mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs.git
synced 2026-10-31 06:14:39 +01:00
Lorenzo Stoakes (ARM)
78436f3882
The locked_vm field in struct user_struct was originally introduced by commit789f90fcf6("perf_counter: per user mlock gift") to provide an mlock-like budget for perf measured against mm->pinned_vm (since 2011). perf grants each user a 'gift' of perf_event_mlock_kb * online CPUs of buffer pages which is charged to user->locked_vm without any RLIMIT_MEMLOCK check. Only pages beyond the gift are checked against RLIMIT_MEMLOCK, per-mm, via mm->pinned_vm, which makes it different from the standard mlock() check, which is per-mm and made against RLIMIT_MEMLOCK. However, since this was introduced, a number of other components have utilised this field where a shared resource needed to be limited against RLIMIT_MEMLOCK. The other users are currently MSG_ZEROCOPY, io_uring, AF_XDP, iommufd, s390 KVM zPCI and most recently, secretmem in commit97d34aa65c("mm/secretmem: properly account locked pages"). This field is shared between all of these, but because the gift is not checked against RLIMIT_MEMLOCK, user->locked_vm alone can exceed it - 16 CPUs * 516 KiB is already more than the default 8 MiB - after which every other user of the field fails unconditionally. This was reported by a user who saw secretmem failing while running a simultaneous perf record. Resolve the issue by simply giving perf its own field separate from the rest. BPF used user->locked_vm up until commit80ee81e040("bpf: Eliminate rlimit-based memory accounting infra for bpf maps") which landed in 5.11. Thus also eliminate the now-defunct ifdef for CONFIG_BPF_SYSCALL for user->locked_vm. This issue exists between all of the components which use user->locked_vm and perf, however secretmem is the first user who has caused a report over many years and has been backported, so target the fix at that. Fixes:97d34aa65c("mm/secretmem: properly account locked pages") Closes: https://lore.kernel.org/[email protected] Reported-by: Ameer Hamza <[email protected]> Signed-off-by: Lorenzo Stoakes (ARM) <[email protected]> Signed-off-by: Peter Zijlstra (Intel) <[email protected]> Cc: [email protected] Link: https://patch.msgid.link/[email protected]
60 lines
1.6 KiB
C
60 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_NET) || defined(CONFIG_IO_URING) || \
|
|
defined(CONFIG_VFIO_PCI_ZDEV_KVM) || IS_ENABLED(CONFIG_IOMMUFD) || \
|
|
defined(CONFIG_SECRETMEM)
|
|
atomic_long_t locked_vm; /* pinned pages charged to RLIMIT_MEMLOCK */
|
|
#endif
|
|
#ifdef CONFIG_PERF_EVENTS
|
|
atomic_long_t perf_mlock; /* perf buffer pages within perf_event_mlock_kb */
|
|
#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 */
|