mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs.git
synced 2026-10-29 13:23:23 +01:00
Lorenzo Stoakes (ARM)
97d34aa65c
secretmem accounts folios by treating memory as if it were mlock()'d and
thus limited by the RLIMIT_MEMLOCK limit.
However the folios are unevictable and remain so until the inode is
evicted, eliminating usual mlock() semantics - mapping folios then
unmapping them does not clear their unevictable state, since it depends on
AS_UNEVICTABLE, not PG_mlocked.
A user can therefore easily work around the RLIMIT_MEMLOCK limit - simply
map then unmap and VmLck no longer counts the secretmem range. Worse,
folios are not accounted in the process's RSS, meaning the OOM killer
won't know to kill the process.
Repeatedly mapping/unmapping (or forking) can then result in the
consumption of all available system memory with unevictable folios and
cause system instability.
A secretmem fd can be passed between processes and over fork so a
per-process limit simply does not make sense, so follow the precedent set
by io_uring, perf, skbuff, iommufd and xdp by tracking the number of
locked pages in user_struct->locked_vm.
Since the scope tracked is actually inode lifetime, the RLIMIT_MEMLOCK
applies per-user not per-process, so it doesn't make sense to bypass for
users with CAP_IPC_LOCK, therefore remove this bypass.
There is simply no reason to carry on marking the mapping as mlock()'d
since it's misleading and the lifecycle is now correctly handled, so
remove this too.
Note that secretmem does not support any form of truncation (including
hole punching) and the folios are unreclaimable, so the folios need only
be accounted on fault and unaccounted on inode destruction.
__secretmem_account_pages() is more or less a duplicate of the code that
io_uring etc. use, but since this is a bug fix that needs backporting,
defer any de-duplication efforts to a follow-up.
test_mlock_limit() asserts mlock_future_ok() on mmap(), however this has
been removed, so remove the test altogether for the fix. A new test will
be sent separately for upstream.
Link: https://lore.kernel.org/[email protected]
Fixes: 1507f51255 ("mm: introduce memfd_secret system call to create "secret" memory areas")
Signed-off-by: Lorenzo Stoakes (ARM) <[email protected]>
Reported-by: Daehyeon Ko <[email protected]>
Closes: https://lore.kernel.org/linux-mm/[email protected]/
Reviewed-by: Mike Rapoport (Microsoft) <[email protected]>
Acked-by: David Hildenbrand (Arm) <[email protected]>
Tested-by: Daehyeon Ko <[email protected]>
Cc: Alexei Starovoitov <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: David S. Miller <[email protected]>
Cc: Hagen Paul Pfeifer <[email protected]>
Cc: Jakub Kacinski <[email protected]>
Cc: James Bottomley <[email protected]>
Cc: Jesper Dangaard Brouer <[email protected]>
Cc: John Fastabend <[email protected]>
Cc: Liam R. Howlett <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Stanislav Fomichev <[email protected]>
Cc: Suren Baghdasaryan <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
58 lines
1.6 KiB
C
58 lines
1.6 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_SCHED_USER_H
|
|
#define _LINUX_SCHED_USER_H
|
|
|
|
#include <linux/uidgid.h>
|
|
#include <linux/atomic.h>
|
|
#include <linux/percpu_counter.h>
|
|
#include <linux/refcount.h>
|
|
#include <linux/ratelimit.h>
|
|
|
|
/*
|
|
* Some day this will be a full-fledged user tracking system..
|
|
*/
|
|
struct user_struct {
|
|
refcount_t __count; /* reference count */
|
|
#ifdef CONFIG_EPOLL
|
|
struct percpu_counter epoll_watches; /* The number of file descriptors currently watched */
|
|
#endif
|
|
unsigned long unix_inflight; /* How many files in flight in unix sockets */
|
|
atomic_long_t pipe_bufs; /* how many pages are allocated in pipe buffers */
|
|
|
|
/* Hash table maintenance information */
|
|
struct hlist_node uidhash_node;
|
|
kuid_t uid;
|
|
|
|
#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \
|
|
defined(CONFIG_NET) || defined(CONFIG_IO_URING) || \
|
|
defined(CONFIG_VFIO_PCI_ZDEV_KVM) || IS_ENABLED(CONFIG_IOMMUFD) || \
|
|
defined(CONFIG_SECRETMEM)
|
|
atomic_long_t locked_vm;
|
|
#endif
|
|
#ifdef CONFIG_WATCH_QUEUE
|
|
atomic_t nr_watches; /* The number of watches this user currently has */
|
|
#endif
|
|
|
|
/* Miscellaneous per-user rate limit */
|
|
struct ratelimit_state ratelimit;
|
|
};
|
|
|
|
extern int uids_sysfs_init(void);
|
|
|
|
extern struct user_struct *find_user(kuid_t);
|
|
|
|
extern struct user_struct root_user;
|
|
#define INIT_USER (&root_user)
|
|
|
|
|
|
/* per-UID process charging. */
|
|
extern struct user_struct * alloc_uid(kuid_t);
|
|
static inline struct user_struct *get_uid(struct user_struct *u)
|
|
{
|
|
refcount_inc(&u->__count);
|
|
return u;
|
|
}
|
|
extern void free_uid(struct user_struct *);
|
|
|
|
#endif /* _LINUX_SCHED_USER_H */
|