbi->total_groups * /* total inodes */ + sbi->inode_blocks * (EFS_BLOCKSIZE / sizeof(struct efs_dinode)); - buf->f_ffree = sb->inode_free; /* free inodes */ + buf->f_ffree = sbi->inode_free; /* free inodes */ + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); buf->f_namelen = EFS_MAXNAMELEN; /* max filename length */ return 0; diff --git a/fs/exec.c b/fs/exec.c index c5128fbc9165..052a961e41aa 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -53,6 +53,7 @@ #include <linux/tracehook.h> #include <linux/kmod.h> #include <linux/fsnotify.h> +#include <linux/fs_struct.h> #include <asm/uaccess.h> #include <asm/mmu_context.h> @@ -1056,28 +1057,35 @@ EXPORT_SYMBOL(install_exec_creds); * - the caller must hold current->cred_exec_mutex to protect against * PTRACE_ATTACH */ -void check_unsafe_exec(struct linux_binprm *bprm) +int check_unsafe_exec(struct linux_binprm *bprm) { struct task_struct *p = current, *t; unsigned long flags; - unsigned n_fs, n_sighand; + unsigned n_fs; + int res = 0; bprm->unsafe = tracehook_unsafe_exec(p); n_fs = 1; - n_sighand = 1; + write_lock(&p->fs->lock); lock_task_sighand(p, &flags); for (t = next_thread(p); t != p; t = next_thread(t)) { if (t->fs == p->fs) n_fs++; - n_sighand++; } - if (atomic_read(&p->fs->count) > n_fs || - atomic_read(&p->sighand->count) > n_sighand) + if (p->fs->users > n_fs) { bprm->unsafe |= LSM_UNSAFE_SHARE; + } else { + if (p->fs->in_exec) + res = -EAGAIN; + p->fs->in_exec = 1; + } unlock_task_sighand(p, &flags); + write_unlock(&p->fs->lock); + + return res; } /* @@ -1296,12 +1304,15 @@ int do_execve(char * filename, bprm->cred = prepare_exec_creds(); if (!bprm->cred) goto out_unlock; - check_unsafe_exec(bprm); + + retval = check_unsafe_exec(bprm); + if (retval) + goto out_unlock; file = open_exec(filename); retval = PTR_ERR(file); if (IS_ERR(file)) - goto out_unlock; + goto out_unmark; sched_exec(); @@ -1344,6 +1355,9 @@ int do_execve(char * filename, goto out; /* execve succeeded */ + write_lock(¤t->fs->lock); + current->fs->in_exec = 0; + write_unlock(¤t->fs->lock); current->in_execve = 0; mutex_unlock(¤t->cred_exec_mutex); acct_update_integrals(current); @@ -1362,6 +1376,11 @@ out_file: fput(bprm->file); } +out_unmark: + write_lock(¤t->fs->lock); + current->fs->in_exec = 0; + write_unlock(¤t->fs->lock); + out_unlock: current->in_execve = 0; mutex_unlock(¤t->cred_exec_mutex); diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index ae8c4f850b27..d46e38cb85c5 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -318,7 +318,7 @@ ext2_init_acl(struct inode *inode, struct inode *dir) return PTR_ERR(acl); } if (!acl) - inode->i_mode &= ~current->fs->umask; + inode->i_mode &= ~current_umask(); } if (test_opt(inode->i_sb, POSIX_ACL) && acl) { struct posix_acl *clone; diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c index b60bb241880c..d81ef2fdb08e 100644 --- a/fs/ext3/acl.c +++ b/fs/ext3/acl.c @@ -323,7 +323,7 @@ ext3_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) return PTR_ERR(acl); } if (!acl) - inode->i_mode &= ~current->fs->umask; + inode->i_mode &= ~current_umask(); } if (test_opt(inode->i_sb, POSIX_ACL) && acl) { struct posix_acl *clone; diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c index 5853f4440af4..3d724a95882f 100644 --- a/fs/ext3/dir.c +++ b/fs/ext3/dir.c @@ -42,7 +42,7 @@ const struct file_operations ext3_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .readdir = ext3_readdir, /* we take BKL. needed?*/ - .ioctl = ext3_ioctl, /* BKL held */ + .unlocked_ioctl = ext3_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext3_compat_ioctl, #endif diff --git a/fs/ext3/file.c b/fs/ext3/file.c index 3be1e0689c9a..521f8238b2fa 100644 --- a/fs/ext3/file.c +++ b/fs/ext3/file.c @@ -112,7 +112,7 @@ const struct file_operations ext3_file_operations = { .write = do_sync_write, .aio_read = generic_file_aio_read, .aio_write = ext3_file_write, - .ioctl = ext3_ioctl, + .unlocked_ioctl = ext3_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext3_compat_ioctl, #endif diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 4a09ff169870..d3ef6566b019 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1149,12 +1149,15 @@ static int ext3_write_begin(struct file *file, struct address_space *mapping, struct page **pagep, void **fsdata) { struct inode *inode = mapping->host; - int ret, needed_blocks = ext3_writepage_trans_blocks(inode); + int ret; handle_t *handle; int retries = 0; struct page *page; pgoff_t index; unsigned from, to; + /* Reserve one block more for addition to orphan list in case + * we allocate blocks but write fails for some reason */ + int needed_blocks = ext3_writepage_trans_blocks(inode) + 1; index = pos >> PAGE_CACHE_SHIFT; from = pos & (PAGE_CACHE_SIZE - 1); @@ -1184,15 +1187,20 @@ retry: } write_begin_failed: if (ret) { - ext3_journal_stop(handle); - unlock_page(page); - page_cache_release(page); /* * block_write_begin may have instantiated a few blocks * outside i_size. Trim these off again. Don't need * i_size_read because we hold i_mutex. + * + * Add inode to orphan list in case we crash before truncate + * finishes. */ if (pos + len > inode->i_size) + ext3_orphan_add(handle, inode); + ext3_journal_stop(handle); + unlock_page(page); + page_cache_release(page); + if (pos + len > inode->i_size) vmtruncate(inode, inode->i_size); } if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries)) @@ -1211,6 +1219,18 @@ int ext3_journal_dirty_data(handle_t *handle, struct buffer_head *bh) return err; } +/* For ordered writepage and write_end functions */ +static int journal_dirty_data_fn(handle_t *handle, struct buffer_head *bh) +{ + /* + * Write could have mapped the buffer but it didn't copy the data in + * yet. So avoid filing such buffer into a transaction. + */ + if (buffer_mapped(bh) && buffer_uptodate(bh)) + return ext3_journal_dirty_data(handle, bh); + return 0; +} + /* For write_end() in data=journal mode */ static int write_end_fn(handle_t *handle, struct buffer_head *bh) { @@ -1221,26 +1241,20 @@ static int write_end_fn(handle_t *handle, struct buffer_head *bh) } /* - * Generic write_end handler for ordered and writeback ext3 journal modes. - * We can't use generic_write_end, because that unlocks the page and we need to - * unlock the page after ext3_journal_stop, but ext3_journal_stop must run - * after block_write_end. + * This is nasty and subtle: ext3_write_begin() could have allocated blocks + * for the whole page but later we failed to copy the data in. Update inode + * size according to what we managed to copy. The rest is going to be + * truncated in write_end function. */ -static int ext3_generic_write_end(struct file *file, - struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) +static void update_file_sizes(struct inode *inode, loff_t pos, unsigned copied) { - struct inode *inode = file->f_mapping->host; - - copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); - - if (pos+copied > inode->i_size) { - i_size_write(inode, pos+copied); + /* What matters to us is i_disksize. We don't write i_size anywhere */ + if (pos + copied > inode->i_size) + i_size_write(inode, pos + copied); + if (pos + copied > EXT3_I(inode)->i_disksize) { + EXT3_I(inode)->i_disksize = pos + copied; mark_inode_dirty(inode); } - - return copied; } /* @@ -1260,35 +1274,29 @@ static int ext3_ordered_write_end(struct file *file, unsigned from, to; int ret = 0, ret2; - from = pos & (PAGE_CACHE_SIZE - 1); - to = from + len; + copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); + from = pos & (PAGE_CACHE_SIZE - 1); + to = from + copied; ret = walk_page_buffers(handle, page_buffers(page), - from, to, NULL, ext3_journal_dirty_data); + from, to, NULL, journal_dirty_data_fn); - if (ret == 0) { - /* - * generic_write_end() will run mark_inode_dirty() if i_size - * changes. So let's piggyback the i_disksize mark_inode_dirty - * into that. - */ - loff_t new_i_size; - - new_i_size = pos + copied; - if (new_i_size > EXT3_I(inode)->i_disksize) - EXT3_I(inode)->i_disksize = new_i_size; - ret2 = ext3_generic_write_end(file, mapping, pos, len, copied, - page, fsdata); - copied = ret2; - if (ret2 < 0) - ret = ret2; - } + if (ret == 0) + update_file_sizes(inode, pos, copied); + /* + * There may be allocated blocks outside of i_size because + * we failed to copy some data. Prepare for truncate. + */ + if (pos + len > inode->i_size) + ext3_orphan_add(handle, inode); ret2 = ext3_journal_stop(handle); if (!ret) ret = ret2; unlock_page(page); page_cache_release(page); + if (pos + len > inode->i_size) + vmtruncate(inode, inode->i_size); return ret ? ret : copied; } @@ -1299,25 +1307,22 @@ static int ext3_writeback_write_end(struct file *file, { handle_t *handle = ext3_journal_current_handle(); struct inode *inode = file->f_mapping->host; - int ret = 0, ret2; - loff_t new_i_size; - - new_i_size = pos + copied; - if (new_i_size > EXT3_I(inode)->i_disksize) - EXT3_I(inode)->i_disksize = new_i_size; - - ret2 = ext3_generic_write_end(file, mapping, pos, len, copied, - page, fsdata); - copied = ret2; - if (ret2 < 0) - ret = ret2; + int ret; - ret2 = ext3_journal_stop(handle); - if (!ret) - ret = ret2; + copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); + update_file_sizes(inode, pos, copied); + /* + * There may be allocated blocks outside of i_size because + * we failed to copy some data. Prepare for truncate. + */ + if (pos + len > inode->i_size) + ext3_orphan_add(handle, inode); + ret = ext3_journal_stop(handle); unlock_page(page); page_cache_release(page); + if (pos + len > inode->i_size) + vmtruncate(inode, inode->i_size); return ret ? ret : copied; } @@ -1338,15 +1343,23 @@ static int ext3_journalled_write_end(struct file *file, if (copied < len) { if (!PageUptodate(page)) copied = 0; - page_zero_new_buffers(page, from+copied, to); + page_zero_new_buffers(page, from + copied, to); + to = from + copied; } ret = walk_page_buffers(handle, page_buffers(page), from, to, &partial, write_end_fn); if (!partial) SetPageUptodate(page); - if (pos+copied > inode->i_size) - i_size_write(inode, pos+copied); + + if (pos + copied > inode->i_size) + i_size_write(inode, pos + copied); + /* + * There may be allocated blocks outside of i_size because + * we failed to copy some data. Prepare for truncate. + */ + if (pos + len > inode->i_size) + ext3_orphan_add(handle, inode); EXT3_I(inode)->i_state |= EXT3_STATE_JDATA; if (inode->i_size > EXT3_I(inode)->i_disksize) { EXT3_I(inode)->i_disksize = inode->i_size; @@ -1361,6 +1374,8 @@ static int ext3_journalled_write_end(struct file *file, unlock_page(page); page_cache_release(page); + if (pos + len > inode->i_size) + vmtruncate(inode, inode->i_size); return ret ? ret : copied; } @@ -1428,17 +1443,11 @@ static int bput_one(handle_t *handle, struct buffer_head *bh) return 0; } -static int journal_dirty_data_fn(handle_t *handle, struct buffer_head *bh) -{ - if (buffer_mapped(bh)) - return ext3_journal_dirty_data(handle, bh); - return 0; -} - static int buffer_unmapped(handle_t *handle, struct buffer_head *bh) { return !buffer_mapped(bh); } + /* * Note that we always start a transaction even if we're not journalling * data. This is to preserve ordering: any hole instantiation within diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c index 5e86ce9a86e0..88974814783a 100644 --- a/fs/ext3/ioctl.c +++ b/fs/ext3/ioctl.c @@ -15,12 +15,11 @@ #include <linux/mount.h> #include <linux/time.h> #include <linux/compat.h> -#include <linux/smp_lock.h> #include <asm/uaccess.h> -int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd, - unsigned long arg) +long ext3_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { + struct inode *inode = filp->f_dentry->d_inode; struct ext3_inode_info *ei = EXT3_I(inode); unsigned int flags; unsigned short rsv_window_size; @@ -39,29 +38,25 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd, unsigned int oldflags; unsigned int jflag; + if (!is_owner_or_cap(inode)) + return -EACCES; + + if (get_user(flags, (int __user *) arg)) + return -EFAULT; + err = mnt_want_write(filp->f_path.mnt); if (err) return err; - if (!is_owner_or_cap(inode)) { - err = -EACCES; - goto flags_out; - } - - if (get_user(flags, (int __user *) arg)) { - err = -EFAULT; - goto flags_out; - } - flags = ext3_mask_flags(inode->i_mode, flags); mutex_lock(&inode->i_mutex); + /* Is it quota file? Do not allow user to mess with it */ - if (IS_NOQUOTA(inode)) { - mutex_unlock(&inode->i_mutex); - err = -EPERM; + err = -EPERM; + if (IS_NOQUOTA(inode)) goto flags_out; - } + oldflags = ei->i_flags; /* The JOURNAL_DATA flag is modifiable only by root */ @@ -74,11 +69,8 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd, * This test looks nicer. Thanks to Pauline Middelink */ if ((flags ^ oldflags) & (EXT3_APPEND_FL | EXT3_IMMUTABLE_FL)) { - if (!capable(CAP_LINUX_IMMUTABLE)) { - mutex_unlock(&inode->i_mutex); - err = -EPERM; + if (!capable(CAP_LINUX_IMMUTABLE)) goto flags_out; - } } /* @@ -86,17 +78,12 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd, * the relevant capability. */ if ((jflag ^ oldflags) & (EXT3_JOURNAL_DATA_FL)) { - if (!capable(CAP_SYS_RESOURCE)) { - mutex_unlock(&inode->i_mutex); - err = -EPERM; + if (!capable(CAP_SYS_RESOURCE)) goto flags_out; - } } - handle = ext3_journal_start(inode, 1); if (IS_ERR(handle)) { - mutex_unlock(&inode->i_mutex); err = PTR_ERR(handle); goto flags_out; } @@ -116,15 +103,13 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd, err = ext3_mark_iloc_dirty(handle, inode, &iloc); flags_err: ext3_journal_stop(handle); - if (err) { - mutex_unlock(&inode->i_mutex); - return err; - } + if (err) + goto flags_out; if ((jflag ^ oldflags) & (EXT3_JOURNAL_DATA_FL)) err = ext3_change_inode_journal_flag(inode, jflag); - mutex_unlock(&inode->i_mutex); flags_out: + mutex_unlock(&inode->i_mutex); mnt_drop_write(filp->f_path.mnt); return err; } @@ -140,6 +125,7 @@ flags_out: if (!is_owner_or_cap(inode)) return -EPERM; + err = mnt_want_write(filp->f_path.mnt); if (err) return err; @@ -147,6 +133,7 @@ flags_out: err = -EFAULT; goto setversion_out; } + handle = ext3_journal_start(inode, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); @@ -299,9 +286,6 @@ group_add_out: #ifdef CONFIG_COMPAT long ext3_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 EXT3_IOC32_GETFLAGS: @@ -341,9 +325,6 @@ long ext3_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) default: return -ENOIOCTLCMD; } - lock_kernel(); - ret = ext3_ioctl(inode, file, cmd, (unsigned long) compat_ptr(arg)); - unlock_kernel(); - return ret; + return ext3_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); } #endif diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index e2fc63cbba8b..6ddaa0a42b24 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -161,12 +161,12 @@ static struct dx_frame *dx_probe(struct qstr *entry, struct dx_frame *frame, int *err); static void dx_release (struct dx_frame *frames); -static int dx_make_map (struct ext3_dir_entry_2 *de, int size, +static int dx_make_map(struct ext3_dir_entry_2 *de, unsigned blocksize, struct dx_hash_info *hinfo, struct dx_map_entry map[]); static void dx_sort_map(struct dx_map_entry *map, unsigned count); static struct ext3_dir_entry_2 *dx_move_dirents (char *from, char *to, struct dx_map_entry *offsets, int count); -static struct ext3_dir_entry_2* dx_pack_dirents (char *base, int size); +static struct ext3_dir_entry_2 *dx_pack_dirents(char *base, unsigned blocksize); static void dx_insert_block (struct dx_frame *frame, u32 hash, u32 block); static int ext3_htree_next_block(struct inode *dir, __u32 hash, struct dx_frame *frame, @@ -708,14 +708,14 @@ errout: * Create map of hash values, offsets, and sizes, stored at end of block. * Returns number of entries mapped. */ -static int dx_make_map (struct ext3_dir_entry_2 *de, int size, - struct dx_hash_info *hinfo, struct dx_map_entry *map_tail) +static int dx_make_map(struct ext3_dir_entry_2 *de, unsigned blocksize, + struct dx_hash_info *hinfo, struct dx_map_entry *map_tail) { int count = 0; char *base = (char *) de; struct dx_hash_info h = *hinfo; - while ((char *) de < base + size) + while ((char *) de < base + blocksize) { if (de->name_len && de->inode) { ext3fs_dirhash(de->name, de->name_len, &h); @@ -1047,8 +1047,16 @@ static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, str return ERR_PTR(-EIO); } inode = ext3_iget(dir->i_sb, ino); - if (IS_ERR(inode)) - return ERR_CAST(inode); + if (unlikely(IS_ERR(inode))) { + if (PTR_ERR(inode) == -ESTALE) { + ext3_error(dir->i_sb, __func__, + "deleted inode referenced: %lu", + ino); + return ERR_PTR(-EIO); + } else { + return ERR_CAST(inode); + } + } } return d_splice_alias(inode, dentry); } @@ -1120,13 +1128,14 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count) * Compact each dir entry in the range to the minimal rec_len. * Returns pointer to last entry in range. */ -static struct ext3_dir_entry_2* dx_pack_dirents(char *base, int size) +static struct ext3_dir_entry_2 *dx_pack_dirents(char *base, unsigned blocksize) { - struct ext3_dir_entry_2 *next, *to, *prev, *de = (struct ext3_dir_entry_2 *) base; + struct ext3_dir_entry_2 *next, *to, *prev; + struct ext3_dir_entry_2 *de = (struct ext3_dir_entry_2 *)base; unsigned rec_len = 0; prev = to = de; - while ((char*)de < base + size) { + while ((char *)de < base + blocksize) { next = ext3_next_entry(de); if (de->inode && de->name_len) { rec_len = EXT3_DIR_REC_LEN(de->name_len); diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index 694ed6fadcc8..647e0d65a284 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -323,7 +323,7 @@ ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) return PTR_ERR(acl); } if (!acl) - inode->i_mode &= ~current->fs->umask; + inode->i_mode &= ~current_umask(); } if (test_opt(inode->i_sb, POSIX_ACL) && acl) { struct posix_acl *clone; diff --git a/fs/fat/inode.c b/fs/fat/inode.c index de0004fe6e00..296785a0dec8 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -523,7 +523,9 @@ static int fat_remount(struct super_block *sb, int *flags, char *data) static int fat_statfs(struct dentry *dentry, struct kstatfs *buf) { - struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb); + struct super_block *sb = dentry->d_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + u64 id = huge_encode_dev(sb->s_bdev->bd_dev); /* If the count of free cluster is still unknown, counts it here. */ if (sbi->free_clusters == -1 || !sbi->free_clus_valid) { @@ -537,6 +539,8 @@ static int fat_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_blocks = sbi->max_cluster - FAT_START_ENT; buf->f_bfree = sbi->free_clusters; buf->f_bavail = sbi->free_clusters; + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); buf->f_namelen = sbi->options.isvfat ? 260 : 12; return 0; @@ -930,7 +934,7 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug, opts->fs_uid = current_uid(); opts->fs_gid = current_gid(); - opts->fs_fmask = opts->fs_dmask = current->fs->umask; + opts->fs_fmask = current_umask(); opts->allow_utime = -1; opts->codepage = fat_default_codepage; opts->iocharset = fat_default_iocharset; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index e3fe9918faaf..eed480639902 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -196,7 +196,7 @@ static void redirty_tail(struct inode *inode) struct inode *tail_inode; tail_inode = list_entry(sb->s_dirty.next, struct inode, i_list); - if (!time_after_eq(inode->dirtied_when, + if (time_before(inode->dirtied_when, tail_inode->dirtied_when)) inode->dirtied_when = jiffies; } @@ -220,6 +220,21 @@ static void inode_sync_complete(struct inode *inode) wake_up_bit(&inode->i_state, __I_SYNC); } +static bool inode_dirtied_after(struct inode *inode, unsigned long t) +{ + bool ret = time_after(inode->dirtied_when, t); +#ifndef CONFIG_64BIT + /* + * For inodes being constantly redirtied, dirtied_when can get stuck. + * It _appears_ to be in the future, but is actually in distant past. + * This test is necessary to prevent such wrapped-around relative times + * from permanently stopping the whole pdflush writeback. + */ + ret = ret && time_before_eq(inode->dirtied_when, jiffies); +#endif + return ret; +} + /* * Move expired dirty inodes from @delaying_queue to @dispatch_queue. */ @@ -231,7 +246,7 @@ static void move_expired_inodes(struct list_head *delaying_queue, struct inode *inode = list_entry(delaying_queue->prev, struct inode, i_list); if (older_than_this && - time_after(inode->dirtied_when, *older_than_this)) + inode_dirtied_after(inode, *older_than_this)) break; list_move(&inode->i_list, dispatch_queue); } @@ -492,8 +507,11 @@ void generic_sync_sb_inodes(struct super_block *sb, continue; /* blockdev has wrong queue */ } - /* Was this inode dirtied after sync_sb_inodes was called? */ - if (time_after(inode->dirtied_when, start)) + /* + * Was this inode dirtied after sync_sb_inodes was called? + * This keeps sync from extra jobs and livelock. + */ + if (inode_dirtied_after(inode, start)) break; /* Is another pdflush already flushing this queue? */ @@ -538,7 +556,8 @@ void generic_sync_sb_inodes(struct super_block *sb, list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { struct address_space *mapping; - if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) + if (inode->i_state & + (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW)) continue; mapping = inode->i_mapping; if (mapping->nrpages == 0) diff --git a/fs/fs_struct.c b/fs/fs_struct.c new file mode 100644 index 000000000000..eee059052db5 --- /dev/null +++ b/fs/fs_struct.c @@ -0,0 +1,177 @@ +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/fs.h> +#include <linux/path.h> +#include <linux/slab.h> +#include <linux/fs_struct.h> + +/* + * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values. + * It can block. + */ +void set_fs_root(struct fs_struct *fs, struct path *path) +{ + struct path old_root; + + write_lock(&fs->lock); + old_root = fs->root; + fs->root = *path; + path_get(path); + write_unlock(&fs->lock); + if (old_root.dentry) + path_put(&old_root); +} + +/* + * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values. + * It can block. + */ +void set_fs_pwd(struct fs_struct *fs, struct path *path) +{ + struct path old_pwd; + + write_lock(&fs->lock); + old_pwd = fs->pwd; + fs->pwd = *path; + path_get(path); + write_unlock(&fs->lock); + + if (old_pwd.dentry) + path_put(&old_pwd); +} + +void chroot_fs_refs(struct path *old_root, struct path *new_root) +{ + struct task_struct *g, *p; + struct fs_struct *fs; + int count = 0; + + read_lock(&tasklist_lock); + do_each_thread(g, p) { + task_lock(p); + fs = p->fs; + if (fs) { + write_lock(&fs->lock); + if (fs->root.dentry == old_root->dentry + && fs->root.mnt == old_root->mnt) { + path_get(new_root); + fs->root = *new_root; + count++; + } + if (fs->pwd.dentry == old_root->dentry + && fs->pwd.mnt == old_root->mnt) { + path_get(new_root); + fs->pwd = *new_root; + count++; + } + write_unlock(&fs->lock); + } + task_unlock(p); + } while_each_thread(g, p); + read_unlock(&tasklist_lock); + while (count--) + path_put(old_root); +} + +void free_fs_struct(struct fs_struct *fs) +{ + path_put(&fs->root); + path_put(&fs->pwd); + kmem_cache_free(fs_cachep, fs); +} + +void exit_fs(struct task_struct *tsk) +{ + struct fs_struct *fs = tsk->fs; + + if (fs) { + int kill; + task_lock(tsk); + write_lock(&fs->lock); + tsk->fs = NULL; + kill = !--fs->users; + write_unlock(&fs->lock); + task_unlock(tsk); + if (kill) + free_fs_struct(fs); + } +} + +struct fs_struct *copy_fs_struct(struct fs_struct *old) +{ + struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL); + /* We don't need to lock fs - think why ;-) */ + if (fs) { + fs->users = 1; + fs->in_exec = 0; + rwlock_init(&fs->lock); + fs->umask = old->umask; + read_lock(&old->lock); + fs->root = old->root; + path_get(&old->root); + fs->pwd = old->pwd; + path_get(&old->pwd); + read_unlock(&old->lock); + } + return fs; +} + +int unshare_fs_struct(void) +{ + struct fs_struct *fs = current->fs; + struct fs_struct *new_fs = copy_fs_struct(fs); + int kill; + + if (!new_fs) + return -ENOMEM; + + task_lock(current); + write_lock(&fs->lock); + kill = !--fs->users; + current->fs = new_fs; + write_unlock(&fs->lock); + task_unlock(current); + + if (kill) + free_fs_struct(fs); + + return 0; +} +EXPORT_SYMBOL_GPL(unshare_fs_struct); + +int current_umask(void) +{ + return current->fs->umask; +} +EXPORT_SYMBOL(current_umask); + +/* to be mentioned only in INIT_TASK */ +struct fs_struct init_fs = { + .users = 1, + .lock = __RW_LOCK_UNLOCKED(init_fs.lock), + .umask = 0022, +}; + +void daemonize_fs_struct(void) +{ + struct fs_struct *fs = current->fs; + + if (fs) { + int kill; + + task_lock(current); + + write_lock(&init_fs.lock); + init_fs.users++; + write_unlock(&init_fs.lock); + + write_lock(&fs->lock); + current->fs = &init_fs; + kill = !--fs->users; + write_unlock(&fs->lock); + + task_unlock(current); + if (kill) + free_fs_struct(fs); + } +} diff --git a/fs/generic_acl.c b/fs/generic_acl.c index 995d63b2e747..e0b53aa7bbec 100644 --- a/fs/generic_acl.c +++ b/fs/generic_acl.c @@ -134,7 +134,7 @@ generic_acl_init(struct inode *inode, struct inode *dir, mode_t mode = inode->i_mode; int error; - inode->i_mode = mode & ~current->fs->umask; + inode->i_mode = mode & ~current_umask(); if (!S_ISLNK(inode->i_mode)) acl = ops->getacl(dir, ACL_TYPE_DEFAULT); if (acl) { diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 43764f4fa763..fa881bdc3d85 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -215,7 +215,7 @@ int gfs2_acl_create(struct gfs2_inode *dip, struct gfs2_inode *ip) if (error) return error; if (!acl) { - mode &= ~current->fs->umask; + mode &= ~current_umask(); if (mode != ip->i_inode.i_mode) error = munge_mode(ip, mode); return error; diff --git a/fs/hfs/super.c b/fs/hfs/super.c index c8b5acf4b0b7..a36bb749926d 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -82,6 +82,7 @@ static void hfs_put_super(struct super_block *sb) static int hfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; + u64 id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = HFS_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; @@ -90,6 +91,8 @@ static int hfs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bavail = buf->f_bfree; buf->f_files = HFS_SB(sb)->fs_ablocks; buf->f_ffree = HFS_SB(sb)->free_ablocks; + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); buf->f_namelen = HFS_NAMELEN; return 0; diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c index bab7f8d1bdfa..3fcbb0e1f6fc 100644 --- a/fs/hfsplus/options.c +++ b/fs/hfsplus/options.c @@ -48,7 +48,7 @@ void hfsplus_fill_defaults(struct hfsplus_sb_info *opts) opts->creator = HFSPLUS_DEF_CR_TYPE; opts->type = HFSPLUS_DEF_CR_TYPE; - opts->umask = current->fs->umask; + opts->umask = current_umask(); opts->uid = current_uid(); opts->gid = current_gid(); opts->part = -1; diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index eb74531a0a8e..f2a64020f42e 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -223,6 +223,7 @@ static void hfsplus_put_super(struct super_block *sb) static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; + u64 id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = HFSPLUS_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; @@ -231,6 +232,8 @@ static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bavail = buf->f_bfree; buf->f_files = 0xFFFFFFFF; buf->f_ffree = 0xFFFFFFFF - HFSPLUS_SB(sb).next_cnid; + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); buf->f_namelen = HFSPLUS_MAX_STRLEN; return 0; diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index 0d049b8919c4..fecf402d7b8a 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -136,6 +136,7 @@ static int hpfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *s = dentry->d_sb; struct hpfs_sb_info *sbi = hpfs_sb(s); + u64 id = huge_encode_dev(s->s_bdev->bd_dev); lock_kernel(); /*if (sbi->sb_n_free == -1) {*/ @@ -149,6 +150,8 @@ static int hpfs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bavail = sbi->sb_n_free; buf->f_files = sbi->sb_dirband_size / 4; buf->f_ffree = sbi->sb_n_free_dnodes; + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); buf->f_namelen = 254; unlock_kernel(); @@ -477,7 +480,7 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent) uid = current_uid(); gid = current_gid(); - umask = current->fs->umask; + umask = current_umask(); lowercase = 0; conv = CONV_BINARY; eas = 2; diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c index b278f7f52024..a5089a6dd67a 100644 --- a/fs/hppfs/hppfs.c +++ b/fs/hppfs/hppfs.c @@ -280,7 +280,12 @@ static ssize_t hppfs_read(struct file *file, char __user *buf, size_t count, "errno = %d\n", err); return err; } - count = hppfs_read_file(hppfs->host_fd, buf, count); + err = hppfs_read_file(hppfs->host_fd, buf, count); + if (err < 0) { + printk(KERN_ERR "hppfs_read: read failed: %d\n", err); + return err; + } + count = err; if (count > 0) *ppos += count; } diff --git a/fs/internal.h b/fs/internal.h index 53af885f1732..b4dac4fb6b61 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -11,6 +11,7 @@ struct super_block; struct linux_binprm; +struct path; /* * block_dev.c @@ -43,7 +44,7 @@ extern void __init chrdev_init(void); /* * exec.c */ -extern void check_unsafe_exec(struct linux_binprm *); +extern int check_unsafe_exec(struct linux_binprm *); /* * namespace.c @@ -60,3 +61,8 @@ extern void umount_tree(struct vfsmount *, int, struct list_head *); extern struct vfsmount *copy_tree(struct vfsmount *, struct dentry *, int); extern void __init mnt_init(void); + +/* + * fs_struct.c + */ +extern void chroot_fs_refs(struct path *, struct path *); diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 13d2eddd0692..b4cbe9603c7d 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -923,6 +923,7 @@ out_freesbi: static int isofs_statfs (struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; + u64 id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = ISOFS_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; @@ -932,6 +933,8 @@ static int isofs_statfs (struct dentry *dentry, struct kstatfs *buf) buf->f_bavail = 0; buf->f_files = ISOFS_SB(sb)->s_ninodes; buf->f_ffree = 0; + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); buf->f_namelen = NAME_MAX; return 0; } diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index e79c07812afa..737f7246a4b5 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -637,6 +637,8 @@ struct journal_head *journal_get_descriptor_buffer(journal_t *journal) return NULL; bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); + if (!bh) + return NULL; lock_buffer(bh); memset(bh->b_data, 0, journal->j_blocksize); set_buffer_uptodate(bh); @@ -733,9 +735,7 @@ journal_t * journal_init_dev(struct block_device *bdev, if (!journal->j_wbuf) { printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n", __func__); - kfree(journal); - journal = NULL; - goto out; + goto out_err; } journal->j_dev = bdev; journal->j_fs_dev = fs_dev; @@ -743,11 +743,19 @@ journal_t * journal_init_dev(struct block_device *bdev, journal->j_maxlen = len; bh = __getblk(journal->j_dev, start, journal->j_blocksize); - J_ASSERT(bh != NULL); + if (!bh) { + printk(KERN_ERR + "%s: Cannot get buffer for journal superblock\n", + __func__); + goto out_err; + } journal->j_sb_buffer = bh; journal->j_superblock = (journal_superblock_t *)bh->b_data; -out: + return journal; +out_err: + kfree(journal); + return NULL; } /** @@ -787,8 +795,7 @@ journal_t * journal_init_inode (struct inode *inode) if (!journal->j_wbuf) { printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n", __func__); - kfree(journal); - return NULL; + goto out_err; } err = journal_bmap(journal, 0, &blocknr); @@ -796,16 +803,23 @@ journal_t * journal_init_inode (struct inode *inode) if (err) { printk(KERN_ERR "%s: Cannnot locate journal superblock\n", __func__); - kfree(journal); - return NULL; + goto out_err; } bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); - J_ASSERT(bh != NULL); + if (!bh) { + printk(KERN_ERR + "%s: Cannot get buffer for journal superblock\n", + __func__); + goto out_err; + } journal->j_sb_buffer = bh; journal->j_superblock = (journal_superblock_t *)bh->b_data; return journal; +out_err: + kfree(journal); + return NULL; } /* diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c index d98713777a1b..77ccf8cb0823 100644 --- a/fs/jffs2/acl.c +++ b/fs/jffs2/acl.c @@ -336,7 +336,7 @@ int jffs2_init_acl_pre(struct inode *dir_i, struct inode *inode, int *i_mode) return PTR_ERR(acl); if (!acl) { - *i_mode &= ~current->fs->umask; + *i_mode &= ~current_umask(); } else { if (S_ISDIR(*i_mode)) jffs2_iset_acl(inode, &f->i_acl_default, acl); diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index a166c1669e82..06ca1b8d2054 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -182,7 +182,7 @@ int jfs_init_acl(tid_t tid, struct inode *inode, struct inode *dir) cleanup: posix_acl_release(acl); } else - inode->i_mode &= ~current->fs->umask; + inode->i_mode &= ~current_umask(); JFS_IP(inode)->mode2 = (JFS_IP(inode)->mode2 & 0xffff0000) | inode->i_mode; diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 618865b3128b..daad3c2740db 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -321,15 +321,20 @@ out: static int minix_statfs(struct dentry *dentry, struct kstatfs *buf) { - struct minix_sb_info *sbi = minix_sb(dentry->d_sb); - buf->f_type = dentry->d_sb->s_magic; - buf->f_bsize = dentry->d_sb->s_blocksize; + struct super_block *sb = dentry->d_sb; + struct minix_sb_info *sbi = minix_sb(sb); + u64 id = huge_encode_dev(sb->s_bdev->bd_dev); + buf->f_type = sb->s_magic; + buf->f_bsize = sb->s_blocksize; buf->f_blocks = (sbi->s_nzones - sbi->s_firstdatazone) << sbi->s_log_zone_size; buf->f_bfree = minix_count_free_blocks(sbi); buf->f_bavail = buf->f_bfree; buf->f_files = sbi->s_ninodes; buf->f_ffree = minix_count_free_inodes(sbi); buf->f_namelen = sbi->s_namelen; + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); + return 0; } diff --git a/fs/mpage.c b/fs/mpage.c index 16c3ef37eae3..680ba60863ff 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -82,7 +82,7 @@ static void mpage_end_io_write(struct bio *bio, int err) bio_put(bio); } -struct bio *mpage_bio_submit(int rw, struct bio *bio) +static struct bio *mpage_bio_submit(int rw, struct bio *bio) { bio->bi_end_io = mpage_end_io_read; if (rw == WRITE) @@ -90,7 +90,6 @@ struct bio *mpage_bio_submit(int rw, struct bio *bio) submit_bio(rw, bio); return NULL; } -EXPORT_SYMBOL(mpage_bio_submit); static struct bio * mpage_alloc(struct block_device *bdev, @@ -439,7 +438,14 @@ EXPORT_SYMBOL(mpage_readpage); * just allocate full-size (16-page) BIOs. */ -int __mpage_writepage(struct page *page, struct writeback_control *wbc, +struct mpage_data { + struct bio *bio; + sector_t last_block_in_bio; + get_block_t *get_block; + unsigned use_writepage; +}; + +static int __mpage_writepage(struct page *page, struct writeback_control *wbc, void *data) { struct mpage_data *mpd = data; @@ -648,7 +654,6 @@ out: mpd->bio = bio; return ret; } -EXPORT_SYMBOL(__mpage_writepage); /** * mpage_writepages - walk the list of dirty pages of the given address space & writepage() all of them diff --git a/fs/namei.c b/fs/namei.c index d040ce11785d..b8433ebfae05 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -32,6 +32,7 @@ #include <linux/file.h> #include <linux/fcntl.h> #include <linux/device_cgroup.h> +#include <linux/fs_struct.h> #include <asm/uaccess.h> #define ACC_MODE(x) ("\000\004\002\006"[(x)&O_ACCMODE]) @@ -1578,7 +1579,7 @@ static int __open_namei_create(struct nameidata *nd, struct path *path, struct dentry *dir = nd->path.dentry; if (!IS_POSIXACL(dir->d_inode)) - mode &= ~current->fs->umask; + mode &= ~current_umask(); error = security_path_mknod(&nd->path, path->dentry, mode, 0); if (error) goto out_unlock; @@ -1989,7 +1990,7 @@ SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, int, mode, goto out_unlock; } if (!IS_POSIXACL(nd.path.dentry->d_inode)) - mode &= ~current->fs->umask; + mode &= ~current_umask(); error = may_mknod(mode); if (error) goto out_dput; @@ -2067,7 +2068,7 @@ SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, int, mode) goto out_unlock; if (!IS_POSIXACL(nd.path.dentry->d_inode)) - mode &= ~current->fs->umask; + mode &= ~current_umask(); error = mnt_want_write(nd.path.mnt); if (error) goto out_dput; @@ -2897,10 +2898,3 @@ EXPORT_SYMBOL(vfs_symlink); EXPORT_SYMBOL(vfs_unlink); EXPORT_SYMBOL(dentry_unhash); EXPORT_SYMBOL(generic_readlink); - -/* to be mentioned only in INIT_TASK */ -struct fs_struct init_fs = { - .count = ATOMIC_INIT(1), - .lock = __RW_LOCK_UNLOCKED(init_fs.lock), - .umask = 0022, -}; diff --git a/fs/namespace.c b/fs/namespace.c index 0a42e0e96027..c6f54e4c4290 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -27,6 +27,7 @@ #include <linux/ramfs.h> #include <linux/log2.h> #include <linux/idr.h> +#include <linux/fs_struct.h> #include <asm/uaccess.h> #include <asm/unistd.h> #include "pnode.h" @@ -2093,66 +2094,6 @@ out1: } /* - * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values. - * It can block. Requires the big lock held. - */ -void set_fs_root(struct fs_struct *fs, struct path *path) -{ - struct path old_root; - - write_lock(&fs->lock); - old_root = fs->root; - fs->root = *path; - path_get(path); - write_unlock(&fs->lock); - if (old_root.dentry) - path_put(&old_root); -} - -/* - * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values. - * It can block. Requires the big lock held. - */ -void set_fs_pwd(struct fs_struct *fs, struct path *path) -{ - struct path old_pwd; - - write_lock(&fs->lock); - old_pwd = fs->pwd; - fs->pwd = *path; - path_get(path); - write_unlock(&fs->lock); - - if (old_pwd.dentry) - path_put(&old_pwd); -} - -static void chroot_fs_refs(struct path *old_root, struct path *new_root) -{ - struct task_struct *g, *p; - struct fs_struct *fs; - - read_lock(&tasklist_lock); - do_each_thread(g, p) { - task_lock(p); - fs = p->fs; - if (fs) { - atomic_inc(&fs->count); - task_unlock(p); - if (fs->root.dentry == old_root->dentry - && fs->root.mnt == old_root->mnt) - set_fs_root(fs, new_root); - if (fs->pwd.dentry == old_root->dentry - && fs->pwd.mnt == old_root->mnt) - set_fs_pwd(fs, new_root); - put_fs_struct(fs); - } else - task_unlock(p); - } while_each_thread(g, p); - read_unlock(&tasklist_lock); -} - -/* * pivot_root Semantics: * Moves the root file system of the current process to the directory put_old, * makes new_root as the new root file system of the current process, and sets diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index b82fe6847f14..d0cc5ce0edfe 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -328,7 +328,7 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, data->arg.create.verifier[1] = current->pid; } - sattr->ia_mode &= ~current->fs->umask; + sattr->ia_mode &= ~current_umask(); for (;;) { status = nfs3_do_create(dir, dentry, data); @@ -528,7 +528,7 @@ nfs3_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr) dprintk("NFS call mkdir %s\n", dentry->d_name.name); - sattr->ia_mode &= ~current->fs->umask; + sattr->ia_mode &= ~current_umask(); data = nfs3_alloc_createdata(); if (data == NULL) @@ -639,7 +639,7 @@ nfs3_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr, dprintk("NFS call mknod %s %u:%u\n", dentry->d_name.name, MAJOR(rdev), MINOR(rdev)); - sattr->ia_mode &= ~current->fs->umask; + sattr->ia_mode &= ~current_umask(); data = nfs3_alloc_createdata(); if (data == NULL) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 97bacccff579..a4d242680299 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1501,7 +1501,7 @@ nfs4_atomic_open(struct inode *dir, struct dentry *dentry, struct nameidata *nd) attr.ia_mode = nd->intent.open.create_mode; attr.ia_valid = ATTR_MODE; if (!IS_POSIXACL(dir)) - attr.ia_mode &= ~current->fs->umask; + attr.ia_mode &= ~current_umask(); } else { attr.ia_valid = 0; BUG_ON(nd->intent.open.flags & O_CREAT); diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index bc3567bab8c4..7c09852be713 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -403,7 +403,6 @@ static int nfsd(void *vrqstp) { struct svc_rqst *rqstp = (struct svc_rqst *) vrqstp; - struct fs_struct *fsp; int err, preverr = 0; /* Lock module and set up kernel thread */ @@ -412,13 +411,11 @@ nfsd(void *vrqstp) /* At this point, the thread shares current->fs * with the init process. We need to create files with a * umask of 0 instead of init's umask. */ - fsp = copy_fs_struct(current->fs); - if (!fsp) { + if (unshare_fs_struct() < 0) { printk("Unable to start nfsd thread: out of memory\n"); goto out; } - exit_fs(current); - current->fs = fsp; + current->fs->umask = 0; /* diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 12dfb44c22e5..fbeaec762103 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -296,7 +296,7 @@ int ocfs2_init_acl(handle_t *handle, return PTR_ERR(acl); } if (!acl) - inode->i_mode &= ~current->fs->umask; + inode->i_mode &= ~current_umask(); } if ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) && acl) { struct posix_acl *clone; diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index 633e9dc972bb..379ae5fb4411 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -262,14 +262,19 @@ static int omfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *s = dentry->d_sb; struct omfs_sb_info *sbi = OMFS_SB(s); + u64 id = huge_encode_dev(s->s_bdev->bd_dev); + buf->f_type = OMFS_MAGIC; buf->f_bsize = sbi->s_blocksize; buf->f_blocks = sbi->s_num_blocks; buf->f_files = sbi->s_num_blocks; buf->f_namelen = OMFS_NAMELEN; + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); buf->f_bfree = buf->f_bavail = buf->f_ffree = omfs_count_free(s); + return 0; } @@ -421,7 +426,7 @@ static int omfs_fill_super(struct super_block *sb, void *data, int silent) sbi->s_uid = current_uid(); sbi->s_gid = current_gid(); - sbi->s_dmask = sbi->s_fmask = current->fs->umask; + sbi->s_dmask = sbi->s_fmask = current_umask(); if (!parse_options((char *) data, sbi)) goto end; diff --git a/fs/open.c b/fs/open.c index 75b61677daaf..377eb25b6abf 100644 --- a/fs/open.c +++ b/fs/open.c @@ -29,6 +29,7 @@ #include <linux/rcupdate.h> #include <linux/audit.h> #include <linux/falloc.h> +#include <linux/fs_struct.h> int vfs_statfs(struct dentry *dentry, struct kstatfs *buf) { diff --git a/fs/proc/base.c b/fs/proc/base.c index e0afd326b688..f71559784bfb 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -80,6 +80,7 @@ #include <linux/oom.h> #include <linux/elf.h> #include <linux/pid_namespace.h> +#include <linux/fs_struct.h> #include "internal.h" /* NOTE: diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 43d23948384a..74ea974f5ca6 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -120,7 +120,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) K(i.freeram-i.freehigh), #endif #ifndef CONFIG_MMU - K((unsigned long) atomic_read(&mmap_pages_allocated)), + K((unsigned long) atomic_long_read(&mmap_pages_allocated)), #endif K(i.totalswap), K(i.freeswap), diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 343ea1216bc8..863464d5519c 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -2,6 +2,7 @@ #include <linux/mm.h> #include <linux/file.h> #include <linux/fdtable.h> +#include <linux/fs_struct.h> #include <linux/mount.h> #include <linux/ptrace.h> #include <linux/seq_file.h> @@ -49,7 +50,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) else bytes += kobjsize(mm); - if (current->fs && atomic_read(¤t->fs->count) > 1) + if (current->fs && current->fs->users > 1) sbytes += kobjsize(current->fs); else bytes += kobjsize(current->fs); @@ -136,14 +137,14 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) } seq_printf(m, - "%08lx-%08lx %c%c%c%c %08lx %02x:%02x %lu %n", + "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n", vma->vm_start, vma->vm_end, flags & VM_READ ? 'r' : '-', flags & VM_WRITE ? 'w' : '-', flags & VM_EXEC ? 'x' : '-', flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p', - vma->vm_pgoff << PAGE_SHIFT, + (unsigned long long) vma->vm_pgoff << PAGE_SHIFT, MAJOR(dev), MINOR(dev), ino, &len); if (file) { diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index 2aad1044b84c..fe1f0f31d11c 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -282,6 +282,7 @@ unsigned long qnx4_block_map( struct inode *inode, long iblock ) static int qnx4_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; + u64 id = huge_encode_dev(sb->s_bdev->bd_dev); lock_kernel(); @@ -291,6 +292,8 @@ static int qnx4_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bfree = qnx4_count_free_blocks(sb); buf->f_bavail = buf->f_bfree; buf->f_namelen = QNX4_NAME_MAX; + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); unlock_kernel(); diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 2ca967a5ef77..607c579e5eca 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -823,7 +823,7 @@ static void add_dquot_ref(struct super_block *sb, int type) spin_lock(&inode_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { - if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) + if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW)) continue; if (!atomic_read(&inode->i_writecount)) continue; diff --git a/fs/read_write.c b/fs/read_write.c index 400fe81c973e..6d5d8ff238aa 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -731,6 +731,56 @@ SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, return ret; } +SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, + unsigned long, vlen, u32, pos_high, u32, pos_low) +{ + loff_t pos = ((loff_t)pos_high << 32) | pos_low; + struct file *file; + ssize_t ret = -EBADF; + int fput_needed; + + if (pos < 0) + return -EINVAL; + + file = fget_light(fd, &fput_needed); + if (file) { + ret = -ESPIPE; + if (file->f_mode & FMODE_PREAD) + ret = vfs_readv(file, vec, vlen, &pos); + fput_light(file, fput_needed); + } + + if (ret > 0) + add_rchar(current, ret); + inc_syscr(current); + return ret; +} + +SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, + unsigned long, vlen, u32, pos_high, u32, pos_low) +{ + loff_t pos = ((loff_t)pos_high << 32) | pos_low; + struct file *file; + ssize_t ret = -EBADF; + int fput_needed; + + if (pos < 0) + return -EINVAL; + + file = fget_light(fd, &fput_needed); + if (file) { + ret = -ESPIPE; + if (file->f_mode & FMODE_PWRITE) + ret = vfs_writev(file, vec, vlen, &pos); + fput_light(file, fput_needed); + } + + if (ret > 0) + add_wchar(current, ret); + inc_syscw(current); + return ret; +} + static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count, loff_t max) { diff --git a/fs/reiserfs/Kconfig b/fs/reiserfs/Kconfig index 949b8c6addc8..513f431038f9 100644 --- a/fs/reiserfs/Kconfig +++ b/fs/reiserfs/Kconfig @@ -1,5 +1,6 @@ config REISERFS_FS tristate "Reiserfs support" + select CRC32 help Stores not just filenames but the files themselves in a balanced tree. Uses journalling. diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 972250c62896..0ae6486d9046 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -27,6 +27,7 @@ #include <linux/mnt_namespace.h> #include <linux/mount.h> #include <linux/namei.h> +#include <linux/crc32.h> struct file_system_type reiserfs_fs_type; @@ -1904,6 +1905,10 @@ static int reiserfs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bsize = dentry->d_sb->s_blocksize; /* changed to accommodate gcc folks. */ buf->f_type = REISERFS_SUPER_MAGIC; + buf->f_fsid.val[0] = (u32)crc32_le(0, rs->s_uuid, sizeof(rs->s_uuid)/2); + buf->f_fsid.val[1] = (u32)crc32_le(0, rs->s_uuid + sizeof(rs->s_uuid)/2, + sizeof(rs->s_uuid)/2); + return 0; } diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index d423416d93d1..c303c426fe2b 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -428,7 +428,7 @@ reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th, } else { apply_umask: /* no ACL, apply umask */ - inode->i_mode &= ~current->fs->umask; + inode->i_mode &= ~current_umask(); } return err; diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 681ec0d83799..ffa6edcd2d0c 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -301,6 +301,7 @@ failure: static int squashfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct squashfs_sb_info *msblk = dentry->d_sb->s_fs_info; + u64 id = huge_encode_dev(dentry->d_sb->s_bdev->bd_dev); TRACE("Entered squashfs_statfs\n"); @@ -311,6 +312,8 @@ static int squashfs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_files = msblk->inodes; buf->f_ffree = 0; buf->f_namelen = SQUASHFS_NAME_LEN; + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); return 0; } diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 3d81bf58dae2..da20b48d350f 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -90,6 +90,7 @@ static int sysv_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct sysv_sb_info *sbi = SYSV_SB(sb); + u64 id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = sb->s_magic; buf->f_bsize = sb->s_blocksize; @@ -98,6 +99,8 @@ static int sysv_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_files = sbi->s_ninodes; buf->f_ffree = sysv_count_free_inodes(sb); buf->f_namelen = SYSV_NAMELEN; + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); return 0; } diff --git a/fs/ufs/super.c b/fs/ufs/super.c index e1c1fc5ee239..60359291761f 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -1268,6 +1268,7 @@ static int ufs_statfs(struct dentry *dentry, struct kstatfs *buf) struct ufs_super_block_first *usb1; struct ufs_super_block_second *usb2; struct ufs_super_block_third *usb3; + u64 id = huge_encode_dev(sb->s_bdev->bd_dev); lock_kernel(); @@ -1290,6 +1291,8 @@ static int ufs_statfs(struct dentry *dentry, struct kstatfs *buf) ? (buf->f_bfree - (((long)buf->f_blocks / 100) * uspi->s_minfree)) : 0; buf->f_files = uspi->s_ncg * uspi->s_ipg; buf->f_namelen = UFS_MAXNAMLEN; + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); unlock_kernel(); diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c index 7aa53fefc67f..2940612e3aeb 100644 --- a/fs/xfs/linux-2.6/xfs_iops.c +++ b/fs/xfs/linux-2.6/xfs_iops.c @@ -227,7 +227,7 @@ xfs_vn_mknod( xfs_dentry_to_name(&name, dentry); if (IS_POSIXACL(dir) && !default_acl) - mode &= ~current->fs->umask; + mode &= ~current_umask(); switch (mode & S_IFMT) { case S_IFCHR: @@ -416,7 +416,7 @@ xfs_vn_symlink( mode_t mode; mode = S_IFLNK | - (irix_symlink_mode ? 0777 & ~current->fs->umask : S_IRWXUGO); + (irix_symlink_mode ? 0777 & ~current_umask() : S_IRWXUGO); xfs_dentry_to_name(&name, dentry); error = xfs_symlink(XFS_I(dir), &name, symname, mode, &cip, NULL); |