mm: fix hugetlb bug due to user_shm_unlock call

2.6.30's commit 8a0bdec removed
user_shm_lock() calls in hugetlb_file_setup() but left the
user_shm_unlock call in shm_destroy().

In detail:
Assume that can_do_hugetlb_shm() returns true and hence user_shm_lock()
is not called in hugetlb_file_setup(). However, user_shm_unlock() is
called in any case in shm_destroy() and in the following
atomic_dec_and_lock(&up->__count) in free_uid() is executed and if
up->__count gets zero, also cleanup_user_struct() is scheduled.

Note that sched_destroy_user() is empty if CONFIG_USER_SCHED is not set.
However, the ref counter up->__count gets unexpectedly non-positive and
the corresponding structs are freed even though there are live
references to them, resulting in a kernel oops after a lots of
shmget(SHM_HUGETLB)/shmctl(IPC_RMID) cycles and CONFIG_USER_SCHED set.

Hugh changed Stefan's suggested patch: can_do_hugetlb_shm() at the
time of shm_destroy() may give a different answer from at the time
of hugetlb_file_setup().  And fixed newseg()'s no_id error path,
which has missed user_shm_unlock() ever since it came in 2.6.9.

Reported-by: Stefan Huber <[email protected]>
Signed-off-by: Hugh Dickins <[email protected]>
Tested-by: Stefan Huber <[email protected]>
Cc: [email protected]
Signed-off-by: Linus Torvalds <[email protected]>

fs/hugetlbfs/inode.c

@@ -935,26 +935,28 @@ static int can_do_hugetlb_shm(void)
 	return capable(CAP_IPC_LOCK) || in_group_p(sysctl_hugetlb_shm_group);
 }
 
-struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag)
+struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag,
+						struct user_struct **user)
 {
 	int error = -ENOMEM;
-	int unlock_shm = 0;
 	struct file *file;
 	struct inode *inode;
 	struct dentry *dentry, *root;
 	struct qstr quick_string;
-	struct user_struct *user = current_user();
 
+	*user = NULL;
 	if (!hugetlbfs_vfsmount)
 		return ERR_PTR(-ENOENT);
 
 	if (!can_do_hugetlb_shm()) {
-		if (user_shm_lock(size, user)) {
-			unlock_shm = 1;
+		*user = current_user();
+		if (user_shm_lock(size, *user)) {
 			WARN_ONCE(1,
 			  "Using mlock ulimits for SHM_HUGETLB deprecated\n");
-		} else
+		} else {
+			*user = NULL;
 			return ERR_PTR(-EPERM);
+		}
 	}
 
 	root = hugetlbfs_vfsmount->mnt_root;
@@ -996,8 +998,10 @@ struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag)
 out_dentry:
 	dput(dentry);
 out_shm_unlock:
-	if (unlock_shm)
-		user_shm_unlock(size, user);
+	if (*user) {
+		user_shm_unlock(size, *user);
+		*user = NULL;
+	}
 	return ERR_PTR(error);
 }
 

include/linux/hugetlb.h

@@ -10,6 +10,7 @@
 #include <asm/tlbflush.h>
 
 struct ctl_table;
+struct user_struct;
 
 int PageHuge(struct page *page);
 
@@ -146,7 +147,8 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
 
 extern const struct file_operations hugetlbfs_file_operations;
 extern struct vm_operations_struct hugetlb_vm_ops;
-struct file *hugetlb_file_setup(const char *name, size_t, int);
+struct file *hugetlb_file_setup(const char *name, size_t size, int acct,
+						struct user_struct **user);
 int hugetlb_get_quota(struct address_space *mapping, long delta);
 void hugetlb_put_quota(struct address_space *mapping, long delta);
 
@@ -168,7 +170,7 @@ static inline void set_file_hugepages(struct file *file)
 
 #define is_file_hugepages(file)			0
 #define set_file_hugepages(file)		BUG()
-#define hugetlb_file_setup(name,size,acctflag)	ERR_PTR(-ENOSYS)
+#define hugetlb_file_setup(name,size,acct,user)	ERR_PTR(-ENOSYS)
 
 #endif /* !CONFIG_HUGETLBFS */
 

ipc/shm.c

@@ -174,7 +174,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
 	shm_unlock(shp);
 	if (!is_file_hugepages(shp->shm_file))
 		shmem_lock(shp->shm_file, 0, shp->mlock_user);
-	else
+	else if (shp->mlock_user)
 		user_shm_unlock(shp->shm_file->f_path.dentry->d_inode->i_size,
 						shp->mlock_user);
 	fput (shp->shm_file);
@@ -369,8 +369,8 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 		/* hugetlb_file_setup applies strict accounting */
 		if (shmflg & SHM_NORESERVE)
 			acctflag = VM_NORESERVE;
-		file = hugetlb_file_setup(name, size, acctflag);
-		shp->mlock_user = current_user();
+		file = hugetlb_file_setup(name, size, acctflag,
+							&shp->mlock_user);
 	} else {
 		/*
 		 * Do not allow no accounting for OVERCOMMIT_NEVER, even
@@ -410,6 +410,8 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	return error;
 
 no_id:
+	if (shp->mlock_user)	/* shmflg & SHM_HUGETLB case */
+		user_shm_unlock(size, shp->mlock_user);
 	fput(file);
 no_file:
 	security_shm_free(shp);