@@ -1451,34 +1451,35 @@ static int get_hstate_idx(int page_size_log)
* otherwise hugetlb_reserve_pages reserves one less hugepages than intended.
*/
struct file *hugetlb_file_setup(const char *name, size_t size,
- vm_flags_t acctflag, struct user_struct **user,
+ vm_flags_t acctflag,
int creat_flags, int page_size_log)
{
struct inode *inode;
struct vfsmount *mnt;
int hstate_idx;
struct file *file;
+ const struct cred *cred;
hstate_idx = get_hstate_idx(page_size_log);
if (hstate_idx < 0)
return ERR_PTR(-ENODEV);
- *user = NULL;
mnt = hugetlbfs_vfsmount[hstate_idx];
if (!mnt)
return ERR_PTR(-ENOENT);
if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
- *user = current_user();
- if (user_shm_lock(size, *user)) {
+ cred = current_cred();
+ if (user_shm_lock(size, cred)) {
task_lock(current);
pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n",
current->comm, current->pid);
task_unlock(current);
} else {
- *user = NULL;
return ERR_PTR(-EPERM);
}
+ } else {
+ cred = NULL;
}
file = ERR_PTR(-ENOSPC);
@@ -1503,10 +1504,8 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
iput(inode);
out:
- if (*user) {
- user_shm_unlock(size, *user);
- *user = NULL;
- }
+ if (cred)
+ user_shm_unlock(size, cred);
return file;
}
@@ -434,8 +434,7 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
extern const struct file_operations hugetlbfs_file_operations;
extern const struct vm_operations_struct hugetlb_vm_ops;
struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct,
- struct user_struct **user, int creat_flags,
- int page_size_log);
+ int creat_flags, int page_size_log);
static inline bool is_file_hugepages(struct file *file)
{
@@ -1628,8 +1628,8 @@ extern bool can_do_mlock(void);
#else
static inline bool can_do_mlock(void) { return false; }
#endif
-extern int user_shm_lock(size_t, struct user_struct *);
-extern void user_shm_unlock(size_t, struct user_struct *);
+extern int user_shm_lock(size_t, const struct cred *);
+extern void user_shm_unlock(size_t, const struct cred *);
/*
* Parameter block passed down to zap_pte_range in exceptional cases.
@@ -65,7 +65,7 @@ extern struct file *shmem_file_setup_with_mnt(struct vfsmount *mnt,
extern int shmem_zero_setup(struct vm_area_struct *);
extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr,
unsigned long len, unsigned long pgoff, unsigned long flags);
-extern int shmem_lock(struct file *file, int lock, struct user_struct *user);
+extern int shmem_lock(struct file *file, int lock, const struct cred *cred);
#ifdef CONFIG_SHMEM
extern const struct address_space_operations shmem_aops;
static inline bool shmem_mapping(struct address_space *mapping)
@@ -53,6 +53,7 @@ enum ucount_type {
UCOUNT_RLIMIT_NPROC,
UCOUNT_RLIMIT_MSGQUEUE,
UCOUNT_RLIMIT_SIGPENDING,
+ UCOUNT_RLIMIT_MEMLOCK,
UCOUNT_COUNTS,
};
@@ -60,7 +60,7 @@ struct shmid_kernel /* private to the kernel */
time64_t shm_ctim;
struct pid *shm_cprid;
struct pid *shm_lprid;
- struct user_struct *mlock_user;
+ const struct cred *mlock_cred;
/* The task created the shm object. NULL if the task is dead. */
struct task_struct *shm_creator;
@@ -286,10 +286,10 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
shm_rmid(ns, shp);
shm_unlock(shp);
if (!is_file_hugepages(shm_file))
- shmem_lock(shm_file, 0, shp->mlock_user);
- else if (shp->mlock_user)
+ shmem_lock(shm_file, 0, shp->mlock_cred);
+ else if (shp->mlock_cred)
user_shm_unlock(i_size_read(file_inode(shm_file)),
- shp->mlock_user);
+ shp->mlock_cred);
fput(shm_file);
ipc_update_pid(&shp->shm_cprid, NULL);
ipc_update_pid(&shp->shm_lprid, NULL);
@@ -625,7 +625,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
shp->shm_perm.key = key;
shp->shm_perm.mode = (shmflg & S_IRWXUGO);
- shp->mlock_user = NULL;
+ shp->mlock_cred = NULL;
shp->shm_perm.security = NULL;
error = security_shm_alloc(&shp->shm_perm);
@@ -650,8 +650,9 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
if (shmflg & SHM_NORESERVE)
acctflag = VM_NORESERVE;
file = hugetlb_file_setup(name, hugesize, acctflag,
- &shp->mlock_user, HUGETLB_SHMFS_INODE,
+ HUGETLB_SHMFS_INODE,
(shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK);
+ shp->mlock_cred = current_cred();
} else {
/*
* Do not allow no accounting for OVERCOMMIT_NEVER, even
@@ -663,8 +664,10 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
file = shmem_kernel_file_setup(name, size, acctflag);
}
error = PTR_ERR(file);
- if (IS_ERR(file))
+ if (IS_ERR(file)) {
+ shp->mlock_cred = NULL;
goto no_file;
+ }
shp->shm_cprid = get_pid(task_tgid(current));
shp->shm_lprid = NULL;
@@ -698,8 +701,8 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
no_id:
ipc_update_pid(&shp->shm_cprid, NULL);
ipc_update_pid(&shp->shm_lprid, NULL);
- if (is_file_hugepages(file) && shp->mlock_user)
- user_shm_unlock(size, shp->mlock_user);
+ if (is_file_hugepages(file) && shp->mlock_cred)
+ user_shm_unlock(size, shp->mlock_cred);
fput(file);
ipc_rcu_putref(&shp->shm_perm, shm_rcu_free);
return error;
@@ -1105,12 +1108,12 @@ static int shmctl_do_lock(struct ipc_namespace *ns, int shmid, int cmd)
goto out_unlock0;
if (cmd == SHM_LOCK) {
- struct user_struct *user = current_user();
+ const struct cred *cred = current_cred();
- err = shmem_lock(shm_file, 1, user);
+ err = shmem_lock(shm_file, 1, cred);
if (!err && !(shp->shm_perm.mode & SHM_LOCKED)) {
shp->shm_perm.mode |= SHM_LOCKED;
- shp->mlock_user = user;
+ shp->mlock_cred = cred;
}
goto out_unlock0;
}
@@ -1118,9 +1121,9 @@ static int shmctl_do_lock(struct ipc_namespace *ns, int shmid, int cmd)
/* SHM_UNLOCK */
if (!(shp->shm_perm.mode & SHM_LOCKED))
goto out_unlock0;
- shmem_lock(shm_file, 0, shp->mlock_user);
+ shmem_lock(shm_file, 0, shp->mlock_cred);
shp->shm_perm.mode &= ~SHM_LOCKED;
- shp->mlock_user = NULL;
+ shp->mlock_cred = NULL;
get_file(shm_file);
ipc_unlock_object(&shp->shm_perm);
rcu_read_unlock();
@@ -826,6 +826,7 @@ void __init fork_init(void)
init_user_ns.ucount_max[UCOUNT_RLIMIT_NPROC] = task_rlimit(&init_task, RLIMIT_NPROC);
init_user_ns.ucount_max[UCOUNT_RLIMIT_MSGQUEUE] = task_rlimit(&init_task, RLIMIT_MSGQUEUE);
init_user_ns.ucount_max[UCOUNT_RLIMIT_SIGPENDING] = task_rlimit(&init_task, RLIMIT_SIGPENDING);
+ init_user_ns.ucount_max[UCOUNT_RLIMIT_MEMLOCK] = task_rlimit(&init_task, RLIMIT_MEMLOCK);
#ifdef CONFIG_VMAP_STACK
cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache",
@@ -78,6 +78,7 @@ static struct ctl_table user_table[] = {
{ },
{ },
{ },
+ { },
{ }
};
#endif /* CONFIG_SYSCTL */
@@ -124,6 +124,7 @@ int create_user_ns(struct cred *new)
ns->ucount_max[UCOUNT_RLIMIT_NPROC] = rlimit(RLIMIT_NPROC);
ns->ucount_max[UCOUNT_RLIMIT_MSGQUEUE] = rlimit(RLIMIT_MSGQUEUE);
ns->ucount_max[UCOUNT_RLIMIT_SIGPENDING] = rlimit(RLIMIT_SIGPENDING);
+ ns->ucount_max[UCOUNT_RLIMIT_MEMLOCK] = rlimit(RLIMIT_MEMLOCK);
ns->ucounts = ucounts;
/* Inherit USERNS_SETGROUPS_ALLOWED from our parent */
@@ -297,9 +297,7 @@ SYSCALL_DEFINE2(memfd_create,
}
if (flags & MFD_HUGETLB) {
- struct user_struct *user = NULL;
-
- file = hugetlb_file_setup(name, 0, VM_NORESERVE, &user,
+ file = hugetlb_file_setup(name, 0, VM_NORESERVE,
HUGETLB_ANONHUGE_INODE,
(flags >> MFD_HUGE_SHIFT) &
MFD_HUGE_MASK);
@@ -812,15 +812,10 @@ SYSCALL_DEFINE0(munlockall)
return ret;
}
-/*
- * Objects with different lifetime than processes (SHM_LOCK and SHM_HUGETLB
- * shm segments) get accounted against the user_struct instead.
- */
-static DEFINE_SPINLOCK(shmlock_user_lock);
-
-int user_shm_lock(size_t size, struct user_struct *user)
+int user_shm_lock(size_t size, const struct cred *cred)
{
unsigned long lock_limit, locked;
+ bool overlimit;
int allowed = 0;
locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
@@ -828,22 +823,18 @@ int user_shm_lock(size_t size, struct user_struct *user)
if (lock_limit == RLIM_INFINITY)
allowed = 1;
lock_limit >>= PAGE_SHIFT;
- spin_lock(&shmlock_user_lock);
- if (!allowed &&
- locked + user->locked_shm > lock_limit && !capable(CAP_IPC_LOCK))
- goto out;
- get_uid(user);
- user->locked_shm += locked;
- allowed = 1;
-out:
- spin_unlock(&shmlock_user_lock);
- return allowed;
+
+ overlimit = inc_rlimit_ucounts_and_test(cred->ucounts, UCOUNT_RLIMIT_MEMLOCK,
+ locked, lock_limit);
+
+ if (!allowed && overlimit && !capable(CAP_IPC_LOCK)) {
+ dec_rlimit_ucounts(cred->ucounts, UCOUNT_RLIMIT_MEMLOCK, locked);
+ return 0;
+ }
+ return 1;
}
-void user_shm_unlock(size_t size, struct user_struct *user)
+void user_shm_unlock(size_t size, const struct cred *cred)
{
- spin_lock(&shmlock_user_lock);
- user->locked_shm -= (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
- spin_unlock(&shmlock_user_lock);
- free_uid(user);
+ dec_rlimit_ucounts(cred->ucounts, UCOUNT_RLIMIT_MEMLOCK, (size + PAGE_SIZE - 1) >> PAGE_SHIFT);
}
@@ -1607,7 +1607,6 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len,
goto out_fput;
}
} else if (flags & MAP_HUGETLB) {
- struct user_struct *user = NULL;
struct hstate *hs;
hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK);
@@ -1623,7 +1622,7 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len,
*/
file = hugetlb_file_setup(HUGETLB_ANON_FILE, len,
VM_NORESERVE,
- &user, HUGETLB_ANONHUGE_INODE,
+ HUGETLB_ANONHUGE_INODE,
(flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK);
if (IS_ERR(file))
return PTR_ERR(file);
@@ -2225,7 +2225,7 @@ static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma,
}
#endif
-int shmem_lock(struct file *file, int lock, struct user_struct *user)
+int shmem_lock(struct file *file, int lock, const struct cred *cred)
{
struct inode *inode = file_inode(file);
struct shmem_inode_info *info = SHMEM_I(inode);
@@ -2237,13 +2237,13 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
* no serialization needed when called from shm_destroy().
*/
if (lock && !(info->flags & VM_LOCKED)) {
- if (!user_shm_lock(inode->i_size, user))
+ if (!user_shm_lock(inode->i_size, cred))
goto out_nomem;
info->flags |= VM_LOCKED;
mapping_set_unevictable(file->f_mapping);
}
- if (!lock && (info->flags & VM_LOCKED) && user) {
- user_shm_unlock(inode->i_size, user);
+ if (!lock && (info->flags & VM_LOCKED) && cred) {
+ user_shm_unlock(inode->i_size, cred);
info->flags &= ~VM_LOCKED;
mapping_clear_unevictable(file->f_mapping);
}
Signed-off-by: Alexey Gladkov <gladkov.alexey@gmail.com> --- fs/hugetlbfs/inode.c | 17 ++++++++--------- include/linux/hugetlb.h | 3 +-- include/linux/mm.h | 4 ++-- include/linux/shmem_fs.h | 2 +- include/linux/user_namespace.h | 1 + ipc/shm.c | 31 ++++++++++++++++-------------- kernel/fork.c | 1 + kernel/ucount.c | 1 + kernel/user_namespace.c | 1 + mm/memfd.c | 4 +--- mm/mlock.c | 35 +++++++++++++--------------------- mm/mmap.c | 3 +-- mm/shmem.c | 8 ++++---- 13 files changed, 52 insertions(+), 59 deletions(-)