From 3e93cd671813e204c258f1e6c797959920cf7772 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 29 Mar 2009 19:00:13 -0400 Subject: Take fs_struct handling to new file (fs/fs_struct.c) Pure code move; two new helper functions for nfsd and daemonize (unshare_fs_struct() and daemonize_fs_struct() resp.; for now - the same code as used to be in callers). unshare_fs_struct() exported (for nfsd, as copy_fs_struct()/exit_fs() used to be), copy_fs_struct() and exit_fs() don't need exports anymore. Signed-off-by: Al Viro --- include/linux/fs_struct.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 18b467dbe278..298cef1c0793 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -20,5 +20,7 @@ extern void set_fs_root(struct fs_struct *, struct path *); extern void set_fs_pwd(struct fs_struct *, struct path *); extern struct fs_struct *copy_fs_struct(struct fs_struct *); extern void put_fs_struct(struct fs_struct *); +extern void daemonize_fs_struct(void); +extern int unshare_fs_struct(void); #endif /* _LINUX_FS_STRUCT_H */ -- cgit v1.2.3 From 498052bba55ecaff58db6a1436b0e25bfd75a7ff Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 30 Mar 2009 07:20:30 -0400 Subject: New locking/refcounting for fs_struct * all changes of current->fs are done under task_lock and write_lock of old fs->lock * refcount is not atomic anymore (same protection) * its decrements are done when removing reference from current; at the same time we decide whether to free it. * put_fs_struct() is gone * new field - ->in_exec. Set by check_unsafe_exec() if we are trying to do execve() and only subthreads share fs_struct. Cleared when finishing exec (success and failure alike). Makes CLONE_FS fail with -EAGAIN if set. * check_unsafe_exec() may fail with -EAGAIN if another execve() from subthread is in progress. Signed-off-by: Al Viro --- fs/compat.c | 16 +++++++++-- fs/exec.c | 31 +++++++++++++++++---- fs/fs_struct.c | 69 +++++++++++++++++++++++++++++++++-------------- fs/internal.h | 2 +- fs/proc/task_nommu.c | 2 +- include/linux/fs_struct.h | 8 +++--- kernel/fork.c | 37 ++++++++++++++++++------- 7 files changed, 121 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/fs/compat.c b/fs/compat.c index 55efdfebdf5a..baabf203b847 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -51,6 +51,7 @@ #include #include #include +#include #include #include @@ -1441,12 +1442,15 @@ 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 +1492,9 @@ 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 +1513,11 @@ 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/exec.c b/fs/exec.c index c5128fbc9165..07a059664b73 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1056,16 +1056,18 @@ 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; + 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) @@ -1073,11 +1075,19 @@ void check_unsafe_exec(struct linux_binprm *bprm) n_sighand++; } - if (atomic_read(&p->fs->count) > n_fs || - atomic_read(&p->sighand->count) > n_sighand) + if (p->fs->users > n_fs || + atomic_read(&p->sighand->count) > n_sighand) { 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 +1306,15 @@ 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 +1357,9 @@ 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 +1378,11 @@ 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/fs_struct.c b/fs/fs_struct.c index 36e0a123bbf3..41cff72b377b 100644 --- a/fs/fs_struct.c +++ b/fs/fs_struct.c @@ -72,25 +72,27 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root) path_put(old_root); } -void put_fs_struct(struct fs_struct *fs) +void free_fs_struct(struct fs_struct *fs) { - /* No need to hold fs->lock if we are killing it */ - if (atomic_dec_and_test(&fs->count)) { - path_put(&fs->root); - path_put(&fs->pwd); - kmem_cache_free(fs_cachep, 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; + 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); - put_fs_struct(fs); + if (kill) + free_fs_struct(fs); } } @@ -99,7 +101,8 @@ 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) { - atomic_set(&fs->count, 1); + fs->users = 1; + fs->in_exec = 0; rwlock_init(&fs->lock); fs->umask = old->umask; read_lock(&old->lock); @@ -114,28 +117,54 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old) int unshare_fs_struct(void) { - struct fs_struct *fsp = copy_fs_struct(current->fs); - if (!fsp) + struct fs_struct *fs = current->fs; + struct fs_struct *new_fs = copy_fs_struct(fs); + int kill; + + if (!new_fs) return -ENOMEM; - exit_fs(current); - current->fs = fsp; + + 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); /* to be mentioned only in INIT_TASK */ struct fs_struct init_fs = { - .count = ATOMIC_INIT(1), + .users = 1, .lock = __RW_LOCK_UNLOCKED(init_fs.lock), .umask = 0022, }; void daemonize_fs_struct(void) { - struct fs_struct *fs; + struct fs_struct *fs = current->fs; + + if (fs) { + int kill; + + task_lock(current); - exit_fs(current); /* current->fs->count--; */ - fs = &init_fs; - current->fs = fs; - atomic_inc(&fs->count); + 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/internal.h b/fs/internal.h index 477a105f8df3..b4dac4fb6b61 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -44,7 +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 diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 343ea1216bc8..6ca01052c5bc 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -49,7 +49,7 @@ 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); diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 298cef1c0793..78a05bfcd8eb 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -4,12 +4,10 @@ #include struct fs_struct { - atomic_t count; /* This usage count is used by check_unsafe_exec() for - * security checking purposes - therefore it may not be - * incremented, except by clone(CLONE_FS). - */ + int users; rwlock_t lock; int umask; + int in_exec; struct path root, pwd; }; @@ -19,7 +17,7 @@ extern void exit_fs(struct task_struct *); extern void set_fs_root(struct fs_struct *, struct path *); extern void set_fs_pwd(struct fs_struct *, struct path *); extern struct fs_struct *copy_fs_struct(struct fs_struct *); -extern void put_fs_struct(struct fs_struct *); +extern void free_fs_struct(struct fs_struct *); extern void daemonize_fs_struct(void); extern int unshare_fs_struct(void); diff --git a/kernel/fork.c b/kernel/fork.c index 05c02dc586b1..51f138a131de 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -683,11 +683,19 @@ fail_nomem: static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) { + struct fs_struct *fs = current->fs; if (clone_flags & CLONE_FS) { - atomic_inc(¤t->fs->count); + /* tsk->fs is already what we want */ + write_lock(&fs->lock); + if (fs->in_exec) { + write_unlock(&fs->lock); + return -EAGAIN; + } + fs->users++; + write_unlock(&fs->lock); return 0; } - tsk->fs = copy_fs_struct(current->fs); + tsk->fs = copy_fs_struct(fs); if (!tsk->fs) return -ENOMEM; return 0; @@ -1518,12 +1526,16 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) { struct fs_struct *fs = current->fs; - if ((unshare_flags & CLONE_FS) && - (fs && atomic_read(&fs->count) > 1)) { - *new_fsp = copy_fs_struct(current->fs); - if (!*new_fsp) - return -ENOMEM; - } + if (!(unshare_flags & CLONE_FS) || !fs) + return 0; + + /* don't need lock here; in the worst case we'll do useless copy */ + if (fs->users == 1) + return 0; + + *new_fsp = copy_fs_struct(fs); + if (!*new_fsp) + return -ENOMEM; return 0; } @@ -1639,8 +1651,13 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) if (new_fs) { fs = current->fs; + write_lock(&fs->lock); current->fs = new_fs; - new_fs = fs; + if (--fs->users) + new_fs = NULL; + else + new_fs = fs; + write_unlock(&fs->lock); } if (new_mm) { @@ -1679,7 +1696,7 @@ bad_unshare_cleanup_sigh: bad_unshare_cleanup_fs: if (new_fs) - put_fs_struct(new_fs); + free_fs_struct(new_fs); bad_unshare_cleanup_thread: bad_unshare_out: -- cgit v1.2.3 From ce3b0f8d5c2203301fc87f3aaaed73e5819e2a48 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 29 Mar 2009 19:08:22 -0400 Subject: New helper - current_umask() current->fs->umask is what most of fs_struct users are doing. Put that into a helper function. Signed-off-by: Al Viro --- arch/powerpc/platforms/cell/spufs/inode.c | 2 +- fs/btrfs/acl.c | 2 +- fs/btrfs/ioctl.c | 2 +- fs/cifs/dir.c | 4 ++-- fs/cifs/inode.c | 4 ++-- fs/ext2/acl.c | 2 +- fs/ext3/acl.c | 2 +- fs/ext4/acl.c | 2 +- fs/fat/inode.c | 2 +- fs/fs_struct.c | 6 ++++++ fs/generic_acl.c | 2 +- fs/gfs2/acl.c | 2 +- fs/hfsplus/options.c | 2 +- fs/hpfs/super.c | 2 +- fs/jffs2/acl.c | 2 +- fs/jfs/acl.c | 2 +- fs/namei.c | 6 +++--- fs/nfs/nfs3proc.c | 6 +++--- fs/nfs/nfs4proc.c | 2 +- fs/ocfs2/acl.c | 2 +- fs/omfs/inode.c | 2 +- fs/reiserfs/xattr_acl.c | 2 +- fs/xfs/linux-2.6/xfs_iops.c | 4 ++-- include/linux/fs.h | 2 ++ ipc/mqueue.c | 2 +- net/unix/af_unix.c | 2 +- 26 files changed, 39 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 64f068540d0d..706eb5c7e2ee 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -635,7 +635,7 @@ long spufs_create(struct nameidata *nd, unsigned int flags, mode_t mode, if (dentry->d_inode) goto out_dput; - mode &= ~current->fs->umask; + mode &= ~current_umask(); if (flags & SPU_CREATE_GANG) ret = spufs_create_gang(nd->path.dentry->d_inode, 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/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/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/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..ab657db4c94e 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -930,7 +930,7 @@ 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_struct.c b/fs/fs_struct.c index 41cff72b377b..6ac219338670 100644 --- a/fs/fs_struct.c +++ b/fs/fs_struct.c @@ -138,6 +138,12 @@ int unshare_fs_struct(void) } 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, 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/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/hpfs/super.c b/fs/hpfs/super.c index 0d049b8919c4..c696d01bc8f7 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -477,7 +477,7 @@ 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/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/namei.c b/fs/namei.c index 4c65a6460138..964c0249444b 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1578,7 +1578,7 @@ 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 +1989,7 @@ 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 +2067,7 @@ 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; diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index c55be7a7679e..e47d4400fb87 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 8dde84b988d9..bbee587dd597 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1509,7 +1509,7 @@ 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/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..aa6fc30772af 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -421,7 +421,7 @@ 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/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/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); diff --git a/include/linux/fs.h b/include/linux/fs.h index 87e7bfc5ebd7..3d7bd5447ca3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1741,6 +1741,8 @@ extern void drop_collected_mounts(struct vfsmount *); extern int vfs_statfs(struct dentry *, struct kstatfs *); +extern int current_umask(void); + /* /sys/fs */ extern struct kobject *fs_kobj; diff --git a/ipc/mqueue.c b/ipc/mqueue.c index a8ddadbc7459..916785363f0f 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -602,7 +602,7 @@ static struct file *do_create(struct dentry *dir, struct dentry *dentry, dentry->d_fsdata = attr; } - mode &= ~current->fs->umask; + mode &= ~current_umask(); ret = mnt_want_write(mqueue_mnt); if (ret) goto out; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index baac91049b0e..9dcc6e7f96ec 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -832,7 +832,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) * All right, let's create it. */ mode = S_IFSOCK | - (SOCK_INODE(sock)->i_mode & ~current->fs->umask); + (SOCK_INODE(sock)->i_mode & ~current_umask()); err = mnt_want_write(nd.path.mnt); if (err) goto out_mknod_dput; -- cgit v1.2.3 From 5ad4e53bd5406ee214ddc5a41f03f779b8b2d526 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 29 Mar 2009 19:50:06 -0400 Subject: Get rid of indirect include of fs_struct.h Don't pull it in sched.h; very few files actually need it and those can include directly. sched.h itself only needs forward declaration of struct fs_struct; Signed-off-by: Al Viro --- arch/cris/kernel/process.c | 1 - fs/dcache.c | 1 + fs/exec.c | 1 + fs/fs_struct.c | 1 + fs/namei.c | 1 + fs/namespace.c | 1 + fs/open.c | 1 + fs/proc/base.c | 1 + fs/proc/task_nommu.c | 1 + include/linux/mnt_namespace.h | 2 ++ include/linux/nsproxy.h | 1 + include/linux/sched.h | 3 ++- init/do_mounts.c | 1 + kernel/auditsc.c | 1 + kernel/exec_domain.c | 1 + kernel/exit.c | 1 + kernel/fork.c | 1 + kernel/sys.c | 1 + security/tomoyo/realpath.c | 1 + 19 files changed, 20 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/cris/kernel/process.c b/arch/cris/kernel/process.c index 60816e876455..4df0b320d524 100644 --- a/arch/cris/kernel/process.c +++ b/arch/cris/kernel/process.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/dcache.c b/fs/dcache.c index 90bbd7e1b116..0dc4de21f088 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -32,6 +32,7 @@ #include #include #include +#include #include "internal.h" int sysctl_vfs_cache_pressure __read_mostly = 100; diff --git a/fs/exec.c b/fs/exec.c index 614991bf0c87..052a961e41aa 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -53,6 +53,7 @@ #include #include #include +#include #include #include diff --git a/fs/fs_struct.c b/fs/fs_struct.c index 6ac219338670..eee059052db5 100644 --- a/fs/fs_struct.c +++ b/fs/fs_struct.c @@ -3,6 +3,7 @@ #include #include #include +#include /* * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values. diff --git a/fs/namei.c b/fs/namei.c index 964c0249444b..b8433ebfae05 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #define ACC_MODE(x) ("\000\004\002\006"[(x)&O_ACCMODE]) diff --git a/fs/namespace.c b/fs/namespace.c index 1e56303c718e..c6f54e4c4290 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include "pnode.h" 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 #include #include +#include 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 #include #include +#include #include "internal.h" /* NOTE: diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 6ca01052c5bc..253afc04484c 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -2,6 +2,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h index 830bbcd449d6..3a059298cc19 100644 --- a/include/linux/mnt_namespace.h +++ b/include/linux/mnt_namespace.h @@ -22,6 +22,8 @@ struct proc_mounts { int event; }; +struct fs_struct; + extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *, struct fs_struct *); extern void __put_mnt_ns(struct mnt_namespace *ns); diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index afad7dec1b36..7b370c7cfeff 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -8,6 +8,7 @@ struct mnt_namespace; struct uts_namespace; struct ipc_namespace; struct pid_namespace; +struct fs_struct; /* * A structure to contain pointers to all per-process diff --git a/include/linux/sched.h b/include/linux/sched.h index 29df6374d2de..b4e065ea0de1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -68,7 +68,7 @@ struct sched_param { #include #include #include -#include +#include #include #include #include @@ -97,6 +97,7 @@ struct futex_pi_state; struct robust_list_head; struct bio; struct bts_tracer; +struct fs_struct; /* * List of flags we want to share for kernel threads, diff --git a/init/do_mounts.c b/init/do_mounts.c index 8d4ff5afc1d8..dd7ee5f203f3 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 8cbddff6c283..2bfc64786765 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -66,6 +66,7 @@ #include #include #include +#include #include "audit.h" diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c index cb8e9626c215..c35452cadded 100644 --- a/kernel/exec_domain.c +++ b/kernel/exec_domain.c @@ -18,6 +18,7 @@ #include #include #include +#include static void default_handler(int, struct pt_regs *); diff --git a/kernel/exit.c b/kernel/exit.c index ad8375758a79..b5d656845c90 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -46,6 +46,7 @@ #include #include #include +#include #include #include diff --git a/kernel/fork.c b/kernel/fork.c index 51f138a131de..e82a14577a98 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -60,6 +60,7 @@ #include #include #include +#include #include #include diff --git a/kernel/sys.c b/kernel/sys.c index 37f458e6882a..ce182aaed204 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include diff --git a/security/tomoyo/realpath.c b/security/tomoyo/realpath.c index d47f16b844b2..3bbe01a7a4b5 100644 --- a/security/tomoyo/realpath.c +++ b/security/tomoyo/realpath.c @@ -12,6 +12,7 @@ #include #include #include +#include #include "common.h" #include "realpath.h" -- cgit v1.2.3 From 47e4491b40df73c3b117e3d80b31b5b512a4b19f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 1 Apr 2009 07:07:16 -0400 Subject: Cleanup after commit 585d3bc06f4ca57f975a5a1f698f65a45ea66225 fsync_bdev() export and a bunch of stubs for !CONFIG_BLOCK case had been left behind Signed-off-by: Al Viro --- fs/block_dev.c | 1 + fs/buffer.c | 1 - include/linux/buffer_head.h | 12 ------------ include/linux/fs.h | 12 ++++++++++++ 4 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') 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/buffer.c b/fs/buffer.c index a2fd743d97cb..b71e52925c83 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3281,7 +3281,6 @@ 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/include/linux/buffer_head.h b/include/linux/buffer_head.h index f19fd9045ea0..fc91665d39d0 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -332,22 +332,10 @@ extern int __set_page_dirty_buffers(struct page *page); static inline void buffer_init(void) {} static inline int try_to_free_buffers(struct page *page) { return 1; } -static inline int sync_blockdev(struct block_device *bdev) { return 0; } static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } -static inline void invalidate_bdev(struct block_device *bdev) {} - -static inline struct super_block *freeze_bdev(struct block_device *sb) -{ - return NULL; -} - -static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb) -{ - return 0; -} #endif /* CONFIG_BLOCK */ #endif /* _LINUX_BUFFER_HEAD_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 3d7bd5447ca3..674134725597 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1886,6 +1886,18 @@ extern int fsync_super(struct super_block *); extern int fsync_no_super(struct block_device *); #else static inline void bd_forget(struct inode *inode) {} +static inline int sync_blockdev(struct block_device *bdev) { return 0; } +static inline void invalidate_bdev(struct block_device *bdev) {} + +static inline struct super_block *freeze_bdev(struct block_device *sb) +{ + return NULL; +} + +static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb) +{ + return 0; +} #endif extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; -- cgit v1.2.3 From ced117c73edc917e96dea7cca98c91383f0792f7 Mon Sep 17 00:00:00 2001 From: Dmitri Vorobiev Date: Tue, 31 Mar 2009 00:41:20 +0300 Subject: Remove two unneeded exports and make two symbols static in fs/mpage.c Commit 29a814d2ee0e43c2980f33f91c1311ec06c0aa35 (vfs: add hooks for ext4's delayed allocation support) exported the following functions mpage_bio_submit() __mpage_writepage() for the benefit of ext4's delayed allocation support. Since commit a1d6cc563bfdf1bf2829d3e6ce4d8b774251796b (ext4: Rework the ext4_da_writepages() function), these functions are not used by the ext4 driver anymore. However, the now unnecessary exports still remain, and this patch removes those. Moreover, these two functions can become static again. The issue was spotted by namespacecheck. Signed-off-by: Dmitri Vorobiev Reviewed-by: Aneesh Kumar K.V Signed-off-by: Al Viro --- fs/mpage.c | 13 +++++++++---- include/linux/mpage.h | 10 ---------- 2 files changed, 9 insertions(+), 14 deletions(-) (limited to 'include/linux') 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/include/linux/mpage.h b/include/linux/mpage.h index 5c42821da2d1..068a0c9946af 100644 --- a/include/linux/mpage.h +++ b/include/linux/mpage.h @@ -11,21 +11,11 @@ */ #ifdef CONFIG_BLOCK -struct mpage_data { - struct bio *bio; - sector_t last_block_in_bio; - get_block_t *get_block; - unsigned use_writepage; -}; - struct writeback_control; -struct bio *mpage_bio_submit(int rw, struct bio *bio); int mpage_readpages(struct address_space *mapping, struct list_head *pages, unsigned nr_pages, get_block_t get_block); int mpage_readpage(struct page *page, get_block_t get_block); -int __mpage_writepage(struct page *page, struct writeback_control *wbc, - void *data); int mpage_writepages(struct address_space *mapping, struct writeback_control *wbc, get_block_t get_block); int mpage_writepage(struct page *page, get_block_t *get_block, -- cgit v1.2.3 From ee3b4290aec03022cfb67c9adba9f1b3215245f0 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Thu, 2 Apr 2009 16:56:30 -0700 Subject: generic debug pagealloc: build fix This fixes a build failure with generic debug pagealloc: mm/debug-pagealloc.c: In function 'set_page_poison': mm/debug-pagealloc.c:8: error: 'struct page' has no member named 'debug_flags' mm/debug-pagealloc.c: In function 'clear_page_poison': mm/debug-pagealloc.c:13: error: 'struct page' has no member named 'debug_flags' mm/debug-pagealloc.c: In function 'page_poison': mm/debug-pagealloc.c:18: error: 'struct page' has no member named 'debug_flags' mm/debug-pagealloc.c: At top level: mm/debug-pagealloc.c:120: error: redefinition of 'kernel_map_pages' include/linux/mm.h:1278: error: previous definition of 'kernel_map_pages' was here mm/debug-pagealloc.c: In function 'kernel_map_pages': mm/debug-pagealloc.c:122: error: 'debug_pagealloc_enabled' undeclared (first use in this function) by fixing - debug_flags should be in struct page - define DEBUG_PAGEALLOC config option for all architectures Signed-off-by: Akinobu Mita Reported-by: Alexander Beregalov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/Kconfig.debug | 10 ---------- arch/s390/Kconfig.debug | 9 --------- arch/sparc/Kconfig.debug | 9 --------- arch/x86/Kconfig.debug | 9 --------- include/linux/mm_types.h | 6 +++--- mm/Kconfig.debug | 9 +++++++++ 6 files changed, 12 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index 6aa0b5e087cd..a1098e23221f 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -27,16 +27,6 @@ config DEBUG_STACK_USAGE This option will slow down process creation somewhat. -config DEBUG_PAGEALLOC - bool "Debug page memory allocations" - depends on DEBUG_KERNEL && !HIBERNATION - depends on ARCH_SUPPORTS_DEBUG_PAGEALLOC - help - Unmap pages from the kernel linear mapping after free_pages(). - This results in a large slowdown, but helps to find certain types - of memory corruptions. - - config HCALL_STATS bool "Hypervisor call instrumentation" depends on PPC_PSERIES && DEBUG_FS diff --git a/arch/s390/Kconfig.debug b/arch/s390/Kconfig.debug index 7e297a3cde34..2283933a9a93 100644 --- a/arch/s390/Kconfig.debug +++ b/arch/s390/Kconfig.debug @@ -6,13 +6,4 @@ config TRACE_IRQFLAGS_SUPPORT source "lib/Kconfig.debug" -config DEBUG_PAGEALLOC - bool "Debug page memory allocations" - depends on DEBUG_KERNEL - depends on ARCH_SUPPORTS_DEBUG_PAGEALLOC - help - Unmap pages from the kernel linear mapping after free_pages(). - This results in a slowdown, but helps to find certain types of - memory corruptions. - endmenu diff --git a/arch/sparc/Kconfig.debug b/arch/sparc/Kconfig.debug index d001b42041a5..90d5fe223a74 100644 --- a/arch/sparc/Kconfig.debug +++ b/arch/sparc/Kconfig.debug @@ -22,15 +22,6 @@ config DEBUG_DCFLUSH config STACK_DEBUG bool "Stack Overflow Detection Support" -config DEBUG_PAGEALLOC - bool "Debug page memory allocations" - depends on DEBUG_KERNEL && !HIBERNATION - depends on ARCH_SUPPORTS_DEBUG_PAGEALLOC - help - Unmap pages from the kernel linear mapping after free_pages(). - This results in a large slowdown, but helps to find certain types - of memory corruptions. - config MCOUNT bool depends on SPARC64 diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index a345cb5447a8..d8359e73317f 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -72,15 +72,6 @@ config DEBUG_STACK_USAGE This option will slow down process creation somewhat. -config DEBUG_PAGEALLOC - bool "Debug page memory allocations" - depends on DEBUG_KERNEL - depends on ARCH_SUPPORTS_DEBUG_PAGEALLOC - ---help--- - Unmap pages from the kernel linear mapping after free_pages(). - This results in a large slowdown, but helps to find certain types - of memory corruptions. - config DEBUG_PER_CPU_MAPS bool "Debug access to per_cpu maps" depends on DEBUG_KERNEL diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index ddadb4defe00..0e80e26ecf21 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -95,6 +95,9 @@ struct page { void *virtual; /* Kernel virtual address (NULL if not kmapped, ie. highmem) */ #endif /* WANT_PAGE_VIRTUAL */ +#ifdef CONFIG_WANT_PAGE_DEBUG_FLAGS + unsigned long debug_flags; /* Use atomic bitops on this */ +#endif }; /* @@ -175,9 +178,6 @@ struct vm_area_struct { #ifdef CONFIG_NUMA struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif -#ifdef CONFIG_WANT_PAGE_DEBUG_FLAGS - unsigned long debug_flags; /* Use atomic bitops on this */ -#endif }; struct core_thread { diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug index c8d62d49a44e..bb01e298f260 100644 --- a/mm/Kconfig.debug +++ b/mm/Kconfig.debug @@ -1,3 +1,12 @@ +config DEBUG_PAGEALLOC + bool "Debug page memory allocations" + depends on DEBUG_KERNEL && ARCH_SUPPORTS_DEBUG_PAGEALLOC + depends on !HIBERNATION || !PPC && !SPARC + ---help--- + Unmap pages from the kernel linear mapping after free_pages(). + This results in a large slowdown, but helps to find certain types + of memory corruptions. + config WANT_PAGE_DEBUG_FLAGS bool -- cgit v1.2.3 From 33e5d76979cf01e3834814fe0aea569d1d602c1a Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 2 Apr 2009 16:56:32 -0700 Subject: nommu: fix a number of issues with the per-MM VMA patch Fix a number of issues with the per-MM VMA patch: (1) Make mmap_pages_allocated an atomic_long_t, just in case this is used on a NOMMU system with more than 2G pages. Makes no difference on a 32-bit system. (2) Report vma->vm_pgoff * PAGE_SIZE as a 64-bit value, not a 32-bit value, lest it overflow. (3) Move the allocation of the vm_area_struct slab back for fork.c. (4) Use KMEM_CACHE() for both vm_area_struct and vm_region slabs. (5) Use BUG_ON() rather than if () BUG(). (6) Make the default validate_nommu_regions() a static inline rather than a #define. (7) Make free_page_series()'s objection to pages with a refcount != 1 more informative. (8) Adjust the __put_nommu_region() banner comment to indicate that the semaphore must be held for writing. (9) Limit the number of warnings about munmaps of non-mmapped regions. Reported-by: Andrew Morton Signed-off-by: David Howells Cc: Greg Ungerer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/meminfo.c | 2 +- fs/proc/task_nommu.c | 4 ++-- include/linux/mm.h | 2 +- kernel/fork.c | 1 + mm/mmap.c | 3 --- mm/nommu.c | 52 +++++++++++++++++++++++++--------------------------- 6 files changed, 30 insertions(+), 34 deletions(-) (limited to 'include/linux') 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..370be0a2c909 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -136,14 +136,14 @@ 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/include/linux/mm.h b/include/linux/mm.h index aeabe953ba4f..bff1f0d475c7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1079,7 +1079,7 @@ static inline void setup_per_cpu_pageset(void) {} #endif /* nommu.c */ -extern atomic_t mmap_pages_allocated; +extern atomic_long_t mmap_pages_allocated; /* prio_tree.c */ void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old); diff --git a/kernel/fork.c b/kernel/fork.c index 47c15840a381..51d1aa21483b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1488,6 +1488,7 @@ void __init proc_caches_init(void) mm_cachep = kmem_cache_create("mm_struct", sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC); mmap_init(); } diff --git a/mm/mmap.c b/mm/mmap.c index 1abb9185a686..4a3841186c11 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2481,7 +2481,4 @@ void mm_drop_all_locks(struct mm_struct *mm) */ void __init mmap_init(void) { - vm_area_cachep = kmem_cache_create("vm_area_struct", - sizeof(struct vm_area_struct), 0, - SLAB_PANIC, NULL); } diff --git a/mm/nommu.c b/mm/nommu.c index 2fcf47d449b4..72eda4aee2cb 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -69,7 +69,7 @@ int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT; int sysctl_nr_trim_pages = 1; /* page trimming behaviour */ int heap_stack_gap = 0; -atomic_t mmap_pages_allocated; +atomic_long_t mmap_pages_allocated; EXPORT_SYMBOL(mem_map); EXPORT_SYMBOL(num_physpages); @@ -463,12 +463,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) */ void __init mmap_init(void) { - vm_region_jar = kmem_cache_create("vm_region_jar", - sizeof(struct vm_region), 0, - SLAB_PANIC, NULL); - vm_area_cachep = kmem_cache_create("vm_area_struct", - sizeof(struct vm_area_struct), 0, - SLAB_PANIC, NULL); + vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC); } /* @@ -486,27 +481,24 @@ static noinline void validate_nommu_regions(void) return; last = rb_entry(lastp, struct vm_region, vm_rb); - if (unlikely(last->vm_end <= last->vm_start)) - BUG(); - if (unlikely(last->vm_top < last->vm_end)) - BUG(); + BUG_ON(unlikely(last->vm_end <= last->vm_start)); + BUG_ON(unlikely(last->vm_top < last->vm_end)); while ((p = rb_next(lastp))) { region = rb_entry(p, struct vm_region, vm_rb); last = rb_entry(lastp, struct vm_region, vm_rb); - if (unlikely(region->vm_end <= region->vm_start)) - BUG(); - if (unlikely(region->vm_top < region->vm_end)) - BUG(); - if (unlikely(region->vm_start < last->vm_top)) - BUG(); + BUG_ON(unlikely(region->vm_end <= region->vm_start)); + BUG_ON(unlikely(region->vm_top < region->vm_end)); + BUG_ON(unlikely(region->vm_start < last->vm_top)); lastp = p; } } #else -#define validate_nommu_regions() do {} while(0) +static void validate_nommu_regions(void) +{ +} #endif /* @@ -563,16 +555,17 @@ static void free_page_series(unsigned long from, unsigned long to) struct page *page = virt_to_page(from); kdebug("- free %lx", from); - atomic_dec(&mmap_pages_allocated); + atomic_long_dec(&mmap_pages_allocated); if (page_count(page) != 1) - kdebug("free page %p [%d]", page, page_count(page)); + kdebug("free page %p: refcount not one: %d", + page, page_count(page)); put_page(page); } } /* * release a reference to a region - * - the caller must hold the region semaphore, which this releases + * - the caller must hold the region semaphore for writing, which this releases * - the region may not have been added to the tree yet, in which case vm_top * will equal vm_start */ @@ -1096,7 +1089,7 @@ static int do_mmap_private(struct vm_area_struct *vma, goto enomem; total = 1 << order; - atomic_add(total, &mmap_pages_allocated); + atomic_long_add(total, &mmap_pages_allocated); point = rlen >> PAGE_SHIFT; @@ -1107,7 +1100,7 @@ static int do_mmap_private(struct vm_area_struct *vma, order = ilog2(total - point); n = 1 << order; kdebug("shave %lu/%lu @%lu", n, total - point, total); - atomic_sub(n, &mmap_pages_allocated); + atomic_long_sub(n, &mmap_pages_allocated); total -= n; set_page_refcounted(pages + total); __free_pages(pages + total, order); @@ -1536,10 +1529,15 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) /* find the first potentially overlapping VMA */ vma = find_vma(mm, start); if (!vma) { - printk(KERN_WARNING - "munmap of memory not mmapped by process %d (%s):" - " 0x%lx-0x%lx\n", - current->pid, current->comm, start, start + len - 1); + static int limit = 0; + if (limit < 5) { + printk(KERN_WARNING + "munmap of memory not mmapped by process %d" + " (%s): 0x%lx-0x%lx\n", + current->pid, current->comm, + start, start + len - 1); + limit++; + } return -EINVAL; } -- cgit v1.2.3 From 8e2c3795c78d5c4e2e1f14ce751e9d08decbe9d3 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Thu, 2 Apr 2009 16:56:44 -0700 Subject: add fiemap.h to header-y Include fiemap.h in header-y; it defines the interface for the FS_IOC_FIEMAP file mapping ioctl. Signed-off-by: Eric Sandeen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/Kbuild | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index a67b6227d272..ca9b9b9bd331 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -67,6 +67,7 @@ header-y += falloc.h header-y += fd.h header-y += fdreg.h header-y += fib_rules.h +header-y += fiemap.h header-y += firewire-cdev.h header-y += firewire-constants.h header-y += fuse.h -- cgit v1.2.3 From 9a896c9a48ac6704c0ce8ee081b836644d0afe40 Mon Sep 17 00:00:00 2001 From: Lee Schermerhorn Date: Thu, 2 Apr 2009 16:56:45 -0700 Subject: mm: define a UNIQUE value for AS_UNEVICTABLE flag A new "address_space flag"--AS_MM_ALL_LOCKS--was defined to use the next available AS flag while the Unevictable LRU was under development. The Unevictable LRU was using the same flag and "no one" noticed. Current mainline, since 2.6.28, has same value for two symbolic flag names. So, define a unique flag value for AS_UNEVICTABLE--up close to the other flags, [at the cost of an additional #ifdef] so we'll notice next time. Note that #ifdef is not actually required, if we don't mind having the unused flag value defined. Replace #defines with an enum. Signed-off-by: Lee Schermerhorn Cc: [2.6.28.x, 2.6.29.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 01ca0856caff..076a7dc67c2b 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -18,9 +18,14 @@ * Bits in mapping->flags. The lower __GFP_BITS_SHIFT bits are the page * allocation mode flags. */ -#define AS_EIO (__GFP_BITS_SHIFT + 0) /* IO error on async write */ -#define AS_ENOSPC (__GFP_BITS_SHIFT + 1) /* ENOSPC on async write */ -#define AS_MM_ALL_LOCKS (__GFP_BITS_SHIFT + 2) /* under mm_take_all_locks() */ +enum mapping_flags { + AS_EIO = __GFP_BITS_SHIFT + 0, /* IO error on async write */ + AS_ENOSPC = __GFP_BITS_SHIFT + 1, /* ENOSPC on async write */ + AS_MM_ALL_LOCKS = __GFP_BITS_SHIFT + 2, /* under mm_take_all_locks() */ +#ifdef CONFIG_UNEVICTABLE_LRU + AS_UNEVICTABLE = __GFP_BITS_SHIFT + 3, /* e.g., ramdisk, SHM_LOCK */ +#endif +}; static inline void mapping_set_error(struct address_space *mapping, int error) { @@ -33,7 +38,6 @@ static inline void mapping_set_error(struct address_space *mapping, int error) } #ifdef CONFIG_UNEVICTABLE_LRU -#define AS_UNEVICTABLE (__GFP_BITS_SHIFT + 2) /* e.g., ramdisk, SHM_LOCK */ static inline void mapping_set_unevictable(struct address_space *mapping) { -- cgit v1.2.3 From bf6aede712334d7338d5c47a5ee5ba3883c82a61 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 2 Apr 2009 16:56:54 -0700 Subject: workqueue: add to_delayed_work() helper function It is a fairly common operation to have a pointer to a work and to need a pointer to the delayed work it is contained in. In particular, all delayed works which want to rearm themselves will have to do that. So it would seem fair to offer a helper function for this operation. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Jean Delvare Acked-by: Ingo Molnar Cc: "David S. Miller" Cc: Herbert Xu Cc: Benjamin Herrenschmidt Cc: Martin Schwidefsky Cc: Greg KH Cc: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/kernel/vio.c | 2 +- drivers/crypto/hifn_795x.c | 2 +- drivers/input/mouse/hgpk.c | 2 +- drivers/net/dm9000.c | 2 +- drivers/net/mlx4/en_netdev.c | 2 +- drivers/net/mlx4/en_rx.c | 2 +- drivers/net/mlx4/sense.c | 2 +- drivers/net/phy/phy.c | 3 +-- drivers/s390/scsi/zfcp_fc.c | 2 +- drivers/staging/rtl8187se/ieee80211/ieee80211_softmac.c | 8 ++++---- drivers/staging/rtl8187se/r8180_core.c | 8 ++++---- drivers/usb/wusbcore/devconnect.c | 2 +- include/linux/workqueue.h | 5 +++++ mm/slab.c | 3 +-- 14 files changed, 24 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index d3694498f3af..819e59f6f7c7 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -482,7 +482,7 @@ static void vio_cmo_balance(struct work_struct *work) cmo->excess.size = cmo->entitled - cmo->reserve.size; cmo->excess.free = cmo->excess.size - need; - cancel_delayed_work(container_of(work, struct delayed_work, work)); + cancel_delayed_work(to_delayed_work(work)); spin_unlock_irqrestore(&vio_cmo.lock, flags); } diff --git a/drivers/crypto/hifn_795x.c b/drivers/crypto/hifn_795x.c index 0c79fe7f1567..4d85402a9e4a 100644 --- a/drivers/crypto/hifn_795x.c +++ b/drivers/crypto/hifn_795x.c @@ -1882,7 +1882,7 @@ static void hifn_clear_rings(struct hifn_device *dev, int error) static void hifn_work(struct work_struct *work) { - struct delayed_work *dw = container_of(work, struct delayed_work, work); + struct delayed_work *dw = to_delayed_work(work); struct hifn_device *dev = container_of(dw, struct hifn_device, work); unsigned long flags; int reset = 0; diff --git a/drivers/input/mouse/hgpk.c b/drivers/input/mouse/hgpk.c index 81e6ebf323e9..55cd0fa68339 100644 --- a/drivers/input/mouse/hgpk.c +++ b/drivers/input/mouse/hgpk.c @@ -381,7 +381,7 @@ static void hgpk_disconnect(struct psmouse *psmouse) static void hgpk_recalib_work(struct work_struct *work) { - struct delayed_work *w = container_of(work, struct delayed_work, work); + struct delayed_work *w = to_delayed_work(work); struct hgpk_data *priv = container_of(w, struct hgpk_data, recalib_wq); struct psmouse *psmouse = priv->psmouse; diff --git a/drivers/net/dm9000.c b/drivers/net/dm9000.c index 254ec62b5f58..d8350860c0f8 100644 --- a/drivers/net/dm9000.c +++ b/drivers/net/dm9000.c @@ -559,7 +559,7 @@ static void dm9000_show_carrier(board_info_t *db, static void dm9000_poll_work(struct work_struct *w) { - struct delayed_work *dw = container_of(w, struct delayed_work, work); + struct delayed_work *dw = to_delayed_work(w); board_info_t *db = container_of(dw, board_info_t, phy_poll); struct net_device *ndev = db->ndev; diff --git a/drivers/net/mlx4/en_netdev.c b/drivers/net/mlx4/en_netdev.c index 9f6644a44030..303c23de6cac 100644 --- a/drivers/net/mlx4/en_netdev.c +++ b/drivers/net/mlx4/en_netdev.c @@ -505,7 +505,7 @@ out: static void mlx4_en_do_get_stats(struct work_struct *work) { - struct delayed_work *delay = container_of(work, struct delayed_work, work); + struct delayed_work *delay = to_delayed_work(work); struct mlx4_en_priv *priv = container_of(delay, struct mlx4_en_priv, stats_task); struct mlx4_en_dev *mdev = priv->mdev; diff --git a/drivers/net/mlx4/en_rx.c b/drivers/net/mlx4/en_rx.c index a4130e764991..7e40741fb7d8 100644 --- a/drivers/net/mlx4/en_rx.c +++ b/drivers/net/mlx4/en_rx.c @@ -298,7 +298,7 @@ static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv, void mlx4_en_rx_refill(struct work_struct *work) { - struct delayed_work *delay = container_of(work, struct delayed_work, work); + struct delayed_work *delay = to_delayed_work(work); struct mlx4_en_priv *priv = container_of(delay, struct mlx4_en_priv, refill_task); struct mlx4_en_dev *mdev = priv->mdev; diff --git a/drivers/net/mlx4/sense.c b/drivers/net/mlx4/sense.c index 6d5089ecb5af..f36ae691cab3 100644 --- a/drivers/net/mlx4/sense.c +++ b/drivers/net/mlx4/sense.c @@ -103,7 +103,7 @@ void mlx4_do_sense_ports(struct mlx4_dev *dev, static void mlx4_sense_port(struct work_struct *work) { - struct delayed_work *delay = container_of(work, struct delayed_work, work); + struct delayed_work *delay = to_delayed_work(work); struct mlx4_sense *sense = container_of(delay, struct mlx4_sense, sense_poll); struct mlx4_dev *dev = sense->dev; diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 58b73b08dde0..3ff1f425f1bb 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -757,8 +757,7 @@ EXPORT_SYMBOL(phy_start); */ static void phy_state_machine(struct work_struct *work) { - struct delayed_work *dwork = - container_of(work, struct delayed_work, work); + struct delayed_work *dwork = to_delayed_work(work); struct phy_device *phydev = container_of(dwork, struct phy_device, state_queue); int needs_aneg = 0; diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c index aab8123c5966..e8d032b9dfbd 100644 --- a/drivers/s390/scsi/zfcp_fc.c +++ b/drivers/s390/scsi/zfcp_fc.c @@ -94,7 +94,7 @@ static int zfcp_wka_port_get(struct zfcp_wka_port *wka_port) static void zfcp_wka_port_offline(struct work_struct *work) { - struct delayed_work *dw = container_of(work, struct delayed_work, work); + struct delayed_work *dw = to_delayed_work(work); struct zfcp_wka_port *wka_port = container_of(dw, struct zfcp_wka_port, work); diff --git a/drivers/staging/rtl8187se/ieee80211/ieee80211_softmac.c b/drivers/staging/rtl8187se/ieee80211/ieee80211_softmac.c index e5752f615e09..80f9cc7137c2 100644 --- a/drivers/staging/rtl8187se/ieee80211/ieee80211_softmac.c +++ b/drivers/staging/rtl8187se/ieee80211/ieee80211_softmac.c @@ -719,7 +719,7 @@ void ieee80211_softmac_scan(struct ieee80211_device *ieee) #if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,20)) void ieee80211_softmac_scan_wq(struct work_struct *work) { - struct delayed_work *dwork = container_of(work, struct delayed_work, work); + struct delayed_work *dwork = to_delayed_work(work); struct ieee80211_device *ieee = container_of(dwork, struct ieee80211_device, softmac_scan_wq); #else void ieee80211_softmac_scan_wq(struct ieee80211_device *ieee) @@ -777,7 +777,7 @@ out: #if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,20)) void ieee80211_softmac_scan_wq(struct work_struct *work) { - struct delayed_work *dwork = container_of(work, struct delayed_work, work); + struct delayed_work *dwork = to_delayed_work(work); struct ieee80211_device *ieee = container_of(work, struct ieee80211_device, softmac_scan_wq); #else void ieee80211_softmac_scan_wq(struct ieee80211_device *ieee) @@ -2980,7 +2980,7 @@ void ieee80211_start_monitor_mode(struct ieee80211_device *ieee) #if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,20)) void ieee80211_start_ibss_wq(struct work_struct *work) { - struct delayed_work *dwork = container_of(work, struct delayed_work, work); + struct delayed_work *dwork = to_delayed_work(work); struct ieee80211_device *ieee = container_of(dwork, struct ieee80211_device, start_ibss_wq); #else void ieee80211_start_ibss_wq(struct ieee80211_device *ieee) @@ -3162,7 +3162,7 @@ void ieee80211_disassociate(struct ieee80211_device *ieee) #if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,20)) void ieee80211_associate_retry_wq(struct work_struct *work) { - struct delayed_work *dwork = container_of(work, struct delayed_work, work); + struct delayed_work *dwork = to_delayed_work(work); struct ieee80211_device *ieee = container_of(dwork, struct ieee80211_device, associate_retry_wq); #else void ieee80211_associate_retry_wq(struct ieee80211_device *ieee) diff --git a/drivers/staging/rtl8187se/r8180_core.c b/drivers/staging/rtl8187se/r8180_core.c index 66de5cc8ddf1..ff1f23f99f27 100644 --- a/drivers/staging/rtl8187se/r8180_core.c +++ b/drivers/staging/rtl8187se/r8180_core.c @@ -5438,7 +5438,7 @@ void rtl8180_hw_wakeup_wq (struct work_struct *work) // struct r8180_priv *priv = container_of(work, struct r8180_priv, watch_dog_wq); // struct ieee80211_device * ieee = (struct ieee80211_device*) // container_of(work, struct ieee80211_device, watch_dog_wq); - struct delayed_work *dwork = container_of(work,struct delayed_work,work); + struct delayed_work *dwork = to_delayed_work(work); struct ieee80211_device *ieee = container_of(dwork,struct ieee80211_device,hw_wakeup_wq); struct net_device *dev = ieee->dev; #else @@ -5459,7 +5459,7 @@ void rtl8180_hw_sleep_wq (struct work_struct *work) // struct r8180_priv *priv = container_of(work, struct r8180_priv, watch_dog_wq); // struct ieee80211_device * ieee = (struct ieee80211_device*) // container_of(work, struct ieee80211_device, watch_dog_wq); - struct delayed_work *dwork = container_of(work,struct delayed_work,work); + struct delayed_work *dwork = to_delayed_work(work); struct ieee80211_device *ieee = container_of(dwork,struct ieee80211_device,hw_sleep_wq); struct net_device *dev = ieee->dev; #else @@ -6407,7 +6407,7 @@ priv->txnpring)/8); void rtl8180_tx_irq_wq(struct work_struct *work) { //struct r8180_priv *priv = container_of(work, struct r8180_priv, reset_wq); - struct delayed_work *dwork = container_of(work,struct delayed_work,work); + struct delayed_work *dwork = to_delayed_work(work); struct ieee80211_device * ieee = (struct ieee80211_device*) container_of(dwork, struct ieee80211_device, watch_dog_wq); struct net_device *dev = ieee->dev; @@ -6691,7 +6691,7 @@ lizhaoming--------------------------- RF power on/power off ----------------- #if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,20)) void GPIOChangeRFWorkItemCallBack(struct work_struct *work) { - //struct delayed_work *dwork = container_of(work, struct delayed_work, work); + //struct delayed_work *dwork = to_delayed_work(work); struct ieee80211_device *ieee = container_of(work, struct ieee80211_device, GPIOChangeRFWorkItem.work); struct net_device *dev = ieee->dev; struct r8180_priv *priv = ieee80211_priv(dev); diff --git a/drivers/usb/wusbcore/devconnect.c b/drivers/usb/wusbcore/devconnect.c index f0aac0cf315a..386eaa22d215 100644 --- a/drivers/usb/wusbcore/devconnect.c +++ b/drivers/usb/wusbcore/devconnect.c @@ -471,7 +471,7 @@ static void __wusbhc_keep_alive(struct wusbhc *wusbhc) */ static void wusbhc_keep_alive_run(struct work_struct *ws) { - struct delayed_work *dw = container_of(ws, struct delayed_work, work); + struct delayed_work *dw = to_delayed_work(ws); struct wusbhc *wusbhc = container_of(dw, struct wusbhc, keep_alive_timer); mutex_lock(&wusbhc->mutex); diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 3cd51e579ab1..13e1adf55c4c 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -41,6 +41,11 @@ struct delayed_work { struct timer_list timer; }; +static inline struct delayed_work *to_delayed_work(struct work_struct *work) +{ + return container_of(work, struct delayed_work, work); +} + struct execute_work { struct work_struct work; }; diff --git a/mm/slab.c b/mm/slab.c index 825c606f691d..208323fd37bc 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3992,8 +3992,7 @@ static void cache_reap(struct work_struct *w) struct kmem_cache *searchp; struct kmem_list3 *l3; int node = numa_node_id(); - struct delayed_work *work = - container_of(w, struct delayed_work, work); + struct delayed_work *work = to_delayed_work(w); if (!mutex_trylock(&cache_chain_mutex)) /* Give up. Setup the next iteration. */ -- cgit v1.2.3 From 06c421ee0d5af95c8c6749ca0ba620cd5010707f Mon Sep 17 00:00:00 2001 From: Kevin Hilman Date: Thu, 2 Apr 2009 16:56:56 -0700 Subject: memory_accessor: new interface for reading/writing persistent memory Add an interface by which other kernel code can read/write persistent memory such as I2C or SPI EEPROMs, or devices which provide NVRAM. Use cases include storage of board-specific configuration data like Ethernet addresses and sensor calibrations. Original idea, review and improvement suggestions by David Brownell. Acked-by: David Brownell Signed-off-by: Kevin Hilman Cc: Jean Delvare Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 3fdc10806d31..42767d1a62e7 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -99,4 +99,15 @@ enum mem_add_context { BOOT, HOTPLUG }; #define hotplug_memory_notifier(fn, pri) do { } while (0) #endif +/* + * 'struct memory_accessor' is a generic interface to provide + * in-kernel access to persistent memory such as i2c or SPI EEPROMs + */ +struct memory_accessor { + ssize_t (*read)(struct memory_accessor *, char *buf, off_t offset, + size_t count); + ssize_t (*write)(struct memory_accessor *, const char *buf, + off_t offset, size_t count); +}; + #endif /* _LINUX_MEMORY_H_ */ -- cgit v1.2.3 From 7274ec8bd71e99018642f474528ea7de4bb3ae25 Mon Sep 17 00:00:00 2001 From: Kevin Hilman Date: Thu, 2 Apr 2009 16:56:57 -0700 Subject: memory_accessor: implement the new memory_accessor interface for I2C EEPROM In the case of at24, the platform code registers a 'setup' callback with the at24_platform_data. When the at24 driver detects an EEPROM, it fills out the read and write functions of the memory_accessor and calls the setup callback passing the memory_accessor struct. The platform code can then use the read/write functions in the memory_accessor struct for reading and writing the EEPROM. Signed-off-by: Kevin Hilman Cc: David Brownell Cc: Jean Delvare Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/misc/eeprom/at24.c | 67 +++++++++++++++++++++++++++++++++++++--------- include/linux/i2c/at24.h | 4 +++ 2 files changed, 58 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index d4775528abc6..d184dfab9631 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -53,6 +53,7 @@ struct at24_data { struct at24_platform_data chip; + struct memory_accessor macc; bool use_smbus; /* @@ -225,14 +226,11 @@ static ssize_t at24_eeprom_read(struct at24_data *at24, char *buf, return status; } -static ssize_t at24_bin_read(struct kobject *kobj, struct bin_attribute *attr, +static ssize_t at24_read(struct at24_data *at24, char *buf, loff_t off, size_t count) { - struct at24_data *at24; ssize_t retval = 0; - at24 = dev_get_drvdata(container_of(kobj, struct device, kobj)); - if (unlikely(!count)) return count; @@ -262,12 +260,14 @@ static ssize_t at24_bin_read(struct kobject *kobj, struct bin_attribute *attr, return retval; } +static ssize_t at24_bin_read(struct kobject *kobj, struct bin_attribute *attr, + char *buf, loff_t off, size_t count) +{ + struct at24_data *at24; -/* - * REVISIT: export at24_bin{read,write}() to let other kernel code use - * eeprom data. For example, it might hold a board's Ethernet address, or - * board-specific calibration data generated on the manufacturing floor. - */ + at24 = dev_get_drvdata(container_of(kobj, struct device, kobj)); + return at24_read(at24, buf, off, count); +} /* @@ -347,14 +347,11 @@ static ssize_t at24_eeprom_write(struct at24_data *at24, char *buf, return -ETIMEDOUT; } -static ssize_t at24_bin_write(struct kobject *kobj, struct bin_attribute *attr, +static ssize_t at24_write(struct at24_data *at24, char *buf, loff_t off, size_t count) { - struct at24_data *at24; ssize_t retval = 0; - at24 = dev_get_drvdata(container_of(kobj, struct device, kobj)); - if (unlikely(!count)) return count; @@ -384,6 +381,39 @@ static ssize_t at24_bin_write(struct kobject *kobj, struct bin_attribute *attr, return retval; } +static ssize_t at24_bin_write(struct kobject *kobj, struct bin_attribute *attr, + char *buf, loff_t off, size_t count) +{ + struct at24_data *at24; + + at24 = dev_get_drvdata(container_of(kobj, struct device, kobj)); + return at24_write(at24, buf, off, count); +} + +/*-------------------------------------------------------------------------*/ + +/* + * This lets other kernel code access the eeprom data. For example, it + * might hold a board's Ethernet address, or board-specific calibration + * data generated on the manufacturing floor. + */ + +static ssize_t at24_macc_read(struct memory_accessor *macc, char *buf, + off_t offset, size_t count) +{ + struct at24_data *at24 = container_of(macc, struct at24_data, macc); + + return at24_read(at24, buf, offset, count); +} + +static ssize_t at24_macc_write(struct memory_accessor *macc, char *buf, + off_t offset, size_t count) +{ + struct at24_data *at24 = container_of(macc, struct at24_data, macc); + + return at24_write(at24, buf, offset, count); +} + /*-------------------------------------------------------------------------*/ static int at24_probe(struct i2c_client *client, const struct i2c_device_id *id) @@ -413,6 +443,9 @@ static int at24_probe(struct i2c_client *client, const struct i2c_device_id *id) * is recommended anyhow. */ chip.page_size = 1; + + chip.setup = NULL; + chip.context = NULL; } if (!is_power_of_2(chip.byte_len)) @@ -463,6 +496,8 @@ static int at24_probe(struct i2c_client *client, const struct i2c_device_id *id) at24->bin.read = at24_bin_read; at24->bin.size = chip.byte_len; + at24->macc.read = at24_macc_read; + writable = !(chip.flags & AT24_FLAG_READONLY); if (writable) { if (!use_smbus || i2c_check_functionality(client->adapter, @@ -470,6 +505,8 @@ static int at24_probe(struct i2c_client *client, const struct i2c_device_id *id) unsigned write_max = chip.page_size; + at24->macc.write = at24_macc_write; + at24->bin.write = at24_bin_write; at24->bin.attr.mode |= S_IWUSR; @@ -520,6 +557,10 @@ static int at24_probe(struct i2c_client *client, const struct i2c_device_id *id) at24->write_max, use_smbus ? ", use_smbus" : ""); + /* export data to kernel code */ + if (chip.setup) + chip.setup(&at24->macc, chip.context); + return 0; err_clients: diff --git a/include/linux/i2c/at24.h b/include/linux/i2c/at24.h index f6edd522a929..8ace93024d60 100644 --- a/include/linux/i2c/at24.h +++ b/include/linux/i2c/at24.h @@ -2,6 +2,7 @@ #define _LINUX_AT24_H #include +#include /* * As seen through Linux I2C, differences between the most common types of I2C @@ -23,6 +24,9 @@ struct at24_platform_data { #define AT24_FLAG_READONLY 0x40 /* sysfs-entry will be read-only */ #define AT24_FLAG_IRUGO 0x20 /* sysfs-entry will be world-readable */ #define AT24_FLAG_TAKE8ADDR 0x10 /* take always 8 addresses (24c00) */ + + void (*setup)(struct memory_accessor *, void *context); + void *context; }; #endif /* _LINUX_AT24_H */ -- cgit v1.2.3 From 14dd1ff0f9e75dd4ae2f1ff8e48becb76d14f4ab Mon Sep 17 00:00:00 2001 From: David Brownell Date: Thu, 2 Apr 2009 16:56:58 -0700 Subject: memory_accessor: implement the new memory_accessor interfaces for SPI EEPROMs - Define new setup() hook to export the accessor - Implement accessor methods Moves some error checking out of the sysfs interface code into the layer below it, which is now shared by both sysfs and memory access code. Signed-off-by: David Brownell Signed-off-by: Kevin Hilman Cc: Jean Delvare Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/misc/eeprom/at25.c | 58 +++++++++++++++++++++++++++++++++++----------- include/linux/spi/eeprom.h | 6 +++++ 2 files changed, 50 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/misc/eeprom/at25.c b/drivers/misc/eeprom/at25.c index 290dbe99647a..6bc0dac5c1e8 100644 --- a/drivers/misc/eeprom/at25.c +++ b/drivers/misc/eeprom/at25.c @@ -30,6 +30,7 @@ struct at25_data { struct spi_device *spi; + struct memory_accessor mem; struct mutex lock; struct spi_eeprom chip; struct bin_attribute bin; @@ -75,6 +76,13 @@ at25_ee_read( struct spi_transfer t[2]; struct spi_message m; + if (unlikely(offset >= at25->bin.size)) + return 0; + if ((offset + count) > at25->bin.size) + count = at25->bin.size - offset; + if (unlikely(!count)) + return count; + cp = command; *cp++ = AT25_READ; @@ -127,13 +135,6 @@ at25_bin_read(struct kobject *kobj, struct bin_attribute *bin_attr, dev = container_of(kobj, struct device, kobj); at25 = dev_get_drvdata(dev); - if (unlikely(off >= at25->bin.size)) - return 0; - if ((off + count) > at25->bin.size) - count = at25->bin.size - off; - if (unlikely(!count)) - return count; - return at25_ee_read(at25, buf, off, count); } @@ -146,6 +147,13 @@ at25_ee_write(struct at25_data *at25, char *buf, loff_t off, size_t count) unsigned buf_size; u8 *bounce; + if (unlikely(off >= at25->bin.size)) + return -EFBIG; + if ((off + count) > at25->bin.size) + count = at25->bin.size - off; + if (unlikely(!count)) + return count; + /* Temp buffer starts with command and address */ buf_size = at25->chip.page_size; if (buf_size > io_limit) @@ -253,18 +261,31 @@ at25_bin_write(struct kobject *kobj, struct bin_attribute *bin_attr, dev = container_of(kobj, struct device, kobj); at25 = dev_get_drvdata(dev); - if (unlikely(off >= at25->bin.size)) - return -EFBIG; - if ((off + count) > at25->bin.size) - count = at25->bin.size - off; - if (unlikely(!count)) - return count; - return at25_ee_write(at25, buf, off, count); } /*-------------------------------------------------------------------------*/ +/* Let in-kernel code access the eeprom data. */ + +static ssize_t at25_mem_read(struct memory_accessor *mem, char *buf, + off_t offset, size_t count) +{ + struct at25_data *at25 = container_of(mem, struct at25_data, mem); + + return at25_ee_read(at25, buf, offset, count); +} + +static ssize_t at25_mem_write(struct memory_accessor *mem, char *buf, + off_t offset, size_t count) +{ + struct at25_data *at25 = container_of(mem, struct at25_data, mem); + + return at25_ee_write(at25, buf, offset, count); +} + +/*-------------------------------------------------------------------------*/ + static int at25_probe(struct spi_device *spi) { struct at25_data *at25 = NULL; @@ -317,6 +338,10 @@ static int at25_probe(struct spi_device *spi) at25->addrlen = addrlen; /* Export the EEPROM bytes through sysfs, since that's convenient. + * And maybe to other kernel code; it might hold a board's Ethernet + * address, or board-specific calibration data generated on the + * manufacturing floor. + * * Default to root-only access to the data; EEPROMs often hold data * that's sensitive for read and/or write, like ethernet addresses, * security codes, board-specific manufacturing calibrations, etc. @@ -324,17 +349,22 @@ static int at25_probe(struct spi_device *spi) at25->bin.attr.name = "eeprom"; at25->bin.attr.mode = S_IRUSR; at25->bin.read = at25_bin_read; + at25->mem.read = at25_mem_read; at25->bin.size = at25->chip.byte_len; if (!(chip->flags & EE_READONLY)) { at25->bin.write = at25_bin_write; at25->bin.attr.mode |= S_IWUSR; + at25->mem.write = at25_mem_write; } err = sysfs_create_bin_file(&spi->dev.kobj, &at25->bin); if (err) goto fail; + if (chip->setup) + chip->setup(&at25->mem, chip->context); + dev_info(&spi->dev, "%Zd %s %s eeprom%s, pagesize %u\n", (at25->bin.size < 1024) ? at25->bin.size diff --git a/include/linux/spi/eeprom.h b/include/linux/spi/eeprom.h index 1085212c446e..306e7b1c69ed 100644 --- a/include/linux/spi/eeprom.h +++ b/include/linux/spi/eeprom.h @@ -1,6 +1,8 @@ #ifndef __LINUX_SPI_EEPROM_H #define __LINUX_SPI_EEPROM_H +#include + /* * Put one of these structures in platform_data for SPI EEPROMS handled * by the "at25" driver. On SPI, most EEPROMS understand the same core @@ -17,6 +19,10 @@ struct spi_eeprom { #define EE_ADDR2 0x0002 /* 16 bit addrs */ #define EE_ADDR3 0x0004 /* 24 bit addrs */ #define EE_READONLY 0x0008 /* disallow writes */ + + /* for exporting this chip's data to other kernel code */ + void (*setup)(struct memory_accessor *mem, void *context); + void *context; }; #endif /* __LINUX_SPI_EEPROM_H */ -- cgit v1.2.3 From 6f2c55b843836d26528c56a0968689accaedbc67 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 2 Apr 2009 16:56:59 -0700 Subject: Simplify copy_thread() First argument unused since 2.3.11. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Alexey Dobriyan Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/process.c | 2 +- arch/arm/kernel/process.c | 2 +- arch/avr32/kernel/process.c | 2 +- arch/blackfin/kernel/process.c | 2 +- arch/cris/arch-v10/kernel/process.c | 2 +- arch/cris/arch-v32/kernel/process.c | 2 +- arch/frv/kernel/process.c | 2 +- arch/h8300/kernel/process.c | 2 +- arch/ia64/kernel/process.c | 2 +- arch/m32r/kernel/process.c | 2 +- arch/m68k/kernel/process.c | 2 +- arch/m68knommu/kernel/process.c | 2 +- arch/mips/kernel/process.c | 2 +- arch/mn10300/kernel/process.c | 2 +- arch/parisc/kernel/process.c | 2 +- arch/powerpc/kernel/process.c | 2 +- arch/s390/kernel/process.c | 2 +- arch/sh/kernel/process_32.c | 2 +- arch/sh/kernel/process_64.c | 2 +- arch/sparc/kernel/process_32.c | 2 +- arch/sparc/kernel/process_64.c | 2 +- arch/um/kernel/process.c | 2 +- arch/x86/kernel/process_32.c | 2 +- arch/x86/kernel/process_64.c | 2 +- arch/xtensa/kernel/process.c | 2 +- include/linux/sched.h | 3 ++- kernel/fork.c | 2 +- 27 files changed, 28 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index 8d0097f10208..3a2fb7a02db4 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -272,7 +272,7 @@ alpha_vfork(struct pt_regs *regs) */ int -copy_thread(int nr, unsigned long clone_flags, unsigned long usp, +copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long unused, struct task_struct * p, struct pt_regs * regs) { diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 2de14e2afdc5..c3265a2e7cd4 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -301,7 +301,7 @@ void release_thread(struct task_struct *dead_task) asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); int -copy_thread(int nr, unsigned long clone_flags, unsigned long stack_start, +copy_thread(unsigned long clone_flags, unsigned long stack_start, unsigned long stk_sz, struct task_struct *p, struct pt_regs *regs) { struct thread_info *thread = task_thread_info(p); diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c index 43ae555ecb33..1bbe1da54869 100644 --- a/arch/avr32/kernel/process.c +++ b/arch/avr32/kernel/process.c @@ -332,7 +332,7 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu) asmlinkage void ret_from_fork(void); -int copy_thread(int nr, unsigned long clone_flags, unsigned long usp, +int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) { diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c index 33e2e8993f7f..f49427293ca1 100644 --- a/arch/blackfin/kernel/process.c +++ b/arch/blackfin/kernel/process.c @@ -193,7 +193,7 @@ asmlinkage int bfin_clone(struct pt_regs *regs) } int -copy_thread(int nr, unsigned long clone_flags, +copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long topstk, struct task_struct *p, struct pt_regs *regs) { diff --git a/arch/cris/arch-v10/kernel/process.c b/arch/cris/arch-v10/kernel/process.c index bd9b3ff63f6c..c4c69cf721e5 100644 --- a/arch/cris/arch-v10/kernel/process.c +++ b/arch/cris/arch-v10/kernel/process.c @@ -115,7 +115,7 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) */ asmlinkage void ret_from_fork(void); -int copy_thread(int nr, unsigned long clone_flags, unsigned long usp, +int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) { diff --git a/arch/cris/arch-v32/kernel/process.c b/arch/cris/arch-v32/kernel/process.c index ced5b725d9bd..120e7f796fea 100644 --- a/arch/cris/arch-v32/kernel/process.c +++ b/arch/cris/arch-v32/kernel/process.c @@ -131,7 +131,7 @@ kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) extern asmlinkage void ret_from_fork(void); int -copy_thread(int nr, unsigned long clone_flags, unsigned long usp, +copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) { diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c index 9583a338e9d6..0de50df74970 100644 --- a/arch/frv/kernel/process.c +++ b/arch/frv/kernel/process.c @@ -204,7 +204,7 @@ void prepare_to_copy(struct task_struct *tsk) /* * set up the kernel stack and exception frames for a new process */ -int copy_thread(int nr, unsigned long clone_flags, +int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long topstk, struct task_struct *p, struct pt_regs *regs) { diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index a8ef654a5a0b..e2f33d0f9969 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -191,7 +191,7 @@ asmlinkage int h8300_clone(struct pt_regs *regs) } -int copy_thread(int nr, unsigned long clone_flags, +int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long topstk, struct task_struct * p, struct pt_regs * regs) { diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index c57162705147..5d7c0e5b9e76 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -413,7 +413,7 @@ ia64_load_extra (struct task_struct *task) * so there is nothing to worry about. */ int -copy_thread (int nr, unsigned long clone_flags, +copy_thread(unsigned long clone_flags, unsigned long user_stack_base, unsigned long user_stack_size, struct task_struct *p, struct pt_regs *regs) { diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c index 7103d91e1a2f..3e876f0baebc 100644 --- a/arch/m32r/kernel/process.c +++ b/arch/m32r/kernel/process.c @@ -225,7 +225,7 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu) return 0; /* Task didn't use the fpu at all. */ } -int copy_thread(int nr, unsigned long clone_flags, unsigned long spu, +int copy_thread(unsigned long clone_flags, unsigned long spu, unsigned long unused, struct task_struct *tsk, struct pt_regs *regs) { struct pt_regs *childregs = task_pt_regs(tsk); diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index 632ce016014d..ec37fb56c127 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -233,7 +233,7 @@ asmlinkage int m68k_clone(struct pt_regs *regs) parent_tidptr, child_tidptr); } -int copy_thread(int nr, unsigned long clone_flags, unsigned long usp, +int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long unused, struct task_struct * p, struct pt_regs * regs) { diff --git a/arch/m68knommu/kernel/process.c b/arch/m68knommu/kernel/process.c index 3f2d7745f31e..1e96c6eb6312 100644 --- a/arch/m68knommu/kernel/process.c +++ b/arch/m68knommu/kernel/process.c @@ -199,7 +199,7 @@ asmlinkage int m68k_clone(struct pt_regs *regs) return do_fork(clone_flags, newsp, regs, 0, NULL, NULL); } -int copy_thread(int nr, unsigned long clone_flags, +int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long topstk, struct task_struct * p, struct pt_regs * regs) { diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index ca2e4026ad20..1eaaa450e20c 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -99,7 +99,7 @@ void flush_thread(void) { } -int copy_thread(int nr, unsigned long clone_flags, unsigned long usp, +int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) { struct thread_info *ti = task_thread_info(p); diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c index b28c9a60445b..234cf344cdce 100644 --- a/arch/mn10300/kernel/process.c +++ b/arch/mn10300/kernel/process.c @@ -193,7 +193,7 @@ void prepare_to_copy(struct task_struct *tsk) * set up the kernel stack for a new thread and copy arch-specific thread * control information */ -int copy_thread(int nr, unsigned long clone_flags, +int copy_thread(unsigned long clone_flags, unsigned long c_usp, unsigned long ustk_size, struct task_struct *p, struct pt_regs *kregs) { diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index b80e02a4d81d..8aa591ed9127 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -263,7 +263,7 @@ sys_vfork(struct pt_regs *regs) } int -copy_thread(int nr, unsigned long clone_flags, unsigned long usp, +copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long unused, /* in ia64 this is "user_stack_size" */ struct task_struct * p, struct pt_regs * pregs) { diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index eac064948780..7b44a33f03c2 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -598,7 +598,7 @@ void prepare_to_copy(struct task_struct *tsk) /* * Copy a thread.. */ -int copy_thread(int nr, unsigned long clone_flags, unsigned long usp, +int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) { diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index b48e961a38f6..a3acd8e60aff 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -160,7 +160,7 @@ void release_thread(struct task_struct *dead_task) { } -int copy_thread(int nr, unsigned long clone_flags, unsigned long new_stackp, +int copy_thread(unsigned long clone_flags, unsigned long new_stackp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) { diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index ddafbbbab2ab..694bc15f84fd 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -170,7 +170,7 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu) asmlinkage void ret_from_fork(void); -int copy_thread(int nr, unsigned long clone_flags, unsigned long usp, +int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) { diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c index c90c7e5e5fee..96be839040f8 100644 --- a/arch/sh/kernel/process_64.c +++ b/arch/sh/kernel/process_64.c @@ -425,7 +425,7 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu) asmlinkage void ret_from_fork(void); -int copy_thread(int nr, unsigned long clone_flags, unsigned long usp, +int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) { diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index f4bee35a1b46..2830b415e214 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -455,7 +455,7 @@ asmlinkage int sparc_do_fork(unsigned long clone_flags, */ extern void ret_from_fork(void); -int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, +int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) { diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index a73954b87f0a..4041f94e7724 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -561,7 +561,7 @@ asmlinkage long sparc_do_fork(unsigned long clone_flags, * Parent --> %o0 == childs pid, %o1 == 0 * Child --> %o0 == parents pid, %o1 == 1 */ -int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, +int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) { diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index a1c6d07cac3e..4a28a1568d85 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -179,7 +179,7 @@ void fork_handler(void) userspace(¤t->thread.regs.regs); } -int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, +int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long stack_top, struct task_struct * p, struct pt_regs *regs) { diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 14014d766cad..76f8f84043a2 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -245,7 +245,7 @@ void prepare_to_copy(struct task_struct *tsk) unlazy_fpu(tsk); } -int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, +int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) { diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index abb7e6a7f0c6..b751a41392b1 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -278,7 +278,7 @@ void prepare_to_copy(struct task_struct *tsk) unlazy_fpu(tsk); } -int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, +int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) { diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index 9185597eb6a0..031f36685710 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -172,7 +172,7 @@ void prepare_to_copy(struct task_struct *tsk) * childregs. */ -int copy_thread(int nr, unsigned long clone_flags, unsigned long usp, +int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long unused, struct task_struct * p, struct pt_regs * regs) { diff --git a/include/linux/sched.h b/include/linux/sched.h index 481fad3a9b42..9186f8c5d5f2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1975,7 +1975,8 @@ extern void mm_release(struct task_struct *, struct mm_struct *); /* Allocate a new mm structure and copy contents from tsk->mm */ extern struct mm_struct *dup_mm(struct task_struct *tsk); -extern int copy_thread(int, unsigned long, unsigned long, unsigned long, struct task_struct *, struct pt_regs *); +extern int copy_thread(unsigned long, unsigned long, unsigned long, + struct task_struct *, struct pt_regs *); extern void flush_thread(void); extern void exit_thread(void); diff --git a/kernel/fork.c b/kernel/fork.c index 51d1aa21483b..d7eb727eb535 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1125,7 +1125,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, goto bad_fork_cleanup_mm; if ((retval = copy_io(clone_flags, p))) goto bad_fork_cleanup_namespaces; - retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs); + retval = copy_thread(clone_flags, stack_start, stack_size, p, regs); if (retval) goto bad_fork_cleanup_io; -- cgit v1.2.3 From 96615841e170f0108832e64a90d51b469573a472 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Thu, 2 Apr 2009 16:57:01 -0700 Subject: rtc-v3020: add ability to access v3020 chip with GPIOs The v3020 RTC can be connected to GPIOs as well as to memory-like interface. Add ability to use GPIO bit-bang for v3020 read-write access. [akpm@linux-foundation.org: fix off-by-one in error path] Signed-off-by: Mike Rapoport Acked-by: Alessandro Zummo Cc: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/rtc/rtc-v3020.c | 190 +++++++++++++++++++++++++++++++++++++++++----- include/linux/rtc-v3020.h | 6 ++ 2 files changed, 176 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/rtc/rtc-v3020.c b/drivers/rtc/rtc-v3020.c index 66955cc9c746..ad164056feb6 100644 --- a/drivers/rtc/rtc-v3020.c +++ b/drivers/rtc/rtc-v3020.c @@ -27,17 +27,162 @@ #include #include #include +#include #include #undef DEBUG +struct v3020; + +struct v3020_chip_ops { + int (*map_io)(struct v3020 *chip, struct platform_device *pdev, + struct v3020_platform_data *pdata); + void (*unmap_io)(struct v3020 *chip); + unsigned char (*read_bit)(struct v3020 *chip); + void (*write_bit)(struct v3020 *chip, unsigned char bit); +}; + +#define V3020_CS 0 +#define V3020_WR 1 +#define V3020_RD 2 +#define V3020_IO 3 + +struct v3020_gpio { + const char *name; + unsigned int gpio; +}; + struct v3020 { + /* MMIO access */ void __iomem *ioaddress; int leftshift; + + /* GPIO access */ + struct v3020_gpio *gpio; + + struct v3020_chip_ops *ops; + struct rtc_device *rtc; }; + +static int v3020_mmio_map(struct v3020 *chip, struct platform_device *pdev, + struct v3020_platform_data *pdata) +{ + if (pdev->num_resources != 1) + return -EBUSY; + + if (pdev->resource[0].flags != IORESOURCE_MEM) + return -EBUSY; + + chip->leftshift = pdata->leftshift; + chip->ioaddress = ioremap(pdev->resource[0].start, 1); + if (chip->ioaddress == NULL) + return -EBUSY; + + return 0; +} + +static void v3020_mmio_unmap(struct v3020 *chip) +{ + iounmap(chip->ioaddress); +} + +static void v3020_mmio_write_bit(struct v3020 *chip, unsigned char bit) +{ + writel(bit << chip->leftshift, chip->ioaddress); +} + +static unsigned char v3020_mmio_read_bit(struct v3020 *chip) +{ + return readl(chip->ioaddress) & (1 << chip->leftshift); +} + +static struct v3020_chip_ops v3020_mmio_ops = { + .map_io = v3020_mmio_map, + .unmap_io = v3020_mmio_unmap, + .read_bit = v3020_mmio_read_bit, + .write_bit = v3020_mmio_write_bit, +}; + +static struct v3020_gpio v3020_gpio[] = { + { "RTC CS", 0 }, + { "RTC WR", 0 }, + { "RTC RD", 0 }, + { "RTC IO", 0 }, +}; + +static int v3020_gpio_map(struct v3020 *chip, struct platform_device *pdev, + struct v3020_platform_data *pdata) +{ + int i, err; + + v3020_gpio[V3020_CS].gpio = pdata->gpio_cs; + v3020_gpio[V3020_WR].gpio = pdata->gpio_wr; + v3020_gpio[V3020_RD].gpio = pdata->gpio_rd; + v3020_gpio[V3020_IO].gpio = pdata->gpio_io; + + for (i = 0; i < ARRAY_SIZE(v3020_gpio); i++) { + err = gpio_request(v3020_gpio[i].gpio, v3020_gpio[i].name); + if (err) + goto err_request; + + gpio_direction_output(v3020_gpio[i].gpio, 1); + } + + chip->gpio = v3020_gpio; + + return 0; + +err_request: + while (--i >= 0) + gpio_free(v3020_gpio[i].gpio); + + return err; +} + +static void v3020_gpio_unmap(struct v3020 *chip) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(v3020_gpio); i++) + gpio_free(v3020_gpio[i].gpio); +} + +static void v3020_gpio_write_bit(struct v3020 *chip, unsigned char bit) +{ + gpio_direction_output(chip->gpio[V3020_IO].gpio, bit); + gpio_set_value(chip->gpio[V3020_CS].gpio, 0); + gpio_set_value(chip->gpio[V3020_WR].gpio, 0); + udelay(1); + gpio_set_value(chip->gpio[V3020_WR].gpio, 1); + gpio_set_value(chip->gpio[V3020_CS].gpio, 1); +} + +static unsigned char v3020_gpio_read_bit(struct v3020 *chip) +{ + int bit; + + gpio_direction_input(chip->gpio[V3020_IO].gpio); + gpio_set_value(chip->gpio[V3020_CS].gpio, 0); + gpio_set_value(chip->gpio[V3020_RD].gpio, 0); + udelay(1); + bit = !!gpio_get_value(chip->gpio[V3020_IO].gpio); + udelay(1); + gpio_set_value(chip->gpio[V3020_RD].gpio, 1); + gpio_set_value(chip->gpio[V3020_CS].gpio, 1); + + return bit; +} + +static struct v3020_chip_ops v3020_gpio_ops = { + .map_io = v3020_gpio_map, + .unmap_io = v3020_gpio_unmap, + .read_bit = v3020_gpio_read_bit, + .write_bit = v3020_gpio_write_bit, +}; + static void v3020_set_reg(struct v3020 *chip, unsigned char address, unsigned char data) { @@ -46,7 +191,7 @@ static void v3020_set_reg(struct v3020 *chip, unsigned char address, tmp = address; for (i = 0; i < 4; i++) { - writel((tmp & 1) << chip->leftshift, chip->ioaddress); + chip->ops->write_bit(chip, (tmp & 1)); tmp >>= 1; udelay(1); } @@ -54,7 +199,7 @@ static void v3020_set_reg(struct v3020 *chip, unsigned char address, /* Commands dont have data */ if (!V3020_IS_COMMAND(address)) { for (i = 0; i < 8; i++) { - writel((data & 1) << chip->leftshift, chip->ioaddress); + chip->ops->write_bit(chip, (data & 1)); data >>= 1; udelay(1); } @@ -67,14 +212,14 @@ static unsigned char v3020_get_reg(struct v3020 *chip, unsigned char address) int i; for (i = 0; i < 4; i++) { - writel((address & 1) << chip->leftshift, chip->ioaddress); + chip->ops->write_bit(chip, (address & 1)); address >>= 1; udelay(1); } for (i = 0; i < 8; i++) { data >>= 1; - if (readl(chip->ioaddress) & (1 << chip->leftshift)) + if (chip->ops->read_bit(chip)) data |= 0x80; udelay(1); } @@ -164,25 +309,23 @@ static int rtc_probe(struct platform_device *pdev) int i; int temp; - if (pdev->num_resources != 1) - return -EBUSY; - - if (pdev->resource[0].flags != IORESOURCE_MEM) - return -EBUSY; - chip = kzalloc(sizeof *chip, GFP_KERNEL); if (!chip) return -ENOMEM; - chip->leftshift = pdata->leftshift; - chip->ioaddress = ioremap(pdev->resource[0].start, 1); - if (chip->ioaddress == NULL) + if (pdata->use_gpio) + chip->ops = &v3020_gpio_ops; + else + chip->ops = &v3020_mmio_ops; + + retval = chip->ops->map_io(chip, pdev, pdata); + if (retval) goto err_chip; /* Make sure the v3020 expects a communication cycle * by reading 8 times */ for (i = 0; i < 8; i++) - temp = readl(chip->ioaddress); + temp = chip->ops->read_bit(chip); /* Test chip by doing a write/read sequence * to the chip ram */ @@ -196,10 +339,17 @@ static int rtc_probe(struct platform_device *pdev) * are all disabled */ v3020_set_reg(chip, V3020_STATUS_0, 0x0); - dev_info(&pdev->dev, "Chip available at physical address 0x%llx," - "data connected to D%d\n", - (unsigned long long)pdev->resource[0].start, - chip->leftshift); + if (pdata->use_gpio) + dev_info(&pdev->dev, "Chip available at GPIOs " + "%d, %d, %d, %d\n", + chip->gpio[V3020_CS].gpio, chip->gpio[V3020_WR].gpio, + chip->gpio[V3020_RD].gpio, chip->gpio[V3020_IO].gpio); + else + dev_info(&pdev->dev, "Chip available at " + "physical address 0x%llx," + "data connected to D%d\n", + (unsigned long long)pdev->resource[0].start, + chip->leftshift); platform_set_drvdata(pdev, chip); @@ -214,7 +364,7 @@ static int rtc_probe(struct platform_device *pdev) return 0; err_io: - iounmap(chip->ioaddress); + chip->ops->unmap_io(chip); err_chip: kfree(chip); @@ -229,7 +379,7 @@ static int rtc_remove(struct platform_device *dev) if (rtc) rtc_device_unregister(rtc); - iounmap(chip->ioaddress); + chip->ops->unmap_io(chip); kfree(chip); return 0; diff --git a/include/linux/rtc-v3020.h b/include/linux/rtc-v3020.h index bf74e63c98fe..8ba646e610d9 100644 --- a/include/linux/rtc-v3020.h +++ b/include/linux/rtc-v3020.h @@ -14,6 +14,12 @@ * is used depends on the board. */ struct v3020_platform_data { int leftshift; /* (1<<(leftshift)) & readl() */ + + int use_gpio:1; + unsigned int gpio_cs; + unsigned int gpio_wr; + unsigned int gpio_rd; + unsigned int gpio_io; }; #define V3020_STATUS_0 0x00 -- cgit v1.2.3 From bfb9bcdbda9a61bca469bf899a589918c60c4c18 Mon Sep 17 00:00:00 2001 From: Michael Buesch Date: Thu, 2 Apr 2009 16:57:07 -0700 Subject: spi-gpio: allow operation without CS signal Change spi-gpio so that it is possible to drive SPI communications over GPIO without the need for a chipselect signal. This is useful in very small setups where there's only one slave device on the bus. This patch does not affect existing setups. I use this for a tiny communication channel between an embedded device and a microcontroller. There are not enough GPIOs available for chipselect and it's not needed anyway in this case. Signed-off-by: Michael Buesch Cc: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/spi/spi_gpio.c | 21 +++++++++++++-------- include/linux/spi/spi_gpio.h | 6 ++++++ 2 files changed, 19 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/spi_gpio.c b/drivers/spi/spi_gpio.c index d2866c293dee..26bd03e61855 100644 --- a/drivers/spi/spi_gpio.c +++ b/drivers/spi/spi_gpio.c @@ -178,8 +178,10 @@ static void spi_gpio_chipselect(struct spi_device *spi, int is_active) if (is_active) setsck(spi, spi->mode & SPI_CPOL); - /* SPI is normally active-low */ - gpio_set_value(cs, (spi->mode & SPI_CS_HIGH) ? is_active : !is_active); + if (cs != SPI_GPIO_NO_CHIPSELECT) { + /* SPI is normally active-low */ + gpio_set_value(cs, (spi->mode & SPI_CS_HIGH) ? is_active : !is_active); + } } static int spi_gpio_setup(struct spi_device *spi) @@ -191,15 +193,17 @@ static int spi_gpio_setup(struct spi_device *spi) return -EINVAL; if (!spi->controller_state) { - status = gpio_request(cs, dev_name(&spi->dev)); - if (status) - return status; - status = gpio_direction_output(cs, spi->mode & SPI_CS_HIGH); + if (cs != SPI_GPIO_NO_CHIPSELECT) { + status = gpio_request(cs, dev_name(&spi->dev)); + if (status) + return status; + status = gpio_direction_output(cs, spi->mode & SPI_CS_HIGH); + } } if (!status) status = spi_bitbang_setup(spi); if (status) { - if (!spi->controller_state) + if (!spi->controller_state && cs != SPI_GPIO_NO_CHIPSELECT) gpio_free(cs); } return status; @@ -209,7 +213,8 @@ static void spi_gpio_cleanup(struct spi_device *spi) { unsigned long cs = (unsigned long) spi->controller_data; - gpio_free(cs); + if (cs != SPI_GPIO_NO_CHIPSELECT) + gpio_free(cs); spi_bitbang_cleanup(spi); } diff --git a/include/linux/spi/spi_gpio.h b/include/linux/spi/spi_gpio.h index 0f01a0f1f40c..ca6782ee4b9f 100644 --- a/include/linux/spi/spi_gpio.h +++ b/include/linux/spi/spi_gpio.h @@ -25,10 +25,16 @@ * ... * }; * + * If chipselect is not used (there's only one device on the bus), assign + * SPI_GPIO_NO_CHIPSELECT to the controller_data: + * .controller_data = (void *) SPI_GPIO_NO_CHIPSELECT; + * * If the bitbanged bus is later switched to a "native" controller, * that platform_device and controller_data should be removed. */ +#define SPI_GPIO_NO_CHIPSELECT ((unsigned long)-1l) + /** * struct spi_gpio_platform_data - parameter for bitbanged SPI master * @sck: number of the GPIO used for clock output -- cgit v1.2.3 From 039fd8ce6258e01ec29f1637f9bf1868dd877c55 Mon Sep 17 00:00:00 2001 From: Cyrus Massoumi Date: Thu, 2 Apr 2009 16:57:12 -0700 Subject: ext3: remove the BKL in ext3/ioctl.c Reformat ext3/ioctl.c to make it look more like ext4/ioctl.c and remove the BKL around ext3_ioctl(). Signed-off-by: Cyrus Massoumi Cc: Acked-by: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext3/dir.c | 2 +- fs/ext3/file.c | 2 +- fs/ext3/ioctl.c | 59 +++++++++++++++++-------------------------------- include/linux/ext3_fs.h | 5 ++--- 4 files changed, 24 insertions(+), 44 deletions(-) (limited to 'include/linux') 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/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 #include #include -#include #include -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/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index dd495b8c3091..e263acaa405b 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -893,9 +893,8 @@ extern int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len); /* ioctl.c */ -extern int ext3_ioctl (struct inode *, struct file *, unsigned int, - unsigned long); -extern long ext3_compat_ioctl (struct file *, unsigned int, unsigned long); +extern long ext3_ioctl(struct file *, unsigned int, unsigned long); +extern long ext3_compat_ioctl(struct file *, unsigned int, unsigned long); /* namei.c */ extern int ext3_orphan_add(handle_t *, struct inode *); -- cgit v1.2.3 From d20a390a0ee2bf2f692c539c6ce1c829e1080bb5 Mon Sep 17 00:00:00 2001 From: Paul Menage Date: Thu, 2 Apr 2009 16:57:22 -0700 Subject: cgroups: fix cgroup.h comments Fix the style of some multi-line comments in cgroup.h to match Documentation/CodingStyle Signed-off-by: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 71 +++++++++++++++++++++++++++++--------------------- 1 file changed, 41 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 499900d0cee7..bb8feb9feccd 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -47,14 +47,18 @@ enum cgroup_subsys_id { /* Per-subsystem/per-cgroup state maintained by the system. */ struct cgroup_subsys_state { - /* The cgroup that this subsystem is attached to. Useful + /* + * The cgroup that this subsystem is attached to. Useful * for subsystems that want to know about the cgroup - * hierarchy structure */ + * hierarchy structure + */ struct cgroup *cgroup; - /* State maintained by the cgroup system to allow subsystems + /* + * State maintained by the cgroup system to allow subsystems * to be "busy". Should be accessed via css_get(), - * css_tryget() and and css_put(). */ + * css_tryget() and and css_put(). + */ atomic_t refcnt; @@ -120,8 +124,10 @@ static inline void css_put(struct cgroup_subsys_state *css) enum { /* Control Group is dead */ CGRP_REMOVED, - /* Control Group has previously had a child cgroup or a task, - * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set) */ + /* + * Control Group has previously had a child cgroup or a task, + * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set) + */ CGRP_RELEASABLE, /* Control Group requires release notifications to userspace */ CGRP_NOTIFY_ON_RELEASE, @@ -130,9 +136,10 @@ enum { struct cgroup { unsigned long flags; /* "unsigned long" so bitops work */ - /* count users of this cgroup. >0 means busy, but doesn't - * necessarily indicate the number of tasks in the - * cgroup */ + /* + * count users of this cgroup. >0 means busy, but doesn't + * necessarily indicate the number of tasks in the cgroup + */ atomic_t count; /* @@ -142,7 +149,7 @@ struct cgroup { struct list_head sibling; /* my parent's children */ struct list_head children; /* my children */ - struct cgroup *parent; /* my parent */ + struct cgroup *parent; /* my parent */ struct dentry *dentry; /* cgroup fs entry, RCU protected */ /* Private pointers for each registered subsystem */ @@ -177,11 +184,12 @@ struct cgroup { struct rcu_head rcu_head; }; -/* A css_set is a structure holding pointers to a set of +/* + * A css_set is a structure holding pointers to a set of * cgroup_subsys_state objects. This saves space in the task struct * object and speeds up fork()/exit(), since a single inc/dec and a - * list_add()/del() can bump the reference count on the entire - * cgroup set for a task. + * list_add()/del() can bump the reference count on the entire cgroup + * set for a task. */ struct css_set { @@ -226,13 +234,8 @@ struct cgroup_map_cb { void *state; }; -/* struct cftype: - * - * The files in the cgroup filesystem mostly have a very simple read/write - * handling, some common function will take care of it. Nevertheless some cases - * (read tasks) are special and therefore I define this structure for every - * kind of file. - * +/* + * struct cftype: handler definitions for cgroup control files * * When reading/writing to a file: * - the cgroup to use is file->f_dentry->d_parent->d_fsdata @@ -241,8 +244,10 @@ struct cgroup_map_cb { #define MAX_CFTYPE_NAME 64 struct cftype { - /* By convention, the name should begin with the name of the - * subsystem, followed by a period */ + /* + * By convention, the name should begin with the name of the + * subsystem, followed by a period + */ char name[MAX_CFTYPE_NAME]; int private; @@ -321,13 +326,17 @@ struct cgroup_scanner { struct ptr_heap *heap; }; -/* Add a new file to the given cgroup directory. Should only be - * called by subsystems from within a populate() method */ +/* + * Add a new file to the given cgroup directory. Should only be + * called by subsystems from within a populate() method + */ int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys, const struct cftype *cft); -/* Add a set of new files to the given cgroup directory. Should - * only be called by subsystems from within a populate() method */ +/* + * Add a set of new files to the given cgroup directory. Should + * only be called by subsystems from within a populate() method + */ int cgroup_add_files(struct cgroup *cgrp, struct cgroup_subsys *subsys, const struct cftype cft[], @@ -419,7 +428,8 @@ struct cgroup_iter { struct list_head *task; }; -/* To iterate across the tasks in a cgroup: +/* + * To iterate across the tasks in a cgroup: * * 1) call cgroup_iter_start to intialize an iterator * @@ -428,9 +438,10 @@ struct cgroup_iter { * * 3) call cgroup_iter_end() to destroy the iterator. * - * Or, call cgroup_scan_tasks() to iterate through every task in a cpuset. - * - cgroup_scan_tasks() holds the css_set_lock when calling the test_task() - * callback, but not while calling the process_task() callback. + * Or, call cgroup_scan_tasks() to iterate through every task in a + * cgroup - cgroup_scan_tasks() holds the css_set_lock when calling + * the test_task() callback, but not while calling the process_task() + * callback. */ void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it); struct task_struct *cgroup_iter_next(struct cgroup *cgrp, -- cgit v1.2.3 From 313e924c0852943e67335fad9d2608701f0dfe8e Mon Sep 17 00:00:00 2001 From: Grzegorz Nosek Date: Thu, 2 Apr 2009 16:57:23 -0700 Subject: cgroups: relax ns_can_attach checks to allow attaching to grandchild cgroups The ns_proxy cgroup allows moving processes to child cgroups only one level deep at a time. This commit relaxes this restriction and makes it possible to attach tasks directly to grandchild cgroups, e.g.: ($pid is in the root cgroup) echo $pid > /cgroup/CG1/CG2/tasks Previously this operation would fail with -EPERM and would have to be performed as two steps: echo $pid > /cgroup/CG1/tasks echo $pid > /cgroup/CG1/CG2/tasks Also, the target cgroup no longer needs to be empty to move a task there. Signed-off-by: Grzegorz Nosek Acked-by: Serge Hallyn Reviewed-by: Li Zefan Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 4 ++-- kernel/cgroup.c | 11 ++++++----- kernel/ns_cgroup.c | 14 ++++---------- 3 files changed, 12 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index bb8feb9feccd..788c4964c142 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -348,8 +348,8 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen); int cgroup_task_count(const struct cgroup *cgrp); -/* Return true if the cgroup is a descendant of the current cgroup */ -int cgroup_is_descendant(const struct cgroup *cgrp); +/* Return true if cgrp is a descendant of the task's cgroup */ +int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task); /* Control Group subsystem type. See Documentation/cgroups.txt for details */ diff --git a/kernel/cgroup.c b/kernel/cgroup.c index c500ca7239b2..27792bcb0758 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3084,18 +3084,19 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, } /** - * cgroup_is_descendant - see if @cgrp is a descendant of current task's cgrp + * cgroup_is_descendant - see if @cgrp is a descendant of @task's cgrp * @cgrp: the cgroup in question + * @task: the task in question * - * See if @cgrp is a descendant of the current task's cgroup in - * the appropriate hierarchy. + * See if @cgrp is a descendant of @task's cgroup in the appropriate + * hierarchy. * * If we are sending in dummytop, then presumably we are creating * the top cgroup in the subsystem. * * Called only by the ns (nsproxy) cgroup. */ -int cgroup_is_descendant(const struct cgroup *cgrp) +int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task) { int ret; struct cgroup *target; @@ -3105,7 +3106,7 @@ int cgroup_is_descendant(const struct cgroup *cgrp) return 1; get_first_subsys(cgrp, NULL, &subsys_id); - target = task_cgroup(current, subsys_id); + target = task_cgroup(task, subsys_id); while (cgrp != target && cgrp!= cgrp->top_cgroup) cgrp = cgrp->parent; ret = (cgrp == target); diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c index 78bc3fdac0d2..5aa854f9e5ae 100644 --- a/kernel/ns_cgroup.c +++ b/kernel/ns_cgroup.c @@ -34,7 +34,7 @@ int ns_cgroup_clone(struct task_struct *task, struct pid *pid) /* * Rules: - * 1. you can only enter a cgroup which is a child of your current + * 1. you can only enter a cgroup which is a descendant of your current * cgroup * 2. you can only place another process into a cgroup if * a. you have CAP_SYS_ADMIN @@ -45,21 +45,15 @@ int ns_cgroup_clone(struct task_struct *task, struct pid *pid) static int ns_can_attach(struct cgroup_subsys *ss, struct cgroup *new_cgroup, struct task_struct *task) { - struct cgroup *orig; - if (current != task) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!cgroup_is_descendant(new_cgroup)) + if (!cgroup_is_descendant(new_cgroup, current)) return -EPERM; } - if (atomic_read(&new_cgroup->count) != 0) - return -EPERM; - - orig = task_cgroup(task, ns_subsys_id); - if (orig && orig != new_cgroup->parent) + if (!cgroup_is_descendant(new_cgroup, task)) return -EPERM; return 0; @@ -77,7 +71,7 @@ static struct cgroup_subsys_state *ns_create(struct cgroup_subsys *ss, if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); - if (!cgroup_is_descendant(cgroup)) + if (!cgroup_is_descendant(cgroup, current)) return ERR_PTR(-EPERM); ns_cgroup = kzalloc(sizeof(*ns_cgroup), GFP_KERNEL); -- cgit v1.2.3 From 38460b48d06440de46b34cb778bd6c4855030754 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Thu, 2 Apr 2009 16:57:25 -0700 Subject: cgroup: CSS ID support Patch for Per-CSS(Cgroup Subsys State) ID and private hierarchy code. This patch attaches unique ID to each css and provides following. - css_lookup(subsys, id) returns pointer to struct cgroup_subysys_state of id. - css_get_next(subsys, id, rootid, depth, foundid) returns the next css under "root" by scanning When cgroup_subsys->use_id is set, an id for css is maintained. The cgroup framework only parepares - css_id of root css for subsys - id is automatically attached at creation of css. - id is *not* freed automatically. Because the cgroup framework don't know lifetime of cgroup_subsys_state. free_css_id() function is provided. This must be called by subsys. There are several reasons to develop this. - Saving space .... For example, memcg's swap_cgroup is array of pointers to cgroup. But it is not necessary to be very fast. By replacing pointers(8bytes per ent) to ID (2byes per ent), we can reduce much amount of memory usage. - Scanning without lock. CSS_ID provides "scan id under this ROOT" function. By this, scanning css under root can be written without locks. ex) do { rcu_read_lock(); next = cgroup_get_next(subsys, id, root, &found); /* check sanity of next here */ css_tryget(); rcu_read_unlock(); id = found + 1 } while(...) Characteristics: - Each css has unique ID under subsys. - Lifetime of ID is controlled by subsys. - css ID contains "ID" and "Depth in hierarchy" and stack of hierarchy - Allowed ID is 1-65535, ID 0 is UNUSED ID. Design Choices: - scan-by-ID v.s. scan-by-tree-walk. As /proc's pid scan does, scan-by-ID is robust when scanning is done by following kind of routine. scan -> rest a while(release a lock) -> conitunue from interrupted memcg's hierarchical reclaim does this. - When subsys->use_id is set, # of css in the system is limited to 65535. [bharata@linux.vnet.ibm.com: remove rcu_read_lock() from css_get_next()] Signed-off-by: KAMEZAWA Hiroyuki Acked-by: Paul Menage Cc: Li Zefan Cc: Balbir Singh Cc: Daisuke Nishimura Signed-off-by: Bharata B Rao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 50 +++++++++ include/linux/idr.h | 1 + kernel/cgroup.c | 286 ++++++++++++++++++++++++++++++++++++++++++++++++- lib/idr.c | 46 ++++++++ 4 files changed, 382 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 788c4964c142..9a23bb098205 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -15,6 +15,7 @@ #include #include #include +#include #ifdef CONFIG_CGROUPS @@ -22,6 +23,7 @@ struct cgroupfs_root; struct cgroup_subsys; struct inode; struct cgroup; +struct css_id; extern int cgroup_init_early(void); extern int cgroup_init(void); @@ -63,6 +65,8 @@ struct cgroup_subsys_state { atomic_t refcnt; unsigned long flags; + /* ID for this css, if possible */ + struct css_id *id; }; /* bits in struct cgroup_subsys_state flags field */ @@ -373,6 +377,11 @@ struct cgroup_subsys { int active; int disabled; int early_init; + /* + * True if this subsys uses ID. ID is not available before cgroup_init() + * (not available in early_init time.) + */ + bool use_id; #define MAX_CGROUP_TYPE_NAMELEN 32 const char *name; @@ -395,6 +404,9 @@ struct cgroup_subsys { */ struct cgroupfs_root *root; struct list_head sibling; + /* used when use_id == true */ + struct idr idr; + spinlock_t id_lock; }; #define SUBSYS(_x) extern struct cgroup_subsys _x ## _subsys; @@ -450,6 +462,44 @@ void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it); int cgroup_scan_tasks(struct cgroup_scanner *scan); int cgroup_attach_task(struct cgroup *, struct task_struct *); +/* + * CSS ID is ID for cgroup_subsys_state structs under subsys. This only works + * if cgroup_subsys.use_id == true. It can be used for looking up and scanning. + * CSS ID is assigned at cgroup allocation (create) automatically + * and removed when subsys calls free_css_id() function. This is because + * the lifetime of cgroup_subsys_state is subsys's matter. + * + * Looking up and scanning function should be called under rcu_read_lock(). + * Taking cgroup_mutex()/hierarchy_mutex() is not necessary for following calls. + * But the css returned by this routine can be "not populated yet" or "being + * destroyed". The caller should check css and cgroup's status. + */ + +/* + * Typically Called at ->destroy(), or somewhere the subsys frees + * cgroup_subsys_state. + */ +void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css); + +/* Find a cgroup_subsys_state which has given ID */ + +struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id); + +/* + * Get a cgroup whose id is greater than or equal to id under tree of root. + * Returning a cgroup_subsys_state or NULL. + */ +struct cgroup_subsys_state *css_get_next(struct cgroup_subsys *ss, int id, + struct cgroup_subsys_state *root, int *foundid); + +/* Returns true if root is ancestor of cg */ +bool css_is_ancestor(struct cgroup_subsys_state *cg, + struct cgroup_subsys_state *root); + +/* Get id and depth of css */ +unsigned short css_id(struct cgroup_subsys_state *css); +unsigned short css_depth(struct cgroup_subsys_state *css); + #else /* !CONFIG_CGROUPS */ static inline int cgroup_init_early(void) { return 0; } diff --git a/include/linux/idr.h b/include/linux/idr.h index dd846df8cd32..e968db71e33a 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -106,6 +106,7 @@ int idr_get_new(struct idr *idp, void *ptr, int *id); int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id); int idr_for_each(struct idr *idp, int (*fn)(int id, void *p, void *data), void *data); +void *idr_get_next(struct idr *idp, int *nextid); void *idr_replace(struct idr *idp, void *ptr, int id); void idr_remove(struct idr *idp, int id); void idr_remove_all(struct idr *idp); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 27792bcb0758..d3c521137425 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -94,7 +94,6 @@ struct cgroupfs_root { char release_agent_path[PATH_MAX]; }; - /* * The "rootnode" hierarchy is the "dummy hierarchy", reserved for the * subsystems that are otherwise unattached - it never has more than a @@ -102,6 +101,39 @@ struct cgroupfs_root { */ static struct cgroupfs_root rootnode; +/* + * CSS ID -- ID per subsys's Cgroup Subsys State(CSS). used only when + * cgroup_subsys->use_id != 0. + */ +#define CSS_ID_MAX (65535) +struct css_id { + /* + * The css to which this ID points. This pointer is set to valid value + * after cgroup is populated. If cgroup is removed, this will be NULL. + * This pointer is expected to be RCU-safe because destroy() + * is called after synchronize_rcu(). But for safe use, css_is_removed() + * css_tryget() should be used for avoiding race. + */ + struct cgroup_subsys_state *css; + /* + * ID of this css. + */ + unsigned short id; + /* + * Depth in hierarchy which this ID belongs to. + */ + unsigned short depth; + /* + * ID is freed by RCU. (and lookup routine is RCU safe.) + */ + struct rcu_head rcu_head; + /* + * Hierarchy of CSS ID belongs to. + */ + unsigned short stack[0]; /* Array of Length (depth+1) */ +}; + + /* The list of hierarchy roots */ static LIST_HEAD(roots); @@ -185,6 +217,8 @@ struct cg_cgroup_link { static struct css_set init_css_set; static struct cg_cgroup_link init_css_set_link; +static int cgroup_subsys_init_idr(struct cgroup_subsys *ss); + /* css_set_lock protects the list of css_set objects, and the * chain of tasks off each css_set. Nests outside task->alloc_lock * due to cgroup_iter_start() */ @@ -567,6 +601,9 @@ static struct backing_dev_info cgroup_backing_dev_info = { .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, }; +static int alloc_css_id(struct cgroup_subsys *ss, + struct cgroup *parent, struct cgroup *child); + static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb) { struct inode *inode = new_inode(sb); @@ -2327,6 +2364,17 @@ static int cgroup_populate_dir(struct cgroup *cgrp) if (ss->populate && (err = ss->populate(ss, cgrp)) < 0) return err; } + /* This cgroup is ready now */ + for_each_subsys(cgrp->root, ss) { + struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; + /* + * Update id->css pointer and make this css visible from + * CSS ID functions. This pointer will be dereferened + * from RCU-read-side without locks. + */ + if (css->id) + rcu_assign_pointer(css->id->css, css); + } return 0; } @@ -2338,6 +2386,7 @@ static void init_cgroup_css(struct cgroup_subsys_state *css, css->cgroup = cgrp; atomic_set(&css->refcnt, 1); css->flags = 0; + css->id = NULL; if (cgrp == dummytop) set_bit(CSS_ROOT, &css->flags); BUG_ON(cgrp->subsys[ss->subsys_id]); @@ -2413,6 +2462,10 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, goto err_destroy; } init_cgroup_css(css, ss, cgrp); + if (ss->use_id) + if (alloc_css_id(ss, parent, cgrp)) + goto err_destroy; + /* At error, ->destroy() callback has to free assigned ID. */ } cgroup_lock_hierarchy(root); @@ -2708,6 +2761,8 @@ int __init cgroup_init(void) struct cgroup_subsys *ss = subsys[i]; if (!ss->early_init) cgroup_init_subsys(ss); + if (ss->use_id) + cgroup_subsys_init_idr(ss); } /* Add init_css_set to the hash table */ @@ -3242,3 +3297,232 @@ static int __init cgroup_disable(char *str) return 1; } __setup("cgroup_disable=", cgroup_disable); + +/* + * Functons for CSS ID. + */ + +/* + *To get ID other than 0, this should be called when !cgroup_is_removed(). + */ +unsigned short css_id(struct cgroup_subsys_state *css) +{ + struct css_id *cssid = rcu_dereference(css->id); + + if (cssid) + return cssid->id; + return 0; +} + +unsigned short css_depth(struct cgroup_subsys_state *css) +{ + struct css_id *cssid = rcu_dereference(css->id); + + if (cssid) + return cssid->depth; + return 0; +} + +bool css_is_ancestor(struct cgroup_subsys_state *child, + struct cgroup_subsys_state *root) +{ + struct css_id *child_id = rcu_dereference(child->id); + struct css_id *root_id = rcu_dereference(root->id); + + if (!child_id || !root_id || (child_id->depth < root_id->depth)) + return false; + return child_id->stack[root_id->depth] == root_id->id; +} + +static void __free_css_id_cb(struct rcu_head *head) +{ + struct css_id *id; + + id = container_of(head, struct css_id, rcu_head); + kfree(id); +} + +void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css) +{ + struct css_id *id = css->id; + /* When this is called before css_id initialization, id can be NULL */ + if (!id) + return; + + BUG_ON(!ss->use_id); + + rcu_assign_pointer(id->css, NULL); + rcu_assign_pointer(css->id, NULL); + spin_lock(&ss->id_lock); + idr_remove(&ss->idr, id->id); + spin_unlock(&ss->id_lock); + call_rcu(&id->rcu_head, __free_css_id_cb); +} + +/* + * This is called by init or create(). Then, calls to this function are + * always serialized (By cgroup_mutex() at create()). + */ + +static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth) +{ + struct css_id *newid; + int myid, error, size; + + BUG_ON(!ss->use_id); + + size = sizeof(*newid) + sizeof(unsigned short) * (depth + 1); + newid = kzalloc(size, GFP_KERNEL); + if (!newid) + return ERR_PTR(-ENOMEM); + /* get id */ + if (unlikely(!idr_pre_get(&ss->idr, GFP_KERNEL))) { + error = -ENOMEM; + goto err_out; + } + spin_lock(&ss->id_lock); + /* Don't use 0. allocates an ID of 1-65535 */ + error = idr_get_new_above(&ss->idr, newid, 1, &myid); + spin_unlock(&ss->id_lock); + + /* Returns error when there are no free spaces for new ID.*/ + if (error) { + error = -ENOSPC; + goto err_out; + } + if (myid > CSS_ID_MAX) + goto remove_idr; + + newid->id = myid; + newid->depth = depth; + return newid; +remove_idr: + error = -ENOSPC; + spin_lock(&ss->id_lock); + idr_remove(&ss->idr, myid); + spin_unlock(&ss->id_lock); +err_out: + kfree(newid); + return ERR_PTR(error); + +} + +static int __init cgroup_subsys_init_idr(struct cgroup_subsys *ss) +{ + struct css_id *newid; + struct cgroup_subsys_state *rootcss; + + spin_lock_init(&ss->id_lock); + idr_init(&ss->idr); + + rootcss = init_css_set.subsys[ss->subsys_id]; + newid = get_new_cssid(ss, 0); + if (IS_ERR(newid)) + return PTR_ERR(newid); + + newid->stack[0] = newid->id; + newid->css = rootcss; + rootcss->id = newid; + return 0; +} + +static int alloc_css_id(struct cgroup_subsys *ss, struct cgroup *parent, + struct cgroup *child) +{ + int subsys_id, i, depth = 0; + struct cgroup_subsys_state *parent_css, *child_css; + struct css_id *child_id, *parent_id = NULL; + + subsys_id = ss->subsys_id; + parent_css = parent->subsys[subsys_id]; + child_css = child->subsys[subsys_id]; + depth = css_depth(parent_css) + 1; + parent_id = parent_css->id; + + child_id = get_new_cssid(ss, depth); + if (IS_ERR(child_id)) + return PTR_ERR(child_id); + + for (i = 0; i < depth; i++) + child_id->stack[i] = parent_id->stack[i]; + child_id->stack[depth] = child_id->id; + /* + * child_id->css pointer will be set after this cgroup is available + * see cgroup_populate_dir() + */ + rcu_assign_pointer(child_css->id, child_id); + + return 0; +} + +/** + * css_lookup - lookup css by id + * @ss: cgroup subsys to be looked into. + * @id: the id + * + * Returns pointer to cgroup_subsys_state if there is valid one with id. + * NULL if not. Should be called under rcu_read_lock() + */ +struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id) +{ + struct css_id *cssid = NULL; + + BUG_ON(!ss->use_id); + cssid = idr_find(&ss->idr, id); + + if (unlikely(!cssid)) + return NULL; + + return rcu_dereference(cssid->css); +} + +/** + * css_get_next - lookup next cgroup under specified hierarchy. + * @ss: pointer to subsystem + * @id: current position of iteration. + * @root: pointer to css. search tree under this. + * @foundid: position of found object. + * + * Search next css under the specified hierarchy of rootid. Calling under + * rcu_read_lock() is necessary. Returns NULL if it reaches the end. + */ +struct cgroup_subsys_state * +css_get_next(struct cgroup_subsys *ss, int id, + struct cgroup_subsys_state *root, int *foundid) +{ + struct cgroup_subsys_state *ret = NULL; + struct css_id *tmp; + int tmpid; + int rootid = css_id(root); + int depth = css_depth(root); + + if (!rootid) + return NULL; + + BUG_ON(!ss->use_id); + /* fill start point for scan */ + tmpid = id; + while (1) { + /* + * scan next entry from bitmap(tree), tmpid is updated after + * idr_get_next(). + */ + spin_lock(&ss->id_lock); + tmp = idr_get_next(&ss->idr, &tmpid); + spin_unlock(&ss->id_lock); + + if (!tmp) + break; + if (tmp->depth >= depth && tmp->stack[depth] == rootid) { + ret = rcu_dereference(tmp->css); + if (ret) { + *foundid = tmpid; + break; + } + } + /* continue to scan from next id */ + tmpid = tmpid + 1; + } + return ret; +} + diff --git a/lib/idr.c b/lib/idr.c index dab4bca86f5d..80ca9aca038b 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -578,6 +578,52 @@ int idr_for_each(struct idr *idp, } EXPORT_SYMBOL(idr_for_each); +/** + * idr_get_next - lookup next object of id to given id. + * @idp: idr handle + * @id: pointer to lookup key + * + * Returns pointer to registered object with id, which is next number to + * given id. + */ + +void *idr_get_next(struct idr *idp, int *nextidp) +{ + struct idr_layer *p, *pa[MAX_LEVEL]; + struct idr_layer **paa = &pa[0]; + int id = *nextidp; + int n, max; + + /* find first ent */ + n = idp->layers * IDR_BITS; + max = 1 << n; + p = rcu_dereference(idp->top); + if (!p) + return NULL; + + while (id < max) { + while (n > 0 && p) { + n -= IDR_BITS; + *paa++ = p; + p = rcu_dereference(p->ary[(id >> n) & IDR_MASK]); + } + + if (p) { + *nextidp = id; + return p; + } + + id += 1 << n; + while (n < fls(id)) { + n += IDR_BITS; + p = *--paa; + } + } + return NULL; +} + + + /** * idr_replace - replace pointer for given id * @idp: idr handle -- cgit v1.2.3 From ec64f51545fffbc4cb968f0cea56341a4b07e85a Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Thu, 2 Apr 2009 16:57:26 -0700 Subject: cgroup: fix frequent -EBUSY at rmdir In following situation, with memory subsystem, /groupA use_hierarchy==1 /01 some tasks /02 some tasks /03 some tasks /04 empty When tasks under 01/02/03 hit limit on /groupA, hierarchical reclaim is triggered and the kernel walks tree under groupA. In this case, rmdir /groupA/04 fails with -EBUSY frequently because of temporal refcnt from the kernel. In general. cgroup can be rmdir'd if there are no children groups and no tasks. Frequent fails of rmdir() is not useful to users. (And the reason for -EBUSY is unknown to users.....in most cases) This patch tries to modify above behavior, by - retries if css_refcnt is got by someone. - add "return value" to pre_destroy() and allows subsystem to say "we're really busy!" Signed-off-by: KAMEZAWA Hiroyuki Cc: Paul Menage Cc: Li Zefan Cc: Balbir Singh Cc: Daisuke Nishimura Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/cgroups.txt | 6 ++- include/linux/cgroup.h | 6 ++- kernel/cgroup.c | 81 ++++++++++++++++++++++++++++++++------- mm/memcontrol.c | 5 ++- 4 files changed, 79 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index 93feb8444489..cdc46a501b85 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -476,11 +476,13 @@ cgroup->parent is still valid. (Note - can also be called for a newly-created cgroup if an error occurs after this subsystem's create() method has been called for the new cgroup). -void pre_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp); +int pre_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp); Called before checking the reference count on each subsystem. This may be useful for subsystems which have some extra references even if -there are not tasks in the cgroup. +there are not tasks in the cgroup. If pre_destroy() returns error code, +rmdir() will fail with it. From this behavior, pre_destroy() can be +called multiple times against a cgroup. int can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, struct task_struct *task) diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 9a23bb098205..7d824b80b3d7 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -135,6 +135,10 @@ enum { CGRP_RELEASABLE, /* Control Group requires release notifications to userspace */ CGRP_NOTIFY_ON_RELEASE, + /* + * A thread in rmdir() is wating for this cgroup. + */ + CGRP_WAIT_ON_RMDIR, }; struct cgroup { @@ -360,7 +364,7 @@ int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task); struct cgroup_subsys { struct cgroup_subsys_state *(*create)(struct cgroup_subsys *ss, struct cgroup *cgrp); - void (*pre_destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp); + int (*pre_destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp); void (*destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp); int (*can_attach)(struct cgroup_subsys *ss, struct cgroup *cgrp, struct task_struct *tsk); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index d3c521137425..fc5e4a48582f 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -622,13 +622,18 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb) * Call subsys's pre_destroy handler. * This is called before css refcnt check. */ -static void cgroup_call_pre_destroy(struct cgroup *cgrp) +static int cgroup_call_pre_destroy(struct cgroup *cgrp) { struct cgroup_subsys *ss; + int ret = 0; + for_each_subsys(cgrp->root, ss) - if (ss->pre_destroy) - ss->pre_destroy(ss, cgrp); - return; + if (ss->pre_destroy) { + ret = ss->pre_destroy(ss, cgrp); + if (ret) + break; + } + return ret; } static void free_cgroup_rcu(struct rcu_head *obj) @@ -722,6 +727,22 @@ static void cgroup_d_remove_dir(struct dentry *dentry) remove_dir(dentry); } +/* + * A queue for waiters to do rmdir() cgroup. A tasks will sleep when + * cgroup->count == 0 && list_empty(&cgroup->children) && subsys has some + * reference to css->refcnt. In general, this refcnt is expected to goes down + * to zero, soon. + * + * CGRP_WAIT_ON_RMDIR flag is modified under cgroup's inode->i_mutex; + */ +DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq); + +static void cgroup_wakeup_rmdir_waiters(const struct cgroup *cgrp) +{ + if (unlikely(test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags))) + wake_up_all(&cgroup_rmdir_waitq); +} + static int rebind_subsystems(struct cgroupfs_root *root, unsigned long final_bits) { @@ -1317,6 +1338,12 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) set_bit(CGRP_RELEASABLE, &oldcgrp->flags); synchronize_rcu(); put_css_set(cg); + + /* + * wake up rmdir() waiter. the rmdir should fail since the cgroup + * is no longer empty. + */ + cgroup_wakeup_rmdir_waiters(cgrp); return 0; } @@ -2608,9 +2635,11 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) struct cgroup *cgrp = dentry->d_fsdata; struct dentry *d; struct cgroup *parent; + DEFINE_WAIT(wait); + int ret; /* the vfs holds both inode->i_mutex already */ - +again: mutex_lock(&cgroup_mutex); if (atomic_read(&cgrp->count) != 0) { mutex_unlock(&cgroup_mutex); @@ -2626,17 +2655,39 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) * Call pre_destroy handlers of subsys. Notify subsystems * that rmdir() request comes. */ - cgroup_call_pre_destroy(cgrp); + ret = cgroup_call_pre_destroy(cgrp); + if (ret) + return ret; mutex_lock(&cgroup_mutex); parent = cgrp->parent; - - if (atomic_read(&cgrp->count) - || !list_empty(&cgrp->children) - || !cgroup_clear_css_refs(cgrp)) { + if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) { mutex_unlock(&cgroup_mutex); return -EBUSY; } + /* + * css_put/get is provided for subsys to grab refcnt to css. In typical + * case, subsystem has no reference after pre_destroy(). But, under + * hierarchy management, some *temporal* refcnt can be hold. + * To avoid returning -EBUSY to a user, waitqueue is used. If subsys + * is really busy, it should return -EBUSY at pre_destroy(). wake_up + * is called when css_put() is called and refcnt goes down to 0. + */ + set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); + prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE); + + if (!cgroup_clear_css_refs(cgrp)) { + mutex_unlock(&cgroup_mutex); + schedule(); + finish_wait(&cgroup_rmdir_waitq, &wait); + clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); + if (signal_pending(current)) + return -EINTR; + goto again; + } + /* NO css_tryget() can success after here. */ + finish_wait(&cgroup_rmdir_waitq, &wait); + clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); spin_lock(&release_list_lock); set_bit(CGRP_REMOVED, &cgrp->flags); @@ -3194,10 +3245,12 @@ void __css_put(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; rcu_read_lock(); - if ((atomic_dec_return(&css->refcnt) == 1) && - notify_on_release(cgrp)) { - set_bit(CGRP_RELEASABLE, &cgrp->flags); - check_for_release(cgrp); + if (atomic_dec_return(&css->refcnt) == 1) { + if (notify_on_release(cgrp)) { + set_bit(CGRP_RELEASABLE, &cgrp->flags); + check_for_release(cgrp); + } + cgroup_wakeup_rmdir_waiters(cgrp); } rcu_read_unlock(); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8e4be9cb2a6a..8ffec674c5ac 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2272,11 +2272,12 @@ free_out: return ERR_PTR(-ENOMEM); } -static void mem_cgroup_pre_destroy(struct cgroup_subsys *ss, +static int mem_cgroup_pre_destroy(struct cgroup_subsys *ss, struct cgroup *cont) { struct mem_cgroup *mem = mem_cgroup_from_cont(cont); - mem_cgroup_force_empty(mem, false); + + return mem_cgroup_force_empty(mem, false); } static void mem_cgroup_destroy(struct cgroup_subsys *ss, -- cgit v1.2.3 From 099fca3225b39f7a3ed853036038054172b55581 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Thu, 2 Apr 2009 16:57:29 -0700 Subject: cgroups: show correct file mode We have some read-only files and write-only files, but currently they are all set to 0644, which is counter-intuitive and cause trouble for some cgroup tools like libcgroup. This patch adds 'mode' to struct cftype to allow cgroup subsys to set it's own files' file mode, and for the most cases cft->mode can be default to 0 and cgroup will figure out proper mode. Acked-by: Paul Menage Reviewed-by: KAMEZAWA Hiroyuki Signed-off-by: Li Zefan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 5 +++++ kernel/cgroup.c | 38 ++++++++++++++++++++++++++++++++++---- kernel/cpuset.c | 1 + 3 files changed, 40 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 7d824b80b3d7..b2816fba5306 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -258,6 +258,11 @@ struct cftype { */ char name[MAX_CFTYPE_NAME]; int private; + /* + * If not 0, file mode is set to this value, otherwise it will + * be figured out automatically + */ + mode_t mode; /* * If non-zero, defines the maximum length of string that can diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 9a6c2bfa1d9f..fea11c5c990c 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1686,7 +1686,7 @@ static struct inode_operations cgroup_dir_inode_operations = { .rename = cgroup_rename, }; -static int cgroup_create_file(struct dentry *dentry, int mode, +static int cgroup_create_file(struct dentry *dentry, mode_t mode, struct super_block *sb) { static const struct dentry_operations cgroup_dops = { @@ -1732,7 +1732,7 @@ static int cgroup_create_file(struct dentry *dentry, int mode, * @mode: mode to set on new directory. */ static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry, - int mode) + mode_t mode) { struct dentry *parent; int error = 0; @@ -1750,6 +1750,33 @@ static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry, return error; } +/** + * cgroup_file_mode - deduce file mode of a control file + * @cft: the control file in question + * + * returns cft->mode if ->mode is not 0 + * returns S_IRUGO|S_IWUSR if it has both a read and a write handler + * returns S_IRUGO if it has only a read handler + * returns S_IWUSR if it has only a write hander + */ +static mode_t cgroup_file_mode(const struct cftype *cft) +{ + mode_t mode = 0; + + if (cft->mode) + return cft->mode; + + if (cft->read || cft->read_u64 || cft->read_s64 || + cft->read_map || cft->read_seq_string) + mode |= S_IRUGO; + + if (cft->write || cft->write_u64 || cft->write_s64 || + cft->write_string || cft->trigger) + mode |= S_IWUSR; + + return mode; +} + int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys, const struct cftype *cft) @@ -1757,6 +1784,7 @@ int cgroup_add_file(struct cgroup *cgrp, struct dentry *dir = cgrp->dentry; struct dentry *dentry; int error; + mode_t mode; char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 }; if (subsys && !test_bit(ROOT_NOPREFIX, &cgrp->root->flags)) { @@ -1767,7 +1795,8 @@ int cgroup_add_file(struct cgroup *cgrp, BUG_ON(!mutex_is_locked(&dir->d_inode->i_mutex)); dentry = lookup_one_len(name, dir, strlen(name)); if (!IS_ERR(dentry)) { - error = cgroup_create_file(dentry, 0644 | S_IFREG, + mode = cgroup_file_mode(cft); + error = cgroup_create_file(dentry, mode | S_IFREG, cgrp->root->sb); if (!error) dentry->d_fsdata = (void *)cft; @@ -2349,6 +2378,7 @@ static struct cftype files[] = { .write_u64 = cgroup_tasks_write, .release = cgroup_tasks_release, .private = FILE_TASKLIST, + .mode = S_IRUGO | S_IWUSR, }, { @@ -2449,7 +2479,7 @@ static void cgroup_unlock_hierarchy(struct cgroupfs_root *root) * Must be called with the mutex on the parent inode held */ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, - int mode) + mode_t mode) { struct cgroup *cgrp; struct cgroupfs_root *root = parent->root; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index f76db9dcaa05..ee5ec386aa8b 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1706,6 +1706,7 @@ static struct cftype files[] = { .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEMORY_PRESSURE, + .mode = S_IRUGO, }, { -- cgit v1.2.3 From 0b7f569e45bb6be142d87017030669a6a7d327a1 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Thu, 2 Apr 2009 16:57:38 -0700 Subject: memcg: fix OOM killer under memcg This patch tries to fix OOM Killer problems caused by hierarchy. Now, memcg itself has OOM KILL function (in oom_kill.c) and tries to kill a task in memcg. But, when hierarchy is used, it's broken and correct task cannot be killed. For example, in following cgroup /groupA/ hierarchy=1, limit=1G, 01 nolimit 02 nolimit All tasks' memory usage under /groupA, /groupA/01, groupA/02 is limited to groupA's 1Gbytes but OOM Killer just kills tasks in groupA. This patch provides makes the bad process be selected from all tasks under hierarchy. BTW, currently, oom_jiffies is updated against groupA in above case. oom_jiffies of tree should be updated. To see how oom_jiffies is used, please check mem_cgroup_oom_called() callers. [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: const fix] Signed-off-by: KAMEZAWA Hiroyuki Cc: Paul Menage Cc: Li Zefan Cc: Balbir Singh Cc: Daisuke Nishimura Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/memcg_test.txt | 20 +++++++++++++++++++- include/linux/cgroup.h | 2 +- kernel/cgroup.c | 2 +- mm/memcontrol.c | 30 ++++++++++++++++++++++++++++-- 4 files changed, 49 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroups/memcg_test.txt index 523a9c16c400..8a11caf417a0 100644 --- a/Documentation/cgroups/memcg_test.txt +++ b/Documentation/cgroups/memcg_test.txt @@ -1,5 +1,5 @@ Memory Resource Controller(Memcg) Implementation Memo. -Last Updated: 2009/1/19 +Last Updated: 2009/1/20 Base Kernel Version: based on 2.6.29-rc2. Because VM is getting complex (one of reasons is memcg...), memcg's behavior @@ -360,3 +360,21 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y. # kill malloc task. Of course, tmpfs v.s. swapoff test should be tested, too. + + 9.8 OOM-Killer + Out-of-memory caused by memcg's limit will kill tasks under + the memcg. When hierarchy is used, a task under hierarchy + will be killed by the kernel. + In this case, panic_on_oom shouldn't be invoked and tasks + in other groups shouldn't be killed. + + It's not difficult to cause OOM under memcg as following. + Case A) when you can swapoff + #swapoff -a + #echo 50M > /memory.limit_in_bytes + run 51M of malloc + + Case B) when you use mem+swap limitation. + #echo 50M > memory.limit_in_bytes + #echo 50M > memory.memsw.limit_in_bytes + run 51M of malloc diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b2816fba5306..43763bd772b9 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -503,7 +503,7 @@ struct cgroup_subsys_state *css_get_next(struct cgroup_subsys *ss, int id, /* Returns true if root is ancestor of cg */ bool css_is_ancestor(struct cgroup_subsys_state *cg, - struct cgroup_subsys_state *root); + const struct cgroup_subsys_state *root); /* Get id and depth of css */ unsigned short css_id(struct cgroup_subsys_state *css); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index f2a3f5c9936c..382109b5baeb 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3405,7 +3405,7 @@ unsigned short css_depth(struct cgroup_subsys_state *css) } bool css_is_ancestor(struct cgroup_subsys_state *child, - struct cgroup_subsys_state *root) + const struct cgroup_subsys_state *root) { struct css_id *child_id = rcu_dereference(child->id); struct css_id *root_id = rcu_dereference(root->id); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6f6a575e77ad..025f8abfae2d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -295,6 +295,9 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) { struct mem_cgroup *mem = NULL; + + if (!mm) + return NULL; /* * Because we have no locks, mm->owner's may be being moved to other * cgroup. We use css_tryget() here even if this looks @@ -486,10 +489,20 @@ void mem_cgroup_move_lists(struct page *page, int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem) { int ret; + struct mem_cgroup *curr = NULL; task_lock(task); - ret = task->mm && mm_match_cgroup(task->mm, mem); + rcu_read_lock(); + curr = try_get_mem_cgroup_from_mm(task->mm); + rcu_read_unlock(); task_unlock(task); + if (!curr) + return 0; + if (curr->use_hierarchy) + ret = css_is_ancestor(&curr->css, &mem->css); + else + ret = (curr == mem); + css_put(&curr->css); return ret; } @@ -820,6 +833,19 @@ bool mem_cgroup_oom_called(struct task_struct *task) rcu_read_unlock(); return ret; } + +static int record_last_oom_cb(struct mem_cgroup *mem, void *data) +{ + mem->last_oom_jiffies = jiffies; + return 0; +} + +static void record_last_oom(struct mem_cgroup *mem) +{ + mem_cgroup_walk_tree(mem, NULL, record_last_oom_cb); +} + + /* * Unlike exported interface, "oom" parameter is added. if oom==true, * oom-killer can be invoked. @@ -902,7 +928,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, mutex_lock(&memcg_tasklist); mem_cgroup_out_of_memory(mem_over_limit, gfp_mask); mutex_unlock(&memcg_tasklist); - mem_over_limit->last_oom_jiffies = jiffies; + record_last_oom(mem_over_limit); } goto nomem; } -- cgit v1.2.3 From e222432bfa7dcf6ec008622a978c9f284ed5e3a9 Mon Sep 17 00:00:00 2001 From: Balbir Singh Date: Thu, 2 Apr 2009 16:57:39 -0700 Subject: memcg: show memcg information during OOM Add RSS and swap to OOM output from memcg Display memcg values like failcnt, usage and limit when an OOM occurs due to memcg. Thanks to Johannes Weiner, Li Zefan, David Rientjes, Kamezawa Hiroyuki, Daisuke Nishimura and KOSAKI Motohiro for review. Sample output ------------- Task in /a/x killed as a result of limit of /a memory: usage 1048576kB, limit 1048576kB, failcnt 4183 memory+swap: usage 1400964kB, limit 9007199254740991kB, failcnt 0 [akpm@linux-foundation.org: compilation fix] [akpm@linux-foundation.org: fix kerneldoc and whitespace] [akpm@linux-foundation.org: add printk facility level] Signed-off-by: Balbir Singh Cc: KAMEZAWA Hiroyuki Cc: Daisuke Nishimura Cc: Li Zefan Cc: Paul Menage Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 7 +++++ mm/memcontrol.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++ mm/oom_kill.c | 1 + 3 files changed, 77 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 326f45c86530..7aba9f264622 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -104,6 +104,8 @@ struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg, struct zone *zone); struct zone_reclaim_stat* mem_cgroup_get_reclaim_stat_from_page(struct page *page); +extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, + struct task_struct *p); #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP extern int do_swap_account; @@ -270,6 +272,11 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page) return NULL; } +static inline void +mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) +{ +} + #endif /* CONFIG_CGROUP_MEM_CONT */ #endif /* _LINUX_MEMCONTROL_H */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 025f8abfae2d..2bdb6149faeb 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -721,6 +722,74 @@ static int mem_cgroup_count_children_cb(struct mem_cgroup *mem, void *data) (*val)++; return 0; } + +/** + * mem_cgroup_print_mem_info: Called from OOM with tasklist_lock held in read mode. + * @memcg: The memory cgroup that went over limit + * @p: Task that is going to be killed + * + * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is + * enabled + */ +void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) +{ + struct cgroup *task_cgrp; + struct cgroup *mem_cgrp; + /* + * Need a buffer in BSS, can't rely on allocations. The code relies + * on the assumption that OOM is serialized for memory controller. + * If this assumption is broken, revisit this code. + */ + static char memcg_name[PATH_MAX]; + int ret; + + if (!memcg) + return; + + + rcu_read_lock(); + + mem_cgrp = memcg->css.cgroup; + task_cgrp = task_cgroup(p, mem_cgroup_subsys_id); + + ret = cgroup_path(task_cgrp, memcg_name, PATH_MAX); + if (ret < 0) { + /* + * Unfortunately, we are unable to convert to a useful name + * But we'll still print out the usage information + */ + rcu_read_unlock(); + goto done; + } + rcu_read_unlock(); + + printk(KERN_INFO "Task in %s killed", memcg_name); + + rcu_read_lock(); + ret = cgroup_path(mem_cgrp, memcg_name, PATH_MAX); + if (ret < 0) { + rcu_read_unlock(); + goto done; + } + rcu_read_unlock(); + + /* + * Continues from above, so we don't need an KERN_ level + */ + printk(KERN_CONT " as a result of limit of %s\n", memcg_name); +done: + + printk(KERN_INFO "memory: usage %llukB, limit %llukB, failcnt %llu\n", + res_counter_read_u64(&memcg->res, RES_USAGE) >> 10, + res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10, + res_counter_read_u64(&memcg->res, RES_FAILCNT)); + printk(KERN_INFO "memory+swap: usage %llukB, limit %llukB, " + "failcnt %llu\n", + res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10, + res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10, + res_counter_read_u64(&memcg->memsw, RES_FAILCNT)); +} + /* * This function returns the number of memcg under hierarchy tree. Returns * 1(self count) if no children. diff --git a/mm/oom_kill.c b/mm/oom_kill.c index d3b9bac085b5..2f3166e308d9 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -394,6 +394,7 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, cpuset_print_task_mems_allowed(current); task_unlock(current); dump_stack(); + mem_cgroup_print_oom_info(mem, current); show_mem(); if (sysctl_oom_dump_tasks) dump_tasks(mem); -- cgit v1.2.3 From c137b5ece4b111e46981aae7da77315b9909809f Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Thu, 2 Apr 2009 16:57:40 -0700 Subject: memcg: remove mem_cgroup_calc_mapped_ratio() Currently, mem_cgroup_calc_mapped_ratio() is unused at all. it can be removed and KAMEZAWA-san suggested it. Signed-off-by: KOSAKI Motohiro Cc: KAMEZAWA Hiroyuki Acked-by: Balbir Singh Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 6 ------ mm/memcontrol.c | 17 ----------------- 2 files changed, 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7aba9f264622..4562d09ab964 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -88,7 +88,6 @@ extern void mem_cgroup_end_migration(struct mem_cgroup *mem, /* * For memory reclaim. */ -extern int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem); extern long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem); extern int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem); @@ -211,11 +210,6 @@ static inline void mem_cgroup_end_migration(struct mem_cgroup *mem, { } -static inline int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem) -{ - return 0; -} - static inline int mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem) { return 0; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2bdb6149faeb..7bb14fdc780c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -507,23 +507,6 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem) return ret; } -/* - * Calculate mapped_ratio under memory controller. This will be used in - * vmscan.c for deteremining we have to reclaim mapped pages. - */ -int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem) -{ - long total, rss; - - /* - * usage is recorded in bytes. But, here, we assume the number of - * physical pages can be represented by "long" on any arch. - */ - total = (long) (mem->res.usage >> PAGE_SHIFT) + 1L; - rss = (long)mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS); - return (int)((rss * 100L) / total); -} - /* * prev_priority control...this will be used in memory reclaim path. */ -- cgit v1.2.3 From 3918b96e03b2b8dd05889320623f6870e81d35ec Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Thu, 2 Apr 2009 16:57:41 -0700 Subject: memcg: remove mem_cgroup_reclaim_imbalance() remnants commit 4f98a2fee8acdb4ac84545df98cccecfd130f8db (vmscan: split LRU lists into anon & file sets) removed mem_cgroup_reclaim_imbalance(), but there are some leftovers in memcontrol.h. Signed-off-by: KOSAKI Motohiro Cc: KAMEZAWA Hiroyuki Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 4562d09ab964..18146c980b68 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -88,8 +88,6 @@ extern void mem_cgroup_end_migration(struct mem_cgroup *mem, /* * For memory reclaim. */ -extern long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem); - extern int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem); extern void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem, int priority); @@ -210,11 +208,6 @@ static inline void mem_cgroup_end_migration(struct mem_cgroup *mem, { } -static inline int mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem) -{ - return 0; -} - static inline int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem) { return 0; -- cgit v1.2.3 From a3b2d692690aef228e493b1beaafe5364cab3237 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Thu, 2 Apr 2009 16:57:45 -0700 Subject: cgroups: use css id in swap cgroup for saving memory v5 Try to use CSS ID for records in swap_cgroup. By this, on 64bit machine, size of swap_cgroup goes down to 2 bytes from 8bytes. This means, when 2GB of swap is equipped, (assume the page size is 4096bytes) From size of swap_cgroup = 2G/4k * 8 = 4Mbytes. To size of swap_cgroup = 2G/4k * 2 = 1Mbytes. Reduction is large. Of course, there are trade-offs. This CSS ID will add overhead to swap-in/swap-out/swap-free. But in general, - swap is a resource which the user tend to avoid use. - If swap is never used, swap_cgroup area is not used. - Reading traditional manuals, size of swap should be proportional to size of memory. Memory size of machine is increasing now. I think reducing size of swap_cgroup makes sense. Note: - ID->CSS lookup routine has no locks, it's under RCU-Read-Side. - memcg can be obsolete at rmdir() but not freed while refcnt from swap_cgroup is available. Changelog v4->v5: - reworked on to memcg-charge-swapcache-to-proper-memcg.patch Changlog ->v4: - fixed not configured case. - deleted unnecessary comments. - fixed NULL pointer bug. - fixed message in dmesg. [nishimura@mxp.nes.nec.co.jp: css_tryget can be called twice in !PageCgroupUsed case] Signed-off-by: KAMEZAWA Hiroyuki Cc: Li Zefan Cc: Balbir Singh Cc: Paul Menage Cc: Hugh Dickins Signed-off-by: Daisuke Nishimura Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_cgroup.h | 13 ++++---- mm/memcontrol.c | 74 +++++++++++++++++++++++++++++++++++++-------- mm/page_cgroup.c | 32 +++++++++----------- 3 files changed, 82 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index 602cc1fdee90..7339c7bf7331 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -91,24 +91,23 @@ static inline void page_cgroup_init(void) #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP #include -extern struct mem_cgroup * -swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem); -extern struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent); +extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id); +extern unsigned short lookup_swap_cgroup(swp_entry_t ent); extern int swap_cgroup_swapon(int type, unsigned long max_pages); extern void swap_cgroup_swapoff(int type); #else #include static inline -struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem) +unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id) { - return NULL; + return 0; } static inline -struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent) +unsigned short lookup_swap_cgroup(swp_entry_t ent) { - return NULL; + return 0; } static inline int diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 81b0ae8183d0..55dea5968464 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -991,10 +991,31 @@ nomem: return -ENOMEM; } + +/* + * A helper function to get mem_cgroup from ID. must be called under + * rcu_read_lock(). The caller must check css_is_removed() or some if + * it's concern. (dropping refcnt from swap can be called against removed + * memcg.) + */ +static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) +{ + struct cgroup_subsys_state *css; + + /* ID 0 is unused ID */ + if (!id) + return NULL; + css = css_lookup(&mem_cgroup_subsys, id); + if (!css) + return NULL; + return container_of(css, struct mem_cgroup, css); +} + static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page) { struct mem_cgroup *mem; struct page_cgroup *pc; + unsigned short id; swp_entry_t ent; VM_BUG_ON(!PageLocked(page)); @@ -1006,16 +1027,19 @@ static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page) /* * Used bit of swapcache is solid under page lock. */ - if (PageCgroupUsed(pc)) + if (PageCgroupUsed(pc)) { mem = pc->mem_cgroup; - else { + if (mem && !css_tryget(&mem->css)) + mem = NULL; + } else { ent.val = page_private(page); - mem = lookup_swap_cgroup(ent); + id = lookup_swap_cgroup(ent); + rcu_read_lock(); + mem = mem_cgroup_lookup(id); + if (mem && !css_tryget(&mem->css)) + mem = NULL; + rcu_read_unlock(); } - if (!mem) - return NULL; - if (!css_tryget(&mem->css)) - return NULL; return mem; } @@ -1276,12 +1300,22 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, if (do_swap_account && !ret && PageSwapCache(page)) { swp_entry_t ent = {.val = page_private(page)}; + unsigned short id; /* avoid double counting */ - mem = swap_cgroup_record(ent, NULL); + id = swap_cgroup_record(ent, 0); + rcu_read_lock(); + mem = mem_cgroup_lookup(id); if (mem) { + /* + * We did swap-in. Then, this entry is doubly counted + * both in mem and memsw. We uncharge it, here. + * Recorded ID can be obsolete. We avoid calling + * css_tryget() + */ res_counter_uncharge(&mem->memsw, PAGE_SIZE); mem_cgroup_put(mem); } + rcu_read_unlock(); } return ret; } @@ -1346,13 +1380,21 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr) */ if (do_swap_account && PageSwapCache(page)) { swp_entry_t ent = {.val = page_private(page)}; + unsigned short id; struct mem_cgroup *memcg; - memcg = swap_cgroup_record(ent, NULL); + + id = swap_cgroup_record(ent, 0); + rcu_read_lock(); + memcg = mem_cgroup_lookup(id); if (memcg) { + /* + * This recorded memcg can be obsolete one. So, avoid + * calling css_tryget + */ res_counter_uncharge(&memcg->memsw, PAGE_SIZE); mem_cgroup_put(memcg); } - + rcu_read_unlock(); } /* add this page(page_cgroup) to the LRU we want. */ @@ -1473,7 +1515,7 @@ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent) MEM_CGROUP_CHARGE_TYPE_SWAPOUT); /* record memcg information */ if (do_swap_account && memcg) { - swap_cgroup_record(ent, memcg); + swap_cgroup_record(ent, css_id(&memcg->css)); mem_cgroup_get(memcg); } if (memcg) @@ -1488,15 +1530,23 @@ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent) void mem_cgroup_uncharge_swap(swp_entry_t ent) { struct mem_cgroup *memcg; + unsigned short id; if (!do_swap_account) return; - memcg = swap_cgroup_record(ent, NULL); + id = swap_cgroup_record(ent, 0); + rcu_read_lock(); + memcg = mem_cgroup_lookup(id); if (memcg) { + /* + * We uncharge this because swap is freed. + * This memcg can be obsolete one. We avoid calling css_tryget + */ res_counter_uncharge(&memcg->memsw, PAGE_SIZE); mem_cgroup_put(memcg); } + rcu_read_unlock(); } #endif diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index ceecfbb143fa..ebf81074bed4 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -285,12 +285,8 @@ struct swap_cgroup_ctrl { struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES]; -/* - * This 8bytes seems big..maybe we can reduce this when we can use "id" for - * cgroup rather than pointer. - */ struct swap_cgroup { - struct mem_cgroup *val; + unsigned short id; }; #define SC_PER_PAGE (PAGE_SIZE/sizeof(struct swap_cgroup)) #define SC_POS_MASK (SC_PER_PAGE - 1) @@ -342,10 +338,10 @@ not_enough_page: * @ent: swap entry to be recorded into * @mem: mem_cgroup to be recorded * - * Returns old value at success, NULL at failure. - * (Of course, old value can be NULL.) + * Returns old value at success, 0 at failure. + * (Of course, old value can be 0.) */ -struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem) +unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id) { int type = swp_type(ent); unsigned long offset = swp_offset(ent); @@ -354,18 +350,18 @@ struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem) struct swap_cgroup_ctrl *ctrl; struct page *mappage; struct swap_cgroup *sc; - struct mem_cgroup *old; + unsigned short old; if (!do_swap_account) - return NULL; + return 0; ctrl = &swap_cgroup_ctrl[type]; mappage = ctrl->map[idx]; sc = page_address(mappage); sc += pos; - old = sc->val; - sc->val = mem; + old = sc->id; + sc->id = id; return old; } @@ -374,9 +370,9 @@ struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem) * lookup_swap_cgroup - lookup mem_cgroup tied to swap entry * @ent: swap entry to be looked up. * - * Returns pointer to mem_cgroup at success. NULL at failure. + * Returns CSS ID of mem_cgroup at success. 0 at failure. (0 is invalid ID) */ -struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent) +unsigned short lookup_swap_cgroup(swp_entry_t ent) { int type = swp_type(ent); unsigned long offset = swp_offset(ent); @@ -385,16 +381,16 @@ struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent) struct swap_cgroup_ctrl *ctrl; struct page *mappage; struct swap_cgroup *sc; - struct mem_cgroup *ret; + unsigned short ret; if (!do_swap_account) - return NULL; + return 0; ctrl = &swap_cgroup_ctrl[type]; mappage = ctrl->map[idx]; sc = page_address(mappage); sc += pos; - ret = sc->val; + ret = sc->id; return ret; } @@ -432,7 +428,7 @@ int swap_cgroup_swapon(int type, unsigned long max_pages) printk(KERN_INFO "swap_cgroup: uses %ld bytes of vmalloc for pointer array space" - " and %ld bytes to hold mem_cgroup pointers on swap\n", + " and %ld bytes to hold mem_cgroup information per swap ents\n", array_size, length * PAGE_SIZE); printk(KERN_INFO "swap_cgroup can be disabled by noswapaccount boot option.\n"); -- cgit v1.2.3 From bd1a8ab73edd449fecda633449cc277b856ad4f5 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Thu, 2 Apr 2009 16:57:50 -0700 Subject: cgroups: add 'data' field to struct cgroup_scanner We need to pass some data to test_task() or process_task() in some cases. Will be used later. Signed-off-by: Li Zefan Cc: KAMEZAWA Hiroyuki Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 43763bd772b9..4316a546beb5 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -337,6 +337,7 @@ struct cgroup_scanner { void (*process_task)(struct task_struct *p, struct cgroup_scanner *scan); struct ptr_heap *heap; + void *data; }; /* -- cgit v1.2.3 From a1bc5a4eee990a1f290735c8694d0aebdad095fa Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 2 Apr 2009 16:57:54 -0700 Subject: cpusets: replace zone allowed functions with node allowed The cpuset_zone_allowed() variants are actually only a function of the zone's node. Cc: Paul Menage Acked-by: Christoph Lameter Cc: Randy Dunlap Signed-off-by: David Rientjes Cc: Ingo Molnar Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuset.h | 33 +++++++++++++++++++++++----- kernel/cpuset.c | 59 +++++++++++++++++++++----------------------------- 2 files changed, 52 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 2e0d79678deb..05ea1dd7d681 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -12,6 +12,7 @@ #include #include #include +#include #ifdef CONFIG_CPUSETS @@ -29,19 +30,29 @@ void cpuset_init_current_mems_allowed(void); void cpuset_update_task_memory_state(void); int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask); -extern int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask); -extern int __cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask); +extern int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask); +extern int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask); -static int inline cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask) +static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask) { return number_of_cpusets <= 1 || - __cpuset_zone_allowed_softwall(z, gfp_mask); + __cpuset_node_allowed_softwall(node, gfp_mask); } -static int inline cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask) +static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask) { return number_of_cpusets <= 1 || - __cpuset_zone_allowed_hardwall(z, gfp_mask); + __cpuset_node_allowed_hardwall(node, gfp_mask); +} + +static inline int cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask) +{ + return cpuset_node_allowed_softwall(zone_to_nid(z), gfp_mask); +} + +static inline int cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask) +{ + return cpuset_node_allowed_hardwall(zone_to_nid(z), gfp_mask); } extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, @@ -112,6 +123,16 @@ static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) return 1; } +static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask) +{ + return 1; +} + +static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask) +{ + return 1; +} + static inline int cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask) { return 1; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 0619f109d38d..3ff910eb30d3 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2181,26 +2181,24 @@ static const struct cpuset *nearest_hardwall_ancestor(const struct cpuset *cs) } /** - * cpuset_zone_allowed_softwall - Can we allocate on zone z's memory node? - * @z: is this zone on an allowed node? + * cpuset_node_allowed_softwall - Can we allocate on a memory node? + * @node: is this an allowed node? * @gfp_mask: memory allocation flags * - * If we're in interrupt, yes, we can always allocate. If - * __GFP_THISNODE is set, yes, we can always allocate. If zone - * z's node is in our tasks mems_allowed, yes. If it's not a - * __GFP_HARDWALL request and this zone's nodes is in the nearest - * hardwalled cpuset ancestor to this tasks cpuset, yes. - * If the task has been OOM killed and has access to memory reserves - * as specified by the TIF_MEMDIE flag, yes. + * If we're in interrupt, yes, we can always allocate. If __GFP_THISNODE is + * set, yes, we can always allocate. If node is in our task's mems_allowed, + * yes. If it's not a __GFP_HARDWALL request and this node is in the nearest + * hardwalled cpuset ancestor to this task's cpuset, yes. If the task has been + * OOM killed and has access to memory reserves as specified by the TIF_MEMDIE + * flag, yes. * Otherwise, no. * - * If __GFP_HARDWALL is set, cpuset_zone_allowed_softwall() - * reduces to cpuset_zone_allowed_hardwall(). Otherwise, - * cpuset_zone_allowed_softwall() might sleep, and might allow a zone - * from an enclosing cpuset. + * If __GFP_HARDWALL is set, cpuset_node_allowed_softwall() reduces to + * cpuset_node_allowed_hardwall(). Otherwise, cpuset_node_allowed_softwall() + * might sleep, and might allow a node from an enclosing cpuset. * - * cpuset_zone_allowed_hardwall() only handles the simpler case of - * hardwall cpusets, and never sleeps. + * cpuset_node_allowed_hardwall() only handles the simpler case of hardwall + * cpusets, and never sleeps. * * The __GFP_THISNODE placement logic is really handled elsewhere, * by forcibly using a zonelist starting at a specified node, and by @@ -2239,20 +2237,17 @@ static const struct cpuset *nearest_hardwall_ancestor(const struct cpuset *cs) * GFP_USER - only nodes in current tasks mems allowed ok. * * Rule: - * Don't call cpuset_zone_allowed_softwall if you can't sleep, unless you + * Don't call cpuset_node_allowed_softwall if you can't sleep, unless you * pass in the __GFP_HARDWALL flag set in gfp_flag, which disables * the code that might scan up ancestor cpusets and sleep. */ - -int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask) +int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask) { - int node; /* node that zone z is on */ const struct cpuset *cs; /* current cpuset ancestors */ int allowed; /* is allocation in zone z allowed? */ if (in_interrupt() || (gfp_mask & __GFP_THISNODE)) return 1; - node = zone_to_nid(z); might_sleep_if(!(gfp_mask & __GFP_HARDWALL)); if (node_isset(node, current->mems_allowed)) return 1; @@ -2281,15 +2276,15 @@ int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask) } /* - * cpuset_zone_allowed_hardwall - Can we allocate on zone z's memory node? - * @z: is this zone on an allowed node? + * cpuset_node_allowed_hardwall - Can we allocate on a memory node? + * @node: is this an allowed node? * @gfp_mask: memory allocation flags * - * If we're in interrupt, yes, we can always allocate. - * If __GFP_THISNODE is set, yes, we can always allocate. If zone - * z's node is in our tasks mems_allowed, yes. If the task has been - * OOM killed and has access to memory reserves as specified by the - * TIF_MEMDIE flag, yes. Otherwise, no. + * If we're in interrupt, yes, we can always allocate. If __GFP_THISNODE is + * set, yes, we can always allocate. If node is in our task's mems_allowed, + * yes. If the task has been OOM killed and has access to memory reserves as + * specified by the TIF_MEMDIE flag, yes. + * Otherwise, no. * * The __GFP_THISNODE placement logic is really handled elsewhere, * by forcibly using a zonelist starting at a specified node, and by @@ -2297,20 +2292,16 @@ int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask) * any node on the zonelist except the first. By the time any such * calls get to this routine, we should just shut up and say 'yes'. * - * Unlike the cpuset_zone_allowed_softwall() variant, above, - * this variant requires that the zone be in the current tasks + * Unlike the cpuset_node_allowed_softwall() variant, above, + * this variant requires that the node be in the current task's * mems_allowed or that we're in interrupt. It does not scan up the * cpuset hierarchy for the nearest enclosing mem_exclusive cpuset. * It never sleeps. */ - -int __cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask) +int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask) { - int node; /* node that zone z is on */ - if (in_interrupt() || (gfp_mask & __GFP_THISNODE)) return 1; - node = zone_to_nid(z); if (node_isset(node, current->mems_allowed)) return 1; /* -- cgit v1.2.3 From 43918f2bf4806675943416d539d9d5e4d585ebff Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 2 Apr 2009 16:58:00 -0700 Subject: signals: remove 'handler' parameter to tracehook functions Container-init must behave like global-init to processes within the container and hence it must be immune to unhandled fatal signals from within the container (i.e SIG_DFL signals that terminate the process). But the same container-init must behave like a normal process to processes in ancestor namespaces and so if it receives the same fatal signal from a process in ancestor namespace, the signal must be processed. Implementing these semantics requires that send_signal() determine pid namespace of the sender but since signals can originate from workqueues/ interrupt-handlers, determining pid namespace of sender may not always be possible or safe. This patchset implements the design/simplified semantics suggested by Oleg Nesterov. The simplified semantics for container-init are: - container-init must never be terminated by a signal from a descendant process. - container-init must never be immune to SIGKILL from an ancestor namespace (so a process in parent namespace must always be able to terminate a descendant container). - container-init may be immune to unhandled fatal signals (like SIGUSR1) even if they are from ancestor namespace. SIGKILL/SIGSTOP are the only reliable signals to a container-init from ancestor namespace. This patch: Based on an earlier patch submitted by Oleg Nesterov and comments from Roland McGrath (http://lkml.org/lkml/2008/11/19/258). The handler parameter is currently unused in the tracehook functions. Besides, the tracehook functions are called with siglock held, so the functions can check the handler if they later need to. Removing the parameter simiplifies changes to sig_ignored() in a follow-on patch. Signed-off-by: Sukadev Bhattiprolu Acked-by: Roland McGrath Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Cc: Daniel Lezcano Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/ptrace.c | 2 +- include/linux/tracehook.h | 13 ++++--------- kernel/signal.c | 6 +++--- 3 files changed, 8 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 19378715f415..b7cc21bc6ae0 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1455,6 +1455,6 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs) * system call instruction. */ if (test_thread_flag(TIF_SINGLESTEP) && - tracehook_consider_fatal_signal(current, SIGTRAP, SIG_DFL)) + tracehook_consider_fatal_signal(current, SIGTRAP)) send_sigtrap(current, regs, 0, TRAP_BRKPT); } diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 6186a789d6c7..eb4c6545b384 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -388,17 +388,14 @@ static inline void tracehook_signal_handler(int sig, siginfo_t *info, * tracehook_consider_ignored_signal - suppress short-circuit of ignored signal * @task: task receiving the signal * @sig: signal number being sent - * @handler: %SIG_IGN or %SIG_DFL * * Return zero iff tracing doesn't care to examine this ignored signal, * so it can short-circuit normal delivery and never even get queued. - * Either @handler is %SIG_DFL and @sig's default is ignore, or it's %SIG_IGN. * * Called with @task->sighand->siglock held. */ static inline int tracehook_consider_ignored_signal(struct task_struct *task, - int sig, - void __user *handler) + int sig) { return (task_ptrace(task) & PT_PTRACED) != 0; } @@ -407,19 +404,17 @@ static inline int tracehook_consider_ignored_signal(struct task_struct *task, * tracehook_consider_fatal_signal - suppress special handling of fatal signal * @task: task receiving the signal * @sig: signal number being sent - * @handler: %SIG_DFL or %SIG_IGN * * Return nonzero to prevent special handling of this termination signal. - * Normally @handler is %SIG_DFL. It can be %SIG_IGN if @sig is ignored, - * in which case force_sig() is about to reset it to %SIG_DFL. + * Normally handler for signal is %SIG_DFL. It can be %SIG_IGN if @sig is + * ignored, in which case force_sig() is about to reset it to %SIG_DFL. * When this returns zero, this signal might cause a quick termination * that does not give the debugger a chance to intercept the signal. * * Called with or without @task->sighand->siglock held. */ static inline int tracehook_consider_fatal_signal(struct task_struct *task, - int sig, - void __user *handler) + int sig) { return (task_ptrace(task) & PT_PTRACED) != 0; } diff --git a/kernel/signal.c b/kernel/signal.c index 1c8814481a11..92a1ab004498 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -74,7 +74,7 @@ static int sig_ignored(struct task_struct *t, int sig) /* * Tracers may want to know about even ignored signals. */ - return !tracehook_consider_ignored_signal(t, sig, handler); + return !tracehook_consider_ignored_signal(t, sig); } /* @@ -318,7 +318,7 @@ int unhandled_signal(struct task_struct *tsk, int sig) return 1; if (handler != SIG_IGN && handler != SIG_DFL) return 0; - return !tracehook_consider_fatal_signal(tsk, sig, handler); + return !tracehook_consider_fatal_signal(tsk, sig); } @@ -777,7 +777,7 @@ static void complete_signal(int sig, struct task_struct *p, int group) !(signal->flags & (SIGNAL_UNKILLABLE | SIGNAL_GROUP_EXIT)) && !sigismember(&t->real_blocked, sig) && (sig == SIGKILL || - !tracehook_consider_fatal_signal(t, sig, SIG_DFL))) { + !tracehook_consider_fatal_signal(t, sig))) { /* * This signal will be fatal to the whole group. */ -- cgit v1.2.3 From 4576145c1ecdaaea9ef8976a48335206aa1ebf91 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 2 Apr 2009 16:58:14 -0700 Subject: ptrace: fix possible zombie leak on PTRACE_DETACH When ptrace_detach() takes tasklist, the tracee can be SIGKILL'ed. If it has already passed exit_notify() we can leak a zombie, because a) ptracing disables the auto-reaping logic, and b) ->real_parent was not notified about the child's death. ptrace_detach() should follow the ptrace_exit's logic, change the code accordingly. Signed-off-by: Oleg Nesterov Cc: Jerome Marchand Cc: Roland McGrath Tested-by: Denys Vlasenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 1 + kernel/ptrace.c | 9 +++++++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 98b93ca4db06..1a2b0cb55535 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -94,6 +94,7 @@ extern void ptrace_notify(int exit_code); extern void __ptrace_link(struct task_struct *child, struct task_struct *new_parent); extern void __ptrace_unlink(struct task_struct *child); +extern int __ptrace_detach(struct task_struct *tracer, struct task_struct *p); extern void ptrace_fork(struct task_struct *task, unsigned long clone_flags); #define PTRACE_MODE_READ 1 #define PTRACE_MODE_ATTACH 2 diff --git a/kernel/ptrace.c b/kernel/ptrace.c index f62a568e84ec..ee553b6ad125 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -237,6 +237,8 @@ out: int ptrace_detach(struct task_struct *child, unsigned int data) { + int dead = 0; + if (!valid_signal(data)) return -EIO; @@ -244,18 +246,21 @@ int ptrace_detach(struct task_struct *child, unsigned int data) ptrace_disable(child); clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); - /* protect against de_thread()->release_task() */ write_lock_irq(&tasklist_lock); + /* protect against de_thread()->release_task() */ if (child->ptrace) { child->exit_code = data; - __ptrace_unlink(child); + dead = __ptrace_detach(current, child); if (!child->exit_state) wake_up_process(child); } write_unlock_irq(&tasklist_lock); + if (unlikely(dead)) + release_task(child); + return 0; } -- cgit v1.2.3 From 39c626ae47c469abdfd30c6e42eff884931380d6 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 2 Apr 2009 16:58:18 -0700 Subject: forget_original_parent: split out the un-ptrace part By discussion with Roland. - Rename ptrace_exit() to exit_ptrace(), and change it to do all the necessary work with ->ptraced list by its own. - Move this code from exit.c to ptrace.c - Update the comment in ptrace_detach() to explain the rechecking of the child->ptrace. Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Cc: "Metzger, Markus T" Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 2 +- include/linux/sched.h | 5 +++ kernel/exit.c | 95 ++++---------------------------------------------- kernel/ptrace.c | 78 +++++++++++++++++++++++++++++++++++++++-- 4 files changed, 88 insertions(+), 92 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 1a2b0cb55535..67c15653fc23 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -94,7 +94,7 @@ extern void ptrace_notify(int exit_code); extern void __ptrace_link(struct task_struct *child, struct task_struct *new_parent); extern void __ptrace_unlink(struct task_struct *child); -extern int __ptrace_detach(struct task_struct *tracer, struct task_struct *p); +extern void exit_ptrace(struct task_struct *tracer); extern void ptrace_fork(struct task_struct *task, unsigned long clone_flags); #define PTRACE_MODE_READ 1 #define PTRACE_MODE_ATTACH 2 diff --git a/include/linux/sched.h b/include/linux/sched.h index 9186f8c5d5f2..b47c94e7560b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2061,6 +2061,11 @@ static inline int thread_group_empty(struct task_struct *p) #define delay_group_leader(p) \ (thread_group_leader(p) && !thread_group_empty(p)) +static inline int task_detached(struct task_struct *p) +{ + return p->exit_signal == -1; +} + /* * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring * subscriptions and synchronises with wait4(). Also used in procfs. Also diff --git a/kernel/exit.c b/kernel/exit.c index 3e09b7cb3b20..506693dfdd4e 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -61,11 +61,6 @@ DEFINE_TRACE(sched_process_wait); static void exit_mm(struct task_struct * tsk); -static inline int task_detached(struct task_struct *p) -{ - return p->exit_signal == -1; -} - static void __unhash_process(struct task_struct *p) { nr_threads--; @@ -731,85 +726,6 @@ static void exit_mm(struct task_struct * tsk) mmput(mm); } -/* - * Called with irqs disabled, returns true if childs should reap themselves. - */ -static int ignoring_children(struct sighand_struct *sigh) -{ - int ret; - spin_lock(&sigh->siglock); - ret = (sigh->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) || - (sigh->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT); - spin_unlock(&sigh->siglock); - return ret; -} - -/* Returns nonzero if the tracee should be released. */ -int __ptrace_detach(struct task_struct *tracer, struct task_struct *p) -{ - __ptrace_unlink(p); - - if (p->exit_state != EXIT_ZOMBIE) - return 0; - /* - * If it's a zombie, our attachedness prevented normal - * parent notification or self-reaping. Do notification - * now if it would have happened earlier. If it should - * reap itself we return true. - * - * If it's our own child, there is no notification to do. - * But if our normal children self-reap, then this child - * was prevented by ptrace and we must reap it now. - */ - if (!task_detached(p) && thread_group_empty(p)) { - if (!same_thread_group(p->real_parent, tracer)) - do_notify_parent(p, p->exit_signal); - else if (ignoring_children(tracer->sighand)) - p->exit_signal = -1; - } - - if (!task_detached(p)) - return 0; - - /* Mark it as in the process of being reaped. */ - p->exit_state = EXIT_DEAD; - return 1; -} - -/* - * Detach all tasks we were using ptrace on. - * Any that need to be release_task'd are put on the @dead list. - * - * Called with write_lock(&tasklist_lock) held. - */ -static void ptrace_exit(struct task_struct *parent, struct list_head *dead) -{ - struct task_struct *p, *n; - - list_for_each_entry_safe(p, n, &parent->ptraced, ptrace_entry) { - if (__ptrace_detach(parent, p)) - list_add(&p->ptrace_entry, dead); - } -} - -/* - * Finish up exit-time ptrace cleanup. - * - * Called without locks. - */ -static void ptrace_exit_finish(struct task_struct *parent, - struct list_head *dead) -{ - struct task_struct *p, *n; - - BUG_ON(!list_empty(&parent->ptraced)); - - list_for_each_entry_safe(p, n, dead, ptrace_entry) { - list_del_init(&p->ptrace_entry); - release_task(p); - } -} - /* Returns nonzero if the child should be released. */ static int reparent_thread(struct task_struct *p, struct task_struct *father) { @@ -894,12 +810,10 @@ static void forget_original_parent(struct task_struct *father) struct task_struct *p, *n, *reaper; LIST_HEAD(ptrace_dead); + exit_ptrace(father); + write_lock_irq(&tasklist_lock); reaper = find_new_reaper(father); - /* - * First clean up ptrace if we were using it. - */ - ptrace_exit(father, &ptrace_dead); list_for_each_entry_safe(p, n, &father->children, sibling) { p->real_parent = reaper; @@ -914,7 +828,10 @@ static void forget_original_parent(struct task_struct *father) write_unlock_irq(&tasklist_lock); BUG_ON(!list_empty(&father->children)); - ptrace_exit_finish(father, &ptrace_dead); + list_for_each_entry_safe(p, n, &ptrace_dead, ptrace_entry) { + list_del_init(&p->ptrace_entry); + release_task(p); + } } /* diff --git a/kernel/ptrace.c b/kernel/ptrace.c index ee553b6ad125..f5a9fa5aafa1 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -235,9 +235,57 @@ out: return retval; } +/* + * Called with irqs disabled, returns true if childs should reap themselves. + */ +static int ignoring_children(struct sighand_struct *sigh) +{ + int ret; + spin_lock(&sigh->siglock); + ret = (sigh->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) || + (sigh->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT); + spin_unlock(&sigh->siglock); + return ret; +} + +/* + * Called with tasklist_lock held for writing. + * Unlink a traced task, and clean it up if it was a traced zombie. + * Return true if it needs to be reaped with release_task(). + * (We can't call release_task() here because we already hold tasklist_lock.) + * + * If it's a zombie, our attachedness prevented normal parent notification + * or self-reaping. Do notification now if it would have happened earlier. + * If it should reap itself, return true. + * + * If it's our own child, there is no notification to do. + * But if our normal children self-reap, then this child + * was prevented by ptrace and we must reap it now. + */ +static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p) +{ + __ptrace_unlink(p); + + if (p->exit_state == EXIT_ZOMBIE) { + if (!task_detached(p) && thread_group_empty(p)) { + if (!same_thread_group(p->real_parent, tracer)) + do_notify_parent(p, p->exit_signal); + else if (ignoring_children(tracer->sighand)) + p->exit_signal = -1; + } + if (task_detached(p)) { + /* Mark it as in the process of being reaped. */ + p->exit_state = EXIT_DEAD; + return true; + } + } + + return false; +} + int ptrace_detach(struct task_struct *child, unsigned int data) { - int dead = 0; + bool dead = false; if (!valid_signal(data)) return -EIO; @@ -247,7 +295,10 @@ int ptrace_detach(struct task_struct *child, unsigned int data) clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); write_lock_irq(&tasklist_lock); - /* protect against de_thread()->release_task() */ + /* + * This child can be already killed. Make sure de_thread() or + * our sub-thread doing do_wait() didn't do release_task() yet. + */ if (child->ptrace) { child->exit_code = data; @@ -264,6 +315,29 @@ int ptrace_detach(struct task_struct *child, unsigned int data) return 0; } +/* + * Detach all tasks we were using ptrace on. + */ +void exit_ptrace(struct task_struct *tracer) +{ + struct task_struct *p, *n; + LIST_HEAD(ptrace_dead); + + write_lock_irq(&tasklist_lock); + list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) { + if (__ptrace_detach(tracer, p)) + list_add(&p->ptrace_entry, &ptrace_dead); + } + write_unlock_irq(&tasklist_lock); + + BUG_ON(!list_empty(&tracer->ptraced)); + + list_for_each_entry_safe(p, n, &ptrace_dead, ptrace_entry) { + list_del_init(&p->ptrace_entry); + release_task(p); + } +} + int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len) { int copied = 0; -- cgit v1.2.3 From bb24c679a51b1a9b726b901330649e3861814ac0 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 2 Apr 2009 16:58:20 -0700 Subject: tracehook_notify_death: use task_detached() helper Now that task_detached() is exported, change tracehook_notify_death() to use this helper, nobody else checks ->exit_signal == -1 by hand. Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Cc: "Metzger, Markus T" Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index eb4c6545b384..c7aa154f4bfc 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -502,7 +502,7 @@ static inline int tracehook_notify_jctl(int notify, int why) static inline int tracehook_notify_death(struct task_struct *task, void **death_cookie, int group_dead) { - if (task->exit_signal == -1) + if (task_detached(task)) return task->ptrace ? SIGCHLD : DEATH_REAP; /* -- cgit v1.2.3 From 40e8a10de2c9f87e892dcd5a6f9d1b208329ffea Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 2 Apr 2009 16:58:25 -0700 Subject: cpu hotplug: remove unused cpuhotplug_mutex_lock() cpuhotplug_mutex_lock() is not used, remove it. Signed-off-by: Lai Jiangshan Cc: Ingo Molnar Cc: Rusty Russell Acked-by: Gautham R Shenoy Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpu.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index c2747ac2ae43..2643d848df90 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -23,7 +23,6 @@ #include #include #include -#include struct cpu { int node_id; /* The node which contains the CPU */ @@ -103,16 +102,6 @@ extern struct sysdev_class cpu_sysdev_class; #ifdef CONFIG_HOTPLUG_CPU /* Stop CPUs going up and down. */ -static inline void cpuhotplug_mutex_lock(struct mutex *cpu_hp_mutex) -{ - mutex_lock(cpu_hp_mutex); -} - -static inline void cpuhotplug_mutex_unlock(struct mutex *cpu_hp_mutex) -{ - mutex_unlock(cpu_hp_mutex); -} - extern void get_online_cpus(void); extern void put_online_cpus(void); #define hotcpu_notifier(fn, pri) { \ @@ -126,11 +115,6 @@ int cpu_down(unsigned int cpu); #else /* CONFIG_HOTPLUG_CPU */ -static inline void cpuhotplug_mutex_lock(struct mutex *cpu_hp_mutex) -{ } -static inline void cpuhotplug_mutex_unlock(struct mutex *cpu_hp_mutex) -{ } - #define get_online_cpus() do { } while (0) #define put_online_cpus() do { } while (0) #define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0) -- cgit v1.2.3 From a50b0aa4bd9a7d42112442a385f3dc0e775284dd Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 2 Apr 2009 16:58:29 -0700 Subject: struct linux_binprm: drop unused fields Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/binfmts.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 77b4a9e46004..6638b8148de7 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -35,8 +35,7 @@ struct linux_binprm{ #endif struct mm_struct *mm; unsigned long p; /* current top of mem */ - unsigned int sh_bang:1, - misc_bang:1, + unsigned int cred_prepared:1,/* true if creds already prepared (multiple * preps happen for interpreters) */ cap_effective:1;/* true if has elevated effective capabilities, -- cgit v1.2.3 From 1f80769ffd36e74357fe896dc43dddf1af1510f3 Mon Sep 17 00:00:00 2001 From: Paul Fulghum Date: Thu, 2 Apr 2009 16:58:30 -0700 Subject: synclink_gt: add clock options Add support for x8 asynchronous sample rate and ability to specify base clock frequency. Signed-off-by: Paul Fulghum Acked-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/char/synclink_gt.c | 58 ++++++++++++++++++++++++++++++---------------- include/linux/synclink.h | 1 + 2 files changed, 39 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/synclink_gt.c b/drivers/char/synclink_gt.c index 6ec6e13d47d7..5e256494686a 100644 --- a/drivers/char/synclink_gt.c +++ b/drivers/char/synclink_gt.c @@ -298,6 +298,7 @@ struct slgt_info { unsigned int rbuf_fill_level; unsigned int if_mode; + unsigned int base_clock; /* device status */ @@ -1156,22 +1157,26 @@ static long set_params32(struct slgt_info *info, struct MGSL_PARAMS32 __user *ne return -EFAULT; spin_lock(&info->lock); - info->params.mode = tmp_params.mode; - info->params.loopback = tmp_params.loopback; - info->params.flags = tmp_params.flags; - info->params.encoding = tmp_params.encoding; - info->params.clock_speed = tmp_params.clock_speed; - info->params.addr_filter = tmp_params.addr_filter; - info->params.crc_type = tmp_params.crc_type; - info->params.preamble_length = tmp_params.preamble_length; - info->params.preamble = tmp_params.preamble; - info->params.data_rate = tmp_params.data_rate; - info->params.data_bits = tmp_params.data_bits; - info->params.stop_bits = tmp_params.stop_bits; - info->params.parity = tmp_params.parity; + if (tmp_params.mode == MGSL_MODE_BASE_CLOCK) { + info->base_clock = tmp_params.clock_speed; + } else { + info->params.mode = tmp_params.mode; + info->params.loopback = tmp_params.loopback; + info->params.flags = tmp_params.flags; + info->params.encoding = tmp_params.encoding; + info->params.clock_speed = tmp_params.clock_speed; + info->params.addr_filter = tmp_params.addr_filter; + info->params.crc_type = tmp_params.crc_type; + info->params.preamble_length = tmp_params.preamble_length; + info->params.preamble = tmp_params.preamble; + info->params.data_rate = tmp_params.data_rate; + info->params.data_bits = tmp_params.data_bits; + info->params.stop_bits = tmp_params.stop_bits; + info->params.parity = tmp_params.parity; + } spin_unlock(&info->lock); - change_params(info); + program_hw(info); return 0; } @@ -2559,10 +2564,13 @@ static int set_params(struct slgt_info *info, MGSL_PARAMS __user *new_params) return -EFAULT; spin_lock_irqsave(&info->lock, flags); - memcpy(&info->params, &tmp_params, sizeof(MGSL_PARAMS)); + if (tmp_params.mode == MGSL_MODE_BASE_CLOCK) + info->base_clock = tmp_params.clock_speed; + else + memcpy(&info->params, &tmp_params, sizeof(MGSL_PARAMS)); spin_unlock_irqrestore(&info->lock, flags); - change_params(info); + program_hw(info); return 0; } @@ -3432,6 +3440,7 @@ static struct slgt_info *alloc_dev(int adapter_num, int port_num, struct pci_dev info->magic = MGSL_MAGIC; INIT_WORK(&info->task, bh_handler); info->max_frame_size = 4096; + info->base_clock = 14745600; info->rbuf_fill_level = DMABUFSIZE; info->port.close_delay = 5*HZ/10; info->port.closing_wait = 30*HZ; @@ -3779,7 +3788,7 @@ static void enable_loopback(struct slgt_info *info) static void set_rate(struct slgt_info *info, u32 rate) { unsigned int div; - static unsigned int osc = 14745600; + unsigned int osc = info->base_clock; /* div = osc/rate - 1 * @@ -4083,18 +4092,27 @@ static void async_mode(struct slgt_info *info) * 06 CTS IRQ enable * 05 DCD IRQ enable * 04 RI IRQ enable - * 03 reserved, must be zero + * 03 0=16x sampling, 1=8x sampling * 02 1=txd->rxd internal loopback enable * 01 reserved, must be zero * 00 1=master IRQ enable */ val = BIT15 + BIT14 + BIT0; + /* JCR[8] : 1 = x8 async mode feature available */ + if ((rd_reg32(info, JCR) & BIT8) && info->params.data_rate && + ((info->base_clock < (info->params.data_rate * 16)) || + (info->base_clock % (info->params.data_rate * 16)))) { + /* use 8x sampling */ + val |= BIT3; + set_rate(info, info->params.data_rate * 8); + } else { + /* use 16x sampling */ + set_rate(info, info->params.data_rate * 16); + } wr_reg16(info, SCR, val); slgt_irq_on(info, IRQ_RXBREAK | IRQ_RXOVER); - set_rate(info, info->params.data_rate * 16); - if (info->params.loopback) enable_loopback(info); } diff --git a/include/linux/synclink.h b/include/linux/synclink.h index 99b8bdb17b2b..0ff2779c44d0 100644 --- a/include/linux/synclink.h +++ b/include/linux/synclink.h @@ -125,6 +125,7 @@ #define MGSL_MODE_MONOSYNC 3 #define MGSL_MODE_BISYNC 4 #define MGSL_MODE_RAW 6 +#define MGSL_MODE_BASE_CLOCK 7 #define MGSL_BUS_TYPE_ISA 1 #define MGSL_BUS_TYPE_EISA 2 -- cgit v1.2.3 From 6dda81f4384b94930826eded254d8c16f89a9248 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 2 Apr 2009 16:58:35 -0700 Subject: pids: document task_pgrp/task_session is not safe without tasklist/rcu Even if task == current, it is not safe to dereference the result of task_pgrp/task_session. We can race with another thread which changes the special pid via setpgid/setsid. Document this. The next 2 patches give an example of the unsafe usage, we have more bad users. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Oleg Nesterov Cc: Louis Rilling Cc: "Eric W. Biederman" Cc: Pavel Emelyanov Cc: Sukadev Bhattiprolu Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b47c94e7560b..722dd313bf8a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1489,6 +1489,11 @@ static inline struct pid *task_tgid(struct task_struct *task) return task->group_leader->pids[PIDTYPE_PID].pid; } +/* + * Without tasklist or rcu lock it is not safe to dereference + * the result of task_pgrp/task_session even if task == current, + * we can race with another thread doing sys_setsid/sys_setpgid. + */ static inline struct pid *task_pgrp(struct task_struct *task) { return task->group_leader->pids[PIDTYPE_PGID].pid; -- cgit v1.2.3 From 52ee2dfdd4f51cf422ea6a96a0846dc94244aa37 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 2 Apr 2009 16:58:38 -0700 Subject: pids: refactor vnr/nr_ns helpers to make them safe Inho, the safety rules for vnr/nr_ns helpers are horrible and buggy. task_pid_nr_ns(task) needs rcu/tasklist depending on task == current. As for "special" pids, vnr/nr_ns helpers always need rcu. However, if task != current, they are unsafe even under rcu lock, we can't trust task->group_leader without the special checks. And almost every helper has a callsite which needs a fix. Also, it is a bit annoying that the implementations of, say, task_pgrp_vnr() and task_pgrp_nr_ns() are not "symmetrical". This patch introduces the new helper, __task_pid_nr_ns(), which is always safe to use, and turns all other helpers into the trivial wrappers. After this I'll send another patch which converts task_tgid_xxx() as well, they're are a bit special. Signed-off-by: Oleg Nesterov Cc: Louis Rilling Cc: "Eric W. Biederman" Cc: Pavel Emelyanov Cc: Sukadev Bhattiprolu Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 27 ++++++++++++++++++++------- kernel/pid.c | 31 ++++++++++++++++--------------- 2 files changed, 36 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 722dd313bf8a..49df878a0cad 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1519,17 +1519,23 @@ struct pid_namespace; * * see also pid_nr() etc in include/linux/pid.h */ +pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, + struct pid_namespace *ns); static inline pid_t task_pid_nr(struct task_struct *tsk) { return tsk->pid; } -pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); +static inline pid_t task_pid_nr_ns(struct task_struct *tsk, + struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns); +} static inline pid_t task_pid_vnr(struct task_struct *tsk) { - return pid_vnr(task_pid(tsk)); + return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL); } @@ -1551,11 +1557,15 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) return tsk->signal->__pgrp; } -pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); +static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, + struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns); +} static inline pid_t task_pgrp_vnr(struct task_struct *tsk) { - return pid_vnr(task_pgrp(tsk)); + return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL); } @@ -1564,14 +1574,17 @@ static inline pid_t task_session_nr(struct task_struct *tsk) return tsk->signal->__session; } -pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); +static inline pid_t task_session_nr_ns(struct task_struct *tsk, + struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns); +} static inline pid_t task_session_vnr(struct task_struct *tsk) { - return pid_vnr(task_session(tsk)); + return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); } - /** * pid_alive - check that a task structure is not stale * @p: Task structure to be checked. diff --git a/kernel/pid.c b/kernel/pid.c index 6628abcc520e..b2e5f78fd281 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -452,11 +452,24 @@ pid_t pid_vnr(struct pid *pid) } EXPORT_SYMBOL_GPL(pid_vnr); -pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, + struct pid_namespace *ns) { - return pid_nr_ns(task_pid(tsk), ns); + pid_t nr = 0; + + rcu_read_lock(); + if (!ns) + ns = current->nsproxy->pid_ns; + if (likely(pid_alive(task))) { + if (type != PIDTYPE_PID) + task = task->group_leader; + nr = pid_nr_ns(task->pids[type].pid, ns); + } + rcu_read_unlock(); + + return nr; } -EXPORT_SYMBOL(task_pid_nr_ns); +EXPORT_SYMBOL(__task_pid_nr_ns); pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { @@ -464,18 +477,6 @@ pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) } EXPORT_SYMBOL(task_tgid_nr_ns); -pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) -{ - return pid_nr_ns(task_pgrp(tsk), ns); -} -EXPORT_SYMBOL(task_pgrp_nr_ns); - -pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) -{ - return pid_nr_ns(task_session(tsk), ns); -} -EXPORT_SYMBOL(task_session_nr_ns); - struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) { return ns_of_pid(task_pid(tsk)); -- cgit v1.2.3 From 1b0f7ffd0ea27cd3a0b9ca04e3df9522048c32a3 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 2 Apr 2009 16:58:39 -0700 Subject: pids: kill signal_struct-> __pgrp/__session and friends We are wasting 2 words in signal_struct without any reason to implement task_pgrp_nr() and task_session_nr(). task_session_nr() has no callers since 2e2ba22ea4fd4bb85f0fa37c521066db6775cbef, we can remove it. task_pgrp_nr() is still (I believe wrongly) used in fs/autofsX and fs/coda. This patch reimplements task_pgrp_nr() via task_pgrp_nr_ns(), and kills __pgrp/__session and the related helpers. The change in drivers/char/tty_io.c is cosmetic, but hopefully makes sense anyway. Signed-off-by: Oleg Nesterov Acked-by: Alan Cox [tty parts] Cc: Cedric Le Goater Cc: Dave Hansen Cc: Eric Biederman Cc: Pavel Emelyanov Cc: Serge Hallyn Cc: Sukadev Bhattiprolu Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/char/tty_io.c | 4 ++-- include/linux/sched.h | 43 ++++++------------------------------------- kernel/exit.c | 10 +++------- kernel/fork.c | 2 -- kernel/sys.c | 4 +--- 5 files changed, 12 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/tty_io.c b/drivers/char/tty_io.c index a44b701c5bba..66b99a2049e3 100644 --- a/drivers/char/tty_io.c +++ b/drivers/char/tty_io.c @@ -2681,7 +2681,7 @@ void __do_SAK(struct tty_struct *tty) /* Kill the entire session */ do_each_pid_task(session, PIDTYPE_SID, p) { printk(KERN_NOTICE "SAK: killed process %d" - " (%s): task_session_nr(p)==tty->session\n", + " (%s): task_session(p)==tty->session\n", task_pid_nr(p), p->comm); send_sig(SIGKILL, p, 1); } while_each_pid_task(session, PIDTYPE_SID, p); @@ -2691,7 +2691,7 @@ void __do_SAK(struct tty_struct *tty) do_each_thread(g, p) { if (p->signal->tty == tty) { printk(KERN_NOTICE "SAK: killed process %d" - " (%s): task_session_nr(p)==tty->session\n", + " (%s): task_session(p)==tty->session\n", task_pid_nr(p), p->comm); send_sig(SIGKILL, p, 1); continue; diff --git a/include/linux/sched.h b/include/linux/sched.h index 49df878a0cad..206ac003e8c0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -547,25 +547,8 @@ struct signal_struct { struct list_head cpu_timers[3]; - /* job control IDs */ - - /* - * pgrp and session fields are deprecated. - * use the task_session_Xnr and task_pgrp_Xnr routines below - */ - - union { - pid_t pgrp __deprecated; - pid_t __pgrp; - }; - struct pid *tty_old_pgrp; - union { - pid_t session __deprecated; - pid_t __session; - }; - /* boolean value for session group leader */ int leader; @@ -1469,16 +1452,6 @@ static inline int rt_task(struct task_struct *p) return rt_prio(p->prio); } -static inline void set_task_session(struct task_struct *tsk, pid_t session) -{ - tsk->signal->__session = session; -} - -static inline void set_task_pgrp(struct task_struct *tsk, pid_t pgrp) -{ - tsk->signal->__pgrp = pgrp; -} - static inline struct pid *task_pid(struct task_struct *task) { return task->pids[PIDTYPE_PID].pid; @@ -1552,11 +1525,6 @@ static inline pid_t task_tgid_vnr(struct task_struct *tsk) } -static inline pid_t task_pgrp_nr(struct task_struct *tsk) -{ - return tsk->signal->__pgrp; -} - static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { @@ -1569,11 +1537,6 @@ static inline pid_t task_pgrp_vnr(struct task_struct *tsk) } -static inline pid_t task_session_nr(struct task_struct *tsk) -{ - return tsk->signal->__session; -} - static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { @@ -1585,6 +1548,12 @@ static inline pid_t task_session_vnr(struct task_struct *tsk) return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); } +/* obsolete, do not use */ +static inline pid_t task_pgrp_nr(struct task_struct *tsk) +{ + return task_pgrp_nr_ns(tsk, &init_pid_ns); +} + /** * pid_alive - check that a task structure is not stale * @p: Task structure to be checked. diff --git a/kernel/exit.c b/kernel/exit.c index 384f09caf2ef..3bec141c82f6 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -357,16 +357,12 @@ static void reparent_to_kthreadd(void) void __set_special_pids(struct pid *pid) { struct task_struct *curr = current->group_leader; - pid_t nr = pid_nr(pid); - if (task_session(curr) != pid) { + if (task_session(curr) != pid) change_pid(curr, PIDTYPE_SID, pid); - set_task_session(curr, nr); - } - if (task_pgrp(curr) != pid) { + + if (task_pgrp(curr) != pid) change_pid(curr, PIDTYPE_PGID, pid); - set_task_pgrp(curr, nr); - } } static void set_special_pids(struct pid *pid) diff --git a/kernel/fork.c b/kernel/fork.c index adbea16ec649..f74458231449 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1265,8 +1265,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->signal->leader_pid = pid; tty_kref_put(p->signal->tty); p->signal->tty = tty_kref_get(current->signal->tty); - set_task_pgrp(p, task_pgrp_nr(current)); - set_task_session(p, task_session_nr(current)); attach_pid(p, PIDTYPE_PGID, task_pgrp(current)); attach_pid(p, PIDTYPE_SID, task_session(current)); list_add_tail_rcu(&p->tasks, &init_task.tasks); diff --git a/kernel/sys.c b/kernel/sys.c index 37f458e6882a..742cefa527e6 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1013,10 +1013,8 @@ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid) if (err) goto out; - if (task_pgrp(p) != pgrp) { + if (task_pgrp(p) != pgrp) change_pid(p, PIDTYPE_PGID, pgrp); - set_task_pgrp(p, pid_nr(pgrp)); - } err = 0; out: -- cgit v1.2.3 From 7c5ff4f92e2b47c56d777a5adbadd9a52841b635 Mon Sep 17 00:00:00 2001 From: Harry Ciao Date: Thu, 2 Apr 2009 16:58:48 -0700 Subject: pci: Add AMD8111 PCI Bridge PCI Device ID Add the PCI Device ID of the PCI Bridge Controller on AMD8111 chip. Signed-off-by: Harry Ciao Cc: Doug Thompson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index cb14fd260837..170f8b1f22db 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -526,6 +526,7 @@ #define PCI_DEVICE_ID_AMD_OPUS_7443 0x7443 #define PCI_DEVICE_ID_AMD_VIPER_7443 0x7443 #define PCI_DEVICE_ID_AMD_OPUS_7445 0x7445 +#define PCI_DEVICE_ID_AMD_8111_PCI 0x7460 #define PCI_DEVICE_ID_AMD_8111_LPC 0x7468 #define PCI_DEVICE_ID_AMD_8111_IDE 0x7469 #define PCI_DEVICE_ID_AMD_8111_SMBUS2 0x746a -- cgit v1.2.3 From 04d491ab2a53008a1aa98ac09561768c7f3adda3 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Thu, 2 Apr 2009 16:58:57 -0700 Subject: kexec: add dmesg log symbols to /proc/vmcoreinfo lists It would be nice to be able to extract the dmesg log from a vmcore file without needing to keep the debug symbols for the running kernel handy all the time. We have a facility to do this in /proc/vmcore. This patch adds the log_buf and log_end symbols to the vmcoreinfo area so that tools (like makedumpfile) can easily extract the dmesg logs from a vmcore image. [akpm@linux-foundation.org: several fixes and cleanups] [akpm@linux-foundation.org: fix unused log_buf_kexec_setup()] [akpm@linux-foundation.org: build fix] Signed-off-by: Neil Horman Cc: Simon Horman Acked-by: Vivek Goyal Cc: Neil Horman Cc: Simon Horman Cc: Vivek Goyal Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 4 ++++ kernel/kexec.c | 1 + kernel/printk.c | 19 +++++++++++++++++++ 3 files changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e720b0da7751..556d781e69fe 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -242,6 +242,7 @@ extern struct ratelimit_state printk_ratelimit_state; extern int printk_ratelimit(void); extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec); +void log_buf_kexec_setup(void); #else static inline int vprintk(const char *s, va_list args) __attribute__ ((format (printf, 1, 0))); @@ -253,6 +254,9 @@ static inline int printk_ratelimit(void) { return 0; } static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, \ unsigned int interval_msec) \ { return false; } +static inline void log_buf_kexec_setup(void) +{ +} #endif extern int printk_needs_cpu(int cpu); diff --git a/kernel/kexec.c b/kernel/kexec.c index 93eed85fe017..589832aac41f 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1409,6 +1409,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_OFFSET(list_head, prev); VMCOREINFO_OFFSET(vm_struct, addr); VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER); + log_buf_kexec_setup(); VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES); VMCOREINFO_NUMBER(NR_FREE_PAGES); VMCOREINFO_NUMBER(PG_lru); diff --git a/kernel/printk.c b/kernel/printk.c index e3602d0755b0..a5f61a9acedb 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -32,6 +32,7 @@ #include #include #include +#include #include @@ -135,6 +136,24 @@ static char *log_buf = __log_buf; static int log_buf_len = __LOG_BUF_LEN; static unsigned logged_chars; /* Number of chars produced since last read+clear operation */ +#ifdef CONFIG_KEXEC +/* + * This appends the listed symbols to /proc/vmcoreinfo + * + * /proc/vmcoreinfo is used by various utiilties, like crash and makedumpfile to + * obtain access to symbols that are otherwise very difficult to locate. These + * symbols are specifically used so that utilities can access and extract the + * dmesg log from a vmcore file after a crash. + */ +void log_buf_kexec_setup(void) +{ + VMCOREINFO_SYMBOL(log_buf); + VMCOREINFO_SYMBOL(log_end); + VMCOREINFO_SYMBOL(log_buf_len); + VMCOREINFO_SYMBOL(logged_chars); +} +#endif + static int __init log_buf_len_setup(char *str) { unsigned size = memparse(str, &str); -- cgit v1.2.3 From f3554f4bc69803ac2baaf7cf2aa4339e1f4b693e Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Thu, 2 Apr 2009 16:59:23 -0700 Subject: preadv/pwritev: Add preadv and pwritev system calls. This patch adds preadv and pwritev system calls. These syscalls are a pretty straightforward combination of pread and readv (same for write). They are quite useful for doing vectored I/O in threaded applications. Using lseek+readv instead opens race windows you'll have to plug with locking. Other systems have such system calls too, for example NetBSD, check here: http://www.daemon-systems.org/man/preadv.2.html The application-visible interface provided by glibc should look like this to be compatible to the existing implementations in the *BSD family: ssize_t preadv(int d, const struct iovec *iov, int iovcnt, off_t offset); ssize_t pwritev(int d, const struct iovec *iov, int iovcnt, off_t offset); This prototype has one problem though: On 32bit archs is the (64bit) offset argument unaligned, which the syscall ABI of several archs doesn't allow to do. At least s390 needs a wrapper in glibc to handle this. As we'll need a wrappers in glibc anyway I've decided to push problem to glibc entriely and use a syscall prototype which works without arch-specific wrappers inside the kernel: The offset argument is explicitly splitted into two 32bit values. The patch sports the actual system call implementation and the windup in the x86 system call tables. Other archs follow as separate patches. Signed-off-by: Gerd Hoffmann Cc: Arnd Bergmann Cc: Al Viro Cc: Cc: Cc: Ralf Baechle Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/ia32/ia32entry.S | 2 ++ arch/x86/include/asm/unistd_32.h | 2 ++ arch/x86/include/asm/unistd_64.h | 4 +++ arch/x86/kernel/syscall_table_32.S | 2 ++ fs/compat.c | 36 +++++++++++++++++++++++++++ fs/read_write.c | 50 ++++++++++++++++++++++++++++++++++++++ include/linux/compat.h | 6 +++++ include/linux/syscalls.h | 4 +++ 8 files changed, 106 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index db0c803170ab..a505202086e8 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -828,4 +828,6 @@ ia32_sys_call_table: .quad sys_dup3 /* 330 */ .quad sys_pipe2 .quad sys_inotify_init1 + .quad compat_sys_preadv + .quad compat_sys_pwritev ia32_syscall_end: diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index f2bba78430a4..6e72d74cf8dc 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -338,6 +338,8 @@ #define __NR_dup3 330 #define __NR_pipe2 331 #define __NR_inotify_init1 332 +#define __NR_preadv 333 +#define __NR_pwritev 334 #ifdef __KERNEL__ diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index d2e415e6666f..f81829462325 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -653,6 +653,10 @@ __SYSCALL(__NR_dup3, sys_dup3) __SYSCALL(__NR_pipe2, sys_pipe2) #define __NR_inotify_init1 294 __SYSCALL(__NR_inotify_init1, sys_inotify_init1) +#define __NR_preadv 295 +__SYSCALL(__NR_preadv, sys_preadv) +#define __NR_pwritev 296 +__SYSCALL(__NR_pwritev, sys_pwritev) #ifndef __NO_STUBS diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index 3bdb64829b82..ff5c8736b491 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -332,3 +332,5 @@ ENTRY(sys_call_table) .long sys_dup3 /* 330 */ .long sys_pipe2 .long sys_inotify_init1 + .long sys_preadv + .long sys_pwritev diff --git a/fs/compat.c b/fs/compat.c index e04b4660db84..7c1615183d1e 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1232,6 +1232,24 @@ compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, 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; + ssize_t ret; + + if (pos < 0) + return -EINVAL; + file = fget(fd); + if (!file) + return -EBADF; + ret = compat_readv(file, vec, vlen, &pos); + fput(file); + return ret; +} + static size_t compat_writev(struct file *file, const struct compat_iovec __user *vec, unsigned long vlen, loff_t *pos) @@ -1269,6 +1287,24 @@ compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, 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; + ssize_t ret; + + if (pos < 0) + return -EINVAL; + file = fget(fd); + if (!file) + return -EBADF; + ret = compat_writev(file, vec, vlen, &pos); + fput(file); + return ret; +} + asmlinkage long compat_sys_vmsplice(int fd, const struct compat_iovec __user *iov32, unsigned int nr_segs, unsigned int flags) 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/include/linux/compat.h b/include/linux/compat.h index b880864672de..9723edd6455c 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -191,6 +191,12 @@ asmlinkage ssize_t compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen); asmlinkage ssize_t compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen); +asmlinkage ssize_t compat_sys_preadv(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low); +asmlinkage ssize_t compat_sys_pwritev(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low); int compat_do_execve(char * filename, compat_uptr_t __user *argv, compat_uptr_t __user *envp, struct pt_regs * regs); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index f9f900cfd066..b299a82a05e7 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -461,6 +461,10 @@ asmlinkage long sys_pread64(unsigned int fd, char __user *buf, size_t count, loff_t pos); asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos); +asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low); +asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low); asmlinkage long sys_getcwd(char __user *buf, unsigned long size); asmlinkage long sys_mkdir(const char __user *pathname, int mode); asmlinkage long sys_chdir(const char __user *filename); -- cgit v1.2.3 From e8c158bb313c1df421eab7dc4299cd39cbbf5895 Mon Sep 17 00:00:00 2001 From: Robin Holt Date: Thu, 2 Apr 2009 16:59:45 -0700 Subject: Factor out #ifdefs from kernel/spinlock.c to LOCK_CONTENDED_FLAGS SGI has observed that on large systems, interrupts are not serviced for a long period of time when waiting for a rwlock. The following patch series re-enables irqs while waiting for the lock, resembling the code which is already there for spinlocks. I only made the ia64 version, because the patch adds some overhead to the fast path. I assume there is currently no demand to have this for other architectures, because the systems are not so large. Of course, the possibility to implement raw_{read|write}_lock_flags for any architecture is still there. This patch: The new macro LOCK_CONTENDED_FLAGS expands to the correct implementation depending on the config options, so that IRQ's are re-enabled when possible, but they remain disabled if CONFIG_LOCKDEP is set. Signed-off-by: Petr Tesarik Signed-off-by: Robin Holt Cc: Cc: Ingo Molnar Cc: Peter Zijlstra Cc: "Luck, Tony" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockdep.h | 17 +++++++++++++++++ kernel/spinlock.c | 12 ++---------- 2 files changed, 19 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 5a58ea3e91e9..da5a5a1f4cd2 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -364,6 +364,23 @@ do { \ #endif /* CONFIG_LOCK_STAT */ +#ifdef CONFIG_LOCKDEP + +/* + * On lockdep we dont want the hand-coded irq-enable of + * _raw_*_lock_flags() code, because lockdep assumes + * that interrupts are not re-enabled during lock-acquire: + */ +#define LOCK_CONTENDED_FLAGS(_lock, try, lock, lockfl, flags) \ + LOCK_CONTENDED((_lock), (try), (lock)) + +#else /* CONFIG_LOCKDEP */ + +#define LOCK_CONTENDED_FLAGS(_lock, try, lock, lockfl, flags) \ + lockfl((_lock), (flags)) + +#endif /* CONFIG_LOCKDEP */ + #ifdef CONFIG_GENERIC_HARDIRQS extern void early_init_irq_lock_class(void); #else diff --git a/kernel/spinlock.c b/kernel/spinlock.c index 29ab20749dd3..7283c6dc2d59 100644 --- a/kernel/spinlock.c +++ b/kernel/spinlock.c @@ -299,16 +299,8 @@ unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclas local_irq_save(flags); preempt_disable(); spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); - /* - * On lockdep we dont want the hand-coded irq-enable of - * _raw_spin_lock_flags() code, because lockdep assumes - * that interrupts are not re-enabled during lock-acquire: - */ -#ifdef CONFIG_LOCKDEP - LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock); -#else - _raw_spin_lock_flags(lock, &flags); -#endif + LOCK_CONTENDED_FLAGS(lock, _raw_spin_trylock, _raw_spin_lock, + _raw_spin_lock_flags, &flags); return flags; } EXPORT_SYMBOL(_spin_lock_irqsave_nested); -- cgit v1.2.3 From f5f7eac41db827a47b2163330eecd7bb55ae9f12 Mon Sep 17 00:00:00 2001 From: Robin Holt Date: Thu, 2 Apr 2009 16:59:46 -0700 Subject: Allow rwlocks to re-enable interrupts Pass the original flags to rwlock arch-code, so that it can re-enable interrupts if implemented for that architecture. Initially, make __raw_read_lock_flags and __raw_write_lock_flags stubs which just do the same thing as non-flags variants. Signed-off-by: Petr Tesarik Signed-off-by: Robin Holt Acked-by: Peter Zijlstra Cc: Acked-by: Ingo Molnar Cc: "Luck, Tony" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/include/asm/spinlock.h | 3 +++ arch/arm/include/asm/spinlock.h | 3 +++ arch/cris/include/arch-v32/arch/spinlock.h | 2 ++ arch/ia64/include/asm/spinlock.h | 3 +++ arch/mips/include/asm/spinlock.h | 2 ++ arch/parisc/include/asm/spinlock.h | 3 +++ arch/powerpc/include/asm/spinlock.h | 3 +++ arch/s390/include/asm/spinlock.h | 3 +++ arch/sh/include/asm/spinlock.h | 3 +++ arch/sparc/include/asm/spinlock_32.h | 2 ++ arch/sparc/include/asm/spinlock_64.h | 2 ++ arch/x86/include/asm/spinlock.h | 3 +++ include/asm-m32r/spinlock.h | 3 +++ include/linux/spinlock.h | 6 ++++++ kernel/spinlock.c | 6 ++++-- 15 files changed, 45 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/include/asm/spinlock.h b/arch/alpha/include/asm/spinlock.h index aeeb125f6851..e38fb95cb335 100644 --- a/arch/alpha/include/asm/spinlock.h +++ b/arch/alpha/include/asm/spinlock.h @@ -166,6 +166,9 @@ static inline void __raw_write_unlock(raw_rwlock_t * lock) lock->lock = 0; } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h index 2b41ebbfa7ff..c13681ac1ede 100644 --- a/arch/arm/include/asm/spinlock.h +++ b/arch/arm/include/asm/spinlock.h @@ -217,6 +217,9 @@ static inline int __raw_read_trylock(raw_rwlock_t *rw) /* read_can_lock - would read_trylock() succeed? */ #define __raw_read_can_lock(x) ((x)->lock < 0x80000000) +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/arch/cris/include/arch-v32/arch/spinlock.h b/arch/cris/include/arch-v32/arch/spinlock.h index 0d5709b983a1..129756b96661 100644 --- a/arch/cris/include/arch-v32/arch/spinlock.h +++ b/arch/cris/include/arch-v32/arch/spinlock.h @@ -121,6 +121,8 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw) return 1; } +#define _raw_read_lock_flags(lock, flags) _raw_read_lock(lock) +#define _raw_write_lock_flags(lock, flags) _raw_write_lock(lock) #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h index 0229fb95fb38..0a619618b2fa 100644 --- a/arch/ia64/include/asm/spinlock.h +++ b/arch/ia64/include/asm/spinlock.h @@ -213,6 +213,9 @@ static inline int __raw_read_trylock(raw_rwlock_t *x) return (u32)ia64_cmpxchg4_acq((__u32 *)(x), new.word, old.word) == old.word; } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h index 10e82441b496..5b60a09a0f08 100644 --- a/arch/mips/include/asm/spinlock.h +++ b/arch/mips/include/asm/spinlock.h @@ -480,6 +480,8 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw) return ret; } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h index f3d2090a18dc..fae03e136fa8 100644 --- a/arch/parisc/include/asm/spinlock.h +++ b/arch/parisc/include/asm/spinlock.h @@ -187,6 +187,9 @@ static __inline__ int __raw_write_can_lock(raw_rwlock_t *rw) return !rw->counter; } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index 36864364e601..c3b193121f81 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -287,6 +287,9 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw) rw->lock = 0; } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_spin_relax(lock) __spin_yield(lock) #define _raw_read_relax(lock) __rw_yield(lock) #define _raw_write_relax(lock) __rw_yield(lock) diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index df84ae96915f..f3861b09ebb0 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -172,6 +172,9 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw) return _raw_write_trylock_retry(rw); } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/arch/sh/include/asm/spinlock.h b/arch/sh/include/asm/spinlock.h index e793181d64da..60283565f89b 100644 --- a/arch/sh/include/asm/spinlock.h +++ b/arch/sh/include/asm/spinlock.h @@ -216,6 +216,9 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw) return (oldval > (RW_LOCK_BIAS - 1)); } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h index bf2d532593e3..46f91ab66a50 100644 --- a/arch/sparc/include/asm/spinlock_32.h +++ b/arch/sparc/include/asm/spinlock_32.h @@ -177,6 +177,8 @@ static inline int __read_trylock(raw_rwlock_t *rw) #define __raw_write_unlock(rw) do { (rw)->lock = 0; } while(0) #define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock) +#define __raw_read_lock_flags(rw, flags) __raw_read_lock(rw) +#define __raw_write_lock_flags(rw, flags) __raw_write_lock(rw) #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h index c4d274d330e9..f6b2b92ad8d2 100644 --- a/arch/sparc/include/asm/spinlock_64.h +++ b/arch/sparc/include/asm/spinlock_64.h @@ -211,9 +211,11 @@ static int inline __write_trylock(raw_rwlock_t *lock) } #define __raw_read_lock(p) __read_lock(p) +#define __raw_read_lock_flags(p, f) __read_lock(p) #define __raw_read_trylock(p) __read_trylock(p) #define __raw_read_unlock(p) __read_unlock(p) #define __raw_write_lock(p) __write_lock(p) +#define __raw_write_lock_flags(p, f) __write_lock(p) #define __raw_write_unlock(p) __write_unlock(p) #define __raw_write_trylock(p) __write_trylock(p) diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 3a5696656680..e5e6caffec87 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -295,6 +295,9 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw) : "+m" (rw->lock) : "i" (RW_LOCK_BIAS) : "memory"); } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/include/asm-m32r/spinlock.h b/include/asm-m32r/spinlock.h index f5cfba81ee10..dded923883b2 100644 --- a/include/asm-m32r/spinlock.h +++ b/include/asm-m32r/spinlock.h @@ -316,6 +316,9 @@ static inline int __raw_write_trylock(raw_rwlock_t *lock) return 0; } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index a0c66a2e00ad..252b245cfcf4 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -153,9 +153,11 @@ do { \ extern int _raw_spin_trylock(spinlock_t *lock); extern void _raw_spin_unlock(spinlock_t *lock); extern void _raw_read_lock(rwlock_t *lock); +#define _raw_read_lock_flags(lock, flags) _raw_read_lock(lock) extern int _raw_read_trylock(rwlock_t *lock); extern void _raw_read_unlock(rwlock_t *lock); extern void _raw_write_lock(rwlock_t *lock); +#define _raw_write_lock_flags(lock, flags) _raw_write_lock(lock) extern int _raw_write_trylock(rwlock_t *lock); extern void _raw_write_unlock(rwlock_t *lock); #else @@ -165,9 +167,13 @@ do { \ # define _raw_spin_trylock(lock) __raw_spin_trylock(&(lock)->raw_lock) # define _raw_spin_unlock(lock) __raw_spin_unlock(&(lock)->raw_lock) # define _raw_read_lock(rwlock) __raw_read_lock(&(rwlock)->raw_lock) +# define _raw_read_lock_flags(lock, flags) \ + __raw_read_lock_flags(&(lock)->raw_lock, *(flags)) # define _raw_read_trylock(rwlock) __raw_read_trylock(&(rwlock)->raw_lock) # define _raw_read_unlock(rwlock) __raw_read_unlock(&(rwlock)->raw_lock) # define _raw_write_lock(rwlock) __raw_write_lock(&(rwlock)->raw_lock) +# define _raw_write_lock_flags(lock, flags) \ + __raw_write_lock_flags(&(lock)->raw_lock, *(flags)) # define _raw_write_trylock(rwlock) __raw_write_trylock(&(rwlock)->raw_lock) # define _raw_write_unlock(rwlock) __raw_write_unlock(&(rwlock)->raw_lock) #endif diff --git a/kernel/spinlock.c b/kernel/spinlock.c index 7283c6dc2d59..7932653c4ebd 100644 --- a/kernel/spinlock.c +++ b/kernel/spinlock.c @@ -121,7 +121,8 @@ unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock) local_irq_save(flags); preempt_disable(); rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_); - LOCK_CONTENDED(lock, _raw_read_trylock, _raw_read_lock); + LOCK_CONTENDED_FLAGS(lock, _raw_read_trylock, _raw_read_lock, + _raw_read_lock_flags, &flags); return flags; } EXPORT_SYMBOL(_read_lock_irqsave); @@ -151,7 +152,8 @@ unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock) local_irq_save(flags); preempt_disable(); rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_); - LOCK_CONTENDED(lock, _raw_write_trylock, _raw_write_lock); + LOCK_CONTENDED_FLAGS(lock, _raw_write_trylock, _raw_write_lock, + _raw_write_lock_flags, &flags); return flags; } EXPORT_SYMBOL(_write_lock_irqsave); -- cgit v1.2.3