From 76aac0e9a17742e60d408be1a706e9aaad370891 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Nov 2008 10:39:12 +1100 Subject: CRED: Wrap task credential accesses in the core kernel Wrap access to task credentials so that they can be separated more easily from the task_struct during the introduction of COW creds. Change most current->(|e|s|fs)[ug]id to current_(|e|s|fs)[ug]id(). Change some task->e?[ug]id to task_e?[ug]id(). In some places it makes more sense to use RCU directly rather than a convenient wrapper; these will be addressed by later patches. Signed-off-by: David Howells Reviewed-by: James Morris Acked-by: Serge Hallyn Cc: Al Viro Cc: linux-audit@redhat.com Cc: containers@lists.linux-foundation.org Cc: linux-mm@kvack.org Signed-off-by: James Morris --- kernel/cgroup.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'kernel/cgroup.c') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 35eebd5510c2..78f9b310c4f3 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -571,8 +571,8 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb) if (inode) { inode->i_mode = mode; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info; @@ -1279,6 +1279,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) static int attach_task_by_pid(struct cgroup *cgrp, u64 pid) { struct task_struct *tsk; + uid_t euid; int ret; if (pid) { @@ -1291,8 +1292,8 @@ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid) get_task_struct(tsk); rcu_read_unlock(); - if ((current->euid) && (current->euid != tsk->uid) - && (current->euid != tsk->suid)) { + euid = current_euid(); + if (euid && euid != tsk->uid && euid != tsk->suid) { put_task_struct(tsk); return -EACCES; } -- cgit v1.2.3 From b6dff3ec5e116e3af6f537d4caedcad6b9e5082a Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Nov 2008 10:39:16 +1100 Subject: CRED: Separate task security context from task_struct Separate the task security context from task_struct. At this point, the security data is temporarily embedded in the task_struct with two pointers pointing to it. Note that the Alpha arch is altered as it refers to (E)UID and (E)GID in entry.S via asm-offsets. With comment fixes Signed-off-by: Marc Dionne Signed-off-by: David Howells Acked-by: James Morris Acked-by: Serge Hallyn Signed-off-by: James Morris --- kernel/cgroup.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/cgroup.c') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 78f9b310c4f3..e210526e6401 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1293,7 +1293,9 @@ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid) rcu_read_unlock(); euid = current_euid(); - if (euid && euid != tsk->uid && euid != tsk->suid) { + if (euid && + euid != tsk->cred->uid && + euid != tsk->cred->suid) { put_task_struct(tsk); return -EACCES; } -- cgit v1.2.3 From c69e8d9c01db2adc503464993c358901c9af9de4 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Nov 2008 10:39:19 +1100 Subject: CRED: Use RCU to access another task's creds and to release a task's own creds Use RCU to access another task's creds and to release a task's own creds. This means that it will be possible for the credentials of a task to be replaced without another task (a) requiring a full lock to read them, and (b) seeing deallocated memory. Signed-off-by: David Howells Acked-by: James Morris Acked-by: Serge Hallyn Signed-off-by: James Morris --- kernel/cgroup.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'kernel/cgroup.c') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index e210526e6401..a512a75a5560 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1279,7 +1279,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) static int attach_task_by_pid(struct cgroup *cgrp, u64 pid) { struct task_struct *tsk; - uid_t euid; + const struct cred *cred = current_cred(), *tcred; int ret; if (pid) { @@ -1289,16 +1289,16 @@ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid) rcu_read_unlock(); return -ESRCH; } - get_task_struct(tsk); - rcu_read_unlock(); - euid = current_euid(); - if (euid && - euid != tsk->cred->uid && - euid != tsk->cred->suid) { - put_task_struct(tsk); + tcred = __task_cred(tsk); + if (cred->euid && + cred->euid != tcred->uid && + cred->euid != tcred->suid) { + rcu_read_unlock(); return -EACCES; } + get_task_struct(tsk); + rcu_read_unlock(); } else { tsk = current; get_task_struct(tsk); -- cgit v1.2.3 From 307257cf475aac25db30b669987f13d90c934e3a Mon Sep 17 00:00:00 2001 From: Paul Menage Date: Mon, 15 Dec 2008 13:54:22 -0800 Subject: cgroups: fix a race between rmdir and remount When a cgroup is removed, it's unlinked from its parent's children list, but not actually freed until the last dentry on it is released (at which point cgrp->root->number_of_cgroups is decremented). Currently rebind_subsystems checks for the top cgroup's child list being empty in order to rebind subsystems into or out of a hierarchy - this can result in the set of subsystems bound to a hierarchy being removed-but-not-freed cgroup. The simplest fix for this is to forbid remounts that change the set of subsystems on a hierarchy that has removed-but-not-freed cgroups. This bug can be reproduced via: mkdir /mnt/cg mount -t cgroup -o ns,freezer cgroup /mnt/cg mkdir /mnt/cg/foo sleep 1h < /mnt/cg/foo & rmdir /mnt/cg/foo mount -t cgroup -o remount,ns,devices,freezer cgroup /mnt/cg kill $! Though the above will cause oops in -mm only but not mainline, but the bug can cause memory leak in mainline (and even oops) Signed-off-by: Paul Menage Reviewed-by: Li Zefan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/cgroup.c') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index fe00b3b983a8..8185a0f09594 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -702,7 +702,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, * any child cgroups exist. This is theoretically supportable * but involves complex error handling, so it's being left until * later */ - if (!list_empty(&cgrp->children)) + if (root->number_of_cgroups > 1) return -EBUSY; /* Process each subsystem */ -- cgit v1.2.3 From e368d3a836797ddf193b1ec18c97407a791d2451 Mon Sep 17 00:00:00 2001 From: Sharyathi Nagesh Date: Tue, 23 Dec 2008 13:57:12 -0800 Subject: cgroups: suppress bogus warning messages Remove spurious warning messages that are thrown onto the console during cgroup operations. Signed-off-by: Alexey Dobriyan Signed-off-by: Sharyathi Nagesh Acked-by: Serge E. Hallyn Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'kernel/cgroup.c') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 8185a0f09594..a3415507bd0a 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2934,9 +2934,6 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, again: root = subsys->root; if (root == &rootnode) { - printk(KERN_INFO - "Not cloning cgroup for unused subsystem %s\n", - subsys->name); mutex_unlock(&cgroup_mutex); return 0; } -- cgit v1.2.3 From 20ca9b3f4c6dfa0af8dd5b18a64df17eb994b54d Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 23 Dec 2008 13:57:14 -0800 Subject: cgroups: avoid accessing uninitialized data in failure path If cgroup_get_rootdir() failed, free_cg_links() will be called in the failure path, but tmp_cg_links hasn't been initialized at that time. I introduced this bug in the 2.6.27 merge window. Signed-off-by: Li Zefan Acked-by: Serge Hallyn Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel/cgroup.c') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index a3415507bd0a..2606d0fb4e54 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1024,7 +1024,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type, if (ret == -EBUSY) { mutex_unlock(&cgroup_mutex); mutex_unlock(&inode->i_mutex); - goto drop_new_super; + goto free_cg_links; } /* EBUSY should be the only error here */ @@ -1073,10 +1073,11 @@ static int cgroup_get_sb(struct file_system_type *fs_type, return simple_set_mnt(mnt, sb); + free_cg_links: + free_cg_links(&tmp_cg_links); drop_new_super: up_write(&sb->s_umount); deactivate_super(sb); - free_cg_links(&tmp_cg_links); return ret; } -- cgit v1.2.3