mirror of
https://github.com/torvalds/linux.git
synced 2024-11-25 13:41:51 +00:00
cf264e1329
There is currently no good way to query the page cache state of large file sets and directory trees. There is mincore(), but it scales poorly: the kernel writes out a lot of bitmap data that userspace has to aggregate, when the user really doesn not care about per-page information in that case. The user also needs to mmap and unmap each file as it goes along, which can be quite slow as well. Some use cases where this information could come in handy: * Allowing database to decide whether to perform an index scan or direct table queries based on the in-memory cache state of the index. * Visibility into the writeback algorithm, for performance issues diagnostic. * Workload-aware writeback pacing: estimating IO fulfilled by page cache (and IO to be done) within a range of a file, allowing for more frequent syncing when and where there is IO capacity, and batching when there is not. * Computing memory usage of large files/directory trees, analogous to the du tool for disk usage. More information about these use cases could be found in the following thread: https://lore.kernel.org/lkml/20230315170934.GA97793@cmpxchg.org/ This patch implements a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range. Currently, the syscall is only wired in for x86 architecture. NAME cachestat - query the page cache statistics of a file. SYNOPSIS #include <sys/mman.h> struct cachestat_range { __u64 off; __u64 len; }; struct cachestat { __u64 nr_cache; __u64 nr_dirty; __u64 nr_writeback; __u64 nr_evicted; __u64 nr_recently_evicted; }; int cachestat(unsigned int fd, struct cachestat_range *cstat_range, struct cachestat *cstat, unsigned int flags); DESCRIPTION cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by `off` and `len`. An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system. These values are returned in a cachestat struct, whose address is given by the `cstat` argument. The `off` and `len` arguments must be non-negative integers. If `len` > 0, the queried range is [`off`, `off` + `len`]. If `len` == 0, we will query in the range from `off` to the end of the file. The `flags` argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified). Currently, hugetlbfs is not supported. Because the status of a page can change after cachestat() checks it but before it returns to the application, the returned values may contain stale information. RETURN VALUE On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EFAULT cstat or cstat_args points to an invalid address. EINVAL invalid flags. EBADF invalid file descriptor. EOPNOTSUPP file descriptor is of a hugetlbfs file [nphamcs@gmail.com: replace rounddown logic with the existing helper] Link: https://lkml.kernel.org/r/20230504022044.3675469-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20230503013608.2431726-3-nphamcs@gmail.com Signed-off-by: Nhat Pham <nphamcs@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Brian Foster <bfoster@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
483 lines
10 KiB
C
483 lines
10 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
|
|
#include <linux/linkage.h>
|
|
#include <linux/errno.h>
|
|
|
|
#include <asm/unistd.h>
|
|
|
|
#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
|
|
/* Architectures may override COND_SYSCALL and COND_SYSCALL_COMPAT */
|
|
#include <asm/syscall_wrapper.h>
|
|
#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */
|
|
|
|
/* we can't #include <linux/syscalls.h> here,
|
|
but tell gcc to not warn with -Wmissing-prototypes */
|
|
asmlinkage long sys_ni_syscall(void);
|
|
|
|
/*
|
|
* Non-implemented system calls get redirected here.
|
|
*/
|
|
asmlinkage long sys_ni_syscall(void)
|
|
{
|
|
return -ENOSYS;
|
|
}
|
|
|
|
#ifndef COND_SYSCALL
|
|
#define COND_SYSCALL(name) cond_syscall(sys_##name)
|
|
#endif /* COND_SYSCALL */
|
|
|
|
#ifndef COND_SYSCALL_COMPAT
|
|
#define COND_SYSCALL_COMPAT(name) cond_syscall(compat_sys_##name)
|
|
#endif /* COND_SYSCALL_COMPAT */
|
|
|
|
/*
|
|
* This list is kept in the same order as include/uapi/asm-generic/unistd.h.
|
|
* Architecture specific entries go below, followed by deprecated or obsolete
|
|
* system calls.
|
|
*/
|
|
|
|
COND_SYSCALL(io_setup);
|
|
COND_SYSCALL_COMPAT(io_setup);
|
|
COND_SYSCALL(io_destroy);
|
|
COND_SYSCALL(io_submit);
|
|
COND_SYSCALL_COMPAT(io_submit);
|
|
COND_SYSCALL(io_cancel);
|
|
COND_SYSCALL(io_getevents_time32);
|
|
COND_SYSCALL(io_getevents);
|
|
COND_SYSCALL(io_pgetevents_time32);
|
|
COND_SYSCALL(io_pgetevents);
|
|
COND_SYSCALL_COMPAT(io_pgetevents_time32);
|
|
COND_SYSCALL_COMPAT(io_pgetevents);
|
|
COND_SYSCALL(io_uring_setup);
|
|
COND_SYSCALL(io_uring_enter);
|
|
COND_SYSCALL(io_uring_register);
|
|
|
|
/* fs/xattr.c */
|
|
|
|
/* fs/dcache.c */
|
|
|
|
/* fs/cookies.c */
|
|
COND_SYSCALL(lookup_dcookie);
|
|
COND_SYSCALL_COMPAT(lookup_dcookie);
|
|
|
|
/* fs/eventfd.c */
|
|
COND_SYSCALL(eventfd2);
|
|
|
|
/* fs/eventfd.c */
|
|
COND_SYSCALL(epoll_create1);
|
|
COND_SYSCALL(epoll_ctl);
|
|
COND_SYSCALL(epoll_pwait);
|
|
COND_SYSCALL_COMPAT(epoll_pwait);
|
|
COND_SYSCALL(epoll_pwait2);
|
|
COND_SYSCALL_COMPAT(epoll_pwait2);
|
|
|
|
/* fs/fcntl.c */
|
|
|
|
/* fs/inotify_user.c */
|
|
COND_SYSCALL(inotify_init1);
|
|
COND_SYSCALL(inotify_add_watch);
|
|
COND_SYSCALL(inotify_rm_watch);
|
|
|
|
/* fs/ioctl.c */
|
|
|
|
/* fs/ioprio.c */
|
|
COND_SYSCALL(ioprio_set);
|
|
COND_SYSCALL(ioprio_get);
|
|
|
|
/* fs/locks.c */
|
|
COND_SYSCALL(flock);
|
|
|
|
/* fs/namei.c */
|
|
|
|
/* fs/namespace.c */
|
|
|
|
/* fs/nfsctl.c */
|
|
|
|
/* fs/open.c */
|
|
|
|
/* fs/pipe.c */
|
|
|
|
/* fs/quota.c */
|
|
COND_SYSCALL(quotactl);
|
|
COND_SYSCALL(quotactl_fd);
|
|
|
|
/* fs/readdir.c */
|
|
|
|
/* fs/read_write.c */
|
|
|
|
/* fs/sendfile.c */
|
|
|
|
/* fs/select.c */
|
|
|
|
/* fs/signalfd.c */
|
|
COND_SYSCALL(signalfd4);
|
|
COND_SYSCALL_COMPAT(signalfd4);
|
|
|
|
/* fs/splice.c */
|
|
|
|
/* fs/stat.c */
|
|
|
|
/* fs/sync.c */
|
|
|
|
/* fs/timerfd.c */
|
|
COND_SYSCALL(timerfd_create);
|
|
COND_SYSCALL(timerfd_settime);
|
|
COND_SYSCALL(timerfd_settime32);
|
|
COND_SYSCALL(timerfd_gettime);
|
|
COND_SYSCALL(timerfd_gettime32);
|
|
|
|
/* fs/utimes.c */
|
|
|
|
/* kernel/acct.c */
|
|
COND_SYSCALL(acct);
|
|
|
|
/* kernel/capability.c */
|
|
COND_SYSCALL(capget);
|
|
COND_SYSCALL(capset);
|
|
|
|
/* kernel/exec_domain.c */
|
|
|
|
/* kernel/exit.c */
|
|
|
|
/* kernel/fork.c */
|
|
/* __ARCH_WANT_SYS_CLONE3 */
|
|
COND_SYSCALL(clone3);
|
|
|
|
/* kernel/futex/syscalls.c */
|
|
COND_SYSCALL(futex);
|
|
COND_SYSCALL(futex_time32);
|
|
COND_SYSCALL(set_robust_list);
|
|
COND_SYSCALL_COMPAT(set_robust_list);
|
|
COND_SYSCALL(get_robust_list);
|
|
COND_SYSCALL_COMPAT(get_robust_list);
|
|
COND_SYSCALL(futex_waitv);
|
|
|
|
/* kernel/hrtimer.c */
|
|
|
|
/* kernel/itimer.c */
|
|
|
|
/* kernel/kexec.c */
|
|
COND_SYSCALL(kexec_load);
|
|
COND_SYSCALL_COMPAT(kexec_load);
|
|
|
|
/* kernel/module.c */
|
|
COND_SYSCALL(init_module);
|
|
COND_SYSCALL(delete_module);
|
|
|
|
/* kernel/posix-timers.c */
|
|
|
|
/* kernel/printk.c */
|
|
COND_SYSCALL(syslog);
|
|
|
|
/* kernel/ptrace.c */
|
|
|
|
/* kernel/sched/core.c */
|
|
|
|
/* kernel/sys.c */
|
|
COND_SYSCALL(setregid);
|
|
COND_SYSCALL(setgid);
|
|
COND_SYSCALL(setreuid);
|
|
COND_SYSCALL(setuid);
|
|
COND_SYSCALL(setresuid);
|
|
COND_SYSCALL(getresuid);
|
|
COND_SYSCALL(setresgid);
|
|
COND_SYSCALL(getresgid);
|
|
COND_SYSCALL(setfsuid);
|
|
COND_SYSCALL(setfsgid);
|
|
COND_SYSCALL(setgroups);
|
|
COND_SYSCALL(getgroups);
|
|
|
|
/* kernel/time.c */
|
|
|
|
/* kernel/timer.c */
|
|
|
|
/* ipc/mqueue.c */
|
|
COND_SYSCALL(mq_open);
|
|
COND_SYSCALL_COMPAT(mq_open);
|
|
COND_SYSCALL(mq_unlink);
|
|
COND_SYSCALL(mq_timedsend);
|
|
COND_SYSCALL(mq_timedsend_time32);
|
|
COND_SYSCALL(mq_timedreceive);
|
|
COND_SYSCALL(mq_timedreceive_time32);
|
|
COND_SYSCALL(mq_notify);
|
|
COND_SYSCALL_COMPAT(mq_notify);
|
|
COND_SYSCALL(mq_getsetattr);
|
|
COND_SYSCALL_COMPAT(mq_getsetattr);
|
|
|
|
/* ipc/msg.c */
|
|
COND_SYSCALL(msgget);
|
|
COND_SYSCALL(old_msgctl);
|
|
COND_SYSCALL(msgctl);
|
|
COND_SYSCALL_COMPAT(msgctl);
|
|
COND_SYSCALL_COMPAT(old_msgctl);
|
|
COND_SYSCALL(msgrcv);
|
|
COND_SYSCALL_COMPAT(msgrcv);
|
|
COND_SYSCALL(msgsnd);
|
|
COND_SYSCALL_COMPAT(msgsnd);
|
|
|
|
/* ipc/sem.c */
|
|
COND_SYSCALL(semget);
|
|
COND_SYSCALL(old_semctl);
|
|
COND_SYSCALL(semctl);
|
|
COND_SYSCALL_COMPAT(semctl);
|
|
COND_SYSCALL_COMPAT(old_semctl);
|
|
COND_SYSCALL(semtimedop);
|
|
COND_SYSCALL(semtimedop_time32);
|
|
COND_SYSCALL(semop);
|
|
|
|
/* ipc/shm.c */
|
|
COND_SYSCALL(shmget);
|
|
COND_SYSCALL(old_shmctl);
|
|
COND_SYSCALL(shmctl);
|
|
COND_SYSCALL_COMPAT(shmctl);
|
|
COND_SYSCALL_COMPAT(old_shmctl);
|
|
COND_SYSCALL(shmat);
|
|
COND_SYSCALL_COMPAT(shmat);
|
|
COND_SYSCALL(shmdt);
|
|
|
|
/* net/socket.c */
|
|
COND_SYSCALL(socket);
|
|
COND_SYSCALL(socketpair);
|
|
COND_SYSCALL(bind);
|
|
COND_SYSCALL(listen);
|
|
COND_SYSCALL(accept);
|
|
COND_SYSCALL(connect);
|
|
COND_SYSCALL(getsockname);
|
|
COND_SYSCALL(getpeername);
|
|
COND_SYSCALL(setsockopt);
|
|
COND_SYSCALL_COMPAT(setsockopt);
|
|
COND_SYSCALL(getsockopt);
|
|
COND_SYSCALL_COMPAT(getsockopt);
|
|
COND_SYSCALL(sendto);
|
|
COND_SYSCALL(shutdown);
|
|
COND_SYSCALL(recvfrom);
|
|
COND_SYSCALL_COMPAT(recvfrom);
|
|
COND_SYSCALL(sendmsg);
|
|
COND_SYSCALL_COMPAT(sendmsg);
|
|
COND_SYSCALL(recvmsg);
|
|
COND_SYSCALL_COMPAT(recvmsg);
|
|
|
|
/* mm/filemap.c */
|
|
|
|
/* mm/nommu.c, also with MMU */
|
|
COND_SYSCALL(mremap);
|
|
|
|
/* security/keys/keyctl.c */
|
|
COND_SYSCALL(add_key);
|
|
COND_SYSCALL(request_key);
|
|
COND_SYSCALL(keyctl);
|
|
COND_SYSCALL_COMPAT(keyctl);
|
|
|
|
/* security/landlock/syscalls.c */
|
|
COND_SYSCALL(landlock_create_ruleset);
|
|
COND_SYSCALL(landlock_add_rule);
|
|
COND_SYSCALL(landlock_restrict_self);
|
|
|
|
/* arch/example/kernel/sys_example.c */
|
|
|
|
/* mm/fadvise.c */
|
|
COND_SYSCALL(fadvise64_64);
|
|
COND_SYSCALL_COMPAT(fadvise64_64);
|
|
|
|
/* mm/, CONFIG_MMU only */
|
|
COND_SYSCALL(swapon);
|
|
COND_SYSCALL(swapoff);
|
|
COND_SYSCALL(mprotect);
|
|
COND_SYSCALL(msync);
|
|
COND_SYSCALL(mlock);
|
|
COND_SYSCALL(munlock);
|
|
COND_SYSCALL(mlockall);
|
|
COND_SYSCALL(munlockall);
|
|
COND_SYSCALL(mincore);
|
|
COND_SYSCALL(madvise);
|
|
COND_SYSCALL(process_madvise);
|
|
COND_SYSCALL(process_mrelease);
|
|
COND_SYSCALL(remap_file_pages);
|
|
COND_SYSCALL(mbind);
|
|
COND_SYSCALL(get_mempolicy);
|
|
COND_SYSCALL(set_mempolicy);
|
|
COND_SYSCALL(migrate_pages);
|
|
COND_SYSCALL(move_pages);
|
|
COND_SYSCALL(set_mempolicy_home_node);
|
|
COND_SYSCALL(cachestat);
|
|
|
|
COND_SYSCALL(perf_event_open);
|
|
COND_SYSCALL(accept4);
|
|
COND_SYSCALL(recvmmsg);
|
|
COND_SYSCALL(recvmmsg_time32);
|
|
COND_SYSCALL_COMPAT(recvmmsg_time32);
|
|
COND_SYSCALL_COMPAT(recvmmsg_time64);
|
|
|
|
/*
|
|
* Architecture specific syscalls: see further below
|
|
*/
|
|
|
|
/* fanotify */
|
|
COND_SYSCALL(fanotify_init);
|
|
COND_SYSCALL(fanotify_mark);
|
|
|
|
/* open by handle */
|
|
COND_SYSCALL(name_to_handle_at);
|
|
COND_SYSCALL(open_by_handle_at);
|
|
COND_SYSCALL_COMPAT(open_by_handle_at);
|
|
|
|
COND_SYSCALL(sendmmsg);
|
|
COND_SYSCALL_COMPAT(sendmmsg);
|
|
COND_SYSCALL(process_vm_readv);
|
|
COND_SYSCALL_COMPAT(process_vm_readv);
|
|
COND_SYSCALL(process_vm_writev);
|
|
COND_SYSCALL_COMPAT(process_vm_writev);
|
|
|
|
/* compare kernel pointers */
|
|
COND_SYSCALL(kcmp);
|
|
|
|
COND_SYSCALL(finit_module);
|
|
|
|
/* operate on Secure Computing state */
|
|
COND_SYSCALL(seccomp);
|
|
|
|
COND_SYSCALL(memfd_create);
|
|
|
|
/* access BPF programs and maps */
|
|
COND_SYSCALL(bpf);
|
|
|
|
/* execveat */
|
|
COND_SYSCALL(execveat);
|
|
|
|
COND_SYSCALL(userfaultfd);
|
|
|
|
/* membarrier */
|
|
COND_SYSCALL(membarrier);
|
|
|
|
COND_SYSCALL(mlock2);
|
|
|
|
COND_SYSCALL(copy_file_range);
|
|
|
|
/* memory protection keys */
|
|
COND_SYSCALL(pkey_mprotect);
|
|
COND_SYSCALL(pkey_alloc);
|
|
COND_SYSCALL(pkey_free);
|
|
|
|
/* memfd_secret */
|
|
COND_SYSCALL(memfd_secret);
|
|
|
|
/*
|
|
* Architecture specific weak syscall entries.
|
|
*/
|
|
|
|
/* pciconfig: alpha, arm, arm64, ia64, sparc */
|
|
COND_SYSCALL(pciconfig_read);
|
|
COND_SYSCALL(pciconfig_write);
|
|
COND_SYSCALL(pciconfig_iobase);
|
|
|
|
/* sys_socketcall: arm, mips, x86, ... */
|
|
COND_SYSCALL(socketcall);
|
|
COND_SYSCALL_COMPAT(socketcall);
|
|
|
|
/* compat syscalls for arm64, x86, ... */
|
|
COND_SYSCALL_COMPAT(fanotify_mark);
|
|
|
|
/* x86 */
|
|
COND_SYSCALL(vm86old);
|
|
COND_SYSCALL(modify_ldt);
|
|
COND_SYSCALL(vm86);
|
|
COND_SYSCALL(kexec_file_load);
|
|
|
|
/* s390 */
|
|
COND_SYSCALL(s390_pci_mmio_read);
|
|
COND_SYSCALL(s390_pci_mmio_write);
|
|
COND_SYSCALL(s390_ipc);
|
|
COND_SYSCALL_COMPAT(s390_ipc);
|
|
|
|
/* powerpc */
|
|
COND_SYSCALL(rtas);
|
|
COND_SYSCALL(spu_run);
|
|
COND_SYSCALL(spu_create);
|
|
COND_SYSCALL(subpage_prot);
|
|
|
|
|
|
/*
|
|
* Deprecated system calls which are still defined in
|
|
* include/uapi/asm-generic/unistd.h and wanted by >= 1 arch
|
|
*/
|
|
|
|
/* __ARCH_WANT_SYSCALL_NO_FLAGS */
|
|
COND_SYSCALL(epoll_create);
|
|
COND_SYSCALL(inotify_init);
|
|
COND_SYSCALL(eventfd);
|
|
COND_SYSCALL(signalfd);
|
|
COND_SYSCALL_COMPAT(signalfd);
|
|
|
|
/* __ARCH_WANT_SYSCALL_OFF_T */
|
|
COND_SYSCALL(fadvise64);
|
|
|
|
/* __ARCH_WANT_SYSCALL_DEPRECATED */
|
|
COND_SYSCALL(epoll_wait);
|
|
COND_SYSCALL(recv);
|
|
COND_SYSCALL_COMPAT(recv);
|
|
COND_SYSCALL(send);
|
|
COND_SYSCALL(uselib);
|
|
|
|
/* optional: time32 */
|
|
COND_SYSCALL(time32);
|
|
COND_SYSCALL(stime32);
|
|
COND_SYSCALL(utime32);
|
|
COND_SYSCALL(adjtimex_time32);
|
|
COND_SYSCALL(sched_rr_get_interval_time32);
|
|
COND_SYSCALL(nanosleep_time32);
|
|
COND_SYSCALL(rt_sigtimedwait_time32);
|
|
COND_SYSCALL_COMPAT(rt_sigtimedwait_time32);
|
|
COND_SYSCALL(timer_settime32);
|
|
COND_SYSCALL(timer_gettime32);
|
|
COND_SYSCALL(clock_settime32);
|
|
COND_SYSCALL(clock_gettime32);
|
|
COND_SYSCALL(clock_getres_time32);
|
|
COND_SYSCALL(clock_nanosleep_time32);
|
|
COND_SYSCALL(utimes_time32);
|
|
COND_SYSCALL(futimesat_time32);
|
|
COND_SYSCALL(pselect6_time32);
|
|
COND_SYSCALL_COMPAT(pselect6_time32);
|
|
COND_SYSCALL(ppoll_time32);
|
|
COND_SYSCALL_COMPAT(ppoll_time32);
|
|
COND_SYSCALL(utimensat_time32);
|
|
COND_SYSCALL(clock_adjtime32);
|
|
|
|
/*
|
|
* The syscalls below are not found in include/uapi/asm-generic/unistd.h
|
|
*/
|
|
|
|
/* obsolete: SGETMASK_SYSCALL */
|
|
COND_SYSCALL(sgetmask);
|
|
COND_SYSCALL(ssetmask);
|
|
|
|
/* obsolete: SYSFS_SYSCALL */
|
|
COND_SYSCALL(sysfs);
|
|
|
|
/* obsolete: __ARCH_WANT_SYS_IPC */
|
|
COND_SYSCALL(ipc);
|
|
COND_SYSCALL_COMPAT(ipc);
|
|
|
|
/* obsolete: UID16 */
|
|
COND_SYSCALL(chown16);
|
|
COND_SYSCALL(fchown16);
|
|
COND_SYSCALL(getegid16);
|
|
COND_SYSCALL(geteuid16);
|
|
COND_SYSCALL(getgid16);
|
|
COND_SYSCALL(getgroups16);
|
|
COND_SYSCALL(getresgid16);
|
|
COND_SYSCALL(getresuid16);
|
|
COND_SYSCALL(getuid16);
|
|
COND_SYSCALL(lchown16);
|
|
COND_SYSCALL(setfsgid16);
|
|
COND_SYSCALL(setfsuid16);
|
|
COND_SYSCALL(setgid16);
|
|
COND_SYSCALL(setgroups16);
|
|
COND_SYSCALL(setregid16);
|
|
COND_SYSCALL(setresgid16);
|
|
COND_SYSCALL(setresuid16);
|
|
COND_SYSCALL(setreuid16);
|
|
COND_SYSCALL(setuid16);
|
|
|
|
/* restartable sequence */
|
|
COND_SYSCALL(rseq);
|