diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-12-19 11:39:50 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-12-19 11:39:50 -0800 |
commit | 1db98bcf56b1126428d59e71b815c310f73e44ab (patch) | |
tree | 086bf1626c161872805a6ba10b1f944646bdb4db | |
parent | 3644e2d2dda78e21edd8f5415b6d7ab03f5f54f3 (diff) | |
parent | 01ab1ede9190b9fafa88b1c97129c034fa9aa437 (diff) | |
download | linux-1db98bcf56b1126428d59e71b815c310f73e44ab.tar.bz2 |
Merge branch 'akpm' (patches from Andrew)
Merge still more updates from Andrew Morton:
"18 patches.
Subsystems affected by this patch series: mm (memcg and cleanups) and
epoll"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
mm/Kconfig: fix spelling mistake "whats" -> "what's"
selftests/filesystems: expand epoll with epoll_pwait2
epoll: wire up syscall epoll_pwait2
epoll: add syscall epoll_pwait2
epoll: convert internal api to timespec64
epoll: eliminate unnecessary lock for zero timeout
epoll: replace gotos with a proper loop
epoll: pull all code between fetch_events and send_event into the loop
epoll: simplify and optimize busy loop logic
epoll: move eavail next to the list_empty_careful check
epoll: pull fatal signal checks into ep_send_events()
epoll: simplify signal handling
epoll: check for events when removing a timed out thread from the wait queue
mm/memcontrol:rewrite mem_cgroup_page_lruvec()
mm, kvm: account kvm_vcpu_mmap to kmemcg
mm/memcg: remove unused definitions
mm/memcg: warning on !memcg after readahead page charged
mm/memcg: bail early from swap accounting if memcg disabled
31 files changed, 331 insertions, 274 deletions
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index ee7b01bb7346..a6617067dbe6 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -480,3 +480,4 @@ 548 common pidfd_getfd sys_pidfd_getfd 549 common faccessat2 sys_faccessat2 550 common process_madvise sys_process_madvise +551 common epoll_pwait2 sys_epoll_pwait2 diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index d056a548358e..20e1170e2e0a 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -454,3 +454,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index b3b2019f8d16..86a9d7b3eabe 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -38,7 +38,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 441 +#define __NR_compat_syscalls 442 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 107f08e03b9f..f4bca2b90218 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -889,6 +889,8 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) __SYSCALL(__NR_faccessat2, sys_faccessat2) #define __NR_process_madvise 440 __SYSCALL(__NR_process_madvise, sys_process_madvise) +#define __NR_epoll_pwait2 441 +__SYSCALL(__NR_epoll_pwait2, sys_epoll_pwait2) /* * Please add new compat syscalls above this comment and update diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index b96ed8b8a508..bfc00f2bd437 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -361,3 +361,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 625fb6d32842..7fe4e45c864c 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -440,3 +440,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index aae729c95cf9..a522adf194ab 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -446,3 +446,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 32817c954435..ad9c3dd0ab1f 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -379,3 +379,4 @@ 438 n32 pidfd_getfd sys_pidfd_getfd 439 n32 faccessat2 sys_faccessat2 440 n32 process_madvise sys_process_madvise +441 n32 epoll_pwait2 sys_epoll_pwait2 diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index 9e4ea3c31b1c..91649690b52f 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -355,3 +355,4 @@ 438 n64 pidfd_getfd sys_pidfd_getfd 439 n64 faccessat2 sys_faccessat2 440 n64 process_madvise sys_process_madvise +441 n64 epoll_pwait2 sys_epoll_pwait2 diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 29f5f28cf5ce..4bad0c40aed6 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -428,3 +428,4 @@ 438 o32 pidfd_getfd sys_pidfd_getfd 439 o32 faccessat2 sys_faccessat2 440 o32 process_madvise sys_process_madvise +441 o32 epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index f375ea528e59..6bcc31966b44 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -438,3 +438,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 1275daec7fec..f744eb5cba88 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -530,3 +530,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 28c168000483..14f6525886a8 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -443,3 +443,4 @@ 438 common pidfd_getfd sys_pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 sys_epoll_pwait2 diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 783738448ff5..9df40ac0ebc0 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -443,3 +443,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 78160260991b..c7da4c3271e6 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -486,3 +486,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 0d0667a9fbd7..874aeacde2dd 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -445,3 +445,4 @@ 438 i386 pidfd_getfd sys_pidfd_getfd 439 i386 faccessat2 sys_faccessat2 440 i386 process_madvise sys_process_madvise +441 i386 epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 379819244b91..78672124d28b 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -362,6 +362,7 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e545a8a613b1..b05aec109242 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9869,7 +9869,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) r = -ENOMEM; - page = alloc_page(GFP_KERNEL | __GFP_ZERO); + page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!page) goto fail_free_lapic; vcpu->arch.pio_data = page_address(page); diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index b070f272995d..46116a28eeed 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -411,3 +411,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 10b81e69db74..a829af074eb5 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -389,19 +389,24 @@ static bool ep_busy_loop_end(void *p, unsigned long start_time) * * we must do our busy polling with irqs enabled */ -static void ep_busy_loop(struct eventpoll *ep, int nonblock) +static bool ep_busy_loop(struct eventpoll *ep, int nonblock) { unsigned int napi_id = READ_ONCE(ep->napi_id); - if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on()) + if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on()) { napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep, false, BUSY_POLL_BUDGET); -} - -static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep) -{ - if (ep->napi_id) + if (ep_events_available(ep)) + return true; + /* + * Busy poll timed out. Drop NAPI ID for now, we can add + * it back in when we have moved a socket with a valid NAPI + * ID onto the ready list. + */ ep->napi_id = 0; + return false; + } + return false; } /* @@ -441,12 +446,9 @@ static inline void ep_set_busy_poll_napi_id(struct epitem *epi) #else -static inline void ep_busy_loop(struct eventpoll *ep, int nonblock) -{ -} - -static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep) +static inline bool ep_busy_loop(struct eventpoll *ep, int nonblock) { + return false; } static inline void ep_set_busy_poll_napi_id(struct epitem *epi) @@ -1625,6 +1627,14 @@ static int ep_send_events(struct eventpoll *ep, poll_table pt; int res = 0; + /* + * Always short-circuit for fatal signals to allow threads to make a + * timely exit without the chance of finding more events available and + * fetching repeatedly. + */ + if (fatal_signal_pending(current)) + return -EINTR; + init_poll_funcptr(&pt, NULL); mutex_lock(&ep->mtx); @@ -1702,15 +1712,25 @@ static int ep_send_events(struct eventpoll *ep, return res; } -static inline struct timespec64 ep_set_mstimeout(long ms) +static struct timespec64 *ep_timeout_to_timespec(struct timespec64 *to, long ms) { - struct timespec64 now, ts = { - .tv_sec = ms / MSEC_PER_SEC, - .tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC), - }; + struct timespec64 now; + + if (ms < 0) + return NULL; + + if (!ms) { + to->tv_sec = 0; + to->tv_nsec = 0; + return to; + } + + to->tv_sec = ms / MSEC_PER_SEC; + to->tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC); ktime_get_ts64(&now); - return timespec64_add_safe(now, ts); + *to = timespec64_add_safe(now, *to); + return to; } /** @@ -1722,8 +1742,8 @@ static inline struct timespec64 ep_set_mstimeout(long ms) * stored. * @maxevents: Size (in terms of number of events) of the caller event buffer. * @timeout: Maximum timeout for the ready events fetch operation, in - * milliseconds. If the @timeout is zero, the function will not block, - * while if the @timeout is less than zero, the function will block + * timespec. If the timeout is zero, the function will not block, + * while if the @timeout ptr is NULL, the function will block * until at least one event has been retrieved (or an error * occurred). * @@ -1731,55 +1751,59 @@ static inline struct timespec64 ep_set_mstimeout(long ms) * error code, in case of error. */ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, - int maxevents, long timeout) + int maxevents, struct timespec64 *timeout) { - int res = 0, eavail, timed_out = 0; + int res, eavail, timed_out = 0; u64 slack = 0; wait_queue_entry_t wait; ktime_t expires, *to = NULL; lockdep_assert_irqs_enabled(); - if (timeout > 0) { - struct timespec64 end_time = ep_set_mstimeout(timeout); - - slack = select_estimate_accuracy(&end_time); + if (timeout && (timeout->tv_sec | timeout->tv_nsec)) { + slack = select_estimate_accuracy(timeout); to = &expires; - *to = timespec64_to_ktime(end_time); - } else if (timeout == 0) { + *to = timespec64_to_ktime(*timeout); + } else if (timeout) { /* * Avoid the unnecessary trip to the wait queue loop, if the - * caller specified a non blocking operation. We still need - * lock because we could race and not see an epi being added - * to the ready list while in irq callback. Thus incorrectly - * returning 0 back to userspace. + * caller specified a non blocking operation. */ timed_out = 1; - - write_lock_irq(&ep->lock); - eavail = ep_events_available(ep); - write_unlock_irq(&ep->lock); - - goto send_events; } -fetch_events: + /* + * This call is racy: We may or may not see events that are being added + * to the ready list under the lock (e.g., in IRQ callbacks). For, cases + * with a non-zero timeout, this thread will check the ready list under + * lock and will added to the wait queue. For, cases with a zero + * timeout, the user by definition should not care and will have to + * recheck again. + */ + eavail = ep_events_available(ep); + + while (1) { + if (eavail) { + /* + * Try to transfer events to user space. In case we get + * 0 events and there's still timeout left over, we go + * trying again in search of more luck. + */ + res = ep_send_events(ep, events, maxevents); + if (res) + return res; + } - if (!ep_events_available(ep)) - ep_busy_loop(ep, timed_out); + if (timed_out) + return 0; - eavail = ep_events_available(ep); - if (eavail) - goto send_events; + eavail = ep_busy_loop(ep, timed_out); + if (eavail) + continue; - /* - * Busy poll timed out. Drop NAPI ID for now, we can add - * it back in when we have moved a socket with a valid NAPI - * ID onto the ready list. - */ - ep_reset_busy_poll_napi_id(ep); + if (signal_pending(current)) + return -EINTR; - do { /* * Internally init_wait() uses autoremove_wake_function(), * thus wait entry is removed from the wait queue on each @@ -1809,55 +1833,38 @@ fetch_events: * important. */ eavail = ep_events_available(ep); - if (!eavail) { - if (signal_pending(current)) - res = -EINTR; - else - __add_wait_queue_exclusive(&ep->wq, &wait); - } - write_unlock_irq(&ep->lock); - - if (eavail || res) - break; - - if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) { - timed_out = 1; - break; - } - - /* We were woken up, thus go and try to harvest some events */ - eavail = 1; - - } while (0); + if (!eavail) + __add_wait_queue_exclusive(&ep->wq, &wait); - __set_current_state(TASK_RUNNING); - - if (!list_empty_careful(&wait.entry)) { - write_lock_irq(&ep->lock); - __remove_wait_queue(&ep->wq, &wait); write_unlock_irq(&ep->lock); - } -send_events: - if (fatal_signal_pending(current)) { + if (!eavail) + timed_out = !schedule_hrtimeout_range(to, slack, + HRTIMER_MODE_ABS); + __set_current_state(TASK_RUNNING); + /* - * Always short-circuit for fatal signals to allow - * threads to make a timely exit without the chance of - * finding more events available and fetching - * repeatedly. + * We were woken up, thus go and try to harvest some events. + * If timed out and still on the wait queue, recheck eavail + * carefully under lock, below. */ - res = -EINTR; - } - /* - * Try to transfer events to user space. In case we get 0 events and - * there's still timeout left over, we go trying again in search of - * more luck. - */ - if (!res && eavail && - !(res = ep_send_events(ep, events, maxevents)) && !timed_out) - goto fetch_events; + eavail = 1; - return res; + if (!list_empty_careful(&wait.entry)) { + write_lock_irq(&ep->lock); + /* + * If the thread timed out and is not on the wait queue, + * it means that the thread was woken up after its + * timeout expired before it could reacquire the lock. + * Thus, when wait.entry is empty, it needs to harvest + * events. + */ + if (timed_out) + eavail = list_empty(&wait.entry); + __remove_wait_queue(&ep->wq, &wait); + write_unlock_irq(&ep->lock); + } + } } /** @@ -2176,7 +2183,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, * part of the user space epoll_wait(2). */ static int do_epoll_wait(int epfd, struct epoll_event __user *events, - int maxevents, int timeout) + int maxevents, struct timespec64 *to) { int error; struct fd f; @@ -2210,7 +2217,7 @@ static int do_epoll_wait(int epfd, struct epoll_event __user *events, ep = f.file->private_data; /* Time to fish for events ... */ - error = ep_poll(ep, events, maxevents, timeout); + error = ep_poll(ep, events, maxevents, to); error_fput: fdput(f); @@ -2220,16 +2227,19 @@ error_fput: SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout) { - return do_epoll_wait(epfd, events, maxevents, timeout); + struct timespec64 to; + + return do_epoll_wait(epfd, events, maxevents, + ep_timeout_to_timespec(&to, timeout)); } /* * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_pwait(2). */ -SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, - int, maxevents, int, timeout, const sigset_t __user *, sigmask, - size_t, sigsetsize) +static int do_epoll_pwait(int epfd, struct epoll_event __user *events, + int maxevents, struct timespec64 *to, + const sigset_t __user *sigmask, size_t sigsetsize) { int error; @@ -2241,18 +2251,47 @@ SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, if (error) return error; - error = do_epoll_wait(epfd, events, maxevents, timeout); + error = do_epoll_wait(epfd, events, maxevents, to); + restore_saved_sigmask_unless(error == -EINTR); return error; } +SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, + int, maxevents, int, timeout, const sigset_t __user *, sigmask, + size_t, sigsetsize) +{ + struct timespec64 to; + + return do_epoll_pwait(epfd, events, maxevents, + ep_timeout_to_timespec(&to, timeout), + sigmask, sigsetsize); +} + +SYSCALL_DEFINE6(epoll_pwait2, int, epfd, struct epoll_event __user *, events, + int, maxevents, const struct __kernel_timespec __user *, timeout, + const sigset_t __user *, sigmask, size_t, sigsetsize) +{ + struct timespec64 ts, *to = NULL; + + if (timeout) { + if (get_timespec64(&ts, timeout)) + return -EFAULT; + to = &ts; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) + return -EINVAL; + } + + return do_epoll_pwait(epfd, events, maxevents, to, + sigmask, sigsetsize); +} + #ifdef CONFIG_COMPAT -COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, - struct epoll_event __user *, events, - int, maxevents, int, timeout, - const compat_sigset_t __user *, sigmask, - compat_size_t, sigsetsize) +static int do_compat_epoll_pwait(int epfd, struct epoll_event __user *events, + int maxevents, struct timespec64 *timeout, + const compat_sigset_t __user *sigmask, + compat_size_t sigsetsize) { long err; @@ -2265,10 +2304,46 @@ COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, return err; err = do_epoll_wait(epfd, events, maxevents, timeout); + restore_saved_sigmask_unless(err == -EINTR); return err; } + +COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, + struct epoll_event __user *, events, + int, maxevents, int, timeout, + const compat_sigset_t __user *, sigmask, + compat_size_t, sigsetsize) +{ + struct timespec64 to; + + return do_compat_epoll_pwait(epfd, events, maxevents, + ep_timeout_to_timespec(&to, timeout), + sigmask, sigsetsize); +} + +COMPAT_SYSCALL_DEFINE6(epoll_pwait2, int, epfd, + struct epoll_event __user *, events, + int, maxevents, + const struct __kernel_timespec __user *, timeout, + const compat_sigset_t __user *, sigmask, + compat_size_t, sigsetsize) +{ + struct timespec64 ts, *to = NULL; + + if (timeout) { + if (get_timespec64(&ts, timeout)) + return -EFAULT; + to = &ts; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) + return -EINVAL; + } + + return do_compat_epoll_pwait(epfd, events, maxevents, to, + sigmask, sigsetsize); +} + #endif static int __init eventpoll_init(void) diff --git a/include/linux/compat.h b/include/linux/compat.h index 400c0941c8af..6e65be753603 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -537,6 +537,12 @@ asmlinkage long compat_sys_epoll_pwait(int epfd, int maxevents, int timeout, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); +asmlinkage long compat_sys_epoll_pwait2(int epfd, + struct epoll_event __user *events, + int maxevents, + const struct __kernel_timespec __user *timeout, + const compat_sigset_t __user *sigmask, + compat_size_t sigsetsize); /* fs/fcntl.c */ asmlinkage long compat_sys_fcntl(unsigned int fd, unsigned int cmd, diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 08ed57e02b73..d827bd7f3bfe 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -620,9 +620,10 @@ mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid) /** * mem_cgroup_lruvec - get the lru list vector for a memcg & node * @memcg: memcg of the wanted lruvec + * @pgdat: pglist_data * * Returns the lru list vector holding pages for a given @memcg & - * @node combination. This can be the node lruvec, if the memory + * @pgdat combination. This can be the node lruvec, if the memory * controller is disabled. */ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, @@ -652,7 +653,21 @@ out: return lruvec; } -struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *); +/** + * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page + * @page: the page + * @pgdat: pgdat of the page + * + * This function relies on page->mem_cgroup being stable. + */ +static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, + struct pglist_data *pgdat) +{ + struct mem_cgroup *memcg = page_memcg(page); + + VM_WARN_ON_ONCE_PAGE(!memcg, page); + return mem_cgroup_lruvec(memcg, pgdat); +} static inline bool lruvec_holds_page_lru_lock(struct page *page, struct lruvec *lruvec) @@ -913,41 +928,6 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, local_irq_restore(flags); } -/** - * mod_memcg_page_state - update page state statistics - * @page: the page - * @idx: page state item to account - * @val: number of pages (positive or negative) - * - * The @page must be locked or the caller must use lock_page_memcg() - * to prevent double accounting when the page is concurrently being - * moved to another memcg: - * - * lock_page(page) or lock_page_memcg(page) - * if (TestClearPageState(page)) - * mod_memcg_page_state(page, state, -1); - * unlock_page(page) or unlock_page_memcg(page) - * - * Kernel pages are an exception to this, since they'll never move. - */ -static inline void __mod_memcg_page_state(struct page *page, - int idx, int val) -{ - struct mem_cgroup *memcg = page_memcg(page); - - if (memcg) - __mod_memcg_state(memcg, idx, val); -} - -static inline void mod_memcg_page_state(struct page *page, - int idx, int val) -{ - struct mem_cgroup *memcg = page_memcg(page); - - if (memcg) - mod_memcg_state(memcg, idx, val); -} - static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { @@ -1395,18 +1375,6 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, { } -static inline void __mod_memcg_page_state(struct page *page, - int idx, - int nr) -{ -} - -static inline void mod_memcg_page_state(struct page *page, - int idx, - int nr) -{ -} - static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { @@ -1479,34 +1447,6 @@ static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) } #endif /* CONFIG_MEMCG */ -/* idx can be of type enum memcg_stat_item or node_stat_item */ -static inline void __inc_memcg_state(struct mem_cgroup *memcg, - int idx) -{ - __mod_memcg_state(memcg, idx, 1); -} - -/* idx can be of type enum memcg_stat_item or node_stat_item */ -static inline void __dec_memcg_state(struct mem_cgroup *memcg, - int idx) -{ - __mod_memcg_state(memcg, idx, -1); -} - -/* idx can be of type enum memcg_stat_item or node_stat_item */ -static inline void __inc_memcg_page_state(struct page *page, - int idx) -{ - __mod_memcg_page_state(page, idx, 1); -} - -/* idx can be of type enum memcg_stat_item or node_stat_item */ -static inline void __dec_memcg_page_state(struct page *page, - int idx) -{ - __mod_memcg_page_state(page, idx, -1); -} - static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx) { __mod_lruvec_kmem_state(p, idx, 1); @@ -1517,34 +1457,6 @@ static inline void __dec_lruvec_kmem_state(void *p, enum node_stat_item idx) __mod_lruvec_kmem_state(p, idx, -1); } -/* idx can be of type enum memcg_stat_item or node_stat_item */ -static inline void inc_memcg_state(struct mem_cgroup *memcg, - int idx) -{ - mod_memcg_state(memcg, idx, 1); -} - -/* idx can be of type enum memcg_stat_item or node_stat_item */ -static inline void dec_memcg_state(struct mem_cgroup *memcg, - int idx) -{ - mod_memcg_state(memcg, idx, -1); -} - -/* idx can be of type enum memcg_stat_item or node_stat_item */ -static inline void inc_memcg_page_state(struct page *page, - int idx) -{ - mod_memcg_page_state(page, idx, 1); -} - -/* idx can be of type enum memcg_stat_item or node_stat_item */ -static inline void dec_memcg_page_state(struct page *page, - int idx) -{ - mod_memcg_page_state(page, idx, -1); -} - static inline struct lruvec *parent_lruvec(struct lruvec *lruvec) { struct mem_cgroup *memcg; @@ -1733,21 +1645,6 @@ static inline void memcg_kmem_uncharge_page(struct page *page, int order) __memcg_kmem_uncharge_page(page, order); } -static inline int memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp, - unsigned int nr_pages) -{ - if (memcg_kmem_enabled()) - return __memcg_kmem_charge(memcg, gfp, nr_pages); - return 0; -} - -static inline void memcg_kmem_uncharge(struct mem_cgroup *memcg, - unsigned int nr_pages) -{ - if (memcg_kmem_enabled()) - __memcg_kmem_uncharge(memcg, nr_pages); -} - /* * A helper for accessing memcg's kmem_id, used for getting * corresponding LRU lists. diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index 2ad72d2c8cc5..5d0767cb424a 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -37,6 +37,18 @@ void dump_mm(const struct mm_struct *mm); BUG(); \ } \ } while (0) +#define VM_WARN_ON_ONCE_PAGE(cond, page) ({ \ + static bool __section(".data.once") __warned; \ + int __ret_warn_once = !!(cond); \ + \ + if (unlikely(__ret_warn_once && !__warned)) { \ + dump_page(page, "VM_WARN_ON_ONCE_PAGE(" __stringify(cond)")");\ + __warned = true; \ + WARN_ON(1); \ + } \ + unlikely(__ret_warn_once); \ +}) + #define VM_WARN_ON(cond) (void)WARN_ON(cond) #define VM_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond) #define VM_WARN_ONCE(cond, format...) (void)WARN_ONCE(cond, format) @@ -48,6 +60,7 @@ void dump_mm(const struct mm_struct *mm); #define VM_BUG_ON_MM(cond, mm) VM_BUG_ON(cond) #define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) +#define VM_WARN_ON_ONCE_PAGE(cond, page) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond) #define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond) #endif diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index df0c3c74609e..f3929aff39cf 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -362,6 +362,11 @@ asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events, int maxevents, int timeout, const sigset_t __user *sigmask, size_t sigsetsize); +asmlinkage long sys_epoll_pwait2(int epfd, struct epoll_event __user *events, + int maxevents, + const struct __kernel_timespec __user *timeout, + const sigset_t __user *sigmask, + size_t sigsetsize); /* fs/fcntl.c */ asmlinkage long sys_dup(unsigned int fildes); diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index fc48c64700eb..728752917785 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -859,9 +859,11 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) __SYSCALL(__NR_faccessat2, sys_faccessat2) #define __NR_process_madvise 440 __SYSCALL(__NR_process_madvise, sys_process_madvise) +#define __NR_epoll_pwait2 441 +__SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2) #undef __NR_syscalls -#define __NR_syscalls 441 +#define __NR_syscalls 442 /* * 32 bit systems traditionally used different diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index f27ac94d5fa7..19aa806890d5 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -68,6 +68,8 @@ 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 */ diff --git a/mm/Kconfig b/mm/Kconfig index 4275c25b5d8a..f730605b8dcf 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -713,7 +713,7 @@ config ZSMALLOC_STAT select DEBUG_FS help This option enables code in the zsmalloc to collect various - statistics about whats happening in zsmalloc and exports that + statistics about what's happening in zsmalloc and exports that information to userspace via debugfs. If unsure, say N. diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e3c7ca7dc174..605f671203ef 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1343,46 +1343,6 @@ void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) #endif /** - * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page - * @page: the page - * @pgdat: pgdat of the page - * - * This function relies on page's memcg being stable - see the - * access rules in commit_charge(). - */ -struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat) -{ - struct mem_cgroup_per_node *mz; - struct mem_cgroup *memcg; - struct lruvec *lruvec; - - if (mem_cgroup_disabled()) { - lruvec = &pgdat->__lruvec; - goto out; - } - - memcg = page_memcg(page); - /* - * Swapcache readahead pages are added to the LRU - and - * possibly migrated - before they are charged. - */ - if (!memcg) - memcg = root_mem_cgroup; - - mz = mem_cgroup_page_nodeinfo(memcg, page); - lruvec = &mz->lruvec; -out: - /* - * Since a node can be onlined after the mem_cgroup was created, - * we have to be prepared to initialize lruvec->zone here; - * and if offlined then reonlined, we need to reinitialize it. - */ - if (unlikely(lruvec->pgdat != pgdat)) - lruvec->pgdat = pgdat; - return lruvec; -} - -/** * lock_page_lruvec - lock and return lruvec for a given page. * @page: the page * @@ -6987,6 +6947,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) return; memcg = page_memcg(oldpage); + VM_WARN_ON_ONCE_PAGE(!memcg, oldpage); if (!memcg) return; @@ -7178,12 +7139,15 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) VM_BUG_ON_PAGE(PageLRU(page), page); VM_BUG_ON_PAGE(page_count(page), page); + if (mem_cgroup_disabled()) + return; + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return; memcg = page_memcg(page); - /* Readahead page, never charged */ + VM_WARN_ON_ONCE_PAGE(!memcg, page); if (!memcg) return; @@ -7242,12 +7206,15 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) struct mem_cgroup *memcg; unsigned short oldid; + if (mem_cgroup_disabled()) + return 0; + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) return 0; memcg = page_memcg(page); - /* Readahead page, never charged */ + VM_WARN_ON_ONCE_PAGE(!memcg, page); if (!memcg) return 0; diff --git a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c index 8f82f99f7748..ad7fabd575f9 100644 --- a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c +++ b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #define _GNU_SOURCE +#include <asm/unistd.h> +#include <linux/time_types.h> #include <poll.h> #include <unistd.h> #include <assert.h> @@ -21,6 +23,19 @@ struct epoll_mtcontext pthread_t waiter; }; +#ifndef __NR_epoll_pwait2 +#define __NR_epoll_pwait2 -1 +#endif + +static inline int sys_epoll_pwait2(int fd, struct epoll_event *events, + int maxevents, + const struct __kernel_timespec *timeout, + const sigset_t *sigset, size_t sigsetsize) +{ + return syscall(__NR_epoll_pwait2, fd, events, maxevents, timeout, + sigset, sigsetsize); +} + static void signal_handler(int signum) { } @@ -3377,4 +3392,61 @@ TEST(epoll61) close(ctx.evfd); } +/* Equivalent to basic test epoll1, but exercising epoll_pwait2. */ +TEST(epoll62) +{ + int efd; + int sfd[2]; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + EXPECT_EQ(sys_epoll_pwait2(efd, &e, 1, NULL, NULL, 0), 1); + EXPECT_EQ(sys_epoll_pwait2(efd, &e, 1, NULL, NULL, 0), 1); + + close(efd); + close(sfd[0]); + close(sfd[1]); +} + +/* Epoll_pwait2 basic timeout test. */ +TEST(epoll63) +{ + const int cfg_delay_ms = 10; + unsigned long long tdiff; + struct __kernel_timespec ts; + int efd; + int sfd[2]; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], &e), 0); + + ts.tv_sec = 0; + ts.tv_nsec = cfg_delay_ms * 1000 * 1000; + + tdiff = msecs(); + EXPECT_EQ(sys_epoll_pwait2(efd, &e, 1, &ts, NULL, 0), 0); + tdiff = msecs() - tdiff; + + EXPECT_GE(tdiff, cfg_delay_ms); + + close(efd); + close(sfd[0]); + close(sfd[1]); +} + TEST_HARNESS_MAIN diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index e2c197fd4f9d..62bd908ecd58 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -111,7 +111,7 @@ int kvm_coalesced_mmio_init(struct kvm *kvm) { struct page *page; - page = alloc_page(GFP_KERNEL | __GFP_ZERO); + page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!page) return -ENOMEM; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2541a17ff1c4..f69357a29688 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3116,7 +3116,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) } BUILD_BUG_ON(sizeof(struct kvm_run) > PAGE_SIZE); - page = alloc_page(GFP_KERNEL | __GFP_ZERO); + page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!page) { r = -ENOMEM; goto vcpu_free; |