In some cases, we were passing in NULL even when we have a dentry. Reported-by: Eric Paris <eparis(a)redhat.com&gt; Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- kernel/auditsc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 4b96415..5c45b9b 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -2226,7 +2226,7 @@ void __audit_inode_child(const struct dentry *dentry, if (!strcmp(dname, n->name) || !audit_compare_dname_path(dname, n->name, &dirlen)) { if (inode) - audit_copy_inode(n, NULL, inode); + audit_copy_inode(n, dentry, inode); else n->ino = (unsigned long)-1; found_child = n->name; @@ -2258,7 +2258,7 @@ add_names: } if (inode) - audit_copy_inode(n, NULL, inode); + audit_copy_inode(n, dentry, inode); } } EXPORT_SYMBOL_GPL(__audit_inode_child); -- 1.7.11.4

On Tue, 2 Oct 2012 11:53:38 -0400 Christoph Hellwig <hch(a)infradead.org&gt; wrote: [...] Thanks Christoph, Both of the above are good suggestions, but I'd prefer not to have to respin this whole set to implement them. I believe what I have here is an improvement on what's there now. Do you have any objection to doing the above in a separate set on top of this series? -- Jeff Layton <jlayton(a)redhat.com&gt;

For now, we just have two possibilities: UNKNOWN: for a new audit_names record that we don't know anything about yet NORMAL: for everything else In later patches, we'll add other types so we can distinguish and update records created under different circumstances. Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- include/linux/audit.h | 5 +++++ kernel/auditsc.c | 15 ++++++++++----- 2 files changed, 15 insertions(+), 5 deletions(-) diff --git a/include/linux/audit.h b/include/linux/audit.h index 2d8b761..48c49eb 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -450,6 +450,11 @@ struct audit_field { extern int __init audit_register_class(int class, unsigned *list); extern int audit_classify_syscall(int abi, unsigned syscall); extern int audit_classify_arch(int arch); + +/* audit_names->type values */ +#define AUDIT_TYPE_UNKNOWN 0 /* we don't know yet */ +#define AUDIT_TYPE_NORMAL 1 /* a "normal" audit record */ + #ifdef CONFIG_AUDITSYSCALL /* These are defined in auditsc.c */ /* Public API */ diff --git a/kernel/auditsc.c b/kernel/auditsc.c index ff58089..bd11d09 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -120,6 +120,7 @@ struct audit_names { struct audit_cap_data fcap; unsigned int fcap_ver; int name_len; /* number of name's characters to log */ + unsigned char type; /* record type */ bool name_put; /* call __putname() for this name */ /* * This was an allocated audit_names and not from the array of @@ -2009,7 +2010,8 @@ retry: #endif } -static struct audit_names *audit_alloc_name(struct audit_context *context) +static struct audit_names *audit_alloc_name(struct audit_context *context, + unsigned char type) { struct audit_names *aname; @@ -2024,6 +2026,7 @@ static struct audit_names *audit_alloc_name(struct audit_context *context) } aname->ino = (unsigned long)-1; + aname->type = type; list_add_tail(&aname->list, &context->names_list); context->name_count++; @@ -2054,7 +2057,7 @@ void __audit_getname(const char *name) return; } - n = audit_alloc_name(context); + n = audit_alloc_name(context, AUDIT_TYPE_UNKNOWN); if (!n) return; @@ -2171,12 +2174,13 @@ void __audit_inode(const char *name, const struct dentry *dentry) out_alloc: /* unable to find the name from a previous getname() */ - n = audit_alloc_name(context); + n = audit_alloc_name(context, AUDIT_TYPE_NORMAL); if (!n) return; out: handle_path(dentry); audit_copy_inode(n, dentry, inode); + n->type = AUDIT_TYPE_NORMAL; } /** @@ -2233,6 +2237,7 @@ void __audit_inode_child(const struct inode *parent, audit_copy_inode(n, dentry, inode); else n->ino = (unsigned long)-1; + n->type = AUDIT_TYPE_NORMAL; found_child = n->name; goto add_names; } @@ -2240,14 +2245,14 @@ void __audit_inode_child(const struct inode *parent, add_names: if (!found_parent) { - n = audit_alloc_name(context); + n = audit_alloc_name(context, AUDIT_TYPE_NORMAL); if (!n) return; audit_copy_inode(n, NULL, parent); } if (!found_child) { - n = audit_alloc_name(context); + n = audit_alloc_name(context, AUDIT_TYPE_NORMAL); if (!n) return; -- 1.7.11.4

Currently, this gets set mostly by happenstance when we call into audit_inode_child. While that might be a little more efficient, it seems wrong. If the syscall ends up failing before audit_inode_child ever gets called, then you'll have an audit_names record that shows the full path but has the parent inode info attached. Fix this by passing in a parent flag when we call audit_inode that gets set to the value of LOOKUP_PARENT. We can then fix up the pathname for the audit entry correctly from the get-go. While we're at it, clean up the no-op macro for audit_inode in the !CONFIG_AUDITSYSCALL case. Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/namei.c | 14 +++++++------- fs/open.c | 4 ++-- fs/xattr.c | 8 ++++---- include/linux/audit.h | 13 ++++++++----- ipc/mqueue.c | 8 ++++---- kernel/audit.h | 1 + kernel/auditfilter.c | 30 ++++++++++++++++++++++++++++++ kernel/auditsc.c | 41 +++++++++++++++++++++++++++++------------ 8 files changed, 85 insertions(+), 34 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index d431111..6c9d86d 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1977,7 +1977,7 @@ static int do_path_lookup(int dfd, const char *name, retval = path_lookupat(dfd, name, flags | LOOKUP_REVAL, nd); if (likely(!retval)) - audit_inode(name, nd->path.dentry); + audit_inode(name, nd->path.dentry, flags & LOOKUP_PARENT); return retval; } @@ -2652,7 +2652,7 @@ static int do_last(struct nameidata *nd, struct path *path, error = complete_walk(nd); if (error) return error; - audit_inode(pathname, nd->path.dentry); + audit_inode(pathname, nd->path.dentry, 0); if (open_flag & O_CREAT) { error = -EISDIR; goto out; @@ -2662,7 +2662,7 @@ static int do_last(struct nameidata *nd, struct path *path, error = complete_walk(nd); if (error) return error; - audit_inode(pathname, dir); + audit_inode(pathname, dir, 0); goto finish_open; } @@ -2691,7 +2691,7 @@ static int do_last(struct nameidata *nd, struct path *path, if (error) return error; - audit_inode(pathname, dir); + audit_inode(pathname, dir, 0); error = -EISDIR; /* trailing slashes? */ if (nd->last.name[nd->last.len]) @@ -2721,7 +2721,7 @@ retry_lookup: !S_ISREG(file->f_path.dentry->d_inode->i_mode)) will_truncate = false; - audit_inode(pathname, file->f_path.dentry); + audit_inode(pathname, file->f_path.dentry, 0); goto opened; } @@ -2738,7 +2738,7 @@ retry_lookup: * create/update audit record if it already exists. */ if (path->dentry->d_inode) - audit_inode(pathname, path->dentry); + audit_inode(pathname, path->dentry, 0); /* * If atomic_open() acquired write access it is dropped now due to @@ -2803,7 +2803,7 @@ finish_lookup: error = -ENOTDIR; if ((nd->flags & LOOKUP_DIRECTORY) && !nd->inode->i_op->lookup) goto out; - audit_inode(pathname, nd->path.dentry); + audit_inode(pathname, nd->path.dentry, 0); finish_open: if (!S_ISREG(nd->inode->i_mode)) will_truncate = false; diff --git a/fs/open.c b/fs/open.c index e1f2cdb..ec06921 100644 --- a/fs/open.c +++ b/fs/open.c @@ -481,7 +481,7 @@ SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode) file = fget(fd); if (file) { - audit_inode(NULL, file->f_path.dentry); + audit_inode(NULL, file->f_path.dentry, 0); err = chmod_common(&file->f_path, mode); fput(file); } @@ -594,7 +594,7 @@ SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) if (error) goto out_fput; dentry = file->f_path.dentry; - audit_inode(NULL, dentry); + audit_inode(NULL, dentry, 0); error = chown_common(&file->f_path, user, group); mnt_drop_write_file(file); out_fput: diff --git a/fs/xattr.c b/fs/xattr.c index 4d45b71..588455b 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -408,7 +408,7 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, if (!f) return error; dentry = f->f_path.dentry; - audit_inode(NULL, dentry); + audit_inode(NULL, dentry, 0); error = mnt_want_write_file(f); if (!error) { error = setxattr(dentry, name, value, size, flags); @@ -502,7 +502,7 @@ SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name, f = fget_light(fd, &fput_needed); if (!f) return error; - audit_inode(NULL, f->f_path.dentry); + audit_inode(NULL, f->f_path.dentry, 0); error = getxattr(f->f_path.dentry, name, value, size); fput_light(f, fput_needed); return error; @@ -583,7 +583,7 @@ SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size) f = fget_light(fd, &fput_needed); if (!f) return error; - audit_inode(NULL, f->f_path.dentry); + audit_inode(NULL, f->f_path.dentry, 0); error = listxattr(f->f_path.dentry, list, size); fput_light(f, fput_needed); return error; @@ -654,7 +654,7 @@ SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) if (!f) return error; dentry = f->f_path.dentry; - audit_inode(NULL, dentry); + audit_inode(NULL, dentry, 0); error = mnt_want_write_file(f); if (!error) { error = removexattr(dentry, name); diff --git a/include/linux/audit.h b/include/linux/audit.h index 48c49eb..155524b 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -454,6 +454,7 @@ extern int audit_classify_arch(int arch); /* audit_names->type values */ #define AUDIT_TYPE_UNKNOWN 0 /* we don't know yet */ #define AUDIT_TYPE_NORMAL 1 /* a "normal" audit record */ +#define AUDIT_TYPE_PARENT 2 /* a parent audit record */ #ifdef CONFIG_AUDITSYSCALL /* These are defined in auditsc.c */ @@ -466,7 +467,8 @@ extern void __audit_syscall_entry(int arch, extern void __audit_syscall_exit(int ret_success, long ret_value); extern void __audit_getname(const char *name); extern void audit_putname(const char *name); -extern void __audit_inode(const char *name, const struct dentry *dentry); +extern void __audit_inode(const char *name, const struct dentry *dentry, + unsigned int parent); extern void __audit_inode_child(const struct inode *parent, const struct dentry *dentry); extern void __audit_seccomp(unsigned long syscall, long signr, int code); @@ -503,9 +505,10 @@ static inline void audit_getname(const char *name) if (unlikely(!audit_dummy_context())) __audit_getname(name); } -static inline void audit_inode(const char *name, const struct dentry *dentry) { +static inline void audit_inode(const char *name, const struct dentry *dentry, + unsigned int parent) { if (unlikely(!audit_dummy_context())) - __audit_inode(name, dentry); + __audit_inode(name, dentry, parent); } static inline void audit_inode_child(const struct inode *parent, const struct dentry *dentry) { @@ -635,9 +638,9 @@ extern int audit_signals; #define audit_dummy_context() 1 #define audit_getname(n) do { ; } while (0) #define audit_putname(n) do { ; } while (0) -#define __audit_inode(n,d) do { ; } while (0) +#define __audit_inode(n,d,p) do { ; } while (0) #define __audit_inode_child(p,d) do { ; } while (0) -#define audit_inode(n,d) do { (void)(d); } while (0) +#define audit_inode(n,d,p) do { ; } while (0) #define audit_inode_child(p,d) do { ; } while (0) #define audit_core_dumps(i) do { ; } while (0) #define audit_seccomp(i,s,c) do { ; } while (0) diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 9a08acc..69cb5fe 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -805,7 +805,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode, if (oflag & O_CREAT) { if (path.dentry->d_inode) { /* entry already exists */ - audit_inode(name, path.dentry); + audit_inode(name, path.dentry, 0); if (oflag & O_EXCL) { error = -EEXIST; goto out; @@ -825,7 +825,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode, error = -ENOENT; goto out; } - audit_inode(name, path.dentry); + audit_inode(name, path.dentry, 0); filp = do_open(&path, oflag); } @@ -979,7 +979,7 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr, goto out_fput; } info = MQUEUE_I(inode); - audit_inode(NULL, filp->f_path.dentry); + audit_inode(NULL, filp->f_path.dentry, 0); if (unlikely(!(filp->f_mode & FMODE_WRITE))) { ret = -EBADF; @@ -1096,7 +1096,7 @@ SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr, goto out_fput; } info = MQUEUE_I(inode); - audit_inode(NULL, filp->f_path.dentry); + audit_inode(NULL, filp->f_path.dentry, 0); if (unlikely(!(filp->f_mode & FMODE_READ))) { ret = -EBADF; diff --git a/kernel/audit.h b/kernel/audit.h index 8167668..276ca88 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -76,6 +76,7 @@ static inline int audit_hash_ino(u32 ino) extern int audit_match_class(int class, unsigned syscall); extern int audit_comparator(const u32 left, const u32 op, const u32 right); +extern int parent_len(const char *path); extern int audit_compare_dname_path(const char *dname, const char *path, int *dirlen); extern struct sk_buff * audit_make_reply(int pid, int seq, int type, diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index a6c3f1a..29b167b 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1198,6 +1198,36 @@ int audit_comparator(u32 left, u32 op, u32 right) } } +/** + * parent_len - find the length of the parent portion of a pathname + * @path: pathname of which to determine length + */ +int parent_len(const char *path) +{ + int plen; + const char *p; + + plen = strlen(path); + + if (plen == 0) + return plen; + + /* disregard trailing slashes */ + p = path + plen - 1; + while ((*p == '/') && (p > path)) + p--; + + /* walk backward until we find the next slash or hit beginning */ + while ((*p != '/') && (p > path)) + p--; + + /* did we find a slash? Then increment to include it in path */ + if (*p == '/') + p++; + + return p - path; +} + /* Compare given dentry name with last component in given path, * return of 0 indicates a match. */ int audit_compare_dname_path(const char *dname, const char *path, diff --git a/kernel/auditsc.c b/kernel/auditsc.c index bd11d09..011e923 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -2149,13 +2149,13 @@ static void audit_copy_inode(struct audit_names *name, const struct dentry *dent } /** - * audit_inode - store the inode and device from a lookup + * __audit_inode - store the inode and device from a lookup * @name: name being audited * @dentry: dentry being audited - * - * Called from fs/namei.c:path_lookup(). + * @parent: does this dentry represent the parent? */ -void __audit_inode(const char *name, const struct dentry *dentry) +void __audit_inode(const char *name, const struct dentry *dentry, + unsigned int parent) { struct audit_context *context = current->audit_context; const struct inode *inode = dentry->d_inode; @@ -2168,19 +2168,38 @@ void __audit_inode(const char *name, const struct dentry *dentry) goto out_alloc; list_for_each_entry_reverse(n, &context->names_list, list) { - if (n->name == name) - goto out; + /* does the name pointer match? */ + if (n->name != name) + continue; + + /* match the correct record type */ + if (parent) { + if (n->type == AUDIT_TYPE_PARENT || + n->type == AUDIT_TYPE_UNKNOWN) + goto out; + } else { + if (n->type != AUDIT_TYPE_PARENT) + goto out; + } } out_alloc: - /* unable to find the name from a previous getname() */ + /* unable to find the name from a previous getname(). Allocate a new + * anonymous entry. + */ n = audit_alloc_name(context, AUDIT_TYPE_NORMAL); if (!n) return; out: + if (parent) { + n->name_len = n->name ? parent_len(n->name) : AUDIT_NAME_FULL; + n->type = AUDIT_TYPE_PARENT; + } else { + n->name_len = AUDIT_NAME_FULL; + n->type = AUDIT_TYPE_NORMAL; + } handle_path(dentry); audit_copy_inode(n, dentry, inode); - n->type = AUDIT_TYPE_NORMAL; } /** @@ -2204,7 +2223,6 @@ void __audit_inode_child(const struct inode *parent, const struct inode *inode = dentry->d_inode; const char *dname = dentry->d_name.name; struct audit_names *n; - int dirlen = 0; if (!context->in_syscall) return; @@ -2218,8 +2236,7 @@ void __audit_inode_child(const struct inode *parent, continue; if (n->ino == parent->i_ino && - !audit_compare_dname_path(dname, n->name, &dirlen)) { - n->name_len = dirlen; /* update parent data in place */ + !audit_compare_dname_path(dname, n->name, NULL)) { found_parent = n->name; goto add_names; } @@ -2232,7 +2249,7 @@ void __audit_inode_child(const struct inode *parent, /* strcmp() is the more likely scenario */ if (!strcmp(dname, n->name) || - !audit_compare_dname_path(dname, n->name, &dirlen)) { + !audit_compare_dname_path(dname, n->name, NULL)) { if (inode) audit_copy_inode(n, dentry, inode); else -- 1.7.11.4

From: Eric Paris <eparis(a)redhat.com&gt; Signed-off-by: Eric Paris <eparis(a)redhat.com&gt; --- kernel/auditfilter.c | 27 +++++++-------------------- 1 file changed, 7 insertions(+), 20 deletions(-) diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index f9c48d0..f47ba18 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1232,32 +1232,19 @@ int parent_len(const char *path) * return of 0 indicates a match. */ int audit_compare_dname_path(const char *dname, const char *path) { - int dlen, plen; + int dlen, pathlen, parentlen; const char *p; - if (!dname || !path) - return 1; - dlen = strlen(dname); - plen = strlen(path); - if (plen < dlen) + pathlen = strlen(path); + if (pathlen < dlen) return 1; - /* disregard trailing slashes */ - p = path + plen - 1; - while ((*p == '/') && (p > path)) - p--; - - /* find last path component */ - p = p - dlen + 1; - if (p < path) + parentlen = parent_len(path); + if (pathlen - parentlen != dlen) return 1; - else if (p > path) { - if (*--p != '/') - return 1; - else - p++; - } + + p = path + parentlen; return strncmp(p, dname, dlen); } -- 1.7.11.4

In order to accomodate retrying path-based syscalls, we need to add a new "type" argument to audit_inode_child. This will tell us whether we're looking for a child entry that represents a create or a delete. If we find a parent, don't automatically assume that we need to create a new entry. Instead, use the information we have to try to find an existing entry first. Update it if one is found and create a new one if not. Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/btrfs/ioctl.c | 2 +- fs/namei.c | 2 +- include/linux/audit.h | 12 ++++++---- include/linux/fsnotify.h | 8 +++---- kernel/auditsc.c | 57 +++++++++++++++++++++++++----------------------- 5 files changed, 44 insertions(+), 37 deletions(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 7e78d47..45f987b 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -614,7 +614,7 @@ static int btrfs_may_delete(struct inode *dir,struct dentry *victim,int isdir) return -ENOENT; BUG_ON(victim->d_parent->d_inode != dir); - audit_inode_child(dir, victim); + audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); error = inode_permission(dir, MAY_WRITE | MAY_EXEC); if (error) diff --git a/fs/namei.c b/fs/namei.c index 6c9d86d..64f7350 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2180,7 +2180,7 @@ static int may_delete(struct inode *dir,struct dentry *victim,int isdir) return -ENOENT; BUG_ON(victim->d_parent->d_inode != dir); - audit_inode_child(dir, victim); + audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); error = inode_permission(dir, MAY_WRITE | MAY_EXEC); if (error) diff --git a/include/linux/audit.h b/include/linux/audit.h index 155524b..0f7284a 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -455,6 +455,8 @@ extern int audit_classify_arch(int arch); #define AUDIT_TYPE_UNKNOWN 0 /* we don't know yet */ #define AUDIT_TYPE_NORMAL 1 /* a "normal" audit record */ #define AUDIT_TYPE_PARENT 2 /* a parent audit record */ +#define AUDIT_TYPE_CHILD_DELETE 3 /* a child being deleted */ +#define AUDIT_TYPE_CHILD_CREATE 4 /* a child being created */ #ifdef CONFIG_AUDITSYSCALL /* These are defined in auditsc.c */ @@ -470,7 +472,8 @@ extern void audit_putname(const char *name); extern void __audit_inode(const char *name, const struct dentry *dentry, unsigned int parent); extern void __audit_inode_child(const struct inode *parent, - const struct dentry *dentry); + const struct dentry *dentry, + const unsigned char type); extern void __audit_seccomp(unsigned long syscall, long signr, int code); extern void __audit_ptrace(struct task_struct *t); @@ -511,9 +514,10 @@ static inline void audit_inode(const char *name, const struct dentry *dentry, __audit_inode(name, dentry, parent); } static inline void audit_inode_child(const struct inode *parent, - const struct dentry *dentry) { + const struct dentry *dentry, + const unsigned char type) { if (unlikely(!audit_dummy_context())) - __audit_inode_child(parent, dentry); + __audit_inode_child(parent, dentry, type); } void audit_core_dumps(long signr); @@ -641,7 +645,7 @@ extern int audit_signals; #define __audit_inode(n,d,p) do { ; } while (0) #define __audit_inode_child(p,d) do { ; } while (0) #define audit_inode(n,d,p) do { ; } while (0) -#define audit_inode_child(p,d) do { ; } while (0) +#define audit_inode_child(p,d,t) do { ; } while (0) #define audit_core_dumps(i) do { ; } while (0) #define audit_seccomp(i,s,c) do { ; } while (0) #define auditsc_get_stamp(c,t,s) (0) diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 9c28471..0fbfb46 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -109,7 +109,7 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, if (source) fsnotify(source, FS_MOVE_SELF, moved->d_inode, FSNOTIFY_EVENT_INODE, NULL, 0); - audit_inode_child(new_dir, moved); + audit_inode_child(new_dir, moved, AUDIT_TYPE_CHILD_CREATE); } /* @@ -155,7 +155,7 @@ static inline void fsnotify_inoderemove(struct inode *inode) */ static inline void fsnotify_create(struct inode *inode, struct dentry *dentry) { - audit_inode_child(inode, dentry); + audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify(inode, FS_CREATE, dentry->d_inode, FSNOTIFY_EVENT_INODE, dentry->d_name.name, 0); } @@ -168,7 +168,7 @@ static inline void fsnotify_create(struct inode *inode, struct dentry *dentry) static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct dentry *new_dentry) { fsnotify_link_count(inode); - audit_inode_child(dir, new_dentry); + audit_inode_child(dir, new_dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify(dir, FS_CREATE, inode, FSNOTIFY_EVENT_INODE, new_dentry->d_name.name, 0); } @@ -181,7 +181,7 @@ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) __u32 mask = (FS_CREATE | FS_ISDIR); struct inode *d_inode = dentry->d_inode; - audit_inode_child(inode, dentry); + audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify(inode, mask, d_inode, FSNOTIFY_EVENT_INODE, dentry->d_name.name, 0); } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 52d1f0f..2f20b97 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -2203,6 +2203,7 @@ out: * __audit_inode_child - collect inode info for created/removed objects * @parent: inode of dentry parent * @dentry: dentry being audited + * @type: AUDIT_TYPE_* value that we're looking for * * For syscalls that create or remove filesystem objects, audit_inode * can only collect information for the filesystem object's parent. @@ -2213,13 +2214,13 @@ out: * unsuccessful attempts. */ void __audit_inode_child(const struct inode *parent, - const struct dentry *dentry) + const struct dentry *dentry, + const unsigned char type) { struct audit_context *context = current->audit_context; - const char *found_parent = NULL, *found_child = NULL; const struct inode *inode = dentry->d_inode; const char *dname = dentry->d_name.name; - struct audit_names *n; + struct audit_names *n, *found_parent = NULL, *found_child = NULL; if (!context->in_syscall) return; @@ -2227,63 +2228,65 @@ void __audit_inode_child(const struct inode *parent, if (inode) handle_one(inode); - /* parent is more likely, look for it first */ + /* look for a parent entry first */ list_for_each_entry(n, &context->names_list, list) { - if (!n->name) + if (!n->name || n->type != AUDIT_TYPE_PARENT) continue; if (n->ino == parent->i_ino && !audit_compare_dname_path(dname, n->name, n->name_len)) { - found_parent = n->name; - goto add_names; + found_parent = n; + break; } } - /* no matching parent, look for matching child */ + /* is there a matching child entry? */ list_for_each_entry(n, &context->names_list, list) { - if (!n->name) + /* can only match entries that have a name */ + if (!n->name || n->type != type) + continue; + + /* if we found a parent, make sure this one is a child of it */ + if (found_parent && (n->name != found_parent->name)) continue; - /* strcmp() is the more likely scenario */ if (!strcmp(dname, n->name) || !audit_compare_dname_path(dname, n->name, + found_parent ? + found_parent->name_len : AUDIT_NAME_FULL)) { - if (inode) - audit_copy_inode(n, dentry, inode); - else - n->ino = (unsigned long)-1; - n->type = AUDIT_TYPE_NORMAL; - found_child = n->name; - goto add_names; + found_child = n; + break; } } -add_names: if (!found_parent) { - n = audit_alloc_name(context, AUDIT_TYPE_NORMAL); + /* create a new, "anonymous" parent record */ + n = audit_alloc_name(context, AUDIT_TYPE_PARENT); if (!n) return; audit_copy_inode(n, NULL, parent); } if (!found_child) { - n = audit_alloc_name(context, AUDIT_TYPE_NORMAL); - if (!n) + found_child = audit_alloc_name(context, type); + if (!found_child) return; /* Re-use the name belonging to the slot for a matching parent * directory. All names for this context are relinquished in * audit_free_names() */ if (found_parent) { - n->name = found_parent; - n->name_len = AUDIT_NAME_FULL; + found_child->name = found_parent->name; + found_child->name_len = AUDIT_NAME_FULL; /* don't call __putname() */ - n->name_put = false; + found_child->name_put = false; } - - if (inode) - audit_copy_inode(n, dentry, inode); } + if (inode) + audit_copy_inode(found_child, dentry, inode); + else + found_child->ino = (unsigned long)-1; } EXPORT_SYMBOL_GPL(__audit_inode_child); -- 1.7.11.4

Nothing changes it, so it should be safe to do. Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/namespace.c | 2 +- include/linux/fs.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/namespace.c b/fs/namespace.c index 4d31f73..8e52b1c 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2185,7 +2185,7 @@ int copy_mount_string(const void __user *data, char **where) * Therefore, if this magic number is present, it carries no information * and must be discarded. */ -long do_mount(char *dev_name, char *dir_name, char *type_page, +long do_mount(char *dev_name, const char *dir_name, char *type_page, unsigned long flags, void *data_page) { struct path path; diff --git a/include/linux/fs.h b/include/linux/fs.h index 69513a7..b6ce6fc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2072,7 +2072,7 @@ extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data); extern void kern_unmount(struct vfsmount *mnt); extern int may_umount_tree(struct vfsmount *); extern int may_umount(struct vfsmount *); -extern long do_mount(char *, char *, char *, unsigned long, void *); +extern long do_mount(char *, const char *, char *, unsigned long, void *); extern struct vfsmount *collect_mounts(struct path *); extern void drop_collected_mounts(struct vfsmount *); extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, -- 1.7.11.4

getname() is intended to copy pathname strings from userspace into a kernel buffer. The result is just a string in kernel space. It would however be quite helpful to be able to attach some ancillary info to the string. For instance, we could attach some audit-related info to reduce the amount of audit-related processing needed. When auditing is enabled, we could also call getname() on the string more than once and not need to recopy it from userspace. This patchset converts the getname()/putname() interfaces to return a struct instead of a string. For now, the struct just tracks the string in kernel space and the original userland pointer for it. Later, we'll add other information to the struct as it becomes convenient. Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- arch/alpha/kernel/osf_sys.c | 16 ++--- arch/avr32/kernel/process.c | 4 +- arch/blackfin/kernel/process.c | 4 +- arch/cris/arch-v10/kernel/process.c | 4 +- arch/cris/arch-v32/kernel/process.c | 4 +- arch/h8300/kernel/process.c | 4 +- arch/hexagon/kernel/syscall.c | 4 +- arch/ia64/kernel/process.c | 4 +- arch/m32r/kernel/process.c | 4 +- arch/microblaze/kernel/sys_microblaze.c | 4 +- arch/mips/kernel/linux32.c | 4 +- arch/mips/kernel/syscall.c | 4 +- arch/openrisc/kernel/process.c | 4 +- arch/parisc/hpux/fs.c | 4 +- arch/parisc/kernel/process.c | 4 +- arch/parisc/kernel/sys_parisc32.c | 4 +- arch/score/kernel/sys_score.c | 4 +- arch/sh/kernel/process_32.c | 4 +- arch/sh/kernel/process_64.c | 4 +- arch/tile/kernel/process.c | 8 +-- arch/unicore32/kernel/sys.c | 4 +- arch/xtensa/kernel/process.c | 4 +- fs/compat.c | 12 ++-- fs/exec.c | 13 ++-- fs/filesystems.c | 4 +- fs/namei.c | 113 +++++++++++++++++++------------- fs/namespace.c | 4 +- fs/open.c | 4 +- fs/quota/quota.c | 4 +- include/linux/audit.h | 8 ++- include/linux/fs.h | 14 +++- ipc/mqueue.c | 13 ++-- kernel/acct.c | 4 +- kernel/auditsc.c | 86 +++++++++++++----------- mm/swapfile.c | 11 ++-- 35 files changed, 218 insertions(+), 176 deletions(-) diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index bc1acdd..b3f41e8 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -452,7 +452,7 @@ osf_ufs_mount(char *dirname, struct ufs_args __user *args, int flags) { int retval; struct cdfs_args tmp; - char *devname; + struct getname_info *devname; retval = -EFAULT; if (copy_from_user(&tmp, args, sizeof(tmp))) @@ -461,7 +461,7 @@ osf_ufs_mount(char *dirname, struct ufs_args __user *args, int flags) retval = PTR_ERR(devname); if (IS_ERR(devname)) goto out; - retval = do_mount(devname, dirname, "ext2", flags, NULL); + retval = do_mount(devname->name, dirname, "ext2", flags, NULL); putname(devname); out: return retval; @@ -472,7 +472,7 @@ osf_cdfs_mount(char *dirname, struct cdfs_args __user *args, int flags) { int retval; struct cdfs_args tmp; - char *devname; + struct getname_info *devname; retval = -EFAULT; if (copy_from_user(&tmp, args, sizeof(tmp))) @@ -481,7 +481,7 @@ osf_cdfs_mount(char *dirname, struct cdfs_args __user *args, int flags) retval = PTR_ERR(devname); if (IS_ERR(devname)) goto out; - retval = do_mount(devname, dirname, "iso9660", flags, NULL); + retval = do_mount(devname->name, dirname, "iso9660", flags, NULL); putname(devname); out: return retval; @@ -502,7 +502,7 @@ SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, const char __user *, path, int, flag, void __user *, data) { int retval; - char *name; + struct getname_info *name; name = getname(path); retval = PTR_ERR(name); @@ -510,13 +510,13 @@ SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, const char __user *, path, goto out; switch (typenr) { case 1: - retval = osf_ufs_mount(name, data, flag); + retval = osf_ufs_mount(name->name, data, flag); break; case 6: - retval = osf_cdfs_mount(name, data, flag); + retval = osf_cdfs_mount(name->name, data, flag); break; case 9: - retval = osf_procfs_mount(name, data, flag); + retval = osf_procfs_mount(name->name, data, flag); break; default: retval = -EINVAL; diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c index 92c5af9..c2034e8 100644 --- a/arch/avr32/kernel/process.c +++ b/arch/avr32/kernel/process.c @@ -388,14 +388,14 @@ asmlinkage int sys_execve(const char __user *ufilename, struct pt_regs *regs) { int error; - char *filename; + struct getname_info *filename; filename = getname(ufilename); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, uargv, uenvp, regs); + error = do_execve(filename->name, uargv, uenvp, regs); putname(filename); out: diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c index 62bcea7..bc5c162 100644 --- a/arch/blackfin/kernel/process.c +++ b/arch/blackfin/kernel/process.c @@ -213,14 +213,14 @@ asmlinkage int sys_execve(const char __user *name, const char __user *const __user *envp) { int error; - char *filename; + struct getname_info *filename; struct pt_regs *regs = (struct pt_regs *)((&name) + 6); filename = getname(name); error = PTR_ERR(filename); if (IS_ERR(filename)) return error; - error = do_execve(filename, argv, envp, regs); + error = do_execve(filename->name, argv, envp, regs); putname(filename); return error; } diff --git a/arch/cris/arch-v10/kernel/process.c b/arch/cris/arch-v10/kernel/process.c index bee8df4..92b57e7 100644 --- a/arch/cris/arch-v10/kernel/process.c +++ b/arch/cris/arch-v10/kernel/process.c @@ -212,14 +212,14 @@ asmlinkage int sys_execve(const char *fname, struct pt_regs *regs) { int error; - char *filename; + struct getname_info *filename; filename = getname(fname); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, argv, envp, regs); + error = do_execve(filename->name, argv, envp, regs); putname(filename); out: return error; diff --git a/arch/cris/arch-v32/kernel/process.c b/arch/cris/arch-v32/kernel/process.c index 0570e8c..a80be6f 100644 --- a/arch/cris/arch-v32/kernel/process.c +++ b/arch/cris/arch-v32/kernel/process.c @@ -224,7 +224,7 @@ sys_execve(const char *fname, struct pt_regs *regs) { int error; - char *filename; + struct getname_info *filename; filename = getname(fname); error = PTR_ERR(filename); @@ -232,7 +232,7 @@ sys_execve(const char *fname, if (IS_ERR(filename)) goto out; - error = do_execve(filename, argv, envp, regs); + error = do_execve(filename->name, argv, envp, regs); putname(filename); out: return error; diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index 0e9c315..67d357d 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -214,14 +214,14 @@ asmlinkage int sys_execve(const char *name, int dummy, ...) { int error; - char * filename; + struct getname_info *filename; struct pt_regs *regs = (struct pt_regs *) ((unsigned char *)&dummy-4); filename = getname(name); error = PTR_ERR(filename); if (IS_ERR(filename)) return error; - error = do_execve(filename, argv, envp, regs); + error = do_execve(filename->name, argv, envp, regs); putname(filename); return error; } diff --git a/arch/hexagon/kernel/syscall.c b/arch/hexagon/kernel/syscall.c index 553cd60..f67b4d5 100644 --- a/arch/hexagon/kernel/syscall.c +++ b/arch/hexagon/kernel/syscall.c @@ -40,7 +40,7 @@ asmlinkage int sys_execve(char __user *ufilename, const char __user *const __user *envp) { struct pt_regs *pregs = current_thread_info()->regs; - char *filename; + struct getname_info *filename; int retval; filename = getname(ufilename); @@ -48,7 +48,7 @@ asmlinkage int sys_execve(char __user *ufilename, if (IS_ERR(filename)) return retval; - retval = do_execve(filename, argv, envp, pregs); + retval = do_execve(filename->name, argv, envp, pregs); putname(filename); return retval; diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index dd6fc14..d2cf668 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -611,14 +611,14 @@ sys_execve (const char __user *filename, const char __user *const __user *envp, struct pt_regs *regs) { - char *fname; + struct getname_info *fname; int error; fname = getname(filename); error = PTR_ERR(fname); if (IS_ERR(fname)) goto out; - error = do_execve(fname, argv, envp, regs); + error = do_execve(fname->name, argv, envp, regs); putname(fname); out: return error; diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c index 3a4a32b..e1ea185 100644 --- a/arch/m32r/kernel/process.c +++ b/arch/m32r/kernel/process.c @@ -293,14 +293,14 @@ asmlinkage int sys_execve(const char __user *ufilename, unsigned long r6, struct pt_regs regs) { int error; - char *filename; + struct getname_info *filename; filename = getname(ufilename); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, uargv, uenvp, &regs); + error = do_execve(filename->name, uargv, uenvp, &regs); putname(filename); out: return error; diff --git a/arch/microblaze/kernel/sys_microblaze.c b/arch/microblaze/kernel/sys_microblaze.c index e5b154f..f273d16 100644 --- a/arch/microblaze/kernel/sys_microblaze.c +++ b/arch/microblaze/kernel/sys_microblaze.c @@ -54,13 +54,13 @@ asmlinkage long microblaze_execve(const char __user *filenamei, struct pt_regs *regs) { int error; - char *filename; + struct getname_info *filename; filename = getname(filenamei); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, argv, envp, regs); + error = do_execve(filename->name, argv, envp, regs); putname(filename); out: return error; diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 922a554..62ff5a9 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -83,13 +83,13 @@ out: asmlinkage int sys32_execve(nabi_no_regargs struct pt_regs regs) { int error; - char * filename; + struct getname_info *filename; filename = getname(compat_ptr(regs.regs[4])); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = compat_do_execve(filename, compat_ptr(regs.regs[5]), + error = compat_do_execve(filename->name, compat_ptr(regs.regs[5]), compat_ptr(regs.regs[6]), &regs); putname(filename); diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index b08220c..679c417 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -133,13 +133,13 @@ _sys_clone(nabi_no_regargs struct pt_regs regs) asmlinkage int sys_execve(nabi_no_regargs struct pt_regs regs) { int error; - char * filename; + struct getname_info *filename; filename = getname((const char __user *) (long)regs.regs[4]); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, + error = do_execve(filename->name, (const char __user *const __user *) (long)regs.regs[5], (const char __user *const __user *) (long)regs.regs[6], &regs); diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index 55210f3..9edec79 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -271,7 +271,7 @@ asmlinkage long _sys_execve(const char __user *name, struct pt_regs *regs) { int error; - char *filename; + struct getname_info *filename; filename = getname(name); error = PTR_ERR(filename); @@ -279,7 +279,7 @@ asmlinkage long _sys_execve(const char __user *name, if (IS_ERR(filename)) goto out; - error = do_execve(filename, argv, envp, regs); + error = do_execve(filename->name, argv, envp, regs); putname(filename); out: diff --git a/arch/parisc/hpux/fs.c b/arch/parisc/hpux/fs.c index c71eb6c..a40d81f 100644 --- a/arch/parisc/hpux/fs.c +++ b/arch/parisc/hpux/fs.c @@ -34,14 +34,14 @@ int hpux_execve(struct pt_regs *regs) { int error; - char *filename; + struct getname_info *filename; filename = getname((const char __user *) regs->gr[26]); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, + error = do_execve(filename->name, (const char __user *const __user *) regs->gr[25], (const char __user *const __user *) regs->gr[24], regs); diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 2c05a92..f8d32be 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -339,13 +339,13 @@ unsigned long thread_saved_pc(struct task_struct *t) asmlinkage int sys_execve(struct pt_regs *regs) { int error; - char *filename; + struct getname_info *filename; filename = getname((const char __user *) regs->gr[26]); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, + error = do_execve(filename->name, (const char __user *const __user *) regs->gr[25], (const char __user *const __user *) regs->gr[24], regs); diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c index dc9a624..7e17607 100644 --- a/arch/parisc/kernel/sys_parisc32.c +++ b/arch/parisc/kernel/sys_parisc32.c @@ -60,14 +60,14 @@ asmlinkage int sys32_execve(struct pt_regs *regs) { int error; - char *filename; + struct getname_info *filename; DBG(("sys32_execve(%p) r26 = 0x%lx\n", regs, regs->gr[26])); filename = getname((const char __user *) regs->gr[26]); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = compat_do_execve(filename, compat_ptr(regs->gr[25]), + error = compat_do_execve(filename->name, compat_ptr(regs->gr[25]), compat_ptr(regs->gr[24]), regs); putname(filename); out: diff --git a/arch/score/kernel/sys_score.c b/arch/score/kernel/sys_score.c index e478bf9..9ee9ac9 100644 --- a/arch/score/kernel/sys_score.c +++ b/arch/score/kernel/sys_score.c @@ -92,14 +92,14 @@ asmlinkage long score_execve(struct pt_regs *regs) { int error; - char *filename; + struct getname_info *filename; filename = getname((char __user*)regs->regs[4]); error = PTR_ERR(filename); if (IS_ERR(filename)) return error; - error = do_execve(filename, + error = do_execve(filename->name, (const char __user *const __user *)regs->regs[5], (const char __user *const __user *)regs->regs[6], regs); diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index 59521e8..93d4879 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -298,14 +298,14 @@ asmlinkage int sys_execve(const char __user *ufilename, { struct pt_regs *regs = RELOC_HIDE(&__regs, 0); int error; - char *filename; + struct getname_info *filename; filename = getname(ufilename); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, uargv, uenvp, regs); + error = do_execve(filename->name, uargv, uenvp, regs); putname(filename); out: return error; diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c index 602545b..bad7c30 100644 --- a/arch/sh/kernel/process_64.c +++ b/arch/sh/kernel/process_64.c @@ -491,14 +491,14 @@ asmlinkage int sys_execve(const char *ufilename, char **uargv, struct pt_regs *pregs) { int error; - char *filename; + struct getname_info *filename; filename = getname((char __user *)ufilename); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, + error = do_execve(filename->name, (const char __user *const __user *)uargv, (const char __user *const __user *)uenvp, pregs); diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index 6be7991..04b0e62 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -594,13 +594,13 @@ SYSCALL_DEFINE4(execve, const char __user *, path, struct pt_regs *, regs) { long error; - char *filename; + struct getname_info *filename; filename = getname(path); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, argv, envp, regs); + error = do_execve(filename->name, argv, envp, regs); putname(filename); if (error == 0) single_step_execve(); @@ -615,13 +615,13 @@ long compat_sys_execve(const char __user *path, struct pt_regs *regs) { long error; - char *filename; + struct getname_info *filename; filename = getname(path); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = compat_do_execve(filename, argv, envp, regs); + error = compat_do_execve(filename->name, argv, envp, regs); putname(filename); if (error == 0) single_step_execve(); diff --git a/arch/unicore32/kernel/sys.c b/arch/unicore32/kernel/sys.c index 5fd9af7..7a0c372 100644 --- a/arch/unicore32/kernel/sys.c +++ b/arch/unicore32/kernel/sys.c @@ -51,13 +51,13 @@ asmlinkage long __sys_execve(const char __user *filename, struct pt_regs *regs) { int error; - char *fn; + struct getname_info *fn; fn = getname(filename); error = PTR_ERR(fn); if (IS_ERR(fn)) goto out; - error = do_execve(fn, argv, envp, regs); + error = do_execve(fn->name, argv, envp, regs); putname(fn); out: return error; diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index 2c8d6a3..03d723d 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -325,13 +325,13 @@ long xtensa_execve(const char __user *name, struct pt_regs *regs) { long error; - char * filename; + struct getname_info *filename; filename = getname(name); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, argv, envp, regs); + error = do_execve(filename->name, argv, envp, regs); putname(filename); out: return error; diff --git a/fs/compat.c b/fs/compat.c index 1bdb350..224f726 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -776,16 +776,16 @@ asmlinkage long compat_sys_mount(const char __user * dev_name, char *kernel_type; unsigned long data_page; char *kernel_dev; - char *dir_page; + struct getname_info *dir; int retval; retval = copy_mount_string(type, &kernel_type); if (retval < 0) goto out; - dir_page = getname(dir_name); - retval = PTR_ERR(dir_page); - if (IS_ERR(dir_page)) + dir = getname(dir_name); + retval = PTR_ERR(dir); + if (IS_ERR(dir)) goto out1; retval = copy_mount_string(dev_name, &kernel_dev); @@ -807,7 +807,7 @@ asmlinkage long compat_sys_mount(const char __user * dev_name, } } - retval = do_mount(kernel_dev, dir_page, kernel_type, + retval = do_mount(kernel_dev, dir->name, kernel_type, flags, (void*)data_page); out4: @@ -815,7 +815,7 @@ asmlinkage long compat_sys_mount(const char __user * dev_name, out3: kfree(kernel_dev); out2: - putname(dir_page); + putname(dir); out1: kfree(kernel_type); out: diff --git a/fs/exec.c b/fs/exec.c index 50a1270..222e282 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -115,7 +115,7 @@ static inline void put_binfmt(struct linux_binfmt * fmt) SYSCALL_DEFINE1(uselib, const char __user *, library) { struct file *file; - char *tmp = getname(library); + struct getname_info *tmp = getname(library); int error = PTR_ERR(tmp); static const struct open_flags uselib_flags = { .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, @@ -126,7 +126,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library) if (IS_ERR(tmp)) goto out; - file = do_filp_open(AT_FDCWD, tmp, &uselib_flags, LOOKUP_FOLLOW); + file = do_filp_open(AT_FDCWD, tmp->name, &uselib_flags, LOOKUP_FOLLOW); putname(tmp); error = PTR_ERR(file); if (IS_ERR(file)) @@ -2325,10 +2325,10 @@ SYSCALL_DEFINE3(execve, const char __user *const __user *, argv, const char __user *const __user *, envp) { - const char *path = getname(filename); + struct getname_info *path = getname(filename); int error = PTR_ERR(path); if (!IS_ERR(path)) { - error = do_execve(path, argv, envp, current_pt_regs()); + error = do_execve(path->name, argv, envp, current_pt_regs()); putname(path); } return error; @@ -2338,10 +2338,11 @@ asmlinkage long compat_sys_execve(const char __user * filename, const compat_uptr_t __user * argv, const compat_uptr_t __user * envp) { - const char *path = getname(filename); + struct getname_info *path = getname(filename); int error = PTR_ERR(path); if (!IS_ERR(path)) { - error = compat_do_execve(path, argv, envp, current_pt_regs()); + error = compat_do_execve(path->name, argv, envp, + current_pt_regs()); putname(path); } return error; diff --git a/fs/filesystems.c b/fs/filesystems.c index 96f2428..9f4d31a 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -124,7 +124,7 @@ EXPORT_SYMBOL(unregister_filesystem); static int fs_index(const char __user * __name) { struct file_system_type * tmp; - char * name; + struct getname_info *name; int err, index; name = getname(__name); @@ -135,7 +135,7 @@ static int fs_index(const char __user * __name) err = -EINVAL; read_lock(&file_systems_lock); for (tmp=file_systems, index=0 ; tmp ; tmp=tmp->next, index++) { - if (strcmp(tmp->name,name) == 0) { + if (strcmp(tmp->name, name->name) == 0) { err = index; break; } diff --git a/fs/namei.c b/fs/namei.c index 64f7350..60db390 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -117,18 +117,37 @@ * POSIX.1 2.4: an empty pathname is invalid (ENOENT). * PATH_MAX includes the nul terminator --RR. */ -static char *getname_flags(const char __user *filename, int flags, int *empty) +void final_putname(struct getname_info *ginfo) { - char *result = __getname(), *err; + __putname(ginfo->name); + kfree(ginfo); +} + +static struct getname_info * +getname_flags(const char __user *filename, int flags, int *empty) +{ + struct getname_info *result, *err; + char *kname; int len; + /* FIXME: create dedicated slabcache? */ + result = kzalloc(sizeof(*result), GFP_KERNEL); if (unlikely(!result)) return ERR_PTR(-ENOMEM); - len = strncpy_from_user(result, filename, PATH_MAX); - err = ERR_PTR(len); - if (unlikely(len < 0)) + kname = __getname(); + if (unlikely(!kname)) { + err = ERR_PTR(-ENOMEM); + goto error_free_ginfo; + } + + result->name = kname; + result->uptr = filename; + len = strncpy_from_user(kname, filename, PATH_MAX); + if (unlikely(len < 0)) { + err = ERR_PTR(len); goto error; + } /* The empty path is special. */ if (unlikely(!len)) { @@ -146,25 +165,28 @@ static char *getname_flags(const char __user *filename, int flags, int *empty) } error: - __putname(result); + __putname(kname); +error_free_ginfo: + kfree(result); return err; } -char *getname(const char __user * filename) +struct getname_info * +getname(const char __user * filename) { return getname_flags(filename, 0, NULL); } +EXPORT_SYMBOL(getname); -#ifdef CONFIG_AUDITSYSCALL -void putname(const char *name) +void putname(struct getname_info *ginfo) { +#ifdef CONFIG_AUDITSYSCALL if (unlikely(!audit_dummy_context())) - audit_putname(name); - else - __putname(name); + return audit_putname(ginfo); +#endif + final_putname(ginfo); } EXPORT_SYMBOL(putname); -#endif static int check_acl(struct inode *inode, int mask) { @@ -2098,13 +2120,13 @@ int user_path_at_empty(int dfd, const char __user *name, unsigned flags, struct path *path, int *empty) { struct nameidata nd; - char *tmp = getname_flags(name, flags, empty); + struct getname_info *tmp = getname_flags(name, flags, empty); int err = PTR_ERR(tmp); if (!IS_ERR(tmp)) { BUG_ON(flags & LOOKUP_PARENT); - err = do_path_lookup(dfd, tmp, flags, &nd); + err = do_path_lookup(dfd, tmp->name, flags, &nd); putname(tmp); if (!err) *path = nd.path; @@ -2118,22 +2140,22 @@ int user_path_at(int dfd, const char __user *name, unsigned flags, return user_path_at_empty(dfd, name, flags, path, NULL); } -static int user_path_parent(int dfd, const char __user *path, - struct nameidata *nd, char **name) +static struct getname_info * +user_path_parent(int dfd, const char __user *path, struct nameidata *nd) { - char *s = getname(path); + struct getname_info *s = getname(path); int error; if (IS_ERR(s)) - return PTR_ERR(s); + return s; - error = do_path_lookup(dfd, s, LOOKUP_PARENT, nd); - if (error) + error = do_path_lookup(dfd, s->name, LOOKUP_PARENT, nd); + if (error) { putname(s); - else - *name = s; + return ERR_PTR(error); + } - return error; + return s; } /* @@ -3044,11 +3066,11 @@ EXPORT_SYMBOL(done_path_create); struct dentry *user_path_create(int dfd, const char __user *pathname, struct path *path, int is_dir) { - char *tmp = getname(pathname); + struct getname_info *tmp = getname(pathname); struct dentry *res; if (IS_ERR(tmp)) return ERR_CAST(tmp); - res = kern_path_create(dfd, tmp, path, is_dir); + res = kern_path_create(dfd, tmp->name, path, is_dir); putname(tmp); return res; } @@ -3253,13 +3275,13 @@ out: static long do_rmdir(int dfd, const char __user *pathname) { int error = 0; - char * name; + struct getname_info *name; struct dentry *dentry; struct nameidata nd; - error = user_path_parent(dfd, pathname, &nd, &name); - if (error) - return error; + name = user_path_parent(dfd, pathname, &nd); + if (IS_ERR(name)) + return PTR_ERR(name); switch(nd.last_type) { case LAST_DOTDOT: @@ -3348,14 +3370,14 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry) static long do_unlinkat(int dfd, const char __user *pathname) { int error; - char *name; + struct getname_info *name; struct dentry *dentry; struct nameidata nd; struct inode *inode = NULL; - error = user_path_parent(dfd, pathname, &nd, &name); - if (error) - return error; + name = user_path_parent(dfd, pathname, &nd); + if (IS_ERR(name)) + return PTR_ERR(name); error = -EISDIR; if (nd.last_type != LAST_NORM) @@ -3439,7 +3461,7 @@ SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, int, newdfd, const char __user *, newname) { int error; - char *from; + struct getname_info *from; struct dentry *dentry; struct path path; @@ -3452,9 +3474,9 @@ SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, if (IS_ERR(dentry)) goto out_putname; - error = security_path_symlink(&path, dentry, from); + error = security_path_symlink(&path, dentry, from->name); if (!error) - error = vfs_symlink(path.dentry->d_inode, dentry, from); + error = vfs_symlink(path.dentry->d_inode, dentry, from->name); done_path_create(&path, dentry); out_putname: putname(from); @@ -3734,17 +3756,21 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, struct dentry *old_dentry, *new_dentry; struct dentry *trap; struct nameidata oldnd, newnd; - char *from; - char *to; + struct getname_info *from; + struct getname_info *to; int error; - error = user_path_parent(olddfd, oldname, &oldnd, &from); - if (error) + from = user_path_parent(olddfd, oldname, &oldnd); + if (IS_ERR(from)) { + error = PTR_ERR(from); goto exit; + } - error = user_path_parent(newdfd, newname, &newnd, &to); - if (error) + to = user_path_parent(newdfd, newname, &newnd); + if (IS_ERR(to)) { + error = PTR_ERR(to); goto exit1; + } error = -EXDEV; if (oldnd.path.mnt != newnd.path.mnt) @@ -3968,7 +3994,6 @@ EXPORT_SYMBOL(follow_down_one); EXPORT_SYMBOL(follow_down); EXPORT_SYMBOL(follow_up); EXPORT_SYMBOL(get_write_access); /* binfmt_aout */ -EXPORT_SYMBOL(getname); EXPORT_SYMBOL(lock_rename); EXPORT_SYMBOL(lookup_one_len); EXPORT_SYMBOL(page_follow_link_light); diff --git a/fs/namespace.c b/fs/namespace.c index 8e52b1c..7dfe6ac 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2402,7 +2402,7 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, { int ret; char *kernel_type; - char *kernel_dir; + struct getname_info *kernel_dir; char *kernel_dev; unsigned long data_page; @@ -2424,7 +2424,7 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, if (ret < 0) goto out_data; - ret = do_mount(kernel_dev, kernel_dir, kernel_type, flags, + ret = do_mount(kernel_dev, kernel_dir->name, kernel_type, flags, (void *) data_page); free_page(data_page); diff --git a/fs/open.c b/fs/open.c index ec06921..3796d0c 100644 --- a/fs/open.c +++ b/fs/open.c @@ -945,13 +945,13 @@ long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode) { struct open_flags op; int lookup = build_open_flags(flags, mode, &op); - char *tmp = getname(filename); + struct getname_info *tmp = getname(filename); int fd = PTR_ERR(tmp); if (!IS_ERR(tmp)) { fd = get_unused_fd_flags(flags); if (fd >= 0) { - struct file *f = do_filp_open(dfd, tmp, &op, lookup); + struct file *f = do_filp_open(dfd, tmp->name, &op, lookup); if (IS_ERR(f)) { put_unused_fd(fd); fd = PTR_ERR(f); diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 6f15578..1cf3f2a 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -315,11 +315,11 @@ static struct super_block *quotactl_block(const char __user *special, int cmd) #ifdef CONFIG_BLOCK struct block_device *bdev; struct super_block *sb; - char *tmp = getname(special); + struct getname_info *tmp = getname(special); if (IS_ERR(tmp)) return ERR_CAST(tmp); - bdev = lookup_bdev(tmp); + bdev = lookup_bdev(tmp->name); putname(tmp); if (IS_ERR(bdev)) return ERR_CAST(bdev); diff --git a/include/linux/audit.h b/include/linux/audit.h index 0f7284a..d361921 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -459,6 +459,8 @@ extern int audit_classify_arch(int arch); #define AUDIT_TYPE_CHILD_CREATE 4 /* a child being created */ #ifdef CONFIG_AUDITSYSCALL +struct getname_info; + /* These are defined in auditsc.c */ /* Public API */ extern int audit_alloc(struct task_struct *task); @@ -467,8 +469,8 @@ extern void __audit_syscall_entry(int arch, int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3); extern void __audit_syscall_exit(int ret_success, long ret_value); -extern void __audit_getname(const char *name); -extern void audit_putname(const char *name); +extern void __audit_getname(struct getname_info *ginfo); +extern void audit_putname(struct getname_info *ginfo); extern void __audit_inode(const char *name, const struct dentry *dentry, unsigned int parent); extern void __audit_inode_child(const struct inode *parent, @@ -503,7 +505,7 @@ static inline void audit_syscall_exit(void *pt_regs) __audit_syscall_exit(success, return_code); } } -static inline void audit_getname(const char *name) +static inline void audit_getname(struct getname_info *name) { if (unlikely(!audit_dummy_context())) __audit_getname(name); diff --git a/include/linux/fs.h b/include/linux/fs.h index b6ce6fc..1b0d0fb 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2189,6 +2189,10 @@ static inline int break_lease(struct inode *inode, unsigned int mode) #endif /* CONFIG_FILE_LOCKING */ /* fs/open.c */ +struct getname_info { + const char *name; /* pointer to actual string */ + const __user char *uptr; /* original userland pointer */ +}; extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); @@ -2201,7 +2205,9 @@ extern struct file *file_open_root(struct dentry *, struct vfsmount *, const char *, int); extern struct file * dentry_open(const struct path *, int, const struct cred *); extern int filp_close(struct file *, fl_owner_t id); -extern char * getname(const char __user *); + +extern struct getname_info *getname(const char __user *); + enum { FILE_CREATED = 1, FILE_OPENED = 2 @@ -2221,12 +2227,14 @@ extern void __init vfs_caches_init(unsigned long); extern struct kmem_cache *names_cachep; +extern void final_putname(struct getname_info *ginfo); + #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) #ifndef CONFIG_AUDITSYSCALL -#define putname(name) __putname(name) +#define putname(name) final_putname(name) #else -extern void putname(const char *name); +extern void putname(struct getname_info *ginfo); #endif #ifdef CONFIG_BLOCK diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 69cb5fe..2071a27 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -773,7 +773,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode, { struct path path; struct file *filp; - char *name; + struct getname_info *name; struct mq_attr attr; int fd, error; struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns; @@ -796,7 +796,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode, ro = mnt_want_write(mnt); /* we'll drop it in any case */ error = 0; mutex_lock(&root->d_inode->i_mutex); - path.dentry = lookup_one_len(name, root, strlen(name)); + path.dentry = lookup_one_len(name->name, root, strlen(name->name)); if (IS_ERR(path.dentry)) { error = PTR_ERR(path.dentry); goto out_putfd; @@ -805,7 +805,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode, if (oflag & O_CREAT) { if (path.dentry->d_inode) { /* entry already exists */ - audit_inode(name, path.dentry, 0); + audit_inode(name->name, path.dentry, 0); if (oflag & O_EXCL) { error = -EEXIST; goto out; @@ -825,7 +825,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode, error = -ENOENT; goto out; } - audit_inode(name, path.dentry, 0); + audit_inode(name->name, path.dentry, 0); filp = do_open(&path, oflag); } @@ -850,7 +850,7 @@ out_putname: SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) { int err; - char *name; + struct getname_info *name; struct dentry *dentry; struct inode *inode = NULL; struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns; @@ -864,7 +864,8 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) if (err) goto out_name; mutex_lock_nested(&mnt->mnt_root->d_inode->i_mutex, I_MUTEX_PARENT); - dentry = lookup_one_len(name, mnt->mnt_root, strlen(name)); + dentry = lookup_one_len(name->name, mnt->mnt_root, + strlen(name->name)); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); goto out_unlock; diff --git a/kernel/acct.c b/kernel/acct.c index e97d159..3943608 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -260,10 +260,10 @@ SYSCALL_DEFINE1(acct, const char __user *, name) return -EPERM; if (name) { - char *tmp = getname(name); + struct getname_info *tmp = getname(name); if (IS_ERR(tmp)) return (PTR_ERR(tmp)); - error = acct_on(tmp); + error = acct_on(tmp->name); putname(tmp); } else { struct bsd_acct_struct *acct; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 2f20b97..0ba346b 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -103,28 +103,29 @@ struct audit_cap_data { * we don't let putname() free it (instead we free all of the saved * pointers at syscall exit time). * - * Further, in fs/namei.c:path_lookup() we store the inode and device. */ + * Further, in fs/namei.c:path_lookup() we store the inode and device. + */ struct audit_names { - struct list_head list; /* audit_context->names_list */ - const char *name; - unsigned long ino; - dev_t dev; - umode_t mode; - uid_t uid; - gid_t gid; - dev_t rdev; - u32 osid; - struct audit_cap_data fcap; - unsigned int fcap_ver; - int name_len; /* number of name's characters to log */ - unsigned char type; /* record type */ - bool name_put; /* call __putname() for this name */ + struct list_head list; /* audit_context->names_list */ + struct getname_info *ginfo; + unsigned long ino; + dev_t dev; + umode_t mode; + uid_t uid; + gid_t gid; + dev_t rdev; + u32 osid; + struct audit_cap_data fcap; + unsigned int fcap_ver; + int name_len; /* nr of characters to log */ + unsigned char type; /* record type */ + bool name_put; /* call final_putname() */ /* * This was an allocated audit_names and not from the array of * names allocated in the task audit context. Thus this name * should be freed on syscall exit */ - bool should_free; + bool should_free; }; struct audit_aux_data { @@ -1004,7 +1005,7 @@ static inline void audit_free_names(struct audit_context *context) context->ino_count); list_for_each_entry(n, &context->names_list, list) { printk(KERN_ERR "names[%d] = %p = %s\n", i, - n->name, n->name ?: "(null)"); + n->ginfo, n->ginfo->name ?: "(null)"); } dump_stack(); return; @@ -1017,8 +1018,8 @@ static inline void audit_free_names(struct audit_context *context) list_for_each_entry_safe(n, next, &context->names_list, list) { list_del(&n->list); - if (n->name && n->name_put) - __putname(n->name); + if (n->ginfo && n->name_put) + __putname(n->ginfo); if (n->should_free) kfree(n); } @@ -1529,12 +1530,12 @@ static void audit_log_name(struct audit_context *context, struct audit_names *n, audit_log_format(ab, "item=%d", record_num); - if (n->name) { + if (n->ginfo) { switch (n->name_len) { case AUDIT_NAME_FULL: /* log the full path */ audit_log_format(ab, " name="); - audit_log_untrustedstring(ab, n->name); + audit_log_untrustedstring(ab, n->ginfo->name); break; case 0: /* name was specified as a relative path and the @@ -1544,7 +1545,7 @@ static void audit_log_name(struct audit_context *context, struct audit_names *n, default: /* log the name's directory component */ audit_log_format(ab, " name="); - audit_log_n_untrustedstring(ab, n->name, + audit_log_n_untrustedstring(ab, n->ginfo->name, n->name_len); } } else @@ -2040,7 +2041,7 @@ static struct audit_names *audit_alloc_name(struct audit_context *context, * Add a name to the list of audit names for this context. * Called from fs/namei.c:getname(). */ -void __audit_getname(const char *name) +void __audit_getname(struct getname_info *ginfo) { struct audit_context *context = current->audit_context; struct audit_names *n; @@ -2048,17 +2049,22 @@ void __audit_getname(const char *name) if (!context->in_syscall) { #if AUDIT_DEBUG == 2 printk(KERN_ERR "%s:%d(:%d): ignoring getname(%p)\n", - __FILE__, __LINE__, context->serial, name); + __FILE__, __LINE__, context->serial, ginfo); dump_stack(); #endif return; } +#if AUDIT_DEBUG + /* The getname_info _must_ have a populated ->name */ + BUG_ON(!ginfo->name); +#endif + n = audit_alloc_name(context, AUDIT_TYPE_UNKNOWN); if (!n) return; - n->name = name; + n->ginfo = ginfo; n->name_len = AUDIT_NAME_FULL; n->name_put = true; @@ -2073,7 +2079,7 @@ void __audit_getname(const char *name) * then we delay the putname until syscall exit. * Called from include/linux/fs.h:putname(). */ -void audit_putname(const char *name) +void audit_putname(struct getname_info *ginfo) { struct audit_context *context = current->audit_context; @@ -2081,17 +2087,17 @@ void audit_putname(const char *name) if (!context->in_syscall) { #if AUDIT_DEBUG == 2 printk(KERN_ERR "%s:%d(:%d): __putname(%p)\n", - __FILE__, __LINE__, context->serial, name); + __FILE__, __LINE__, context->serial, ginfo); if (context->name_count) { struct audit_names *n; int i; list_for_each_entry(n, &context->names_list, list) printk(KERN_ERR "name[%d] = %p = %s\n", i, - n->name, n->name ?: "(null)"); + n->ginfo, n->ginfo->name ?: "(null)"); } #endif - __putname(name); + __putname(ginfo); } #if AUDIT_DEBUG else { @@ -2102,8 +2108,8 @@ void audit_putname(const char *name) " put_count=%d\n", __FILE__, __LINE__, context->serial, context->major, - context->in_syscall, name, context->name_count, - context->put_count); + context->in_syscall, ginfo->name, + context->name_count, context->put_count); dump_stack(); } } @@ -2166,7 +2172,7 @@ void __audit_inode(const char *name, const struct dentry *dentry, list_for_each_entry_reverse(n, &context->names_list, list) { /* does the name pointer match? */ - if (n->name != name) + if (!n->ginfo || n->ginfo->name != name) continue; /* match the correct record type */ @@ -2189,7 +2195,7 @@ out_alloc: return; out: if (parent) { - n->name_len = n->name ? parent_len(n->name) : AUDIT_NAME_FULL; + n->name_len = n->ginfo ? parent_len(n->ginfo->name) : AUDIT_NAME_FULL; n->type = AUDIT_TYPE_PARENT; } else { n->name_len = AUDIT_NAME_FULL; @@ -2230,11 +2236,11 @@ void __audit_inode_child(const struct inode *parent, /* look for a parent entry first */ list_for_each_entry(n, &context->names_list, list) { - if (!n->name || n->type != AUDIT_TYPE_PARENT) + if (!n->ginfo || n->type != AUDIT_TYPE_PARENT) continue; if (n->ino == parent->i_ino && - !audit_compare_dname_path(dname, n->name, n->name_len)) { + !audit_compare_dname_path(dname, n->ginfo->name, n->name_len)) { found_parent = n; break; } @@ -2243,15 +2249,15 @@ void __audit_inode_child(const struct inode *parent, /* is there a matching child entry? */ list_for_each_entry(n, &context->names_list, list) { /* can only match entries that have a name */ - if (!n->name || n->type != type) + if (!n->ginfo || n->type != type) continue; /* if we found a parent, make sure this one is a child of it */ - if (found_parent && (n->name != found_parent->name)) + if (found_parent && (n->ginfo != found_parent->ginfo)) continue; - if (!strcmp(dname, n->name) || - !audit_compare_dname_path(dname, n->name, + if (!strcmp(dname, n->ginfo->name) || + !audit_compare_dname_path(dname, n->ginfo->name, found_parent ? found_parent->name_len : AUDIT_NAME_FULL)) { @@ -2277,7 +2283,7 @@ void __audit_inode_child(const struct inode *parent, * directory. All names for this context are relinquished in * audit_free_names() */ if (found_parent) { - found_child->name = found_parent->name; + found_child->ginfo = found_parent->ginfo; found_child->name_len = AUDIT_NAME_FULL; /* don't call __putname() */ found_child->name_put = false; diff --git a/mm/swapfile.c b/mm/swapfile.c index 14e254c..8dbf46d 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1483,7 +1483,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; - char *pathname; + struct getname_info *pathname; int oom_score_adj; int i, type, prev; int err; @@ -1498,8 +1498,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) if (IS_ERR(pathname)) goto out; - victim = filp_open(pathname, O_RDWR|O_LARGEFILE, 0); - putname(pathname); + victim = filp_open(pathname->name, O_RDWR|O_LARGEFILE, 0); err = PTR_ERR(victim); if (IS_ERR(victim)) goto out; @@ -1936,7 +1935,7 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *p; - char *name; + struct getname_info *name; struct file *swap_file = NULL; struct address_space *mapping; int i; @@ -1967,7 +1966,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) name = NULL; goto bad_swap; } - swap_file = filp_open(name, O_RDWR|O_LARGEFILE, 0); + swap_file = filp_open(name->name, O_RDWR|O_LARGEFILE, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; @@ -2053,7 +2052,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) printk(KERN_INFO "Adding %uk swap on %s. " "Priority:%d extents:%d across:%lluk %s%s%s\n", - p->pages<<(PAGE_SHIFT-10), name, p->prio, + p->pages<<(PAGE_SHIFT-10), name->name, p->prio, nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10), (p->flags & SWP_SOLIDSTATE) ? "SS" : "", (p->flags & SWP_DISCARDABLE) ? "D" : "", -- 1.7.11.4

...and make the user_path callers use that variant instead. Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/namei.c | 30 +++++++++++++++++++++++------- 1 file changed, 23 insertions(+), 7 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index 01a2dd18..5e31fbb 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1993,20 +1993,30 @@ static int path_lookupat(int dfd, const char *name, return err; } -static int do_path_lookup(int dfd, const char *name, +static int ginfo_lookup(int dfd, struct getname_info *ginfo, unsigned int flags, struct nameidata *nd) { - int retval = path_lookupat(dfd, name, flags | LOOKUP_RCU, nd); + int retval = path_lookupat(dfd, ginfo->name, flags | LOOKUP_RCU, nd); if (unlikely(retval == -ECHILD)) - retval = path_lookupat(dfd, name, flags, nd); + retval = path_lookupat(dfd, ginfo->name, flags, nd); if (unlikely(retval == -ESTALE)) - retval = path_lookupat(dfd, name, flags | LOOKUP_REVAL, nd); + retval = path_lookupat(dfd, ginfo->name, + flags | LOOKUP_REVAL, nd); if (likely(!retval)) - audit_inode(name, nd->path.dentry, flags & LOOKUP_PARENT); + audit_inode(ginfo->name, nd->path.dentry, + flags & LOOKUP_PARENT); return retval; } +static int do_path_lookup(int dfd, const char *name, + unsigned int flags, struct nameidata *nd) +{ + struct getname_info ginfo = { .name = name }; + + return ginfo_lookup(dfd, &ginfo, flags, nd); +} + /* does lookup, returns the object with parent locked */ struct dentry *kern_path_locked(const char *name, struct path *path) { @@ -2130,7 +2140,7 @@ int user_path_at_empty(int dfd, const char __user *name, unsigned flags, BUG_ON(flags & LOOKUP_PARENT); - err = do_path_lookup(dfd, tmp->name, flags, &nd); + err = ginfo_lookup(dfd, tmp, flags, &nd); putname(tmp); if (!err) *path = nd.path; @@ -2144,6 +2154,12 @@ int user_path_at(int dfd, const char __user *name, unsigned flags, return user_path_at_empty(dfd, name, flags, path, NULL); } +/* + * NB: most callers don't do anything directly with the reference to the + * to ginfo, but the nd->last pointer points into the name string + * allocated by getname. So we must hold the reference to it until all + * path-walking is complete. + */ static struct getname_info * user_path_parent(int dfd, const char __user *path, struct nameidata *nd) { @@ -2153,7 +2169,7 @@ user_path_parent(int dfd, const char __user *path, struct nameidata *nd) if (IS_ERR(s)) return s; - error = do_path_lookup(dfd, s->name, LOOKUP_PARENT, nd); + error = ginfo_lookup(dfd, s, LOOKUP_PARENT, nd); if (error) { putname(s); return ERR_PTR(error); -- 1.7.11.4

Keep a pointer to the audit_names "slot" in getname_info. Have all of the audit_inode callers pass a getname_info ponter to audit_inode instead of a string pointer. If the aname field is already populated, then we can skip walking the list altogether and just use it directly. Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/namei.c | 16 +++++++--------- include/linux/audit.h | 10 +++++----- include/linux/fs.h | 6 ++++-- ipc/mqueue.c | 4 ++-- kernel/auditsc.c | 29 +++++++++++++++++++++++++---- 5 files changed, 43 insertions(+), 22 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index 048373c..5e2f5ae 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2004,8 +2004,7 @@ static int ginfo_lookup(int dfd, struct getname_info *ginfo, flags | LOOKUP_REVAL, nd); if (likely(!retval)) - audit_inode(ginfo->name, nd->path.dentry, - flags & LOOKUP_PARENT); + audit_inode(ginfo, nd->path.dentry, flags & LOOKUP_PARENT); return retval; } @@ -2679,7 +2678,6 @@ static int do_last(struct nameidata *nd, struct path *path, struct path save_parent = { .dentry = NULL, .mnt = NULL }; bool retried = false; int error; - const char *pathname = ginfo->name; nd->flags &= ~LOOKUP_PARENT; nd->flags |= op->intent; @@ -2695,7 +2693,7 @@ static int do_last(struct nameidata *nd, struct path *path, error = complete_walk(nd); if (error) return error; - audit_inode(pathname, nd->path.dentry, 0); + audit_inode(ginfo, nd->path.dentry, 0); if (open_flag & O_CREAT) { error = -EISDIR; goto out; @@ -2705,7 +2703,7 @@ static int do_last(struct nameidata *nd, struct path *path, error = complete_walk(nd); if (error) return error; - audit_inode(pathname, dir, 0); + audit_inode(ginfo, dir, 0); goto finish_open; } @@ -2734,7 +2732,7 @@ static int do_last(struct nameidata *nd, struct path *path, if (error) return error; - audit_inode(pathname, dir, 0); + audit_inode(ginfo, dir, 0); error = -EISDIR; /* trailing slashes? */ if (nd->last.name[nd->last.len]) @@ -2764,7 +2762,7 @@ retry_lookup: !S_ISREG(file->f_path.dentry->d_inode->i_mode)) will_truncate = false; - audit_inode(pathname, file->f_path.dentry, 0); + audit_inode(ginfo, file->f_path.dentry, 0); goto opened; } @@ -2781,7 +2779,7 @@ retry_lookup: * create/update audit record if it already exists. */ if (path->dentry->d_inode) - audit_inode(pathname, path->dentry, 0); + audit_inode(ginfo, path->dentry, 0); /* * If atomic_open() acquired write access it is dropped now due to @@ -2846,7 +2844,7 @@ finish_lookup: error = -ENOTDIR; if ((nd->flags & LOOKUP_DIRECTORY) && !nd->inode->i_op->lookup) goto out; - audit_inode(pathname, nd->path.dentry, 0); + audit_inode(ginfo, nd->path.dentry, 0); finish_open: if (!S_ISREG(nd->inode->i_mode)) will_truncate = false; diff --git a/include/linux/audit.h b/include/linux/audit.h index ea58de3..481cf75 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -472,7 +472,7 @@ extern void __audit_syscall_exit(int ret_success, long ret_value); extern struct getname_info *__audit_reusename(const __user char *uptr); extern void __audit_getname(struct getname_info *ginfo); extern void audit_putname(struct getname_info *ginfo); -extern void __audit_inode(const char *name, const struct dentry *dentry, +extern void __audit_inode(struct getname_info *ginfo, const struct dentry *dentry, unsigned int parent); extern void __audit_inode_child(const struct inode *parent, const struct dentry *dentry, @@ -517,10 +517,10 @@ static inline void audit_getname(struct getname_info *name) if (unlikely(!audit_dummy_context())) __audit_getname(name); } -static inline void audit_inode(const char *name, const struct dentry *dentry, +static inline void audit_inode(struct getname_info *ginfo, const struct dentry *dentry, unsigned int parent) { if (unlikely(!audit_dummy_context())) - __audit_inode(name, dentry, parent); + __audit_inode(ginfo, dentry, parent); } static inline void audit_inode_child(const struct inode *parent, const struct dentry *dentry, @@ -652,9 +652,9 @@ extern int audit_signals; #define audit_reusename(g) ({ NULL; }) #define audit_getname(n) do { ; } while (0) #define audit_putname(n) do { ; } while (0) -#define __audit_inode(n,d,p) do { ; } while (0) +#define __audit_inode(g,d,p) do { ; } while (0) #define __audit_inode_child(p,d) do { ; } while (0) -#define audit_inode(n,d,p) do { ; } while (0) +#define audit_inode(g,d,p) do { ; } while (0) #define audit_inode_child(p,d,t) do { ; } while (0) #define audit_core_dumps(i) do { ; } while (0) #define audit_seccomp(i,s,c) do { ; } while (0) diff --git a/include/linux/fs.h b/include/linux/fs.h index a37b0c1..4ce38f2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2189,9 +2189,11 @@ static inline int break_lease(struct inode *inode, unsigned int mode) #endif /* CONFIG_FILE_LOCKING */ /* fs/open.c */ +struct audit_names; struct getname_info { - const char *name; /* pointer to actual string */ - const __user char *uptr; /* original userland pointer */ + const char *name; /* pointer to actual string */ + const __user char *uptr; /* original userland pointer */ + struct audit_names *aname; }; extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 2071a27..07d489e 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -805,7 +805,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode, if (oflag & O_CREAT) { if (path.dentry->d_inode) { /* entry already exists */ - audit_inode(name->name, path.dentry, 0); + audit_inode(name, path.dentry, 0); if (oflag & O_EXCL) { error = -EEXIST; goto out; @@ -825,7 +825,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode, error = -ENOENT; goto out; } - audit_inode(name->name, path.dentry, 0); + audit_inode(name, path.dentry, 0); filp = do_open(&path, oflag); } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 89974ca..92ef854 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -2090,6 +2090,7 @@ void __audit_getname(struct getname_info *ginfo) n->ginfo = ginfo; n->name_len = AUDIT_NAME_FULL; n->name_put = true; + ginfo->aname = n; if (!context->pwd.dentry) get_fs_pwd(current->fs, &context->pwd); @@ -2176,11 +2177,11 @@ static void audit_copy_inode(struct audit_names *name, const struct dentry *dent /** * __audit_inode - store the inode and device from a lookup - * @name: name being audited + * @ginfo: getname_info for name being audited * @dentry: dentry being audited * @parent: does this dentry represent the parent? */ -void __audit_inode(const char *name, const struct dentry *dentry, +void __audit_inode(struct getname_info *ginfo, const struct dentry *dentry, unsigned int parent) { struct audit_context *context = current->audit_context; @@ -2190,12 +2191,32 @@ void __audit_inode(const char *name, const struct dentry *dentry, if (!context->in_syscall) return; - if (!name) + if (!ginfo) goto out_alloc; +#if AUDIT_DEBUG + /* The getname_info _must_ have a populated ->name */ + BUG_ON(!ginfo->name); +#endif + /* + * If we have a pointer to an audit_names entry already, then we can + * just use it directly if the type is correct. + */ + n = ginfo->aname; + if (n) { + if (parent) { + if (n->type == AUDIT_TYPE_PARENT || + n->type == AUDIT_TYPE_UNKNOWN) + goto out; + } else { + if (n->type != AUDIT_TYPE_PARENT) + goto out; + } + } + list_for_each_entry_reverse(n, &context->names_list, list) { /* does the name pointer match? */ - if (!n->ginfo || n->ginfo->name != name) + if (!n->ginfo || n->ginfo->name != ginfo->name) continue; /* match the correct record type */ -- 1.7.11.4

I see no callers in module code. Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/namei.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index 48cb4aa..d3f8998 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -209,7 +209,6 @@ getname(const char __user * filename) { return getname_flags(filename, 0, NULL); } -EXPORT_SYMBOL(getname); void putname(struct getname_info *ginfo) { @@ -219,7 +218,6 @@ void putname(struct getname_info *ginfo) #endif final_putname(ginfo); } -EXPORT_SYMBOL(putname); static int check_acl(struct inode *inode, int mask) { -- 1.7.11.4

Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/stat.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/fs/stat.c b/fs/stat.c index 4078022..7f1602a 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -74,7 +74,8 @@ int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, { struct path path; int error = -EINVAL; - int lookup_flags = 0; + unsigned int try = 0; + unsigned int lookup_flags = 0; if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT | AT_EMPTY_PATH)) != 0) @@ -85,12 +86,15 @@ int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, if (flag & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; - error = user_path_at(dfd, filename, lookup_flags, &path); - if (error) - goto out; + do { + error = user_path_at(dfd, filename, lookup_flags, &path); + if (error) + break; - error = vfs_getattr(path.mnt, path.dentry, stat); - path_put(&path); + error = vfs_getattr(path.mnt, path.dentry, stat); + path_put(&path); + lookup_flags |= LOOKUP_REVAL; + } while (retry_estale(error, try++)); out: return error; } -- 1.7.11.4

...for now, all of the callers pass in "false". Eventually, we'll set that to "true" when we retry the lookup after getting back an ESTALE on a call. While we're at it, change the is_dir arg to a bool since that's how it's used currently. Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- arch/powerpc/platforms/cell/spufs/syscalls.c | 2 +- drivers/base/devtmpfs.c | 7 ++++--- fs/namei.c | 23 +++++++++++++++-------- fs/ocfs2/refcounttree.c | 3 ++- include/linux/namei.h | 4 ++-- net/unix/af_unix.c | 2 +- 6 files changed, 25 insertions(+), 16 deletions(-) diff --git a/arch/powerpc/platforms/cell/spufs/syscalls.c b/arch/powerpc/platforms/cell/spufs/syscalls.c index 5b7d8ff..cb4acc7 100644 --- a/arch/powerpc/platforms/cell/spufs/syscalls.c +++ b/arch/powerpc/platforms/cell/spufs/syscalls.c @@ -66,7 +66,7 @@ static long do_spu_create(const char __user *pathname, unsigned int flags, struct dentry *dentry; int ret; - dentry = user_path_create(AT_FDCWD, pathname, &path, 1); + dentry = user_path_create(AT_FDCWD, pathname, &path, true, false); ret = PTR_ERR(dentry); if (!IS_ERR(dentry)) { ret = spufs_create(&path, dentry, flags, mode, neighbor); diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index deb4a45..2124437 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -148,7 +148,7 @@ static int dev_mkdir(const char *name, umode_t mode) struct path path; int err; - dentry = kern_path_create(AT_FDCWD, name, &path, 1); + dentry = kern_path_create(AT_FDCWD, name, &path, true, false); if (IS_ERR(dentry)) return PTR_ERR(dentry); @@ -193,10 +193,11 @@ static int handle_create(const char *nodename, umode_t mode, struct device *dev) struct path path; int err; - dentry = kern_path_create(AT_FDCWD, nodename, &path, 0); + dentry = kern_path_create(AT_FDCWD, nodename, &path, false, false); if (dentry == ERR_PTR(-ENOENT)) { create_path(nodename); - dentry = kern_path_create(AT_FDCWD, nodename, &path, 0); + dentry = kern_path_create(AT_FDCWD, nodename, &path, + false, false); } if (IS_ERR(dentry)) return PTR_ERR(dentry); diff --git a/fs/namei.c b/fs/namei.c index d3f8998..6c75fc1 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3042,12 +3042,18 @@ struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt, return file; } -struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path, int is_dir) +struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path, bool is_dir, bool reval) { struct dentry *dentry = ERR_PTR(-EEXIST); struct nameidata nd; int err2; - int error = do_path_lookup(dfd, pathname, LOOKUP_PARENT, &nd); + int error; + unsigned int lookup_flags = LOOKUP_PARENT; + + if (reval) + lookup_flags |= LOOKUP_REVAL; + + error = do_path_lookup(dfd, pathname, lookup_flags, &nd); if (error) return ERR_PTR(error); @@ -3111,13 +3117,14 @@ void done_path_create(struct path *path, struct dentry *dentry) } EXPORT_SYMBOL(done_path_create); -struct dentry *user_path_create(int dfd, const char __user *pathname, struct path *path, int is_dir) +struct dentry *user_path_create(int dfd, const char __user *pathname, + struct path *path, bool is_dir, bool reval) { struct getname_info *tmp = getname(pathname); struct dentry *res; if (IS_ERR(tmp)) return ERR_CAST(tmp); - res = kern_path_create(dfd, tmp->name, path, is_dir); + res = kern_path_create(dfd, tmp->name, path, is_dir, reval); putname(tmp); return res; } @@ -3178,7 +3185,7 @@ SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, if (error) return error; - dentry = user_path_create(dfd, filename, &path, 0); + dentry = user_path_create(dfd, filename, &path, false, false); if (IS_ERR(dentry)) return PTR_ERR(dentry); @@ -3240,7 +3247,7 @@ SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode) struct path path; int error; - dentry = user_path_create(dfd, pathname, &path, 1); + dentry = user_path_create(dfd, pathname, &path, true, false); if (IS_ERR(dentry)) return PTR_ERR(dentry); @@ -3516,7 +3523,7 @@ SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, if (IS_ERR(from)) return PTR_ERR(from); - dentry = user_path_create(newdfd, newname, &path, 0); + dentry = user_path_create(newdfd, newname, &path, false, false); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_putname; @@ -3616,7 +3623,7 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, if (error) return error; - new_dentry = user_path_create(newdfd, newname, &new_path, 0); + new_dentry = user_path_create(newdfd, newname, &new_path, false, false); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) goto out; diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 30a0550..645e225 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4453,7 +4453,8 @@ int ocfs2_reflink_ioctl(struct inode *inode, return error; } - new_dentry = user_path_create(AT_FDCWD, newname, &new_path, 0); + new_dentry = user_path_create(AT_FDCWD, newname, &new_path, + false, false); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) { mlog_errno(error); diff --git a/include/linux/namei.h b/include/linux/namei.h index 4bf19d8..2202740 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -65,8 +65,8 @@ extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, extern int kern_path(const char *, unsigned, struct path *); -extern struct dentry *kern_path_create(int, const char *, struct path *, int); -extern struct dentry *user_path_create(int, const char __user *, struct path *, int); +extern struct dentry *kern_path_create(int, const char *, struct path *, bool, bool); +extern struct dentry *user_path_create(int, const char __user *, struct path *, bool, bool); extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); extern int vfs_path_lookup(struct dentry *, struct vfsmount *, diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index c5ee4ff..f15b0ff 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -832,7 +832,7 @@ static int unix_mknod(const char *sun_path, umode_t mode, struct path *res) * Get the parent directory, calculate the hash for last * component. */ - dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0); + dentry = kern_path_create(AT_FDCWD, sun_path, &path, false, false); err = PTR_ERR(dentry); if (IS_ERR(dentry)) return err; -- 1.7.11.4

Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/namei.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index ac62973..dd1d519 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3253,17 +3253,20 @@ SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode) struct dentry *dentry; struct path path; int error; + unsigned int try = 0; - dentry = user_path_create(dfd, pathname, &path, true, false); - if (IS_ERR(dentry)) - return PTR_ERR(dentry); + do { + dentry = user_path_create(dfd, pathname, &path, true, false); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); - if (!IS_POSIXACL(path.dentry->d_inode)) - mode &= ~current_umask(); - error = security_path_mkdir(&path, dentry, mode); - if (!error) - error = vfs_mkdir(path.dentry->d_inode, dentry, mode); - done_path_create(&path, dentry); + if (!IS_POSIXACL(path.dentry->d_inode)) + mode &= ~current_umask(); + error = security_path_mkdir(&path, dentry, mode); + if (!error) + error = vfs_mkdir(path.dentry->d_inode, dentry, mode); + done_path_create(&path, dentry); + } while (retry_estale(error, try++)); return error; } -- 1.7.11.4

Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/namei.c | 46 ++++++++++++++++++++++++++-------------------- 1 file changed, 26 insertions(+), 20 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index fb9d36f..e0ee4b9 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3616,6 +3616,7 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, struct path old_path, new_path; int how = 0; int error; + unsigned int try = 0; if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; @@ -3633,30 +3634,35 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, if (flags & AT_SYMLINK_FOLLOW) how |= LOOKUP_FOLLOW; - error = user_path_at(olddfd, oldname, how, &old_path); - if (error) - return error; + do { + error = user_path_at(olddfd, oldname, how, &old_path); + if (error) + break; - new_dentry = user_path_create(newdfd, newname, &new_path, false, false); - error = PTR_ERR(new_dentry); - if (IS_ERR(new_dentry)) - goto out; + new_dentry = user_path_create(newdfd, newname, &new_path, + false, false); + error = PTR_ERR(new_dentry); + if (IS_ERR(new_dentry)) + goto out; - error = -EXDEV; - if (old_path.mnt != new_path.mnt) - goto out_dput; - error = may_linkat(&old_path); - if (unlikely(error)) - goto out_dput; - error = security_path_link(old_path.dentry, &new_path, new_dentry); - if (error) - goto out_dput; - error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry); + error = -EXDEV; + if (old_path.mnt != new_path.mnt) + goto out_dput; + error = may_linkat(&old_path); + if (unlikely(error)) + goto out_dput; + error = security_path_link(old_path.dentry, &new_path, + new_dentry); + if (error) + goto out_dput; + error = vfs_link(old_path.dentry, new_path.dentry->d_inode, + new_dentry); out_dput: - done_path_create(&new_path, new_dentry); + done_path_create(&new_path, new_dentry); out: - path_put(&old_path); - + path_put(&old_path); + how |= LOOKUP_REVAL; + } while (retry_estale(error, try++)); return error; } -- 1.7.11.4

Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/namei.c | 81 ++++++++++++++++++++++++++++++++++---------------------------- 1 file changed, 44 insertions(+), 37 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index b73315d..0d0b1c0 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3347,49 +3347,56 @@ static long do_rmdir(int dfd, const char __user *pathname) struct getname_info *name; struct dentry *dentry; struct nameidata nd; + unsigned int try = 0; + unsigned int lookup_flags = LOOKUP_PARENT; - name = user_path_parent(dfd, pathname, &nd, 0); - if (IS_ERR(name)) - return PTR_ERR(name); - - switch(nd.last_type) { - case LAST_DOTDOT: - error = -ENOTEMPTY; - goto exit1; - case LAST_DOT: - error = -EINVAL; - goto exit1; - case LAST_ROOT: - error = -EBUSY; - goto exit1; - } + do { + name = user_path_parent(dfd, pathname, &nd, try); + if (IS_ERR(name)) + return PTR_ERR(name); + + switch (nd.last_type) { + case LAST_DOTDOT: + error = -ENOTEMPTY; + goto exit1; + case LAST_DOT: + error = -EINVAL; + goto exit1; + case LAST_ROOT: + error = -EBUSY; + goto exit1; + } - nd.flags &= ~LOOKUP_PARENT; - error = mnt_want_write(nd.path.mnt); - if (error) - goto exit1; + nd.flags &= ~LOOKUP_PARENT; + error = mnt_want_write(nd.path.mnt); + if (error) + goto exit1; - mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); - dentry = lookup_hash(&nd); - error = PTR_ERR(dentry); - if (IS_ERR(dentry)) - goto exit2; - if (!dentry->d_inode) { - error = -ENOENT; - goto exit3; - } - error = security_path_rmdir(&nd.path, dentry); - if (error) - goto exit3; - error = vfs_rmdir(nd.path.dentry->d_inode, dentry); + mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, + I_MUTEX_PARENT); + dentry = lookup_hash(&nd); + if (IS_ERR(dentry)) { + error = PTR_ERR(dentry); + goto exit2; + } + if (!dentry->d_inode) { + error = -ENOENT; + goto exit3; + } + error = security_path_rmdir(&nd.path, dentry); + if (error) + goto exit3; + error = vfs_rmdir(nd.path.dentry->d_inode, dentry); exit3: - dput(dentry); + dput(dentry); exit2: - mutex_unlock(&nd.path.dentry->d_inode->i_mutex); - mnt_drop_write(nd.path.mnt); + mutex_unlock(&nd.path.dentry->d_inode->i_mutex); + mnt_drop_write(nd.path.mnt); exit1: - path_put(&nd.path); - putname(name); + path_put(&nd.path); + lookup_flags |= LOOKUP_REVAL; + putname(name); + } while (retry_estale(error, try++)); return error; } -- 1.7.11.4

...as always, rename is the messiest of the bunch. We have to track whether to retry or not via a separate flag since the error handling is already quite complex. Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/namei.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index f311ed1..dfdcd47 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3851,15 +3851,18 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, struct nameidata oldnd, newnd; struct getname_info *from; struct getname_info *to; + unsigned int try = 0; + bool should_retry = false; int error; - from = user_path_parent(olddfd, oldname, &oldnd, 0); +retry: + from = user_path_parent(olddfd, oldname, &oldnd, try); if (IS_ERR(from)) { error = PTR_ERR(from); goto exit; } - to = user_path_parent(newdfd, newname, &newnd, 0); + to = user_path_parent(newdfd, newname, &newnd, try); if (IS_ERR(to)) { error = PTR_ERR(to); goto exit1; @@ -3931,11 +3934,17 @@ exit3: unlock_rename(new_dir, old_dir); mnt_drop_write(oldnd.path.mnt); exit2: + if (retry_estale(error, try++)) + should_retry = true; path_put(&newnd.path); putname(to); exit1: path_put(&oldnd.path); putname(from); + if (should_retry) { + should_retry = false; + goto retry; + } exit: return error; } -- 1.7.11.4

Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/open.c | 64 +++++++++++++++++++++++++++++++++------------------------------ 1 file changed, 34 insertions(+), 30 deletions(-) diff --git a/fs/open.c b/fs/open.c index 5dcee00..a5a5c9a 100644 --- a/fs/open.c +++ b/fs/open.c @@ -312,6 +312,8 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) struct path path; struct inode *inode; int res; + unsigned int lookup_flags = LOOKUP_FOLLOW; + unsigned int try = 0; if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */ return -EINVAL; @@ -335,42 +337,44 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) old_cred = override_creds(override_cred); - res = user_path_at(dfd, filename, LOOKUP_FOLLOW, &path); - if (res) - goto out; + do { + res = user_path_at(dfd, filename, lookup_flags, &path); + if (res) + break; - inode = path.dentry->d_inode; + inode = path.dentry->d_inode; + + if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) { + /* + * MAY_EXEC on regular files is denied if the fs is + * mounted with the "noexec" flag. + */ + res = -EACCES; + if (path.mnt->mnt_flags & MNT_NOEXEC) + goto out_path_release; + } - if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) { + res = inode_permission(inode, mode | MAY_ACCESS); + /* SuS v2 requires we report a read only fs too */ + if (res || !(mode & S_IWOTH) || special_file(inode->i_mode)) + goto out_path_release; /* - * MAY_EXEC on regular files is denied if the fs is mounted - * with the "noexec" flag. + * This is a rare case where using __mnt_is_readonly() + * is OK without a mnt_want/drop_write() pair. Since + * no actual write to the fs is performed here, we do + * not need to telegraph to that to anyone. + * + * By doing this, we accept that this access is + * inherently racy and know that the fs may change + * state before we even see this result. */ - res = -EACCES; - if (path.mnt->mnt_flags & MNT_NOEXEC) - goto out_path_release; - } - - res = inode_permission(inode, mode | MAY_ACCESS); - /* SuS v2 requires we report a read only fs too */ - if (res || !(mode & S_IWOTH) || special_file(inode->i_mode)) - goto out_path_release; - /* - * This is a rare case where using __mnt_is_readonly() - * is OK without a mnt_want/drop_write() pair. Since - * no actual write to the fs is performed here, we do - * not need to telegraph to that to anyone. - * - * By doing this, we accept that this access is - * inherently racy and know that the fs may change - * state before we even see this result. - */ - if (__mnt_is_readonly(path.mnt)) - res = -EROFS; + if (__mnt_is_readonly(path.mnt)) + res = -EROFS; out_path_release: - path_put(&path); -out: + path_put(&path); + lookup_flags |= LOOKUP_REVAL; + } while (retry_estale(res, try++)); revert_creds(old_cred); put_cred(override_cred); return res; -- 1.7.11.4

Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/open.c | 37 +++++++++++++++++++++---------------- 1 file changed, 21 insertions(+), 16 deletions(-) diff --git a/fs/open.c b/fs/open.c index 81ba325..a015cb8 100644 --- a/fs/open.c +++ b/fs/open.c @@ -437,27 +437,32 @@ SYSCALL_DEFINE1(chroot, const char __user *, filename) { struct path path; int error; + int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY; + unsigned int try = 0; - error = user_path_dir(filename, &path); - if (error) - goto out; + do { + error = user_path_at(AT_FDCWD, filename, lookup_flags, &path); + if (error) + break; - error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR); - if (error) - goto dput_and_out; + error = inode_permission(path.dentry->d_inode, + MAY_EXEC | MAY_CHDIR); + if (error) + goto dput_and_out; - error = -EPERM; - if (!capable(CAP_SYS_CHROOT)) - goto dput_and_out; - error = security_path_chroot(&path); - if (error) - goto dput_and_out; + error = -EPERM; + if (!capable(CAP_SYS_CHROOT)) + goto dput_and_out; + error = security_path_chroot(&path); + if (error) + goto dput_and_out; - set_fs_root(current->fs, &path); - error = 0; + set_fs_root(current->fs, &path); + error = 0; dput_and_out: - path_put(&path); -out: + path_put(&path); + lookup_flags |= LOOKUP_REVAL; + } while (retry_estale(error, try++)); return error; } -- 1.7.11.4

Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/open.c | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) diff --git a/fs/open.c b/fs/open.c index 232cbfb..1bdfd9a 100644 --- a/fs/open.c +++ b/fs/open.c @@ -567,24 +567,29 @@ SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user, struct path path; int error = -EINVAL; int lookup_flags; + unsigned int try = 0; if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) - goto out; + return error; lookup_flags = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; if (flag & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; - error = user_path_at(dfd, filename, lookup_flags, &path); - if (error) - goto out; - error = mnt_want_write(path.mnt); - if (error) - goto out_release; - error = chown_common(&path, user, group); - mnt_drop_write(path.mnt); -out_release: - path_put(&path); -out: + + do { + error = user_path_at(dfd, filename, lookup_flags, &path); + if (error) + break; + + error = mnt_want_write(path.mnt); + if (!error) { + error = chown_common(&path, user, group); + mnt_drop_write(path.mnt); + } + + path_put(&path); + lookup_flags |= LOOKUP_REVAL; + } while (retry_estale(error, try++)); return error; } -- 1.7.11.4

Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/namei.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/namei.c b/fs/namei.c index 8e39510..9a7736f 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3031,6 +3031,7 @@ struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt, struct nameidata nd; struct file *file; struct getname_info ginfo = { .name = name }; + unsigned int try = 0; nd.root.mnt = mnt; nd.root.dentry = dentry; @@ -3043,7 +3044,7 @@ struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt, file = path_openat(-1, &ginfo, &nd, op, flags | LOOKUP_RCU); if (unlikely(file == ERR_PTR(-ECHILD))) file = path_openat(-1, &ginfo, &nd, op, flags); - if (unlikely(file == ERR_PTR(-ESTALE))) + while (retry_estale(PTR_ERR(file), try++)) file = path_openat(-1, &ginfo, &nd, op, flags | LOOKUP_REVAL); return file; } -- 1.7.11.4

Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/xattr.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/fs/xattr.c b/fs/xattr.c index 588455b..ba286ba 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -364,16 +364,21 @@ SYSCALL_DEFINE5(setxattr, const char __user *, pathname, { struct path path; int error; + unsigned int try = 0; + unsigned int lookup_flags = LOOKUP_FOLLOW; - error = user_path(pathname, &path); - if (error) - return error; - error = mnt_want_write(path.mnt); - if (!error) { - error = setxattr(path.dentry, name, value, size, flags); - mnt_drop_write(path.mnt); - } - path_put(&path); + do { + error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); + if (error) + break; + error = mnt_want_write(path.mnt); + if (!error) { + error = setxattr(path.dentry, name, value, size, flags); + mnt_drop_write(path.mnt); + } + path_put(&path); + lookup_flags |= LOOKUP_REVAL; + } while (retry_estale(error, try++)); return error; } -- 1.7.11.4

Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/xattr.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/fs/xattr.c b/fs/xattr.c index d981635..1775213 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -479,12 +479,17 @@ SYSCALL_DEFINE4(getxattr, const char __user *, pathname, { struct path path; ssize_t error; + unsigned int try = 0; + unsigned int lookup_flags = LOOKUP_FOLLOW; - error = user_path(pathname, &path); - if (error) - return error; - error = getxattr(path.dentry, name, value, size); - path_put(&path); + do { + error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); + if (error) + break; + error = getxattr(path.dentry, name, value, size); + path_put(&path); + lookup_flags |= LOOKUP_REVAL; + } while (retry_estale(error, try++)); return error; } -- 1.7.11.4

Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/xattr.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/fs/xattr.c b/fs/xattr.c index fbb93d7..6be45cd 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -571,12 +571,17 @@ SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list, { struct path path; ssize_t error; + unsigned int try = 0; + unsigned int lookup_flags = LOOKUP_FOLLOW; - error = user_path(pathname, &path); - if (error) - return error; - error = listxattr(path.dentry, list, size); - path_put(&path); + do { + error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); + if (error) + break; + error = listxattr(path.dentry, list, size); + path_put(&path); + lookup_flags |= LOOKUP_REVAL; + } while (retry_estale(error, try++)); return error; } -- 1.7.11.4

Signed-off-by: Jeff Layton <jlayton(a)redhat.com&gt; --- fs/xattr.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/fs/xattr.c b/fs/xattr.c index db6c528..d29d5a4 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -642,16 +642,21 @@ SYSCALL_DEFINE2(removexattr, const char __user *, pathname, { struct path path; int error; + unsigned int try = 0; + unsigned int lookup_flags = LOOKUP_FOLLOW; - error = user_path(pathname, &path); - if (error) - return error; - error = mnt_want_write(path.mnt); - if (!error) { - error = removexattr(path.dentry, name); - mnt_drop_write(path.mnt); - } - path_put(&path); + do { + error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); + if (error) + break; + error = mnt_want_write(path.mnt); + if (!error) { + error = removexattr(path.dentry, name); + mnt_drop_write(path.mnt); + } + path_put(&path); + lookup_flags |= LOOKUP_REVAL; + } while (retry_estale(error, try++)); return error; } -- 1.7.11.4