diff options
Diffstat (limited to 'fs')
37 files changed, 1112 insertions, 572 deletions
diff --git a/fs/afs/write.c b/fs/afs/write.c index 97bccde3298b..768497f82aee 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -447,6 +447,7 @@ static int afs_store_data(struct address_space *mapping, op->store.last = last; op->store.first_offset = offset; op->store.last_to = to; + op->mtime = vnode->vfs_inode.i_mtime; op->ops = &afs_store_data_operation; try_next_key: @@ -27,7 +27,6 @@ #include <linux/file.h> #include <linux/mm.h> #include <linux/mman.h> -#include <linux/mmu_context.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/timer.h> diff --git a/fs/io-wq.c b/fs/io-wq.c index 4023c9846860..0b65a912b036 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -10,7 +10,6 @@ #include <linux/errno.h> #include <linux/sched/signal.h> #include <linux/mm.h> -#include <linux/mmu_context.h> #include <linux/sched/mm.h> #include <linux/percpu.h> #include <linux/slab.h> @@ -112,6 +111,7 @@ struct io_wq { unsigned long state; free_work_fn *free_work; + io_wq_work_fn *do_work; struct task_struct *manager; struct user_struct *user; @@ -170,8 +170,7 @@ static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker) dropped_lock = true; } __set_current_state(TASK_RUNNING); - set_fs(KERNEL_DS); - unuse_mm(worker->mm); + kthread_unuse_mm(worker->mm); mmput(worker->mm); worker->mm = NULL; } @@ -418,18 +417,15 @@ static struct io_wq_work *io_get_next_work(struct io_wqe *wqe) static void io_wq_switch_mm(struct io_worker *worker, struct io_wq_work *work) { if (worker->mm) { - unuse_mm(worker->mm); + kthread_unuse_mm(worker->mm); mmput(worker->mm); worker->mm = NULL; } - if (!work->mm) { - set_fs(KERNEL_DS); + if (!work->mm) return; - } + if (mmget_not_zero(work->mm)) { - use_mm(work->mm); - if (!worker->mm) - set_fs(USER_DS); + kthread_use_mm(work->mm); worker->mm = work->mm; /* hang on to this mm */ work->mm = NULL; @@ -528,7 +524,7 @@ get_next: hash = io_get_work_hash(work); linked = old_work = work; - linked->func(&linked); + wq->do_work(&linked); linked = (old_work == linked) ? NULL : linked; work = next_hashed; @@ -785,7 +781,7 @@ static void io_run_cancel(struct io_wq_work *work, struct io_wqe *wqe) struct io_wq_work *old_work = work; work->flags |= IO_WQ_WORK_CANCEL; - work->func(&work); + wq->do_work(&work); work = (work == old_work) ? NULL : work; wq->free_work(old_work); } while (work); @@ -1023,7 +1019,7 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) int ret = -ENOMEM, node; struct io_wq *wq; - if (WARN_ON_ONCE(!data->free_work)) + if (WARN_ON_ONCE(!data->free_work || !data->do_work)) return ERR_PTR(-EINVAL); wq = kzalloc(sizeof(*wq), GFP_KERNEL); @@ -1037,6 +1033,7 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) } wq->free_work = data->free_work; + wq->do_work = data->do_work; /* caller must already hold a reference to this */ wq->user = data->user; @@ -1093,7 +1090,7 @@ err: bool io_wq_get(struct io_wq *wq, struct io_wq_data *data) { - if (data->free_work != wq->free_work) + if (data->free_work != wq->free_work || data->do_work != wq->do_work) return false; return refcount_inc_not_zero(&wq->use_refs); diff --git a/fs/io-wq.h b/fs/io-wq.h index 5ba12de7572f..8e138fa88b9f 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -85,7 +85,6 @@ static inline void wq_list_del(struct io_wq_work_list *list, struct io_wq_work { struct io_wq_work_node list; - void (*func)(struct io_wq_work **); struct files_struct *files; struct mm_struct *mm; const struct cred *creds; @@ -94,11 +93,6 @@ struct io_wq_work { pid_t task_pid; }; -#define INIT_IO_WORK(work, _func) \ - do { \ - *(work) = (struct io_wq_work){ .func = _func }; \ - } while (0) \ - static inline struct io_wq_work *wq_next_work(struct io_wq_work *work) { if (!work->list.next) @@ -108,10 +102,12 @@ static inline struct io_wq_work *wq_next_work(struct io_wq_work *work) } typedef void (free_work_fn)(struct io_wq_work *); +typedef void (io_wq_work_fn)(struct io_wq_work **); struct io_wq_data { struct user_struct *user; + io_wq_work_fn *do_work; free_work_fn *free_work; }; diff --git a/fs/io_uring.c b/fs/io_uring.c index 9fb0dc6033ba..155f3d830ddb 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -55,7 +55,6 @@ #include <linux/fdtable.h> #include <linux/mm.h> #include <linux/mman.h> -#include <linux/mmu_context.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/kthread.h> @@ -529,7 +528,6 @@ enum { REQ_F_INFLIGHT_BIT, REQ_F_CUR_POS_BIT, REQ_F_NOWAIT_BIT, - REQ_F_IOPOLL_COMPLETED_BIT, REQ_F_LINK_TIMEOUT_BIT, REQ_F_TIMEOUT_BIT, REQ_F_ISREG_BIT, @@ -541,6 +539,8 @@ enum { REQ_F_POLLED_BIT, REQ_F_BUFFER_SELECTED_BIT, REQ_F_NO_FILE_TABLE_BIT, + REQ_F_QUEUE_TIMEOUT_BIT, + REQ_F_WORK_INITIALIZED_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -572,8 +572,6 @@ enum { REQ_F_CUR_POS = BIT(REQ_F_CUR_POS_BIT), /* must not punt to workers */ REQ_F_NOWAIT = BIT(REQ_F_NOWAIT_BIT), - /* polled IO has completed */ - REQ_F_IOPOLL_COMPLETED = BIT(REQ_F_IOPOLL_COMPLETED_BIT), /* has linked timeout */ REQ_F_LINK_TIMEOUT = BIT(REQ_F_LINK_TIMEOUT_BIT), /* timeout request */ @@ -596,6 +594,10 @@ enum { REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT), /* doesn't need file table for this request */ REQ_F_NO_FILE_TABLE = BIT(REQ_F_NO_FILE_TABLE_BIT), + /* needs to queue linked timeout */ + REQ_F_QUEUE_TIMEOUT = BIT(REQ_F_QUEUE_TIMEOUT_BIT), + /* io_wq_work is initialized */ + REQ_F_WORK_INITIALIZED = BIT(REQ_F_WORK_INITIALIZED_BIT), }; struct async_poll { @@ -634,6 +636,8 @@ struct io_kiocb { struct io_async_ctx *io; int cflags; u8 opcode; + /* polled IO has completed */ + u8 iopoll_completed; u16 buf_index; @@ -698,6 +702,8 @@ struct io_op_def { unsigned needs_mm : 1; /* needs req->file assigned */ unsigned needs_file : 1; + /* don't fail if file grab fails */ + unsigned needs_file_no_error : 1; /* hash wq insertion if file is a regular file */ unsigned hash_reg_file : 1; /* unbound wq insertion if file is a non-regular file */ @@ -804,6 +810,8 @@ static const struct io_op_def io_op_defs[] = { .needs_fs = 1, }, [IORING_OP_CLOSE] = { + .needs_file = 1, + .needs_file_no_error = 1, .file_table = 1, }, [IORING_OP_FILES_UPDATE] = { @@ -904,6 +912,19 @@ EXPORT_SYMBOL(io_uring_get_socket); static void io_file_put_work(struct work_struct *work); +/* + * Note: must call io_req_init_async() for the first time you + * touch any members of io_wq_work. + */ +static inline void io_req_init_async(struct io_kiocb *req) +{ + if (req->flags & REQ_F_WORK_INITIALIZED) + return; + + memset(&req->work, 0, sizeof(req->work)); + req->flags |= REQ_F_WORK_INITIALIZED; +} + static inline bool io_async_submit(struct io_ring_ctx *ctx) { return ctx->flags & IORING_SETUP_SQPOLL; @@ -1030,6 +1051,9 @@ static inline void io_req_work_grab_env(struct io_kiocb *req, static inline void io_req_work_drop_env(struct io_kiocb *req) { + if (!(req->flags & REQ_F_WORK_INITIALIZED)) + return; + if (req->work.mm) { mmdrop(req->work.mm); req->work.mm = NULL; @@ -1576,16 +1600,6 @@ static void io_free_req(struct io_kiocb *req) io_queue_async_work(nxt); } -static void io_link_work_cb(struct io_wq_work **workptr) -{ - struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); - struct io_kiocb *link; - - link = list_first_entry(&req->link_list, struct io_kiocb, link_list); - io_queue_linked_timeout(link); - io_wq_submit_work(workptr); -} - static void io_wq_assign_next(struct io_wq_work **workptr, struct io_kiocb *nxt) { struct io_kiocb *link; @@ -1597,7 +1611,7 @@ static void io_wq_assign_next(struct io_wq_work **workptr, struct io_kiocb *nxt) *workptr = &nxt->work; link = io_prep_linked_timeout(nxt); if (link) - nxt->work.func = io_link_work_cb; + nxt->flags |= REQ_F_QUEUE_TIMEOUT; } /* @@ -1782,7 +1796,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, * If we find a request that requires polling, break out * and complete those lists first, if we have entries there. */ - if (req->flags & REQ_F_IOPOLL_COMPLETED) { + if (READ_ONCE(req->iopoll_completed)) { list_move_tail(&req->list, &done); continue; } @@ -1963,7 +1977,7 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) req_set_fail_links(req); req->result = res; if (res != -EAGAIN) - req->flags |= REQ_F_IOPOLL_COMPLETED; + WRITE_ONCE(req->iopoll_completed, 1); } /* @@ -1996,7 +2010,7 @@ static void io_iopoll_req_issued(struct io_kiocb *req) * For fast devices, IO may have already completed. If it has, add * it to the front so we find it first. */ - if (req->flags & REQ_F_IOPOLL_COMPLETED) + if (READ_ONCE(req->iopoll_completed)) list_add(&req->list, &ctx->poll_list); else list_add_tail(&req->list, &ctx->poll_list); @@ -2064,6 +2078,10 @@ static bool io_file_supports_async(struct file *file, int rw) if (S_ISREG(mode) && file->f_op != &io_uring_fops) return true; + /* any ->read/write should understand O_NONBLOCK */ + if (file->f_flags & O_NONBLOCK) + return true; + if (!(file->f_mode & FMODE_NOWAIT)) return false; @@ -2106,8 +2124,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, kiocb->ki_ioprio = get_current_ioprio(); /* don't allow async punt if RWF_NOWAIT was requested */ - if ((kiocb->ki_flags & IOCB_NOWAIT) || - (req->file->f_flags & O_NONBLOCK)) + if (kiocb->ki_flags & IOCB_NOWAIT) req->flags |= REQ_F_NOWAIT; if (force_nonblock) @@ -2121,6 +2138,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, kiocb->ki_flags |= IOCB_HIPRI; kiocb->ki_complete = io_complete_rw_iopoll; req->result = 0; + req->iopoll_completed = 0; } else { if (kiocb->ki_flags & IOCB_HIPRI) return -EINVAL; @@ -2359,8 +2377,14 @@ static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, bool needs_lock) { - if (req->flags & REQ_F_BUFFER_SELECTED) + if (req->flags & REQ_F_BUFFER_SELECTED) { + struct io_buffer *kbuf; + + kbuf = (struct io_buffer *) (unsigned long) req->rw.addr; + iov[0].iov_base = u64_to_user_ptr(kbuf->addr); + iov[0].iov_len = kbuf->len; return 0; + } if (!req->rw.len) return 0; else if (req->rw.len > 1) @@ -2742,7 +2766,8 @@ copy_iov: if (ret) goto out_free; /* any defer here is final, must blocking retry */ - if (!file_can_poll(req->file)) + if (!(req->flags & REQ_F_NOWAIT) && + !file_can_poll(req->file)) req->flags |= REQ_F_MUST_PUNT; return -EAGAIN; } @@ -2762,6 +2787,8 @@ static int __io_splice_prep(struct io_kiocb *req, if (req->flags & REQ_F_NEED_CLEANUP) return 0; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; sp->file_in = NULL; sp->len = READ_ONCE(sqe->len); @@ -2776,8 +2803,14 @@ static int __io_splice_prep(struct io_kiocb *req, return ret; req->flags |= REQ_F_NEED_CLEANUP; - if (!S_ISREG(file_inode(sp->file_in)->i_mode)) + if (!S_ISREG(file_inode(sp->file_in)->i_mode)) { + /* + * Splice operation will be punted aync, and here need to + * modify io_wq_work.flags, so initialize io_wq_work firstly. + */ + io_req_init_async(req); req->work.flags |= IO_WQ_WORK_UNBOUND; + } return 0; } @@ -2886,23 +2919,15 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static bool io_req_cancelled(struct io_kiocb *req) -{ - if (req->work.flags & IO_WQ_WORK_CANCEL) { - req_set_fail_links(req); - io_cqring_add_event(req, -ECANCELED); - io_put_req(req); - return true; - } - - return false; -} - -static void __io_fsync(struct io_kiocb *req) +static int io_fsync(struct io_kiocb *req, bool force_nonblock) { loff_t end = req->sync.off + req->sync.len; int ret; + /* fsync always requires a blocking context */ + if (force_nonblock) + return -EAGAIN; + ret = vfs_fsync_range(req->file, req->sync.off, end > 0 ? end : LLONG_MAX, req->sync.flags & IORING_FSYNC_DATASYNC); @@ -2910,58 +2935,16 @@ static void __io_fsync(struct io_kiocb *req) req_set_fail_links(req); io_cqring_add_event(req, ret); io_put_req(req); -} - -static void io_fsync_finish(struct io_wq_work **workptr) -{ - struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); - - if (io_req_cancelled(req)) - return; - __io_fsync(req); - io_steal_work(req, workptr); -} - -static int io_fsync(struct io_kiocb *req, bool force_nonblock) -{ - /* fsync always requires a blocking context */ - if (force_nonblock) { - req->work.func = io_fsync_finish; - return -EAGAIN; - } - __io_fsync(req); return 0; } -static void __io_fallocate(struct io_kiocb *req) -{ - int ret; - - current->signal->rlim[RLIMIT_FSIZE].rlim_cur = req->fsize; - ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off, - req->sync.len); - current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; - if (ret < 0) - req_set_fail_links(req); - io_cqring_add_event(req, ret); - io_put_req(req); -} - -static void io_fallocate_finish(struct io_wq_work **workptr) -{ - struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); - - if (io_req_cancelled(req)) - return; - __io_fallocate(req); - io_steal_work(req, workptr); -} - static int io_fallocate_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (sqe->ioprio || sqe->buf_index || sqe->rw_flags) return -EINVAL; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; req->sync.off = READ_ONCE(sqe->off); req->sync.len = READ_ONCE(sqe->addr); @@ -2972,66 +2955,74 @@ static int io_fallocate_prep(struct io_kiocb *req, static int io_fallocate(struct io_kiocb *req, bool force_nonblock) { + int ret; + /* fallocate always requiring blocking context */ - if (force_nonblock) { - req->work.func = io_fallocate_finish; + if (force_nonblock) return -EAGAIN; - } - __io_fallocate(req); + current->signal->rlim[RLIMIT_FSIZE].rlim_cur = req->fsize; + ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off, + req->sync.len); + current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; + if (ret < 0) + req_set_fail_links(req); + io_cqring_add_event(req, ret); + io_put_req(req); return 0; } -static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { const char __user *fname; int ret; - if (sqe->ioprio || sqe->buf_index) + if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) return -EINVAL; - if (req->flags & REQ_F_FIXED_FILE) + if (unlikely(sqe->ioprio || sqe->buf_index)) + return -EINVAL; + if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; - if (req->flags & REQ_F_NEED_CLEANUP) - return 0; - req->open.dfd = READ_ONCE(sqe->fd); - req->open.how.mode = READ_ONCE(sqe->len); - fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); - req->open.how.flags = READ_ONCE(sqe->open_flags); - if (force_o_largefile()) + /* open.how should be already initialised */ + if (!(req->open.how.flags & O_PATH) && force_o_largefile()) req->open.how.flags |= O_LARGEFILE; + req->open.dfd = READ_ONCE(sqe->fd); + fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); req->open.filename = getname(fname); if (IS_ERR(req->open.filename)) { ret = PTR_ERR(req->open.filename); req->open.filename = NULL; return ret; } - req->open.nofile = rlimit(RLIMIT_NOFILE); req->flags |= REQ_F_NEED_CLEANUP; return 0; } +static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + u64 flags, mode; + + if (req->flags & REQ_F_NEED_CLEANUP) + return 0; + mode = READ_ONCE(sqe->len); + flags = READ_ONCE(sqe->open_flags); + req->open.how = build_open_how(flags, mode); + return __io_openat_prep(req, sqe); +} + static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct open_how __user *how; - const char __user *fname; size_t len; int ret; - if (sqe->ioprio || sqe->buf_index) - return -EINVAL; - if (req->flags & REQ_F_FIXED_FILE) - return -EBADF; if (req->flags & REQ_F_NEED_CLEANUP) return 0; - - req->open.dfd = READ_ONCE(sqe->fd); - fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); how = u64_to_user_ptr(READ_ONCE(sqe->addr2)); len = READ_ONCE(sqe->len); - if (len < OPEN_HOW_SIZE_VER0) return -EINVAL; @@ -3040,19 +3031,7 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (ret) return ret; - if (!(req->open.how.flags & O_PATH) && force_o_largefile()) - req->open.how.flags |= O_LARGEFILE; - - req->open.filename = getname(fname); - if (IS_ERR(req->open.filename)) { - ret = PTR_ERR(req->open.filename); - req->open.filename = NULL; - return ret; - } - - req->open.nofile = rlimit(RLIMIT_NOFILE); - req->flags |= REQ_F_NEED_CLEANUP; - return 0; + return __io_openat_prep(req, sqe); } static int io_openat2(struct io_kiocb *req, bool force_nonblock) @@ -3092,7 +3071,6 @@ err: static int io_openat(struct io_kiocb *req, bool force_nonblock) { - req->open.how = build_open_how(req->open.how.flags, req->open.how.mode); return io_openat2(req, force_nonblock); } @@ -3181,7 +3159,7 @@ static int io_provide_buffers_prep(struct io_kiocb *req, p->addr = READ_ONCE(sqe->addr); p->len = READ_ONCE(sqe->len); - if (!access_ok(u64_to_user_ptr(p->addr), p->len)) + if (!access_ok(u64_to_user_ptr(p->addr), (p->len * p->nbufs))) return -EFAULT; p->bgid = READ_ONCE(sqe->buf_group); @@ -3259,6 +3237,8 @@ static int io_epoll_ctl_prep(struct io_kiocb *req, #if defined(CONFIG_EPOLL) if (sqe->ioprio || sqe->buf_index) return -EINVAL; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; req->epoll.epfd = READ_ONCE(sqe->fd); req->epoll.op = READ_ONCE(sqe->len); @@ -3303,6 +3283,8 @@ static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) #if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU) if (sqe->ioprio || sqe->buf_index || sqe->off) return -EINVAL; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; req->madvise.addr = READ_ONCE(sqe->addr); req->madvise.len = READ_ONCE(sqe->len); @@ -3337,6 +3319,8 @@ static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (sqe->ioprio || sqe->buf_index || sqe->addr) return -EINVAL; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; req->fadvise.offset = READ_ONCE(sqe->off); req->fadvise.len = READ_ONCE(sqe->len); @@ -3370,6 +3354,8 @@ static int io_fadvise(struct io_kiocb *req, bool force_nonblock) static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; if (sqe->ioprio || sqe->buf_index) return -EINVAL; if (req->flags & REQ_F_FIXED_FILE) @@ -3410,10 +3396,14 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { /* * If we queue this for async, it must not be cancellable. That would - * leave the 'file' in an undeterminate state. + * leave the 'file' in an undeterminate state, and here need to modify + * io_wq_work.flags, so initialize io_wq_work firstly. */ + io_req_init_async(req); req->work.flags |= IO_WQ_WORK_NO_CANCEL; + if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) + return -EINVAL; if (sqe->ioprio || sqe->off || sqe->addr || sqe->len || sqe->rw_flags || sqe->buf_index) return -EINVAL; @@ -3421,53 +3411,41 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EBADF; req->close.fd = READ_ONCE(sqe->fd); - return 0; -} - -/* only called when __close_fd_get_file() is done */ -static void __io_close_finish(struct io_kiocb *req) -{ - int ret; - - ret = filp_close(req->close.put_file, req->work.files); - if (ret < 0) - req_set_fail_links(req); - io_cqring_add_event(req, ret); - fput(req->close.put_file); - io_put_req(req); -} - -static void io_close_finish(struct io_wq_work **workptr) -{ - struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); + if ((req->file && req->file->f_op == &io_uring_fops) || + req->close.fd == req->ctx->ring_fd) + return -EBADF; - /* not cancellable, don't do io_req_cancelled() */ - __io_close_finish(req); - io_steal_work(req, workptr); + req->close.put_file = NULL; + return 0; } static int io_close(struct io_kiocb *req, bool force_nonblock) { + struct io_close *close = &req->close; int ret; - req->close.put_file = NULL; - ret = __close_fd_get_file(req->close.fd, &req->close.put_file); - if (ret < 0) - return (ret == -ENOENT) ? -EBADF : ret; + /* might be already done during nonblock submission */ + if (!close->put_file) { + ret = __close_fd_get_file(close->fd, &close->put_file); + if (ret < 0) + return (ret == -ENOENT) ? -EBADF : ret; + } /* if the file has a flush method, be safe and punt to async */ - if (req->close.put_file->f_op->flush && force_nonblock) { + if (close->put_file->f_op->flush && force_nonblock) { /* avoid grabbing files - we don't need the files */ req->flags |= REQ_F_NO_FILE_TABLE | REQ_F_MUST_PUNT; - req->work.func = io_close_finish; return -EAGAIN; } - /* - * No ->flush(), safely close from here and just punt the - * fput() to async context. - */ - __io_close_finish(req); + /* No ->flush() or already async, safely close from here */ + ret = filp_close(close->put_file, req->work.files); + if (ret < 0) + req_set_fail_links(req); + io_cqring_add_event(req, ret); + fput(close->put_file); + close->put_file = NULL; + io_put_req(req); return 0; } @@ -3489,38 +3467,20 @@ static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static void __io_sync_file_range(struct io_kiocb *req) +static int io_sync_file_range(struct io_kiocb *req, bool force_nonblock) { int ret; + /* sync_file_range always requires a blocking context */ + if (force_nonblock) + return -EAGAIN; + ret = sync_file_range(req->file, req->sync.off, req->sync.len, req->sync.flags); if (ret < 0) req_set_fail_links(req); io_cqring_add_event(req, ret); io_put_req(req); -} - - -static void io_sync_file_range_finish(struct io_wq_work **workptr) -{ - struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); - - if (io_req_cancelled(req)) - return; - __io_sync_file_range(req); - io_steal_work(req, workptr); -} - -static int io_sync_file_range(struct io_kiocb *req, bool force_nonblock) -{ - /* sync_file_range always requires a blocking context */ - if (force_nonblock) { - req->work.func = io_sync_file_range_finish; - return -EAGAIN; - } - - __io_sync_file_range(req); return 0; } @@ -3546,6 +3506,9 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) struct io_async_ctx *io = req->io; int ret; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + sr->msg_flags = READ_ONCE(sqe->msg_flags); sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); @@ -3575,9 +3538,6 @@ static int io_sendmsg(struct io_kiocb *req, bool force_nonblock) struct socket *sock; int ret; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - sock = sock_from_file(req->file, &ret); if (sock) { struct io_async_ctx io; @@ -3631,9 +3591,6 @@ static int io_send(struct io_kiocb *req, bool force_nonblock) struct socket *sock; int ret; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - sock = sock_from_file(req->file, &ret); if (sock) { struct io_sr_msg *sr = &req->sr_msg; @@ -3786,6 +3743,9 @@ static int io_recvmsg_prep(struct io_kiocb *req, struct io_async_ctx *io = req->io; int ret; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + sr->msg_flags = READ_ONCE(sqe->msg_flags); sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); @@ -3814,9 +3774,6 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock) struct socket *sock; int ret, cflags = 0; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - sock = sock_from_file(req->file, &ret); if (sock) { struct io_buffer *kbuf; @@ -3878,9 +3835,6 @@ static int io_recv(struct io_kiocb *req, bool force_nonblock) struct socket *sock; int ret, cflags = 0; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - sock = sock_from_file(req->file, &ret); if (sock) { struct io_sr_msg *sr = &req->sr_msg; @@ -3948,49 +3902,30 @@ static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static int __io_accept(struct io_kiocb *req, bool force_nonblock) +static int io_accept(struct io_kiocb *req, bool force_nonblock) { struct io_accept *accept = &req->accept; - unsigned file_flags; + unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0; int ret; - file_flags = force_nonblock ? O_NONBLOCK : 0; + if (req->file->f_flags & O_NONBLOCK) + req->flags |= REQ_F_NOWAIT; + ret = __sys_accept4_file(req->file, file_flags, accept->addr, accept->addr_len, accept->flags, accept->nofile); if (ret == -EAGAIN && force_nonblock) return -EAGAIN; - if (ret == -ERESTARTSYS) - ret = -EINTR; - if (ret < 0) + if (ret < 0) { + if (ret == -ERESTARTSYS) + ret = -EINTR; req_set_fail_links(req); + } io_cqring_add_event(req, ret); io_put_req(req); return 0; } -static void io_accept_finish(struct io_wq_work **workptr) -{ - struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); - - if (io_req_cancelled(req)) - return; - __io_accept(req, false); - io_steal_work(req, workptr); -} - -static int io_accept(struct io_kiocb *req, bool force_nonblock) -{ - int ret; - - ret = __io_accept(req, force_nonblock); - if (ret == -EAGAIN && force_nonblock) { - req->work.func = io_accept_finish; - return -EAGAIN; - } - return 0; -} - static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_connect *conn = &req->connect; @@ -4329,7 +4264,8 @@ static void io_async_task_func(struct callback_head *cb) spin_unlock_irq(&ctx->completion_lock); /* restore ->work in case we need to retry again */ - memcpy(&req->work, &apoll->work, sizeof(req->work)); + if (req->flags & REQ_F_WORK_INITIALIZED) + memcpy(&req->work, &apoll->work, sizeof(req->work)); kfree(apoll); if (!canceled) { @@ -4426,7 +4362,8 @@ static bool io_arm_poll_handler(struct io_kiocb *req) return false; req->flags |= REQ_F_POLLED; - memcpy(&apoll->work, &req->work, sizeof(req->work)); + if (req->flags & REQ_F_WORK_INITIALIZED) + memcpy(&apoll->work, &req->work, sizeof(req->work)); had_io = req->io != NULL; get_task_struct(current); @@ -4451,7 +4388,8 @@ static bool io_arm_poll_handler(struct io_kiocb *req) if (!had_io) io_poll_remove_double(req); spin_unlock_irq(&ctx->completion_lock); - memcpy(&req->work, &apoll->work, sizeof(req->work)); + if (req->flags & REQ_F_WORK_INITIALIZED) + memcpy(&req->work, &apoll->work, sizeof(req->work)); kfree(apoll); return false; } @@ -4496,7 +4434,9 @@ static bool io_poll_remove_one(struct io_kiocb *req) * io_req_work_drop_env below when dropping the * final reference. */ - memcpy(&req->work, &apoll->work, sizeof(req->work)); + if (req->flags & REQ_F_WORK_INITIALIZED) + memcpy(&req->work, &apoll->work, + sizeof(req->work)); kfree(apoll); } } @@ -4945,6 +4885,8 @@ static int io_req_defer_prep(struct io_kiocb *req, if (!sqe) return 0; + io_req_init_async(req); + if (io_op_defs[req->opcode].file_table) { ret = io_grab_files(req); if (unlikely(ret)) @@ -5382,12 +5324,26 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, return 0; } +static void io_arm_async_linked_timeout(struct io_kiocb *req) +{ + struct io_kiocb *link; + + /* link head's timeout is queued in io_queue_async_work() */ + if (!(req->flags & REQ_F_QUEUE_TIMEOUT)) + return; + + link = list_first_entry(&req->link_list, struct io_kiocb, link_list); + io_queue_linked_timeout(link); +} + static void io_wq_submit_work(struct io_wq_work **workptr) { struct io_wq_work *work = *workptr; struct io_kiocb *req = container_of(work, struct io_kiocb, work); int ret = 0; + io_arm_async_linked_timeout(req); + /* if NO_CANCEL is set, we must still run the work */ if ((work->flags & (IO_WQ_WORK_CANCEL|IO_WQ_WORK_NO_CANCEL)) == IO_WQ_WORK_CANCEL) { @@ -5438,19 +5394,20 @@ static int io_file_get(struct io_submit_state *state, struct io_kiocb *req, return -EBADF; fd = array_index_nospec(fd, ctx->nr_user_files); file = io_file_from_index(ctx, fd); - if (!file) - return -EBADF; - req->fixed_file_refs = ctx->file_data->cur_refs; - percpu_ref_get(req->fixed_file_refs); + if (file) { + req->fixed_file_refs = ctx->file_data->cur_refs; + percpu_ref_get(req->fixed_file_refs); + } } else { trace_io_uring_file_get(ctx, fd); file = __io_file_get(state, fd); - if (unlikely(!file)) - return -EBADF; } - *out_file = file; - return 0; + if (file || io_op_defs[req->opcode].needs_file_no_error) { + *out_file = file; + return 0; + } + return -EBADF; } static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req, @@ -5584,7 +5541,8 @@ static void __io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe) again: linked_timeout = io_prep_linked_timeout(req); - if (req->work.creds && req->work.creds != current_cred()) { + if ((req->flags & REQ_F_WORK_INITIALIZED) && req->work.creds && + req->work.creds != current_cred()) { if (old_creds) revert_creds(old_creds); if (old_creds == req->work.creds) @@ -5607,6 +5565,8 @@ again: goto exit; } punt: + io_req_init_async(req); + if (io_op_defs[req->opcode].file_table) { ret = io_grab_files(req); if (ret) @@ -5859,7 +5819,6 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, refcount_set(&req->refs, 2); req->task = NULL; req->result = 0; - INIT_IO_WORK(&req->work, io_wq_submit_work); if (unlikely(req->opcode >= IORING_OP_LAST)) return -EINVAL; @@ -5867,7 +5826,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, if (io_op_defs[req->opcode].needs_mm && !current->mm) { if (unlikely(!mmget_not_zero(ctx->sqo_mm))) return -EFAULT; - use_mm(ctx->sqo_mm); + kthread_use_mm(ctx->sqo_mm); } sqe_flags = READ_ONCE(sqe->flags); @@ -5881,6 +5840,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, id = READ_ONCE(sqe->personality); if (id) { + io_req_init_async(req); req->work.creds = idr_find(&ctx->personality_idr, id); if (unlikely(!req->work.creds)) return -EINVAL; @@ -5981,7 +5941,7 @@ static inline void io_sq_thread_drop_mm(struct io_ring_ctx *ctx) struct mm_struct *mm = current->mm; if (mm) { - unuse_mm(mm); + kthread_unuse_mm(mm); mmput(mm); } } @@ -5990,15 +5950,12 @@ static int io_sq_thread(void *data) { struct io_ring_ctx *ctx = data; const struct cred *old_cred; - mm_segment_t old_fs; DEFINE_WAIT(wait); unsigned long timeout; int ret = 0; complete(&ctx->sq_thread_comp); - old_fs = get_fs(); - set_fs(USER_DS); old_cred = override_creds(ctx->creds); timeout = jiffies + ctx->sq_thread_idle; @@ -6103,7 +6060,6 @@ static int io_sq_thread(void *data) if (current->task_works) task_work_run(); - set_fs(old_fs); io_sq_thread_drop_mm(ctx); revert_creds(old_cred); @@ -6879,6 +6835,7 @@ static int io_init_wq_offload(struct io_ring_ctx *ctx, data.user = ctx->user; data.free_work = io_free_work; + data.do_work = io_wq_submit_work; if (!(p->flags & IORING_SETUP_ATTACH_WQ)) { /* Do QD, or 4 * CPUS, whatever is smallest */ @@ -7160,8 +7117,8 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, ret = 0; if (!pages || nr_pages > got_pages) { - kfree(vmas); - kfree(pages); + kvfree(vmas); + kvfree(pages); pages = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL); vmas = kvmalloc_array(nr_pages, diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index a1ed7620fbac..bcfc288dba3f 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -870,7 +870,7 @@ iomap_unshare_actor(struct inode *inode, loff_t pos, loff_t length, void *data, struct iomap *iomap, struct iomap *srcmap) { long status = 0; - ssize_t written = 0; + loff_t written = 0; /* don't bother with blocks that are not shared to start with */ if (!(iomap->flags & IOMAP_F_SHARED)) diff --git a/fs/locks.c b/fs/locks.c index 6fd1f6e83178..7df0f9fa66f4 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1557,6 +1557,9 @@ static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker) { bool rc; + if (lease->fl_lmops->lm_breaker_owns_lease + && lease->fl_lmops->lm_breaker_owns_lease(lease)) + return false; if ((breaker->fl_flags & FL_LAYOUT) != (lease->fl_flags & FL_LAYOUT)) { rc = false; goto trace; diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index a57e7c72c7f4..1b79dd5cf661 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -446,7 +446,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter) struct inode *inode = mapping->host; struct nfs_direct_req *dreq; struct nfs_lock_context *l_ctx; - ssize_t result = -EINVAL, requested; + ssize_t result, requested; size_t count = iov_iter_count(iter); nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count); @@ -731,6 +731,8 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) nfs_list_remove_request(req); if (request_commit) { kref_get(&req->wb_kref); + memcpy(&req->wb_verf, &hdr->verf.verifier, + sizeof(req->wb_verf)); nfs_mark_request_commit(req, hdr->lseg, &cinfo, hdr->ds_commit_idx); } diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c index 963800037609..e87d500ad95a 100644 --- a/fs/nfs/dns_resolve.c +++ b/fs/nfs/dns_resolve.c @@ -39,7 +39,6 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen, #include <linux/string.h> #include <linux/kmod.h> #include <linux/slab.h> -#include <linux/module.h> #include <linux/socket.h> #include <linux/seq_file.h> #include <linux/inet.h> diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index b9d0921cb4fe..0bf1f835de01 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -833,6 +833,8 @@ int nfs_getattr(const struct path *path, struct kstat *stat, do_update |= cache_validity & NFS_INO_INVALID_ATIME; if (request_mask & (STATX_CTIME|STATX_MTIME)) do_update |= cache_validity & NFS_INO_REVAL_PAGECACHE; + if (request_mask & STATX_BLOCKS) + do_update |= cache_validity & NFS_INO_INVALID_BLOCKS; if (do_update) { /* Update the attribute cache */ if (!(server->flags & NFS_MOUNT_NOAC)) @@ -1764,7 +1766,8 @@ out_noforce: status = nfs_post_op_update_inode_locked(inode, fattr, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME - | NFS_INO_INVALID_MTIME); + | NFS_INO_INVALID_MTIME + | NFS_INO_INVALID_BLOCKS); return status; } @@ -1871,7 +1874,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ATIME | NFS_INO_REVAL_FORCED - | NFS_INO_REVAL_PAGECACHE); + | NFS_INO_REVAL_PAGECACHE + | NFS_INO_INVALID_BLOCKS); /* Do atomic weak cache consistency updates */ nfs_wcc_update_inode(inode, fattr); @@ -2033,8 +2037,12 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); } else if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; - else + else { + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_BLOCKS + | NFS_INO_REVAL_FORCED); cache_revalidated = false; + } /* Update attrtimeo value if we're out of the unstable period */ if (attr_changed) { diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index a46d1d5d16d8..2397ceedba8a 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -179,11 +179,11 @@ nfs3_proc_lookup(struct inode *dir, struct dentry *dentry, if (nfs_lookup_is_soft_revalidate(dentry)) task_flags |= RPC_TASK_TIMEOUT; - dprintk("NFS call lookup %pd2\n", dentry); res.dir_attr = nfs_alloc_fattr(); if (res.dir_attr == NULL) return -ENOMEM; + dprintk("NFS call lookup %pd2\n", dentry); nfs_fattr_init(fattr); status = rpc_call_sync(NFS_CLIENT(dir), &msg, task_flags); nfs_refresh_inode(dir, res.dir_attr); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 9056f3dd380e..e32717fd1169 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7909,7 +7909,7 @@ nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata) } static const struct rpc_call_ops nfs4_bind_one_conn_to_session_ops = { - .rpc_call_done = &nfs4_bind_one_conn_to_session_done, + .rpc_call_done = nfs4_bind_one_conn_to_session_done, }; /* diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 7e7a97ae21ed..547cec79899f 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -961,6 +961,97 @@ TRACE_EVENT(nfs_readpage_done, ) ); +TRACE_EVENT(nfs_readpage_short, + TP_PROTO( + const struct rpc_task *task, + const struct nfs_pgio_header *hdr + ), + + TP_ARGS(task, hdr), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(loff_t, offset) + __field(u32, arg_count) + __field(u32, res_count) + __field(bool, eof) + __field(int, status) + ), + + TP_fast_assign( + const struct inode *inode = hdr->inode; + const struct nfs_inode *nfsi = NFS_I(inode); + const struct nfs_fh *fh = hdr->args.fh ? + hdr->args.fh : &nfsi->fh; + + __entry->status = task->tk_status; + __entry->offset = hdr->args.offset; + __entry->arg_count = hdr->args.count; + __entry->res_count = hdr->res.count; + __entry->eof = hdr->res.eof; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(fh); + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%u res=%u status=%d%s", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + (long long)__entry->offset, __entry->arg_count, + __entry->res_count, __entry->status, + __entry->eof ? " eof" : "" + ) +); + +TRACE_EVENT(nfs_pgio_error, + TP_PROTO( + const struct nfs_pgio_header *hdr, + int error, + loff_t pos + ), + + TP_ARGS(hdr, error, pos), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(loff_t, offset) + __field(u32, arg_count) + __field(u32, res_count) + __field(loff_t, pos) + __field(int, status) + ), + + TP_fast_assign( + const struct inode *inode = hdr->inode; + const struct nfs_inode *nfsi = NFS_I(inode); + const struct nfs_fh *fh = hdr->args.fh ? + hdr->args.fh : &nfsi->fh; + + __entry->status = error; + __entry->offset = hdr->args.offset; + __entry->arg_count = hdr->args.count; + __entry->res_count = hdr->res.count; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(fh); + ), + + TP_printk("fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%u res=%u pos=%llu status=%d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, __entry->fhandle, + (long long)__entry->offset, __entry->arg_count, __entry->res_count, + __entry->pos, __entry->status + ) +); + TRACE_DEFINE_ENUM(NFS_UNSTABLE); TRACE_DEFINE_ENUM(NFS_DATA_SYNC); TRACE_DEFINE_ENUM(NFS_FILE_SYNC); @@ -1312,7 +1403,12 @@ TRACE_EVENT(nfs_xdr_status, __field(unsigned int, task_id) __field(unsigned int, client_id) __field(u32, xid) + __field(int, version) __field(unsigned long, error) + __string(program, + xdr->rqst->rq_task->tk_client->cl_program->name) + __string(procedure, + xdr->rqst->rq_task->tk_msg.rpc_proc->p_name) ), TP_fast_assign( @@ -1322,13 +1418,19 @@ TRACE_EVENT(nfs_xdr_status, __entry->task_id = task->tk_pid; __entry->client_id = task->tk_client->cl_clid; __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->version = task->tk_client->cl_vers; __entry->error = error; + __assign_str(program, + task->tk_client->cl_program->name) + __assign_str(procedure, task->tk_msg.rpc_proc->p_name) ), TP_printk( - "task:%u@%d xid=0x%08x error=%ld (%s)", + "task:%u@%d xid=0x%08x %sv%d %s error=%ld (%s)", __entry->task_id, __entry->client_id, __entry->xid, - -__entry->error, nfs_show_status(__entry->error) + __get_str(program), __entry->version, + __get_str(procedure), -__entry->error, + nfs_show_status(__entry->error) ) ); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 6ca421cbe19c..6ea4cac41e46 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -24,6 +24,7 @@ #include "internal.h" #include "pnfs.h" +#include "nfstrace.h" #define NFSDBG_FACILITY NFSDBG_PAGECACHE @@ -64,6 +65,7 @@ void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos) { unsigned int new = pos - hdr->io_start; + trace_nfs_pgio_error(hdr, error, pos); if (hdr->good_bytes > new) { hdr->good_bytes = new; clear_bit(NFS_IOHDR_EOF, &hdr->flags); diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 13b22e898116..eb854f1f86e2 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -264,6 +264,8 @@ static void nfs_readpage_retry(struct rpc_task *task, /* This is a short read! */ nfs_inc_stats(hdr->inode, NFSIOS_SHORTREAD); + trace_nfs_readpage_short(task, hdr); + /* Has the server at least made some progress? */ if (resp->count == 0) { nfs_set_pgio_error(hdr, -EIO, argp->offset); diff --git a/fs/nfs/sysfs.h b/fs/nfs/sysfs.h index f1b27411dcc0..ebcbdc40483b 100644 --- a/fs/nfs/sysfs.h +++ b/fs/nfs/sysfs.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2019 Hammerspace Inc */ diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h index 10ec5ecdf117..65c331f75e9c 100644 --- a/fs/nfsd/cache.h +++ b/fs/nfsd/cache.h @@ -78,6 +78,8 @@ enum { /* Checksum this amount of the request */ #define RC_CSUMLEN (256U) +int nfsd_drc_slab_create(void); +void nfsd_drc_slab_free(void); int nfsd_reply_cache_init(struct nfsd_net *); void nfsd_reply_cache_shutdown(struct nfsd_net *); int nfsd_cache_lookup(struct svc_rqst *); diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 09aa545825bd..9217cb64bf0e 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -139,7 +139,6 @@ struct nfsd_net { * Duplicate reply cache */ struct nfsd_drc_bucket *drc_hashtbl; - struct kmem_cache *drc_slab; /* max number of entries allowed in the cache */ unsigned int max_drc_entries; diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 5cf91322de0f..7fbe9840a03e 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -38,6 +38,7 @@ #include "nfsd.h" #include "state.h" #include "netns.h" +#include "trace.h" #include "xdr4cb.h" #include "xdr4.h" @@ -904,16 +905,20 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c if (clp->cl_minorversion == 0) { if (!clp->cl_cred.cr_principal && - (clp->cl_cred.cr_flavor >= RPC_AUTH_GSS_KRB5)) + (clp->cl_cred.cr_flavor >= RPC_AUTH_GSS_KRB5)) { + trace_nfsd_cb_setup_err(clp, -EINVAL); return -EINVAL; + } args.client_name = clp->cl_cred.cr_principal; args.prognumber = conn->cb_prog; args.protocol = XPRT_TRANSPORT_TCP; args.authflavor = clp->cl_cred.cr_flavor; clp->cl_cb_ident = conn->cb_ident; } else { - if (!conn->cb_xprt) + if (!conn->cb_xprt) { + trace_nfsd_cb_setup_err(clp, -EINVAL); return -EINVAL; + } clp->cl_cb_conn.cb_xprt = conn->cb_xprt; clp->cl_cb_session = ses; args.bc_xprt = conn->cb_xprt; @@ -925,32 +930,27 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c /* Create RPC client */ client = rpc_create(&args); if (IS_ERR(client)) { - dprintk("NFSD: couldn't create callback client: %ld\n", - PTR_ERR(client)); + trace_nfsd_cb_setup_err(clp, PTR_ERR(client)); return PTR_ERR(client); } cred = get_backchannel_cred(clp, client, ses); if (!cred) { + trace_nfsd_cb_setup_err(clp, -ENOMEM); rpc_shutdown_client(client); return -ENOMEM; } clp->cl_cb_client = client; clp->cl_cb_cred = cred; + trace_nfsd_cb_setup(clp); return 0; } -static void warn_no_callback_path(struct nfs4_client *clp, int reason) -{ - dprintk("NFSD: warning: no callback path to client %.*s: error %d\n", - (int)clp->cl_name.len, clp->cl_name.data, reason); -} - static void nfsd4_mark_cb_down(struct nfs4_client *clp, int reason) { if (test_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags)) return; clp->cl_cb_state = NFSD4_CB_DOWN; - warn_no_callback_path(clp, reason); + trace_nfsd_cb_state(clp); } static void nfsd4_mark_cb_fault(struct nfs4_client *clp, int reason) @@ -958,17 +958,20 @@ static void nfsd4_mark_cb_fault(struct nfs4_client *clp, int reason) if (test_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags)) return; clp->cl_cb_state = NFSD4_CB_FAULT; - warn_no_callback_path(clp, reason); + trace_nfsd_cb_state(clp); } static void nfsd4_cb_probe_done(struct rpc_task *task, void *calldata) { struct nfs4_client *clp = container_of(calldata, struct nfs4_client, cl_cb_null); + trace_nfsd_cb_done(clp, task->tk_status); if (task->tk_status) nfsd4_mark_cb_down(clp, task->tk_status); - else + else { clp->cl_cb_state = NFSD4_CB_UP; + trace_nfsd_cb_state(clp); + } } static void nfsd4_cb_probe_release(void *calldata) @@ -993,6 +996,7 @@ static const struct rpc_call_ops nfsd4_cb_probe_ops = { void nfsd4_probe_callback(struct nfs4_client *clp) { clp->cl_cb_state = NFSD4_CB_UNKNOWN; + trace_nfsd_cb_state(clp); set_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags); nfsd4_run_cb(&clp->cl_cb_null); } @@ -1009,6 +1013,7 @@ void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn) spin_lock(&clp->cl_lock); memcpy(&clp->cl_cb_conn, conn, sizeof(struct nfs4_cb_conn)); spin_unlock(&clp->cl_lock); + trace_nfsd_cb_state(clp); } /* @@ -1165,8 +1170,7 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata) struct nfsd4_callback *cb = calldata; struct nfs4_client *clp = cb->cb_clp; - dprintk("%s: minorversion=%d\n", __func__, - clp->cl_minorversion); + trace_nfsd_cb_done(clp, task->tk_status); if (!nfsd4_cb_sequence_done(task, cb)) return; @@ -1271,6 +1275,7 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) * kill the old client: */ if (clp->cl_cb_client) { + trace_nfsd_cb_shutdown(clp); rpc_shutdown_client(clp->cl_cb_client); clp->cl_cb_client = NULL; put_cred(clp->cl_cb_cred); @@ -1301,6 +1306,8 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) err = setup_callback_client(clp, &conn, ses); if (err) { nfsd4_mark_cb_down(clp, err); + if (c) + svc_xprt_put(c->cn_xprt); return; } } @@ -1314,6 +1321,8 @@ nfsd4_run_cb_work(struct work_struct *work) struct rpc_clnt *clnt; int flags; + trace_nfsd_cb_work(clp, cb->cb_msg.rpc_proc->p_name); + if (cb->cb_need_restart) { cb->cb_need_restart = false; } else { diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 0e75f7fb5fec..a09c35f0f6f0 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1155,7 +1155,7 @@ extern void nfs_sb_deactive(struct super_block *sb); #define NFSD42_INTERSSC_MOUNTOPS "vers=4.2,addr=%s,sec=sys" -/** +/* * Support one copy source server for now. */ static __be32 @@ -1245,10 +1245,9 @@ nfsd4_interssc_disconnect(struct vfsmount *ss_mnt) mntput(ss_mnt); } -/** - * nfsd4_setup_inter_ssc - * +/* * Verify COPY destination stateid. + * * Connect to the source server with NFSv4.1. * Create the source struct file for nfsd_copy_range. * Called with COPY cstate: @@ -2302,6 +2301,8 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) } check_if_stalefh_allowed(args); + rqstp->rq_lease_breaker = (void **)&cstate->clp; + trace_nfsd_compound(rqstp, args->opcnt); while (!status && resp->opcnt < args->opcnt) { op = &args->ops[resp->opcnt++]; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c107caa56525..bb3d2c32664a 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -51,6 +51,7 @@ #include "netns.h" #include "pnfs.h" #include "filecache.h" +#include "trace.h" #define NFSDDBG_FACILITY NFSDDBG_PROC @@ -167,9 +168,6 @@ renew_client_locked(struct nfs4_client *clp) return; } - dprintk("renewing client (clientid %08x/%08x)\n", - clp->cl_clientid.cl_boot, - clp->cl_clientid.cl_id); list_move_tail(&clp->cl_lru, &nn->client_lru); clp->cl_time = ktime_get_boottime_seconds(); } @@ -1922,8 +1920,7 @@ STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn) */ if (clid->cl_boot == (u32)nn->boot_time) return 0; - dprintk("NFSD stale clientid (%08x/%08x) boot_time %08llx\n", - clid->cl_boot, clid->cl_id, nn->boot_time); + trace_nfsd_clid_stale(clid); return 1; } @@ -2406,6 +2403,11 @@ static void states_stop(struct seq_file *s, void *v) spin_unlock(&clp->cl_lock); } +static void nfs4_show_fname(struct seq_file *s, struct nfsd_file *f) +{ + seq_printf(s, "filename: \"%pD2\"", f->nf_file); +} + static void nfs4_show_superblock(struct seq_file *s, struct nfsd_file *f) { struct inode *inode = f->nf_inode; @@ -2422,6 +2424,12 @@ static void nfs4_show_owner(struct seq_file *s, struct nfs4_stateowner *oo) seq_quote_mem(s, oo->so_owner.data, oo->so_owner.len); } +static void nfs4_show_stateid(struct seq_file *s, stateid_t *stid) +{ + seq_printf(s, "0x%.8x", stid->si_generation); + seq_printf(s, "%12phN", &stid->si_opaque); +} + static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st) { struct nfs4_ol_stateid *ols; @@ -2437,7 +2445,9 @@ static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st) nf = st->sc_file; file = find_any_file(nf); - seq_printf(s, "- 0x%16phN: { type: open, ", &st->sc_stateid); + seq_printf(s, "- "); + nfs4_show_stateid(s, &st->sc_stateid); + seq_printf(s, ": { type: open, "); access = bmap_to_share_mode(ols->st_access_bmap); deny = bmap_to_share_mode(ols->st_deny_bmap); @@ -2451,6 +2461,8 @@ static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st) nfs4_show_superblock(s, file); seq_printf(s, ", "); + nfs4_show_fname(s, file); + seq_printf(s, ", "); nfs4_show_owner(s, oo); seq_printf(s, " }\n"); nfsd_file_put(file); @@ -2470,7 +2482,9 @@ static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st) nf = st->sc_file; file = find_any_file(nf); - seq_printf(s, "- 0x%16phN: { type: lock, ", &st->sc_stateid); + seq_printf(s, "- "); + nfs4_show_stateid(s, &st->sc_stateid); + seq_printf(s, ": { type: lock, "); /* * Note: a lock stateid isn't really the same thing as a lock, @@ -2482,6 +2496,8 @@ static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st) nfs4_show_superblock(s, file); /* XXX: open stateid? */ seq_printf(s, ", "); + nfs4_show_fname(s, file); + seq_printf(s, ", "); nfs4_show_owner(s, oo); seq_printf(s, " }\n"); nfsd_file_put(file); @@ -2499,7 +2515,9 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) nf = st->sc_file; file = nf->fi_deleg_file; - seq_printf(s, "- 0x%16phN: { type: deleg, ", &st->sc_stateid); + seq_printf(s, "- "); + nfs4_show_stateid(s, &st->sc_stateid); + seq_printf(s, ": { type: deleg, "); /* Kinda dead code as long as we only support read delegs: */ seq_printf(s, "access: %s, ", @@ -2508,6 +2526,8 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) /* XXX: lease time, whether it's being recalled. */ nfs4_show_superblock(s, file); + seq_printf(s, ", "); + nfs4_show_fname(s, file); seq_printf(s, " }\n"); return 0; @@ -2521,11 +2541,15 @@ static int nfs4_show_layout(struct seq_file *s, struct nfs4_stid *st) ls = container_of(st, struct nfs4_layout_stateid, ls_stid); file = ls->ls_file; - seq_printf(s, "- 0x%16phN: { type: layout, ", &st->sc_stateid); + seq_printf(s, "- "); + nfs4_show_stateid(s, &st->sc_stateid); + seq_printf(s, ": { type: layout, "); /* XXX: What else would be useful? */ nfs4_show_superblock(s, file); + seq_printf(s, ", "); + nfs4_show_fname(s, file); seq_printf(s, " }\n"); return 0; @@ -2845,14 +2869,12 @@ gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, struct svc_r conn->cb_prog = se->se_callback_prog; conn->cb_ident = se->se_callback_ident; memcpy(&conn->cb_saddr, &rqstp->rq_daddr, rqstp->rq_daddrlen); + trace_nfsd_cb_args(clp, conn); return; out_err: conn->cb_addr.ss_family = AF_UNSPEC; conn->cb_addrlen = 0; - dprintk("NFSD: this client (clientid %08x/%08x) " - "will not receive delegations\n", - clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id); - + trace_nfsd_cb_nodelegs(clp); return; } @@ -3458,6 +3480,45 @@ __be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp, return nfs_ok; } +static struct nfsd4_conn *__nfsd4_find_conn(struct svc_xprt *xpt, struct nfsd4_session *s) +{ + struct nfsd4_conn *c; + + list_for_each_entry(c, &s->se_conns, cn_persession) { + if (c->cn_xprt == xpt) { + return c; + } + } + return NULL; +} + +static __be32 nfsd4_match_existing_connection(struct svc_rqst *rqst, + struct nfsd4_session *session, u32 req) +{ + struct nfs4_client *clp = session->se_client; + struct svc_xprt *xpt = rqst->rq_xprt; + struct nfsd4_conn *c; + __be32 status; + + /* Following the last paragraph of RFC 5661 Section 18.34.3: */ + spin_lock(&clp->cl_lock); + c = __nfsd4_find_conn(xpt, session); + if (!c) + status = nfserr_noent; + else if (req == c->cn_flags) + status = nfs_ok; + else if (req == NFS4_CDFC4_FORE_OR_BOTH && + c->cn_flags != NFS4_CDFC4_BACK) + status = nfs_ok; + else if (req == NFS4_CDFC4_BACK_OR_BOTH && + c->cn_flags != NFS4_CDFC4_FORE) + status = nfs_ok; + else + status = nfserr_inval; + spin_unlock(&clp->cl_lock); + return status; +} + __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -3479,6 +3540,9 @@ __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp, status = nfserr_wrong_cred; if (!nfsd4_mach_creds_match(session->se_client, rqstp)) goto out; + status = nfsd4_match_existing_connection(rqstp, session, bcts->dir); + if (status == nfs_ok || status == nfserr_inval) + goto out; status = nfsd4_map_bcts_dir(&bcts->dir); if (status) goto out; @@ -3544,18 +3608,6 @@ out: return status; } -static struct nfsd4_conn *__nfsd4_find_conn(struct svc_xprt *xpt, struct nfsd4_session *s) -{ - struct nfsd4_conn *c; - - list_for_each_entry(c, &s->se_conns, cn_persession) { - if (c->cn_xprt == xpt) { - return c; - } - } - return NULL; -} - static __be32 nfsd4_sequence_check_conn(struct nfsd4_conn *new, struct nfsd4_session *ses) { struct nfs4_client *clp = ses->se_client; @@ -3879,23 +3931,18 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (clp_used_exchangeid(conf)) goto out; if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) { - char addr_str[INET6_ADDRSTRLEN]; - rpc_ntop((struct sockaddr *) &conf->cl_addr, addr_str, - sizeof(addr_str)); - dprintk("NFSD: setclientid: string in use by client " - "at %s\n", addr_str); + trace_nfsd_clid_inuse_err(conf); goto out; } } unconf = find_unconfirmed_client_by_name(&clname, nn); if (unconf) unhash_client_locked(unconf); + /* We need to handle only case 1: probable callback update */ if (conf && same_verf(&conf->cl_verifier, &clverifier)) { - /* case 1: probable callback update */ copy_clid(new, conf); gen_confirm(new, nn); - } else /* case 4 (new client) or cases 2, 3 (client reboot): */ - ; + } new->cl_minorversion = 0; gen_callback(new, setclid, rqstp); add_to_unconfirmed(new); @@ -4076,7 +4123,6 @@ out_free_openowner_slab: out_free_client_slab: kmem_cache_destroy(client_slab); out: - dprintk("nfsd4: out of memory while initializing nfsv4\n"); return -ENOMEM; } @@ -4508,6 +4554,8 @@ nfsd_break_deleg_cb(struct file_lock *fl) struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner; struct nfs4_file *fp = dp->dl_stid.sc_file; + trace_nfsd_deleg_break(&dp->dl_stid.sc_stateid); + /* * We don't want the locks code to timeout the lease for us; * we'll remove it ourself if a delegation isn't returned @@ -4522,6 +4570,19 @@ nfsd_break_deleg_cb(struct file_lock *fl) return ret; } +static bool nfsd_breaker_owns_lease(struct file_lock *fl) +{ + struct nfs4_delegation *dl = fl->fl_owner; + struct svc_rqst *rqst; + struct nfs4_client *clp; + + if (!i_am_nfsd()) + return NULL; + rqst = kthread_data(current); + clp = *(rqst->rq_lease_breaker); + return dl->dl_stid.sc_client == clp; +} + static int nfsd_change_deleg_cb(struct file_lock *onlist, int arg, struct list_head *dispose) @@ -4533,6 +4594,7 @@ nfsd_change_deleg_cb(struct file_lock *onlist, int arg, } static const struct lock_manager_operations nfsd_lease_mng_ops = { + .lm_breaker_owns_lease = nfsd_breaker_owns_lease, .lm_break = nfsd_break_deleg_cb, .lm_change = nfsd_change_deleg_cb, }; @@ -5018,8 +5080,7 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, memcpy(&open->op_delegate_stateid, &dp->dl_stid.sc_stateid, sizeof(dp->dl_stid.sc_stateid)); - dprintk("NFSD: delegation stateid=" STATEID_FMT "\n", - STATEID_VAL(&dp->dl_stid.sc_stateid)); + trace_nfsd_deleg_open(&dp->dl_stid.sc_stateid); open->op_delegate_type = NFS4_OPEN_DELEGATE_READ; nfs4_put_stid(&dp->dl_stid); return; @@ -5136,9 +5197,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf nfs4_open_delegation(current_fh, open, stp); nodeleg: status = nfs_ok; - - dprintk("%s: stateid=" STATEID_FMT "\n", __func__, - STATEID_VAL(&stp->st_stid.sc_stateid)); + trace_nfsd_deleg_none(&stp->st_stid.sc_stateid); out: /* 4.1 client trying to upgrade/downgrade delegation? */ if (open->op_delegate_type == NFS4_OPEN_DELEGATE_NONE && dp && @@ -5192,8 +5251,7 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - dprintk("process_renew(%08x/%08x): starting\n", - clid->cl_boot, clid->cl_id); + trace_nfsd_clid_renew(clid); status = lookup_clientid(clid, cstate, nn, false); if (status) goto out; @@ -5214,6 +5272,7 @@ nfsd4_end_grace(struct nfsd_net *nn) if (nn->grace_ended) return; + trace_nfsd_grace_complete(nn); nn->grace_ended = true; /* * If the server goes down again right now, an NFSv4 @@ -5279,13 +5338,10 @@ nfs4_laundromat(struct nfsd_net *nn) copy_stateid_t *cps_t; int i; - dprintk("NFSD: laundromat service - starting\n"); - if (clients_still_reclaiming(nn)) { new_timeo = 0; goto out; } - dprintk("NFSD: end of grace period\n"); nfsd4_end_grace(nn); INIT_LIST_HEAD(&reaplist); @@ -5307,8 +5363,7 @@ nfs4_laundromat(struct nfsd_net *nn) break; } if (mark_client_expired_locked(clp)) { - dprintk("NFSD: client in use (clientid %08x)\n", - clp->cl_clientid.cl_id); + trace_nfsd_clid_expired(&clp->cl_clientid); continue; } list_add(&clp->cl_lru, &reaplist); @@ -5316,8 +5371,7 @@ nfs4_laundromat(struct nfsd_net *nn) spin_unlock(&nn->client_lock); list_for_each_safe(pos, next, &reaplist) { clp = list_entry(pos, struct nfs4_client, cl_lru); - dprintk("NFSD: purging unused client (clientid %08x)\n", - clp->cl_clientid.cl_id); + trace_nfsd_clid_purged(&clp->cl_clientid); list_del_init(&clp->cl_lru); expire_client(clp); } @@ -5407,7 +5461,6 @@ laundromat_main(struct work_struct *laundry) laundromat_work); t = nfs4_laundromat(nn); - dprintk("NFSD: laundromat_main - sleeping for %lld seconds\n", t); queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ); } @@ -5948,8 +6001,7 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, struct nfs4_stid *s; struct nfs4_ol_stateid *stp = NULL; - dprintk("NFSD: %s: seqid=%d stateid = " STATEID_FMT "\n", __func__, - seqid, STATEID_VAL(stateid)); + trace_nfsd_preprocess(seqid, stateid); *stpp = NULL; status = nfsd4_lookup_stateid(cstate, stateid, typemask, &s, nn); @@ -6018,9 +6070,7 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, oo->oo_flags |= NFS4_OO_CONFIRMED; nfs4_inc_and_copy_stateid(&oc->oc_resp_stateid, &stp->st_stid); mutex_unlock(&stp->st_mutex); - dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n", - __func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid)); - + trace_nfsd_open_confirm(oc->oc_seqid, &stp->st_stid.sc_stateid); nfsd4_client_record_create(oo->oo_owner.so_client); status = nfs_ok; put_stateid: @@ -7072,7 +7122,7 @@ nfs4_client_to_reclaim(struct xdr_netobj name, struct xdr_netobj princhash, unsigned int strhashval; struct nfs4_client_reclaim *crp; - dprintk("NFSD nfs4_client_to_reclaim NAME: %.*s\n", name.len, name.data); + trace_nfsd_clid_reclaim(nn, name.len, name.data); crp = alloc_reclaim(); if (crp) { strhashval = clientstr_hashval(name); @@ -7122,7 +7172,7 @@ nfsd4_find_reclaim_client(struct xdr_netobj name, struct nfsd_net *nn) unsigned int strhashval; struct nfs4_client_reclaim *crp = NULL; - dprintk("NFSD: nfs4_find_reclaim_client for name %.*s\n", name.len, name.data); + trace_nfsd_clid_find(nn, name.len, name.data); strhashval = clientstr_hashval(name); list_for_each_entry(crp, &nn->reclaim_str_hashtbl[strhashval], cr_strhash) { @@ -7686,6 +7736,9 @@ nfsd_recall_delegations(struct list_head *reaplist) list_for_each_entry_safe(dp, next, reaplist, dl_recall_lru) { list_del_init(&dp->dl_recall_lru); clp = dp->dl_stid.sc_client; + + trace_nfsd_deleg_recall(&dp->dl_stid.sc_stateid); + /* * We skipped all entries that had a zero dl_time before, * so we can now reset the dl_time back to 0. If a delegation @@ -7868,6 +7921,7 @@ nfs4_state_start_net(struct net *net) goto skip_grace; printk(KERN_INFO "NFSD: starting %lld-second grace period (net %x)\n", nn->nfsd4_grace, net->ns.inum); + trace_nfsd_grace_start(nn); queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_grace * HZ); return 0; diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 96352ab7bd81..0a0cf1fd77d3 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -20,8 +20,7 @@ #include "nfsd.h" #include "cache.h" - -#define NFSDDBG_FACILITY NFSDDBG_REPCACHE +#include "trace.h" /* * We use this value to determine the number of hash buckets from the max @@ -36,6 +35,8 @@ struct nfsd_drc_bucket { spinlock_t cache_lock; }; +static struct kmem_cache *drc_slab; + static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec); static unsigned long nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc); @@ -95,7 +96,7 @@ nfsd_reply_cache_alloc(struct svc_rqst *rqstp, __wsum csum, { struct svc_cacherep *rp; - rp = kmem_cache_alloc(nn->drc_slab, GFP_KERNEL); + rp = kmem_cache_alloc(drc_slab, GFP_KERNEL); if (rp) { rp->c_state = RC_UNUSED; rp->c_type = RC_NOCACHE; @@ -129,7 +130,7 @@ nfsd_reply_cache_free_locked(struct nfsd_drc_bucket *b, struct svc_cacherep *rp, atomic_dec(&nn->num_drc_entries); nn->drc_mem_usage -= sizeof(*rp); } - kmem_cache_free(nn->drc_slab, rp); + kmem_cache_free(drc_slab, rp); } static void @@ -141,6 +142,18 @@ nfsd_reply_cache_free(struct nfsd_drc_bucket *b, struct svc_cacherep *rp, spin_unlock(&b->cache_lock); } +int nfsd_drc_slab_create(void) +{ + drc_slab = kmem_cache_create("nfsd_drc", + sizeof(struct svc_cacherep), 0, 0, NULL); + return drc_slab ? 0: -ENOMEM; +} + +void nfsd_drc_slab_free(void) +{ + kmem_cache_destroy(drc_slab); +} + int nfsd_reply_cache_init(struct nfsd_net *nn) { unsigned int hashsize; @@ -159,18 +172,13 @@ int nfsd_reply_cache_init(struct nfsd_net *nn) if (status) goto out_nomem; - nn->drc_slab = kmem_cache_create("nfsd_drc", - sizeof(struct svc_cacherep), 0, 0, NULL); - if (!nn->drc_slab) - goto out_shrinker; - nn->drc_hashtbl = kcalloc(hashsize, sizeof(*nn->drc_hashtbl), GFP_KERNEL); if (!nn->drc_hashtbl) { nn->drc_hashtbl = vzalloc(array_size(hashsize, sizeof(*nn->drc_hashtbl))); if (!nn->drc_hashtbl) - goto out_slab; + goto out_shrinker; } for (i = 0; i < hashsize; i++) { @@ -180,8 +188,6 @@ int nfsd_reply_cache_init(struct nfsd_net *nn) nn->drc_hashsize = hashsize; return 0; -out_slab: - kmem_cache_destroy(nn->drc_slab); out_shrinker: unregister_shrinker(&nn->nfsd_reply_cache_shrinker); out_nomem: @@ -209,8 +215,6 @@ void nfsd_reply_cache_shutdown(struct nfsd_net *nn) nn->drc_hashtbl = NULL; nn->drc_hashsize = 0; - kmem_cache_destroy(nn->drc_slab); - nn->drc_slab = NULL; } /* @@ -323,8 +327,10 @@ nfsd_cache_key_cmp(const struct svc_cacherep *key, const struct svc_cacherep *rp, struct nfsd_net *nn) { if (key->c_key.k_xid == rp->c_key.k_xid && - key->c_key.k_csum != rp->c_key.k_csum) + key->c_key.k_csum != rp->c_key.k_csum) { ++nn->payload_misses; + trace_nfsd_drc_mismatch(nn, key, rp); + } return memcmp(&key->c_key, &rp->c_key, sizeof(key->c_key)); } @@ -377,15 +383,22 @@ out: return ret; } -/* +/** + * nfsd_cache_lookup - Find an entry in the duplicate reply cache + * @rqstp: Incoming Call to find + * * Try to find an entry matching the current call in the cache. When none * is found, we try to grab the oldest expired entry off the LRU list. If * a suitable one isn't there, then drop the cache_lock and allocate a * new one, then search again in case one got inserted while this thread * didn't hold the lock. + * + * Return values: + * %RC_DOIT: Process the request normally + * %RC_REPLY: Reply from cache + * %RC_DROPIT: Do not process the request further */ -int -nfsd_cache_lookup(struct svc_rqst *rqstp) +int nfsd_cache_lookup(struct svc_rqst *rqstp) { struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct svc_cacherep *rp, *found; @@ -399,7 +412,7 @@ nfsd_cache_lookup(struct svc_rqst *rqstp) rqstp->rq_cacherep = NULL; if (type == RC_NOCACHE) { nfsdstats.rcnocache++; - return rtn; + goto out; } csum = nfsd_cache_csum(rqstp); @@ -409,10 +422,8 @@ nfsd_cache_lookup(struct svc_rqst *rqstp) * preallocate an entry. */ rp = nfsd_reply_cache_alloc(rqstp, csum, nn); - if (!rp) { - dprintk("nfsd: unable to allocate DRC entry!\n"); - return rtn; - } + if (!rp) + goto out; spin_lock(&b->cache_lock); found = nfsd_cache_insert(b, rp, nn); @@ -431,8 +442,10 @@ nfsd_cache_lookup(struct svc_rqst *rqstp) /* go ahead and prune the cache */ prune_bucket(b, nn); - out: + +out_unlock: spin_unlock(&b->cache_lock); +out: return rtn; found_entry: @@ -442,13 +455,13 @@ found_entry: /* Request being processed */ if (rp->c_state == RC_INPROG) - goto out; + goto out_trace; /* From the hall of fame of impractical attacks: * Is this a user who tries to snoop on the cache? */ rtn = RC_DOIT; if (!test_bit(RQ_SECURE, &rqstp->rq_flags) && rp->c_secure) - goto out; + goto out_trace; /* Compose RPC reply header */ switch (rp->c_type) { @@ -460,21 +473,26 @@ found_entry: break; case RC_REPLBUFF: if (!nfsd_cache_append(rqstp, &rp->c_replvec)) - goto out; /* should not happen */ + goto out_unlock; /* should not happen */ rtn = RC_REPLY; break; default: - printk(KERN_WARNING "nfsd: bad repcache type %d\n", rp->c_type); - nfsd_reply_cache_free_locked(b, rp, nn); + WARN_ONCE(1, "nfsd: bad repcache type %d\n", rp->c_type); } - goto out; +out_trace: + trace_nfsd_drc_found(nn, rqstp, rtn); + goto out_unlock; } -/* - * Update a cache entry. This is called from nfsd_dispatch when - * the procedure has been executed and the complete reply is in - * rqstp->rq_res. +/** + * nfsd_cache_update - Update an entry in the duplicate reply cache. + * @rqstp: svc_rqst with a finished Reply + * @cachetype: which cache to update + * @statp: Reply's status code + * + * This is called from nfsd_dispatch when the procedure has been + * executed and the complete reply is in rqstp->rq_res. * * We're copying around data here rather than swapping buffers because * the toplevel loop requires max-sized buffers, which would be a waste @@ -487,8 +505,7 @@ found_entry: * nfsd failed to encode a reply that otherwise would have been cached. * In this case, nfsd_cache_update is called with statp == NULL. */ -void -nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp) +void nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp) { struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct svc_cacherep *rp = rqstp->rq_cacherep; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 3bb2db947d29..b68e96681522 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -238,7 +238,7 @@ static inline struct net *netns(struct file *file) return file_inode(file)->i_sb->s_fs_info; } -/** +/* * write_unlock_ip - Release all locks used by a client * * Experimental. @@ -277,7 +277,7 @@ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size) return nlmsvc_unlock_all_by_ip(sap); } -/** +/* * write_unlock_fs - Release all locks on a local file system * * Experimental. @@ -327,7 +327,7 @@ static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size) return error; } -/** +/* * write_filehandle - Get a variable-length NFS file handle by path * * On input, the buffer contains a '\n'-terminated C string comprised of @@ -402,7 +402,7 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size) return mesg - buf; } -/** +/* * write_threads - Start NFSD, or report the current number of running threads * * Input: @@ -452,7 +452,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size) return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%d\n", rv); } -/** +/* * write_pool_threads - Set or report the current number of threads per pool * * Input: @@ -661,7 +661,7 @@ out: return tlen + len; } -/** +/* * write_versions - Set or report the available NFS protocol versions * * Input: @@ -811,7 +811,7 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size, return -EINVAL; } -/** +/* * write_ports - Pass a socket file descriptor or transport name to listen on * * Input: @@ -867,7 +867,7 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size) int nfsd_max_blksize; -/** +/* * write_maxblksize - Set or report the current NFS blksize * * Input: @@ -917,7 +917,7 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) nfsd_max_blksize); } -/** +/* * write_maxconn - Set or report the current max number of connections * * Input: @@ -998,7 +998,7 @@ static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size, return rv; } -/** +/* * write_leasetime - Set or report the current NFSv4 lease time * * Input: @@ -1025,7 +1025,7 @@ static ssize_t write_leasetime(struct file *file, char *buf, size_t size) return nfsd4_write_time(file, buf, size, &nn->nfsd4_lease, nn); } -/** +/* * write_gracetime - Set or report current NFSv4 grace period time * * As above, but sets the time of the NFSv4 grace period. @@ -1069,7 +1069,7 @@ static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size, nfs4_recoverydir()); } -/** +/* * write_recoverydir - Set or report the pathname of the recovery directory * * Input: @@ -1101,7 +1101,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size) return rv; } -/** +/* * write_v4_end_grace - release grace period for nfsd's v4.x lock manager * * Input: @@ -1533,6 +1533,9 @@ static int __init init_nfsd(void) goto out_free_slabs; nfsd_fault_inject_init(); /* nfsd fault injection controls */ nfsd_stat_init(); /* Statistics */ + retval = nfsd_drc_slab_create(); + if (retval) + goto out_free_stat; nfsd_lockd_init(); /* lockd->nfsd callbacks */ retval = create_proc_exports_entry(); if (retval) @@ -1546,6 +1549,8 @@ out_free_all: remove_proc_entry("fs/nfs", NULL); out_free_lockd: nfsd_lockd_shutdown(); + nfsd_drc_slab_free(); +out_free_stat: nfsd_stat_shutdown(); nfsd_fault_inject_cleanup(); nfsd4_exit_pnfs(); @@ -1560,6 +1565,7 @@ out_unregister_pernet: static void __exit exit_nfsd(void) { + nfsd_drc_slab_free(); remove_proc_entry("fs/nfs/exports", NULL); remove_proc_entry("fs/nfs", NULL); nfsd_stat_shutdown(); diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 2ab5569126b8..36cdd81b6688 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -88,6 +88,8 @@ int nfsd_pool_stats_release(struct inode *, struct file *); void nfsd_destroy(struct net *net); +bool i_am_nfsd(void); + struct nfsdfs_client { struct kref cl_ref; void (*cl_release)(struct kref *kref); diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index ca9fd348548b..b603dfcdd361 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -601,6 +601,11 @@ static const struct svc_serv_ops nfsd_thread_sv_ops = { .svo_module = THIS_MODULE, }; +bool i_am_nfsd(void) +{ + return kthread_func(current) == nfsd; +} + int nfsd_create_serv(struct net *net) { int error; @@ -1011,6 +1016,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) *statp = rpc_garbage_args; return 1; } + rqstp->rq_lease_breaker = NULL; /* * Give the xdr decoder a chance to change this if it wants * (necessary in the NFSv4.0 compound case) diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 68d3f30ee760..3b408532a5dc 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -64,13 +64,6 @@ typedef struct { refcount_t sc_count; } copy_stateid_t; -#define STATEID_FMT "(%08x/%08x/%08x/%08x)" -#define STATEID_VAL(s) \ - (s)->si_opaque.so_clid.cl_boot, \ - (s)->si_opaque.so_clid.cl_id, \ - (s)->si_opaque.so_id, \ - (s)->si_generation - struct nfsd4_callback { struct nfs4_client *cb_clp; struct rpc_message cb_msg; diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 78c574251c60..1861db1bdc67 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -277,6 +277,7 @@ DECLARE_EVENT_CLASS(nfsd_stateid_class, DEFINE_EVENT(nfsd_stateid_class, nfsd_##name, \ TP_PROTO(stateid_t *stp), \ TP_ARGS(stp)) + DEFINE_STATEID_EVENT(layoutstate_alloc); DEFINE_STATEID_EVENT(layoutstate_unhash); DEFINE_STATEID_EVENT(layoutstate_free); @@ -288,6 +289,138 @@ DEFINE_STATEID_EVENT(layout_recall_done); DEFINE_STATEID_EVENT(layout_recall_fail); DEFINE_STATEID_EVENT(layout_recall_release); +DEFINE_STATEID_EVENT(deleg_open); +DEFINE_STATEID_EVENT(deleg_none); +DEFINE_STATEID_EVENT(deleg_break); +DEFINE_STATEID_EVENT(deleg_recall); + +DECLARE_EVENT_CLASS(nfsd_stateseqid_class, + TP_PROTO(u32 seqid, const stateid_t *stp), + TP_ARGS(seqid, stp), + TP_STRUCT__entry( + __field(u32, seqid) + __field(u32, cl_boot) + __field(u32, cl_id) + __field(u32, si_id) + __field(u32, si_generation) + ), + TP_fast_assign( + __entry->seqid = seqid; + __entry->cl_boot = stp->si_opaque.so_clid.cl_boot; + __entry->cl_id = stp->si_opaque.so_clid.cl_id; + __entry->si_id = stp->si_opaque.so_id; + __entry->si_generation = stp->si_generation; + ), + TP_printk("seqid=%u client %08x:%08x stateid %08x:%08x", + __entry->seqid, __entry->cl_boot, __entry->cl_id, + __entry->si_id, __entry->si_generation) +) + +#define DEFINE_STATESEQID_EVENT(name) \ +DEFINE_EVENT(nfsd_stateseqid_class, nfsd_##name, \ + TP_PROTO(u32 seqid, const stateid_t *stp), \ + TP_ARGS(seqid, stp)) + +DEFINE_STATESEQID_EVENT(preprocess); +DEFINE_STATESEQID_EVENT(open_confirm); + +DECLARE_EVENT_CLASS(nfsd_clientid_class, + TP_PROTO(const clientid_t *clid), + TP_ARGS(clid), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + ), + TP_fast_assign( + __entry->cl_boot = clid->cl_boot; + __entry->cl_id = clid->cl_id; + ), + TP_printk("client %08x:%08x", __entry->cl_boot, __entry->cl_id) +) + +#define DEFINE_CLIENTID_EVENT(name) \ +DEFINE_EVENT(nfsd_clientid_class, nfsd_clid_##name, \ + TP_PROTO(const clientid_t *clid), \ + TP_ARGS(clid)) + +DEFINE_CLIENTID_EVENT(expired); +DEFINE_CLIENTID_EVENT(purged); +DEFINE_CLIENTID_EVENT(renew); +DEFINE_CLIENTID_EVENT(stale); + +DECLARE_EVENT_CLASS(nfsd_net_class, + TP_PROTO(const struct nfsd_net *nn), + TP_ARGS(nn), + TP_STRUCT__entry( + __field(unsigned long long, boot_time) + ), + TP_fast_assign( + __entry->boot_time = nn->boot_time; + ), + TP_printk("boot_time=%16llx", __entry->boot_time) +) + +#define DEFINE_NET_EVENT(name) \ +DEFINE_EVENT(nfsd_net_class, nfsd_##name, \ + TP_PROTO(const struct nfsd_net *nn), \ + TP_ARGS(nn)) + +DEFINE_NET_EVENT(grace_start); +DEFINE_NET_EVENT(grace_complete); + +DECLARE_EVENT_CLASS(nfsd_clid_class, + TP_PROTO(const struct nfsd_net *nn, + unsigned int namelen, + const unsigned char *namedata), + TP_ARGS(nn, namelen, namedata), + TP_STRUCT__entry( + __field(unsigned long long, boot_time) + __field(unsigned int, namelen) + __dynamic_array(unsigned char, name, namelen) + ), + TP_fast_assign( + __entry->boot_time = nn->boot_time; + __entry->namelen = namelen; + memcpy(__get_dynamic_array(name), namedata, namelen); + ), + TP_printk("boot_time=%16llx nfs4_clientid=%.*s", + __entry->boot_time, __entry->namelen, __get_str(name)) +) + +#define DEFINE_CLID_EVENT(name) \ +DEFINE_EVENT(nfsd_clid_class, nfsd_clid_##name, \ + TP_PROTO(const struct nfsd_net *nn, \ + unsigned int namelen, \ + const unsigned char *namedata), \ + TP_ARGS(nn, namelen, namedata)) + +DEFINE_CLID_EVENT(find); +DEFINE_CLID_EVENT(reclaim); + +TRACE_EVENT(nfsd_clid_inuse_err, + TP_PROTO(const struct nfs4_client *clp), + TP_ARGS(clp), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + __field(unsigned int, namelen) + __dynamic_array(unsigned char, name, clp->cl_name.len) + ), + TP_fast_assign( + __entry->cl_boot = clp->cl_clientid.cl_boot; + __entry->cl_id = clp->cl_clientid.cl_id; + memcpy(__entry->addr, &clp->cl_addr, + sizeof(struct sockaddr_in6)); + __entry->namelen = clp->cl_name.len; + memcpy(__get_dynamic_array(name), clp->cl_name.data, + clp->cl_name.len); + ), + TP_printk("nfs4_clientid %.*s already in use by %pISpc, client %08x:%08x", + __entry->namelen, __get_str(name), __entry->addr, + __entry->cl_boot, __entry->cl_id) +) + TRACE_DEFINE_ENUM(NFSD_FILE_HASHED); TRACE_DEFINE_ENUM(NFSD_FILE_PENDING); TRACE_DEFINE_ENUM(NFSD_FILE_BREAK_READ); @@ -432,6 +565,218 @@ TRACE_EVENT(nfsd_file_fsnotify_handle_event, __entry->nlink, __entry->mode, __entry->mask) ); +#include "cache.h" + +TRACE_DEFINE_ENUM(RC_DROPIT); +TRACE_DEFINE_ENUM(RC_REPLY); +TRACE_DEFINE_ENUM(RC_DOIT); + +#define show_drc_retval(x) \ + __print_symbolic(x, \ + { RC_DROPIT, "DROPIT" }, \ + { RC_REPLY, "REPLY" }, \ + { RC_DOIT, "DOIT" }) + +TRACE_EVENT(nfsd_drc_found, + TP_PROTO( + const struct nfsd_net *nn, + const struct svc_rqst *rqstp, + int result + ), + TP_ARGS(nn, rqstp, result), + TP_STRUCT__entry( + __field(unsigned long long, boot_time) + __field(unsigned long, result) + __field(u32, xid) + ), + TP_fast_assign( + __entry->boot_time = nn->boot_time; + __entry->result = result; + __entry->xid = be32_to_cpu(rqstp->rq_xid); + ), + TP_printk("boot_time=%16llx xid=0x%08x result=%s", + __entry->boot_time, __entry->xid, + show_drc_retval(__entry->result)) + +); + +TRACE_EVENT(nfsd_drc_mismatch, + TP_PROTO( + const struct nfsd_net *nn, + const struct svc_cacherep *key, + const struct svc_cacherep *rp + ), + TP_ARGS(nn, key, rp), + TP_STRUCT__entry( + __field(unsigned long long, boot_time) + __field(u32, xid) + __field(u32, cached) + __field(u32, ingress) + ), + TP_fast_assign( + __entry->boot_time = nn->boot_time; + __entry->xid = be32_to_cpu(key->c_key.k_xid); + __entry->cached = (__force u32)key->c_key.k_csum; + __entry->ingress = (__force u32)rp->c_key.k_csum; + ), + TP_printk("boot_time=%16llx xid=0x%08x cached-csum=0x%08x ingress-csum=0x%08x", + __entry->boot_time, __entry->xid, __entry->cached, + __entry->ingress) +); + +TRACE_EVENT(nfsd_cb_args, + TP_PROTO( + const struct nfs4_client *clp, + const struct nfs4_cb_conn *conn + ), + TP_ARGS(clp, conn), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __field(u32, prog) + __field(u32, ident) + __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + ), + TP_fast_assign( + __entry->cl_boot = clp->cl_clientid.cl_boot; + __entry->cl_id = clp->cl_clientid.cl_id; + __entry->prog = conn->cb_prog; + __entry->ident = conn->cb_ident; + memcpy(__entry->addr, &conn->cb_addr, + sizeof(struct sockaddr_in6)); + ), + TP_printk("client %08x:%08x callback addr=%pISpc prog=%u ident=%u", + __entry->cl_boot, __entry->cl_id, + __entry->addr, __entry->prog, __entry->ident) +); + +TRACE_EVENT(nfsd_cb_nodelegs, + TP_PROTO(const struct nfs4_client *clp), + TP_ARGS(clp), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + ), + TP_fast_assign( + __entry->cl_boot = clp->cl_clientid.cl_boot; + __entry->cl_id = clp->cl_clientid.cl_id; + ), + TP_printk("client %08x:%08x", __entry->cl_boot, __entry->cl_id) +) + +TRACE_DEFINE_ENUM(NFSD4_CB_UP); +TRACE_DEFINE_ENUM(NFSD4_CB_UNKNOWN); +TRACE_DEFINE_ENUM(NFSD4_CB_DOWN); +TRACE_DEFINE_ENUM(NFSD4_CB_FAULT); + +#define show_cb_state(val) \ + __print_symbolic(val, \ + { NFSD4_CB_UP, "UP" }, \ + { NFSD4_CB_UNKNOWN, "UNKNOWN" }, \ + { NFSD4_CB_DOWN, "DOWN" }, \ + { NFSD4_CB_FAULT, "FAULT"}) + +DECLARE_EVENT_CLASS(nfsd_cb_class, + TP_PROTO(const struct nfs4_client *clp), + TP_ARGS(clp), + TP_STRUCT__entry( + __field(unsigned long, state) + __field(u32, cl_boot) + __field(u32, cl_id) + __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + ), + TP_fast_assign( + __entry->state = clp->cl_cb_state; + __entry->cl_boot = clp->cl_clientid.cl_boot; + __entry->cl_id = clp->cl_clientid.cl_id; + memcpy(__entry->addr, &clp->cl_cb_conn.cb_addr, + sizeof(struct sockaddr_in6)); + ), + TP_printk("addr=%pISpc client %08x:%08x state=%s", + __entry->addr, __entry->cl_boot, __entry->cl_id, + show_cb_state(__entry->state)) +); + +#define DEFINE_NFSD_CB_EVENT(name) \ +DEFINE_EVENT(nfsd_cb_class, nfsd_cb_##name, \ + TP_PROTO(const struct nfs4_client *clp), \ + TP_ARGS(clp)) + +DEFINE_NFSD_CB_EVENT(setup); +DEFINE_NFSD_CB_EVENT(state); +DEFINE_NFSD_CB_EVENT(shutdown); + +TRACE_EVENT(nfsd_cb_setup_err, + TP_PROTO( + const struct nfs4_client *clp, + long error + ), + TP_ARGS(clp, error), + TP_STRUCT__entry( + __field(long, error) + __field(u32, cl_boot) + __field(u32, cl_id) + __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + ), + TP_fast_assign( + __entry->error = error; + __entry->cl_boot = clp->cl_clientid.cl_boot; + __entry->cl_id = clp->cl_clientid.cl_id; + memcpy(__entry->addr, &clp->cl_cb_conn.cb_addr, + sizeof(struct sockaddr_in6)); + ), + TP_printk("addr=%pISpc client %08x:%08x error=%ld", + __entry->addr, __entry->cl_boot, __entry->cl_id, __entry->error) +); + +TRACE_EVENT(nfsd_cb_work, + TP_PROTO( + const struct nfs4_client *clp, + const char *procedure + ), + TP_ARGS(clp, procedure), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __string(procedure, procedure) + __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + ), + TP_fast_assign( + __entry->cl_boot = clp->cl_clientid.cl_boot; + __entry->cl_id = clp->cl_clientid.cl_id; + __assign_str(procedure, procedure) + memcpy(__entry->addr, &clp->cl_cb_conn.cb_addr, + sizeof(struct sockaddr_in6)); + ), + TP_printk("addr=%pISpc client %08x:%08x procedure=%s", + __entry->addr, __entry->cl_boot, __entry->cl_id, + __get_str(procedure)) +); + +TRACE_EVENT(nfsd_cb_done, + TP_PROTO( + const struct nfs4_client *clp, + int status + ), + TP_ARGS(clp, status), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __field(int, status) + __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + ), + TP_fast_assign( + __entry->cl_boot = clp->cl_clientid.cl_boot; + __entry->cl_id = clp->cl_clientid.cl_id; + __entry->status = status; + memcpy(__entry->addr, &clp->cl_cb_conn.cb_addr, + sizeof(struct sockaddr_in6)); + ), + TP_printk("addr=%pISpc client %08x:%08x status=%d", + __entry->addr, __entry->cl_boot, __entry->cl_id, + __entry->status) +); + #endif /* _NFSD_TRACE_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 445eef41bfaf..91b58c897f92 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2780,6 +2780,8 @@ int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root) if (!nilfs->ns_writer) return -ENOMEM; + inode_attach_wb(nilfs->ns_bdev->bd_inode, NULL); + err = nilfs_segctor_start_thread(nilfs->ns_writer); if (err) { kfree(nilfs->ns_writer); diff --git a/fs/ocfs2/Kconfig b/fs/ocfs2/Kconfig index 1177c33df895..aca16624b370 100644 --- a/fs/ocfs2/Kconfig +++ b/fs/ocfs2/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config OCFS2_FS tristate "OCFS2 file system support" - depends on NET && SYSFS && CONFIGFS_FS + depends on INET && SYSFS && CONFIGFS_FS select JBD2 select CRC32 select QUOTA diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index 3a44e461828a..25cabbfe87fc 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -62,7 +62,7 @@ static vm_fault_t __ocfs2_page_mkwrite(struct file *file, last_index = (size - 1) >> PAGE_SHIFT; /* - * There are cases that lead to the page no longer bebongs to the + * There are cases that lead to the page no longer belonging to the * mapping. * 1) pagecache truncates locally due to memory pressure. * 2) pagecache truncates when another is taking EX lock against diff --git a/fs/pipe.c b/fs/pipe.c index c7c4fb5f345f..60dbee457143 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -24,6 +24,7 @@ #include <linux/syscalls.h> #include <linux/fcntl.h> #include <linux/memcontrol.h> +#include <linux/watch_queue.h> #include <linux/uaccess.h> #include <asm/ioctls.h> @@ -259,14 +260,44 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; +#ifdef CONFIG_WATCH_QUEUE + if (pipe->note_loss) { + struct watch_notification n; + + if (total_len < 8) { + if (ret == 0) + ret = -ENOBUFS; + break; + } + + n.type = WATCH_TYPE_META; + n.subtype = WATCH_META_LOSS_NOTIFICATION; + n.info = watch_sizeof(n); + if (copy_to_iter(&n, sizeof(n), to) != sizeof(n)) { + if (ret == 0) + ret = -EFAULT; + break; + } + ret += sizeof(n); + total_len -= sizeof(n); + pipe->note_loss = false; + } +#endif + if (!pipe_empty(head, tail)) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t chars = buf->len; size_t written; int error; - if (chars > total_len) + if (chars > total_len) { + if (buf->flags & PIPE_BUF_FLAG_WHOLE) { + if (ret == 0) + ret = -ENOBUFS; + break; + } chars = total_len; + } error = pipe_buf_confirm(pipe, buf); if (error) { @@ -294,6 +325,10 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) if (!buf->len) { pipe_buf_release(pipe, buf); spin_lock_irq(&pipe->rd_wait.lock); +#ifdef CONFIG_WATCH_QUEUE + if (buf->flags & PIPE_BUF_FLAG_LOSS) + pipe->note_loss = true; +#endif tail++; pipe->tail = tail; spin_unlock_irq(&pipe->rd_wait.lock); @@ -405,6 +440,13 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) goto out; } +#ifdef CONFIG_WATCH_QUEUE + if (pipe->watch_queue) { + ret = -EXDEV; + goto out; + } +#endif + /* * Only wake up if the pipe started out empty, since * otherwise there should be no readers waiting. @@ -574,22 +616,37 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) int count, head, tail, mask; switch (cmd) { - case FIONREAD: - __pipe_lock(pipe); - count = 0; - head = pipe->head; - tail = pipe->tail; - mask = pipe->ring_size - 1; + case FIONREAD: + __pipe_lock(pipe); + count = 0; + head = pipe->head; + tail = pipe->tail; + mask = pipe->ring_size - 1; - while (tail != head) { - count += pipe->bufs[tail & mask].len; - tail++; - } - __pipe_unlock(pipe); + while (tail != head) { + count += pipe->bufs[tail & mask].len; + tail++; + } + __pipe_unlock(pipe); + + return put_user(count, (int __user *)arg); - return put_user(count, (int __user *)arg); - default: - return -ENOIOCTLCMD; +#ifdef CONFIG_WATCH_QUEUE + case IOC_WATCH_QUEUE_SET_SIZE: { + int ret; + __pipe_lock(pipe); + ret = watch_queue_set_size(pipe, arg); + __pipe_unlock(pipe); + return ret; + } + + case IOC_WATCH_QUEUE_SET_FILTER: + return watch_queue_set_filter( + pipe, (struct watch_notification_filter __user *)arg); +#endif + + default: + return -ENOIOCTLCMD; } } @@ -700,27 +757,27 @@ pipe_fasync(int fd, struct file *filp, int on) return retval; } -static unsigned long account_pipe_buffers(struct user_struct *user, - unsigned long old, unsigned long new) +unsigned long account_pipe_buffers(struct user_struct *user, + unsigned long old, unsigned long new) { return atomic_long_add_return(new - old, &user->pipe_bufs); } -static bool too_many_pipe_buffers_soft(unsigned long user_bufs) +bool too_many_pipe_buffers_soft(unsigned long user_bufs) { unsigned long soft_limit = READ_ONCE(pipe_user_pages_soft); return soft_limit && user_bufs > soft_limit; } -static bool too_many_pipe_buffers_hard(unsigned long user_bufs) +bool too_many_pipe_buffers_hard(unsigned long user_bufs) { unsigned long hard_limit = READ_ONCE(pipe_user_pages_hard); return hard_limit && user_bufs > hard_limit; } -static bool is_unprivileged_user(void) +bool pipe_is_unprivileged_user(void) { return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); } @@ -742,12 +799,12 @@ struct pipe_inode_info *alloc_pipe_info(void) user_bufs = account_pipe_buffers(user, 0, pipe_bufs); - if (too_many_pipe_buffers_soft(user_bufs) && is_unprivileged_user()) { + if (too_many_pipe_buffers_soft(user_bufs) && pipe_is_unprivileged_user()) { user_bufs = account_pipe_buffers(user, pipe_bufs, 1); pipe_bufs = 1; } - if (too_many_pipe_buffers_hard(user_bufs) && is_unprivileged_user()) + if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user()) goto out_revert_acct; pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), @@ -759,6 +816,7 @@ struct pipe_inode_info *alloc_pipe_info(void) pipe->r_counter = pipe->w_counter = 1; pipe->max_usage = pipe_bufs; pipe->ring_size = pipe_bufs; + pipe->nr_accounted = pipe_bufs; pipe->user = user; mutex_init(&pipe->mutex); return pipe; @@ -776,7 +834,14 @@ void free_pipe_info(struct pipe_inode_info *pipe) { int i; - (void) account_pipe_buffers(pipe->user, pipe->ring_size, 0); +#ifdef CONFIG_WATCH_QUEUE + if (pipe->watch_queue) { + watch_queue_clear(pipe->watch_queue); + put_watch_queue(pipe->watch_queue); + } +#endif + + (void) account_pipe_buffers(pipe->user, pipe->nr_accounted, 0); free_uid(pipe->user); for (i = 0; i < pipe->ring_size; i++) { struct pipe_buffer *buf = pipe->bufs + i; @@ -852,6 +917,17 @@ int create_pipe_files(struct file **res, int flags) if (!inode) return -ENFILE; + if (flags & O_NOTIFICATION_PIPE) { +#ifdef CONFIG_WATCH_QUEUE + if (watch_queue_init(inode->i_pipe) < 0) { + iput(inode); + return -ENOMEM; + } +#else + return -ENOPKG; +#endif + } + f = alloc_file_pseudo(inode, pipe_mnt, "", O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)), &pipefifo_fops); @@ -882,7 +958,7 @@ static int __do_pipe_flags(int *fd, struct file **files, int flags) int error; int fdw, fdr; - if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT)) + if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT | O_NOTIFICATION_PIPE)) return -EINVAL; error = create_pipe_files(files, flags); @@ -1130,42 +1206,12 @@ unsigned int round_pipe_size(unsigned long size) } /* - * Allocate a new array of pipe buffers and copy the info over. Returns the - * pipe size if successful, or return -ERROR on error. + * Resize the pipe ring to a number of slots. */ -static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) +int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) { struct pipe_buffer *bufs; - unsigned int size, nr_slots, head, tail, mask, n; - unsigned long user_bufs; - long ret = 0; - - size = round_pipe_size(arg); - nr_slots = size >> PAGE_SHIFT; - - if (!nr_slots) - return -EINVAL; - - /* - * If trying to increase the pipe capacity, check that an - * unprivileged user is not trying to exceed various limits - * (soft limit check here, hard limit check just below). - * Decreasing the pipe capacity is always permitted, even - * if the user is currently over a limit. - */ - if (nr_slots > pipe->ring_size && - size > pipe_max_size && !capable(CAP_SYS_RESOURCE)) - return -EPERM; - - user_bufs = account_pipe_buffers(pipe->user, pipe->ring_size, nr_slots); - - if (nr_slots > pipe->ring_size && - (too_many_pipe_buffers_hard(user_bufs) || - too_many_pipe_buffers_soft(user_bufs)) && - is_unprivileged_user()) { - ret = -EPERM; - goto out_revert_acct; - } + unsigned int head, tail, mask, n; /* * We can shrink the pipe, if arg is greater than the ring occupancy. @@ -1177,17 +1223,13 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) head = pipe->head; tail = pipe->tail; n = pipe_occupancy(pipe->head, pipe->tail); - if (nr_slots < n) { - ret = -EBUSY; - goto out_revert_acct; - } + if (nr_slots < n) + return -EBUSY; bufs = kcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); - if (unlikely(!bufs)) { - ret = -ENOMEM; - goto out_revert_acct; - } + if (unlikely(!bufs)) + return -ENOMEM; /* * The pipe array wraps around, so just start the new one at zero @@ -1215,16 +1257,68 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) kfree(pipe->bufs); pipe->bufs = bufs; pipe->ring_size = nr_slots; - pipe->max_usage = nr_slots; + if (pipe->max_usage > nr_slots) + pipe->max_usage = nr_slots; pipe->tail = tail; pipe->head = head; /* This might have made more room for writers */ wake_up_interruptible(&pipe->wr_wait); + return 0; +} + +/* + * Allocate a new array of pipe buffers and copy the info over. Returns the + * pipe size if successful, or return -ERROR on error. + */ +static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) +{ + unsigned long user_bufs; + unsigned int nr_slots, size; + long ret = 0; + +#ifdef CONFIG_WATCH_QUEUE + if (pipe->watch_queue) + return -EBUSY; +#endif + + size = round_pipe_size(arg); + nr_slots = size >> PAGE_SHIFT; + + if (!nr_slots) + return -EINVAL; + + /* + * If trying to increase the pipe capacity, check that an + * unprivileged user is not trying to exceed various limits + * (soft limit check here, hard limit check just below). + * Decreasing the pipe capacity is always permitted, even + * if the user is currently over a limit. + */ + if (nr_slots > pipe->max_usage && + size > pipe_max_size && !capable(CAP_SYS_RESOURCE)) + return -EPERM; + + user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_slots); + + if (nr_slots > pipe->max_usage && + (too_many_pipe_buffers_hard(user_bufs) || + too_many_pipe_buffers_soft(user_bufs)) && + pipe_is_unprivileged_user()) { + ret = -EPERM; + goto out_revert_acct; + } + + ret = pipe_resize_ring(pipe, nr_slots); + if (ret < 0) + goto out_revert_acct; + + pipe->max_usage = nr_slots; + pipe->nr_accounted = nr_slots; return pipe->max_usage * PAGE_SIZE; out_revert_acct: - (void) account_pipe_buffers(pipe->user, nr_slots, pipe->ring_size); + (void) account_pipe_buffers(pipe->user, nr_slots, pipe->nr_accounted); return ret; } @@ -1233,9 +1327,17 @@ out_revert_acct: * location, so checking ->i_pipe is not enough to verify that this is a * pipe. */ -struct pipe_inode_info *get_pipe_info(struct file *file) +struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice) { - return file->f_op == &pipefifo_fops ? file->private_data : NULL; + struct pipe_inode_info *pipe = file->private_data; + + if (file->f_op != &pipefifo_fops || !pipe) + return NULL; +#ifdef CONFIG_WATCH_QUEUE + if (for_splice && pipe->watch_queue) + return NULL; +#endif + return pipe; } long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg) @@ -1243,7 +1345,7 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg) struct pipe_inode_info *pipe; long ret; - pipe = get_pipe_info(file); + pipe = get_pipe_info(file, false); if (!pipe) return -EBADF; diff --git a/fs/proc/inode.c b/fs/proc/inode.c index f40c2532c057..28d6105e908e 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -617,7 +617,7 @@ const struct inode_operations proc_link_inode_operations = { struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) { - struct inode *inode = new_inode_pseudo(sb); + struct inode *inode = new_inode(sb); if (inode) { inode->i_ino = de->low_ino; diff --git a/fs/proc/self.c b/fs/proc/self.c index ca5158fa561c..72cd69bcaf4a 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -43,7 +43,7 @@ int proc_setup_self(struct super_block *s) inode_lock(root_inode); self = d_alloc_name(s->s_root, "self"); if (self) { - struct inode *inode = new_inode_pseudo(s); + struct inode *inode = new_inode(s); if (inode) { inode->i_ino = self_inum; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c index ac284f409568..a553273fbd41 100644 --- a/fs/proc/thread_self.c +++ b/fs/proc/thread_self.c @@ -43,7 +43,7 @@ int proc_setup_thread_self(struct super_block *s) inode_lock(root_inode); thread_self = d_alloc_name(s->s_root, "thread-self"); if (thread_self) { - struct inode *inode = new_inode_pseudo(s); + struct inode *inode = new_inode(s); if (inode) { inode->i_ino = thread_self_inum; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); diff --git a/fs/splice.c b/fs/splice.c index 6b3c9a018a8e..d7c8a7c4db07 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1101,8 +1101,8 @@ long do_splice(struct file *in, loff_t __user *off_in, !(out->f_mode & FMODE_WRITE))) return -EBADF; - ipipe = get_pipe_info(in); - opipe = get_pipe_info(out); + ipipe = get_pipe_info(in, true); + opipe = get_pipe_info(out, true); if (ipipe && opipe) { if (off_in || off_out) @@ -1252,7 +1252,7 @@ static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf, static long vmsplice_to_user(struct file *file, struct iov_iter *iter, unsigned int flags) { - struct pipe_inode_info *pipe = get_pipe_info(file); + struct pipe_inode_info *pipe = get_pipe_info(file, true); struct splice_desc sd = { .total_len = iov_iter_count(iter), .flags = flags, @@ -1287,7 +1287,7 @@ static long vmsplice_to_pipe(struct file *file, struct iov_iter *iter, if (flags & SPLICE_F_GIFT) buf_flag = PIPE_BUF_FLAG_GIFT; - pipe = get_pipe_info(file); + pipe = get_pipe_info(file, true); if (!pipe) return -EBADF; @@ -1733,8 +1733,8 @@ static int link_pipe(struct pipe_inode_info *ipipe, */ long do_tee(struct file *in, struct file *out, size_t len, unsigned int flags) { - struct pipe_inode_info *ipipe = get_pipe_info(in); - struct pipe_inode_info *opipe = get_pipe_info(out); + struct pipe_inode_info *ipipe = get_pipe_info(in, true); + struct pipe_inode_info *opipe = get_pipe_info(out, true); int ret = -EINVAL; if (unlikely(!(in->f_mode & FMODE_READ) || diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 4c91fb25ec66..9aea7d68d8ab 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2634,8 +2634,10 @@ xfs_ifree_cluster( error = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno, mp->m_bsize * igeo->blocks_per_cluster, XBF_UNMAPPED, &bp); - if (error) + if (error) { + xfs_perag_put(pag); return error; + } /* * This buffer may not have been correctly initialised as we diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index a40f88cf3ab7..a190212ca85d 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1236,64 +1236,26 @@ xfs_ioctl_setattr_xflags( return 0; } -/* - * If we are changing DAX flags, we have to ensure the file is clean and any - * cached objects in the address space are invalidated and removed. This - * requires us to lock out other IO and page faults similar to a truncate - * operation. The locks need to be held until the transaction has been committed - * so that the cache invalidation is atomic with respect to the DAX flag - * manipulation. - */ -static int -xfs_ioctl_setattr_dax_invalidate( +static void +xfs_ioctl_setattr_prepare_dax( struct xfs_inode *ip, - struct fsxattr *fa, - int *join_flags) + struct fsxattr *fa) { - struct inode *inode = VFS_I(ip); - struct super_block *sb = inode->i_sb; - int error; - - *join_flags = 0; - - /* - * It is only valid to set the DAX flag on regular files and - * directories on filesystems where the block size is equal to the page - * size. On directories it serves as an inherited hint so we don't - * have to check the device for dax support or flush pagecache. - */ - if (fa->fsx_xflags & FS_XFLAG_DAX) { - struct xfs_buftarg *target = xfs_inode_buftarg(ip); - - if (!bdev_dax_supported(target->bt_bdev, sb->s_blocksize)) - return -EINVAL; - } - - /* If the DAX state is not changing, we have nothing to do here. */ - if ((fa->fsx_xflags & FS_XFLAG_DAX) && IS_DAX(inode)) - return 0; - if (!(fa->fsx_xflags & FS_XFLAG_DAX) && !IS_DAX(inode)) - return 0; + struct xfs_mount *mp = ip->i_mount; + struct inode *inode = VFS_I(ip); if (S_ISDIR(inode->i_mode)) - return 0; - - /* lock, flush and invalidate mapping in preparation for flag change */ - xfs_ilock(ip, XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL); - error = filemap_write_and_wait(inode->i_mapping); - if (error) - goto out_unlock; - error = invalidate_inode_pages2(inode->i_mapping); - if (error) - goto out_unlock; - - *join_flags = XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL; - return 0; + return; -out_unlock: - xfs_iunlock(ip, XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL); - return error; + if ((mp->m_flags & XFS_MOUNT_DAX_ALWAYS) || + (mp->m_flags & XFS_MOUNT_DAX_NEVER)) + return; + if (((fa->fsx_xflags & FS_XFLAG_DAX) && + !(ip->i_d.di_flags2 & XFS_DIFLAG2_DAX)) || + (!(fa->fsx_xflags & FS_XFLAG_DAX) && + (ip->i_d.di_flags2 & XFS_DIFLAG2_DAX))) + d_mark_dontcache(inode); } /* @@ -1301,17 +1263,10 @@ out_unlock: * have permission to do so. On success, return a clean transaction and the * inode locked exclusively ready for further operation specific checks. On * failure, return an error without modifying or locking the inode. - * - * The inode might already be IO locked on call. If this is the case, it is - * indicated in @join_flags and we take full responsibility for ensuring they - * are unlocked from now on. Hence if we have an error here, we still have to - * unlock them. Otherwise, once they are joined to the transaction, they will - * be unlocked on commit/cancel. */ static struct xfs_trans * xfs_ioctl_setattr_get_trans( - struct xfs_inode *ip, - int join_flags) + struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; @@ -1328,8 +1283,7 @@ xfs_ioctl_setattr_get_trans( goto out_unlock; xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | join_flags); - join_flags = 0; + xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); /* * CAP_FOWNER overrides the following restrictions: @@ -1350,8 +1304,6 @@ xfs_ioctl_setattr_get_trans( out_cancel: xfs_trans_cancel(tp); out_unlock: - if (join_flags) - xfs_iunlock(ip, join_flags); return ERR_PTR(error); } @@ -1476,7 +1428,6 @@ xfs_ioctl_setattr( struct xfs_dquot *pdqp = NULL; struct xfs_dquot *olddquot = NULL; int code; - int join_flags = 0; trace_xfs_ioctl_setattr(ip); @@ -1500,18 +1451,9 @@ xfs_ioctl_setattr( return code; } - /* - * Changing DAX config may require inode locking for mapping - * invalidation. These need to be held all the way to transaction commit - * or cancel time, so need to be passed through to - * xfs_ioctl_setattr_get_trans() so it can apply them to the join call - * appropriately. - */ - code = xfs_ioctl_setattr_dax_invalidate(ip, fa, &join_flags); - if (code) - goto error_free_dquots; + xfs_ioctl_setattr_prepare_dax(ip, fa); - tp = xfs_ioctl_setattr_get_trans(ip, join_flags); + tp = xfs_ioctl_setattr_get_trans(ip); if (IS_ERR(tp)) { code = PTR_ERR(tp); goto error_free_dquots; @@ -1639,7 +1581,6 @@ xfs_ioc_setxflags( struct fsxattr fa; struct fsxattr old_fa; unsigned int flags; - int join_flags = 0; int error; if (copy_from_user(&flags, arg, sizeof(flags))) @@ -1656,18 +1597,9 @@ xfs_ioc_setxflags( if (error) return error; - /* - * Changing DAX config may require inode locking for mapping - * invalidation. These need to be held all the way to transaction commit - * or cancel time, so need to be passed through to - * xfs_ioctl_setattr_get_trans() so it can apply them to the join call - * appropriately. - */ - error = xfs_ioctl_setattr_dax_invalidate(ip, &fa, &join_flags); - if (error) - goto out_drop_write; + xfs_ioctl_setattr_prepare_dax(ip, &fa); - tp = xfs_ioctl_setattr_get_trans(ip, join_flags); + tp = xfs_ioctl_setattr_get_trans(ip); if (IS_ERR(tp)) { error = PTR_ERR(tp); goto out_drop_write; |